Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d41f4a21bdbeb71ccbfdfbd3c1e51e850c6b98638681a203e1acf9bd628d6a1
+oid sha256:706891d98ff443d81ad4f1bead854fdfd9994e0f8aed962e21485df8921cbf6e
 size 524761122

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8be70d832a1bbff101f33c955af2006518b5495f9530a45087a280e66288a93d
+oid sha256:98d249c44d2043ac3faca89a38c200b16da869b2b95fda57466053e0556cdb5a
 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": 0.6722689075630253,
+  "epoch": 1.0168067226890756,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 10.794,
       "eval_steps_per_second": 5.812,
       "step": 20
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": NaN,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.8403361344537815,
+      "eval_loss": NaN,
+      "eval_runtime": 1.2096,
+      "eval_samples_per_second": 10.747,
+      "eval_steps_per_second": 5.787,
+      "step": 25
+    },
+    {
+      "epoch": 0.907563025210084,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.0168067226890756,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 1.0168067226890756,
+      "eval_loss": NaN,
+      "eval_runtime": 1.2054,
+      "eval_samples_per_second": 10.784,
+      "eval_steps_per_second": 5.807,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.3626513555456e+16,
+  "total_flos": 2.0439770333184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null