Hugging Face's logo

phungkhaccuong
/
de44363b-1544-49f6-86e7-c7aec3410086

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
de44363b-1544-49f6-86e7-c7aec3410086
File size: 3,775 Bytes 
0326ea8
 
 
51615dd
73ba1d0
51615dd
0326ea8
 
 
 
 
 
 
73ba1d0
 
 
0326ea8
73ba1d0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1080bd0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0237686
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
51615dd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0326ea8
 
 
73ba1d0
0326ea8
 
73ba1d0
0326ea8
 
 
 
 
 
 
51615dd
0326ea8
 
 
 
51615dd
0326ea8
 
 
 
 
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": 0.0006934981084839091,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.3869962169678183e-05,
      "eval_loss": 0.3170296847820282,
      "eval_runtime": 1026.3822,
      "eval_samples_per_second": 29.578,
      "eval_steps_per_second": 14.789,
      "step": 1
    },
    {
      "epoch": 6.934981084839092e-05,
      "grad_norm": 0.6361538171768188,
      "learning_rate": 5e-05,
      "loss": 0.2943,
      "step": 5
    },
    {
      "epoch": 0.00013869962169678183,
      "grad_norm": 0.7165965437889099,
      "learning_rate": 0.0001,
      "loss": 0.2509,
      "step": 10
    },
    {
      "epoch": 0.00013869962169678183,
      "eval_loss": 0.20657119154930115,
      "eval_runtime": 1002.4208,
      "eval_samples_per_second": 30.285,
      "eval_steps_per_second": 15.142,
      "step": 10
    },
    {
      "epoch": 0.00020804943254517272,
      "grad_norm": 0.8206524848937988,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.1373,
      "step": 15
    },
    {
      "epoch": 0.00027739924339356366,
      "grad_norm": 0.30765119194984436,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.076,
      "step": 20
    },
    {
      "epoch": 0.00027739924339356366,
      "eval_loss": 0.048924922943115234,
      "eval_runtime": 1003.0336,
      "eval_samples_per_second": 30.266,
      "eval_steps_per_second": 15.133,
      "step": 20
    },
    {
      "epoch": 0.00034674905424195455,
      "grad_norm": 0.2791261374950409,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.042,
      "step": 25
    },
    {
      "epoch": 0.00041609886509034544,
      "grad_norm": 0.2505738139152527,
      "learning_rate": 5e-05,
      "loss": 0.0624,
      "step": 30
    },
    {
      "epoch": 0.00041609886509034544,
      "eval_loss": 0.03364470601081848,
      "eval_runtime": 1002.5128,
      "eval_samples_per_second": 30.282,
      "eval_steps_per_second": 15.141,
      "step": 30
    },
    {
      "epoch": 0.0004854486759387364,
      "grad_norm": 0.33506065607070923,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0356,
      "step": 35
    },
    {
      "epoch": 0.0005547984867871273,
      "grad_norm": 0.15996599197387695,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0201,
      "step": 40
    },
    {
      "epoch": 0.0005547984867871273,
      "eval_loss": 0.029385773465037346,
      "eval_runtime": 998.9003,
      "eval_samples_per_second": 30.391,
      "eval_steps_per_second": 15.196,
      "step": 40
    },
    {
      "epoch": 0.0006241482976355182,
      "grad_norm": 0.20267634093761444,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0171,
      "step": 45
    },
    {
      "epoch": 0.0006934981084839091,
      "grad_norm": 0.5985381007194519,
      "learning_rate": 0.0,
      "loss": 0.0319,
      "step": 50
    },
    {
      "epoch": 0.0006934981084839091,
      "eval_loss": 0.028885377570986748,
      "eval_runtime": 999.0425,
      "eval_samples_per_second": 30.387,
      "eval_steps_per_second": 15.194,
      "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": 1621484686540800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}