Training in progress, step 410000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c173163e338165d1fe37ba14405dbe53b272a5ca3e52267ff5c851a862f35da2
+oid sha256:b34864a6b7e56f463c01712ba93853b0b92d97d75c7a8f55af696917f965b657
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e086dc2588b852e6182d32ad6ab8f484673dafebd51e08d7a801497b43f4fe30
+oid sha256:17d6344d188b78b37f915e82d50b318e55130c0a455c5f454004c35b9cff6e85
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8c3463e55c2827928dfa1b830953cf8eccfe7f6ab2a72af5d13db1a192ce98b
-size 14503
+oid sha256:54613cd3fa85ce3d795b198f6a5830b40bce93f547d2ed6957cd550ac0a0ffe4
+size 14439

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fbc08cc620efc6ad1b3090a70819940a5a6dca3de71f9ffed8d3aa8dee8bdcc
-size 14503
+oid sha256:fb5bb1df5224c0e4d6ed966bcba6b3adb22ec82383dd1cc287456a25bd70f43f
+size 14439

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8c2cc612f6c582ed6586d60fa04580b6f35775b91158d5b84ddd0f0a65ddd3
+oid sha256:1a6aecdb0c3b41413d899f1eab1b175b3005a1299de10e0ce83edd3a90a57013
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60fbf66cb187e2da54f6604ee46efd1578eb148d61f9556ffc6254e09665c1a9
+oid sha256:a262d68237e1b1dd83e70942fcc61f603591d3b3fa40239b6de9b406bb8e1459
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:591046c9a1cdb63ed76af20e30931eec37ddea64d1cedd0e21228761a5b0c89f
+oid sha256:4383c4a3fe7ea0ffc9a2a89b96314f2922a440b702dbdb834df8ceb90aebf44a
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.108082520194848,
-  "global_step": 400000,
+  "epoch": 6.260784583199719,
+  "global_step": 410000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2966,11 +2966,85 @@
       "eval_samples_per_second": 902.417,
       "eval_steps_per_second": 14.439,
       "step": 400000
+    },
+    {
+      "epoch": 6.12,
+      "learning_rate": 0.00010790653786363416,
+      "loss": 0.2759,
+      "step": 401000
+    },
+    {
+      "epoch": 6.14,
+      "learning_rate": 0.00010769409082013337,
+      "loss": 0.2759,
+      "step": 402000
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 0.00010748134091849238,
+      "loss": 0.2757,
+      "step": 403000
+    },
+    {
+      "epoch": 6.17,
+      "learning_rate": 0.00010726829048531,
+      "loss": 0.2762,
+      "step": 404000
+    },
+    {
+      "epoch": 6.18,
+      "learning_rate": 0.00010705494185047165,
+      "loss": 0.276,
+      "step": 405000
+    },
+    {
+      "epoch": 6.18,
+      "eval_runtime": 1.1676,
+      "eval_samples_per_second": 856.476,
+      "eval_steps_per_second": 13.704,
+      "step": 405000
+    },
+    {
+      "epoch": 6.2,
+      "learning_rate": 0.0001068412973471238,
+      "loss": 0.2754,
+      "step": 406000
+    },
+    {
+      "epoch": 6.21,
+      "learning_rate": 0.00010662735931164853,
+      "loss": 0.2755,
+      "step": 407000
+    },
+    {
+      "epoch": 6.23,
+      "learning_rate": 0.0001064131300836379,
+      "loss": 0.2752,
+      "step": 408000
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 0.0001061986120058684,
+      "loss": 0.2748,
+      "step": 409000
+    },
+    {
+      "epoch": 6.26,
+      "learning_rate": 0.00010598380742427543,
+      "loss": 0.2749,
+      "step": 410000
+    },
+    {
+      "epoch": 6.26,
+      "eval_runtime": 1.0797,
+      "eval_samples_per_second": 926.22,
+      "eval_steps_per_second": 14.82,
+      "step": 410000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.8040064988049933e+22,
+  "total_flos": 2.8741067598353404e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e086dc2588b852e6182d32ad6ab8f484673dafebd51e08d7a801497b43f4fe30
+oid sha256:17d6344d188b78b37f915e82d50b318e55130c0a455c5f454004c35b9cff6e85
 size 449471589