Hugging Face's logo

phungkhaccuong
/
2b1d8ae7-b97a-9f46-10b2-c3de8f5a5766

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
2b1d8ae7-b97a-9f46-10b2-c3de8f5a5766
File size: 3,704 Bytes 
c475157
 
 
ca79f83
b195bd7
ca79f83
c475157
 
 
 
 
 
 
b195bd7
 
 
c475157
b195bd7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
269ec1b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ac0fc7d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ca79f83
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c475157
 
 
b195bd7
c475157
 
b195bd7
c475157
 
 
 
 
 
 
ca79f83
c475157
 
 
 
ca79f83
c475157
 
 
 
 
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": 0.03073140749846343,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006146281499692685,
      "eval_loss": 32.18796920776367,
      "eval_runtime": 9.9698,
      "eval_samples_per_second": 68.708,
      "eval_steps_per_second": 34.404,
      "step": 1
    },
    {
      "epoch": 0.003073140749846343,
      "grad_norm": 1042.032958984375,
      "learning_rate": 5e-05,
      "loss": 151.3782,
      "step": 5
    },
    {
      "epoch": 0.006146281499692686,
      "grad_norm": 1655.912109375,
      "learning_rate": 0.0001,
      "loss": 90.5781,
      "step": 10
    },
    {
      "epoch": 0.006146281499692686,
      "eval_loss": 32.177650451660156,
      "eval_runtime": 7.9223,
      "eval_samples_per_second": 86.465,
      "eval_steps_per_second": 43.296,
      "step": 10
    },
    {
      "epoch": 0.00921942224953903,
      "grad_norm": 1991.4852294921875,
      "learning_rate": 9.619397662556435e-05,
      "loss": 130.4381,
      "step": 15
    },
    {
      "epoch": 0.012292562999385371,
      "grad_norm": 642.9652099609375,
      "learning_rate": 8.535533905932738e-05,
      "loss": 99.3049,
      "step": 20
    },
    {
      "epoch": 0.012292562999385371,
      "eval_loss": 32.11423873901367,
      "eval_runtime": 7.9533,
      "eval_samples_per_second": 86.128,
      "eval_steps_per_second": 43.127,
      "step": 20
    },
    {
      "epoch": 0.015365703749231715,
      "grad_norm": 820.176513671875,
      "learning_rate": 6.91341716182545e-05,
      "loss": 36.4627,
      "step": 25
    },
    {
      "epoch": 0.01843884449907806,
      "grad_norm": 483.0568542480469,
      "learning_rate": 5e-05,
      "loss": 69.362,
      "step": 30
    },
    {
      "epoch": 0.01843884449907806,
      "eval_loss": 32.029048919677734,
      "eval_runtime": 8.109,
      "eval_samples_per_second": 84.474,
      "eval_steps_per_second": 42.299,
      "step": 30
    },
    {
      "epoch": 0.0215119852489244,
      "grad_norm": 1287.2490234375,
      "learning_rate": 3.086582838174551e-05,
      "loss": 60.0403,
      "step": 35
    },
    {
      "epoch": 0.024585125998770743,
      "grad_norm": 5726.9609375,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 177.8988,
      "step": 40
    },
    {
      "epoch": 0.024585125998770743,
      "eval_loss": 32.00729751586914,
      "eval_runtime": 7.9572,
      "eval_samples_per_second": 86.086,
      "eval_steps_per_second": 43.106,
      "step": 40
    },
    {
      "epoch": 0.027658266748617086,
      "grad_norm": 1328.4888916015625,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 125.6105,
      "step": 45
    },
    {
      "epoch": 0.03073140749846343,
      "grad_norm": 929.8414306640625,
      "learning_rate": 0.0,
      "loss": 61.2684,
      "step": 50
    },
    {
      "epoch": 0.03073140749846343,
      "eval_loss": 31.988927841186523,
      "eval_runtime": 7.9558,
      "eval_samples_per_second": 86.101,
      "eval_steps_per_second": 43.113,
      "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": 92199173750784.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}