Hugging Face's logo

chauhoang
/
13f84693-d330-3b01-d18b-36c968f891fa

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
13f84693-d330-3b01-d18b-36c968f891fa
File size: 3,731 Bytes 
95c5df9
 
 
7b96575
c9af940
7b96575
95c5df9
 
 
 
 
 
 
c9af940
 
 
95c5df9
c9af940
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7433d95
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b1ac742
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7b96575
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
95c5df9
 
 
c9af940
95c5df9
 
c9af940
95c5df9
 
 
 
 
 
 
7b96575
95c5df9
 
 
 
7b96575
95c5df9
 
 
 
 
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": 0.003770810158562567,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 7.541620317125135e-05,
      "eval_loss": 2.0435900688171387,
      "eval_runtime": 665.4247,
      "eval_samples_per_second": 8.392,
      "eval_steps_per_second": 4.196,
      "step": 1
    },
    {
      "epoch": 0.0003770810158562567,
      "grad_norm": 2.116191864013672,
      "learning_rate": 5e-05,
      "loss": 2.0936,
      "step": 5
    },
    {
      "epoch": 0.0007541620317125134,
      "grad_norm": 1.9126191139221191,
      "learning_rate": 0.0001,
      "loss": 1.8052,
      "step": 10
    },
    {
      "epoch": 0.0007541620317125134,
      "eval_loss": 1.2857778072357178,
      "eval_runtime": 669.1514,
      "eval_samples_per_second": 8.345,
      "eval_steps_per_second": 4.172,
      "step": 10
    },
    {
      "epoch": 0.0011312430475687702,
      "grad_norm": 1.9551734924316406,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.9694,
      "step": 15
    },
    {
      "epoch": 0.0015083240634250269,
      "grad_norm": 1.7354230880737305,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.7,
      "step": 20
    },
    {
      "epoch": 0.0015083240634250269,
      "eval_loss": 0.6742600798606873,
      "eval_runtime": 670.7305,
      "eval_samples_per_second": 8.325,
      "eval_steps_per_second": 4.163,
      "step": 20
    },
    {
      "epoch": 0.0018854050792812835,
      "grad_norm": 1.9610943794250488,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.6783,
      "step": 25
    },
    {
      "epoch": 0.0022624860951375404,
      "grad_norm": 1.485725998878479,
      "learning_rate": 5e-05,
      "loss": 0.5881,
      "step": 30
    },
    {
      "epoch": 0.0022624860951375404,
      "eval_loss": 0.5489432215690613,
      "eval_runtime": 667.7804,
      "eval_samples_per_second": 8.362,
      "eval_steps_per_second": 4.181,
      "step": 30
    },
    {
      "epoch": 0.002639567110993797,
      "grad_norm": 1.5018064975738525,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.569,
      "step": 35
    },
    {
      "epoch": 0.0030166481268500537,
      "grad_norm": 1.476067066192627,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5314,
      "step": 40
    },
    {
      "epoch": 0.0030166481268500537,
      "eval_loss": 0.5157779455184937,
      "eval_runtime": 664.516,
      "eval_samples_per_second": 8.403,
      "eval_steps_per_second": 4.202,
      "step": 40
    },
    {
      "epoch": 0.0033937291427063106,
      "grad_norm": 1.6906317472457886,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.4455,
      "step": 45
    },
    {
      "epoch": 0.003770810158562567,
      "grad_norm": 1.3468632698059082,
      "learning_rate": 0.0,
      "loss": 0.4905,
      "step": 50
    },
    {
      "epoch": 0.003770810158562567,
      "eval_loss": 0.5104564428329468,
      "eval_runtime": 667.6626,
      "eval_samples_per_second": 8.364,
      "eval_steps_per_second": 4.182,
      "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": 1.780205588840448e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}