ccore commited on
Commit
4466f80
·
verified ·
1 Parent(s): 9c53a81

Training in progress, epoch 8, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3cf8f08f616176452394d58e4224ada71da7d64b801e705eb0b77875c79a4da0
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13af9c289571a03baeeb850184a18f4f4cd637be9624b07a787f2f75f79fb5ea
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a168c21d32e0ab0112605e3b30fc1d7b10b74cadd6992eeb837a29e605090ee8
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b9e192057e824235aa53d0fb85e6e279ebacedec4fe01e030cc560b5e133706
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dbb430077813eebb78e89f25ad57a8b8a506e2650404fdf80d07e549f36aeda
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:84c3990f6d2b95e593198178da870517dc28edd5d6e6e3fb826e1b0603e625f2
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7b9862d898cb0a9519e8aaf124fb3ce78820e2fee42eb8cbf3caef99627a3651
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50bf5fe001fa4e99cdad0ccd9b8de4ef1b5c03d3cc277a4b134d13a346f5902a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6723850965499878,
3
- "best_model_checkpoint": "./opt_trained3/checkpoint-90",
4
- "epoch": 7.0,
5
  "eval_steps": 500,
6
- "global_step": 105,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -63,6 +63,14 @@
63
  "eval_samples_per_second": 50.39,
64
  "eval_steps_per_second": 12.598,
65
  "step": 105
 
 
 
 
 
 
 
 
66
  }
67
  ],
68
  "logging_steps": 500,
@@ -82,7 +90,7 @@
82
  "attributes": {}
83
  }
84
  },
85
- "total_flos": 3896239294080000.0,
86
  "train_batch_size": 24,
87
  "trial_name": null,
88
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6707628965377808,
3
+ "best_model_checkpoint": "./opt_trained3/checkpoint-120",
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,
 
63
  "eval_samples_per_second": 50.39,
64
  "eval_steps_per_second": 12.598,
65
  "step": 105
66
+ },
67
+ {
68
+ "epoch": 8.0,
69
+ "eval_loss": 0.6707628965377808,
70
+ "eval_runtime": 5.9562,
71
+ "eval_samples_per_second": 50.368,
72
+ "eval_steps_per_second": 12.592,
73
+ "step": 120
74
  }
75
  ],
76
  "logging_steps": 500,
 
90
  "attributes": {}
91
  }
92
  },
93
+ "total_flos": 4452844907520000.0,
94
  "train_batch_size": 24,
95
  "trial_name": null,
96
  "trial_params": null