Training in progress, step 90, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:575024a35a870380b336799922d1050199a457150079de3148aec63822a61263
+oid sha256:ca6d80fdb6b06900b16612d724e8387d91f681cbc15771837666fa89c46b3ce4
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b43e51c818353fdc58a80e47797b9309f858b46f69d4373d744fb2a934a15b3
+oid sha256:0fb22c85dfbc20aa45d4b5c97669f2a88c9102e142b0f1bd4f0ad19181f33e67
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
+oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7168141592920354,
+  "epoch": 0.7964601769911505,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 36.214,
       "eval_steps_per_second": 4.574,
       "step": 81
+    },
+    {
+      "epoch": 0.7433628318584071,
+      "grad_norm": NaN,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.7699115044247787,
+      "grad_norm": NaN,
+      "learning_rate": 5.060297685041659e-06,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "grad_norm": NaN,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.7964601769911505,
+      "eval_loss": NaN,
+      "eval_runtime": 5.2502,
+      "eval_samples_per_second": 36.189,
+      "eval_steps_per_second": 4.571,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.204372318552064e+16,
+  "total_flos": 2.44930257616896e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null