Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5df9672ac81c739a0742b305bf73c9ad7ad732b0261440da07a75a00778d93a6
+oid sha256:d20655116a9e6831b9bf58db8165360b40fe252b7898bbe49fcdaa5a0f9bdc50
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f65d33f8dbb303a0d5f68445f3c91506d6bca32bb2475114b5510685edbdcace
+oid sha256:a002c35283ee15865b652908226f5a02d99c68599148fb6605a660ea5c853706
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
+oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004655734312761885,
+  "epoch": 0.005121307744038074,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 14.126,
       "eval_steps_per_second": 1.766,
       "step": 90
+    },
+    {
+      "epoch": 0.0048109254565206145,
+      "grad_norm": NaN,
+      "learning_rate": 7.426068431000882e-07,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.004966116600279344,
+      "grad_norm": NaN,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.005121307744038074,
+      "grad_norm": NaN,
+      "learning_rate": 1.522932452260595e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.005121307744038074,
+      "eval_loss": NaN,
+      "eval_runtime": 2305.688,
+      "eval_samples_per_second": 14.121,
+      "eval_steps_per_second": 1.765,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1762254882013184e+17,
+  "total_flos": 1.2938480370214502e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null