Training in progress, step 420000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b34864a6b7e56f463c01712ba93853b0b92d97d75c7a8f55af696917f965b657
+oid sha256:c2f3d6b44eb31a5904720c6ef9f3e390e0825c4e9bc44d807b8966079fa39c18
 size 893439185

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d6344d188b78b37f915e82d50b318e55130c0a455c5f454004c35b9cff6e85
+oid sha256:43bdf8dfd2503753ae90f61b7bb9fe12717af35ea212a47dbf67cd5903f5bff5
 size 449471589

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54613cd3fa85ce3d795b198f6a5830b40bce93f547d2ed6957cd550ac0a0ffe4
-size 14439
+oid sha256:cc2e9e51fe4eee7b642ed745674287b01af0553fd6bc1b8f03d1bfb83d45dd88
+size 14503

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb5bb1df5224c0e4d6ed966bcba6b3adb22ec82383dd1cc287456a25bd70f43f
-size 14439
+oid sha256:d7303688061045aa652b3652b66ace516eee8a80cc0cf60b455e243337822a42
+size 14503

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6aecdb0c3b41413d899f1eab1b175b3005a1299de10e0ce83edd3a90a57013
+oid sha256:f87a487e7aba37c8dacc6a7f2504b596187c112ee85cf9f5586b459f5ed62ff7
 size 14503

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a262d68237e1b1dd83e70942fcc61f603591d3b3fa40239b6de9b406bb8e1459
+oid sha256:c8eef20e1504bbd40c9a4046a6d63e017b73406d2bc77b0cb51859e2e7910822
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4383c4a3fe7ea0ffc9a2a89b96314f2922a440b702dbdb834df8ceb90aebf44a
+oid sha256:5ecb3d640c7c2649b2bba280f1d77ce8c7f1955289fab0ee4959a38aa2646819
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.260784583199719,
-  "global_step": 410000,
+  "epoch": 6.41348664620459,
+  "global_step": 420000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3040,11 +3040,85 @@
       "eval_samples_per_second": 926.22,
       "eval_steps_per_second": 14.82,
       "step": 410000
+    },
+    {
+      "epoch": 6.28,
+      "learning_rate": 0.00010576871868792746,
+      "loss": 0.275,
+      "step": 411000
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 0.0001055533481490004,
+      "loss": 0.2746,
+      "step": 412000
+    },
+    {
+      "epoch": 6.31,
+      "learning_rate": 0.000105337698162752,
+      "loss": 0.2741,
+      "step": 413000
+    },
+    {
+      "epoch": 6.32,
+      "learning_rate": 0.00010512177108749594,
+      "loss": 0.2746,
+      "step": 414000
+    },
+    {
+      "epoch": 6.34,
+      "learning_rate": 0.00010490556928457616,
+      "loss": 0.2743,
+      "step": 415000
+    },
+    {
+      "epoch": 6.34,
+      "eval_runtime": 1.0107,
+      "eval_samples_per_second": 989.389,
+      "eval_steps_per_second": 15.83,
+      "step": 415000
+    },
+    {
+      "epoch": 6.35,
+      "learning_rate": 0.00010468909511834088,
+      "loss": 0.2741,
+      "step": 416000
+    },
+    {
+      "epoch": 6.37,
+      "learning_rate": 0.00010447235095611692,
+      "loss": 0.2738,
+      "step": 417000
+    },
+    {
+      "epoch": 6.38,
+      "learning_rate": 0.00010425533916818376,
+      "loss": 0.2738,
+      "step": 418000
+    },
+    {
+      "epoch": 6.4,
+      "learning_rate": 0.00010403806212774747,
+      "loss": 0.2742,
+      "step": 419000
+    },
+    {
+      "epoch": 6.41,
+      "learning_rate": 0.000103820522210915,
+      "loss": 0.2737,
+      "step": 420000
+    },
+    {
+      "epoch": 6.41,
+      "eval_runtime": 1.055,
+      "eval_samples_per_second": 947.861,
+      "eval_steps_per_second": 15.166,
+      "step": 420000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 16,
-  "total_flos": 2.8741067598353404e+22,
+  "total_flos": 2.9442070208656875e+22,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d6344d188b78b37f915e82d50b318e55130c0a455c5f454004c35b9cff6e85
+oid sha256:43bdf8dfd2503753ae90f61b7bb9fe12717af35ea212a47dbf67cd5903f5bff5
 size 449471589