Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36d1741f1c2fdfc1389a2054eac709f84a531e3af46a79b487f335e795223ebb
+oid sha256:355b00ffa8e07d4346760e95eccf2eb530e9a1b84d8356dcbf28db9cd7dd5295
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a4132076705e8c6d24d8425e81772d9bf33bee1eaec44d5be4091c1caeb53bb
+oid sha256:6c08f01c9be95dfaa9d09755bce204473729e762258d21a0f4b953c864ea7e68
 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:c248f64379de1457aeba2dcf4a115bd43fe65fcd6c7b097c336db9e1a90ff441
+oid sha256:f8c98fcf42f494fa75f135fb338a20acefff4d78f4f44abc68b10fde88458a02
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.670530378818512,
-  "best_model_checkpoint": "./opt_trained3/checkpoint-135",
-  "epoch": 9.0,
+  "best_metric": 0.6704908013343811,
+  "best_model_checkpoint": "./opt_trained3/checkpoint-140",
+  "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": 50.417,
       "eval_steps_per_second": 12.604,
       "step": 135
+    },
+    {
+      "epoch": 9.353982300884956,
+      "eval_loss": 0.6704908013343811,
+      "eval_runtime": 5.9917,
+      "eval_samples_per_second": 50.069,
+      "eval_steps_per_second": 12.517,
+      "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