Training in progress, step 54, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c210e3897c6c86fe375c0dcf4a9243a3b5d968a30a0c410ea21ad00754c02b03
+oid sha256:7eb24f8916d7d1653746d40409f0668d46e875d4337228061a96e1bde68658a2
 size 240145026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840017c18eec8d45f1c67e338cd06d19e25c6b6193df0faed965125ac76f040b
+oid sha256:a6373884c409fa797b7259c6d64c1de3929dfd27f38b8f95c7509cd031abd5ec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
+oid sha256:f449418676ee143dc49fe68c0605204371c150076b291ef62a6b7b955efd8f73
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004043183445410004,
+  "epoch": 0.004851820134492005,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 26.804,
       "eval_steps_per_second": 13.402,
       "step": 45
+    },
+    {
+      "epoch": 0.004312729008437338,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.0045822745714646715,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001346117057077493,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.004851820134492005,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.004851820134492005,
+      "eval_loss": NaN,
+      "eval_runtime": 1397.5409,
+      "eval_samples_per_second": 26.826,
+      "eval_steps_per_second": 13.413,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.706377867984896e+16,
+  "total_flos": 5.639927513481216e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null