Hugging Face's logo

chauhoang
/
e468ec6d-4fa6-44c9-924e-b5eab8c90782

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e468ec6d-4fa6-44c9-924e-b5eab8c90782
File size: 3,686 Bytes 
7f9b26e
 
 
6ae896d
b228a72
6ae896d
7f9b26e
 
 
 
 
 
 
b228a72
 
 
7f9b26e
b228a72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fe28a08
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f9251e3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6ae896d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f9b26e
 
 
b228a72
7f9b26e
 
b228a72
7f9b26e
 
 
 
 
 
 
6ae896d
7f9b26e
 
 
 
6ae896d
7f9b26e
 
 
 
 
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": 0.0490075961774075,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00098015192354815,
      "eval_loss": 2.4223687648773193,
      "eval_runtime": 7.5327,
      "eval_samples_per_second": 57.084,
      "eval_steps_per_second": 28.542,
      "step": 1
    },
    {
      "epoch": 0.00490075961774075,
      "grad_norm": 0.6046074628829956,
      "learning_rate": 5e-05,
      "loss": 2.2393,
      "step": 5
    },
    {
      "epoch": 0.0098015192354815,
      "grad_norm": 0.5879426598548889,
      "learning_rate": 0.0001,
      "loss": 2.3545,
      "step": 10
    },
    {
      "epoch": 0.0098015192354815,
      "eval_loss": 2.399517774581909,
      "eval_runtime": 7.6193,
      "eval_samples_per_second": 56.435,
      "eval_steps_per_second": 28.218,
      "step": 10
    },
    {
      "epoch": 0.014702278853222249,
      "grad_norm": 0.5461297035217285,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.2989,
      "step": 15
    },
    {
      "epoch": 0.019603038470963,
      "grad_norm": 0.7177299857139587,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.279,
      "step": 20
    },
    {
      "epoch": 0.019603038470963,
      "eval_loss": 2.260446548461914,
      "eval_runtime": 7.5302,
      "eval_samples_per_second": 57.103,
      "eval_steps_per_second": 28.552,
      "step": 20
    },
    {
      "epoch": 0.02450379808870375,
      "grad_norm": 0.7443307638168335,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.1953,
      "step": 25
    },
    {
      "epoch": 0.029404557706444498,
      "grad_norm": 0.5858839750289917,
      "learning_rate": 5e-05,
      "loss": 2.1387,
      "step": 30
    },
    {
      "epoch": 0.029404557706444498,
      "eval_loss": 2.1607236862182617,
      "eval_runtime": 7.7464,
      "eval_samples_per_second": 55.51,
      "eval_steps_per_second": 27.755,
      "step": 30
    },
    {
      "epoch": 0.03430531732418525,
      "grad_norm": 0.620461642742157,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.094,
      "step": 35
    },
    {
      "epoch": 0.039206076941926,
      "grad_norm": 0.6441255211830139,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.0022,
      "step": 40
    },
    {
      "epoch": 0.039206076941926,
      "eval_loss": 2.119108200073242,
      "eval_runtime": 7.7335,
      "eval_samples_per_second": 55.602,
      "eval_steps_per_second": 27.801,
      "step": 40
    },
    {
      "epoch": 0.04410683655966675,
      "grad_norm": 0.7288550734519958,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.0913,
      "step": 45
    },
    {
      "epoch": 0.0490075961774075,
      "grad_norm": 0.7713973522186279,
      "learning_rate": 0.0,
      "loss": 2.0359,
      "step": 50
    },
    {
      "epoch": 0.0490075961774075,
      "eval_loss": 2.1122353076934814,
      "eval_runtime": 7.5703,
      "eval_samples_per_second": 56.801,
      "eval_steps_per_second": 28.4,
      "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": 171463252377600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}