Hugging Face's logo

chauhoang
/
bf4b9c7f-2a45-4eba-a1ab-793694bf8015

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
bf4b9c7f-2a45-4eba-a1ab-793694bf8015
File size: 3,479 Bytes 
c9bf96b
 
 
04a63bd
811bded
04a63bd
c9bf96b
 
 
 
 
 
 
811bded
 
 
c9bf96b
811bded
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7e07833
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1f2cc6f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
04a63bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c9bf96b
 
 
811bded
c9bf96b
 
811bded
c9bf96b
 
 
 
 
 
 
04a63bd
c9bf96b
 
 
 
04a63bd
c9bf96b
 
 
 
 
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": 0.001661115771463692,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.322231542927384e-05,
      "eval_loss": NaN,
      "eval_runtime": 476.0967,
      "eval_samples_per_second": 26.621,
      "eval_steps_per_second": 13.31,
      "step": 1
    },
    {
      "epoch": 0.00016611157714636923,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00033222315429273845,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.00033222315429273845,
      "eval_loss": NaN,
      "eval_runtime": 481.9219,
      "eval_samples_per_second": 26.299,
      "eval_steps_per_second": 13.149,
      "step": 10
    },
    {
      "epoch": 0.0004983347314391076,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0006644463085854769,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.0006644463085854769,
      "eval_loss": NaN,
      "eval_runtime": 473.5066,
      "eval_samples_per_second": 26.766,
      "eval_steps_per_second": 13.383,
      "step": 20
    },
    {
      "epoch": 0.000830557885731846,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0009966694628782153,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0009966694628782153,
      "eval_loss": NaN,
      "eval_runtime": 475.6133,
      "eval_samples_per_second": 26.648,
      "eval_steps_per_second": 13.324,
      "step": 30
    },
    {
      "epoch": 0.0011627810400245844,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.0013288926171709538,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.0013288926171709538,
      "eval_loss": NaN,
      "eval_runtime": 478.3548,
      "eval_samples_per_second": 26.495,
      "eval_steps_per_second": 13.247,
      "step": 40
    },
    {
      "epoch": 0.001495004194317323,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.001661115771463692,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.001661115771463692,
      "eval_loss": NaN,
      "eval_runtime": 476.8849,
      "eval_samples_per_second": 26.577,
      "eval_steps_per_second": 13.288,
      "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": 1621491292569600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}