Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5b0f2517c02f83bc1369b687b2c7d09a6483d08f5bac14ea52ace5a911f8851
+oid sha256:89657f9d55a8fb888a19b5830288050f2aea41864ec29c8ad8c276fe984fc1ad
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5a445e5da9d6ddd074b49ee7fb56d32a094be2c1a1a357628b3a4ed18671b69
+oid sha256:496d10a4c361f48ab7e207e9c89126c6c565ecaf0d2f89c9aec3fb5d7f07668c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
+oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06709677419354838,
+  "epoch": 0.10064516129032258,
   "eval_steps": 10,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,6 +66,28 @@
       "learning_rate": 6.91341716182545e-05,
       "loss": 0.0,
       "step": 25
+    },
+    {
+      "epoch": 0.07741935483870968,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.07741935483870968,
+      "eval_loss": NaN,
+      "eval_runtime": 12.6772,
+      "eval_samples_per_second": 12.937,
+      "eval_steps_per_second": 6.468,
+      "step": 30
+    },
+    {
+      "epoch": 0.09032258064516129,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
     }
   ],
   "logging_steps": 5,
@@ -85,7 +107,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5532869446336512.0,
+  "total_flos": 8103257614319616.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null