Training in progress, step 10000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:871ebcfdbf95ed1b85e34a0d8c4baff06510b3c4b138cc50fc955cc995e23c61
+oid sha256:cf9880d96a86df526af2581930438d89880e300ecdc4bef1a55d85f888f89073
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c530228c57dccf707451e18a5aa17e60c2ebd57f76855004ad3cf222094b874c
+oid sha256:1772e3c93bae9f3496c8b26bc91c354020c3df87ce73758f9047a700a19f43a7
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de0999d7eb4ee09cb700dbfb0de90b09986dee497b72b547b3437bdc5aad41a3
+oid sha256:405962457206f8e1fb8df318cb7d0e755c7b9e0fa0fe32525b189f837ff53cb7
 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": 0.7293047058493298,
-  "best_model_checkpoint": "training_dir/checkpoint-5000",
-  "epoch": 1.4093329157532102,
+  "best_metric": 0.7351907898564811,
+  "best_model_checkpoint": "training_dir/checkpoint-10000",
+  "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": 75.707,
       "eval_steps_per_second": 9.463,
       "step": 9000
+    },
+    {
+      "epoch": 1.5659254619480114,
+      "grad_norm": 9.159900665283203,
+      "learning_rate": 8.500631313131314e-06,
+      "loss": 0.3932,
+      "step": 10000
+    },
+    {
+      "epoch": 1.5659254619480114,
+      "eval_accuracy": 0.7443181818181818,
+      "eval_f1": 0.7351907898564811,
+      "eval_loss": 0.9013388156890869,
+      "eval_precision": 0.7458339781734145,
+      "eval_recall": 0.7443181818181818,
+      "eval_runtime": 29.7576,
+      "eval_samples_per_second": 76.888,
+      "eval_steps_per_second": 9.611,
+      "step": 10000
     }
   ],
   "logging_steps": 1000,
@@ -197,7 +216,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9062108875550700.0,
+  "total_flos": 1.0072339831839852e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null