Training in progress, step 13700, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:788f0a9eff630ca6c52493f2edf2dbdc21f975a3aa5704a4b73beaa033619871
+oid sha256:e371f5504566f00a547c6bf5dc76271ea0ad06d762d643694654527dc3346840
 size 1716360444

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69dc091531e18951b58a324059cfe6c9652a9413b6b83e33460cdd2a96993f24
+oid sha256:16e466d2ee4c48404eed81b17e1872461c9a51ce80d03b824705ab4d31a12f3d
 size 3433062021

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12adab35ae48469922be738c04a81e7ee535ebff85c8a60e17fd4cd6a02709d4
+oid sha256:cc5d802f36cedde4a662f27d6a60aa6a1c9ef6ec948baf9bbe72cb2ba9b0eb3d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d93dc684a8e187c71e594356b780264cb734773ada5bad2a28dbdd4507a46ff
+oid sha256:a2ecaf274f2d11ebe93c1edafaab1e1809e0fd9e148dbce8088ae8dd2ca43011
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6632016632016633,
+  "epoch": 1.675431087195793,
   "eval_steps": 1000,
-  "global_step": 13600,
+  "global_step": 13700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1063,6 +1063,13 @@
       "learning_rate": 3.755265096622077e-05,
       "loss": 1.3863,
       "step": 13600
+    },
+    {
+      "epoch": 1.675431087195793,
+      "grad_norm": 0.00034479121677577496,
+      "learning_rate": 3.7386132941443e-05,
+      "loss": 1.3863,
+      "step": 13700
     }
   ],
   "logging_steps": 100,
@@ -1082,7 +1089,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2544384540672e+16,
+  "total_flos": 3.2783681485824e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null