Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e37318e129be4a3b241f4398755cdc6c0b1f5ec5b734c8c1d351041444e793d7
+oid sha256:521a0d7eaae4e907f7fd69650050c9a3451db74c95a4db6219a2739aee1ccd19
 size 18763860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1ba80a9ce902b738c175ebd676819779b18d64fc6ee9dc7b6d4bb80caffdc6e
+oid sha256:c7d68fceb13086e9892e1c9c3203d31df35fd3183cd6aac7813303ae766d2416
 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": 0.0003614185678789248,
+  "epoch": 0.0005421278518183872,
   "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": 49.719,
       "eval_steps_per_second": 24.859,
       "step": 6
+    },
+    {
+      "epoch": 0.00042165499585874555,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0004818914238385664,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.0005421278518183872,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 3.1081,
+      "step": 9
+    },
+    {
+      "epoch": 0.0005421278518183872,
+      "eval_loss": NaN,
+      "eval_runtime": 139.9544,
+      "eval_samples_per_second": 49.945,
+      "eval_steps_per_second": 24.972,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 338360769970176.0,
+  "total_flos": 507541154955264.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null