Hugging Face's logo

tuanna08go
/
dae97f7e-c7bd-473b-b1ce-72e91441c5b2

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
dae97f7e-c7bd-473b-b1ce-72e91441c5b2
File size: 3,749 Bytes 
e59cac3
 
 
9495dec
695ee50
9495dec
e59cac3
 
 
 
 
 
 
695ee50
 
 
e59cac3
695ee50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7def727
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d908914
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9495dec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e59cac3
 
 
695ee50
e59cac3
 
695ee50
e59cac3
 
 
 
 
 
 
9495dec
e59cac3
 
 
 
9495dec
e59cac3
 
 
 
 
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": 0.0008861438122792948,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.7722876245585897e-05,
      "eval_loss": 1.7361408472061157,
      "eval_runtime": 1985.431,
      "eval_samples_per_second": 11.966,
      "eval_steps_per_second": 5.983,
      "step": 1
    },
    {
      "epoch": 8.861438122792948e-05,
      "grad_norm": 0.8715835809707642,
      "learning_rate": 5e-05,
      "loss": 1.6216,
      "step": 5
    },
    {
      "epoch": 0.00017722876245585895,
      "grad_norm": 1.0856618881225586,
      "learning_rate": 0.0001,
      "loss": 1.3852,
      "step": 10
    },
    {
      "epoch": 0.00017722876245585895,
      "eval_loss": 1.437419056892395,
      "eval_runtime": 2011.3717,
      "eval_samples_per_second": 11.812,
      "eval_steps_per_second": 5.906,
      "step": 10
    },
    {
      "epoch": 0.00026584314368378843,
      "grad_norm": 1.6904109716415405,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.2922,
      "step": 15
    },
    {
      "epoch": 0.0003544575249117179,
      "grad_norm": 1.2493869066238403,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.8623,
      "step": 20
    },
    {
      "epoch": 0.0003544575249117179,
      "eval_loss": 0.7036842107772827,
      "eval_runtime": 2008.721,
      "eval_samples_per_second": 11.827,
      "eval_steps_per_second": 5.914,
      "step": 20
    },
    {
      "epoch": 0.0004430719061396474,
      "grad_norm": 1.8683321475982666,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7287,
      "step": 25
    },
    {
      "epoch": 0.0005316862873675769,
      "grad_norm": 1.5432759523391724,
      "learning_rate": 5e-05,
      "loss": 0.6118,
      "step": 30
    },
    {
      "epoch": 0.0005316862873675769,
      "eval_loss": 0.5978233218193054,
      "eval_runtime": 2010.9302,
      "eval_samples_per_second": 11.814,
      "eval_steps_per_second": 5.907,
      "step": 30
    },
    {
      "epoch": 0.0006203006685955064,
      "grad_norm": 1.030396819114685,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.6266,
      "step": 35
    },
    {
      "epoch": 0.0007089150498234358,
      "grad_norm": 0.6566690802574158,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.5257,
      "step": 40
    },
    {
      "epoch": 0.0007089150498234358,
      "eval_loss": 0.5642721056938171,
      "eval_runtime": 2008.0741,
      "eval_samples_per_second": 11.831,
      "eval_steps_per_second": 5.916,
      "step": 40
    },
    {
      "epoch": 0.0007975294310513653,
      "grad_norm": 0.8434397578239441,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.586,
      "step": 45
    },
    {
      "epoch": 0.0008861438122792948,
      "grad_norm": 1.120571255683899,
      "learning_rate": 0.0,
      "loss": 0.5317,
      "step": 50
    },
    {
      "epoch": 0.0008861438122792948,
      "eval_loss": 0.5591886043548584,
      "eval_runtime": 2006.7277,
      "eval_samples_per_second": 11.839,
      "eval_steps_per_second": 5.92,
      "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": 8980634932346880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}