Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44026e57a9e8d56457d53b6e6abb1678d0f701a7c11ba4bb52b599da11582ea
+oid sha256:7dca466cd745146a4892c25b064185d56ccd8a718909812cc29b77d32e7cabd5
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe1724de21b92dce1e8f0ccc057867e8e1d095ba94119a826db96dc7ef66c8c2
+oid sha256:6113d479c60c8b8bfca33e994f87404a12d90f4c0fae485fe797feb08d5c1939
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84c3990f6d2b95e593198178da870517dc28edd5d6e6e3fb826e1b0603e625f2
+oid sha256:79f99c3423a1a837c0044fd54e06d7d82d98d4715055617568b6a0802f4f5619
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:762dfbff70fdef35bd3e1956814e0e48e0265f023ff1798f261d2c92f46b61f4
+oid sha256:eafb059b24c048fdb576d0c24ef98dd629ed0a08dffd4d0840cb64cb9bf7cb3e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5292332172393799,
   "best_model_checkpoint": "./opt_trained3/checkpoint-30",
-  "epoch": 8.0,
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 120,
+  "global_step": 135,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -71,6 +71,14 @@
       "eval_samples_per_second": 49.967,
       "eval_steps_per_second": 12.492,
       "step": 120
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.5451622009277344,
+      "eval_runtime": 5.9841,
+      "eval_samples_per_second": 50.133,
+      "eval_steps_per_second": 12.533,
+      "step": 135
     }
   ],
   "logging_steps": 500,
@@ -90,7 +98,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4452844907520000.0,
+  "total_flos": 5009450520960000.0,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null