Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb38fcc937c94e156f08a2e15f02d498d3b79358d9123cd2194a960ee6ef559f
+oid sha256:0e68230f20cd63ff99df7fa109e58cd76e033f8340ac50d35d2f7b356518119e
 size 69844690

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b14aba306d43aa11411cf19f21eb8eed734ad54f9d36f6deed699e0278723edf
+oid sha256:296b33cdc44ff7ea9b92973992937930ce2bd345a45dac3efdfb0792c06bac1f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c792918044964431737f4cb39f3769dbfd230048b1125ac69a6439eb6c8534b
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02738319356494951,
+  "epoch": 0.03422899195618689,
   "eval_steps": 13,
-  "global_step": 40,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -130,6 +130,27 @@
       "eval_samples_per_second": 42.812,
       "eval_steps_per_second": 21.441,
       "step": 39
+    },
+    {
+      "epoch": 0.028752353243196988,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.030806092760568202,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.03285983227793941,
+      "grad_norm": NaN,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 0.0,
+      "step": 48
     }
   ],
   "logging_steps": 3,
@@ -144,12 +165,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 671426932899840.0,
+  "total_flos": 842263371448320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null