Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd7b2c1a7bd05c82552bfb8d8ba3ad7299f537af66427a1ff4f4714dae48dfc8
+oid sha256:6b6be78a2dd0e0be68c245a8d4a9b9ccfeb5c50e5371c60c58cfea0e0459f51a
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c5346f10f837817f0ebca76904fcc0bbcd7f7eb8932d174ece4e97e815daecc
+oid sha256:23709651cc0736566b6cf6e31352814a96bb51f7ed34d31167879425e695e042
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79f99c3423a1a837c0044fd54e06d7d82d98d4715055617568b6a0802f4f5619
+oid sha256:4b00502da5feba7cd8100a8570af5fac37e5c8c267a539c58346d380c13e441c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9816d85fc06543cac1870dafa72c10f1a5da99b9fdbd2d1d62a89e1088e08b5
+oid sha256:9ce2a9fef65681ae0027502eaf6f2b8935ec5c8dbe0972fb30de040f99f9d624
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5374372005462646,
   "best_model_checkpoint": "./opt_trained3/checkpoint-60",
-  "epoch": 9.0,
+  "epoch": 9.353982300884956,
   "eval_steps": 500,
-  "global_step": 135,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,6 +79,14 @@
       "eval_samples_per_second": 50.141,
       "eval_steps_per_second": 12.535,
       "step": 135
+    },
+    {
+      "epoch": 9.353982300884956,
+      "eval_loss": 0.5497786998748779,
+      "eval_runtime": 6.0047,
+      "eval_samples_per_second": 49.961,
+      "eval_steps_per_second": 12.49,
+      "step": 140
     }
   ],
   "logging_steps": 500,
@@ -93,12 +101,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5009450520960000.0,
+  "total_flos": 5207869157760000.0,
   "train_batch_size": 24,
   "trial_name": null,
   "trial_params": null