Training in progress, step 2000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af6d42d568c10c05bd0a235b35138ad5ac51f2a52cb724441cd7bfb5e2d9653f
+oid sha256:6b35451dd7360715ae863af7120dda5d7fc2bbd626c9fb758684acaa3cd6f788
 size 160285149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b5c2cb2dfb3f60750713c8e1a124a5bce3de66d8a6642dd7a6723300b51429a
+oid sha256:038e0e9b03dce20f31830a28ed6c6c117e9aaccbaa8a7bf8a3350824f2df080e
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:504ae0bcaabd05c86ca42a16a90534b6c93ee4e2544d2c7bdfb57fa3e94a82bc
+oid sha256:a5200b825cc4dc17aebed9fc4560364bf9274ccd027923f8a91cf4235243813c
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.814814814814815,
+  "epoch": 2.962962962962963,
   "eval_steps": 100,
-  "global_step": 1900,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -254,13 +254,26 @@
       "eval_samples_per_second": 1.904,
       "eval_steps_per_second": 0.239,
       "step": 1900
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 0.0,
+      "loss": 8.5097,
+      "step": 2000
+    },
+    {
+      "epoch": 2.96,
+      "eval_runtime": 786.5132,
+      "eval_samples_per_second": 1.907,
+      "eval_steps_per_second": 0.239,
+      "step": 2000
     }
   ],
   "logging_steps": 100,
   "max_steps": 2025,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.95656757772288e+17,
+  "total_flos": 4.1648079765504e+17,
   "trial_name": null,
   "trial_params": null
 }