Hugging Face's logo

chauhoang
/
067383fa-f1d7-4901-9f23-3073b0e4a009

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
067383fa-f1d7-4901-9f23-3073b0e4a009
File size: 2,241 Bytes 
ab3464d
 
 
2a7527d
d6d6d3d
2a7527d
ab3464d
 
 
 
 
 
 
d6d6d3d
 
 
ab3464d
d6d6d3d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2a7527d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ab3464d
 
 
d6d6d3d
ab3464d
 
d6d6d3d
ab3464d
 
 
 
 
 
 
d6d6d3d
ab3464d
 
 
 
2a7527d
ab3464d
 
 
 
 
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
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.004903809883062995,
  "eval_steps": 10,
  "global_step": 26,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001886080724254998,
      "eval_loss": 1.0262165069580078,
      "eval_runtime": 142.6224,
      "eval_samples_per_second": 15.657,
      "eval_steps_per_second": 7.832,
      "step": 1
    },
    {
      "epoch": 0.000943040362127499,
      "grad_norm": 21.677078247070312,
      "learning_rate": 5e-05,
      "loss": 3.7955,
      "step": 5
    },
    {
      "epoch": 0.001886080724254998,
      "grad_norm": 15.723212242126465,
      "learning_rate": 0.0001,
      "loss": 3.4928,
      "step": 10
    },
    {
      "epoch": 0.001886080724254998,
      "eval_loss": 0.7923435568809509,
      "eval_runtime": 143.6773,
      "eval_samples_per_second": 15.542,
      "eval_steps_per_second": 7.774,
      "step": 10
    },
    {
      "epoch": 0.002829121086382497,
      "grad_norm": 10.258428573608398,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.9175,
      "step": 15
    },
    {
      "epoch": 0.003772161448509996,
      "grad_norm": 13.949254989624023,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.6865,
      "step": 20
    },
    {
      "epoch": 0.003772161448509996,
      "eval_loss": 0.6223310232162476,
      "eval_runtime": 143.8688,
      "eval_samples_per_second": 15.521,
      "eval_steps_per_second": 7.764,
      "step": 20
    },
    {
      "epoch": 0.004715201810637495,
      "grad_norm": 14.729504585266113,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.512,
      "step": 25
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 4556946677956608.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}