Training in progress, step 3, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff1b87e3a4190e6c411b8f2add7b45135c685fa8e7f3739d80f9b9d72bbfc42f
+oid sha256:8afb38a9f379b9c51dd90e2ff7b02b277ac2bd6bf01e9d845f907c3078521a05
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66c699e83742d2565e0833a315073c2f0af2d1281c4a783ab4651d7ca45e4246
+oid sha256:7b36ab806eeef83b857b4af0f86b98f1ed73628d9526509db26447d1171fd344
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
+oid sha256:dc78163c347c258a17d5fa38a4e22e79b63c35d2cfce0e026e30c38b9ae55f80
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6153846153846154,
+  "epoch": 0.9230769230769231,
   "eval_steps": 1,
-  "global_step": 2,
+  "global_step": 3,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -23,6 +23,14 @@
       "eval_samples_per_second": 23.802,
       "eval_steps_per_second": 11.901,
       "step": 2
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "eval_loss": NaN,
+      "eval_runtime": 0.1013,
+      "eval_samples_per_second": 19.752,
+      "eval_steps_per_second": 9.876,
+      "step": 3
     }
   ],
   "logging_steps": 5,
@@ -42,7 +50,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 64859651702784.0,
+  "total_flos": 97289477554176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null