Hugging Face's logo

goendalf666
/
falcon-7b-sql-instruction-lora

Model card Files
xet
 Community
tom813 commited on
Commit
60e7d25
·
1 Parent(s): 7e8a666

checkpoint 30000

Browse files
Files changed (5) hide show
  1. adapter_model.bin +1 -1
  2. optimizer.pt +1 -1
  3. rng_state.pth +1 -1
  4. scheduler.pt +1 -1
  5. trainer_state.json +33 -3
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:58ff9f13fe4fd43916c511c4e7a58027c1ce30fb6b7744815a66a31aa378e9d7
3
  size 261189898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9c4c7ad6ebdf2339a8e4943f3789ad3d1356d61545dc81a808ca389600603c2
3
  size 261189898
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7318a7e6b468b1f60f77c2df735b4138a4972075a7f9d23b7cbbc3ea18158b34
3
  size 1044540346
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e11dee7b190c2fdad32a73d0114456b9d1228b2639e23b931aba09ba9c01fba5
3
  size 1044540346
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:453bd6991fe36c7874b91d8fe044905b7822553a1079f2afd925646c3b124eb5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ddba1f85ace420be047b39da567706e4ccc0c0db8f35bf72010cd9c84b58dc
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25d9b43d9967cc267ee69f422bfad8c170bd37836e9da711be203c8963d6971e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7de8907e79c9f47fccf3aa89da8ca3d3d851fdb56e005195640f80ea9c8917
3
  size 1064
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 14.634146341463415,
5
- "global_step": 15000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -36,11 +36,41 @@
36
  "learning_rate": 0.0002,
37
  "loss": 1.3908,
38
  "step": 15000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39
  }
40
  ],
41
  "max_steps": 30000,
42
  "num_train_epochs": 30,
43
- "total_flos": 3.1738277265408e+18,
44
  "trial_name": null,
45
  "trial_params": null
46
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 29.26829268292683,
5
+ "global_step": 30000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
36
  "learning_rate": 0.0002,
37
  "loss": 1.3908,
38
  "step": 15000
39
+ },
40
+ {
41
+ "epoch": 17.56,
42
+ "learning_rate": 0.0002,
43
+ "loss": 1.7294,
44
+ "step": 18000
45
+ },
46
+ {
47
+ "epoch": 20.49,
48
+ "learning_rate": 0.0002,
49
+ "loss": 1.2396,
50
+ "step": 21000
51
+ },
52
+ {
53
+ "epoch": 23.41,
54
+ "learning_rate": 0.0002,
55
+ "loss": 1.5304,
56
+ "step": 24000
57
+ },
58
+ {
59
+ "epoch": 26.34,
60
+ "learning_rate": 0.0002,
61
+ "loss": 2.3882,
62
+ "step": 27000
63
+ },
64
+ {
65
+ "epoch": 29.27,
66
+ "learning_rate": 0.0002,
67
+ "loss": 2.0081,
68
+ "step": 30000
69
  }
70
  ],
71
  "max_steps": 30000,
72
  "num_train_epochs": 30,
73
+ "total_flos": 6.3476554530816e+18,
74
  "trial_name": null,
75
  "trial_params": null
76
  }