Training in progress, step 26, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d774e4637966928a617795fc0c3eebb3ad7e7153ca620acea8f9b2be3f84e7b
+oid sha256:765600a2e8d6be9b0bbfb75caaac7d04dda8e193f6b4feeac34b4f640fce2938
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb94c29888a6b84c5e0cd3746ef6c8fd70e42cc495671a91001b9f13041d2399
+oid sha256:322a97cf94d0a1106f2a31574761e008a02faf3cb921c0e9d9610b47b898b0fe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35e92785679980f3fcd23b14ce1acaffcae115e3e9164492d0e4b31775d32447
+oid sha256:d8712da1b2787df41952a507984ec77e0f72c59fac7ee6cf21606445686249de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006150206978119456,
+  "epoch": 0.012300413956238912,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -30,6 +30,21 @@
       "eval_samples_per_second": 17.927,
       "eval_steps_per_second": 8.963,
       "step": 13
+    },
+    {
+      "epoch": 0.009461856889414548,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.012300413956238912,
+      "eval_loss": NaN,
+      "eval_runtime": 49.6409,
+      "eval_samples_per_second": 17.929,
+      "eval_steps_per_second": 8.964,
+      "step": 26
     }
   ],
   "logging_steps": 10,
@@ -49,7 +64,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3984675689201664.0,
+  "total_flos": 8092588770852864.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null