Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dd41644b46c8e96d6b145ae0e19f4a7f62145b5a622196de21adccfa99ebcb9
+oid sha256:b8c0d8a34a23ea500b10e94e2714eecf4473da1619425477861639db897058d2
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae2be3b7bc5de30f888aa7806ac10f8ac5d98cac9fed1e3f02f3349c405f5610
+oid sha256:dc43b18bca1154840a039f0dc4227703e7dfde494131380c48b07aeae0a12235
 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": 0.001575248404556103,
+  "epoch": 0.0020195492366103887,
   "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": 34.459,
       "eval_steps_per_second": 17.233,
       "step": 39
+    },
+    {
+      "epoch": 0.0016156393892883109,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.0020195492366103887,
+      "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": 3308132147134464.0,
+  "total_flos": 4206637174751232.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null