Training in progress, step 81, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f6aefaeb5bf994ebe0d957edc1597ab057b6f8093ec70fed9308c20c5491a5
+oid sha256:575024a35a870380b336799922d1050199a457150079de3148aec63822a61263
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:045b4c272e1eb6e89091f4c9d82e18f4b0934375c807b878adae2bc236109356
+oid sha256:0b43e51c818353fdc58a80e47797b9309f858b46f69d4373d744fb2a934a15b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6371681415929203,
+  "epoch": 0.7168141592920354,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 36.219,
       "eval_steps_per_second": 4.575,
       "step": 72
+    },
+    {
+      "epoch": 0.6637168141592921,
+      "grad_norm": NaN,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.6902654867256637,
+      "grad_norm": NaN,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.7168141592920354,
+      "grad_norm": NaN,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.7168141592920354,
+      "eval_loss": NaN,
+      "eval_runtime": 5.2465,
+      "eval_samples_per_second": 36.214,
+      "eval_steps_per_second": 4.574,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.959442060935168e+16,
+  "total_flos": 2.204372318552064e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null