Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1060a7fca1980d8430e89e1346e26327288872e04c64c7dc5ad730e5e819e9e7
+oid sha256:7627004b5709b0660422cbd70c6ac0b419042fef40957dc1b5cf176392fc657a
 size 403961210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:206cbcf6b3d5e71f5f2b30af10bad2fa0e04237c3638fb1873a1d609be82d65e
+oid sha256:6b0ef7915397502015c95bbe7ddaaea74270df10182e3225089e3815cd07e413
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
+oid sha256:1eef4c60eef56c59d148e4191bea64e9a3bf517b29f5a413c536dcdc8e61edf1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0588235294117647,
+  "epoch": 1.1647058823529413,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -221,6 +221,21 @@
       "eval_samples_per_second": 69.61,
       "eval_steps_per_second": 8.759,
       "step": 90
+    },
+    {
+      "epoch": 1.1176470588235294,
+      "grad_norm": NaN,
+      "learning_rate": 1.4411039697577175e-06,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 1.1647058823529413,
+      "eval_loss": NaN,
+      "eval_runtime": 4.3544,
+      "eval_samples_per_second": 69.355,
+      "eval_steps_per_second": 8.727,
+      "step": 99
     }
   ],
   "logging_steps": 5,
@@ -240,7 +255,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.915166806297805e+16,
+  "total_flos": 2.1071501130203136e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null