Hugging Face's logo

tuanna08go
/
4ee3ace5-396b-4af9-8ea5-56788c1d2866

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
4ee3ace5-396b-4af9-8ea5-56788c1d2866
File size: 3,453 Bytes 
2018f17
 
 
01f605b
94a8a7d
01f605b
2018f17
 
 
 
 
 
 
94a8a7d
 
 
2018f17
94a8a7d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fe998d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a197a1a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
01f605b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2018f17
 
 
94a8a7d
2018f17
 
94a8a7d
2018f17
 
 
 
 
 
 
01f605b
2018f17
 
 
 
01f605b
2018f17
 
 
 
 
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": 0.01697792869269949,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00033955857385398983,
      "eval_loss": NaN,
      "eval_runtime": 85.5346,
      "eval_samples_per_second": 14.497,
      "eval_steps_per_second": 7.249,
      "step": 1
    },
    {
      "epoch": 0.001697792869269949,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.003395585738539898,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.003395585738539898,
      "eval_loss": NaN,
      "eval_runtime": 87.9719,
      "eval_samples_per_second": 14.095,
      "eval_steps_per_second": 7.048,
      "step": 10
    },
    {
      "epoch": 0.0050933786078098476,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.006791171477079796,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.006791171477079796,
      "eval_loss": NaN,
      "eval_runtime": 89.1861,
      "eval_samples_per_second": 13.904,
      "eval_steps_per_second": 6.952,
      "step": 20
    },
    {
      "epoch": 0.008488964346349746,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.010186757215619695,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.010186757215619695,
      "eval_loss": NaN,
      "eval_runtime": 87.5572,
      "eval_samples_per_second": 14.162,
      "eval_steps_per_second": 7.081,
      "step": 30
    },
    {
      "epoch": 0.011884550084889643,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.013582342954159592,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.013582342954159592,
      "eval_loss": NaN,
      "eval_runtime": 91.4195,
      "eval_samples_per_second": 13.564,
      "eval_steps_per_second": 6.782,
      "step": 40
    },
    {
      "epoch": 0.015280135823429542,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.0,
      "step": 45
    },
    {
      "epoch": 0.01697792869269949,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.01697792869269949,
      "eval_loss": NaN,
      "eval_runtime": 94.5532,
      "eval_samples_per_second": 13.114,
      "eval_steps_per_second": 6.557,
      "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": 1278959891251200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}