Training in progress, step 3000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:242cd9b3efe54016ea7e4a89d51ef6411a671bb1527f976cdcdbe6520e0f845b
+oid sha256:d16848521b5f211c51bd2b253bdc28aaf9a346fbc5fd4aec9c15cb5825f28615
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c2c2aa104d93faa88772c843d01d9fe4cd91c524e96a31c64e168ceb9c5aba5
+oid sha256:30a419bb2d2294db4015ccf4f984a71493d06deda8043d661fc666e34e19d15d
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb957c1ac7b25fd12c650020dc9afd45f1bbd680fa7794b06deb24956308ae77
+oid sha256:cd680bce7049a97dfbda7e74506101a3130ce0e3b97bfb0721afdcd06344a009
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30e2a9d4d34dceffa0b31a9e7095a6b0d17a664b3a581f4c86f30752f304b65d
+oid sha256:fce293a85c3a6d15ea092b89fa1d71f8b33619837f3a63ea3c7e7e335811845b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6840354165768472,
-  "best_model_checkpoint": "training_dir/checkpoint-2000",
-  "epoch": 0.31318509238960224,
+  "best_metric": 0.6892053083671648,
+  "best_model_checkpoint": "training_dir/checkpoint-3000",
+  "epoch": 0.46977763858440336,
   "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": 76.707,
       "eval_steps_per_second": 9.588,
       "step": 2000
+    },
+    {
+      "epoch": 0.46977763858440336,
+      "grad_norm": 2.5105936527252197,
+      "learning_rate": 9.605429292929293e-06,
+      "loss": 0.4747,
+      "step": 3000
+    },
+    {
+      "epoch": 0.46977763858440336,
+      "eval_accuracy": 0.7076048951048951,
+      "eval_f1": 0.6892053083671648,
+      "eval_loss": 0.8822671175003052,
+      "eval_precision": 0.7144457563342712,
+      "eval_recall": 0.7076048951048951,
+      "eval_runtime": 29.6497,
+      "eval_samples_per_second": 77.168,
+      "eval_steps_per_second": 9.646,
+      "step": 3000
     }
   ],
   "logging_steps": 1000,
@@ -64,7 +83,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2013142958281728.0,
+  "total_flos": 3022521140484288.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null