Training in progress, step 35, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6a4a5888d0eb9edb735edf1836a19a959b1ba8681885f9aa21198c19709da23
+oid sha256:14d79aec87f25697b8cf04ac479bb9cdc2a09c6015a47112596f400eff01a54c
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d003c8d3ec225855b33dde2ea80eeb4f521574e37dab0bf55687c6326b82d05
+oid sha256:6e0e618ec3b5bec33efe1e10231b87a2c5463e3fb7d638971889723d5edaadb9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
+oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0020200999949497502,
+  "epoch": 0.002356783327441375,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,21 @@
       "eval_samples_per_second": 13.639,
       "eval_steps_per_second": 1.705,
       "step": 30
+    },
+    {
+      "epoch": 0.002222109994444725,
+      "grad_norm": NaN,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.002356783327441375,
+      "eval_loss": NaN,
+      "eval_runtime": 1834.8435,
+      "eval_samples_per_second": 13.632,
+      "eval_steps_per_second": 1.704,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.638679254643507e+16,
+  "total_flos": 5.392936044016435e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null