Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4523a9c93b74b8c5c6c35d9977a37738c2da28419bfceec3dc2abc9f3fea4fc
+oid sha256:db509c74b27cc4e88ddc7d56dc34e1f22fefcd08f5e7e1bf48c0dffc68aea2db
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:053550d54418a8a41e8640524ab398a874541d31509cb91da0928e8cd3937d51
+oid sha256:154d21450f386a8606820e756b4499dd66e016837200f023ec287f61d93fa2aa
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa26de2555f562032c37435ab63a13624ac910b9318e07a207eeee632f850008
+oid sha256:5e155eca4770006b851ebce82a20242de821161258f243fc0b888e431a980cd9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7f6bb8605f469a84fbad16fb286e3274b0712f3f3c877543edc1e6dc05b8980
+oid sha256:ce5386222d26d7802b580935f5da10bebf188e3a1526eaff62e2981a60df9cf4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.28598517179489136,
   "best_model_checkpoint": "./opt_trained/checkpoint-644",
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 2254,
+  "global_step": 2576,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,21 @@
       "eval_samples_per_second": 24.78,
       "eval_steps_per_second": 6.195,
       "step": 2254
+    },
+    {
+      "epoch": 7.765758754863813,
+      "grad_norm": 3.3326103687286377,
+      "learning_rate": 2.680973820971481e-05,
+      "loss": 0.2756,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.2883214056491852,
+      "eval_runtime": 115.3007,
+      "eval_samples_per_second": 24.77,
+      "eval_steps_per_second": 6.193,
+      "step": 2576
     }
   ],
   "logging_steps": 500,
@@ -110,7 +125,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.104668651136e+16,
+  "total_flos": 8.119621315584e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null