Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24d71c509df481ce2b666570621cd4aeb0e74dbea1d6f4910bcb6b8b380212e4
+oid sha256:cc66a7721c18943169d4b3ee985fdcce10036fcd4bd982456a4bb5bba0de91a9
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9c101bb52e4f809de6487fd71b71482099d5184955d481f2aa26d4c99dfba27
+oid sha256:bb9fd29eefd5c42407ec295468332b1e9c3ce692abc97431dfed1b61fac9d9ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49fa7e5c4bd2e7be73796ceecdd7226a0477f69897edbc4e406600122a0902ee
+oid sha256:694a539f11c8d87dcdc9a0523d10086c9a55d2b245bea58f425e64a8cd3022da
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.09022556390977443,
+  "epoch": 0.12030075187969924,
   "eval_steps": 10,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,21 @@
       "eval_samples_per_second": 24.809,
       "eval_steps_per_second": 12.405,
       "step": 30
+    },
+    {
+      "epoch": 0.12030075187969924,
+      "grad_norm": NaN,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.12030075187969924,
+      "eval_loss": NaN,
+      "eval_runtime": 5.5475,
+      "eval_samples_per_second": 25.236,
+      "eval_steps_per_second": 12.618,
+      "step": 40
     }
   ],
   "logging_steps": 10,
@@ -79,7 +94,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 523099212349440.0,
+  "total_flos": 694497677672448.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null