Training in progress, step 45, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b411d8f3e7add8b3d93adcf458ccd53cd6ff52a54095368d2ebd43894569e445
+oid sha256:c210e3897c6c86fe375c0dcf4a9243a3b5d968a30a0c410ea21ad00754c02b03
 size 240145026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e40dca7108cb0726f72ab1eed645c75414cec0897da6df467a42096be439a048
+oid sha256:840017c18eec8d45f1c67e338cd06d19e25c6b6193df0faed965125ac76f040b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1fbe8f3807fcf2c9b342444bf912c2b4a5837aba74951c80e3f443bde6ab488
+oid sha256:e917c3eea1680bab35c1f582cbc388a7464296952762325512c323f5f76cc5cb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0032345467563280033,
+  "epoch": 0.004043183445410004,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 26.823,
       "eval_steps_per_second": 13.411,
       "step": 36
+    },
+    {
+      "epoch": 0.0035040923193553368,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017343225094356855,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.0037736378823826707,
+      "grad_norm": NaN,
+      "learning_rate": 0.00016494480483301836,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.004043183445410004,
+      "grad_norm": NaN,
+      "learning_rate": 0.00015555702330196023,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 0.004043183445410004,
+      "eval_loss": NaN,
+      "eval_runtime": 1398.6647,
+      "eval_samples_per_second": 26.804,
+      "eval_steps_per_second": 13.402,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.756732538945536e+16,
+  "total_flos": 4.706377867984896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null