Hugging Face's logo

duyphu
/
f49a43d2-f6d2-45f1-be79-7a2e758120f0

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
f49a43d2-f6d2-45f1-be79-7a2e758120f0
File size: 3,492 Bytes 
71f6d29
 
 
cd25c3a
0efea5b
cd25c3a
71f6d29
 
 
 
 
 
 
0efea5b
 
 
71f6d29
0efea5b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
023f608
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
128ee33
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cd25c3a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
71f6d29
 
 
0efea5b
71f6d29
 
0efea5b
71f6d29
 
 
 
 
 
 
cd25c3a
71f6d29
 
 
 
cd25c3a
71f6d29
 
 
 
 
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": 0.0004216198211910338,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.432396423820677e-06,
      "eval_loss": NaN,
      "eval_runtime": 2042.9263,
      "eval_samples_per_second": 24.442,
      "eval_steps_per_second": 12.221,
      "step": 1
    },
    {
      "epoch": 4.216198211910338e-05,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 8.432396423820676e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 8.432396423820676e-05,
      "eval_loss": NaN,
      "eval_runtime": 2055.2843,
      "eval_samples_per_second": 24.295,
      "eval_steps_per_second": 12.148,
      "step": 10
    },
    {
      "epoch": 0.00012648594635731016,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.00016864792847641352,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.00016864792847641352,
      "eval_loss": NaN,
      "eval_runtime": 2067.6727,
      "eval_samples_per_second": 24.149,
      "eval_steps_per_second": 12.075,
      "step": 20
    },
    {
      "epoch": 0.0002108099105955169,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.0002529718927146203,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.0002529718927146203,
      "eval_loss": NaN,
      "eval_runtime": 2046.6025,
      "eval_samples_per_second": 24.398,
      "eval_steps_per_second": 12.199,
      "step": 30
    },
    {
      "epoch": 0.0002951338748337237,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.00033729585695282705,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.00033729585695282705,
      "eval_loss": NaN,
      "eval_runtime": 2060.3373,
      "eval_samples_per_second": 24.235,
      "eval_steps_per_second": 12.118,
      "step": 40
    },
    {
      "epoch": 0.00037945783907193046,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.0004216198211910338,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.0004216198211910338,
      "eval_loss": NaN,
      "eval_runtime": 2058.08,
      "eval_samples_per_second": 24.262,
      "eval_steps_per_second": 12.131,
      "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": 2302517635448832.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}