Training in progress, step 4000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d16848521b5f211c51bd2b253bdc28aaf9a346fbc5fd4aec9c15cb5825f28615
+oid sha256:8bc5bd5a71c67b305edcef1e48d81dd18c0068f2c4658bceee353301acf3a4b5
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a419bb2d2294db4015ccf4f984a71493d06deda8043d661fc666e34e19d15d
+oid sha256:f69c75e81b22152cc1ea3af87eb6846cc209c513d4ddbb848997b84594b92e09
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd680bce7049a97dfbda7e74506101a3130ce0e3b97bfb0721afdcd06344a009
+oid sha256:ea6da068f05bdae369cb14af09b1a103dcf7ea57f912e3af8f0bf546abf4d1c9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fce293a85c3a6d15ea092b89fa1d71f8b33619837f3a63ea3c7e7e335811845b
+oid sha256:934377a13b65a28f5105294df26e4fe3b57c4d88e0a4908173ecc003fa91b9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6892053083671648,
-  "best_model_checkpoint": "training_dir/checkpoint-3000",
-  "epoch": 0.46977763858440336,
+  "best_metric": 0.727562941019853,
+  "best_model_checkpoint": "training_dir/checkpoint-4000",
+  "epoch": 0.6263701847792045,
   "eval_steps": 1000,
-  "global_step": 3000,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,25 @@
       "eval_samples_per_second": 77.168,
       "eval_steps_per_second": 9.646,
       "step": 3000
+    },
+    {
+      "epoch": 0.6263701847792045,
+      "grad_norm": 28.96643829345703,
+      "learning_rate": 9.44760101010101e-06,
+      "loss": 0.4593,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6263701847792045,
+      "eval_accuracy": 0.7338286713286714,
+      "eval_f1": 0.727562941019853,
+      "eval_loss": 0.7618293762207031,
+      "eval_precision": 0.7330094463964066,
+      "eval_recall": 0.7338286713286714,
+      "eval_runtime": 29.7317,
+      "eval_samples_per_second": 76.955,
+      "eval_steps_per_second": 9.619,
+      "step": 4000
     }
   ],
   "logging_steps": 1000,
@@ -83,7 +102,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3022521140484288.0,
+  "total_flos": 4032940452214896.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null