Hugging Face's logo

tuanna08go
/
bf558d70-56a0-4fe8-9cba-4567595eb1dd

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
bf558d70-56a0-4fe8-9cba-4567595eb1dd
File size: 2,801 Bytes 
9ecd75f
 
 
eb900ce
e82b880
eb900ce
9ecd75f
 
 
 
 
 
 
e82b880
 
 
9ecd75f
e82b880
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
831c2db
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eb900ce
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ecd75f
 
 
e82b880
9ecd75f
 
e82b880
9ecd75f
 
 
 
 
 
 
e82b880
9ecd75f
 
 
 
eb900ce
9ecd75f
 
 
 
 
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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.008407437348423606,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002155753166262463,
      "eval_loss": 10.379223823547363,
      "eval_runtime": 8.4382,
      "eval_samples_per_second": 231.567,
      "eval_steps_per_second": 115.783,
      "step": 1
    },
    {
      "epoch": 0.0010778765831312314,
      "grad_norm": 0.9546406865119934,
      "learning_rate": 5e-05,
      "loss": 41.5054,
      "step": 5
    },
    {
      "epoch": 0.002155753166262463,
      "grad_norm": 1.1193766593933105,
      "learning_rate": 0.0001,
      "loss": 41.5383,
      "step": 10
    },
    {
      "epoch": 0.002155753166262463,
      "eval_loss": 10.377625465393066,
      "eval_runtime": 8.7272,
      "eval_samples_per_second": 223.898,
      "eval_steps_per_second": 111.949,
      "step": 10
    },
    {
      "epoch": 0.0032336297493936943,
      "grad_norm": 1.069719672203064,
      "learning_rate": 9.619397662556435e-05,
      "loss": 41.5022,
      "step": 15
    },
    {
      "epoch": 0.004311506332524926,
      "grad_norm": 0.9299646019935608,
      "learning_rate": 8.535533905932738e-05,
      "loss": 41.482,
      "step": 20
    },
    {
      "epoch": 0.004311506332524926,
      "eval_loss": 10.374091148376465,
      "eval_runtime": 8.7331,
      "eval_samples_per_second": 223.746,
      "eval_steps_per_second": 111.873,
      "step": 20
    },
    {
      "epoch": 0.0053893829156561575,
      "grad_norm": 1.0937271118164062,
      "learning_rate": 6.91341716182545e-05,
      "loss": 41.4792,
      "step": 25
    },
    {
      "epoch": 0.0064672594987873885,
      "grad_norm": 0.9614943861961365,
      "learning_rate": 5e-05,
      "loss": 41.5162,
      "step": 30
    },
    {
      "epoch": 0.0064672594987873885,
      "eval_loss": 10.371255874633789,
      "eval_runtime": 8.5479,
      "eval_samples_per_second": 228.595,
      "eval_steps_per_second": 114.297,
      "step": 30
    },
    {
      "epoch": 0.00754513608191862,
      "grad_norm": 1.0435622930526733,
      "learning_rate": 3.086582838174551e-05,
      "loss": 41.4971,
      "step": 35
    }
  ],
  "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": 1000927789056.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}