Training in progress, step 125, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:182bf3c39d6c91d05aa220ffcd319dd6528addc989a54949e2c0ca43c8ac6576
+oid sha256:b81ea93ac3b894bdf225bcf512002650ddb7c1054f564bf9978ee2109ed75c81
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335aa2100acb8a771c7f2d5f4036044fb43a252a64d2da3b9ac21b9b984ad771
+oid sha256:4ee00649ffa674df7ba84e043487069fd7706a186415980a37c8f74056517ac4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a6931f5ae97ea6589f97d1d8881c031e8cd196fac6a4029b4ea8f8c7247406b
+oid sha256:25c0243da09e051ffbb600413baac079966a139cd6939cbef7eb321283bd0767
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.022975137957633656,
+  "epoch": 0.023734646650447992,
   "eval_steps": 25,
-  "global_step": 121,
+  "global_step": 125,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -894,6 +894,42 @@
       "learning_rate": 7.153073658162646e-07,
       "loss": 0.0,
       "step": 121
+    },
+    {
+      "epoch": 0.02316501513083724,
+      "grad_norm": NaN,
+      "learning_rate": 4.025706004760932e-07,
+      "loss": 0.0,
+      "step": 122
+    },
+    {
+      "epoch": 0.023354892304040822,
+      "grad_norm": NaN,
+      "learning_rate": 1.7898702322648453e-07,
+      "loss": 0.0,
+      "step": 123
+    },
+    {
+      "epoch": 0.023544769477244407,
+      "grad_norm": NaN,
+      "learning_rate": 4.475677164966774e-08,
+      "loss": 0.0,
+      "step": 124
+    },
+    {
+      "epoch": 0.023734646650447992,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 125
+    },
+    {
+      "epoch": 0.023734646650447992,
+      "eval_loss": NaN,
+      "eval_runtime": 4140.6967,
+      "eval_samples_per_second": 4.284,
+      "eval_steps_per_second": 2.142,
+      "step": 125
     }
   ],
   "logging_steps": 1,
@@ -908,12 +944,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7.970830675869696e+17,
+  "total_flos": 8.238716325388616e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null