Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3005f7130dea7c99e3a23fe693aca2f872a4909870b225fd381e552552cf3ab3
+oid sha256:199cacde961d6c2ba5263dceeac08e655820340c9818c11e9bab049cc55050b6
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49e98b38a7667b6478792575464c5f70db060a96ad9bd23b60f51316b49032f
+oid sha256:1b6fc76771668e064b558e177954d0f21f929a5b81ef9f148add0c26ef682de7
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b877278faa523a92a4cc98264dadc986c246d2d7704a09f27fad64a3fb519e0
+oid sha256:c886040a9700ad45a90256e2d04b0fccdd47353c85f48617c6569803c67f29c7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d54b3990ddc5c14708bc858361b93e000545e1cc595791b44c2db8c9f6c8ddbe
+oid sha256:a1544f4ff6d9ad84288c11d28405d9c1f0c9ee9893907a119666fc3b3c33ec4b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9996200203895569,
-  "best_model_checkpoint": "./opt_trained/checkpoint-1407",
-  "epoch": 7.0,
+  "best_metric": 0.9977834820747375,
+  "best_model_checkpoint": "./opt_trained/checkpoint-1608",
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 1407,
+  "global_step": 1608,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,21 @@
       "eval_samples_per_second": 37.068,
       "eval_steps_per_second": 9.267,
       "step": 1407
+    },
+    {
+      "epoch": 7.463262764632628,
+      "grad_norm": 1.7347174882888794,
+      "learning_rate": 0.0002501,
+      "loss": 0.9871,
+      "step": 1500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.9977834820747375,
+      "eval_runtime": 76.773,
+      "eval_samples_per_second": 37.201,
+      "eval_steps_per_second": 9.3,
+      "step": 1608
     }
   ],
   "logging_steps": 500,
@@ -96,7 +111,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.736445767424e+16,
+  "total_flos": 5.413080877056e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null