Training in progress, step 9, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:457d4563feeddee4c9f3d298b524ea8041e8bb738eaed743df78a78da518277f
+oid sha256:0b110989631b571b8e06a0afd848f9ec5e707f7f7f0fe37c93978e7d01842091
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57fe62218ee3734254ba00aa6f612a2938621f075dd8673d5188946b5efa8c82
+oid sha256:bf419f76d381b7979bcc69770feb487268d9381b12b1404a5601817407bf045e
 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": 0.00020824295010845987,
+  "epoch": 0.0003123644251626898,
   "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": 47.272,
       "eval_steps_per_second": 23.636,
       "step": 6
+    },
+    {
+      "epoch": 0.00024295010845986985,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 0.0,
+      "step": 7
+    },
+    {
+      "epoch": 0.00027765726681127983,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016,
+      "loss": 0.0,
+      "step": 8
+    },
+    {
+      "epoch": 0.0003123644251626898,
+      "grad_norm": NaN,
+      "learning_rate": 0.00018,
+      "loss": 0.0,
+      "step": 9
+    },
+    {
+      "epoch": 0.0003123644251626898,
+      "eval_loss": NaN,
+      "eval_runtime": 256.5453,
+      "eval_samples_per_second": 47.29,
+      "eval_steps_per_second": 23.645,
+      "step": 9
     }
   ],
   "logging_steps": 1,
@@ -92,7 +121,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 77908393328640.0,
+  "total_flos": 122427475230720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null