Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d1d00962b34e17a50f93dcb472397e3f035895271a4c90999415b1e14287aaa
+oid sha256:0ac2d8feab6cb233c72156da7d84b90e6b5b6afc1390c6c482eb3c630ae0e830
 size 127788180

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8f464a425f07706e30bf8638dd8ea141b3dee643ecebb4338bcd7a3756a09f2
+oid sha256:5a3ba56a9898bfda216d3b1f75e9e6c6fbb66b131d3905195c470a33236a6337
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
+oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001993661179838462,
+  "epoch": 0.0025559758715877723,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,20 @@
       "eval_samples_per_second": 21.12,
       "eval_steps_per_second": 10.563,
       "step": 39
+    },
+    {
+      "epoch": 0.0020447806972702176,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0025559758715877723,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6202914011873280.0,
+  "total_flos": 7952453861376000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null