Hugging Face's logo

duyphu
/
ea7b14e5-4610-46ac-b82c-e7e7b273e0ed

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ea7b14e5-4610-46ac-b82c-e7e7b273e0ed
File size: 3,698 Bytes 
befc1d7
 
 
1616b4d
62d9a05
1616b4d
befc1d7
 
 
 
 
 
 
62d9a05
 
 
befc1d7
62d9a05
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
00e1105
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41539e1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1616b4d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
befc1d7
 
 
62d9a05
befc1d7
 
62d9a05
befc1d7
 
 
 
 
 
 
1616b4d
befc1d7
 
 
 
1616b4d
befc1d7
 
 
 
 
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": 0.18298261665141813,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0036596523330283625,
      "eval_loss": 6.844988822937012,
      "eval_runtime": 6.9069,
      "eval_samples_per_second": 16.65,
      "eval_steps_per_second": 8.397,
      "step": 1
    },
    {
      "epoch": 0.018298261665141813,
      "grad_norm": 11.751487731933594,
      "learning_rate": 5e-05,
      "loss": 6.8396,
      "step": 5
    },
    {
      "epoch": 0.036596523330283626,
      "grad_norm": 8.099217414855957,
      "learning_rate": 0.0001,
      "loss": 4.2657,
      "step": 10
    },
    {
      "epoch": 0.036596523330283626,
      "eval_loss": 1.4936703443527222,
      "eval_runtime": 6.9534,
      "eval_samples_per_second": 16.539,
      "eval_steps_per_second": 8.341,
      "step": 10
    },
    {
      "epoch": 0.05489478499542543,
      "grad_norm": 2.1512739658355713,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.9735,
      "step": 15
    },
    {
      "epoch": 0.07319304666056725,
      "grad_norm": 1.4982128143310547,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.6925,
      "step": 20
    },
    {
      "epoch": 0.07319304666056725,
      "eval_loss": 0.7363909482955933,
      "eval_runtime": 6.9844,
      "eval_samples_per_second": 16.465,
      "eval_steps_per_second": 8.304,
      "step": 20
    },
    {
      "epoch": 0.09149130832570906,
      "grad_norm": 0.9344391822814941,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.7451,
      "step": 25
    },
    {
      "epoch": 0.10978956999085086,
      "grad_norm": 1.2351694107055664,
      "learning_rate": 5e-05,
      "loss": 0.6899,
      "step": 30
    },
    {
      "epoch": 0.10978956999085086,
      "eval_loss": 0.6869314908981323,
      "eval_runtime": 7.1682,
      "eval_samples_per_second": 16.043,
      "eval_steps_per_second": 8.091,
      "step": 30
    },
    {
      "epoch": 0.1280878316559927,
      "grad_norm": 1.4144127368927002,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.6356,
      "step": 35
    },
    {
      "epoch": 0.1463860933211345,
      "grad_norm": 1.1237945556640625,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.631,
      "step": 40
    },
    {
      "epoch": 0.1463860933211345,
      "eval_loss": 0.6841559410095215,
      "eval_runtime": 7.1948,
      "eval_samples_per_second": 15.984,
      "eval_steps_per_second": 8.061,
      "step": 40
    },
    {
      "epoch": 0.16468435498627632,
      "grad_norm": 0.3947688043117523,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.6806,
      "step": 45
    },
    {
      "epoch": 0.18298261665141813,
      "grad_norm": 1.5522825717926025,
      "learning_rate": 0.0,
      "loss": 0.7376,
      "step": 50
    },
    {
      "epoch": 0.18298261665141813,
      "eval_loss": 0.6734411120414734,
      "eval_runtime": 7.0017,
      "eval_samples_per_second": 16.425,
      "eval_steps_per_second": 8.284,
      "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": 8239114616832000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}