Training in progress, step 18, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4b430c53d00e36230c97d15330321d89283f1a2ca0d556fef8c1adb6eaadf8
+oid sha256:4d94de2d90888ff412be9030ba29b6ba01bbe7b6fc630ac425ff3dc994ec422d
 size 4628218

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ecbc9473bce22fd4e8ced00e412be5ae768ff439263e805330760249992215
+oid sha256:744f4b25d9d27786fbe13b26cfbe9f12e3cb849ad67e1877f33c639773c136fa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1fa12db6e65a79cc008f6035c457ab68bb8c45c7fe7a2790ea24e528e6b743
+oid sha256:a4b679dfcad285902b67d18379c2cc1ca0aebfc7646cb33fa82a3fb8ed15c820
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.016311735387403714,
+  "epoch": 0.03262347077480743,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,28 @@
       "eval_samples_per_second": 284.955,
       "eval_steps_per_second": 35.728,
       "step": 9
+    },
+    {
+      "epoch": 0.01812415043044857,
+      "grad_norm": NaN,
+      "learning_rate": 7.5e-05,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.02718622564567286,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001125,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.03262347077480743,
+      "eval_loss": NaN,
+      "eval_runtime": 6.9012,
+      "eval_samples_per_second": 284.299,
+      "eval_steps_per_second": 35.646,
+      "step": 18
     }
   ],
   "logging_steps": 5,
@@ -49,7 +71,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 161783532748800.0,
+  "total_flos": 323567065497600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null