Training in progress, step 45, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61ef777d3cf5653eab13fc05ebe02815da4b6a32d0500f707858f99ba52c0fe4
+oid sha256:e5bd53e406d3ec1f854877d7973c4484bead90a7eec17d8008bd799eb224bb93
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f460a79034f1e3c3842d20a3765feb14ab6e7319ab4dac56475879db4a3c877
+oid sha256:2184dee4b408b279b5c02427b1aad0c6149bd58c42401dc540958e2815a56404
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9573e9d18ad7803441c819253e1705231d5811c0e4f29747c0574440f588f00
+oid sha256:b665a2618254d0693455029a117143eb612684fd8f287fa7207d501afc785521
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.040357330530740934,
+  "epoch": 0.05044666316342617,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 8.273,
       "eval_steps_per_second": 4.138,
       "step": 36
+    },
+    {
+      "epoch": 0.04372044140830268,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001300741882076764,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.04708355228586442,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012370860362476374,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.05044666316342617,
+      "grad_norm": NaN,
+      "learning_rate": 0.00011666776747647015,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.05044666316342617,
+      "eval_loss": NaN,
+      "eval_runtime": 363.3478,
+      "eval_samples_per_second": 8.27,
+      "eval_steps_per_second": 4.137,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.335012715275223e+17,
+  "total_flos": 2.909440763441971e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null