Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0746bc9bd8e01351f0af8dfdcca317812440d3459dd4fd0b1a8a4d17d2795f18
+oid sha256:c808475ef21e058693edab788f7732c8f7e68bf5cafca868b958716451ec0144
 size 498615900

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a0b635dac92d0112c8e3734ea4e409d540e536a02d8dd568d88385630ea710
+oid sha256:b1aedc6950d3b3fb19b031a9167a1fade50d5dce31f54cb161dfaeb26e0e1e31
 size 997351674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a983b82f33fb22e5ea2ad59f31f42e8cddca7bc637db21ed5f9dc99571dbef03
+oid sha256:052183e50b1b5ae1798367b38b1751bac816715b41cae2d732d506663586f370
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39893f8b6ee435640978da157dad268e2888562745141a95ed487427fd81ebb5
+oid sha256:b8409b85759d90925b91547cef68cf8d92d7246de5d32ea5c6e2cb9cb720fc23
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7624731472235634,
   "best_model_checkpoint": "training_dir/checkpoint-6000",
-  "epoch": 1.4093329157532102,
+  "epoch": 1.5659254619480114,
   "eval_steps": 1000,
-  "global_step": 9000,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -178,6 +178,25 @@
       "eval_samples_per_second": 48.153,
       "eval_steps_per_second": 6.019,
       "step": 9000
+    },
+    {
+      "epoch": 1.5659254619480114,
+      "grad_norm": 5.539546489715576,
+      "learning_rate": 8.500631313131314e-06,
+      "loss": 0.401,
+      "step": 10000
+    },
+    {
+      "epoch": 1.5659254619480114,
+      "eval_accuracy": 0.7622377622377622,
+      "eval_f1": 0.7562280560821415,
+      "eval_loss": 0.951400876045227,
+      "eval_precision": 0.760121427774359,
+      "eval_recall": 0.7622377622377622,
+      "eval_runtime": 47.6294,
+      "eval_samples_per_second": 48.038,
+      "eval_steps_per_second": 6.005,
+      "step": 10000
     }
   ],
   "logging_steps": 1000,
@@ -197,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8425658947524668e+16,
+  "total_flos": 2.0475444028334652e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null