Training in progress, step 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:207ddbedd699f5bf984e4941c9340244ad7e06c333c33f7112318ac9084bafe0
+oid sha256:fd6982bcc60cdab0257c5094b578ba6dd17785574ecd91ea21df18552dbdab50
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61aad8dd7670b93cb8426d8435674cce78183be79c2a40df620d05688de71b9b
+oid sha256:6dfc6c9a79d5a3b2c5d198ce0b76d564b33522114642fd45d0f84103f7381088
 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": 6.26169175256925e-05,
+  "epoch": 0.000125233835051385,
   "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": 4.053,
       "eval_steps_per_second": 4.053,
       "step": 2
+    },
+    {
+      "epoch": 9.392537628853876e-05,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.000125233835051385,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.000125233835051385,
+      "eval_loss": NaN,
+      "eval_runtime": 3321.6951,
+      "eval_samples_per_second": 4.049,
+      "eval_steps_per_second": 4.049,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1406258997362688.0,
+  "total_flos": 2812517994725376.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null