Training in progress, step 12000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c6bc66d4b06be01722ead53718cdb38f760258e27b606dda260284c694f6516
+oid sha256:8a908ddb4e1d0cb01ff53d6d4956579766f00d9bef503b98c5bec7c6dc8b5b3f
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d7efed836b0a7a09c864c26b9572f9547494689160dc13e5d77f14817033216
+oid sha256:b29f0f01286b776ce5d34976c5047f77bd8b668153ee2e8a06d87389a148cabe
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae59f0f934189fcaa1a1041dd640da3c651fe2389123125ddf12471b0819bde8
+oid sha256:7e1b0bf54794dbc1aa0f801e685ac358890e80baa7b67e058aa2ff95290be389
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e82a21c3091e4958c484cdc7bf981ac78cd588dced7632b6352c65dac794dad2
+oid sha256:c7b9276fef8f7eda277dcd2d635a37b8e237abadc5a5e9f8450094c074a687d1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7187402398550484,
-  "best_model_checkpoint": "training_dir/checkpoint-10000",
-  "epoch": 1.165624668856628,
+  "best_metric": 0.7260786855980778,
+  "best_model_checkpoint": "training_dir/checkpoint-12000",
+  "epoch": 1.2715905478435943,
   "eval_steps": 1000,
-  "global_step": 11000,
+  "global_step": 12000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -216,6 +216,25 @@
       "eval_samples_per_second": 87.688,
       "eval_steps_per_second": 10.961,
       "step": 11000
+    },
+    {
+      "epoch": 1.2715905478435943,
+      "grad_norm": 3.347665548324585,
+      "learning_rate": 8.774901459465218e-06,
+      "loss": 0.4096,
+      "step": 12000
+    },
+    {
+      "epoch": 1.2715905478435943,
+      "eval_accuracy": 0.7338286713286714,
+      "eval_f1": 0.7260786855980778,
+      "eval_loss": 0.8679103851318359,
+      "eval_precision": 0.7338714881942328,
+      "eval_recall": 0.7338286713286714,
+      "eval_runtime": 26.1513,
+      "eval_samples_per_second": 87.491,
+      "eval_steps_per_second": 10.936,
+      "step": 12000
     }
   ],
   "logging_steps": 1000,
@@ -235,7 +254,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0678923524708784e+16,
+  "total_flos": 1.1650955583502656e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null