Training in progress, step 39, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d541821d55ccd6fd96f832b60a1d2b2ead8b7f1e7660d2fa97d0da67f401799
+oid sha256:0dd41644b46c8e96d6b145ae0e19f4a7f62145b5a622196de21adccfa99ebcb9
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:627cce84d4bda7b93dc609b3b52700ad17d0c0fcb3890bd0b03fc2bee36b5f43
+oid sha256:ae2be3b7bc5de30f888aa7806ac10f8ac5d98cac9fed1e3f02f3349c405f5610
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
+oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001050165603037402,
+  "epoch": 0.001575248404556103,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,21 @@
       "eval_samples_per_second": 34.421,
       "eval_steps_per_second": 17.214,
       "step": 26
+    },
+    {
+      "epoch": 0.001211729541966233,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.001575248404556103,
+      "eval_loss": NaN,
+      "eval_runtime": 151.2802,
+      "eval_samples_per_second": 34.459,
+      "eval_steps_per_second": 17.233,
+      "step": 39
     }
   ],
   "logging_steps": 10,
@@ -64,7 +79,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2205421431422976.0,
+  "total_flos": 3308132147134464.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null