Hugging Face's logo

duyphu
/
188c3e9c-47ed-4e67-bf2c-06cc29614d5d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
188c3e9c-47ed-4e67-bf2c-06cc29614d5d
File size: 3,750 Bytes 
37e9c1c
 
 
5a454aa
fe96686
5a454aa
37e9c1c
 
 
 
 
 
 
fe96686
 
 
37e9c1c
fe96686
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
38e7e87
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8ca9c36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5a454aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37e9c1c
 
 
fe96686
37e9c1c
 
fe96686
37e9c1c
 
 
 
 
 
 
5a454aa
37e9c1c
 
 
 
5a454aa
37e9c1c
 
 
 
 
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": 0.0015519154516461943,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.103830903292389e-05,
      "eval_loss": 3.7120916843414307,
      "eval_runtime": 1355.8503,
      "eval_samples_per_second": 10.006,
      "eval_steps_per_second": 5.003,
      "step": 1
    },
    {
      "epoch": 0.00015519154516461942,
      "grad_norm": 2.1552507877349854,
      "learning_rate": 5e-05,
      "loss": 3.9595,
      "step": 5
    },
    {
      "epoch": 0.00031038309032923884,
      "grad_norm": 3.6430537700653076,
      "learning_rate": 0.0001,
      "loss": 3.5018,
      "step": 10
    },
    {
      "epoch": 0.00031038309032923884,
      "eval_loss": 3.1252193450927734,
      "eval_runtime": 1356.105,
      "eval_samples_per_second": 10.004,
      "eval_steps_per_second": 5.002,
      "step": 10
    },
    {
      "epoch": 0.0004655746354938583,
      "grad_norm": 2.4750373363494873,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.5722,
      "step": 15
    },
    {
      "epoch": 0.0006207661806584777,
      "grad_norm": 1.5241283178329468,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.5678,
      "step": 20
    },
    {
      "epoch": 0.0006207661806584777,
      "eval_loss": 1.1251658201217651,
      "eval_runtime": 1355.943,
      "eval_samples_per_second": 10.005,
      "eval_steps_per_second": 5.002,
      "step": 20
    },
    {
      "epoch": 0.0007759577258230971,
      "grad_norm": 1.527565360069275,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.1063,
      "step": 25
    },
    {
      "epoch": 0.0009311492709877166,
      "grad_norm": 1.7839757204055786,
      "learning_rate": 5e-05,
      "loss": 0.799,
      "step": 30
    },
    {
      "epoch": 0.0009311492709877166,
      "eval_loss": 0.6185202598571777,
      "eval_runtime": 1357.0146,
      "eval_samples_per_second": 9.997,
      "eval_steps_per_second": 4.998,
      "step": 30
    },
    {
      "epoch": 0.0010863408161523361,
      "grad_norm": 1.172727346420288,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.4837,
      "step": 35
    },
    {
      "epoch": 0.0012415323613169554,
      "grad_norm": 1.2722738981246948,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.4368,
      "step": 40
    },
    {
      "epoch": 0.0012415323613169554,
      "eval_loss": 0.4388025104999542,
      "eval_runtime": 1356.999,
      "eval_samples_per_second": 9.997,
      "eval_steps_per_second": 4.999,
      "step": 40
    },
    {
      "epoch": 0.0013967239064815748,
      "grad_norm": 1.1449508666992188,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.3963,
      "step": 45
    },
    {
      "epoch": 0.0015519154516461943,
      "grad_norm": 0.7516467571258545,
      "learning_rate": 0.0,
      "loss": 0.403,
      "step": 50
    },
    {
      "epoch": 0.0015519154516461943,
      "eval_loss": 0.41470852494239807,
      "eval_runtime": 1355.9699,
      "eval_samples_per_second": 10.005,
      "eval_steps_per_second": 5.002,
      "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": 1.547311779938304e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}