Training in progress, step 1900, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ceb2949c288c43991698176ffbd5aa30aed17f67428acf5a2ec2d8b5e97b044e
+oid sha256:af6d42d568c10c05bd0a235b35138ad5ac51f2a52cb724441cd7bfb5e2d9653f
 size 160285149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d780045b7ba04666ddb94197b3702ccc98c54e1ba36cf994425e87905fd032e
+oid sha256:1b5c2cb2dfb3f60750713c8e1a124a5bce3de66d8a6642dd7a6723300b51429a
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be50d991d0ad05925161d2b4ecb2ad706ca272d5d5a04ebcad5d79266d1efcea
+oid sha256:504ae0bcaabd05c86ca42a16a90534b6c93ee4e2544d2c7bdfb57fa3e94a82bc
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.6666666666666665,
+  "epoch": 2.814814814814815,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -241,13 +241,26 @@
       "eval_samples_per_second": 1.903,
       "eval_steps_per_second": 0.239,
       "step": 1800
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 0.0,
+      "loss": 8.657,
+      "step": 1900
+    },
+    {
+      "epoch": 2.81,
+      "eval_runtime": 787.6516,
+      "eval_samples_per_second": 1.904,
+      "eval_steps_per_second": 0.239,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
   "max_steps": 2025,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.74832717889536e+17,
+  "total_flos": 3.95656757772288e+17,
   "trial_name": null,
   "trial_params": null
 }