Hugging Face's logo

duyphu
/
eeb52018-b87d-3570-d255-3277215dd4ea

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
eeb52018-b87d-3570-d255-3277215dd4ea
File size: 3,712 Bytes 
d0403e5
 
 
1f6fc1d
5e88a4b
1f6fc1d
d0403e5
 
 
 
 
 
 
5e88a4b
 
 
d0403e5
5e88a4b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a258800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ffc8f3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1f6fc1d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d0403e5
 
 
5e88a4b
d0403e5
 
5e88a4b
d0403e5
 
 
 
 
 
 
1f6fc1d
d0403e5
 
 
 
1f6fc1d
d0403e5
 
 
 
 
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": 0.043402777777777776,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0008680555555555555,
      "eval_loss": 4.605380535125732,
      "eval_runtime": 21.8282,
      "eval_samples_per_second": 22.219,
      "eval_steps_per_second": 11.132,
      "step": 1
    },
    {
      "epoch": 0.004340277777777778,
      "grad_norm": 1.5089558362960815,
      "learning_rate": 5e-05,
      "loss": 4.1534,
      "step": 5
    },
    {
      "epoch": 0.008680555555555556,
      "grad_norm": 1.6227378845214844,
      "learning_rate": 0.0001,
      "loss": 4.2115,
      "step": 10
    },
    {
      "epoch": 0.008680555555555556,
      "eval_loss": 4.272531509399414,
      "eval_runtime": 17.0616,
      "eval_samples_per_second": 28.426,
      "eval_steps_per_second": 14.243,
      "step": 10
    },
    {
      "epoch": 0.013020833333333334,
      "grad_norm": 2.2388646602630615,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.6183,
      "step": 15
    },
    {
      "epoch": 0.017361111111111112,
      "grad_norm": 3.2893173694610596,
      "learning_rate": 8.535533905932738e-05,
      "loss": 3.1206,
      "step": 20
    },
    {
      "epoch": 0.017361111111111112,
      "eval_loss": 2.4937543869018555,
      "eval_runtime": 16.1492,
      "eval_samples_per_second": 30.033,
      "eval_steps_per_second": 15.047,
      "step": 20
    },
    {
      "epoch": 0.021701388888888888,
      "grad_norm": 3.498352289199829,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.8513,
      "step": 25
    },
    {
      "epoch": 0.026041666666666668,
      "grad_norm": 3.8759148120880127,
      "learning_rate": 5e-05,
      "loss": 1.4983,
      "step": 30
    },
    {
      "epoch": 0.026041666666666668,
      "eval_loss": 1.2910934686660767,
      "eval_runtime": 16.1354,
      "eval_samples_per_second": 30.058,
      "eval_steps_per_second": 15.06,
      "step": 30
    },
    {
      "epoch": 0.030381944444444444,
      "grad_norm": 2.2127106189727783,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.0924,
      "step": 35
    },
    {
      "epoch": 0.034722222222222224,
      "grad_norm": 2.26999831199646,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.0614,
      "step": 40
    },
    {
      "epoch": 0.034722222222222224,
      "eval_loss": 0.9549398422241211,
      "eval_runtime": 16.2023,
      "eval_samples_per_second": 29.934,
      "eval_steps_per_second": 14.998,
      "step": 40
    },
    {
      "epoch": 0.0390625,
      "grad_norm": 2.241302728652954,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.9946,
      "step": 45
    },
    {
      "epoch": 0.043402777777777776,
      "grad_norm": 2.1079211235046387,
      "learning_rate": 0.0,
      "loss": 0.9447,
      "step": 50
    },
    {
      "epoch": 0.043402777777777776,
      "eval_loss": 0.9167178273200989,
      "eval_runtime": 15.9527,
      "eval_samples_per_second": 30.402,
      "eval_steps_per_second": 15.233,
      "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": 1581936279552000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}