Training in progress, step 54, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1d068c9e12e77a9e0be4657461e0f3b3ce24dcf1db781c5ff4d5308370941a8
+oid sha256:167982673263fefed59672346edc9f1210361bb99721b1c2d1a3bd53cefcce5d
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6ad7439565a5462d968f8d3364199f027aa6f68d9890049e5a20a8e24781131
+oid sha256:cea0571e03c42072c2619a6841806791c3454e943bf747e8a4e1158abf717848
 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": 0.01624805361857694,
+  "epoch": 0.01949766434229233,
   "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": 9.655,
       "eval_steps_per_second": 4.828,
       "step": 45
+    },
+    {
+      "epoch": 0.017331257193148736,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 0.0,
+      "step": 48
+    },
+    {
+      "epoch": 0.018414460767720534,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001346117057077493,
+      "loss": 0.0,
+      "step": 51
+    },
+    {
+      "epoch": 0.01949766434229233,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012334453638559057,
+      "loss": 0.0,
+      "step": 54
+    },
+    {
+      "epoch": 0.01949766434229233,
+      "eval_loss": NaN,
+      "eval_runtime": 966.6085,
+      "eval_samples_per_second": 9.651,
+      "eval_steps_per_second": 4.826,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.3873779188891648e+17,
+  "total_flos": 2.8648535026669978e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null