Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ed1255637034f06fedc891d31b14507630bd3afa2c2b7509eaff7f480d34308
+oid sha256:0693e278cfa5bc32cd36744d1aaad53ba6429329360040cab49896ad5e9ec549
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:210a5a85541b415d009b0822ceb8a45234fd44c2c0623ef47b0e85fef844e373
+oid sha256:f35e58618a6603a93c4f6e2d4d56078920a6d0120800182348586172e353d278
 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": 0.6301519274711609,
   "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": 49.889,
       "eval_steps_per_second": 12.472,
       "step": 135
+    },
+    {
+      "epoch": 9.353982300884956,
+      "eval_loss": 0.6347810626029968,
+      "eval_runtime": 5.9964,
+      "eval_samples_per_second": 50.03,
+      "eval_steps_per_second": 12.508,
+      "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