Hugging Face's logo

duyphu
/
6da5970f-fbcc-4885-a229-c7aa96c72467

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
6da5970f-fbcc-4885-a229-c7aa96c72467
File size: 3,714 Bytes 
833cb5f
 
 
154f54b
1e37e4d
154f54b
833cb5f
 
 
 
 
 
 
1e37e4d
 
 
833cb5f
1e37e4d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b865f42
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c88d09d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
154f54b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
833cb5f
 
 
1e37e4d
833cb5f
 
1e37e4d
833cb5f
 
 
 
 
 
 
154f54b
833cb5f
 
 
 
154f54b
833cb5f
 
 
 
 
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": 0.0485319097306479,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000970638194612958,
      "eval_loss": 2.2291553020477295,
      "eval_runtime": 14.4912,
      "eval_samples_per_second": 29.949,
      "eval_steps_per_second": 14.975,
      "step": 1
    },
    {
      "epoch": 0.0048531909730647905,
      "grad_norm": 1.095381498336792,
      "learning_rate": 5e-05,
      "loss": 2.2359,
      "step": 5
    },
    {
      "epoch": 0.009706381946129581,
      "grad_norm": 0.7277218103408813,
      "learning_rate": 0.0001,
      "loss": 2.1487,
      "step": 10
    },
    {
      "epoch": 0.009706381946129581,
      "eval_loss": 2.1091368198394775,
      "eval_runtime": 14.5705,
      "eval_samples_per_second": 29.786,
      "eval_steps_per_second": 14.893,
      "step": 10
    },
    {
      "epoch": 0.01455957291919437,
      "grad_norm": 0.7657337784767151,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1049,
      "step": 15
    },
    {
      "epoch": 0.019412763892259162,
      "grad_norm": 0.8005470633506775,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9949,
      "step": 20
    },
    {
      "epoch": 0.019412763892259162,
      "eval_loss": 1.9761087894439697,
      "eval_runtime": 14.7541,
      "eval_samples_per_second": 29.416,
      "eval_steps_per_second": 14.708,
      "step": 20
    },
    {
      "epoch": 0.02426595486532395,
      "grad_norm": 0.6035395264625549,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0049,
      "step": 25
    },
    {
      "epoch": 0.02911914583838874,
      "grad_norm": 0.9888164401054382,
      "learning_rate": 5e-05,
      "loss": 1.9446,
      "step": 30
    },
    {
      "epoch": 0.02911914583838874,
      "eval_loss": 1.9136253595352173,
      "eval_runtime": 14.7115,
      "eval_samples_per_second": 29.501,
      "eval_steps_per_second": 14.75,
      "step": 30
    },
    {
      "epoch": 0.03397233681145353,
      "grad_norm": 0.6257792115211487,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.8295,
      "step": 35
    },
    {
      "epoch": 0.038825527784518324,
      "grad_norm": 0.7209451198577881,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.9043,
      "step": 40
    },
    {
      "epoch": 0.038825527784518324,
      "eval_loss": 1.8833268880844116,
      "eval_runtime": 14.8456,
      "eval_samples_per_second": 29.234,
      "eval_steps_per_second": 14.617,
      "step": 40
    },
    {
      "epoch": 0.04367871875758311,
      "grad_norm": 0.6183915734291077,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.8511,
      "step": 45
    },
    {
      "epoch": 0.0485319097306479,
      "grad_norm": 0.6538072228431702,
      "learning_rate": 0.0,
      "loss": 1.8676,
      "step": 50
    },
    {
      "epoch": 0.0485319097306479,
      "eval_loss": 1.8793177604675293,
      "eval_runtime": 14.6525,
      "eval_samples_per_second": 29.62,
      "eval_steps_per_second": 14.81,
      "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": 1995177430351872.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}