Training in progress, epoch 3, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:610aeb0cae11943ac229dd161a4cba3f7ac2c6c4a5228df85ee96f46ce3f6a37
+oid sha256:f4520baad3f6b69630065cdafd5c5b37d97d73083631718eb2d3f930865f247b
 size 498615900

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:081d184c3a09c40305064c7b7db7573966885c1810f831eac5b01bd70f2e2757
+oid sha256:6852a54b62e1d649e6a859cd34725af91411a6e5cb31c94b824235999d27ae02
 size 997351674

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a06e53d3b8db8cc45595ffd5e46327d27c2e05c52ebbf3fbc6aae1a160aa1f9
+oid sha256:694f423926ac4340014289d665fb41e7c4dde468bc19fcd2c2b612fc44bafec6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f071afedb6f79dad7634efb3c11b5cadc1617244cc1febacfa77506e4d908406
+oid sha256:877229026b55d004235a151c979fd49f2e0a0f7eab8421f7dbe46ed565dd74f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.57190397933845,
   "best_model_checkpoint": "training_dir/checkpoint-500",
-  "epoch": 2.0,
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -45,6 +45,25 @@
       "eval_samples_per_second": 47.104,
       "eval_steps_per_second": 5.888,
       "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 17.603412628173828,
+      "learning_rate": 5.25e-05,
+      "loss": 0.5728,
+      "step": 750
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5878496503496503,
+      "eval_f1": 0.5621748822370558,
+      "eval_loss": 1.6389495134353638,
+      "eval_precision": 0.6276473886381739,
+      "eval_recall": 0.5878496503496503,
+      "eval_runtime": 48.841,
+      "eval_samples_per_second": 46.846,
+      "eval_steps_per_second": 5.856,
+      "step": 750
     }
   ],
   "logging_steps": 500,
@@ -64,7 +83,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 834505315795872.0,
+  "total_flos": 1251671639603616.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null