Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960cd9845c564bfc5e3103367fd2ab34c17fd8f491a601ce226f7d51fce43bb8
+oid sha256:93a48d4497c53c5c4cadb807b99facccc26970afcf17ac4796756576006b5f31
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd824ab7bf9f8eea6d9bd6e51d86488e2d9ca4852207360bea549e24419edb8
+oid sha256:adae4d92330c3538125f704355fef4ac69505b8124db6a0652197adde9cc4fdd
 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": 0.0028208744710860366,
+  "epoch": 0.004231311706629055,
   "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": 30.039,
       "eval_steps_per_second": 15.019,
       "step": 6
+    },
+    {
+      "epoch": 0.003291020216267043,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.0037611659614480487,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.004231311706629055,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.004231311706629055,
+      "eval_loss": NaN,
+      "eval_runtime": 29.7452,
+      "eval_samples_per_second": 30.122,
+      "eval_steps_per_second": 15.061,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1109135852568576.0,
+  "total_flos": 1684243331678208.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null