Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63ac2740529d45592199af761ef88351d8bf33a0ced6a1c7bfa51ae6a262e3e
+oid sha256:515b87cf0a6a3172ae5c57e520f7d2104f42512194d4ce128b9412164367303b
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44796c23481279b04feeb89690334c50fc7938f1076fc5c8d84157bb2cd2e390
+oid sha256:c3883c680b06616a54d83f9d39716d483ff373243037f1e452335ed8a9e5c4a7
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d406d538cd09764f86141c5283b0697ea9959a1fda63bbb795129d06c6b2a1d8
+oid sha256:d00d1c63ddb24d4f81ac1488700230d892db68acd5821c3502fd0057c64003c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4841384879f1112c4a211310579ca4e33089f588151f1074a18f817f4e1294d
+oid sha256:33ab6338b810850df27c82b146a27ff4faf907486cbc0e08077af4440dd9d4fb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6366336108184594,
-  "best_model_checkpoint": "training_dir/checkpoint-2000",
-  "epoch": 0.2119317579739324,
+  "best_metric": 0.669233772837662,
+  "best_model_checkpoint": "training_dir/checkpoint-3000",
+  "epoch": 0.31789763696089857,
   "eval_steps": 1000,
-  "global_step": 2000,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,25 @@
       "eval_samples_per_second": 88.066,
       "eval_steps_per_second": 11.008,
       "step": 2000
+    },
+    {
+      "epoch": 0.31789763696089857,
+      "grad_norm": 8.239383697509766,
+      "learning_rate": 9.733674230318526e-06,
+      "loss": 0.5349,
+      "step": 3000
+    },
+    {
+      "epoch": 0.31789763696089857,
+      "eval_accuracy": 0.6914335664335665,
+      "eval_f1": 0.669233772837662,
+      "eval_loss": 0.8858013153076172,
+      "eval_precision": 0.6967032053774095,
+      "eval_recall": 0.6914335664335665,
+      "eval_runtime": 25.9486,
+      "eval_samples_per_second": 88.174,
+      "eval_steps_per_second": 11.022,
+      "step": 3000
     }
   ],
   "logging_steps": 1000,
@@ -64,7 +83,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1940081745396960.0,
+  "total_flos": 2912647822914960.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null