Training in progress, step 370000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032632aa2e59a7370c8a2f40437ef69da58b65449cfe7fa3a8278baf768cc91b
+oid sha256:2d5937fbf5a223bdee412711090b2afe19ccd59cb5aa00ff257849fe3abbc0df
 size 893441530

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:927cfdcc9ed50ca027e558ae501d9eb171688bcdcc5554011a95dbad82ff27f7
+oid sha256:cb18529144e5631f4110d550e5ae8dec1ab66ae10143ec11a390bb4bb1168003
 size 454197066

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dea57f79fcdb60961c4b12abe4b4ae1797e7d5be498f1ee068e015bcea184a5
+oid sha256:57495da3e14701eaa78ba01626380cf06c08d77e93ad6e4f3e1fa2ad42d22c6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96cf24b2595fb9ea938ee5062cd07f0addfb4ccce513bd6fa04dd8edc00aa72d
+oid sha256:83bbce26cd1d82261c68bda952c3a8a3f941ff6e36a11d4fea5bc7113b3bffa2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.36,
-  "global_step": 360000,
+  "epoch": 0.37,
+  "global_step": 370000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2670,11 +2670,85 @@
       "eval_samples_per_second": 102.337,
       "eval_steps_per_second": 12.792,
       "step": 360000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6633112470897675e-05,
+      "loss": 0.3442,
+      "step": 361000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6620708362146338e-05,
+      "loss": 0.3441,
+      "step": 362000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.6608279694688143e-05,
+      "loss": 0.3441,
+      "step": 363000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.659582660444101e-05,
+      "loss": 0.3419,
+      "step": 364000
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.658334922758994e-05,
+      "loss": 0.3405,
+      "step": 365000
+    },
+    {
+      "epoch": 0.36,
+      "eval_runtime": 3198.5996,
+      "eval_samples_per_second": 106.188,
+      "eval_steps_per_second": 13.274,
+      "step": 365000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.6570847700585524e-05,
+      "loss": 0.3406,
+      "step": 366000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.6558322160142462e-05,
+      "loss": 0.341,
+      "step": 367000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.654577274323806e-05,
+      "loss": 0.342,
+      "step": 368000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.653319958711072e-05,
+      "loss": 0.3479,
+      "step": 369000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.6520602829258474e-05,
+      "loss": 0.3487,
+      "step": 370000
+    },
+    {
+      "epoch": 0.37,
+      "eval_runtime": 3164.3305,
+      "eval_samples_per_second": 107.338,
+      "eval_steps_per_second": 13.417,
+      "step": 370000
     }
   ],
   "max_steps": 1000000,
   "num_train_epochs": 9223372036854775807,
-  "total_flos": 3.1876596623631974e+21,
+  "total_flos": 3.2762057640955085e+21,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:927cfdcc9ed50ca027e558ae501d9eb171688bcdcc5554011a95dbad82ff27f7
+oid sha256:cb18529144e5631f4110d550e5ae8dec1ab66ae10143ec11a390bb4bb1168003
 size 454197066