duyphu commited on
Commit
0e52458
·
verified ·
1 Parent(s): 469245a

Training in progress, step 39, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92265d12a584ba5e1ca98dad8f70b99ef54e03e8c4b6831f9301af4c971fd43b
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ea613c1bd30b1668db6c9a1bb4149ba77b5fc14e0b229e4bcf2c9cdefb10a0a
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a2228365e17169e509ebe52385f51321ca3d6221ed41508f8341c3e2331420b
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac620220980d7bc2d0f8d1c45a534f9625edf18437813879b8aac6d370d43f91
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b48b39a0e824b1a3c18c1be18c454fa0b89a07e7ba413d8629bdab8b716f86c9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60197ddd2b9e7ee46919c36404e76c5aca074008f3439670b71d1d51cb8b8db7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0006141526759931262,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.0475,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4059240891678720.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0009212290139896894,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 2.0475,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0007086377030689918,
72
+ "grad_norm": 1.5635089874267578,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.9059,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0007086377030689918,
79
+ "eval_loss": 1.9371638298034668,
80
+ "eval_runtime": 1091.4736,
81
+ "eval_samples_per_second": 16.332,
82
+ "eval_steps_per_second": 8.166,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0008267439869138238,
87
+ "grad_norm": 1.4265427589416504,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.9827,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6109362554142720.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null