diff --git a/propositional_logic/ln_alm/checkpoint-100000/config.json b/propositional_logic/ln_alm/checkpoint-100000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff8809f9ee0000962c182321c304c5b09e84f1ba
--- /dev/null
+++ b/propositional_logic/ln_alm/checkpoint-100000/config.json
@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/ln_alm/checkpoint-100000/optimizer.pt b/propositional_logic/ln_alm/checkpoint-100000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..87eadd2a746bcac464caf13af13ad3d0665b7701
--- /dev/null
+++ b/propositional_logic/ln_alm/checkpoint-100000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dacc63c09d9d07e13ec9e4ea8aa7bbf2c551ec834c172702d61414374aaf1d59
+size 694198065
diff --git a/propositional_logic/ln_alm/checkpoint-100000/pytorch_model.bin b/propositional_logic/ln_alm/checkpoint-100000/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ea45f289651c6a19c5113875279faed7fc78683b
--- /dev/null
+++ b/propositional_logic/ln_alm/checkpoint-100000/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d33019ba41adae198befff715674fa10743b9c2adff598ade2f1594a02b1a7a3
+size 359700713
diff --git a/propositional_logic/ln_alm/checkpoint-100000/rng_state.pth b/propositional_logic/ln_alm/checkpoint-100000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1a0052329f405f8d16b98093adef52f7ec5fc386
--- /dev/null
+++ b/propositional_logic/ln_alm/checkpoint-100000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:275268d12ae096293e6c66801629ae22ecc01c39d8a1be7750d5de7ef54cf04f
+size 14503
diff --git a/propositional_logic/ln_alm/checkpoint-100000/scaler.pt b/propositional_logic/ln_alm/checkpoint-100000/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c044f241dc2354e4553b1dceb5a706f22139e028
--- /dev/null
+++ b/propositional_logic/ln_alm/checkpoint-100000/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cadaddb0cdb0eb56ab6fdc9548b07e37223df7c02a52dd312f849241c130451
+size 559
diff --git a/propositional_logic/ln_alm/checkpoint-100000/scheduler.pt b/propositional_logic/ln_alm/checkpoint-100000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..1e8832360461716948976f2e9023e5604c8ee153
--- /dev/null
+++ b/propositional_logic/ln_alm/checkpoint-100000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc5801efc8ad93998c06ee5b26161b05bdeaa5fcd97377dd4122f24bd465d35
+size 623
diff --git a/propositional_logic/ln_alm/checkpoint-100000/trainer_state.json b/propositional_logic/ln_alm/checkpoint-100000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5983b65da530d0f3e342e3804b00fee1dd21b35a
--- /dev/null
+++ b/propositional_logic/ln_alm/checkpoint-100000/trainer_state.json
@@ -0,0 +1,1216 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 100000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.2353,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 0.5742,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 0.5163,
+      "step": 1500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 0.443,
+      "step": 2000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015,
+      "loss": 0.4029,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.3979,
+      "step": 3000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.3979,
+      "step": 3500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.3973,
+      "step": 4000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00027,
+      "loss": 0.3936,
+      "step": 4500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.394,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00033,
+      "loss": 0.3894,
+      "step": 5500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00035999999999999997,
+      "loss": 0.391,
+      "step": 6000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039,
+      "loss": 0.3901,
+      "step": 6500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00041999999999999996,
+      "loss": 0.3881,
+      "step": 7000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00045,
+      "loss": 0.3888,
+      "step": 7500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00047999999999999996,
+      "loss": 0.3862,
+      "step": 8000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0005099999999999999,
+      "loss": 0.3892,
+      "step": 8500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00054,
+      "loss": 0.3855,
+      "step": 9000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00057,
+      "loss": 0.3841,
+      "step": 9500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0006,
+      "loss": 0.385,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0005966666666666667,
+      "loss": 0.3842,
+      "step": 10500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0005933333333333333,
+      "loss": 0.3836,
+      "step": 11000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005899999999999999,
+      "loss": 0.3823,
+      "step": 11500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005866666666666665,
+      "loss": 0.3828,
+      "step": 12000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 0.3822,
+      "step": 12500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00058,
+      "loss": 0.3815,
+      "step": 13000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005766666666666666,
+      "loss": 0.3802,
+      "step": 13500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005733333333333334,
+      "loss": 0.3802,
+      "step": 14000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00057,
+      "loss": 0.3798,
+      "step": 14500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005666666666666666,
+      "loss": 0.3792,
+      "step": 15000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005633333333333333,
+      "loss": 0.3791,
+      "step": 15500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00056,
+      "loss": 0.3789,
+      "step": 16000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005566666666666667,
+      "loss": 0.3788,
+      "step": 16500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005533333333333333,
+      "loss": 0.3789,
+      "step": 17000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005499999999999999,
+      "loss": 0.3785,
+      "step": 17500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005466666666666667,
+      "loss": 0.3788,
+      "step": 18000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005433399999999999,
+      "loss": 0.3784,
+      "step": 18500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0005400066666666666,
+      "loss": 0.3783,
+      "step": 19000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005366733333333333,
+      "loss": 0.3781,
+      "step": 19500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00053334,
+      "loss": 0.3784,
+      "step": 20000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005300133333333333,
+      "loss": 0.3785,
+      "step": 20500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00052668,
+      "loss": 0.378,
+      "step": 21000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0005233466666666667,
+      "loss": 0.3781,
+      "step": 21500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0005200133333333332,
+      "loss": 0.3781,
+      "step": 22000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005166866666666667,
+      "loss": 0.3783,
+      "step": 22500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005133533333333333,
+      "loss": 0.3779,
+      "step": 23000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005100199999999999,
+      "loss": 0.3779,
+      "step": 23500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005066866666666666,
+      "loss": 0.3779,
+      "step": 24000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005033599999999999,
+      "loss": 0.3779,
+      "step": 24500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0005000266666666666,
+      "loss": 0.3781,
+      "step": 25000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0004966933333333332,
+      "loss": 0.3779,
+      "step": 25500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00049336,
+      "loss": 0.378,
+      "step": 26000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0004900333333333333,
+      "loss": 0.3776,
+      "step": 26500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00048669999999999996,
+      "loss": 0.3779,
+      "step": 27000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004833666666666666,
+      "loss": 0.378,
+      "step": 27500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00048003333333333326,
+      "loss": 0.3778,
+      "step": 28000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004767066666666666,
+      "loss": 0.378,
+      "step": 28500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004733733333333333,
+      "loss": 0.3777,
+      "step": 29000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00047003999999999997,
+      "loss": 0.3777,
+      "step": 29500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046670666666666664,
+      "loss": 0.3776,
+      "step": 30000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046337999999999994,
+      "loss": 0.3778,
+      "step": 30500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0004600466666666666,
+      "loss": 0.3778,
+      "step": 31000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0004567133333333333,
+      "loss": 0.3776,
+      "step": 31500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00045337999999999997,
+      "loss": 0.3778,
+      "step": 32000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00045005333333333333,
+      "loss": 0.3777,
+      "step": 32500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00044672,
+      "loss": 0.3777,
+      "step": 33000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00044338666666666663,
+      "loss": 0.3776,
+      "step": 33500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004400533333333333,
+      "loss": 0.3777,
+      "step": 34000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004367266666666666,
+      "loss": 0.3776,
+      "step": 34500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0004333933333333333,
+      "loss": 0.3777,
+      "step": 35000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00043005999999999996,
+      "loss": 0.3775,
+      "step": 35500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042672666666666663,
+      "loss": 0.3776,
+      "step": 36000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042339999999999994,
+      "loss": 0.3776,
+      "step": 36500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0004200666666666666,
+      "loss": 0.3776,
+      "step": 37000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00041673333333333334,
+      "loss": 0.3777,
+      "step": 37500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0004133999999999999,
+      "loss": 0.3777,
+      "step": 38000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0004100733333333333,
+      "loss": 0.3775,
+      "step": 38500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00040673999999999994,
+      "loss": 0.3777,
+      "step": 39000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004034066666666666,
+      "loss": 0.3776,
+      "step": 39500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004000733333333333,
+      "loss": 0.3776,
+      "step": 40000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003967466666666666,
+      "loss": 0.3776,
+      "step": 40500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003934133333333333,
+      "loss": 0.3776,
+      "step": 41000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039007999999999995,
+      "loss": 0.3776,
+      "step": 41500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00038674666666666663,
+      "loss": 0.3775,
+      "step": 42000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00038342,
+      "loss": 0.3776,
+      "step": 42500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00038008666666666666,
+      "loss": 0.3775,
+      "step": 43000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00037675333333333334,
+      "loss": 0.3777,
+      "step": 43500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00037341999999999996,
+      "loss": 0.3776,
+      "step": 44000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003700933333333333,
+      "loss": 0.3775,
+      "step": 44500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00036675999999999994,
+      "loss": 0.3775,
+      "step": 45000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003634266666666666,
+      "loss": 0.3776,
+      "step": 45500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003600933333333333,
+      "loss": 0.3776,
+      "step": 46000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00035676666666666665,
+      "loss": 0.3775,
+      "step": 46500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003534333333333333,
+      "loss": 0.3777,
+      "step": 47000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003501,
+      "loss": 0.3776,
+      "step": 47500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003467666666666667,
+      "loss": 0.3774,
+      "step": 48000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00034344,
+      "loss": 0.3776,
+      "step": 48500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003401133333333333,
+      "loss": 0.3776,
+      "step": 49000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00033677999999999996,
+      "loss": 0.3775,
+      "step": 49500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003334466666666667,
+      "loss": 0.3776,
+      "step": 50000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00033011333333333325,
+      "loss": 0.3776,
+      "step": 50500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00032678666666666667,
+      "loss": 0.3776,
+      "step": 51000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003234533333333333,
+      "loss": 0.3775,
+      "step": 51500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00032011999999999996,
+      "loss": 0.3776,
+      "step": 52000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00031678666666666664,
+      "loss": 0.3776,
+      "step": 52500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003134533333333333,
+      "loss": 0.3776,
+      "step": 53000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003101266666666666,
+      "loss": 0.3775,
+      "step": 53500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003067933333333333,
+      "loss": 0.3777,
+      "step": 54000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00030345999999999997,
+      "loss": 0.3775,
+      "step": 54500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00030012666666666665,
+      "loss": 0.3776,
+      "step": 55000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967933333333333,
+      "loss": 0.3775,
+      "step": 55500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002934666666666666,
+      "loss": 0.3776,
+      "step": 56000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002901333333333333,
+      "loss": 0.3776,
+      "step": 56500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002868,
+      "loss": 0.3774,
+      "step": 57000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00028346666666666665,
+      "loss": 0.3776,
+      "step": 57500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00028013999999999996,
+      "loss": 0.3775,
+      "step": 58000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00027680666666666663,
+      "loss": 0.3777,
+      "step": 58500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002734733333333333,
+      "loss": 0.3775,
+      "step": 59000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00027014,
+      "loss": 0.3775,
+      "step": 59500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026681333333333334,
+      "loss": 0.3776,
+      "step": 60000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026347999999999996,
+      "loss": 0.3775,
+      "step": 60500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00026014666666666664,
+      "loss": 0.3776,
+      "step": 61000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002568133333333333,
+      "loss": 0.3776,
+      "step": 61500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002534866666666667,
+      "loss": 0.3774,
+      "step": 62000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00025015333333333335,
+      "loss": 0.3776,
+      "step": 62500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00024681999999999997,
+      "loss": 0.3776,
+      "step": 63000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00024348666666666665,
+      "loss": 0.3774,
+      "step": 63500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00024015999999999998,
+      "loss": 0.3775,
+      "step": 64000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00023682666666666665,
+      "loss": 0.3775,
+      "step": 64500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002334933333333333,
+      "loss": 0.3775,
+      "step": 65000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00023015999999999998,
+      "loss": 0.3774,
+      "step": 65500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002268333333333333,
+      "loss": 0.3774,
+      "step": 66000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022349999999999998,
+      "loss": 0.3775,
+      "step": 66500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022016666666666666,
+      "loss": 0.3775,
+      "step": 67000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002168333333333333,
+      "loss": 0.3775,
+      "step": 67500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00021350666666666667,
+      "loss": 0.3775,
+      "step": 68000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00021017333333333332,
+      "loss": 0.3776,
+      "step": 68500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020684,
+      "loss": 0.3774,
+      "step": 69000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020350666666666667,
+      "loss": 0.3773,
+      "step": 69500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00020018,
+      "loss": 0.3775,
+      "step": 70000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00019684666666666667,
+      "loss": 0.3776,
+      "step": 70500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019351333333333332,
+      "loss": 0.3775,
+      "step": 71000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019018,
+      "loss": 0.3775,
+      "step": 71500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018684666666666667,
+      "loss": 0.3775,
+      "step": 72000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018351999999999998,
+      "loss": 0.3776,
+      "step": 72500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00018018666666666663,
+      "loss": 0.3774,
+      "step": 73000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0001768533333333333,
+      "loss": 0.3776,
+      "step": 73500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017352,
+      "loss": 0.3776,
+      "step": 74000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0001701933333333333,
+      "loss": 0.3775,
+      "step": 74500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00016685999999999998,
+      "loss": 0.3775,
+      "step": 75000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016352666666666663,
+      "loss": 0.3776,
+      "step": 75500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0001601933333333333,
+      "loss": 0.3775,
+      "step": 76000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015686666666666664,
+      "loss": 0.3775,
+      "step": 76500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015353333333333332,
+      "loss": 0.3775,
+      "step": 77000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001502,
+      "loss": 0.3775,
+      "step": 77500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014686666666666667,
+      "loss": 0.3774,
+      "step": 78000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014353999999999997,
+      "loss": 0.3774,
+      "step": 78500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014020666666666667,
+      "loss": 0.3775,
+      "step": 79000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013687333333333332,
+      "loss": 0.3775,
+      "step": 79500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013354,
+      "loss": 0.3775,
+      "step": 80000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00013021333333333333,
+      "loss": 0.3776,
+      "step": 80500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012687999999999998,
+      "loss": 0.3776,
+      "step": 81000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012354666666666665,
+      "loss": 0.3776,
+      "step": 81500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00012021333333333333,
+      "loss": 0.3775,
+      "step": 82000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00011688666666666665,
+      "loss": 0.3774,
+      "step": 82500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011355333333333334,
+      "loss": 0.3775,
+      "step": 83000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011022,
+      "loss": 0.3775,
+      "step": 83500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010688666666666665,
+      "loss": 0.3774,
+      "step": 84000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010355999999999999,
+      "loss": 0.3775,
+      "step": 84500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00010022666666666665,
+      "loss": 0.3775,
+      "step": 85000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 9.689333333333332e-05,
+      "loss": 0.3775,
+      "step": 85500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.355999999999999e-05,
+      "loss": 0.3773,
+      "step": 86000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.023333333333332e-05,
+      "loss": 0.3775,
+      "step": 86500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.69e-05,
+      "loss": 0.3775,
+      "step": 87000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.356666666666666e-05,
+      "loss": 0.3773,
+      "step": 87500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.023333333333332e-05,
+      "loss": 0.3775,
+      "step": 88000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.690666666666667e-05,
+      "loss": 0.3775,
+      "step": 88500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.357333333333333e-05,
+      "loss": 0.3776,
+      "step": 89000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.023999999999999e-05,
+      "loss": 0.3774,
+      "step": 89500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.690666666666667e-05,
+      "loss": 0.3776,
+      "step": 90000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.358e-05,
+      "loss": 0.3774,
+      "step": 90500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.024666666666667e-05,
+      "loss": 0.3775,
+      "step": 91000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.691333333333333e-05,
+      "loss": 0.3774,
+      "step": 91500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.358e-05,
+      "loss": 0.3775,
+      "step": 92000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.025333333333333e-05,
+      "loss": 0.3775,
+      "step": 92500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.692e-05,
+      "loss": 0.3773,
+      "step": 93000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.358666666666666e-05,
+      "loss": 0.3773,
+      "step": 93500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.025333333333333e-05,
+      "loss": 0.3774,
+      "step": 94000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.692666666666666e-05,
+      "loss": 0.3774,
+      "step": 94500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.359333333333333e-05,
+      "loss": 0.3775,
+      "step": 95000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.0259999999999995e-05,
+      "loss": 0.3774,
+      "step": 95500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.6926666666666667e-05,
+      "loss": 0.3774,
+      "step": 96000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.3599999999999998e-05,
+      "loss": 0.3774,
+      "step": 96500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.0266666666666663e-05,
+      "loss": 0.3775,
+      "step": 97000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6933333333333333e-05,
+      "loss": 0.3774,
+      "step": 97500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.36e-05,
+      "loss": 0.3775,
+      "step": 98000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0266666666666666e-05,
+      "loss": 0.3775,
+      "step": 98500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.939999999999999e-06,
+      "loss": 0.3774,
+      "step": 99000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.6066666666666663e-06,
+      "loss": 0.3774,
+      "step": 99500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.733333333333333e-07,
+      "loss": 0.3774,
+      "step": 100000
+    }
+  ],
+  "max_steps": 100000,
+  "num_train_epochs": 1,
+  "total_flos": 4.005757407028838e+19,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/propositional_logic/ln_alm/checkpoint-100000/training_args.bin b/propositional_logic/ln_alm/checkpoint-100000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6631b245d4a5c05f6a6b607e12052d7ab6dca82d
--- /dev/null
+++ b/propositional_logic/ln_alm/checkpoint-100000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80979526bc93bd92f79329c7626a6e5643dd6e98c75ea67395c79b09f05795cf
+size 2735
diff --git a/propositional_logic/ln_alm/config.json b/propositional_logic/ln_alm/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff8809f9ee0000962c182321c304c5b09e84f1ba
--- /dev/null
+++ b/propositional_logic/ln_alm/config.json
@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/ln_alm/pytorch_model.bin b/propositional_logic/ln_alm/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..ea45f289651c6a19c5113875279faed7fc78683b
--- /dev/null
+++ b/propositional_logic/ln_alm/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d33019ba41adae198befff715674fa10743b9c2adff598ade2f1594a02b1a7a3
+size 359700713
diff --git a/propositional_logic/ln_alm/runs/Oct27_11-35-54_allennlp-cirrascale-01.reviz.ai2.in/1666977158.968696/events.out.tfevents.1666977158.allennlp-cirrascale-01.reviz.ai2.in.1236.1 b/propositional_logic/ln_alm/runs/Oct27_11-35-54_allennlp-cirrascale-01.reviz.ai2.in/1666977158.968696/events.out.tfevents.1666977158.allennlp-cirrascale-01.reviz.ai2.in.1236.1
new file mode 100644
index 0000000000000000000000000000000000000000..d27e5f803d7ca36c8dcca432b70c6fda58cc52db
--- /dev/null
+++ b/propositional_logic/ln_alm/runs/Oct27_11-35-54_allennlp-cirrascale-01.reviz.ai2.in/1666977158.968696/events.out.tfevents.1666977158.allennlp-cirrascale-01.reviz.ai2.in.1236.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1abb58bb59be5dafa13472e41f33e99947caba071ecead163de80ea12333d7f
+size 4463
diff --git a/propositional_logic/ln_alm/runs/Oct27_11-35-54_allennlp-cirrascale-01.reviz.ai2.in/events.out.tfevents.1666977153.allennlp-cirrascale-01.reviz.ai2.in.1236.0 b/propositional_logic/ln_alm/runs/Oct27_11-35-54_allennlp-cirrascale-01.reviz.ai2.in/events.out.tfevents.1666977153.allennlp-cirrascale-01.reviz.ai2.in.1236.0
new file mode 100644
index 0000000000000000000000000000000000000000..ae4bc9a5d1f737fe8d5bab13b58b2b9bf0b27dfa
--- /dev/null
+++ b/propositional_logic/ln_alm/runs/Oct27_11-35-54_allennlp-cirrascale-01.reviz.ai2.in/events.out.tfevents.1666977153.allennlp-cirrascale-01.reviz.ai2.in.1236.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e24f78669645c7fa6d59835daf009e81b4f61ccaab0a5bc542abef1af3192bd4
+size 35661
diff --git a/propositional_logic/ln_alm/training_args.bin b/propositional_logic/ln_alm/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..6631b245d4a5c05f6a6b607e12052d7ab6dca82d
--- /dev/null
+++ b/propositional_logic/ln_alm/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80979526bc93bd92f79329c7626a6e5643dd6e98c75ea67395c79b09f05795cf
+size 2735
diff --git a/propositional_logic/ln_mlm/checkpoint-100000/config.json b/propositional_logic/ln_mlm/checkpoint-100000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..102fa0515a2e7f9a348f86a1dcb7d135d6cfa8c6
--- /dev/null
+++ b/propositional_logic/ln_mlm/checkpoint-100000/config.json
@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/ln_mlm/checkpoint-100000/optimizer.pt b/propositional_logic/ln_mlm/checkpoint-100000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..ad38cf46618ea8f7fa2258f77c46273c97b0d285
--- /dev/null
+++ b/propositional_logic/ln_mlm/checkpoint-100000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df9d8863f266529665ce1bd08fc457ddae23f94a274a2c830e9b516ba0ad138d
+size 695849113
diff --git a/propositional_logic/ln_mlm/checkpoint-100000/pytorch_model.bin b/propositional_logic/ln_mlm/checkpoint-100000/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1126259f6fcb441966008604c9c135dab2d2574a
--- /dev/null
+++ b/propositional_logic/ln_mlm/checkpoint-100000/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810a13b278b8bdcc7a273dde004d8b35700c28c3c143a425ff66da9ecf1c9740
+size 347937771
diff --git a/propositional_logic/ln_mlm/checkpoint-100000/rng_state.pth b/propositional_logic/ln_mlm/checkpoint-100000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..1a0052329f405f8d16b98093adef52f7ec5fc386
--- /dev/null
+++ b/propositional_logic/ln_mlm/checkpoint-100000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:275268d12ae096293e6c66801629ae22ecc01c39d8a1be7750d5de7ef54cf04f
+size 14503
diff --git a/propositional_logic/ln_mlm/checkpoint-100000/scaler.pt b/propositional_logic/ln_mlm/checkpoint-100000/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..18973ed63ba788903f022db6a1421dacb199f986
--- /dev/null
+++ b/propositional_logic/ln_mlm/checkpoint-100000/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9d1f280998184f253723b01066537d6427ea14f757cd61741edd038bbb20496
+size 559
diff --git a/propositional_logic/ln_mlm/checkpoint-100000/scheduler.pt b/propositional_logic/ln_mlm/checkpoint-100000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f9c53104ef99d6b0bf7a8783ed9f1b0b713b1f32
--- /dev/null
+++ b/propositional_logic/ln_mlm/checkpoint-100000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52aa869af3168494a9663ed52b1edb8f050b60bc9e3263f9e675f8db24049470
+size 623
diff --git a/propositional_logic/ln_mlm/checkpoint-100000/trainer_state.json b/propositional_logic/ln_mlm/checkpoint-100000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..0547a42f58cdf41a4b0ea5f4385ead028d6ac99c
--- /dev/null
+++ b/propositional_logic/ln_mlm/checkpoint-100000/trainer_state.json
@@ -0,0 +1,1216 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 100000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 2.1616,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.5106,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.478,
+      "step": 1500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.3936,
+      "step": 2000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015,
+      "loss": 1.3072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.2877,
+      "step": 3000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.2655,
+      "step": 3500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.2326,
+      "step": 4000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00027,
+      "loss": 1.2196,
+      "step": 4500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.2138,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00033,
+      "loss": 1.21,
+      "step": 5500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00035999999999999997,
+      "loss": 1.2076,
+      "step": 6000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039,
+      "loss": 1.2057,
+      "step": 6500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00041999999999999996,
+      "loss": 1.2044,
+      "step": 7000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00045,
+      "loss": 1.203,
+      "step": 7500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00047999999999999996,
+      "loss": 1.2026,
+      "step": 8000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0005099999999999999,
+      "loss": 1.2016,
+      "step": 8500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00054,
+      "loss": 1.2018,
+      "step": 9000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00057,
+      "loss": 1.2005,
+      "step": 9500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0006,
+      "loss": 1.1998,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0005966666666666667,
+      "loss": 1.201,
+      "step": 10500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0005933333333333333,
+      "loss": 1.1983,
+      "step": 11000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005899999999999999,
+      "loss": 1.1981,
+      "step": 11500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005866666666666665,
+      "loss": 1.198,
+      "step": 12000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 1.1963,
+      "step": 12500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00058,
+      "loss": 1.1961,
+      "step": 13000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005766666666666666,
+      "loss": 1.1953,
+      "step": 13500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00057334,
+      "loss": 1.1958,
+      "step": 14000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005700066666666666,
+      "loss": 1.1948,
+      "step": 14500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005666733333333333,
+      "loss": 1.1942,
+      "step": 15000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00056334,
+      "loss": 1.1937,
+      "step": 15500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0005600066666666666,
+      "loss": 1.1933,
+      "step": 16000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005566733333333333,
+      "loss": 1.1934,
+      "step": 16500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005533399999999999,
+      "loss": 1.193,
+      "step": 17000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005500066666666667,
+      "loss": 1.193,
+      "step": 17500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005466733333333333,
+      "loss": 1.1925,
+      "step": 18000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005433399999999999,
+      "loss": 1.1927,
+      "step": 18500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0005400133333333333,
+      "loss": 1.1928,
+      "step": 19000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005366799999999999,
+      "loss": 1.192,
+      "step": 19500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005333466666666666,
+      "loss": 1.1928,
+      "step": 20000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005300133333333333,
+      "loss": 1.1916,
+      "step": 20500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00052668,
+      "loss": 1.1924,
+      "step": 21000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0005233466666666667,
+      "loss": 1.1916,
+      "step": 21500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0005200199999999999,
+      "loss": 1.1939,
+      "step": 22000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005166866666666667,
+      "loss": 1.1912,
+      "step": 22500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005133533333333333,
+      "loss": 1.1921,
+      "step": 23000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005100199999999999,
+      "loss": 1.1908,
+      "step": 23500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005066933333333333,
+      "loss": 1.1917,
+      "step": 24000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005033599999999999,
+      "loss": 1.1912,
+      "step": 24500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0005000266666666666,
+      "loss": 1.1906,
+      "step": 25000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0004966933333333332,
+      "loss": 1.1906,
+      "step": 25500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00049336,
+      "loss": 1.1905,
+      "step": 26000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0004900333333333333,
+      "loss": 1.191,
+      "step": 26500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00048669999999999996,
+      "loss": 1.1902,
+      "step": 27000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004833666666666666,
+      "loss": 1.19,
+      "step": 27500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00048003333333333326,
+      "loss": 1.1906,
+      "step": 28000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00047669999999999993,
+      "loss": 1.1905,
+      "step": 28500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004733666666666666,
+      "loss": 1.1903,
+      "step": 29000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004700333333333333,
+      "loss": 1.1899,
+      "step": 29500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046670666666666664,
+      "loss": 1.1904,
+      "step": 30000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0004633733333333333,
+      "loss": 1.1898,
+      "step": 30500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00046004,
+      "loss": 1.1908,
+      "step": 31000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0004567066666666666,
+      "loss": 1.1902,
+      "step": 31500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0004533733333333333,
+      "loss": 1.1899,
+      "step": 32000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0004500466666666666,
+      "loss": 1.1898,
+      "step": 32500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00044671333333333327,
+      "loss": 1.1895,
+      "step": 33000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00044337999999999995,
+      "loss": 1.1897,
+      "step": 33500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004400466666666666,
+      "loss": 1.1892,
+      "step": 34000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004367133333333333,
+      "loss": 1.1894,
+      "step": 34500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00043338,
+      "loss": 1.1893,
+      "step": 35000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00043005333333333333,
+      "loss": 1.1895,
+      "step": 35500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042672,
+      "loss": 1.1894,
+      "step": 36000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042338666666666663,
+      "loss": 1.1896,
+      "step": 36500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0004200533333333333,
+      "loss": 1.1891,
+      "step": 37000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00041672,
+      "loss": 1.1891,
+      "step": 37500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0004133933333333333,
+      "loss": 1.1889,
+      "step": 38000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00041005999999999996,
+      "loss": 1.189,
+      "step": 38500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00040672666666666664,
+      "loss": 1.1893,
+      "step": 39000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004033933333333333,
+      "loss": 1.1889,
+      "step": 39500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.00040005999999999993,
+      "loss": 1.1887,
+      "step": 40000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003967266666666666,
+      "loss": 1.1885,
+      "step": 40500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003933999999999999,
+      "loss": 1.1889,
+      "step": 41000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039006666666666664,
+      "loss": 1.1885,
+      "step": 41500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003867333333333333,
+      "loss": 1.1889,
+      "step": 42000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003834,
+      "loss": 1.1888,
+      "step": 42500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00038006666666666667,
+      "loss": 1.1889,
+      "step": 43000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00037673333333333335,
+      "loss": 1.1883,
+      "step": 43500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00037339999999999997,
+      "loss": 1.1883,
+      "step": 44000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00037006666666666664,
+      "loss": 1.1886,
+      "step": 44500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00036674666666666663,
+      "loss": 1.1882,
+      "step": 45000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00036341333333333336,
+      "loss": 1.1881,
+      "step": 45500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003600799999999999,
+      "loss": 1.1879,
+      "step": 46000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003567466666666666,
+      "loss": 1.1882,
+      "step": 46500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003534133333333333,
+      "loss": 1.1883,
+      "step": 47000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00035008,
+      "loss": 1.188,
+      "step": 47500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003467466666666667,
+      "loss": 1.1883,
+      "step": 48000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00034342,
+      "loss": 1.1881,
+      "step": 48500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00034008666666666666,
+      "loss": 1.1876,
+      "step": 49000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003367533333333333,
+      "loss": 1.1889,
+      "step": 49500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00033341999999999996,
+      "loss": 1.1881,
+      "step": 50000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00033008666666666664,
+      "loss": 1.1879,
+      "step": 50500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003267533333333333,
+      "loss": 1.1881,
+      "step": 51000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00032342,
+      "loss": 1.1878,
+      "step": 51500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00032008666666666667,
+      "loss": 1.1877,
+      "step": 52000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00031675999999999997,
+      "loss": 1.1877,
+      "step": 52500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003134333333333333,
+      "loss": 1.1879,
+      "step": 53000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003101,
+      "loss": 1.1877,
+      "step": 53500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003067666666666667,
+      "loss": 1.1875,
+      "step": 54000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003034333333333333,
+      "loss": 1.1873,
+      "step": 54500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003001,
+      "loss": 1.1873,
+      "step": 55000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029677333333333333,
+      "loss": 1.1877,
+      "step": 55500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029343999999999996,
+      "loss": 1.1876,
+      "step": 56000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029010666666666663,
+      "loss": 1.1874,
+      "step": 56500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002867733333333333,
+      "loss": 1.1874,
+      "step": 57000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00028344,
+      "loss": 1.1871,
+      "step": 57500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00028010666666666666,
+      "loss": 1.1873,
+      "step": 58000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00027677999999999996,
+      "loss": 1.1871,
+      "step": 58500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00027344666666666664,
+      "loss": 1.1874,
+      "step": 59000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002701133333333333,
+      "loss": 1.1873,
+      "step": 59500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026678,
+      "loss": 1.1877,
+      "step": 60000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026344666666666667,
+      "loss": 1.1874,
+      "step": 60500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002601133333333333,
+      "loss": 1.1869,
+      "step": 61000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00025677999999999996,
+      "loss": 1.1873,
+      "step": 61500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002534533333333333,
+      "loss": 1.1873,
+      "step": 62000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00025012,
+      "loss": 1.1872,
+      "step": 62500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002467866666666667,
+      "loss": 1.1871,
+      "step": 63000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002434533333333333,
+      "loss": 1.1871,
+      "step": 63500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00024011999999999997,
+      "loss": 1.1866,
+      "step": 64000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00023678666666666665,
+      "loss": 1.187,
+      "step": 64500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002334533333333333,
+      "loss": 1.1868,
+      "step": 65000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00023011999999999997,
+      "loss": 1.1868,
+      "step": 65500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002267933333333333,
+      "loss": 1.1868,
+      "step": 66000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022345999999999998,
+      "loss": 1.1868,
+      "step": 66500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022012666666666665,
+      "loss": 1.1871,
+      "step": 67000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002167933333333333,
+      "loss": 1.1865,
+      "step": 67500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00021346666666666666,
+      "loss": 1.1865,
+      "step": 68000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002101333333333333,
+      "loss": 1.187,
+      "step": 68500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020679999999999999,
+      "loss": 1.1869,
+      "step": 69000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020346666666666663,
+      "loss": 1.1866,
+      "step": 69500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00020014,
+      "loss": 1.1865,
+      "step": 70000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00019680666666666664,
+      "loss": 1.1865,
+      "step": 70500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019347333333333332,
+      "loss": 1.1867,
+      "step": 71000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019014,
+      "loss": 1.1866,
+      "step": 71500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018681333333333332,
+      "loss": 1.1866,
+      "step": 72000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018348,
+      "loss": 1.1867,
+      "step": 72500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00018014666666666665,
+      "loss": 1.1864,
+      "step": 73000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017682,
+      "loss": 1.1865,
+      "step": 73500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017348666666666665,
+      "loss": 1.1865,
+      "step": 74000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017015333333333333,
+      "loss": 1.1866,
+      "step": 74500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00016682,
+      "loss": 1.1864,
+      "step": 75000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016348666666666665,
+      "loss": 1.1864,
+      "step": 75500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016015333333333333,
+      "loss": 1.1864,
+      "step": 76000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015682,
+      "loss": 1.1861,
+      "step": 76500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015348666666666666,
+      "loss": 1.1863,
+      "step": 77000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00015016,
+      "loss": 1.1864,
+      "step": 77500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014682666666666666,
+      "loss": 1.186,
+      "step": 78000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014349333333333334,
+      "loss": 1.1862,
+      "step": 78500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014015999999999999,
+      "loss": 1.1862,
+      "step": 79000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013683333333333332,
+      "loss": 1.1861,
+      "step": 79500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0001335,
+      "loss": 1.186,
+      "step": 80000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00013016666666666664,
+      "loss": 1.1859,
+      "step": 80500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012684,
+      "loss": 1.1864,
+      "step": 81000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012350666666666665,
+      "loss": 1.1858,
+      "step": 81500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00012017333333333331,
+      "loss": 1.186,
+      "step": 82000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00011684,
+      "loss": 1.1857,
+      "step": 82500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011350666666666666,
+      "loss": 1.1859,
+      "step": 83000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011017333333333332,
+      "loss": 1.1856,
+      "step": 83500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010684,
+      "loss": 1.1858,
+      "step": 84000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010350666666666666,
+      "loss": 1.1858,
+      "step": 84500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00010017999999999999,
+      "loss": 1.1856,
+      "step": 85000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 9.684666666666666e-05,
+      "loss": 1.1857,
+      "step": 85500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.351333333333332e-05,
+      "loss": 1.1857,
+      "step": 86000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.017999999999998e-05,
+      "loss": 1.1858,
+      "step": 86500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.685333333333332e-05,
+      "loss": 1.1855,
+      "step": 87000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.351999999999999e-05,
+      "loss": 1.1854,
+      "step": 87500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.018666666666666e-05,
+      "loss": 1.1859,
+      "step": 88000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.685333333333332e-05,
+      "loss": 1.1859,
+      "step": 88500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.352666666666666e-05,
+      "loss": 1.1856,
+      "step": 89000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.019333333333333e-05,
+      "loss": 1.1857,
+      "step": 89500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.686e-05,
+      "loss": 1.1858,
+      "step": 90000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.352666666666666e-05,
+      "loss": 1.1855,
+      "step": 90500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.019999999999999e-05,
+      "loss": 1.1852,
+      "step": 91000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.686666666666666e-05,
+      "loss": 1.1855,
+      "step": 91500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.3533333333333324e-05,
+      "loss": 1.1854,
+      "step": 92000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.0199999999999994e-05,
+      "loss": 1.1853,
+      "step": 92500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.6873333333333324e-05,
+      "loss": 1.1856,
+      "step": 93000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.354e-05,
+      "loss": 1.1856,
+      "step": 93500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.020666666666666e-05,
+      "loss": 1.1852,
+      "step": 94000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.687333333333333e-05,
+      "loss": 1.1853,
+      "step": 94500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.354666666666666e-05,
+      "loss": 1.1854,
+      "step": 95000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.021333333333333e-05,
+      "loss": 1.1853,
+      "step": 95500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.6879999999999997e-05,
+      "loss": 1.1854,
+      "step": 96000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.3546666666666663e-05,
+      "loss": 1.1854,
+      "step": 96500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.022e-05,
+      "loss": 1.1854,
+      "step": 97000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6886666666666665e-05,
+      "loss": 1.1852,
+      "step": 97500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3553333333333331e-05,
+      "loss": 1.1851,
+      "step": 98000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.022e-05,
+      "loss": 1.1853,
+      "step": 98500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.893333333333332e-06,
+      "loss": 1.1851,
+      "step": 99000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.5599999999999994e-06,
+      "loss": 1.1851,
+      "step": 99500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.2666666666666663e-07,
+      "loss": 1.1852,
+      "step": 100000
+    }
+  ],
+  "max_steps": 100000,
+  "num_train_epochs": 1,
+  "total_flos": 4.033700503703942e+19,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/propositional_logic/ln_mlm/checkpoint-100000/training_args.bin b/propositional_logic/ln_mlm/checkpoint-100000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8d6510e69f7f4b4e104614b057ec57a7a631e373
--- /dev/null
+++ b/propositional_logic/ln_mlm/checkpoint-100000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21b6f934872fd1ff44db7303058ff9e1201e5175891842ccc1d594dd226d3ae
+size 2799
diff --git a/propositional_logic/ln_mlm/config.json b/propositional_logic/ln_mlm/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..102fa0515a2e7f9a348f86a1dcb7d135d6cfa8c6
--- /dev/null
+++ b/propositional_logic/ln_mlm/config.json
@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/ln_mlm/pytorch_model.bin b/propositional_logic/ln_mlm/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..1126259f6fcb441966008604c9c135dab2d2574a
--- /dev/null
+++ b/propositional_logic/ln_mlm/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:810a13b278b8bdcc7a273dde004d8b35700c28c3c143a425ff66da9ecf1c9740
+size 347937771
diff --git a/propositional_logic/ln_mlm/runs/Oct27_11-38-51_allennlp-cirrascale-01.reviz.ai2.in/1666978568.2974002/events.out.tfevents.1666978568.allennlp-cirrascale-01.reviz.ai2.in.1011.1 b/propositional_logic/ln_mlm/runs/Oct27_11-38-51_allennlp-cirrascale-01.reviz.ai2.in/1666978568.2974002/events.out.tfevents.1666978568.allennlp-cirrascale-01.reviz.ai2.in.1011.1
new file mode 100644
index 0000000000000000000000000000000000000000..4db72cc8d40be9fccc8b8a50501d3e1887128d75
--- /dev/null
+++ b/propositional_logic/ln_mlm/runs/Oct27_11-38-51_allennlp-cirrascale-01.reviz.ai2.in/1666978568.2974002/events.out.tfevents.1666978568.allennlp-cirrascale-01.reviz.ai2.in.1011.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7f88108614985a48ff44cf54bb2925c76c359bc311e81ba151639072cb2dd7
+size 4511
diff --git a/propositional_logic/ln_mlm/runs/Oct27_11-38-51_allennlp-cirrascale-01.reviz.ai2.in/events.out.tfevents.1666978564.allennlp-cirrascale-01.reviz.ai2.in.1011.0 b/propositional_logic/ln_mlm/runs/Oct27_11-38-51_allennlp-cirrascale-01.reviz.ai2.in/events.out.tfevents.1666978564.allennlp-cirrascale-01.reviz.ai2.in.1011.0
new file mode 100644
index 0000000000000000000000000000000000000000..77f37b0fac78f540ebe056032d61c545c9c859ff
--- /dev/null
+++ b/propositional_logic/ln_mlm/runs/Oct27_11-38-51_allennlp-cirrascale-01.reviz.ai2.in/events.out.tfevents.1666978564.allennlp-cirrascale-01.reviz.ai2.in.1011.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f44089b3692bf07c2c76a18ffe9a2031072c563542a1bbb3035e8f30047b68d
+size 35546
diff --git a/propositional_logic/ln_mlm/training_args.bin b/propositional_logic/ln_mlm/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..8d6510e69f7f4b4e104614b057ec57a7a631e373
--- /dev/null
+++ b/propositional_logic/ln_mlm/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f21b6f934872fd1ff44db7303058ff9e1201e5175891842ccc1d594dd226d3ae
+size 2799
diff --git a/propositional_logic/lt_alm/checkpoint-100000/config.json b/propositional_logic/lt_alm/checkpoint-100000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff8809f9ee0000962c182321c304c5b09e84f1ba
--- /dev/null
+++ b/propositional_logic/lt_alm/checkpoint-100000/config.json
@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/lt_alm/checkpoint-100000/optimizer.pt b/propositional_logic/lt_alm/checkpoint-100000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fd0a3de9da921db710909d0fe3a4c50fd6568cd9
--- /dev/null
+++ b/propositional_logic/lt_alm/checkpoint-100000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c779ab9a3d1939b649ebf721d0af1e4e20143515f2a88db3ac3e9e33c2bfc2f
+size 694198065
diff --git a/propositional_logic/lt_alm/checkpoint-100000/pytorch_model.bin b/propositional_logic/lt_alm/checkpoint-100000/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d8604f3a75823ef3631155b986d4d9cf53df986a
--- /dev/null
+++ b/propositional_logic/lt_alm/checkpoint-100000/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f124fd83e9e8f3118d339e6d8a19797a22ffb26b6972ea38c5239a967fb1250
+size 359700713
diff --git a/propositional_logic/lt_alm/checkpoint-100000/rng_state.pth b/propositional_logic/lt_alm/checkpoint-100000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4a3150d29fa8c09ae8334d72c8db783e38d463a0
--- /dev/null
+++ b/propositional_logic/lt_alm/checkpoint-100000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ace806f1cf6b8fea340c8dcb0738206e80dd48ed2f8e8fdeb7d956fbc92c63b
+size 14503
diff --git a/propositional_logic/lt_alm/checkpoint-100000/scaler.pt b/propositional_logic/lt_alm/checkpoint-100000/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..40ebe2d68777171491b4742ce7d196b125693729
--- /dev/null
+++ b/propositional_logic/lt_alm/checkpoint-100000/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bfb9f24f635e91458f1872f8625881995ec548e5b089e8b716074ac10ba4308
+size 559
diff --git a/propositional_logic/lt_alm/checkpoint-100000/scheduler.pt b/propositional_logic/lt_alm/checkpoint-100000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..c451d8bad3816a4910e1b57458c1c1386fc59d1a
--- /dev/null
+++ b/propositional_logic/lt_alm/checkpoint-100000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d3a2780a4009edea40751d0cb4f0b7a6c72e9ad8fa677d488e630fd61edd523
+size 623
diff --git a/propositional_logic/lt_alm/checkpoint-100000/trainer_state.json b/propositional_logic/lt_alm/checkpoint-100000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..3e1f8a8c5babbaef7d6ffc02c68d938168b0cd0c
--- /dev/null
+++ b/propositional_logic/lt_alm/checkpoint-100000/trainer_state.json
@@ -0,0 +1,1216 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 100000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.3008,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 0.632,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 0.568,
+      "step": 1500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 0.4923,
+      "step": 2000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015,
+      "loss": 0.444,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.4349,
+      "step": 3000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.431,
+      "step": 3500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.4373,
+      "step": 4000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00027,
+      "loss": 0.4326,
+      "step": 4500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.4285,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00033,
+      "loss": 0.4293,
+      "step": 5500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00035999999999999997,
+      "loss": 0.4299,
+      "step": 6000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039,
+      "loss": 0.4273,
+      "step": 6500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00041999999999999996,
+      "loss": 0.427,
+      "step": 7000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00045,
+      "loss": 0.4243,
+      "step": 7500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00047999999999999996,
+      "loss": 0.4261,
+      "step": 8000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0005099999999999999,
+      "loss": 0.4256,
+      "step": 8500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00054,
+      "loss": 0.4256,
+      "step": 9000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00057,
+      "loss": 0.4229,
+      "step": 9500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0006,
+      "loss": 0.4216,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0005966666666666667,
+      "loss": 0.4225,
+      "step": 10500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0005933333333333333,
+      "loss": 0.42,
+      "step": 11000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005899999999999999,
+      "loss": 0.4192,
+      "step": 11500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005866666666666665,
+      "loss": 0.4186,
+      "step": 12000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 0.4179,
+      "step": 12500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00058,
+      "loss": 0.4173,
+      "step": 13000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005766666666666666,
+      "loss": 0.417,
+      "step": 13500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005733333333333334,
+      "loss": 0.4166,
+      "step": 14000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00057,
+      "loss": 0.4168,
+      "step": 14500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005666666666666666,
+      "loss": 0.4167,
+      "step": 15000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005633333333333333,
+      "loss": 0.4169,
+      "step": 15500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00056,
+      "loss": 0.4163,
+      "step": 16000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005566666666666667,
+      "loss": 0.4163,
+      "step": 16500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005533333333333333,
+      "loss": 0.4161,
+      "step": 17000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005499999999999999,
+      "loss": 0.416,
+      "step": 17500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005466666666666667,
+      "loss": 0.4159,
+      "step": 18000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005433399999999999,
+      "loss": 0.4159,
+      "step": 18500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0005400066666666666,
+      "loss": 0.4159,
+      "step": 19000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005366733333333333,
+      "loss": 0.4157,
+      "step": 19500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00053334,
+      "loss": 0.4159,
+      "step": 20000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005300133333333333,
+      "loss": 0.4158,
+      "step": 20500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00052668,
+      "loss": 0.4158,
+      "step": 21000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0005233466666666667,
+      "loss": 0.4158,
+      "step": 21500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0005200133333333332,
+      "loss": 0.4158,
+      "step": 22000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005166866666666667,
+      "loss": 0.4156,
+      "step": 22500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005133533333333333,
+      "loss": 0.4155,
+      "step": 23000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005100199999999999,
+      "loss": 0.4156,
+      "step": 23500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005066866666666666,
+      "loss": 0.4157,
+      "step": 24000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005033599999999999,
+      "loss": 0.4157,
+      "step": 24500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0005000266666666666,
+      "loss": 0.4157,
+      "step": 25000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0004966933333333332,
+      "loss": 0.4156,
+      "step": 25500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00049336,
+      "loss": 0.4154,
+      "step": 26000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0004900333333333333,
+      "loss": 0.4156,
+      "step": 26500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00048669999999999996,
+      "loss": 0.4156,
+      "step": 27000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004833666666666666,
+      "loss": 0.4156,
+      "step": 27500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00048003333333333326,
+      "loss": 0.4156,
+      "step": 28000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004767066666666666,
+      "loss": 0.4156,
+      "step": 28500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004733733333333333,
+      "loss": 0.4155,
+      "step": 29000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00047003999999999997,
+      "loss": 0.4155,
+      "step": 29500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046670666666666664,
+      "loss": 0.4155,
+      "step": 30000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046337999999999994,
+      "loss": 0.4155,
+      "step": 30500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0004600466666666666,
+      "loss": 0.4155,
+      "step": 31000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0004567133333333333,
+      "loss": 0.4153,
+      "step": 31500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00045337999999999997,
+      "loss": 0.4154,
+      "step": 32000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00045005333333333333,
+      "loss": 0.4155,
+      "step": 32500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00044672,
+      "loss": 0.4155,
+      "step": 33000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00044338666666666663,
+      "loss": 0.4154,
+      "step": 33500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004400533333333333,
+      "loss": 0.4153,
+      "step": 34000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004367266666666666,
+      "loss": 0.4154,
+      "step": 34500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0004333933333333333,
+      "loss": 0.4154,
+      "step": 35000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00043005999999999996,
+      "loss": 0.4154,
+      "step": 35500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042672666666666663,
+      "loss": 0.4154,
+      "step": 36000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042339999999999994,
+      "loss": 0.4154,
+      "step": 36500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0004200666666666666,
+      "loss": 0.4154,
+      "step": 37000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00041673333333333334,
+      "loss": 0.4155,
+      "step": 37500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0004133999999999999,
+      "loss": 0.4154,
+      "step": 38000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0004100733333333333,
+      "loss": 0.4153,
+      "step": 38500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00040673999999999994,
+      "loss": 0.4155,
+      "step": 39000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004034066666666666,
+      "loss": 0.4154,
+      "step": 39500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004000733333333333,
+      "loss": 0.4153,
+      "step": 40000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003967466666666666,
+      "loss": 0.4155,
+      "step": 40500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003934133333333333,
+      "loss": 0.4155,
+      "step": 41000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039007999999999995,
+      "loss": 0.4154,
+      "step": 41500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00038674666666666663,
+      "loss": 0.4153,
+      "step": 42000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00038342,
+      "loss": 0.4155,
+      "step": 42500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00038008666666666666,
+      "loss": 0.4154,
+      "step": 43000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00037675333333333334,
+      "loss": 0.4155,
+      "step": 43500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00037341999999999996,
+      "loss": 0.4155,
+      "step": 44000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003700933333333333,
+      "loss": 0.4153,
+      "step": 44500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00036675999999999994,
+      "loss": 0.4154,
+      "step": 45000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003634266666666666,
+      "loss": 0.4154,
+      "step": 45500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003600933333333333,
+      "loss": 0.4155,
+      "step": 46000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00035676666666666665,
+      "loss": 0.4153,
+      "step": 46500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003534333333333333,
+      "loss": 0.4154,
+      "step": 47000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003501,
+      "loss": 0.4154,
+      "step": 47500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003467666666666667,
+      "loss": 0.4153,
+      "step": 48000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00034344,
+      "loss": 0.4155,
+      "step": 48500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00034010666666666665,
+      "loss": 0.4154,
+      "step": 49000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003367733333333333,
+      "loss": 0.4154,
+      "step": 49500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00033343999999999995,
+      "loss": 0.4155,
+      "step": 50000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00033011333333333325,
+      "loss": 0.4154,
+      "step": 50500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00032677999999999993,
+      "loss": 0.4154,
+      "step": 51000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003234466666666666,
+      "loss": 0.4153,
+      "step": 51500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00032011333333333334,
+      "loss": 0.4155,
+      "step": 52000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00031678666666666664,
+      "loss": 0.4154,
+      "step": 52500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003134533333333333,
+      "loss": 0.4154,
+      "step": 53000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00031012,
+      "loss": 0.4153,
+      "step": 53500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030678666666666667,
+      "loss": 0.4154,
+      "step": 54000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00030345999999999997,
+      "loss": 0.4154,
+      "step": 54500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00030012666666666665,
+      "loss": 0.4154,
+      "step": 55000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967933333333333,
+      "loss": 0.4154,
+      "step": 55500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029345999999999994,
+      "loss": 0.4154,
+      "step": 56000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029014,
+      "loss": 0.4154,
+      "step": 56500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00028680666666666666,
+      "loss": 0.4153,
+      "step": 57000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00028347333333333334,
+      "loss": 0.4154,
+      "step": 57500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00028013999999999996,
+      "loss": 0.4154,
+      "step": 58000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00027680666666666663,
+      "loss": 0.4155,
+      "step": 58500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002734733333333333,
+      "loss": 0.4153,
+      "step": 59000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00027014,
+      "loss": 0.4154,
+      "step": 59500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026680666666666666,
+      "loss": 0.4154,
+      "step": 60000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026347999999999996,
+      "loss": 0.4153,
+      "step": 60500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00026014666666666664,
+      "loss": 0.4154,
+      "step": 61000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002568133333333333,
+      "loss": 0.4154,
+      "step": 61500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00025348,
+      "loss": 0.4153,
+      "step": 62000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00025015333333333335,
+      "loss": 0.4154,
+      "step": 62500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00024681999999999997,
+      "loss": 0.4154,
+      "step": 63000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00024348666666666665,
+      "loss": 0.4152,
+      "step": 63500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002401533333333333,
+      "loss": 0.4153,
+      "step": 64000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00023682666666666665,
+      "loss": 0.4153,
+      "step": 64500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002334933333333333,
+      "loss": 0.4154,
+      "step": 65000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00023015999999999998,
+      "loss": 0.4152,
+      "step": 65500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00022682666666666665,
+      "loss": 0.4153,
+      "step": 66000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022349999999999998,
+      "loss": 0.4153,
+      "step": 66500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022016666666666666,
+      "loss": 0.4153,
+      "step": 67000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002168333333333333,
+      "loss": 0.4153,
+      "step": 67500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00021350666666666667,
+      "loss": 0.4153,
+      "step": 68000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00021017333333333332,
+      "loss": 0.4155,
+      "step": 68500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020684,
+      "loss": 0.4153,
+      "step": 69000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020350666666666667,
+      "loss": 0.4152,
+      "step": 69500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00020017333333333332,
+      "loss": 0.4153,
+      "step": 70000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00019684,
+      "loss": 0.4154,
+      "step": 70500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019350666666666667,
+      "loss": 0.4154,
+      "step": 71000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019018,
+      "loss": 0.4153,
+      "step": 71500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018684666666666667,
+      "loss": 0.4154,
+      "step": 72000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018351333333333332,
+      "loss": 0.4154,
+      "step": 72500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00018018,
+      "loss": 0.4153,
+      "step": 73000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017684666666666665,
+      "loss": 0.4154,
+      "step": 73500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017352,
+      "loss": 0.4154,
+      "step": 74000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017018666666666663,
+      "loss": 0.4154,
+      "step": 74500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0001668533333333333,
+      "loss": 0.4154,
+      "step": 75000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016352,
+      "loss": 0.4154,
+      "step": 75500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016018666666666663,
+      "loss": 0.4153,
+      "step": 76000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015685333333333333,
+      "loss": 0.4154,
+      "step": 76500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015352666666666663,
+      "loss": 0.4153,
+      "step": 77000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001501933333333333,
+      "loss": 0.4154,
+      "step": 77500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014685999999999999,
+      "loss": 0.4152,
+      "step": 78000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014352666666666666,
+      "loss": 0.4153,
+      "step": 78500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0001402,
+      "loss": 0.4154,
+      "step": 79000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013686666666666664,
+      "loss": 0.4153,
+      "step": 79500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013353333333333332,
+      "loss": 0.4153,
+      "step": 80000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0001302,
+      "loss": 0.4154,
+      "step": 80500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012686666666666664,
+      "loss": 0.4155,
+      "step": 81000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012353333333333332,
+      "loss": 0.4154,
+      "step": 81500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00012020666666666665,
+      "loss": 0.4154,
+      "step": 82000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00011687333333333332,
+      "loss": 0.4152,
+      "step": 82500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011353999999999999,
+      "loss": 0.4153,
+      "step": 83000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011020666666666665,
+      "loss": 0.4153,
+      "step": 83500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010687333333333331,
+      "loss": 0.4152,
+      "step": 84000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010354666666666666,
+      "loss": 0.4154,
+      "step": 84500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00010021333333333332,
+      "loss": 0.4154,
+      "step": 85000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 9.688e-05,
+      "loss": 0.4154,
+      "step": 85500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.354666666666666e-05,
+      "loss": 0.4152,
+      "step": 86000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.021333333333332e-05,
+      "loss": 0.4153,
+      "step": 86500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.688666666666666e-05,
+      "loss": 0.4154,
+      "step": 87000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.355333333333333e-05,
+      "loss": 0.4152,
+      "step": 87500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.022e-05,
+      "loss": 0.4153,
+      "step": 88000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.688666666666666e-05,
+      "loss": 0.4154,
+      "step": 88500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.355333333333333e-05,
+      "loss": 0.4154,
+      "step": 89000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.022666666666667e-05,
+      "loss": 0.4153,
+      "step": 89500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.689333333333333e-05,
+      "loss": 0.4154,
+      "step": 90000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.356e-05,
+      "loss": 0.4153,
+      "step": 90500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.022666666666666e-05,
+      "loss": 0.4153,
+      "step": 91000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.689333333333333e-05,
+      "loss": 0.4152,
+      "step": 91500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.356666666666666e-05,
+      "loss": 0.4153,
+      "step": 92000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.023333333333333e-05,
+      "loss": 0.4154,
+      "step": 92500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.6899999999999995e-05,
+      "loss": 0.4152,
+      "step": 93000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.3566666666666664e-05,
+      "loss": 0.4151,
+      "step": 93500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.0233333333333326e-05,
+      "loss": 0.4153,
+      "step": 94000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.6899999999999996e-05,
+      "loss": 0.4153,
+      "step": 94500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.357333333333333e-05,
+      "loss": 0.4153,
+      "step": 95000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.024e-05,
+      "loss": 0.4152,
+      "step": 95500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.6906666666666664e-05,
+      "loss": 0.4153,
+      "step": 96000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.357333333333333e-05,
+      "loss": 0.4153,
+      "step": 96500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.0246666666666664e-05,
+      "loss": 0.4153,
+      "step": 97000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6913333333333333e-05,
+      "loss": 0.4153,
+      "step": 97500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3579999999999997e-05,
+      "loss": 0.4153,
+      "step": 98000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0246666666666666e-05,
+      "loss": 0.4153,
+      "step": 98500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.913333333333333e-06,
+      "loss": 0.4153,
+      "step": 99000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.58e-06,
+      "loss": 0.4152,
+      "step": 99500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.533333333333333e-07,
+      "loss": 0.4153,
+      "step": 100000
+    }
+  ],
+  "max_steps": 100000,
+  "num_train_epochs": 1,
+  "total_flos": 4.274433427739443e+19,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/propositional_logic/lt_alm/checkpoint-100000/training_args.bin b/propositional_logic/lt_alm/checkpoint-100000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..958ab44b86bef1f2099dbd539a747d080cce5d62
--- /dev/null
+++ b/propositional_logic/lt_alm/checkpoint-100000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ac725474a043e56f1f775f1db8ecef5606d8ab95da29e9391f919b2d60d457
+size 2735
diff --git a/propositional_logic/lt_alm/config.json b/propositional_logic/lt_alm/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff8809f9ee0000962c182321c304c5b09e84f1ba
--- /dev/null
+++ b/propositional_logic/lt_alm/config.json
@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/lt_alm/pytorch_model.bin b/propositional_logic/lt_alm/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d8604f3a75823ef3631155b986d4d9cf53df986a
--- /dev/null
+++ b/propositional_logic/lt_alm/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f124fd83e9e8f3118d339e6d8a19797a22ffb26b6972ea38c5239a967fb1250
+size 359700713
diff --git a/propositional_logic/lt_alm/runs/Feb20_15-40-53_allennlp-server4/1645484343.3786743/events.out.tfevents.1645484343.allennlp-server4.3588209.1 b/propositional_logic/lt_alm/runs/Feb20_15-40-53_allennlp-server4/1645484343.3786743/events.out.tfevents.1645484343.allennlp-server4.3588209.1
new file mode 100644
index 0000000000000000000000000000000000000000..7aca01c63bf7fd7a719c044e6e9c48b83f10009a
--- /dev/null
+++ b/propositional_logic/lt_alm/runs/Feb20_15-40-53_allennlp-server4/1645484343.3786743/events.out.tfevents.1645484343.allennlp-server4.3588209.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15db4a80e37335462e0e68f688272b065df9f9d86ad22dc2387fe0e8ffd4d06d
+size 4393
diff --git a/propositional_logic/lt_alm/runs/Feb20_15-40-53_allennlp-server4/events.out.tfevents.1645484338.allennlp-server4.3588209.0 b/propositional_logic/lt_alm/runs/Feb20_15-40-53_allennlp-server4/events.out.tfevents.1645484338.allennlp-server4.3588209.0
new file mode 100644
index 0000000000000000000000000000000000000000..f0638d9a6b254a7531b707a60482f67ee34fd1b2
--- /dev/null
+++ b/propositional_logic/lt_alm/runs/Feb20_15-40-53_allennlp-server4/events.out.tfevents.1645484338.allennlp-server4.3588209.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5ea8838b7af5cb1a4a2175459b331b5357598e22491db5abeb3188ba53ce1d7
+size 5058
diff --git a/propositional_logic/lt_alm/runs/Feb22_12-59-13_allennlp-server4/1645647176.6903071/events.out.tfevents.1645647176.allennlp-server4.336403.1 b/propositional_logic/lt_alm/runs/Feb22_12-59-13_allennlp-server4/1645647176.6903071/events.out.tfevents.1645647176.allennlp-server4.336403.1
new file mode 100644
index 0000000000000000000000000000000000000000..bfe87badcdd0d78ca105dd9e80ae794a0ddc70bf
--- /dev/null
+++ b/propositional_logic/lt_alm/runs/Feb22_12-59-13_allennlp-server4/1645647176.6903071/events.out.tfevents.1645647176.allennlp-server4.336403.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e92f6692ecc61ed5c53a498564c62a6ac37eb85e43285da46182bbfef075cfe5
+size 4393
diff --git a/propositional_logic/lt_alm/runs/Feb22_12-59-13_allennlp-server4/events.out.tfevents.1645647171.allennlp-server4.336403.0 b/propositional_logic/lt_alm/runs/Feb22_12-59-13_allennlp-server4/events.out.tfevents.1645647171.allennlp-server4.336403.0
new file mode 100644
index 0000000000000000000000000000000000000000..5b980a1a53958d5d5269dcce73d79a0cfdd9ba97
--- /dev/null
+++ b/propositional_logic/lt_alm/runs/Feb22_12-59-13_allennlp-server4/events.out.tfevents.1645647171.allennlp-server4.336403.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a75521654ba6fc727c3b4f8062862c9fa91633b0596eb71cd3f58e5a2ed164
+size 35594
diff --git a/propositional_logic/lt_alm/training_args.bin b/propositional_logic/lt_alm/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..958ab44b86bef1f2099dbd539a747d080cce5d62
--- /dev/null
+++ b/propositional_logic/lt_alm/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ac725474a043e56f1f775f1db8ecef5606d8ab95da29e9391f919b2d60d457
+size 2735
diff --git a/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/config.json b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff8809f9ee0000962c182321c304c5b09e84f1ba
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/config.json
@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/optimizer.pt b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..27f4ff3fed51b0673738d23a38d0563f69ddec38
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd48b4b729cef50798aace235354f92c04defb657372dd7fade3803f53b1ce43
+size 694198065
diff --git a/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/pytorch_model.bin b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c24a5fc1a6c097c5b1d29e21b8ffe0906d5ac611
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044620c7cdb9a56568ca95b7715f08ab4b1ebe466efc936ac34c69aa496700cf
+size 359700713
diff --git a/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/rng_state.pth b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..5206cac95e4215a367485236c10528a3c00afb68
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094559b9c2dfa71e135104716de983b855fdf5edd6d1838d723e40e786b2a786
+size 14503
diff --git a/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/scaler.pt b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..227cb46a31084c8420f0bc37a070c36ec29a9f17
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd17ba3fcebe8d211b2d455e4f630394c54494f8e62d632dbd6c66c30976403
+size 559
diff --git a/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/scheduler.pt b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..15945f035518eb624e24acd009d0fee087074c8e
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a150dd417a024836c3dc23fd696b007ee1fc159e8de0d8ec1a517cf40baac2ae
+size 623
diff --git a/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/trainer_state.json b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1fcd9abf7365354107a675a316bda2a31bed4ec4
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/trainer_state.json
@@ -0,0 +1,1216 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 100000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.302,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 0.6367,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 0.5862,
+      "step": 1500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 0.5642,
+      "step": 2000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015,
+      "loss": 0.5646,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.5588,
+      "step": 3000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.5619,
+      "step": 3500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.5606,
+      "step": 4000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00027,
+      "loss": 0.5595,
+      "step": 4500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.5576,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00033,
+      "loss": 0.557,
+      "step": 5500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00035999999999999997,
+      "loss": 0.5564,
+      "step": 6000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039,
+      "loss": 0.56,
+      "step": 6500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00041999999999999996,
+      "loss": 0.5536,
+      "step": 7000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00045,
+      "loss": 0.5529,
+      "step": 7500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00047999999999999996,
+      "loss": 0.5543,
+      "step": 8000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0005099999999999999,
+      "loss": 0.5512,
+      "step": 8500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00054,
+      "loss": 0.5521,
+      "step": 9000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00057,
+      "loss": 0.5526,
+      "step": 9500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0006,
+      "loss": 0.5508,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0005966666666666667,
+      "loss": 0.552,
+      "step": 10500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0005933333333333333,
+      "loss": 0.5517,
+      "step": 11000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005899999999999999,
+      "loss": 0.549,
+      "step": 11500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005866666666666665,
+      "loss": 0.549,
+      "step": 12000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 0.5491,
+      "step": 12500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00058,
+      "loss": 0.5486,
+      "step": 13000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005766666666666666,
+      "loss": 0.5484,
+      "step": 13500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005733333333333334,
+      "loss": 0.5487,
+      "step": 14000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00057,
+      "loss": 0.5483,
+      "step": 14500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005666666666666666,
+      "loss": 0.5487,
+      "step": 15000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005633333333333333,
+      "loss": 0.5485,
+      "step": 15500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00056,
+      "loss": 0.5482,
+      "step": 16000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005566666666666667,
+      "loss": 0.5481,
+      "step": 16500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005533333333333333,
+      "loss": 0.5478,
+      "step": 17000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005499999999999999,
+      "loss": 0.548,
+      "step": 17500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005466733333333333,
+      "loss": 0.5478,
+      "step": 18000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005433399999999999,
+      "loss": 0.5477,
+      "step": 18500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0005400066666666666,
+      "loss": 0.5479,
+      "step": 19000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005366733333333333,
+      "loss": 0.5479,
+      "step": 19500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005333466666666666,
+      "loss": 0.5477,
+      "step": 20000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005300133333333333,
+      "loss": 0.5478,
+      "step": 20500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00052668,
+      "loss": 0.5476,
+      "step": 21000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0005233466666666667,
+      "loss": 0.5479,
+      "step": 21500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0005200199999999999,
+      "loss": 0.5475,
+      "step": 22000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005166866666666667,
+      "loss": 0.5475,
+      "step": 22500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005133533333333333,
+      "loss": 0.5476,
+      "step": 23000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005100199999999999,
+      "loss": 0.5478,
+      "step": 23500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005066933333333333,
+      "loss": 0.5475,
+      "step": 24000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005033599999999999,
+      "loss": 0.5475,
+      "step": 24500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0005000266666666666,
+      "loss": 0.5475,
+      "step": 25000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0004966933333333332,
+      "loss": 0.5478,
+      "step": 25500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0004933666666666666,
+      "loss": 0.5475,
+      "step": 26000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0004900333333333333,
+      "loss": 0.5475,
+      "step": 26500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00048669999999999996,
+      "loss": 0.5474,
+      "step": 27000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004833666666666666,
+      "loss": 0.5475,
+      "step": 27500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00048004,
+      "loss": 0.5476,
+      "step": 28000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004767066666666666,
+      "loss": 0.5475,
+      "step": 28500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004733733333333333,
+      "loss": 0.5475,
+      "step": 29000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00047003999999999997,
+      "loss": 0.5474,
+      "step": 29500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046670666666666664,
+      "loss": 0.5476,
+      "step": 30000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046337999999999994,
+      "loss": 0.5474,
+      "step": 30500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0004600466666666666,
+      "loss": 0.5474,
+      "step": 31000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0004567133333333333,
+      "loss": 0.5474,
+      "step": 31500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00045337999999999997,
+      "loss": 0.5475,
+      "step": 32000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00045005333333333333,
+      "loss": 0.5474,
+      "step": 32500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00044672,
+      "loss": 0.5474,
+      "step": 33000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00044338666666666663,
+      "loss": 0.5475,
+      "step": 33500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004400533333333333,
+      "loss": 0.5474,
+      "step": 34000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004367266666666666,
+      "loss": 0.5474,
+      "step": 34500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0004333933333333333,
+      "loss": 0.5474,
+      "step": 35000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00043005999999999996,
+      "loss": 0.5474,
+      "step": 35500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042672666666666663,
+      "loss": 0.5473,
+      "step": 36000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042339999999999994,
+      "loss": 0.5474,
+      "step": 36500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0004200666666666666,
+      "loss": 0.5474,
+      "step": 37000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00041673333333333334,
+      "loss": 0.5473,
+      "step": 37500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0004133999999999999,
+      "loss": 0.5474,
+      "step": 38000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0004100733333333333,
+      "loss": 0.5473,
+      "step": 38500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00040673999999999994,
+      "loss": 0.5474,
+      "step": 39000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004034066666666666,
+      "loss": 0.5473,
+      "step": 39500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004000733333333333,
+      "loss": 0.5474,
+      "step": 40000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003967466666666666,
+      "loss": 0.5474,
+      "step": 40500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003934133333333333,
+      "loss": 0.5474,
+      "step": 41000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039007999999999995,
+      "loss": 0.5474,
+      "step": 41500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00038674666666666663,
+      "loss": 0.5474,
+      "step": 42000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00038342,
+      "loss": 0.5474,
+      "step": 42500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00038008666666666666,
+      "loss": 0.5473,
+      "step": 43000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00037675333333333334,
+      "loss": 0.5473,
+      "step": 43500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00037341999999999996,
+      "loss": 0.5474,
+      "step": 44000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003700933333333333,
+      "loss": 0.5473,
+      "step": 44500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00036675999999999994,
+      "loss": 0.5473,
+      "step": 45000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003634266666666666,
+      "loss": 0.5474,
+      "step": 45500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003600933333333333,
+      "loss": 0.5473,
+      "step": 46000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00035676666666666665,
+      "loss": 0.5474,
+      "step": 46500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003534333333333333,
+      "loss": 0.5474,
+      "step": 47000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003501,
+      "loss": 0.5473,
+      "step": 47500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003467666666666667,
+      "loss": 0.5473,
+      "step": 48000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00034344,
+      "loss": 0.5473,
+      "step": 48500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00034010666666666665,
+      "loss": 0.5474,
+      "step": 49000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003367733333333333,
+      "loss": 0.5474,
+      "step": 49500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00033343999999999995,
+      "loss": 0.5474,
+      "step": 50000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00033011333333333325,
+      "loss": 0.5473,
+      "step": 50500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00032677999999999993,
+      "loss": 0.5473,
+      "step": 51000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003234466666666666,
+      "loss": 0.5473,
+      "step": 51500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00032011333333333334,
+      "loss": 0.5473,
+      "step": 52000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00031678666666666664,
+      "loss": 0.5473,
+      "step": 52500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003134533333333333,
+      "loss": 0.5473,
+      "step": 53000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00031012,
+      "loss": 0.5473,
+      "step": 53500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030678666666666667,
+      "loss": 0.5474,
+      "step": 54000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00030345999999999997,
+      "loss": 0.5473,
+      "step": 54500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00030012666666666665,
+      "loss": 0.5473,
+      "step": 55000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967933333333333,
+      "loss": 0.5473,
+      "step": 55500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029345999999999994,
+      "loss": 0.5473,
+      "step": 56000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002901333333333333,
+      "loss": 0.5473,
+      "step": 56500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002868,
+      "loss": 0.5473,
+      "step": 57000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00028346666666666665,
+      "loss": 0.5473,
+      "step": 57500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00028013333333333333,
+      "loss": 0.5473,
+      "step": 58000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00027680666666666663,
+      "loss": 0.5473,
+      "step": 58500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002734733333333333,
+      "loss": 0.5473,
+      "step": 59000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00027014,
+      "loss": 0.5473,
+      "step": 59500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026680666666666666,
+      "loss": 0.5473,
+      "step": 60000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026347999999999996,
+      "loss": 0.5473,
+      "step": 60500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00026014666666666664,
+      "loss": 0.5473,
+      "step": 61000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002568133333333333,
+      "loss": 0.5473,
+      "step": 61500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00025348,
+      "loss": 0.5473,
+      "step": 62000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00025015333333333335,
+      "loss": 0.5474,
+      "step": 62500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00024681999999999997,
+      "loss": 0.5473,
+      "step": 63000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00024348666666666665,
+      "loss": 0.5473,
+      "step": 63500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002401533333333333,
+      "loss": 0.5474,
+      "step": 64000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00023682666666666665,
+      "loss": 0.5473,
+      "step": 64500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002334933333333333,
+      "loss": 0.5473,
+      "step": 65000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00023015999999999998,
+      "loss": 0.5474,
+      "step": 65500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00022682666666666665,
+      "loss": 0.5473,
+      "step": 66000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022349999999999998,
+      "loss": 0.5473,
+      "step": 66500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022016666666666666,
+      "loss": 0.5473,
+      "step": 67000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002168333333333333,
+      "loss": 0.5473,
+      "step": 67500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00021349999999999999,
+      "loss": 0.5473,
+      "step": 68000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00021017333333333332,
+      "loss": 0.5473,
+      "step": 68500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020684,
+      "loss": 0.5473,
+      "step": 69000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020350666666666667,
+      "loss": 0.5472,
+      "step": 69500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00020017333333333332,
+      "loss": 0.5473,
+      "step": 70000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00019684666666666667,
+      "loss": 0.5474,
+      "step": 70500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019351333333333332,
+      "loss": 0.5473,
+      "step": 71000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019018,
+      "loss": 0.5473,
+      "step": 71500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018684666666666667,
+      "loss": 0.5473,
+      "step": 72000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018351999999999998,
+      "loss": 0.5473,
+      "step": 72500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0001801933333333333,
+      "loss": 0.5473,
+      "step": 73000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017685999999999998,
+      "loss": 0.5473,
+      "step": 73500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017352666666666663,
+      "loss": 0.5473,
+      "step": 74000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0001701933333333333,
+      "loss": 0.5473,
+      "step": 74500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00016685999999999998,
+      "loss": 0.5472,
+      "step": 75000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016352666666666663,
+      "loss": 0.5473,
+      "step": 75500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0001601933333333333,
+      "loss": 0.5473,
+      "step": 76000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015685999999999999,
+      "loss": 0.5473,
+      "step": 76500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015353333333333332,
+      "loss": 0.5473,
+      "step": 77000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00015020666666666665,
+      "loss": 0.5473,
+      "step": 77500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014687333333333332,
+      "loss": 0.5473,
+      "step": 78000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014353999999999997,
+      "loss": 0.5472,
+      "step": 78500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014020666666666667,
+      "loss": 0.5472,
+      "step": 79000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013687999999999998,
+      "loss": 0.5472,
+      "step": 79500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013354666666666665,
+      "loss": 0.5473,
+      "step": 80000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00013021333333333333,
+      "loss": 0.5473,
+      "step": 80500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012687999999999998,
+      "loss": 0.5472,
+      "step": 81000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012355333333333334,
+      "loss": 0.5472,
+      "step": 81500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00012021999999999998,
+      "loss": 0.5473,
+      "step": 82000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00011688666666666665,
+      "loss": 0.5472,
+      "step": 82500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011355333333333334,
+      "loss": 0.5472,
+      "step": 83000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011022666666666665,
+      "loss": 0.5473,
+      "step": 83500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010689333333333333,
+      "loss": 0.5473,
+      "step": 84000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010355999999999999,
+      "loss": 0.5472,
+      "step": 84500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00010022666666666665,
+      "loss": 0.5473,
+      "step": 85000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 9.69e-05,
+      "loss": 0.5472,
+      "step": 85500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.356666666666666e-05,
+      "loss": 0.5473,
+      "step": 86000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.023333333333332e-05,
+      "loss": 0.5472,
+      "step": 86500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.69e-05,
+      "loss": 0.5472,
+      "step": 87000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.357333333333331e-05,
+      "loss": 0.5472,
+      "step": 87500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.024e-05,
+      "loss": 0.5472,
+      "step": 88000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.690666666666667e-05,
+      "loss": 0.5472,
+      "step": 88500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.357333333333333e-05,
+      "loss": 0.5472,
+      "step": 89000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.024666666666666e-05,
+      "loss": 0.5472,
+      "step": 89500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.691999999999999e-05,
+      "loss": 0.5472,
+      "step": 90000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.358666666666667e-05,
+      "loss": 0.5472,
+      "step": 90500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.025333333333333e-05,
+      "loss": 0.5472,
+      "step": 91000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.692e-05,
+      "loss": 0.5472,
+      "step": 91500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.359333333333333e-05,
+      "loss": 0.5472,
+      "step": 92000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.0259999999999997e-05,
+      "loss": 0.5472,
+      "step": 92500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.692666666666666e-05,
+      "loss": 0.5472,
+      "step": 93000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.359333333333333e-05,
+      "loss": 0.5471,
+      "step": 93500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.026666666666666e-05,
+      "loss": 0.5473,
+      "step": 94000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.6933333333333334e-05,
+      "loss": 0.5472,
+      "step": 94500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.36e-05,
+      "loss": 0.5472,
+      "step": 95000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.0266666666666663e-05,
+      "loss": 0.5472,
+      "step": 95500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.694e-05,
+      "loss": 0.5472,
+      "step": 96000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.3606666666666665e-05,
+      "loss": 0.5472,
+      "step": 96500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.027333333333333e-05,
+      "loss": 0.5472,
+      "step": 97000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6939999999999997e-05,
+      "loss": 0.5472,
+      "step": 97500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3613333333333332e-05,
+      "loss": 0.5472,
+      "step": 98000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.028e-05,
+      "loss": 0.5472,
+      "step": 98500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.946666666666666e-06,
+      "loss": 0.5471,
+      "step": 99000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.613333333333333e-06,
+      "loss": 0.5472,
+      "step": 99500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.8666666666666664e-07,
+      "loss": 0.5472,
+      "step": 100000
+    }
+  ],
+  "max_steps": 100000,
+  "num_train_epochs": 1,
+  "total_flos": 4.214257693131571e+19,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/training_args.bin b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..15e2a84cbc0c8386fe339c58b8194aeb0f14c793
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/checkpoint-100000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4df81e52587acbe0101b10601f3f46dd97916bfc5d01cc59be7943e28c1e412
+size 2735
diff --git a/propositional_logic/lt_alm_noreflexivity/config.json b/propositional_logic/lt_alm_noreflexivity/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff8809f9ee0000962c182321c304c5b09e84f1ba
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/config.json
@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/lt_alm_noreflexivity/pytorch_model.bin b/propositional_logic/lt_alm_noreflexivity/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..c24a5fc1a6c097c5b1d29e21b8ffe0906d5ac611
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:044620c7cdb9a56568ca95b7715f08ab4b1ebe466efc936ac34c69aa496700cf
+size 359700713
diff --git a/propositional_logic/lt_alm_noreflexivity/runs/Jun02_02-52-27_allennlp-server4/1654250114.9441073/events.out.tfevents.1654250114.allennlp-server4.2845725.1 b/propositional_logic/lt_alm_noreflexivity/runs/Jun02_02-52-27_allennlp-server4/1654250114.9441073/events.out.tfevents.1654250114.allennlp-server4.2845725.1
new file mode 100644
index 0000000000000000000000000000000000000000..70cbbfc68ed4bb441099cd37d464f62af7de2700
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/runs/Jun02_02-52-27_allennlp-server4/1654250114.9441073/events.out.tfevents.1654250114.allennlp-server4.2845725.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe739aa30bb26e223fd2d4897896e7f942b1b2d576e0fda4aee47540310e78a
+size 4425
diff --git a/propositional_logic/lt_alm_noreflexivity/runs/Jun02_02-52-27_allennlp-server4/events.out.tfevents.1654250109.allennlp-server4.2845725.0 b/propositional_logic/lt_alm_noreflexivity/runs/Jun02_02-52-27_allennlp-server4/events.out.tfevents.1654250109.allennlp-server4.2845725.0
new file mode 100644
index 0000000000000000000000000000000000000000..f3c6e1f676daac6a70320558c68c714b22a54421
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/runs/Jun02_02-52-27_allennlp-server4/events.out.tfevents.1654250109.allennlp-server4.2845725.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:876b7af5e9be817eec01bce9583998aa3e21a5eca1989169595a021ecf138ff8
+size 35626
diff --git a/propositional_logic/lt_alm_noreflexivity/training_args.bin b/propositional_logic/lt_alm_noreflexivity/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..15e2a84cbc0c8386fe339c58b8194aeb0f14c793
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4df81e52587acbe0101b10601f3f46dd97916bfc5d01cc59be7943e28c1e412
+size 2735
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/config.json b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff8809f9ee0000962c182321c304c5b09e84f1ba
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/config.json
@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/optimizer.pt b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4569dddde7ae5ee789c53a69a1e4195438a0abdd
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2782cf1e0bfb8bdc248e3d34cc79875e576158ca05daa414c72299f650072ff4
+size 694198065
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/pytorch_model.bin b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4412048281e2dd6ebef89f9e1ebe6d58e3497880
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4353422edf337e6431cd9b876ce10a85ed87598959c86c2e3e37b7d59a000e
+size 359700713
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/rng_state.pth b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..35f6fde045a6c640c8505d1e1f0fe1b8ea05f3f3
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bd6c5f036db3e720e6c9b6038bd5ebba7707a753fba41942931fba45076bdff
+size 14503
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/scaler.pt b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e2d741d84c76b2dfbf645502922b64f2453d404c
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ade96461600bebab219d001f402561ab67ea3b8b429c89ff75ce4db44f23ffae
+size 559
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/scheduler.pt b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e60662986041b9dbd11ffc15e5d83dec334e7397
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19c8fa2673f2a310c2a4524c4ab6b58be6ff56aeba25233fe1a478391d398b2b
+size 623
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/trainer_state.json b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..13461503870c9f47db566da927f34ace6308b8e8
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/trainer_state.json
@@ -0,0 +1,1216 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 100000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.3017,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 0.6339,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 0.5877,
+      "step": 1500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 0.568,
+      "step": 2000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015,
+      "loss": 0.5622,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.5659,
+      "step": 3000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.561,
+      "step": 3500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.559,
+      "step": 4000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00027,
+      "loss": 0.5594,
+      "step": 4500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.5607,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00033,
+      "loss": 0.5592,
+      "step": 5500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00035999999999999997,
+      "loss": 0.5539,
+      "step": 6000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039,
+      "loss": 0.5569,
+      "step": 6500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00041999999999999996,
+      "loss": 0.5565,
+      "step": 7000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00045,
+      "loss": 0.5574,
+      "step": 7500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00047999999999999996,
+      "loss": 0.5555,
+      "step": 8000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0005099999999999999,
+      "loss": 0.5538,
+      "step": 8500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00054,
+      "loss": 0.5526,
+      "step": 9000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00057,
+      "loss": 0.5537,
+      "step": 9500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0006,
+      "loss": 0.5535,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0005966666666666667,
+      "loss": 0.5522,
+      "step": 10500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0005933333333333333,
+      "loss": 0.5507,
+      "step": 11000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005899999999999999,
+      "loss": 0.5501,
+      "step": 11500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005866666666666665,
+      "loss": 0.55,
+      "step": 12000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 0.5494,
+      "step": 12500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00058,
+      "loss": 0.5491,
+      "step": 13000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005766666666666666,
+      "loss": 0.5487,
+      "step": 13500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005733333333333334,
+      "loss": 0.549,
+      "step": 14000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00057,
+      "loss": 0.5484,
+      "step": 14500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005666666666666666,
+      "loss": 0.5484,
+      "step": 15000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005633333333333333,
+      "loss": 0.5483,
+      "step": 15500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00056,
+      "loss": 0.5479,
+      "step": 16000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005566666666666667,
+      "loss": 0.5484,
+      "step": 16500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005533333333333333,
+      "loss": 0.548,
+      "step": 17000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005499999999999999,
+      "loss": 0.548,
+      "step": 17500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005466666666666667,
+      "loss": 0.5479,
+      "step": 18000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005433399999999999,
+      "loss": 0.5479,
+      "step": 18500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0005400066666666666,
+      "loss": 0.5478,
+      "step": 19000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005366733333333333,
+      "loss": 0.5481,
+      "step": 19500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00053334,
+      "loss": 0.5479,
+      "step": 20000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005300133333333333,
+      "loss": 0.5476,
+      "step": 20500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00052668,
+      "loss": 0.5477,
+      "step": 21000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0005233466666666667,
+      "loss": 0.5477,
+      "step": 21500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0005200133333333332,
+      "loss": 0.5476,
+      "step": 22000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005166866666666667,
+      "loss": 0.5477,
+      "step": 22500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005133533333333333,
+      "loss": 0.5476,
+      "step": 23000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005100199999999999,
+      "loss": 0.5476,
+      "step": 23500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005066866666666666,
+      "loss": 0.5476,
+      "step": 24000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005033599999999999,
+      "loss": 0.5475,
+      "step": 24500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0005000266666666666,
+      "loss": 0.5476,
+      "step": 25000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0004966933333333332,
+      "loss": 0.5476,
+      "step": 25500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00049336,
+      "loss": 0.5476,
+      "step": 26000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0004900333333333333,
+      "loss": 0.5475,
+      "step": 26500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00048669999999999996,
+      "loss": 0.5476,
+      "step": 27000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004833666666666666,
+      "loss": 0.5476,
+      "step": 27500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00048003333333333326,
+      "loss": 0.5474,
+      "step": 28000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004767066666666666,
+      "loss": 0.5474,
+      "step": 28500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004733733333333333,
+      "loss": 0.5474,
+      "step": 29000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00047003999999999997,
+      "loss": 0.5475,
+      "step": 29500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046670666666666664,
+      "loss": 0.5474,
+      "step": 30000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046337999999999994,
+      "loss": 0.5475,
+      "step": 30500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0004600466666666666,
+      "loss": 0.5475,
+      "step": 31000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0004567133333333333,
+      "loss": 0.5474,
+      "step": 31500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00045337999999999997,
+      "loss": 0.5474,
+      "step": 32000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00045005333333333333,
+      "loss": 0.5474,
+      "step": 32500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00044672,
+      "loss": 0.5474,
+      "step": 33000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00044338666666666663,
+      "loss": 0.5474,
+      "step": 33500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004400533333333333,
+      "loss": 0.5475,
+      "step": 34000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004367266666666666,
+      "loss": 0.5475,
+      "step": 34500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0004333933333333333,
+      "loss": 0.5474,
+      "step": 35000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00043005999999999996,
+      "loss": 0.5474,
+      "step": 35500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042672666666666663,
+      "loss": 0.5474,
+      "step": 36000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042339999999999994,
+      "loss": 0.5475,
+      "step": 36500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0004200666666666666,
+      "loss": 0.5474,
+      "step": 37000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.00041673333333333334,
+      "loss": 0.5473,
+      "step": 37500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0004133999999999999,
+      "loss": 0.5474,
+      "step": 38000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0004100733333333333,
+      "loss": 0.5475,
+      "step": 38500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00040673999999999994,
+      "loss": 0.5473,
+      "step": 39000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004034066666666666,
+      "loss": 0.5474,
+      "step": 39500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004000733333333333,
+      "loss": 0.5474,
+      "step": 40000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003967466666666666,
+      "loss": 0.5474,
+      "step": 40500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003934133333333333,
+      "loss": 0.5473,
+      "step": 41000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039007999999999995,
+      "loss": 0.5473,
+      "step": 41500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00038674666666666663,
+      "loss": 0.5473,
+      "step": 42000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00038342,
+      "loss": 0.5474,
+      "step": 42500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00038008666666666666,
+      "loss": 0.5473,
+      "step": 43000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00037675333333333334,
+      "loss": 0.5475,
+      "step": 43500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00037341999999999996,
+      "loss": 0.5473,
+      "step": 44000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003700933333333333,
+      "loss": 0.5473,
+      "step": 44500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00036675999999999994,
+      "loss": 0.5474,
+      "step": 45000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003634266666666666,
+      "loss": 0.5473,
+      "step": 45500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003600933333333333,
+      "loss": 0.5473,
+      "step": 46000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00035676666666666665,
+      "loss": 0.5474,
+      "step": 46500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00035343999999999995,
+      "loss": 0.5474,
+      "step": 47000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003501066666666666,
+      "loss": 0.5474,
+      "step": 47500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003467733333333333,
+      "loss": 0.5473,
+      "step": 48000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00034344,
+      "loss": 0.5473,
+      "step": 48500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00034010666666666665,
+      "loss": 0.5473,
+      "step": 49000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003367733333333333,
+      "loss": 0.5474,
+      "step": 49500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00033343999999999995,
+      "loss": 0.5473,
+      "step": 50000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00033010666666666663,
+      "loss": 0.5473,
+      "step": 50500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00032677999999999993,
+      "loss": 0.5473,
+      "step": 51000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003234466666666666,
+      "loss": 0.5474,
+      "step": 51500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00032011333333333334,
+      "loss": 0.5473,
+      "step": 52000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00031678,
+      "loss": 0.5473,
+      "step": 52500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003134533333333333,
+      "loss": 0.5473,
+      "step": 53000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00031012,
+      "loss": 0.5473,
+      "step": 53500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030678666666666667,
+      "loss": 0.5473,
+      "step": 54000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0003034533333333333,
+      "loss": 0.5473,
+      "step": 54500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00030012666666666665,
+      "loss": 0.5474,
+      "step": 55000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002967933333333333,
+      "loss": 0.5473,
+      "step": 55500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029345999999999994,
+      "loss": 0.5474,
+      "step": 56000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002901266666666666,
+      "loss": 0.5474,
+      "step": 56500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002868,
+      "loss": 0.5474,
+      "step": 57000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00028346666666666665,
+      "loss": 0.5473,
+      "step": 57500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00028013333333333333,
+      "loss": 0.5474,
+      "step": 58000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00027679999999999995,
+      "loss": 0.5475,
+      "step": 58500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002734733333333333,
+      "loss": 0.5474,
+      "step": 59000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00027014,
+      "loss": 0.5474,
+      "step": 59500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026680666666666666,
+      "loss": 0.5473,
+      "step": 60000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026347333333333334,
+      "loss": 0.5473,
+      "step": 60500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00026014666666666664,
+      "loss": 0.5473,
+      "step": 61000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002568133333333333,
+      "loss": 0.5475,
+      "step": 61500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00025348,
+      "loss": 0.5475,
+      "step": 62000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00025014666666666667,
+      "loss": 0.5479,
+      "step": 62500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00024681999999999997,
+      "loss": 0.5477,
+      "step": 63000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00024348666666666665,
+      "loss": 0.5478,
+      "step": 63500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002401533333333333,
+      "loss": 0.5478,
+      "step": 64000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00023681999999999997,
+      "loss": 0.5476,
+      "step": 64500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002334933333333333,
+      "loss": 0.5475,
+      "step": 65000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00023015999999999998,
+      "loss": 0.5478,
+      "step": 65500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00022682666666666665,
+      "loss": 0.5478,
+      "step": 66000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002234933333333333,
+      "loss": 0.5478,
+      "step": 66500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022016666666666666,
+      "loss": 0.5478,
+      "step": 67000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002168333333333333,
+      "loss": 0.5477,
+      "step": 67500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00021349999999999999,
+      "loss": 0.5477,
+      "step": 68000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00021016666666666666,
+      "loss": 0.5478,
+      "step": 68500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020684,
+      "loss": 0.5477,
+      "step": 69000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020350666666666667,
+      "loss": 0.5477,
+      "step": 69500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00020017333333333332,
+      "loss": 0.5477,
+      "step": 70000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00019684,
+      "loss": 0.5477,
+      "step": 70500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019351333333333332,
+      "loss": 0.5477,
+      "step": 71000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019018,
+      "loss": 0.5477,
+      "step": 71500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018684666666666667,
+      "loss": 0.5477,
+      "step": 72000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018351333333333332,
+      "loss": 0.5477,
+      "step": 72500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00018018666666666663,
+      "loss": 0.5477,
+      "step": 73000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0001768533333333333,
+      "loss": 0.5477,
+      "step": 73500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017352,
+      "loss": 0.5476,
+      "step": 74000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017018666666666663,
+      "loss": 0.5477,
+      "step": 74500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00016685999999999998,
+      "loss": 0.5477,
+      "step": 75000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016353333333333331,
+      "loss": 0.5476,
+      "step": 75500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0001602,
+      "loss": 0.5476,
+      "step": 76000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015686666666666664,
+      "loss": 0.5476,
+      "step": 76500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015353333333333332,
+      "loss": 0.5477,
+      "step": 77000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.0001502,
+      "loss": 0.5475,
+      "step": 77500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014686666666666667,
+      "loss": 0.5473,
+      "step": 78000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014353333333333332,
+      "loss": 0.5474,
+      "step": 78500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014020666666666667,
+      "loss": 0.5481,
+      "step": 79000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013687333333333332,
+      "loss": 0.548,
+      "step": 79500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013354,
+      "loss": 0.5481,
+      "step": 80000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00013020666666666665,
+      "loss": 0.548,
+      "step": 80500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012687999999999998,
+      "loss": 0.548,
+      "step": 81000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012354666666666665,
+      "loss": 0.5479,
+      "step": 81500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00012021333333333333,
+      "loss": 0.5479,
+      "step": 82000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00011687999999999999,
+      "loss": 0.5479,
+      "step": 82500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011354666666666665,
+      "loss": 0.5478,
+      "step": 83000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011021333333333333,
+      "loss": 0.5475,
+      "step": 83500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010687999999999999,
+      "loss": 0.5473,
+      "step": 84000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010354666666666666,
+      "loss": 0.5473,
+      "step": 84500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00010022,
+      "loss": 0.5473,
+      "step": 85000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 9.688666666666666e-05,
+      "loss": 0.5473,
+      "step": 85500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.355333333333332e-05,
+      "loss": 0.5473,
+      "step": 86000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.022666666666665e-05,
+      "loss": 0.5472,
+      "step": 86500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.69e-05,
+      "loss": 0.5472,
+      "step": 87000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.356666666666666e-05,
+      "loss": 0.5473,
+      "step": 87500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.023333333333332e-05,
+      "loss": 0.5472,
+      "step": 88000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.69e-05,
+      "loss": 0.5472,
+      "step": 88500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.356666666666666e-05,
+      "loss": 0.5472,
+      "step": 89000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.023333333333332e-05,
+      "loss": 0.5472,
+      "step": 89500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.69e-05,
+      "loss": 0.5472,
+      "step": 90000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.356666666666666e-05,
+      "loss": 0.5473,
+      "step": 90500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.024e-05,
+      "loss": 0.5472,
+      "step": 91000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.690666666666666e-05,
+      "loss": 0.5472,
+      "step": 91500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.357333333333333e-05,
+      "loss": 0.5472,
+      "step": 92000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.024e-05,
+      "loss": 0.5472,
+      "step": 92500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.691333333333333e-05,
+      "loss": 0.5472,
+      "step": 93000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.357999999999999e-05,
+      "loss": 0.5472,
+      "step": 93500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.024666666666666e-05,
+      "loss": 0.5472,
+      "step": 94000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.691333333333333e-05,
+      "loss": 0.5472,
+      "step": 94500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.358666666666666e-05,
+      "loss": 0.5472,
+      "step": 95000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.025333333333333e-05,
+      "loss": 0.5472,
+      "step": 95500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.6919999999999996e-05,
+      "loss": 0.5472,
+      "step": 96000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.3586666666666662e-05,
+      "loss": 0.5472,
+      "step": 96500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.026e-05,
+      "loss": 0.5472,
+      "step": 97000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6926666666666665e-05,
+      "loss": 0.5472,
+      "step": 97500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3593333333333332e-05,
+      "loss": 0.5472,
+      "step": 98000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.026e-05,
+      "loss": 0.5471,
+      "step": 98500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.933333333333333e-06,
+      "loss": 0.5472,
+      "step": 99000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.6e-06,
+      "loss": 0.5471,
+      "step": 99500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.6666666666666667e-07,
+      "loss": 0.5472,
+      "step": 100000
+    }
+  ],
+  "max_steps": 100000,
+  "num_train_epochs": 1,
+  "total_flos": 4.202631887940403e+19,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/training_args.bin b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..32bfed89aed5e13492c22cd464e6a8d260086cd9
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/checkpoint-100000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9a1b19f49599700a19dc280892b717e93dc7910bf7e6a33a4d264084e33ba1
+size 2735
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/config.json b/propositional_logic/lt_alm_noreflexivity_nosymmetry/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff8809f9ee0000962c182321c304c5b09e84f1ba
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/config.json
@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/pytorch_model.bin b/propositional_logic/lt_alm_noreflexivity_nosymmetry/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4412048281e2dd6ebef89f9e1ebe6d58e3497880
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f4353422edf337e6431cd9b876ce10a85ed87598959c86c2e3e37b7d59a000e
+size 359700713
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/runs/May18_01-00-49_zhaofengw-vm-1/1652932399.9015605/events.out.tfevents.1652932399.zhaofengw-vm-1.88182.1 b/propositional_logic/lt_alm_noreflexivity_nosymmetry/runs/May18_01-00-49_zhaofengw-vm-1/1652932399.9015605/events.out.tfevents.1652932399.zhaofengw-vm-1.88182.1
new file mode 100644
index 0000000000000000000000000000000000000000..2e9828b5a3337b0287c361737efeeb95751d5ca6
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/runs/May18_01-00-49_zhaofengw-vm-1/1652932399.9015605/events.out.tfevents.1652932399.zhaofengw-vm-1.88182.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daf7741b4f2ff02741e27ca440d13d4ec6759c2dae3ca44a4fc2688e4ba74f34
+size 4395
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/runs/May18_01-00-49_zhaofengw-vm-1/events.out.tfevents.1652932396.zhaofengw-vm-1.88182.0 b/propositional_logic/lt_alm_noreflexivity_nosymmetry/runs/May18_01-00-49_zhaofengw-vm-1/events.out.tfevents.1652932396.zhaofengw-vm-1.88182.0
new file mode 100644
index 0000000000000000000000000000000000000000..a14917fc70464ba3dd07424d763ef2d1ac4f9cec
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/runs/May18_01-00-49_zhaofengw-vm-1/events.out.tfevents.1652932396.zhaofengw-vm-1.88182.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fceb38230df0497588286792ea6fc0e7a04d05c31eb0bf2ed66b6df3a6c9d4f3
+size 35596
diff --git a/propositional_logic/lt_alm_noreflexivity_nosymmetry/training_args.bin b/propositional_logic/lt_alm_noreflexivity_nosymmetry/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..32bfed89aed5e13492c22cd464e6a8d260086cd9
--- /dev/null
+++ b/propositional_logic/lt_alm_noreflexivity_nosymmetry/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef9a1b19f49599700a19dc280892b717e93dc7910bf7e6a33a4d264084e33ba1
+size 2735
diff --git a/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/config.json b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff8809f9ee0000962c182321c304c5b09e84f1ba
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/config.json
@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/optimizer.pt b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..399f21c7e286a9c2f982ee291f4bca5dba1cedd4
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780a53b3bcf77d6a2b64b200f43d88e18c481c72a92b2afaaf256daa8d9cdf4a
+size 694198065
diff --git a/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/pytorch_model.bin b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d1fe8d12bae692227cb2d31392e2cd13f3fc18be
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fd0763cf3d418bd7fbbebbe87a24ea6f917433a1b89ddfbc7cba881a62130f
+size 359700713
diff --git a/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/rng_state.pth b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..db1360b0d46f29967341c303c1ce87509d2c3a64
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f04f0b4d009d10f7eb65f17fa9bd7ab6d4824fdfef3bdaf701fd26a4a4490a43
+size 14503
diff --git a/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/scaler.pt b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f653870e3a339c3a43e2f60fd0320ea0addf8070
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:656f8daee627965f3c20bb09bc52387653e95a8352ccbe2cb42905caa184a9b2
+size 559
diff --git a/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/scheduler.pt b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5cbfcd3c8ca21bc2c76483147b6f1c8652f9e232
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1270c5626b0e62d4fa47ac4c2e42caccce8b5e7b608cbc7f83868d16ed1977
+size 623
diff --git a/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/trainer_state.json b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c23948ca0b6a340dd01deb24cfdf9b922afe1138
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/trainer_state.json
@@ -0,0 +1,1216 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9999999218750061,
+  "global_step": 100000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 1.2997,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 0.6204,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 0.5267,
+      "step": 1500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 0.4277,
+      "step": 2000
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00015,
+      "loss": 0.396,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 0.3923,
+      "step": 3000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 0.3918,
+      "step": 3500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 0.3874,
+      "step": 4000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00027,
+      "loss": 0.3845,
+      "step": 4500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 0.3839,
+      "step": 5000
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.00033,
+      "loss": 0.3841,
+      "step": 5500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00035999999999999997,
+      "loss": 0.3817,
+      "step": 6000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00039,
+      "loss": 0.3811,
+      "step": 6500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00041999999999999996,
+      "loss": 0.3822,
+      "step": 7000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00045,
+      "loss": 0.3797,
+      "step": 7500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00047999999999999996,
+      "loss": 0.3788,
+      "step": 8000
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.0005099999999999999,
+      "loss": 0.3808,
+      "step": 8500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00054,
+      "loss": 0.3806,
+      "step": 9000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00057,
+      "loss": 0.3782,
+      "step": 9500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0006,
+      "loss": 0.3778,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0005966666666666667,
+      "loss": 0.3761,
+      "step": 10500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0005933333333333333,
+      "loss": 0.377,
+      "step": 11000
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0005899999999999999,
+      "loss": 0.3753,
+      "step": 11500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005866666666666665,
+      "loss": 0.3748,
+      "step": 12000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 0.3752,
+      "step": 12500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00058,
+      "loss": 0.3731,
+      "step": 13000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0005766666666666666,
+      "loss": 0.3728,
+      "step": 13500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005733333333333334,
+      "loss": 0.3724,
+      "step": 14000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00057,
+      "loss": 0.372,
+      "step": 14500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005666666666666666,
+      "loss": 0.3721,
+      "step": 15000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005633333333333333,
+      "loss": 0.372,
+      "step": 15500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00056,
+      "loss": 0.3721,
+      "step": 16000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0005566666666666667,
+      "loss": 0.3716,
+      "step": 16500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005533333333333333,
+      "loss": 0.3716,
+      "step": 17000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005499999999999999,
+      "loss": 0.3718,
+      "step": 17500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005466666666666667,
+      "loss": 0.3717,
+      "step": 18000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005433399999999999,
+      "loss": 0.3712,
+      "step": 18500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0005400066666666666,
+      "loss": 0.3714,
+      "step": 19000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0005366733333333333,
+      "loss": 0.3711,
+      "step": 19500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00053334,
+      "loss": 0.3715,
+      "step": 20000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005300133333333333,
+      "loss": 0.3714,
+      "step": 20500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00052668,
+      "loss": 0.3709,
+      "step": 21000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0005233466666666667,
+      "loss": 0.371,
+      "step": 21500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0005200133333333332,
+      "loss": 0.3712,
+      "step": 22000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0005166866666666667,
+      "loss": 0.3711,
+      "step": 22500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005133533333333333,
+      "loss": 0.371,
+      "step": 23000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005100199999999999,
+      "loss": 0.371,
+      "step": 23500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005066866666666666,
+      "loss": 0.3711,
+      "step": 24000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005033599999999999,
+      "loss": 0.3709,
+      "step": 24500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0005000266666666666,
+      "loss": 0.371,
+      "step": 25000
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0004966933333333332,
+      "loss": 0.3709,
+      "step": 25500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.00049336,
+      "loss": 0.371,
+      "step": 26000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0004900333333333333,
+      "loss": 0.3708,
+      "step": 26500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00048669999999999996,
+      "loss": 0.3709,
+      "step": 27000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0004833666666666666,
+      "loss": 0.371,
+      "step": 27500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00048003333333333326,
+      "loss": 0.3709,
+      "step": 28000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004767066666666666,
+      "loss": 0.371,
+      "step": 28500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004733733333333333,
+      "loss": 0.3709,
+      "step": 29000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00047003999999999997,
+      "loss": 0.3708,
+      "step": 29500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046670666666666664,
+      "loss": 0.371,
+      "step": 30000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046337999999999994,
+      "loss": 0.3709,
+      "step": 30500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0004600466666666666,
+      "loss": 0.3709,
+      "step": 31000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0004567133333333333,
+      "loss": 0.3708,
+      "step": 31500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00045337999999999997,
+      "loss": 0.3709,
+      "step": 32000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00045005333333333333,
+      "loss": 0.3709,
+      "step": 32500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00044672,
+      "loss": 0.3708,
+      "step": 33000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00044338666666666663,
+      "loss": 0.3707,
+      "step": 33500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004400533333333333,
+      "loss": 0.3708,
+      "step": 34000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004367266666666666,
+      "loss": 0.3708,
+      "step": 34500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0004333933333333333,
+      "loss": 0.3708,
+      "step": 35000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00043005999999999996,
+      "loss": 0.3707,
+      "step": 35500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042672666666666663,
+      "loss": 0.3708,
+      "step": 36000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042339999999999994,
+      "loss": 0.3707,
+      "step": 36500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.0004200666666666666,
+      "loss": 0.3706,
+      "step": 37000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00041673333333333334,
+      "loss": 0.3708,
+      "step": 37500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0004133999999999999,
+      "loss": 0.3708,
+      "step": 38000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0004100733333333333,
+      "loss": 0.3708,
+      "step": 38500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00040673999999999994,
+      "loss": 0.3708,
+      "step": 39000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0004034066666666666,
+      "loss": 0.3707,
+      "step": 39500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004000733333333333,
+      "loss": 0.3708,
+      "step": 40000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0003967466666666666,
+      "loss": 0.3707,
+      "step": 40500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.0003934133333333333,
+      "loss": 0.3708,
+      "step": 41000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039007999999999995,
+      "loss": 0.3707,
+      "step": 41500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00038674666666666663,
+      "loss": 0.3706,
+      "step": 42000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00038342,
+      "loss": 0.3706,
+      "step": 42500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00038008666666666666,
+      "loss": 0.3709,
+      "step": 43000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.00037675333333333334,
+      "loss": 0.3707,
+      "step": 43500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00037341999999999996,
+      "loss": 0.3708,
+      "step": 44000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0003700933333333333,
+      "loss": 0.3707,
+      "step": 44500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00036675999999999994,
+      "loss": 0.3707,
+      "step": 45000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003634266666666666,
+      "loss": 0.3707,
+      "step": 45500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.0003600933333333333,
+      "loss": 0.3708,
+      "step": 46000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00035676666666666665,
+      "loss": 0.3707,
+      "step": 46500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003534333333333333,
+      "loss": 0.3708,
+      "step": 47000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003501,
+      "loss": 0.3706,
+      "step": 47500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003467666666666667,
+      "loss": 0.3708,
+      "step": 48000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00034344,
+      "loss": 0.3709,
+      "step": 48500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00034010666666666665,
+      "loss": 0.3707,
+      "step": 49000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.0003367733333333333,
+      "loss": 0.3707,
+      "step": 49500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00033343999999999995,
+      "loss": 0.3706,
+      "step": 50000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.00033011333333333325,
+      "loss": 0.3708,
+      "step": 50500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00032677999999999993,
+      "loss": 0.3707,
+      "step": 51000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003234466666666666,
+      "loss": 0.3708,
+      "step": 51500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00032011333333333334,
+      "loss": 0.3706,
+      "step": 52000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.00031678666666666664,
+      "loss": 0.3707,
+      "step": 52500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003134533333333333,
+      "loss": 0.3706,
+      "step": 53000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00031012,
+      "loss": 0.3707,
+      "step": 53500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030678666666666667,
+      "loss": 0.3707,
+      "step": 54000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00030345999999999997,
+      "loss": 0.3707,
+      "step": 54500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00030012666666666665,
+      "loss": 0.3709,
+      "step": 55000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.0002967933333333333,
+      "loss": 0.3708,
+      "step": 55500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029345999999999994,
+      "loss": 0.3707,
+      "step": 56000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002901333333333333,
+      "loss": 0.3709,
+      "step": 56500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.0002868,
+      "loss": 0.3707,
+      "step": 57000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00028347333333333334,
+      "loss": 0.3706,
+      "step": 57500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00028013999999999996,
+      "loss": 0.3708,
+      "step": 58000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00027680666666666663,
+      "loss": 0.3707,
+      "step": 58500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002734733333333333,
+      "loss": 0.3707,
+      "step": 59000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00027014666666666667,
+      "loss": 0.3706,
+      "step": 59500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026681333333333334,
+      "loss": 0.3708,
+      "step": 60000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026347999999999996,
+      "loss": 0.3706,
+      "step": 60500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00026014666666666664,
+      "loss": 0.3706,
+      "step": 61000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.0002568133333333333,
+      "loss": 0.3707,
+      "step": 61500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00025348,
+      "loss": 0.3707,
+      "step": 62000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00025014666666666667,
+      "loss": 0.3709,
+      "step": 62500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002468133333333333,
+      "loss": 0.3708,
+      "step": 63000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.00024348666666666665,
+      "loss": 0.3707,
+      "step": 63500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002401533333333333,
+      "loss": 0.3707,
+      "step": 64000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00023681999999999997,
+      "loss": 0.3707,
+      "step": 64500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002334933333333333,
+      "loss": 0.3706,
+      "step": 65000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00023015999999999998,
+      "loss": 0.3707,
+      "step": 65500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00022682666666666665,
+      "loss": 0.3706,
+      "step": 66000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002234933333333333,
+      "loss": 0.3706,
+      "step": 66500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022016666666666666,
+      "loss": 0.3707,
+      "step": 67000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002168333333333333,
+      "loss": 0.3706,
+      "step": 67500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00021349999999999999,
+      "loss": 0.3707,
+      "step": 68000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00021016666666666666,
+      "loss": 0.3707,
+      "step": 68500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002068333333333333,
+      "loss": 0.3708,
+      "step": 69000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020350666666666667,
+      "loss": 0.3709,
+      "step": 69500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00020017333333333332,
+      "loss": 0.3706,
+      "step": 70000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00019684,
+      "loss": 0.3707,
+      "step": 70500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019350666666666667,
+      "loss": 0.3706,
+      "step": 71000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019018,
+      "loss": 0.3707,
+      "step": 71500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018684666666666667,
+      "loss": 0.3706,
+      "step": 72000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018351333333333332,
+      "loss": 0.3707,
+      "step": 72500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00018018,
+      "loss": 0.3706,
+      "step": 73000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00017684666666666665,
+      "loss": 0.3706,
+      "step": 73500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017352,
+      "loss": 0.3706,
+      "step": 74000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017018666666666663,
+      "loss": 0.3707,
+      "step": 74500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.0001668533333333333,
+      "loss": 0.3707,
+      "step": 75000
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00016352,
+      "loss": 0.3707,
+      "step": 75500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016018666666666663,
+      "loss": 0.3707,
+      "step": 76000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00015685999999999999,
+      "loss": 0.3707,
+      "step": 76500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015352666666666663,
+      "loss": 0.3708,
+      "step": 77000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.0001501933333333333,
+      "loss": 0.3707,
+      "step": 77500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014685999999999999,
+      "loss": 0.3707,
+      "step": 78000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014353333333333332,
+      "loss": 0.3707,
+      "step": 78500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.0001402,
+      "loss": 0.3707,
+      "step": 79000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00013686666666666664,
+      "loss": 0.3707,
+      "step": 79500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013353333333333332,
+      "loss": 0.3707,
+      "step": 80000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.0001302,
+      "loss": 0.3705,
+      "step": 80500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012687333333333332,
+      "loss": 0.3707,
+      "step": 81000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012354,
+      "loss": 0.3707,
+      "step": 81500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00012020666666666665,
+      "loss": 0.3707,
+      "step": 82000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00011687333333333332,
+      "loss": 0.3706,
+      "step": 82500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011354666666666665,
+      "loss": 0.3707,
+      "step": 83000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011021333333333333,
+      "loss": 0.3706,
+      "step": 83500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010687999999999999,
+      "loss": 0.3707,
+      "step": 84000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010354666666666666,
+      "loss": 0.3706,
+      "step": 84500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.00010021333333333332,
+      "loss": 0.3706,
+      "step": 85000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 9.688666666666666e-05,
+      "loss": 0.3707,
+      "step": 85500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.355333333333332e-05,
+      "loss": 0.3706,
+      "step": 86000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.022e-05,
+      "loss": 0.3705,
+      "step": 86500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.688666666666666e-05,
+      "loss": 0.3706,
+      "step": 87000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.355333333333333e-05,
+      "loss": 0.3707,
+      "step": 87500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.022666666666666e-05,
+      "loss": 0.3707,
+      "step": 88000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 7.689333333333332e-05,
+      "loss": 0.3707,
+      "step": 88500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.356e-05,
+      "loss": 0.3706,
+      "step": 89000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.022666666666667e-05,
+      "loss": 0.3707,
+      "step": 89500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.69e-05,
+      "loss": 0.3706,
+      "step": 90000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.356666666666666e-05,
+      "loss": 0.3708,
+      "step": 90500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.0233333333333325e-05,
+      "loss": 0.3707,
+      "step": 91000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 5.69e-05,
+      "loss": 0.3707,
+      "step": 91500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.356666666666666e-05,
+      "loss": 0.3706,
+      "step": 92000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.024e-05,
+      "loss": 0.3707,
+      "step": 92500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.690666666666666e-05,
+      "loss": 0.3707,
+      "step": 93000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.357333333333333e-05,
+      "loss": 0.3707,
+      "step": 93500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.0239999999999994e-05,
+      "loss": 0.3706,
+      "step": 94000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.6906666666666663e-05,
+      "loss": 0.3707,
+      "step": 94500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.3579999999999994e-05,
+      "loss": 0.3706,
+      "step": 95000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.0246666666666663e-05,
+      "loss": 0.3706,
+      "step": 95500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.6913333333333332e-05,
+      "loss": 0.3708,
+      "step": 96000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.3579999999999998e-05,
+      "loss": 0.3706,
+      "step": 96500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.0246666666666664e-05,
+      "loss": 0.3708,
+      "step": 97000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6919999999999997e-05,
+      "loss": 0.3706,
+      "step": 97500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3586666666666665e-05,
+      "loss": 0.3705,
+      "step": 98000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.0253333333333332e-05,
+      "loss": 0.3705,
+      "step": 98500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.919999999999999e-06,
+      "loss": 0.3706,
+      "step": 99000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.593333333333333e-06,
+      "loss": 0.3706,
+      "step": 99500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.5999999999999995e-07,
+      "loss": 0.3706,
+      "step": 100000
+    }
+  ],
+  "max_steps": 100000,
+  "num_train_epochs": 1,
+  "total_flos": 4.279970369205043e+19,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/training_args.bin b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d61ec21f9c74de5c181bef692eafd6efdb12e3eb
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/checkpoint-100000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa664ed90be2484917e9ff73703f8d5d4df0ad7b33379f7a8b34f7a0526e3d0
+size 2735
diff --git a/propositional_logic/lt_alm_nosymmetry/config.json b/propositional_logic/lt_alm_nosymmetry/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..ff8809f9ee0000962c182321c304c5b09e84f1ba
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/config.json
@@ -0,0 +1,37 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/lt_alm_nosymmetry/pytorch_model.bin b/propositional_logic/lt_alm_nosymmetry/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d1fe8d12bae692227cb2d31392e2cd13f3fc18be
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37fd0763cf3d418bd7fbbebbe87a24ea6f917433a1b89ddfbc7cba881a62130f
+size 359700713
diff --git a/propositional_logic/lt_alm_nosymmetry/runs/Aug09_21-06-39_allennlp-server4/1660189990.7456152/events.out.tfevents.1660189990.allennlp-server4.1210921.1 b/propositional_logic/lt_alm_nosymmetry/runs/Aug09_21-06-39_allennlp-server4/1660189990.7456152/events.out.tfevents.1660189990.allennlp-server4.1210921.1
new file mode 100644
index 0000000000000000000000000000000000000000..b2f8a5dd09de7ed3ed6faab2a088ee3331cdbaa8
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/runs/Aug09_21-06-39_allennlp-server4/1660189990.7456152/events.out.tfevents.1660189990.allennlp-server4.1210921.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:675cb4d2c6cf877499a1c42b8ccda5f4c6bee99cbe875447442caa0e9ff53c65
+size 4441
diff --git a/propositional_logic/lt_alm_nosymmetry/runs/Aug09_21-06-39_allennlp-server4/events.out.tfevents.1660189984.allennlp-server4.1210921.0 b/propositional_logic/lt_alm_nosymmetry/runs/Aug09_21-06-39_allennlp-server4/events.out.tfevents.1660189984.allennlp-server4.1210921.0
new file mode 100644
index 0000000000000000000000000000000000000000..475e6c500f7db7fd13b315f0c40a43b44f014384
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/runs/Aug09_21-06-39_allennlp-server4/events.out.tfevents.1660189984.allennlp-server4.1210921.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c941a6b8664320179dc6097f71fd86daf0b9ce0a186b33245d3db88bb087372b
+size 35642
diff --git a/propositional_logic/lt_alm_nosymmetry/training_args.bin b/propositional_logic/lt_alm_nosymmetry/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d61ec21f9c74de5c181bef692eafd6efdb12e3eb
--- /dev/null
+++ b/propositional_logic/lt_alm_nosymmetry/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fa664ed90be2484917e9ff73703f8d5d4df0ad7b33379f7a8b34f7a0526e3d0
+size 2735
diff --git a/propositional_logic/lt_mlm/checkpoint-100000/config.json b/propositional_logic/lt_mlm/checkpoint-100000/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..102fa0515a2e7f9a348f86a1dcb7d135d6cfa8c6
--- /dev/null
+++ b/propositional_logic/lt_mlm/checkpoint-100000/config.json
@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/lt_mlm/checkpoint-100000/optimizer.pt b/propositional_logic/lt_mlm/checkpoint-100000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0f4a2dd0ad72c7c255fb56be72cf914d30478d2f
--- /dev/null
+++ b/propositional_logic/lt_mlm/checkpoint-100000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7984f845fb9635b528ee15befc0abe4cf4e24319efe16541d9dba9c330008e3e
+size 695849113
diff --git a/propositional_logic/lt_mlm/checkpoint-100000/pytorch_model.bin b/propositional_logic/lt_mlm/checkpoint-100000/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..429948f73d4102f926a1455b98d19f197736281d
--- /dev/null
+++ b/propositional_logic/lt_mlm/checkpoint-100000/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f23111770b8a777a22ecb76287021a193552ce1614742744e911970c7e51751
+size 347937771
diff --git a/propositional_logic/lt_mlm/checkpoint-100000/rng_state.pth b/propositional_logic/lt_mlm/checkpoint-100000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..4a3150d29fa8c09ae8334d72c8db783e38d463a0
--- /dev/null
+++ b/propositional_logic/lt_mlm/checkpoint-100000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ace806f1cf6b8fea340c8dcb0738206e80dd48ed2f8e8fdeb7d956fbc92c63b
+size 14503
diff --git a/propositional_logic/lt_mlm/checkpoint-100000/scaler.pt b/propositional_logic/lt_mlm/checkpoint-100000/scaler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..3149e8d1aa3683f7ad4902a718e70fbcbc0a4105
--- /dev/null
+++ b/propositional_logic/lt_mlm/checkpoint-100000/scaler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eaf42f90c719c5e8e25b899abaf67f6cdff129bbeceed648e90c2d5b22d73400
+size 559
diff --git a/propositional_logic/lt_mlm/checkpoint-100000/scheduler.pt b/propositional_logic/lt_mlm/checkpoint-100000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..fce4e115e566b7e0e0bab426d064c559a4ace555
--- /dev/null
+++ b/propositional_logic/lt_mlm/checkpoint-100000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa032dacd66db7654b168dca5b484fbe4877894e335431edca5660559a893ab0
+size 623
diff --git a/propositional_logic/lt_mlm/checkpoint-100000/trainer_state.json b/propositional_logic/lt_mlm/checkpoint-100000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..75cbbda0c6f65f266ad54840ff076e95b32770e2
--- /dev/null
+++ b/propositional_logic/lt_mlm/checkpoint-100000/trainer_state.json
@@ -0,0 +1,1216 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 100000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 2.9999999999999997e-05,
+      "loss": 2.2066,
+      "step": 500
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 5.9999999999999995e-05,
+      "loss": 1.5564,
+      "step": 1000
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 8.999999999999999e-05,
+      "loss": 1.5224,
+      "step": 1500
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 0.00011999999999999999,
+      "loss": 1.4586,
+      "step": 2000
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00015,
+      "loss": 1.3594,
+      "step": 2500
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.00017999999999999998,
+      "loss": 1.3323,
+      "step": 3000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00020999999999999998,
+      "loss": 1.3147,
+      "step": 3500
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00023999999999999998,
+      "loss": 1.2778,
+      "step": 4000
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.00027,
+      "loss": 1.2596,
+      "step": 4500
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 0.0003,
+      "loss": 1.2521,
+      "step": 5000
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00033,
+      "loss": 1.2477,
+      "step": 5500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00035999999999999997,
+      "loss": 1.245,
+      "step": 6000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00039,
+      "loss": 1.2433,
+      "step": 6500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00041999999999999996,
+      "loss": 1.2422,
+      "step": 7000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.00045,
+      "loss": 1.2404,
+      "step": 7500
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 0.00047999999999999996,
+      "loss": 1.2397,
+      "step": 8000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.0005099999999999999,
+      "loss": 1.2385,
+      "step": 8500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00054,
+      "loss": 1.2378,
+      "step": 9000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.00057,
+      "loss": 1.2379,
+      "step": 9500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0006,
+      "loss": 1.2372,
+      "step": 10000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0005966666666666667,
+      "loss": 1.2359,
+      "step": 10500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.0005933333333333333,
+      "loss": 1.2361,
+      "step": 11000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005899999999999999,
+      "loss": 1.2339,
+      "step": 11500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005866666666666665,
+      "loss": 1.2344,
+      "step": 12000
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0005833333333333333,
+      "loss": 1.233,
+      "step": 12500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00058,
+      "loss": 1.2328,
+      "step": 13000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005766666666666666,
+      "loss": 1.2321,
+      "step": 13500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.0005733333333333334,
+      "loss": 1.2309,
+      "step": 14000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 0.00057,
+      "loss": 1.2315,
+      "step": 14500
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005666666666666666,
+      "loss": 1.2301,
+      "step": 15000
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0005633333333333333,
+      "loss": 1.2305,
+      "step": 15500
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.00056,
+      "loss": 1.2297,
+      "step": 16000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005566799999999999,
+      "loss": 1.2307,
+      "step": 16500
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005533466666666666,
+      "loss": 1.2295,
+      "step": 17000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0005500133333333333,
+      "loss": 1.2301,
+      "step": 17500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005466799999999999,
+      "loss": 1.2282,
+      "step": 18000
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0005433466666666666,
+      "loss": 1.2287,
+      "step": 18500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0005400133333333333,
+      "loss": 1.2283,
+      "step": 19000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005366799999999999,
+      "loss": 1.2284,
+      "step": 19500
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0005333533333333332,
+      "loss": 1.2286,
+      "step": 20000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.00053002,
+      "loss": 1.2283,
+      "step": 20500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0005266866666666666,
+      "loss": 1.2273,
+      "step": 21000
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.0005233533333333333,
+      "loss": 1.2272,
+      "step": 21500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0005200199999999999,
+      "loss": 1.2275,
+      "step": 22000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005166866666666667,
+      "loss": 1.2274,
+      "step": 22500
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005133533333333333,
+      "loss": 1.2275,
+      "step": 23000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 0.0005100199999999999,
+      "loss": 1.2272,
+      "step": 23500
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005066933333333333,
+      "loss": 1.2272,
+      "step": 24000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0005033599999999999,
+      "loss": 1.2266,
+      "step": 24500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0005000266666666666,
+      "loss": 1.2264,
+      "step": 25000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0004966933333333332,
+      "loss": 1.2262,
+      "step": 25500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0004933666666666666,
+      "loss": 1.2264,
+      "step": 26000
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.0004900333333333333,
+      "loss": 1.2267,
+      "step": 26500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00048669999999999996,
+      "loss": 1.2261,
+      "step": 27000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004833666666666666,
+      "loss": 1.2268,
+      "step": 27500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.00048004,
+      "loss": 1.2264,
+      "step": 28000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0004767066666666666,
+      "loss": 1.226,
+      "step": 28500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0004733733333333333,
+      "loss": 1.2259,
+      "step": 29000
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.00047003999999999997,
+      "loss": 1.2259,
+      "step": 29500
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046671333333333327,
+      "loss": 1.2259,
+      "step": 30000
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.00046337999999999994,
+      "loss": 1.2262,
+      "step": 30500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0004600466666666666,
+      "loss": 1.2257,
+      "step": 31000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0004567133333333333,
+      "loss": 1.2259,
+      "step": 31500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.00045337999999999997,
+      "loss": 1.2258,
+      "step": 32000
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00045005333333333333,
+      "loss": 1.2253,
+      "step": 32500
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00044672,
+      "loss": 1.2258,
+      "step": 33000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00044338666666666663,
+      "loss": 1.2256,
+      "step": 33500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0004400533333333333,
+      "loss": 1.2255,
+      "step": 34000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00043672,
+      "loss": 1.2249,
+      "step": 34500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.0004333933333333333,
+      "loss": 1.2253,
+      "step": 35000
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 0.00043005999999999996,
+      "loss": 1.225,
+      "step": 35500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00042672666666666663,
+      "loss": 1.2247,
+      "step": 36000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.0004233933333333333,
+      "loss": 1.2252,
+      "step": 36500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00042005999999999993,
+      "loss": 1.2248,
+      "step": 37000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0004167266666666666,
+      "loss": 1.2253,
+      "step": 37500
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 0.0004133933333333333,
+      "loss": 1.2249,
+      "step": 38000
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00041005999999999996,
+      "loss": 1.2246,
+      "step": 38500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00040673333333333326,
+      "loss": 1.2249,
+      "step": 39000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004034066666666666,
+      "loss": 1.2251,
+      "step": 39500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0004000733333333333,
+      "loss": 1.225,
+      "step": 40000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039673999999999997,
+      "loss": 1.2252,
+      "step": 40500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039340666666666665,
+      "loss": 1.2244,
+      "step": 41000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 0.00039007999999999995,
+      "loss": 1.2243,
+      "step": 41500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00038674666666666663,
+      "loss": 1.2246,
+      "step": 42000
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.0003834133333333333,
+      "loss": 1.2245,
+      "step": 42500
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003800799999999999,
+      "loss": 1.2243,
+      "step": 43000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0003767466666666666,
+      "loss": 1.2244,
+      "step": 43500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.00037341999999999996,
+      "loss": 1.2247,
+      "step": 44000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00037008666666666663,
+      "loss": 1.2241,
+      "step": 44500
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.0003667533333333333,
+      "loss": 1.2242,
+      "step": 45000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00036342,
+      "loss": 1.2246,
+      "step": 45500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00036008666666666666,
+      "loss": 1.2239,
+      "step": 46000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.0003567533333333333,
+      "loss": 1.224,
+      "step": 46500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00035341999999999996,
+      "loss": 1.224,
+      "step": 47000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 0.00035009333333333326,
+      "loss": 1.2238,
+      "step": 47500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00034675999999999994,
+      "loss": 1.2238,
+      "step": 48000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.0003434266666666666,
+      "loss": 1.2242,
+      "step": 48500
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00034009999999999997,
+      "loss": 1.2238,
+      "step": 49000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00033676666666666665,
+      "loss": 1.2236,
+      "step": 49500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 0.0003334333333333333,
+      "loss": 1.224,
+      "step": 50000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003301,
+      "loss": 1.2239,
+      "step": 50500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.0003267666666666667,
+      "loss": 1.2238,
+      "step": 51000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003234333333333333,
+      "loss": 1.2235,
+      "step": 51500
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0003201,
+      "loss": 1.2233,
+      "step": 52000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.00031676666666666665,
+      "loss": 1.2242,
+      "step": 52500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 0.0003134333333333333,
+      "loss": 1.223,
+      "step": 53000
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00031010666666666663,
+      "loss": 1.2236,
+      "step": 53500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0003067733333333333,
+      "loss": 1.2234,
+      "step": 54000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00030344,
+      "loss": 1.2232,
+      "step": 54500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00030010666666666666,
+      "loss": 1.2235,
+      "step": 55000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029677999999999996,
+      "loss": 1.2234,
+      "step": 55500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.00029344666666666664,
+      "loss": 1.2232,
+      "step": 56000
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 0.0002901133333333333,
+      "loss": 1.2233,
+      "step": 56500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00028678,
+      "loss": 1.223,
+      "step": 57000
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00028345333333333335,
+      "loss": 1.223,
+      "step": 57500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00028011999999999997,
+      "loss": 1.2232,
+      "step": 58000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00027678666666666664,
+      "loss": 1.2229,
+      "step": 58500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0002734533333333333,
+      "loss": 1.223,
+      "step": 59000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.00027012,
+      "loss": 1.2234,
+      "step": 59500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.0002667933333333333,
+      "loss": 1.223,
+      "step": 60000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00026346,
+      "loss": 1.2227,
+      "step": 60500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00026012666666666665,
+      "loss": 1.2229,
+      "step": 61000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 0.00025679333333333327,
+      "loss": 1.2226,
+      "step": 61500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.00025346666666666663,
+      "loss": 1.2228,
+      "step": 62000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 0.0002501333333333333,
+      "loss": 1.2225,
+      "step": 62500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 0.0002468,
+      "loss": 1.2222,
+      "step": 63000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.00024346666666666666,
+      "loss": 1.2223,
+      "step": 63500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 0.0002401333333333333,
+      "loss": 1.2225,
+      "step": 64000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00023680666666666666,
+      "loss": 1.2225,
+      "step": 64500
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.0002334733333333333,
+      "loss": 1.222,
+      "step": 65000
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00023014,
+      "loss": 1.2215,
+      "step": 65500
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.00022680666666666666,
+      "loss": 1.2218,
+      "step": 66000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022348,
+      "loss": 1.2219,
+      "step": 66500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.00022014666666666667,
+      "loss": 1.2217,
+      "step": 67000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.0002168133333333333,
+      "loss": 1.2214,
+      "step": 67500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.00021348,
+      "loss": 1.2215,
+      "step": 68000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.0002101533333333333,
+      "loss": 1.2215,
+      "step": 68500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020681999999999997,
+      "loss": 1.2212,
+      "step": 69000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 0.00020348666666666668,
+      "loss": 1.2211,
+      "step": 69500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.0002001533333333333,
+      "loss": 1.2213,
+      "step": 70000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 0.00019681999999999998,
+      "loss": 1.221,
+      "step": 70500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.0001934933333333333,
+      "loss": 1.2211,
+      "step": 71000
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 0.00019015999999999998,
+      "loss": 1.2207,
+      "step": 71500
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.00018682666666666663,
+      "loss": 1.2211,
+      "step": 72000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 0.0001834933333333333,
+      "loss": 1.221,
+      "step": 72500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.00018016666666666664,
+      "loss": 1.2208,
+      "step": 73000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0001768333333333333,
+      "loss": 1.2208,
+      "step": 73500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.0001735,
+      "loss": 1.2207,
+      "step": 74000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 0.00017016666666666664,
+      "loss": 1.2207,
+      "step": 74500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 0.00016684,
+      "loss": 1.2206,
+      "step": 75000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016350666666666664,
+      "loss": 1.2207,
+      "step": 75500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.00016017333333333332,
+      "loss": 1.2207,
+      "step": 76000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015684,
+      "loss": 1.2209,
+      "step": 76500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 0.00015350666666666664,
+      "loss": 1.2205,
+      "step": 77000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00015018,
+      "loss": 1.2208,
+      "step": 77500
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 0.00014684666666666665,
+      "loss": 1.2207,
+      "step": 78000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014351333333333333,
+      "loss": 1.2204,
+      "step": 78500
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 0.00014017999999999998,
+      "loss": 1.2204,
+      "step": 79000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013685333333333333,
+      "loss": 1.2202,
+      "step": 79500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 0.00013351999999999998,
+      "loss": 1.2203,
+      "step": 80000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00013018666666666666,
+      "loss": 1.2203,
+      "step": 80500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012685333333333333,
+      "loss": 1.2204,
+      "step": 81000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.00012352666666666666,
+      "loss": 1.2203,
+      "step": 81500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00012019333333333333,
+      "loss": 1.2201,
+      "step": 82000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 0.00011685999999999999,
+      "loss": 1.2199,
+      "step": 82500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011352666666666665,
+      "loss": 1.2201,
+      "step": 83000
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 0.00011019333333333331,
+      "loss": 1.2199,
+      "step": 83500
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010686666666666666,
+      "loss": 1.2199,
+      "step": 84000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 0.00010353333333333332,
+      "loss": 1.22,
+      "step": 84500
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 0.0001002,
+      "loss": 1.2201,
+      "step": 85000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 9.686666666666666e-05,
+      "loss": 1.2201,
+      "step": 85500
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.353333333333332e-05,
+      "loss": 1.22,
+      "step": 86000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 9.02e-05,
+      "loss": 1.2199,
+      "step": 86500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 8.686666666666666e-05,
+      "loss": 1.2198,
+      "step": 87000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.353333333333332e-05,
+      "loss": 1.2198,
+      "step": 87500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 8.020666666666667e-05,
+      "loss": 1.2196,
+      "step": 88000
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.687333333333333e-05,
+      "loss": 1.2199,
+      "step": 88500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 7.353999999999999e-05,
+      "loss": 1.2198,
+      "step": 89000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 7.020666666666665e-05,
+      "loss": 1.2196,
+      "step": 89500
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 6.688e-05,
+      "loss": 1.2195,
+      "step": 90000
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.354666666666666e-05,
+      "loss": 1.2196,
+      "step": 90500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.021333333333333e-05,
+      "loss": 1.2194,
+      "step": 91000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.687999999999999e-05,
+      "loss": 1.2196,
+      "step": 91500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 5.3553333333333334e-05,
+      "loss": 1.2194,
+      "step": 92000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 5.022e-05,
+      "loss": 1.2194,
+      "step": 92500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.6886666666666666e-05,
+      "loss": 1.2193,
+      "step": 93000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.355333333333333e-05,
+      "loss": 1.219,
+      "step": 93500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.0226666666666666e-05,
+      "loss": 1.2193,
+      "step": 94000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.6893333333333335e-05,
+      "loss": 1.2193,
+      "step": 94500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.356e-05,
+      "loss": 1.2194,
+      "step": 95000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 3.0226666666666663e-05,
+      "loss": 1.2192,
+      "step": 95500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.69e-05,
+      "loss": 1.2192,
+      "step": 96000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2.3566666666666666e-05,
+      "loss": 1.2192,
+      "step": 96500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 2.023333333333333e-05,
+      "loss": 1.2191,
+      "step": 97000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6899999999999997e-05,
+      "loss": 1.2189,
+      "step": 97500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.3573333333333331e-05,
+      "loss": 1.2191,
+      "step": 98000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 1.024e-05,
+      "loss": 1.219,
+      "step": 98500
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 6.906666666666666e-06,
+      "loss": 1.2192,
+      "step": 99000
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 3.573333333333333e-06,
+      "loss": 1.2192,
+      "step": 99500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.4666666666666665e-07,
+      "loss": 1.2192,
+      "step": 100000
+    }
+  ],
+  "max_steps": 100000,
+  "num_train_epochs": 1,
+  "total_flos": 4.3042507367689535e+19,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/propositional_logic/lt_mlm/checkpoint-100000/training_args.bin b/propositional_logic/lt_mlm/checkpoint-100000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3a3714d22119f3e9c3715a628a0f0b38ff19395f
--- /dev/null
+++ b/propositional_logic/lt_mlm/checkpoint-100000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8977891f234daea77e0d92d656616105cf1eae06c0ba8268d5dfbb09c99054ff
+size 2735
diff --git a/propositional_logic/lt_mlm/config.json b/propositional_logic/lt_mlm/config.json
new file mode 100644
index 0000000000000000000000000000000000000000..102fa0515a2e7f9a348f86a1dcb7d135d6cfa8c6
--- /dev/null
+++ b/propositional_logic/lt_mlm/config.json
@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.10.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 1200
+}
diff --git a/propositional_logic/lt_mlm/pytorch_model.bin b/propositional_logic/lt_mlm/pytorch_model.bin
new file mode 100644
index 0000000000000000000000000000000000000000..429948f73d4102f926a1455b98d19f197736281d
--- /dev/null
+++ b/propositional_logic/lt_mlm/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f23111770b8a777a22ecb76287021a193552ce1614742744e911970c7e51751
+size 347937771
diff --git a/propositional_logic/lt_mlm/runs/Mar11_06-48-33_allennlp-server4/1647095768.8678484/events.out.tfevents.1647095768.allennlp-server4.29741.1 b/propositional_logic/lt_mlm/runs/Mar11_06-48-33_allennlp-server4/1647095768.8678484/events.out.tfevents.1647095768.allennlp-server4.29741.1
new file mode 100644
index 0000000000000000000000000000000000000000..a2609bc24d55f4568b8ed7e0d28c3761a1b95aaf
--- /dev/null
+++ b/propositional_logic/lt_mlm/runs/Mar11_06-48-33_allennlp-server4/1647095768.8678484/events.out.tfevents.1647095768.allennlp-server4.29741.1
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5063100fa937e6bd565c5f870e693cf84533d0517a96d53cb66dd2f683b84d8d
+size 4441
diff --git a/propositional_logic/lt_mlm/runs/Mar11_06-48-33_allennlp-server4/events.out.tfevents.1647095757.allennlp-server4.29741.0 b/propositional_logic/lt_mlm/runs/Mar11_06-48-33_allennlp-server4/events.out.tfevents.1647095757.allennlp-server4.29741.0
new file mode 100644
index 0000000000000000000000000000000000000000..23310bf7aa1595371f423ee2b2c9d05275679e75
--- /dev/null
+++ b/propositional_logic/lt_mlm/runs/Mar11_06-48-33_allennlp-server4/events.out.tfevents.1647095757.allennlp-server4.29741.0
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:557d054d08ab35fe65940752d001e591dd5c80d669d4dd1f4ec9ec3e24afba39
+size 35479
diff --git a/propositional_logic/lt_mlm/training_args.bin b/propositional_logic/lt_mlm/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..3a3714d22119f3e9c3715a628a0f0b38ff19395f
--- /dev/null
+++ b/propositional_logic/lt_mlm/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8977891f234daea77e0d92d656616105cf1eae06c0ba8268d5dfbb09c99054ff
+size 2735