Hugging Face's logo

chauhoang
/
f88a2499-7863-40fe-8e8a-a717b5e783be

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
f88a2499-7863-40fe-8e8a-a717b5e783be
File size: 3,738 Bytes 
f807d54
 
 
290ad4e
e3f99e7
290ad4e
f807d54
 
 
 
 
 
 
e3f99e7
 
 
f807d54
e3f99e7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
398cb01
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ef08500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
290ad4e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f807d54
 
 
e3f99e7
f807d54
 
e3f99e7
f807d54
 
 
 
 
 
 
290ad4e
f807d54
 
 
 
290ad4e
f807d54
 
 
 
 
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": 0.005446771426237098,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00010893542852474196,
      "eval_loss": 4.965454578399658,
      "eval_runtime": 146.1989,
      "eval_samples_per_second": 26.443,
      "eval_steps_per_second": 13.222,
      "step": 1
    },
    {
      "epoch": 0.0005446771426237097,
      "grad_norm": 2.617262125015259,
      "learning_rate": 5e-05,
      "loss": 4.4074,
      "step": 5
    },
    {
      "epoch": 0.0010893542852474195,
      "grad_norm": 3.2852272987365723,
      "learning_rate": 0.0001,
      "loss": 4.7221,
      "step": 10
    },
    {
      "epoch": 0.0010893542852474195,
      "eval_loss": 4.596639633178711,
      "eval_runtime": 146.8778,
      "eval_samples_per_second": 26.321,
      "eval_steps_per_second": 13.161,
      "step": 10
    },
    {
      "epoch": 0.0016340314278711294,
      "grad_norm": 1.9587860107421875,
      "learning_rate": 9.619397662556435e-05,
      "loss": 4.1211,
      "step": 15
    },
    {
      "epoch": 0.002178708570494839,
      "grad_norm": 3.960905075073242,
      "learning_rate": 8.535533905932738e-05,
      "loss": 4.1157,
      "step": 20
    },
    {
      "epoch": 0.002178708570494839,
      "eval_loss": 3.9367244243621826,
      "eval_runtime": 147.1567,
      "eval_samples_per_second": 26.271,
      "eval_steps_per_second": 13.136,
      "step": 20
    },
    {
      "epoch": 0.002723385713118549,
      "grad_norm": 2.2079458236694336,
      "learning_rate": 6.91341716182545e-05,
      "loss": 3.8274,
      "step": 25
    },
    {
      "epoch": 0.0032680628557422587,
      "grad_norm": 2.1029868125915527,
      "learning_rate": 5e-05,
      "loss": 3.572,
      "step": 30
    },
    {
      "epoch": 0.0032680628557422587,
      "eval_loss": 3.6732211112976074,
      "eval_runtime": 147.1822,
      "eval_samples_per_second": 26.267,
      "eval_steps_per_second": 13.133,
      "step": 30
    },
    {
      "epoch": 0.0038127399983659688,
      "grad_norm": 3.5215439796447754,
      "learning_rate": 3.086582838174551e-05,
      "loss": 3.7833,
      "step": 35
    },
    {
      "epoch": 0.004357417140989678,
      "grad_norm": 1.7290146350860596,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 3.5714,
      "step": 40
    },
    {
      "epoch": 0.004357417140989678,
      "eval_loss": 3.5499491691589355,
      "eval_runtime": 147.1354,
      "eval_samples_per_second": 26.275,
      "eval_steps_per_second": 13.138,
      "step": 40
    },
    {
      "epoch": 0.004902094283613388,
      "grad_norm": 1.980006456375122,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 3.6728,
      "step": 45
    },
    {
      "epoch": 0.005446771426237098,
      "grad_norm": 2.2260336875915527,
      "learning_rate": 0.0,
      "loss": 3.2603,
      "step": 50
    },
    {
      "epoch": 0.005446771426237098,
      "eval_loss": 3.5256547927856445,
      "eval_runtime": 149.9294,
      "eval_samples_per_second": 25.785,
      "eval_steps_per_second": 12.893,
      "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": 4120744541552640.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}