Hugging Face's logo

TokenBender
/
test_tokenizer_issue

PEFT
Safetensors
trl
sft
Generated from Trainer
Model card Files Community
test_tokenizer_issue
File size: 2,673 Bytes 
8cada09
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.6666666666666666,
  "eval_steps": 500,
  "global_step": 16,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04,
      "grad_norm": 0.049072265625,
      "learning_rate": 0.0002,
      "loss": 1.2558,
      "step": 1
    },
    {
      "epoch": 0.08,
      "grad_norm": 0.046630859375,
      "learning_rate": 0.0002,
      "loss": 1.276,
      "step": 2
    },
    {
      "epoch": 0.12,
      "grad_norm": 0.046875,
      "learning_rate": 0.0002,
      "loss": 1.2758,
      "step": 3
    },
    {
      "epoch": 0.17,
      "grad_norm": 0.054443359375,
      "learning_rate": 0.0002,
      "loss": 1.2889,
      "step": 4
    },
    {
      "epoch": 0.21,
      "grad_norm": 0.058349609375,
      "learning_rate": 0.0002,
      "loss": 1.3781,
      "step": 5
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.042724609375,
      "learning_rate": 0.0002,
      "loss": 1.2866,
      "step": 6
    },
    {
      "epoch": 0.29,
      "grad_norm": 0.041748046875,
      "learning_rate": 0.0002,
      "loss": 1.1998,
      "step": 7
    },
    {
      "epoch": 0.33,
      "grad_norm": 0.044677734375,
      "learning_rate": 0.0002,
      "loss": 1.2973,
      "step": 8
    },
    {
      "epoch": 0.38,
      "grad_norm": 0.044921875,
      "learning_rate": 0.0002,
      "loss": 1.2811,
      "step": 9
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.039794921875,
      "learning_rate": 0.0002,
      "loss": 1.2072,
      "step": 10
    },
    {
      "epoch": 0.46,
      "grad_norm": 0.040283203125,
      "learning_rate": 0.0002,
      "loss": 1.2256,
      "step": 11
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.0380859375,
      "learning_rate": 0.0002,
      "loss": 1.3164,
      "step": 12
    },
    {
      "epoch": 0.54,
      "grad_norm": 0.0380859375,
      "learning_rate": 0.0002,
      "loss": 1.2636,
      "step": 13
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.039794921875,
      "learning_rate": 0.0002,
      "loss": 1.2758,
      "step": 14
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.0400390625,
      "learning_rate": 0.0002,
      "loss": 1.097,
      "step": 15
    },
    {
      "epoch": 0.67,
      "grad_norm": 0.04248046875,
      "learning_rate": 0.0002,
      "loss": 1.1723,
      "step": 16
    }
  ],
  "logging_steps": 1,
  "max_steps": 24,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 8,
  "total_flos": 3333678453227520.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}