Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c7755db217291b6bb9b913f26e773f85206608a5b23dd05eb5ea8fd216c683e
+oid sha256:20928efcf87ab7d7b9058cf889e6ca1b0ce7b102a83aeaf47520859779dbf1c4
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf4a70b2f1e0083900a8a144d37753c55636b180594109e7e6c3f925b4e7d11
+oid sha256:a9df42a9d1501f6518540f2f97c2607aaa7a902f0945692ed6b6ad9ee3c0889b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
+oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00023875608081893335,
+  "epoch": 0.0003581341212284,
   "eval_steps": 3,
-  "global_step": 6,
+  "global_step": 9,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,35 @@
       "eval_samples_per_second": 278.483,
       "eval_steps_per_second": 139.241,
       "step": 6
+    },
+    {
+      "epoch": 0.00027854876095542225,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.00031834144109191113,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.0003581341212284,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0003581341212284,
+      "eval_loss": NaN,
+      "eval_runtime": 37.378,
+      "eval_samples_per_second": 283.108,
+      "eval_steps_per_second": 141.554,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 12898516598784.0,
+  "total_flos": 19347774898176.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null