Training in progress, step 280000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f45e9ea7aeadf9f10b1643bf00c0b8ef58ef51944d08e1b0ad72f902bd82cd
+oid sha256:bc8ad2cb8ff3175b9f7848007e562d12603a8c18323c57ee3a36077f04ace11d
 size 202194449

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1752842aa50d3948c8a46f98f668fd33584b25521cc864747236962908637e8
+oid sha256:a667bd305925526eed71d832e21eaecb45af259ca2eb092c78d12e83a2aae49b
 size 102501541

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20a1051f008a83adbc4c881b4baac5cd60ff30165ed01dcd9fea7e631712e7d
+oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
 size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20a1051f008a83adbc4c881b4baac5cd60ff30165ed01dcd9fea7e631712e7d
+oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
 size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20a1051f008a83adbc4c881b4baac5cd60ff30165ed01dcd9fea7e631712e7d
+oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20a1051f008a83adbc4c881b4baac5cd60ff30165ed01dcd9fea7e631712e7d
+oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
 size 14503

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20a1051f008a83adbc4c881b4baac5cd60ff30165ed01dcd9fea7e631712e7d
+oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
 size 14503

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20a1051f008a83adbc4c881b4baac5cd60ff30165ed01dcd9fea7e631712e7d
+oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
 size 14503

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20a1051f008a83adbc4c881b4baac5cd60ff30165ed01dcd9fea7e631712e7d
+oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
 size 14503

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20a1051f008a83adbc4c881b4baac5cd60ff30165ed01dcd9fea7e631712e7d
+oid sha256:e7bfe10858f498e014bc778ce784581af325183b5d21115eaa6c144489816d8f
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb61348726887e329b19406ea4e3e39ac391edeec6dfd8508b3cb524aa33e28
+oid sha256:80db35d9a6af0da10cd7cebe3bf01f3932293e48fc6a8607555efe3b5591e844
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.881084662826852,
-  "global_step": 270000,
+  "epoch": 7.135939650338957,
+  "global_step": 280000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5406,11 +5406,211 @@
       "eval_samples_per_second": 817.974,
       "eval_steps_per_second": 13.088,
       "step": 270000
+    },
+    {
+      "epoch": 6.89,
+      "learning_rate": 0.00014733147931802578,
+      "loss": 0.2858,
+      "step": 270500
+    },
+    {
+      "epoch": 6.91,
+      "learning_rate": 0.00014685268692538238,
+      "loss": 0.2852,
+      "step": 271000
+    },
+    {
+      "epoch": 6.91,
+      "eval_loss": 0.8104480504989624,
+      "eval_runtime": 1.2885,
+      "eval_samples_per_second": 776.067,
+      "eval_steps_per_second": 12.417,
+      "step": 271000
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 0.00014637398363044946,
+      "loss": 0.2851,
+      "step": 271500
+    },
+    {
+      "epoch": 6.93,
+      "learning_rate": 0.00014589537466824955,
+      "loss": 0.2852,
+      "step": 272000
+    },
+    {
+      "epoch": 6.93,
+      "eval_loss": 0.8213782906532288,
+      "eval_runtime": 1.2391,
+      "eval_samples_per_second": 807.026,
+      "eval_steps_per_second": 12.912,
+      "step": 272000
+    },
+    {
+      "epoch": 6.94,
+      "learning_rate": 0.00014541686527277356,
+      "loss": 0.285,
+      "step": 272500
+    },
+    {
+      "epoch": 6.96,
+      "learning_rate": 0.00014493846067692358,
+      "loss": 0.2848,
+      "step": 273000
+    },
+    {
+      "epoch": 6.96,
+      "eval_loss": 0.8104705810546875,
+      "eval_runtime": 1.1998,
+      "eval_samples_per_second": 833.443,
+      "eval_steps_per_second": 13.335,
+      "step": 273000
+    },
+    {
+      "epoch": 6.97,
+      "learning_rate": 0.00014446016611245567,
+      "loss": 0.2855,
+      "step": 273500
+    },
+    {
+      "epoch": 6.98,
+      "learning_rate": 0.00014398198680992252,
+      "loss": 0.2857,
+      "step": 274000
+    },
+    {
+      "epoch": 6.98,
+      "eval_loss": 0.8124169707298279,
+      "eval_runtime": 1.3472,
+      "eval_samples_per_second": 742.261,
+      "eval_steps_per_second": 11.876,
+      "step": 274000
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.00014350392799861636,
+      "loss": 0.286,
+      "step": 274500
+    },
+    {
+      "epoch": 7.01,
+      "learning_rate": 0.0001430259949065118,
+      "loss": 0.2849,
+      "step": 275000
+    },
+    {
+      "epoch": 7.01,
+      "eval_loss": 0.8163594007492065,
+      "eval_runtime": 1.223,
+      "eval_samples_per_second": 817.633,
+      "eval_steps_per_second": 13.082,
+      "step": 275000
+    },
+    {
+      "epoch": 7.02,
+      "learning_rate": 0.0001425481927602085,
+      "loss": 0.2846,
+      "step": 275500
+    },
+    {
+      "epoch": 7.03,
+      "learning_rate": 0.0001420705267848743,
+      "loss": 0.2848,
+      "step": 276000
+    },
+    {
+      "epoch": 7.03,
+      "eval_loss": 0.8182600736618042,
+      "eval_runtime": 1.2318,
+      "eval_samples_per_second": 811.808,
+      "eval_steps_per_second": 12.989,
+      "step": 276000
+    },
+    {
+      "epoch": 7.05,
+      "learning_rate": 0.00014159300220418757,
+      "loss": 0.2852,
+      "step": 276500
+    },
+    {
+      "epoch": 7.06,
+      "learning_rate": 0.0001411156242402808,
+      "loss": 0.2847,
+      "step": 277000
+    },
+    {
+      "epoch": 7.06,
+      "eval_loss": 0.8188433647155762,
+      "eval_runtime": 1.2733,
+      "eval_samples_per_second": 785.37,
+      "eval_steps_per_second": 12.566,
+      "step": 277000
+    },
+    {
+      "epoch": 7.07,
+      "learning_rate": 0.0001406383981136829,
+      "loss": 0.2844,
+      "step": 277500
+    },
+    {
+      "epoch": 7.08,
+      "learning_rate": 0.00014016132904326226,
+      "loss": 0.2846,
+      "step": 278000
+    },
+    {
+      "epoch": 7.08,
+      "eval_loss": 0.8136109709739685,
+      "eval_runtime": 1.2428,
+      "eval_samples_per_second": 804.644,
+      "eval_steps_per_second": 12.874,
+      "step": 278000
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 0.00013968442224616989,
+      "loss": 0.2845,
+      "step": 278500
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 0.00013920768293778195,
+      "loss": 0.2847,
+      "step": 279000
+    },
+    {
+      "epoch": 7.11,
+      "eval_loss": 0.8128536343574524,
+      "eval_runtime": 1.3248,
+      "eval_samples_per_second": 754.825,
+      "eval_steps_per_second": 12.077,
+      "step": 279000
+    },
+    {
+      "epoch": 7.12,
+      "learning_rate": 0.00013873111633164336,
+      "loss": 0.2843,
+      "step": 279500
+    },
+    {
+      "epoch": 7.14,
+      "learning_rate": 0.00013825472763941,
+      "loss": 0.2845,
+      "step": 280000
+    },
+    {
+      "epoch": 7.14,
+      "eval_loss": 0.8165821433067322,
+      "eval_runtime": 1.2675,
+      "eval_samples_per_second": 788.963,
+      "eval_steps_per_second": 12.623,
+      "step": 280000
     }
   ],
   "max_steps": 500000,
   "num_train_epochs": 13,
-  "total_flos": 8.62607187343323e+21,
+  "total_flos": 8.945545533294685e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1752842aa50d3948c8a46f98f668fd33584b25521cc864747236962908637e8
+oid sha256:a667bd305925526eed71d832e21eaecb45af259ca2eb092c78d12e83a2aae49b
 size 102501541