Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d11e05c0bd09f6757b3ec6a154e446132cfbd78617981902cf25a677040f19
+oid sha256:1ed1255637034f06fedc891d31b14507630bd3afa2c2b7509eaff7f480d34308
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eb9ebeff6ff138456de25bcca83846cfa6361faf770f9b8ed27c75a4a242bc1
+oid sha256:210a5a85541b415d009b0822ceb8a45234fd44c2c0623ef47b0e85fef844e373
 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 sha256:50bf5fe001fa4e99cdad0ccd9b8de4ef1b5c03d3cc277a4b134d13a346f5902a
+oid sha256:c248f64379de1457aeba2dcf4a115bd43fe65fcd6c7b097c336db9e1a90ff441
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.6301519274711609,
   "best_model_checkpoint": "./opt_trained3/checkpoint-60",
-  "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": 50.111,
       "eval_steps_per_second": 12.528,
       "step": 120
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.6348392963409424,
+      "eval_runtime": 6.0134,
+      "eval_samples_per_second": 49.889,
+      "eval_steps_per_second": 12.472,
+      "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