Hugging Face's logo

phungkhaccuong
/
04e11ef6-814a-064d-e8c3-6db4a2a90db4

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
04e11ef6-814a-064d-e8c3-6db4a2a90db4
File size: 3,702 Bytes 
d1d7830
 
 
9cb60d7
e811c75
9cb60d7
d1d7830
 
 
 
 
 
 
e811c75
 
 
d1d7830
e811c75
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
74586d1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8b5e469
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9cb60d7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d1d7830
 
 
e811c75
d1d7830
 
e811c75
d1d7830
 
 
 
 
 
 
9cb60d7
d1d7830
 
 
 
9cb60d7
d1d7830
 
 
 
 
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
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06946856547412296,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013893713094824591,
      "eval_loss": 2.9451565742492676,
      "eval_runtime": 34.4539,
      "eval_samples_per_second": 8.794,
      "eval_steps_per_second": 4.412,
      "step": 1
    },
    {
      "epoch": 0.0069468565474122956,
      "grad_norm": 1.3465774059295654,
      "learning_rate": 5e-05,
      "loss": 2.808,
      "step": 5
    },
    {
      "epoch": 0.013893713094824591,
      "grad_norm": 1.7650309801101685,
      "learning_rate": 0.0001,
      "loss": 2.7516,
      "step": 10
    },
    {
      "epoch": 0.013893713094824591,
      "eval_loss": 2.687224864959717,
      "eval_runtime": 33.832,
      "eval_samples_per_second": 8.956,
      "eval_steps_per_second": 4.493,
      "step": 10
    },
    {
      "epoch": 0.02084056964223689,
      "grad_norm": 1.5081523656845093,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.2467,
      "step": 15
    },
    {
      "epoch": 0.027787426189649182,
      "grad_norm": 1.763542652130127,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.5649,
      "step": 20
    },
    {
      "epoch": 0.027787426189649182,
      "eval_loss": 1.5423730611801147,
      "eval_runtime": 33.9487,
      "eval_samples_per_second": 8.925,
      "eval_steps_per_second": 4.477,
      "step": 20
    },
    {
      "epoch": 0.03473428273706148,
      "grad_norm": 2.000399351119995,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.2685,
      "step": 25
    },
    {
      "epoch": 0.04168113928447378,
      "grad_norm": 1.7187610864639282,
      "learning_rate": 5e-05,
      "loss": 1.0837,
      "step": 30
    },
    {
      "epoch": 0.04168113928447378,
      "eval_loss": 1.0210185050964355,
      "eval_runtime": 34.0398,
      "eval_samples_per_second": 8.901,
      "eval_steps_per_second": 4.465,
      "step": 30
    },
    {
      "epoch": 0.048627995831886074,
      "grad_norm": 2.0270674228668213,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.0,
      "step": 35
    },
    {
      "epoch": 0.055574852379298365,
      "grad_norm": 1.9555302858352661,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.9449,
      "step": 40
    },
    {
      "epoch": 0.055574852379298365,
      "eval_loss": 0.8849262595176697,
      "eval_runtime": 34.1213,
      "eval_samples_per_second": 8.88,
      "eval_steps_per_second": 4.455,
      "step": 40
    },
    {
      "epoch": 0.06252170892671066,
      "grad_norm": 1.7785624265670776,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.7927,
      "step": 45
    },
    {
      "epoch": 0.06946856547412296,
      "grad_norm": 1.3851503133773804,
      "learning_rate": 0.0,
      "loss": 0.8639,
      "step": 50
    },
    {
      "epoch": 0.06946856547412296,
      "eval_loss": 0.8625767230987549,
      "eval_runtime": 34.1038,
      "eval_samples_per_second": 8.885,
      "eval_steps_per_second": 4.457,
      "step": 50
    }
  ],
  "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": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8713180230451200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}