Training in progress, step 30, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:566441d1ec2a535e553fafef599dfc79558d6278f2ebe74fafc6587de76dd77a
+oid sha256:173f30dc58dab74d2bea2343bc2c34154dcb7c1f879d81a28b92b1980e87e538
 size 503884594

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94679c79f797d0ad9ee8e3fa04683f5ac3ac382e4b5be6af9c8493feaaea69bd
+oid sha256:d8499756812b26ce8f2ce9d439126e69f58899480f58682d1e03352b776e532e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03508771929824561,
+  "epoch": 0.05263157894736842,
   "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": 4.838,
       "eval_steps_per_second": 2.419,
       "step": 20
+    },
+    {
+      "epoch": 0.03684210526315789,
+      "grad_norm": NaN,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0,
+      "step": 21
+    },
+    {
+      "epoch": 0.042105263157894736,
+      "grad_norm": NaN,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0,
+      "step": 24
+    },
+    {
+      "epoch": 0.043859649122807015,
+      "eval_loss": NaN,
+      "eval_runtime": 49.6144,
+      "eval_samples_per_second": 4.837,
+      "eval_steps_per_second": 2.419,
+      "step": 25
+    },
+    {
+      "epoch": 0.04736842105263158,
+      "grad_norm": NaN,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.05263157894736842,
+      "eval_loss": NaN,
+      "eval_runtime": 49.6176,
+      "eval_samples_per_second": 4.837,
+      "eval_steps_per_second": 2.418,
+      "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": 1.9392654521401344e+16,
+  "total_flos": 2.9088981782102016e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null