Training in progress, step 13000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a908ddb4e1d0cb01ff53d6d4956579766f00d9bef503b98c5bec7c6dc8b5b3f
+oid sha256:07394dd2da2fc8953cab465ecc516b2b637a9ad1e5f80b5e3ea2227894fa654a
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b29f0f01286b776ce5d34976c5047f77bd8b668153ee2e8a06d87389a148cabe
+oid sha256:78de506312ed56afb09869d301b9813ec41093ce0949b835b41413fe2335de94
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e1b0bf54794dbc1aa0f801e685ac358890e80baa7b67e058aa2ff95290be389
+oid sha256:d92adf6dbb6d04b5365a21d7e5c277f9e5493f67b515b76e0f0b04c6e28d7e18
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7b9276fef8f7eda277dcd2d635a37b8e237abadc5a5e9f8450094c074a687d1
+oid sha256:efac40282b6ccc72dd2d6d02d04092dc1f619670b356e71b004fd44491288981
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7260786855980778,
   "best_model_checkpoint": "training_dir/checkpoint-12000",
-  "epoch": 1.2715905478435943,
+  "epoch": 1.3775564268305605,
   "eval_steps": 1000,
-  "global_step": 12000,
+  "global_step": 13000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -235,6 +235,25 @@
       "eval_samples_per_second": 87.491,
       "eval_steps_per_second": 10.936,
       "step": 12000
+    },
+    {
+      "epoch": 1.3775564268305605,
+      "grad_norm": 15.350415229797363,
+      "learning_rate": 8.668371151592628e-06,
+      "loss": 0.3868,
+      "step": 13000
+    },
+    {
+      "epoch": 1.3775564268305605,
+      "eval_accuracy": 0.7268356643356644,
+      "eval_f1": 0.7121431239588121,
+      "eval_loss": 0.9578595161437988,
+      "eval_precision": 0.7318944469113846,
+      "eval_recall": 0.7268356643356644,
+      "eval_runtime": 25.9641,
+      "eval_samples_per_second": 88.122,
+      "eval_steps_per_second": 11.015,
+      "step": 13000
     }
   ],
   "logging_steps": 1000,
@@ -254,7 +273,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1650955583502656e+16,
+  "total_flos": 1.2625401075755184e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null