Training in progress, step 40, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0902123b7ce12f682124ca9b7659ceace9da91e87b23f67c825372f2e81c97
+oid sha256:b471266a90991ea66c7601f69d0e9aff06a8962022faa60188ed46a716c89d8b
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c06cc185129710fbc4aefbd4aecab61cbe55d72872505d4a12d4f40835976880
+oid sha256:ed6f7f8d04ad72e879047959c007e2ed191fb05126a1dd1916dde953c96f9f0c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec942292267bb06cc495f28f765abdfdf101d23971c1de481c4ea2a744d43b7
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.14925373134328357,
+  "epoch": 0.19900497512437812,
   "eval_steps": 5,
-  "global_step": 30,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,43 @@
       "eval_samples_per_second": 12.421,
       "eval_steps_per_second": 6.283,
       "step": 30
+    },
+    {
+      "epoch": 0.16417910447761194,
+      "grad_norm": NaN,
+      "learning_rate": 2.5685517452260567e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 0.17412935323383086,
+      "eval_loss": NaN,
+      "eval_runtime": 6.8394,
+      "eval_samples_per_second": 12.428,
+      "eval_steps_per_second": 6.287,
+      "step": 35
+    },
+    {
+      "epoch": 0.1791044776119403,
+      "grad_norm": NaN,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 0.19402985074626866,
+      "grad_norm": NaN,
+      "learning_rate": 5.478104631726711e-07,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.19900497512437812,
+      "eval_loss": NaN,
+      "eval_runtime": 6.8248,
+      "eval_samples_per_second": 12.455,
+      "eval_steps_per_second": 6.301,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -147,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.112830925340672e+16,
+  "total_flos": 1.483774567120896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null