Training in progress, step 150, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae56495bc22a94f1c21dfab10ffcb919002e044c09149f05ea612ed2638857fa
+oid sha256:1ed7305e40b81e4dc54aa2b8c7af62094df217791884070b20e9d78020af2424
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64d4968559533980e4aa75808bb9d31ceeb8c578adf5720f38446c96e6557139
+oid sha256:7b9bcc60e9ef74261dfa7dc11ed8bffcdebb36a349d5be503aa5c8f1b28d3912
 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": 0.02020558832880003,
+  "epoch": 0.021194673072167863,
   "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": 50.542,
       "eval_steps_per_second": 6.318,
       "step": 143
+    },
+    {
+      "epoch": 0.020346886149281148,
+      "grad_norm": NaN,
+      "learning_rate": 4.52511911603265e-07,
+      "loss": 0.0,
+      "step": 144
+    },
+    {
+      "epoch": 0.020770779610724505,
+      "grad_norm": NaN,
+      "learning_rate": 1.132562476771959e-07,
+      "loss": 0.0,
+      "step": 147
+    },
+    {
+      "epoch": 0.021194673072167863,
+      "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": 3.0504014290354176e+16,
+  "total_flos": 3.19972177870848e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null