Training in progress, epoch 9, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199cacde961d6c2ba5263dceeac08e655820340c9818c11e9bab049cc55050b6
+oid sha256:2f906cae71eeab352318738ca14756442ba163e636920c59a394a833c3dc856b
 size 500979600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b6fc76771668e064b558e177954d0f21f929a5b81ef9f148add0c26ef682de7
+oid sha256:b8b25cc5f1a898ad72fef4fd30212846ab27173034c9792b0977650565a3991b
 size 1002078330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c886040a9700ad45a90256e2d04b0fccdd47353c85f48617c6569803c67f29c7
+oid sha256:c9fe00b64fad24a81305617574b1f144e0a203f88aad01c498c11972a75112b9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1544f4ff6d9ad84288c11d28405d9c1f0c9ee9893907a119666fc3b3c33ec4b
+oid sha256:93718a710ffbdf979db46548e4ac66f31c764b1a1991b166a6b3d69faeec3671
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9977834820747375,
-  "best_model_checkpoint": "./opt_trained/checkpoint-1608",
-  "epoch": 8.0,
+  "best_metric": 0.9954783320426941,
+  "best_model_checkpoint": "./opt_trained/checkpoint-1809",
+  "epoch": 9.0,
   "eval_steps": 500,
-  "global_step": 1608,
+  "global_step": 1809,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,14 @@
       "eval_samples_per_second": 37.201,
       "eval_steps_per_second": 9.3,
       "step": 1608
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.9954783320426941,
+      "eval_runtime": 76.956,
+      "eval_samples_per_second": 37.112,
+      "eval_steps_per_second": 9.278,
+      "step": 1809
     }
   ],
   "logging_steps": 500,
@@ -111,7 +119,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.413080877056e+16,
+  "total_flos": 6.089715986688e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null