Training in progress, epoch 8, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2865ac223aaf2258b943599d521d3936de1c0602a9d87c3866ab455828fa437
+oid sha256:2a7360f2e09dd026d68fbf244aaca10d8337c6e7f676b318f556ea857e73b86b
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1056e5a11f3361ae565dc7ba196187d5de7b5879650096ffa751d58013159ec2
+oid sha256:ad617129654170a729bfc1ab97900e8b2ee6e3f29fd95fbe9f7472e915f5506a
 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:e80e230602e7a193cb259f6d595adaedbdfa6e184c93cf7d550ef28b903e0783
+oid sha256:459118a97cfef37c931ad5b3ea220c0300c75674dcb929001a0e3daa633cce3c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5374372005462646,
   "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": 50.168,
       "eval_steps_per_second": 12.542,
       "step": 105
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 0.548169732093811,
+      "eval_runtime": 5.9928,
+      "eval_samples_per_second": 50.06,
+      "eval_steps_per_second": 12.515,
+      "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