Training in progress, step 11000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c808475ef21e058693edab788f7732c8f7e68bf5cafca868b958716451ec0144
+oid sha256:f2d9fb3b6451701ab0f2b4824a5375c62006fafa087665c750e5619e2afc89a5
 size 498615900

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1aedc6950d3b3fb19b031a9167a1fade50d5dce31f54cb161dfaeb26e0e1e31
+oid sha256:7780208e680819257b41d50d9dbf64fedfef08bbc5208d0f983c6de4437369bb
 size 997351674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:052183e50b1b5ae1798367b38b1751bac816715b41cae2d732d506663586f370
+oid sha256:ff74a6d71562ab6f97231e9e623c95eb7bdf04875ef1e5eba2c042d1af40b2d6
 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": 0.7624731472235634,
   "best_model_checkpoint": "training_dir/checkpoint-6000",
-  "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": 48.038,
       "eval_steps_per_second": 6.005,
       "step": 10000
+    },
+    {
+      "epoch": 1.7225180081428124,
+      "grad_norm": 44.26694107055664,
+      "learning_rate": 8.342803030303031e-06,
+      "loss": 0.3903,
+      "step": 11000
+    },
+    {
+      "epoch": 1.7225180081428124,
+      "eval_accuracy": 0.7552447552447552,
+      "eval_f1": 0.7447143825904207,
+      "eval_loss": 0.9456614255905151,
+      "eval_precision": 0.7531489883387709,
+      "eval_recall": 0.7552447552447552,
+      "eval_runtime": 47.5072,
+      "eval_samples_per_second": 48.161,
+      "eval_steps_per_second": 6.02,
+      "step": 11000
     }
   ],
   "logging_steps": 1000,
@@ -216,7 +235,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.0475444028334652e+16,
+  "total_flos": 2.2525788225157308e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null