Hugging Face's logo

phungkhaccuong
/
ac8add57-1cd9-4238-a0d7-c40d6498c187

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ac8add57-1cd9-4238-a0d7-c40d6498c187
File size: 3,701 Bytes 
01c010e
 
 
b4a6be5
65f5b8e
b4a6be5
01c010e
 
 
 
 
 
 
65f5b8e
 
 
01c010e
65f5b8e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b2d2bc8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
830a919
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b4a6be5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
01c010e
 
 
65f5b8e
01c010e
 
65f5b8e
01c010e
 
 
 
 
 
 
b4a6be5
01c010e
 
 
 
b4a6be5
01c010e
 
 
 
 
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": 0.04657661853749418,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009315323707498836,
      "eval_loss": 2.67449688911438,
      "eval_runtime": 54.9548,
      "eval_samples_per_second": 8.243,
      "eval_steps_per_second": 4.131,
      "step": 1
    },
    {
      "epoch": 0.004657661853749418,
      "grad_norm": 1.050082802772522,
      "learning_rate": 5e-05,
      "loss": 2.3571,
      "step": 5
    },
    {
      "epoch": 0.009315323707498836,
      "grad_norm": 1.03178071975708,
      "learning_rate": 0.0001,
      "loss": 2.2236,
      "step": 10
    },
    {
      "epoch": 0.009315323707498836,
      "eval_loss": 2.541896104812622,
      "eval_runtime": 55.3938,
      "eval_samples_per_second": 8.178,
      "eval_steps_per_second": 4.098,
      "step": 10
    },
    {
      "epoch": 0.013972985561248253,
      "grad_norm": 1.6759586334228516,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.084,
      "step": 15
    },
    {
      "epoch": 0.018630647414997672,
      "grad_norm": 1.6972988843917847,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.2981,
      "step": 20
    },
    {
      "epoch": 0.018630647414997672,
      "eval_loss": 2.2054669857025146,
      "eval_runtime": 55.6666,
      "eval_samples_per_second": 8.138,
      "eval_steps_per_second": 4.078,
      "step": 20
    },
    {
      "epoch": 0.02328830926874709,
      "grad_norm": 2.279262065887451,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0858,
      "step": 25
    },
    {
      "epoch": 0.027945971122496506,
      "grad_norm": 2.0147440433502197,
      "learning_rate": 5e-05,
      "loss": 1.9067,
      "step": 30
    },
    {
      "epoch": 0.027945971122496506,
      "eval_loss": 2.0615034103393555,
      "eval_runtime": 55.7005,
      "eval_samples_per_second": 8.133,
      "eval_steps_per_second": 4.075,
      "step": 30
    },
    {
      "epoch": 0.032603632976245925,
      "grad_norm": 2.2418673038482666,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.9613,
      "step": 35
    },
    {
      "epoch": 0.037261294829995344,
      "grad_norm": 2.235062599182129,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.933,
      "step": 40
    },
    {
      "epoch": 0.037261294829995344,
      "eval_loss": 2.0007143020629883,
      "eval_runtime": 55.7249,
      "eval_samples_per_second": 8.129,
      "eval_steps_per_second": 4.074,
      "step": 40
    },
    {
      "epoch": 0.04191895668374476,
      "grad_norm": 1.7607734203338623,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.893,
      "step": 45
    },
    {
      "epoch": 0.04657661853749418,
      "grad_norm": 2.078504800796509,
      "learning_rate": 0.0,
      "loss": 1.7617,
      "step": 50
    },
    {
      "epoch": 0.04657661853749418,
      "eval_loss": 1.9849607944488525,
      "eval_runtime": 55.6865,
      "eval_samples_per_second": 8.135,
      "eval_steps_per_second": 4.076,
      "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": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}