Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3768217573c1658afad5ef321418ab100ca3cf01f01ab905b4c09440048bddc9
+oid sha256:9db4d0a39712a58195d22e74137ccd962270dff5c9af4c11bf1afd68212c705e
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:663e3c3f170d4fcfce6ba3deb4ce9cfef2f3ad793eddb4ad0bda5ead8da908ac
+oid sha256:a06d7b4007962cc470a0e69a905c80df628980e0da312dc44565e5cee37d2eb8
 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": 0.0037794817749027872,
+  "epoch": 0.005669222662354181,
   "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": 0.004360940509503216,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.004360940509503216,
+      "eval_loss": NaN,
+      "eval_runtime": 56.8191,
+      "eval_samples_per_second": 50.986,
+      "eval_steps_per_second": 25.502,
+      "step": 30
+    },
+    {
+      "epoch": 0.005087763927753753,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 35
     }
   ],
   "logging_steps": 5,
@@ -85,7 +107,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 28484224155648.0,
+  "total_flos": 42995055329280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null