Training in progress, step 200, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eb69cffb024d0acadfed017480ed2bbab1e828a601aab179623209cf230ebe5
+oid sha256:4f8009fdc806005f5a11dfe3d501909749d95aec61cb68fbf25b5adf49c5f6f1
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55f5b8fc91a819fc39bd479452495c8f8f43e1c210ee91583af5c241cfc6079a
+oid sha256:ab25f1bb566d6940a6c530bc3bcd4512bcc2278b20c9a86ed24b271b2778f563
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4034969737726967,
+  "epoch": 0.5379959650302623,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 21.072,
       "eval_steps_per_second": 10.603,
       "step": 150
+    },
+    {
+      "epoch": 0.43039677202420984,
+      "grad_norm": NaN,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.45729657027572296,
+      "grad_norm": NaN,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.484196368527236,
+      "grad_norm": NaN,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.5110961667787491,
+      "grad_norm": NaN,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.5379959650302623,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.5379959650302623,
+      "eval_loss": NaN,
+      "eval_runtime": 7.4553,
+      "eval_samples_per_second": 21.059,
+      "eval_steps_per_second": 10.596,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.759936303104e+16,
+  "total_flos": 6.346581737472e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null