Training in progress, step 35, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2648ff728f90c3482885079d09e8740207b49cb18e38688b145bf1d4cbe39ed4
+oid sha256:c937b91af294a1acd2d1897711087333b66f7235025617bef77a8f9b25207c1d
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dd2ab2df980b0072a85742a669169e7a0f21dccbc2a2e9994737ca0875c042b
+oid sha256:2e309b04479ffbfd8df710ea7543dea1cfb2f7def8016c11c2c136bfce3c7316
 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": 0.5581395348837209,
+  "epoch": 0.6511627906976745,
   "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": 14.866,
       "eval_steps_per_second": 1.96,
       "step": 30
+    },
+    {
+      "epoch": 0.6139534883720931,
+      "grad_norm": NaN,
+      "learning_rate": 3.832773180720475e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.6511627906976745,
+      "eval_loss": NaN,
+      "eval_runtime": 6.119,
+      "eval_samples_per_second": 14.872,
+      "eval_steps_per_second": 1.961,
+      "step": 35
     }
   ],
   "logging_steps": 3,
@@ -152,7 +167,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.26566605602816e+16,
+  "total_flos": 4.97661039869952e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null