Training in progress, step 6, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c0738670dc2b6a97c831aa719211ea4a2ace79a726920aced5e9dfae1be380a
+oid sha256:0716e8cd0716ed13e89d4d72d43d071a71741c79c2d481e68fc4ba0145fb0c6d
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee98d32837ae1d3dbfef4ce2e075517075d618418a072afd3b231336a8448da
+oid sha256:69c293a25ab19b4a61cf39ee3caa3e9ac1b234a2c7b35f74a010d03dda7d741b
 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": 28.454,
       "eval_steps_per_second": 18.97,
       "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": 0.1041,
+      "eval_samples_per_second": 28.819,
+      "eval_steps_per_second": 19.212,
+      "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": 129719303405568.0,
+  "total_flos": 202686411571200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null