Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38042cd2489098d9b4939a59988ffa044fb5d29acc22328bcc59b69df59cd348
+oid sha256:bdb338cd915f173556f0eb3016ec5695ea43b361c9ca6c4a2d6f07f283abd10f
 size 90310010

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2caab57c9738a6223b66a33175b22839bf9437a089ed80e62b0e4247b5a00c6c
+oid sha256:deed864d9094dd276975b1a0b401102b49095b3b4735cef2dfce0c737a2bfd46
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0008326481333069661,
+  "epoch": 0.0012489721999604491,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 6.545084971874738e-05,
       "loss": 0.0,
       "step": 18
+    },
+    {
+      "epoch": 0.0008742805399723144,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009991777599683595,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.0009991777599683595,
+      "eval_loss": NaN,
+      "eval_runtime": 222.8241,
+      "eval_samples_per_second": 45.39,
+      "eval_steps_per_second": 22.695,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011240749799644042,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.0012489721999604491,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1233846276194304.0,
+  "total_flos": 1838672882171904.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null