Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f468eb4f0acbf19a5233da76bd6e7daeec96385f93f13fa0c419ba0ac7edd23
+oid sha256:bd231aeb12e588e4178bc7a43d2d2e8ac90bf93d8422b059bd329010eba465b7
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b596dc35d1da9511957c2e4c124ac42a9a7bd98335ad4e77e73c20baeeb90d
+oid sha256:8d5d7a37a75514386b20e172de4f6ff0424612e2010b5d0d52f160fc8ce60cdd
 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": 0.0062827225130890054,
+  "epoch": 0.009424083769633508,
   "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": 38.685,
       "eval_steps_per_second": 19.39,
       "step": 6
+    },
+    {
+      "epoch": 0.007329842931937173,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.008376963350785341,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.009424083769633508,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.009424083769633508,
+      "eval_loss": NaN,
+      "eval_runtime": 10.347,
+      "eval_samples_per_second": 38.949,
+      "eval_steps_per_second": 19.523,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 172659585318912.0,
+  "total_flos": 274976376619008.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null