Training in progress, step 650000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:625d8a0012f84980eea15c97c7df03c49dfa5fc6015e7fcaa016eb1b27ab5685
+oid sha256:5b254973e04f78692edaf0ebc674dcd6a1f6c1c033dec892e0999288c6c7fbd3
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a384a8675e00c8c913ad9984a62d855b944319fd0302d5aeb3e2d99f3e8e335
+oid sha256:3d09118465ef0159b7efd2eee2688641c444f8ba8f4010b2ee8866772ea196af
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
+oid sha256:45718bf8c484c661f76e2ae60034e83eb407a1a65a3e9a77feee084fc1e3399f
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
+oid sha256:45718bf8c484c661f76e2ae60034e83eb407a1a65a3e9a77feee084fc1e3399f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
+oid sha256:45718bf8c484c661f76e2ae60034e83eb407a1a65a3e9a77feee084fc1e3399f
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
+oid sha256:45718bf8c484c661f76e2ae60034e83eb407a1a65a3e9a77feee084fc1e3399f
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
+oid sha256:45718bf8c484c661f76e2ae60034e83eb407a1a65a3e9a77feee084fc1e3399f
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
+oid sha256:45718bf8c484c661f76e2ae60034e83eb407a1a65a3e9a77feee084fc1e3399f
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
+oid sha256:45718bf8c484c661f76e2ae60034e83eb407a1a65a3e9a77feee084fc1e3399f
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65f68d3cd45e110417fc415ca02d5ecabffe718dd4e6856c7d2a0556a6509e8b
+oid sha256:45718bf8c484c661f76e2ae60034e83eb407a1a65a3e9a77feee084fc1e3399f
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ba925316c6e59686c34db192a6703d2b94be7f6c9b908cf313be2f93b23828d
+oid sha256:b544465929a51046e9a52e629bd463b9098d69ff8cc60ad2e18003214dae8858
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.7807010695604655,
-  "global_step": 640000,
+  "epoch": 6.892229793783389,
+  "global_step": 650000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -12806,11 +12806,211 @@
       "eval_samples_per_second": 886.813,
       "eval_steps_per_second": 13.899,
       "step": 640000
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 5.390875461869379e-05,
+      "loss": 0.1994,
+      "step": 640500
+    },
+    {
+      "epoch": 6.79,
+      "learning_rate": 5.3801387994131576e-05,
+      "loss": 0.1988,
+      "step": 641000
+    },
+    {
+      "epoch": 6.79,
+      "eval_loss": 0.1891511082649231,
+      "eval_runtime": 2.5529,
+      "eval_samples_per_second": 899.746,
+      "eval_steps_per_second": 14.101,
+      "step": 641000
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 5.36940929955742e-05,
+      "loss": 0.1984,
+      "step": 641500
+    },
+    {
+      "epoch": 6.8,
+      "learning_rate": 5.358686991636209e-05,
+      "loss": 0.1986,
+      "step": 642000
+    },
+    {
+      "epoch": 6.8,
+      "eval_loss": 0.1878819614648819,
+      "eval_runtime": 2.5682,
+      "eval_samples_per_second": 894.392,
+      "eval_steps_per_second": 14.017,
+      "step": 642000
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 5.347971904963904e-05,
+      "loss": 0.1984,
+      "step": 642500
+    },
+    {
+      "epoch": 6.81,
+      "learning_rate": 5.3372640688351476e-05,
+      "loss": 0.1988,
+      "step": 643000
+    },
+    {
+      "epoch": 6.81,
+      "eval_loss": 0.18957975506782532,
+      "eval_runtime": 2.5593,
+      "eval_samples_per_second": 897.526,
+      "eval_steps_per_second": 14.067,
+      "step": 643000
+    },
+    {
+      "epoch": 6.82,
+      "learning_rate": 5.326563512524748e-05,
+      "loss": 0.1984,
+      "step": 643500
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 5.315870265287618e-05,
+      "loss": 0.1985,
+      "step": 644000
+    },
+    {
+      "epoch": 6.83,
+      "eval_loss": 0.18896985054016113,
+      "eval_runtime": 2.5541,
+      "eval_samples_per_second": 899.348,
+      "eval_steps_per_second": 14.095,
+      "step": 644000
+    },
+    {
+      "epoch": 6.83,
+      "learning_rate": 5.3051843563586914e-05,
+      "loss": 0.1985,
+      "step": 644500
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 5.294505814952835e-05,
+      "loss": 0.1981,
+      "step": 645000
+    },
+    {
+      "epoch": 6.84,
+      "eval_loss": 0.18807749450206757,
+      "eval_runtime": 2.6155,
+      "eval_samples_per_second": 878.24,
+      "eval_steps_per_second": 13.764,
+      "step": 645000
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 5.28383467026477e-05,
+      "loss": 0.1983,
+      "step": 645500
+    },
+    {
+      "epoch": 6.85,
+      "learning_rate": 5.2731709514689995e-05,
+      "loss": 0.1982,
+      "step": 646000
+    },
+    {
+      "epoch": 6.85,
+      "eval_loss": 0.18697316944599152,
+      "eval_runtime": 2.5109,
+      "eval_samples_per_second": 914.815,
+      "eval_steps_per_second": 14.338,
+      "step": 646000
+    },
+    {
+      "epoch": 6.85,
+      "learning_rate": 5.262514687719722e-05,
+      "loss": 0.1983,
+      "step": 646500
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 5.25186590815076e-05,
+      "loss": 0.1985,
+      "step": 647000
+    },
+    {
+      "epoch": 6.86,
+      "eval_loss": 0.1897994428873062,
+      "eval_runtime": 2.4914,
+      "eval_samples_per_second": 921.982,
+      "eval_steps_per_second": 14.45,
+      "step": 647000
+    },
+    {
+      "epoch": 6.86,
+      "learning_rate": 5.24122464187547e-05,
+      "loss": 0.1981,
+      "step": 647500
+    },
+    {
+      "epoch": 6.87,
+      "learning_rate": 5.2305909179866635e-05,
+      "loss": 0.1982,
+      "step": 648000
+    },
+    {
+      "epoch": 6.87,
+      "eval_loss": 0.18750005960464478,
+      "eval_runtime": 2.5048,
+      "eval_samples_per_second": 917.025,
+      "eval_steps_per_second": 14.372,
+      "step": 648000
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 5.219964765556536e-05,
+      "loss": 0.1982,
+      "step": 648500
+    },
+    {
+      "epoch": 6.88,
+      "learning_rate": 5.209346213636584e-05,
+      "loss": 0.198,
+      "step": 649000
+    },
+    {
+      "epoch": 6.88,
+      "eval_loss": 0.18683280050754547,
+      "eval_runtime": 2.5207,
+      "eval_samples_per_second": 911.266,
+      "eval_steps_per_second": 14.282,
+      "step": 649000
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 5.1987352912575244e-05,
+      "loss": 0.1982,
+      "step": 649500
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 5.188132027429215e-05,
+      "loss": 0.198,
+      "step": 650000
+    },
+    {
+      "epoch": 6.89,
+      "eval_loss": 0.18715369701385498,
+      "eval_runtime": 2.4622,
+      "eval_samples_per_second": 932.918,
+      "eval_steps_per_second": 14.621,
+      "step": 650000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 12,
-  "total_flos": 4.4863838472571235e+22,
+  "total_flos": 4.556484108287471e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a384a8675e00c8c913ad9984a62d855b944319fd0302d5aeb3e2d99f3e8e335
+oid sha256:3d09118465ef0159b7efd2eee2688641c444f8ba8f4010b2ee8866772ea196af
 size 449471589