Hugging Face's logo

tuanna08go
/
b6257239-b146-4506-9371-045353298d72

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
8-bit precision
bitsandbytes
Model card Files Community
b6257239-b146-4506-9371-045353298d72
File size: 3,064 Bytes 
7285197
 
 
39b83d8
7285197
39b83d8
7285197
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
39b83d8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7285197
 
 
 
 
 
 
 
 
 
 
 
 
 
39b83d8
7285197
 
 
 
39b83d8
7285197
 
 
 
 
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
116
117
118
119
120
121
122
123
124
125
126
127
128
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01547029702970297,
  "eval_steps": 25,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0003094059405940594,
      "eval_loss": 9.276086807250977,
      "eval_runtime": 78.2213,
      "eval_samples_per_second": 4.602,
      "eval_steps_per_second": 4.602,
      "step": 1
    },
    {
      "epoch": 0.001547029702970297,
      "grad_norm": 20.956584930419922,
      "learning_rate": 5e-05,
      "loss": 9.4537,
      "step": 5
    },
    {
      "epoch": 0.003094059405940594,
      "grad_norm": 19.363298416137695,
      "learning_rate": 0.0001,
      "loss": 8.2148,
      "step": 10
    },
    {
      "epoch": 0.004641089108910891,
      "grad_norm": 35.757205963134766,
      "learning_rate": 9.619397662556435e-05,
      "loss": 8.377,
      "step": 15
    },
    {
      "epoch": 0.006188118811881188,
      "grad_norm": 16.865013122558594,
      "learning_rate": 8.535533905932738e-05,
      "loss": 8.3326,
      "step": 20
    },
    {
      "epoch": 0.007735148514851485,
      "grad_norm": 29.526941299438477,
      "learning_rate": 6.91341716182545e-05,
      "loss": 8.19,
      "step": 25
    },
    {
      "epoch": 0.007735148514851485,
      "eval_loss": 7.6531758308410645,
      "eval_runtime": 78.2396,
      "eval_samples_per_second": 4.601,
      "eval_steps_per_second": 4.601,
      "step": 25
    },
    {
      "epoch": 0.009282178217821782,
      "grad_norm": 21.752103805541992,
      "learning_rate": 5e-05,
      "loss": 7.5132,
      "step": 30
    },
    {
      "epoch": 0.010829207920792078,
      "grad_norm": 11.453251838684082,
      "learning_rate": 3.086582838174551e-05,
      "loss": 7.5282,
      "step": 35
    },
    {
      "epoch": 0.012376237623762377,
      "grad_norm": 14.995335578918457,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 6.517,
      "step": 40
    },
    {
      "epoch": 0.013923267326732673,
      "grad_norm": 22.817428588867188,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 7.4861,
      "step": 45
    },
    {
      "epoch": 0.01547029702970297,
      "grad_norm": 21.126054763793945,
      "learning_rate": 0.0,
      "loss": 9.1762,
      "step": 50
    },
    {
      "epoch": 0.01547029702970297,
      "eval_loss": 7.1646647453308105,
      "eval_runtime": 77.8098,
      "eval_samples_per_second": 4.627,
      "eval_steps_per_second": 4.627,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 225298219008000.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}