Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c7e78804dd19cd55c65a1b6b95b5c55996dc7c4a8c1d11b210ee7423c2313fc
+oid sha256:6a04667c008502e91e06fe4ddbdbe9546b47afa389d863fcab516dd677024a7a
 size 267835644

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:379de5d281003514e53cff5d5da207fad69f34d9d6b845d9d7026096a123dc3e
+oid sha256:d1976ef43ce351bc5e7482a4f88d5b02ba7afb62acc5f9c10faaf9ea69ee52ad
 size 535733434

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca9f956b39f51ec6c505767cab574a3581a608a9ada47e5e1ea34242b023aaa2
+oid sha256:4b9ae8ccced4a36fd061b274c705b6295d38a5288bf82c4c189b032dcc5f78bb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27ebe124b49d962b3686f19f4ac88c29ccf1175d00244819004baf43745fc5ca
+oid sha256:87a047fc70d34ba9e25294567dfd8e018dbff83f6d11a990d60dd7e409be4fbb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7293047058493298,
   "best_model_checkpoint": "training_dir/checkpoint-5000",
-  "epoch": 0.7829627309740056,
+  "epoch": 0.9395552771688067,
   "eval_steps": 1000,
-  "global_step": 5000,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,25 @@
       "eval_samples_per_second": 76.93,
       "eval_steps_per_second": 9.616,
       "step": 5000
+    },
+    {
+      "epoch": 0.9395552771688067,
+      "grad_norm": 16.398216247558594,
+      "learning_rate": 9.131944444444445e-06,
+      "loss": 0.4562,
+      "step": 6000
+    },
+    {
+      "epoch": 0.9395552771688067,
+      "eval_accuracy": 0.728583916083916,
+      "eval_f1": 0.722523941260205,
+      "eval_loss": 0.764935314655304,
+      "eval_precision": 0.7390044648352858,
+      "eval_recall": 0.728583916083916,
+      "eval_runtime": 29.8199,
+      "eval_samples_per_second": 76.727,
+      "eval_steps_per_second": 9.591,
+      "step": 6000
     }
   ],
   "logging_steps": 1000,
@@ -121,7 +140,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5037055031256768.0,
+  "total_flos": 6048548589955680.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null