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 sha256:0cf2560c9ac719d0b40536645a3970fccfda3bb12e32ed7ca6cc5199b720993e
+oid sha256:b0342d92050a310b32631cadaf14a8987476d97b2ab3644276649f1ba7932af2
 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": 0.07476635514018691,
+  "epoch": 0.11214953271028037,
   "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": 0.1538,
       "step": 25
+    },
+    {
+      "epoch": 0.08626887131560029,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.08626887131560029,
+      "eval_loss": NaN,
+      "eval_runtime": 13.8087,
+      "eval_samples_per_second": 10.645,
+      "eval_steps_per_second": 5.359,
+      "step": 30
+    },
+    {
+      "epoch": 0.100647016534867,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.9161,
+      "step": 35
     }
   ],
   "logging_steps": 5,
@@ -85,7 +107,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7406203195883520.0,
+  "total_flos": 1.1196436596129792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null