Hugging Face's logo

chauhoang
/
d0839f9f-293b-41b8-9a7f-f010911cb3ce

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
d0839f9f-293b-41b8-9a7f-f010911cb3ce
File size: 3,446 Bytes 
cc32617
 
 
7642f39
313663d
7642f39
cc32617
 
 
 
 
 
 
313663d
 
 
cc32617
313663d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c541389
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eddfc34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7642f39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cc32617
 
 
313663d
cc32617
 
313663d
cc32617
 
 
 
 
 
 
7642f39
cc32617
 
 
 
7642f39
cc32617
 
 
 
 
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": 0.06191950464396285,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001238390092879257,
      "eval_loss": NaN,
      "eval_runtime": 24.0496,
      "eval_samples_per_second": 14.137,
      "eval_steps_per_second": 7.069,
      "step": 1
    },
    {
      "epoch": 0.006191950464396285,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.01238390092879257,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.01238390092879257,
      "eval_loss": NaN,
      "eval_runtime": 22.9903,
      "eval_samples_per_second": 14.789,
      "eval_steps_per_second": 7.394,
      "step": 10
    },
    {
      "epoch": 0.018575851393188854,
      "grad_norm": NaN,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.02476780185758514,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.4791,
      "step": 20
    },
    {
      "epoch": 0.02476780185758514,
      "eval_loss": NaN,
      "eval_runtime": 23.0187,
      "eval_samples_per_second": 14.771,
      "eval_steps_per_second": 7.385,
      "step": 20
    },
    {
      "epoch": 0.030959752321981424,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 25
    },
    {
      "epoch": 0.03715170278637771,
      "grad_norm": NaN,
      "learning_rate": 5e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.03715170278637771,
      "eval_loss": NaN,
      "eval_runtime": 23.1016,
      "eval_samples_per_second": 14.718,
      "eval_steps_per_second": 7.359,
      "step": 30
    },
    {
      "epoch": 0.043343653250773995,
      "grad_norm": NaN,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.0,
      "step": 35
    },
    {
      "epoch": 0.04953560371517028,
      "grad_norm": NaN,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.04953560371517028,
      "eval_loss": NaN,
      "eval_runtime": 23.0164,
      "eval_samples_per_second": 14.772,
      "eval_steps_per_second": 7.386,
      "step": 40
    },
    {
      "epoch": 0.05572755417956656,
      "grad_norm": NaN,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.7407,
      "step": 45
    },
    {
      "epoch": 0.06191950464396285,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.06191950464396285,
      "eval_loss": NaN,
      "eval_runtime": 23.0344,
      "eval_samples_per_second": 14.761,
      "eval_steps_per_second": 7.38,
      "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": 9001625343492096.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}