Training in progress, step 620000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eec3868da233996b1dca4bf1cb09b5b2ffd1c4a958ecc59e4b82425f78ddef43
+oid sha256:f902a0072d31f63b96927b6a6d51b56be111838845c62df2a4b9cbba3e56aec6
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30693ace0d2956b7e113ad396e1aa14e2b72f02cf98fd1f2b4183fa6aec48af3
+oid sha256:cd5261e1974ad45164fe18686543155fd69b03009a425c734e5f5a744490a226
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdbd6f069207b6a5e0cacc85e6677e399c9463922f16c7a1b9e54b0ce635a16e
+oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdbd6f069207b6a5e0cacc85e6677e399c9463922f16c7a1b9e54b0ce635a16e
+oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdbd6f069207b6a5e0cacc85e6677e399c9463922f16c7a1b9e54b0ce635a16e
+oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdbd6f069207b6a5e0cacc85e6677e399c9463922f16c7a1b9e54b0ce635a16e
+oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdbd6f069207b6a5e0cacc85e6677e399c9463922f16c7a1b9e54b0ce635a16e
+oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdbd6f069207b6a5e0cacc85e6677e399c9463922f16c7a1b9e54b0ce635a16e
+oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdbd6f069207b6a5e0cacc85e6677e399c9463922f16c7a1b9e54b0ce635a16e
+oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdbd6f069207b6a5e0cacc85e6677e399c9463922f16c7a1b9e54b0ce635a16e
+oid sha256:e37040ab33982f6d1312ce35ee66415b5fb51e1c104e02428f2187d6ddef02e5
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71de57969ec7a3201bd7bf6de3d6e1584c8439f398aacc61865ba691cc2653d6
+oid sha256:87df12c543e6333a1257623848db6de543e5639171e7cc03225528d064da559b
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.446114896891695,
-  "global_step": 610000,
+  "epoch": 6.557643621114618,
+  "global_step": 620000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12206,11 +12206,211 @@
       "eval_samples_per_second": 909.494,
       "eval_steps_per_second": 14.254,
       "step": 610000
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 6.047062257725395e-05,
+      "loss": 0.2011,
+      "step": 610500
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 6.035950216040917e-05,
+      "loss": 0.2014,
+      "step": 611000
+    },
+    {
+      "epoch": 6.46,
+      "eval_loss": 0.19371135532855988,
+      "eval_runtime": 2.5383,
+      "eval_samples_per_second": 904.933,
+      "eval_steps_per_second": 14.183,
+      "step": 611000
+    },
+    {
+      "epoch": 6.46,
+      "learning_rate": 6.0248435439935516e-05,
+      "loss": 0.2018,
+      "step": 611500
+    },
+    {
+      "epoch": 6.47,
+      "learning_rate": 6.0137422719485145e-05,
+      "loss": 0.2009,
+      "step": 612000
+    },
+    {
+      "epoch": 6.47,
+      "eval_loss": 0.18979497253894806,
+      "eval_runtime": 2.61,
+      "eval_samples_per_second": 880.076,
+      "eval_steps_per_second": 13.793,
+      "step": 612000
+    },
+    {
+      "epoch": 6.47,
+      "learning_rate": 6.0026464302562636e-05,
+      "loss": 0.2009,
+      "step": 612500
+    },
+    {
+      "epoch": 6.48,
+      "learning_rate": 5.991556049252401e-05,
+      "loss": 0.2012,
+      "step": 613000
+    },
+    {
+      "epoch": 6.48,
+      "eval_loss": 0.19082209467887878,
+      "eval_runtime": 2.5296,
+      "eval_samples_per_second": 908.057,
+      "eval_steps_per_second": 14.232,
+      "step": 613000
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 5.980471159257609e-05,
+      "loss": 0.2015,
+      "step": 613500
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 5.969391790577551e-05,
+      "loss": 0.201,
+      "step": 614000
+    },
+    {
+      "epoch": 6.49,
+      "eval_loss": 0.19177234172821045,
+      "eval_runtime": 2.4578,
+      "eval_samples_per_second": 934.56,
+      "eval_steps_per_second": 14.647,
+      "step": 614000
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 5.958317973502798e-05,
+      "loss": 0.2009,
+      "step": 614500
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 5.947249738308747e-05,
+      "loss": 0.2009,
+      "step": 615000
+    },
+    {
+      "epoch": 6.5,
+      "eval_loss": 0.18852779269218445,
+      "eval_runtime": 2.5225,
+      "eval_samples_per_second": 910.6,
+      "eval_steps_per_second": 14.271,
+      "step": 615000
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 5.9361871152555254e-05,
+      "loss": 0.2008,
+      "step": 615500
+    },
+    {
+      "epoch": 6.51,
+      "learning_rate": 5.925130134587924e-05,
+      "loss": 0.2007,
+      "step": 616000
+    },
+    {
+      "epoch": 6.51,
+      "eval_loss": 0.18964450061321259,
+      "eval_runtime": 2.6115,
+      "eval_samples_per_second": 879.56,
+      "eval_steps_per_second": 13.785,
+      "step": 616000
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 5.914078826535307e-05,
+      "loss": 0.2009,
+      "step": 616500
+    },
+    {
+      "epoch": 6.52,
+      "learning_rate": 5.903033221311528e-05,
+      "loss": 0.2005,
+      "step": 617000
+    },
+    {
+      "epoch": 6.52,
+      "eval_loss": 0.19303825497627258,
+      "eval_runtime": 2.4819,
+      "eval_samples_per_second": 925.494,
+      "eval_steps_per_second": 14.505,
+      "step": 617000
+    },
+    {
+      "epoch": 6.53,
+      "learning_rate": 5.891993349114847e-05,
+      "loss": 0.201,
+      "step": 617500
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 5.880959240127858e-05,
+      "loss": 0.2008,
+      "step": 618000
+    },
+    {
+      "epoch": 6.54,
+      "eval_loss": 0.1906815767288208,
+      "eval_runtime": 2.5316,
+      "eval_samples_per_second": 907.334,
+      "eval_steps_per_second": 14.22,
+      "step": 618000
+    },
+    {
+      "epoch": 6.54,
+      "learning_rate": 5.86993092451739e-05,
+      "loss": 0.2005,
+      "step": 618500
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 5.858908432434438e-05,
+      "loss": 0.2002,
+      "step": 619000
+    },
+    {
+      "epoch": 6.55,
+      "eval_loss": 0.18906356394290924,
+      "eval_runtime": 2.5512,
+      "eval_samples_per_second": 900.346,
+      "eval_steps_per_second": 14.111,
+      "step": 619000
+    },
+    {
+      "epoch": 6.55,
+      "learning_rate": 5.847891794014074e-05,
+      "loss": 0.2007,
+      "step": 619500
+    },
+    {
+      "epoch": 6.56,
+      "learning_rate": 5.8368810393753684e-05,
+      "loss": 0.2003,
+      "step": 620000
+    },
+    {
+      "epoch": 6.56,
+      "eval_loss": 0.19198235869407654,
+      "eval_runtime": 2.5115,
+      "eval_samples_per_second": 914.603,
+      "eval_steps_per_second": 14.334,
+      "step": 620000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 4.276083064166082e+22,
+  "total_flos": 4.346183325196429e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30693ace0d2956b7e113ad396e1aa14e2b72f02cf98fd1f2b4183fa6aec48af3
+oid sha256:cd5261e1974ad45164fe18686543155fd69b03009a425c734e5f5a744490a226
 size 449471589