Hugging Face's logo

knowledgator
/
flan-t5-large-for-classification

Text2Text Generation
Transformers
PyTorch
English
t5
text-generation-inference
Inference Endpoints
Model card Files Community
1
Ihor commited on
Commit
db6fc41
·
verified ·
1 Parent(s): 6fff896

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. pytorch_model.bin +1 -1
  2. trainer_state.json +20 -38
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de576e876f5dc8b105817e78ed7414438dff420d247fc73e943fab684f13fd96
3
  size 3132793669
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac2b09fcc1866c02049c06f2c11808f5c602370b8ddeca77781b48f24c3b7d2
3
  size 3132793669
trainer_state.json CHANGED
@@ -3,71 +3,53 @@
3
  "best_model_checkpoint": null,
4
  "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 4500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.11,
13
- "learning_rate": 8.888888888888888e-06,
14
- "loss": 2.4115,
15
  "step": 500
16
  },
17
  {
18
- "epoch": 0.22,
19
- "learning_rate": 7.77777777777778e-06,
20
- "loss": 1.8379,
21
  "step": 1000
22
  },
23
  {
24
- "epoch": 0.33,
25
- "learning_rate": 6.666666666666667e-06,
26
- "loss": 1.548,
27
  "step": 1500
28
  },
29
  {
30
- "epoch": 0.44,
31
- "learning_rate": 5.555555555555557e-06,
32
- "loss": 1.462,
33
  "step": 2000
34
  },
35
  {
36
- "epoch": 0.56,
37
- "learning_rate": 4.444444444444444e-06,
38
- "loss": 1.4512,
39
- "step": 2500
40
- },
41
- {
42
- "epoch": 0.67,
43
  "learning_rate": 3.3333333333333333e-06,
44
- "loss": 1.4267,
45
- "step": 3000
46
- },
47
- {
48
- "epoch": 0.78,
49
- "learning_rate": 2.222222222222222e-06,
50
- "loss": 1.3252,
51
- "step": 3500
52
- },
53
- {
54
- "epoch": 0.89,
55
- "learning_rate": 1.111111111111111e-06,
56
- "loss": 1.3507,
57
- "step": 4000
58
  },
59
  {
60
  "epoch": 1.0,
61
  "learning_rate": 0.0,
62
- "loss": 1.3253,
63
- "step": 4500
64
  }
65
  ],
66
  "logging_steps": 500,
67
- "max_steps": 4500,
68
  "num_train_epochs": 1,
69
  "save_steps": 300,
70
- "total_flos": 2.024400132027187e+16,
71
  "trial_name": null,
72
  "trial_params": null
73
  }
 
3
  "best_model_checkpoint": null,
4
  "epoch": 1.0,
5
  "eval_steps": 500,
6
+ "global_step": 3000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.17,
13
+ "learning_rate": 1.6666666666666667e-05,
14
+ "loss": 2.1442,
15
  "step": 500
16
  },
17
  {
18
+ "epoch": 0.33,
19
+ "learning_rate": 1.3333333333333333e-05,
20
+ "loss": 1.5391,
21
  "step": 1000
22
  },
23
  {
24
+ "epoch": 0.5,
25
+ "learning_rate": 1e-05,
26
+ "loss": 1.3816,
27
  "step": 1500
28
  },
29
  {
30
+ "epoch": 0.67,
31
+ "learning_rate": 6.666666666666667e-06,
32
+ "loss": 1.2825,
33
  "step": 2000
34
  },
35
  {
36
+ "epoch": 0.83,
 
 
 
 
 
 
37
  "learning_rate": 3.3333333333333333e-06,
38
+ "loss": 1.2975,
39
+ "step": 2500
 
 
 
 
 
 
 
 
 
 
 
 
40
  },
41
  {
42
  "epoch": 1.0,
43
  "learning_rate": 0.0,
44
+ "loss": 1.2718,
45
+ "step": 3000
46
  }
47
  ],
48
  "logging_steps": 500,
49
+ "max_steps": 3000,
50
  "num_train_epochs": 1,
51
  "save_steps": 300,
52
+ "total_flos": 1.34514945506304e+16,
53
  "trial_name": null,
54
  "trial_params": null
55
  }