Training in progress, step 150, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3e3cb36c280cfb01ac73a99ddbf9973c2057019fbe14027e45b990306e9157
+oid sha256:347d17149c3cc1b78e2c09d89fae5de9717242bba799dfaa2c8ce2abefa5b58f
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cb81b7c9730504bc1d548652797affe9958b5f68b25fefb7f810992b4fce281
+oid sha256:607198e0934bfa3a0c2e07cb88a946e7486b7ae6c8c9320a294db9aff4dfd81f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a71f60f9bd2ac4332e4682c06bcf0e8b6f23e0f17b0fa94d84f1fe3045e8b4a8
+oid sha256:b0edab479cf5df2fd0e0eb08833b9040a0342b7b3b1ce5f746c88e4c78156c68
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4591836734693877,
+  "epoch": 1.5306122448979593,
   "eval_steps": 13,
-  "global_step": 143,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -432,6 +432,27 @@
       "eval_samples_per_second": 36.421,
       "eval_steps_per_second": 4.635,
       "step": 143
+    },
+    {
+      "epoch": 1.469387755102041,
+      "grad_norm": NaN,
+      "learning_rate": 4.52511911603265e-07,
+      "loss": 0.0,
+      "step": 144
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": NaN,
+      "learning_rate": 1.132562476771959e-07,
+      "loss": 0.0,
+      "step": 147
+    },
+    {
+      "epoch": 1.5306122448979593,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 150
     }
   ],
   "logging_steps": 3,
@@ -446,12 +467,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.8908191965184e+16,
+  "total_flos": 4.081320507998208e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null