Training in progress, step 4, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cadf274e078e0c5d8cb002a87e9f3602f945cdf51e07b88f1767472cb8df81d
+oid sha256:b3c1ae2560015323435492196bec6a8736a11a4fa7e0125e83be82f37c96d74b
 size 70674004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd31991177e24926a50ee6c3209ef4303d67acfabd9978d996903de291272c42
+oid sha256:a53a508a4ce3f62bf889a072faf0852fce1aa0e321838e146e5720292e6b860a
 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": 0.38095238095238093,
+  "epoch": 0.7619047619047619,
   "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": 15.42,
       "eval_steps_per_second": 10.28,
       "step": 2
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": NaN,
+      "learning_rate": 6e-05,
+      "loss": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": NaN,
+      "learning_rate": 8e-05,
+      "loss": 0.0,
+      "step": 4
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "eval_loss": NaN,
+      "eval_runtime": 0.2002,
+      "eval_samples_per_second": 14.987,
+      "eval_steps_per_second": 9.991,
+      "step": 4
     }
   ],
   "logging_steps": 1,
@@ -56,7 +78,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 689399679418368.0,
+  "total_flos": 1378799358836736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null