Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db509c74b27cc4e88ddc7d56dc34e1f22fefcd08f5e7e1bf48c0dffc68aea2db
+oid sha256:7b73e9181993fc42aff7016ef767360614c22895cb7cb74ca0157b22657aaae7
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:154d21450f386a8606820e756b4499dd66e016837200f023ec287f61d93fa2aa
+oid sha256:f3a08bdf51d589d884a653cd1b74378c42928ada63b38f4d516573370100259c
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e155eca4770006b851ebce82a20242de821161258f243fc0b888e431a980cd9
+oid sha256:8f7fba221647949a8433d18d5404dddfdbde6e6b2c411f1b844118552ba1303a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce5386222d26d7802b580935f5da10bebf188e3a1526eaff62e2981a60df9cf4
+oid sha256:f1894d71618d2cb906b7f2808a5fea15bc7a5439f41ed98833d51cedffc3b06a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.28598517179489136,
   "best_model_checkpoint": "./opt_trained/checkpoint-644",
-  "epoch": 8.0,
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 2576,
+  "global_step": 2898,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -106,6 +106,14 @@
       "eval_samples_per_second": 24.77,
       "eval_steps_per_second": 6.193,
       "step": 2576
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.28775903582572937,
+      "eval_runtime": 115.3453,
+      "eval_samples_per_second": 24.76,
+      "eval_steps_per_second": 6.19,
+      "step": 2898
     }
   ],
   "logging_steps": 500,
@@ -125,7 +133,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.119621315584e+16,
+  "total_flos": 9.134573980032e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null