Training in progress, step 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d00e7ac926f968aceba1906f6ac446d001593e4753e60751c35f10ec438b5240
+oid sha256:554c27f0adb6b0b054a2ca73f8f5d87b25104569ec7ee558389235ecc94de49f
 size 335810490

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:049c306a67a9bf5a5c55385c4c3d8c96f923249cec6471081b080d3935493ea9
+oid sha256:1e541f7aee48cc7ed448f7f7a74ac3c336f54829308a589e6265d77e6e70e6da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
+oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8731297720889808e-05,
+  "epoch": 5.7462595441779616e-05,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,28 @@
       "eval_samples_per_second": 8.475,
       "eval_steps_per_second": 4.237,
       "step": 2
+    },
+    {
+      "epoch": 4.3096946581334714e-05,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 5.7462595441779616e-05,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 5.7462595441779616e-05,
+      "eval_loss": NaN,
+      "eval_runtime": 3460.8748,
+      "eval_samples_per_second": 8.469,
+      "eval_steps_per_second": 4.234,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 741887283560448.0,
+  "total_flos": 1483774567120896.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null