Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:576846bd48b72cd7aaf1830841153e585d029c6c4825445154a8e90cdd1d588d
+oid sha256:27d11e05c0bd09f6757b3ec6a154e446132cfbd78617981902cf25a677040f19
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c72e158baa306f60707acab85d117f5dd90e0927a25c1e424ec553e2e2f4d5e
+oid sha256:3eb9ebeff6ff138456de25bcca83846cfa6361faf770f9b8ed27c75a4a242bc1
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dbb430077813eebb78e89f25ad57a8b8a506e2650404fdf80d07e549f36aeda
+oid sha256:84c3990f6d2b95e593198178da870517dc28edd5d6e6e3fb826e1b0603e625f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b9862d898cb0a9519e8aaf124fb3ce78820e2fee42eb8cbf3caef99627a3651
+oid sha256:50bf5fe001fa4e99cdad0ccd9b8de4ef1b5c03d3cc277a4b134d13a346f5902a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6301519274711609,
   "best_model_checkpoint": "./opt_trained3/checkpoint-60",
-  "epoch": 7.0,
+  "epoch": 8.0,
   "eval_steps": 500,
-  "global_step": 105,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,14 @@
       "eval_samples_per_second": 50.062,
       "eval_steps_per_second": 12.516,
       "step": 105
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.6336122751235962,
+      "eval_runtime": 5.9867,
+      "eval_samples_per_second": 50.111,
+      "eval_steps_per_second": 12.528,
+      "step": 120
     }
   ],
   "logging_steps": 500,
@@ -82,7 +90,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3896239294080000.0,
+  "total_flos": 4452844907520000.0,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null