Hugging Face's logo

chauhoang
/
103a311e-9739-47b3-98a2-b2d257c07424

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
103a311e-9739-47b3-98a2-b2d257c07424
File size: 3,743 Bytes 
9a8cba4
 
 
93a9396
fa75a9e
93a9396
9a8cba4
 
 
 
 
 
 
fa75a9e
 
 
9a8cba4
fa75a9e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dc66d79
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8dd249d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
93a9396
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9a8cba4
 
 
fa75a9e
9a8cba4
 
fa75a9e
9a8cba4
 
 
 
 
 
 
93a9396
9a8cba4
 
 
 
93a9396
9a8cba4
 
 
 
 
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": 0.0012362314719808138,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.4724629439616273e-05,
      "eval_loss": 7.831309795379639,
      "eval_runtime": 1144.6074,
      "eval_samples_per_second": 14.878,
      "eval_steps_per_second": 7.439,
      "step": 1
    },
    {
      "epoch": 0.00012362314719808137,
      "grad_norm": 6.500582695007324,
      "learning_rate": 5e-05,
      "loss": 8.1156,
      "step": 5
    },
    {
      "epoch": 0.00024724629439616273,
      "grad_norm": 6.574873924255371,
      "learning_rate": 0.0001,
      "loss": 6.4498,
      "step": 10
    },
    {
      "epoch": 0.00024724629439616273,
      "eval_loss": 5.1529107093811035,
      "eval_runtime": 1151.9378,
      "eval_samples_per_second": 14.784,
      "eval_steps_per_second": 7.392,
      "step": 10
    },
    {
      "epoch": 0.0003708694415942441,
      "grad_norm": 8.13021469116211,
      "learning_rate": 9.619397662556435e-05,
      "loss": 3.7931,
      "step": 15
    },
    {
      "epoch": 0.0004944925887923255,
      "grad_norm": 6.818072319030762,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.3798,
      "step": 20
    },
    {
      "epoch": 0.0004944925887923255,
      "eval_loss": 0.8881871104240417,
      "eval_runtime": 1151.8026,
      "eval_samples_per_second": 14.786,
      "eval_steps_per_second": 7.393,
      "step": 20
    },
    {
      "epoch": 0.0006181157359904069,
      "grad_norm": 4.882168292999268,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.9035,
      "step": 25
    },
    {
      "epoch": 0.0007417388831884882,
      "grad_norm": 2.6614863872528076,
      "learning_rate": 5e-05,
      "loss": 0.3125,
      "step": 30
    },
    {
      "epoch": 0.0007417388831884882,
      "eval_loss": 0.48977532982826233,
      "eval_runtime": 1152.265,
      "eval_samples_per_second": 14.78,
      "eval_steps_per_second": 7.39,
      "step": 30
    },
    {
      "epoch": 0.0008653620303865696,
      "grad_norm": 10.399094581604004,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.5635,
      "step": 35
    },
    {
      "epoch": 0.000988985177584651,
      "grad_norm": 3.535245418548584,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.1906,
      "step": 40
    },
    {
      "epoch": 0.000988985177584651,
      "eval_loss": 0.3746371567249298,
      "eval_runtime": 1149.4454,
      "eval_samples_per_second": 14.816,
      "eval_steps_per_second": 7.408,
      "step": 40
    },
    {
      "epoch": 0.0011126083247827323,
      "grad_norm": 9.233739852905273,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.5945,
      "step": 45
    },
    {
      "epoch": 0.0012362314719808138,
      "grad_norm": 8.951319694519043,
      "learning_rate": 0.0,
      "loss": 0.4922,
      "step": 50
    },
    {
      "epoch": 0.0012362314719808138,
      "eval_loss": 0.34176287055015564,
      "eval_runtime": 1153.5101,
      "eval_samples_per_second": 14.764,
      "eval_steps_per_second": 7.382,
      "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": 9247821240729600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}