Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c1ae2560015323435492196bec6a8736a11a4fa7e0125e83be82f37c96d74b
+oid sha256:85a364db9c7f6f2f5f06abfc82286fd338e35398b9bed16aeeb9e8202728c415
 size 70674004

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a53a508a4ce3f62bf889a072faf0852fce1aa0e321838e146e5720292e6b860a
+oid sha256:997b65752d298b6b114ea1a250e02363747d1128ad12c30762f0b1c94e70d30e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917587e2c0a52fd7c3d6680e02e388879c84c249a215f319208d6a9951b36ba9
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7619047619047619,
+  "epoch": 1.1428571428571428,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 14.987,
       "eval_steps_per_second": 9.991,
       "step": 4
+    },
+    {
+      "epoch": 0.9523809523809523,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 0.0,
+      "step": 6
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "eval_loss": NaN,
+      "eval_runtime": 0.2101,
+      "eval_samples_per_second": 14.279,
+      "eval_steps_per_second": 9.519,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -73,12 +95,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1378799358836736.0,
+  "total_flos": 2154373998182400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null