Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4232b6d791f9ba6d7568eff0f6f15e9648e69bdca43b2a90646770e2c33cbb8c
+oid sha256:b257616acfcf1172ad314132418975d4a42d2853b8150b66345d9c093b0368af
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f22ee2bd42680b5f198191658fb24f22c66fd0968ab26c6e7ce687248687a73
+oid sha256:0f5adca46d5768b2528d11214bf50c169d41422785e8b729921c5399a7fed5df
 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": 0.034210526315789476,
+  "epoch": 0.043859649122807015,
   "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": 33.177,
       "eval_steps_per_second": 16.589,
       "step": 39
+    },
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.043859649122807015,
+      "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": 3447856753016832.0,
+  "total_flos": 4420329170534400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null