ccore commited on
Commit
c27e089
·
verified ·
1 Parent(s): 2a0dae2

Training in progress, epoch 9, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a7360f2e09dd026d68fbf244aaca10d8337c6e7f676b318f556ea857e73b86b
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd7b2c1a7bd05c82552bfb8d8ba3ad7299f537af66427a1ff4f4714dae48dfc8
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad617129654170a729bfc1ab97900e8b2ee6e3f29fd95fbe9f7472e915f5506a
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c5346f10f837817f0ebca76904fcc0bbcd7f7eb8932d174ece4e97e815daecc
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84c3990f6d2b95e593198178da870517dc28edd5d6e6e3fb826e1b0603e625f2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79f99c3423a1a837c0044fd54e06d7d82d98d4715055617568b6a0802f4f5619
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:459118a97cfef37c931ad5b3ea220c0300c75674dcb929001a0e3daa633cce3c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9816d85fc06543cac1870dafa72c10f1a5da99b9fdbd2d1d62a89e1088e08b5
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.5374372005462646,
3
  "best_model_checkpoint": "./opt_trained3/checkpoint-60",
4
- "epoch": 8.0,
5
  "eval_steps": 500,
6
- "global_step": 120,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -71,6 +71,14 @@
71
  "eval_samples_per_second": 50.06,
72
  "eval_steps_per_second": 12.515,
73
  "step": 120
 
 
 
 
 
 
 
 
74
  }
75
  ],
76
  "logging_steps": 500,
@@ -90,7 +98,7 @@
90
  "attributes": {}
91
  }
92
  },
93
- "total_flos": 4452844907520000.0,
94
  "train_batch_size": 24,
95
  "trial_name": null,
96
  "trial_params": null
 
1
  {
2
  "best_metric": 0.5374372005462646,
3
  "best_model_checkpoint": "./opt_trained3/checkpoint-60",
4
+ "epoch": 9.0,
5
  "eval_steps": 500,
6
+ "global_step": 135,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
71
  "eval_samples_per_second": 50.06,
72
  "eval_steps_per_second": 12.515,
73
  "step": 120
74
+ },
75
+ {
76
+ "epoch": 9.0,
77
+ "eval_loss": 0.5496641993522644,
78
+ "eval_runtime": 5.9832,
79
+ "eval_samples_per_second": 50.141,
80
+ "eval_steps_per_second": 12.535,
81
+ "step": 135
82
  }
83
  ],
84
  "logging_steps": 500,
 
98
  "attributes": {}
99
  }
100
  },
101
+ "total_flos": 5009450520960000.0,
102
  "train_batch_size": 24,
103
  "trial_name": null,
104
  "trial_params": null