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:c4dda2251239c76c64ff3aac152211950bbfbcfe6f98a981dc5291eec0d2e00c
+oid sha256:280161a9f4714c93fb07ab718a953373e16ed075446dacc05329de7060dc0809
 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": 0.0010227999147666737,
+  "epoch": 0.0015341998721500106,
   "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": 41.655,
       "eval_steps_per_second": 20.828,
       "step": 6
+    },
+    {
+      "epoch": 0.0011932665672277861,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0013637332196888984,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.0015341998721500106,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0015341998721500106,
+      "eval_loss": NaN,
+      "eval_runtime": 58.1064,
+      "eval_samples_per_second": 42.508,
+      "eval_steps_per_second": 21.254,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 153475186950144.0,
+  "total_flos": 230212780425216.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null