Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf9880d96a86df526af2581930438d89880e300ecdc4bef1a55d85f888f89073
+oid sha256:9c69342f9f8cbafbe88e53a1502bc9cf5e2b17b9101e74f4510c6e26f122fd23
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1772e3c93bae9f3496c8b26bc91c354020c3df87ce73758f9047a700a19f43a7
+oid sha256:f833a5c16ee95394fc72af6094e6983e4669a09de851d977753fe331a396533c
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:405962457206f8e1fb8df318cb7d0e755c7b9e0fa0fe32525b189f837ff53cb7
+oid sha256:2373950d6eeee44479ba05e37591ef1c6aa608226cacd6fdf2d774c4934649f3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8409b85759d90925b91547cef68cf8d92d7246de5d32ea5c6e2cb9cb720fc23
+oid sha256:884b5db9dd691ce707dfb4a94a86e37c81019d23d8b0ae7bb40693c59676428e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7351907898564811,
   "best_model_checkpoint": "training_dir/checkpoint-10000",
-  "epoch": 1.5659254619480114,
+  "epoch": 1.7225180081428124,
   "eval_steps": 1000,
-  "global_step": 10000,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -197,6 +197,25 @@
       "eval_samples_per_second": 76.888,
       "eval_steps_per_second": 9.611,
       "step": 10000
+    },
+    {
+      "epoch": 1.7225180081428124,
+      "grad_norm": 15.05197811126709,
+      "learning_rate": 8.342803030303031e-06,
+      "loss": 0.3855,
+      "step": 11000
+    },
+    {
+      "epoch": 1.7225180081428124,
+      "eval_accuracy": 0.736013986013986,
+      "eval_f1": 0.724627459472447,
+      "eval_loss": 0.8597542643547058,
+      "eval_precision": 0.7372131719239822,
+      "eval_recall": 0.736013986013986,
+      "eval_runtime": 29.7901,
+      "eval_samples_per_second": 76.804,
+      "eval_steps_per_second": 9.601,
+      "step": 11000
     }
   ],
   "logging_steps": 1000,
@@ -216,7 +235,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0072339831839852e+16,
+  "total_flos": 1.1082287220046812e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null