Hugging Face's logo

phungkhaccuong
/
016417b1-8b1c-b5e3-255d-1696aa29db09

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
016417b1-8b1c-b5e3-255d-1696aa29db09
File size: 3,736 Bytes 
fde6a9c
 
 
ba48f8b
5486eea
ba48f8b
fde6a9c
 
 
 
 
 
 
5486eea
 
 
fde6a9c
5486eea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bc4134a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ad81ff0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ba48f8b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fde6a9c
 
 
5486eea
fde6a9c
 
5486eea
fde6a9c
 
 
 
 
 
 
ba48f8b
fde6a9c
 
 
 
ba48f8b
fde6a9c
 
 
 
 
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": 0.08880994671403197,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0017761989342806395,
      "eval_loss": 10.375921249389648,
      "eval_runtime": 1.1462,
      "eval_samples_per_second": 207.638,
      "eval_steps_per_second": 103.819,
      "step": 1
    },
    {
      "epoch": 0.008880994671403197,
      "grad_norm": 0.04732152819633484,
      "learning_rate": 5e-05,
      "loss": 10.38,
      "step": 5
    },
    {
      "epoch": 0.017761989342806393,
      "grad_norm": 0.03675731271505356,
      "learning_rate": 0.0001,
      "loss": 10.3764,
      "step": 10
    },
    {
      "epoch": 0.017761989342806393,
      "eval_loss": 10.375849723815918,
      "eval_runtime": 1.1333,
      "eval_samples_per_second": 210.002,
      "eval_steps_per_second": 105.001,
      "step": 10
    },
    {
      "epoch": 0.02664298401420959,
      "grad_norm": 0.054118264466524124,
      "learning_rate": 9.619397662556435e-05,
      "loss": 10.3796,
      "step": 15
    },
    {
      "epoch": 0.035523978685612786,
      "grad_norm": 0.052961334586143494,
      "learning_rate": 8.535533905932738e-05,
      "loss": 10.3793,
      "step": 20
    },
    {
      "epoch": 0.035523978685612786,
      "eval_loss": 10.375701904296875,
      "eval_runtime": 1.157,
      "eval_samples_per_second": 205.713,
      "eval_steps_per_second": 102.856,
      "step": 20
    },
    {
      "epoch": 0.04440497335701599,
      "grad_norm": 0.04892309010028839,
      "learning_rate": 6.91341716182545e-05,
      "loss": 10.3723,
      "step": 25
    },
    {
      "epoch": 0.05328596802841918,
      "grad_norm": 0.04572363942861557,
      "learning_rate": 5e-05,
      "loss": 10.3777,
      "step": 30
    },
    {
      "epoch": 0.05328596802841918,
      "eval_loss": 10.375574111938477,
      "eval_runtime": 1.2336,
      "eval_samples_per_second": 192.927,
      "eval_steps_per_second": 96.464,
      "step": 30
    },
    {
      "epoch": 0.06216696269982238,
      "grad_norm": 0.056839704513549805,
      "learning_rate": 3.086582838174551e-05,
      "loss": 10.3748,
      "step": 35
    },
    {
      "epoch": 0.07104795737122557,
      "grad_norm": 0.05530121922492981,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 10.3747,
      "step": 40
    },
    {
      "epoch": 0.07104795737122557,
      "eval_loss": 10.37551498413086,
      "eval_runtime": 1.2478,
      "eval_samples_per_second": 190.729,
      "eval_steps_per_second": 95.364,
      "step": 40
    },
    {
      "epoch": 0.07992895204262877,
      "grad_norm": 0.05178322643041611,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 10.364,
      "step": 45
    },
    {
      "epoch": 0.08880994671403197,
      "grad_norm": 0.05107550323009491,
      "learning_rate": 0.0,
      "loss": 10.3756,
      "step": 50
    },
    {
      "epoch": 0.08880994671403197,
      "eval_loss": 10.375503540039062,
      "eval_runtime": 1.2205,
      "eval_samples_per_second": 195.007,
      "eval_steps_per_second": 97.503,
      "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": 646545408000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}