Hugging Face's logo

zzunyang
/
KLQD_law_gemma

PEFT
Safetensors
Model card Files Community
KLQD_law_gemma
File size: 1,809 Bytes 
ffe4a1c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.997686030934113,
  "eval_steps": 500,
  "global_step": 3078,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.48715138229204724,
      "grad_norm": 0.1553633213043213,
      "learning_rate": 0.00019316938294480988,
      "loss": 1.4919,
      "step": 500
    },
    {
      "epoch": 0.9743027645840945,
      "grad_norm": 0.147247314453125,
      "learning_rate": 0.00016145696457272202,
      "loss": 1.3582,
      "step": 1000
    },
    {
      "epoch": 1.4608452076482767,
      "grad_norm": 0.18102706968784332,
      "learning_rate": 0.00011243098608364038,
      "loss": 1.1912,
      "step": 1500
    },
    {
      "epoch": 1.947996589940324,
      "grad_norm": 0.20963045954704285,
      "learning_rate": 5.990296960148566e-05,
      "loss": 1.1563,
      "step": 2000
    },
    {
      "epoch": 2.4345390330045062,
      "grad_norm": 0.2900982201099396,
      "learning_rate": 1.8671025926443465e-05,
      "loss": 0.9564,
      "step": 2500
    },
    {
      "epoch": 2.9216904152965535,
      "grad_norm": 0.2768326997756958,
      "learning_rate": 3.509538621403463e-07,
      "loss": 0.9263,
      "step": 3000
    }
  ],
  "logging_steps": 500,
  "max_steps": 3078,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.296618368751632e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}