Training in progress, step 1400, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73c72087c278a19d041000058ef12b3a0f26d21baaaa01b7d96279e32367abfa
+oid sha256:1b3fc1519a80ff09d34e614c9dcdfe5447dd304b116bc3936ecf5d7f466c41c5
 size 160285149

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22f55e2747dba123d2b4ec620eafd1a6796097d64b95110119ff4da1c567fe11
+oid sha256:00c70fec5855430ce0afb62afb7a7522f878bca813147b4cb565f553e75c1fd5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b07bb44c7eb6649b82d385b24afe36ce65d36c6d2f9dadc9eabdc31b084d574b
+oid sha256:426b58c51fde03deb12bf7d7b53933d1a534d1c5cd0baca806ba16d364acbc1f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.925925925925926,
+  "epoch": 2.074074074074074,
   "eval_steps": 100,
-  "global_step": 1300,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -176,13 +176,26 @@
       "eval_samples_per_second": 1.904,
       "eval_steps_per_second": 0.239,
       "step": 1300
+    },
+    {
+      "epoch": 2.07,
+      "learning_rate": 0.0,
+      "loss": 8.4373,
+      "step": 1400
+    },
+    {
+      "epoch": 2.07,
+      "eval_runtime": 788.547,
+      "eval_samples_per_second": 1.902,
+      "eval_steps_per_second": 0.238,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
   "max_steps": 2025,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.70712518475776e+17,
+  "total_flos": 2.91536558358528e+17,
   "trial_name": null,
   "trial_params": null
 }