Hugging Face's logo

tuanna08go
/
cb04c128-780d-46f1-9306-db98b4c250ac

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
cb04c128-780d-46f1-9306-db98b4c250ac
File size: 3,708 Bytes 
f12186f
 
 
8c41747
a449156
8c41747
f12186f
 
 
 
 
 
 
a449156
 
 
f12186f
a449156
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bab6bf1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ff57e6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8c41747
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f12186f
 
 
a449156
f12186f
 
a449156
f12186f
 
 
 
 
 
 
8c41747
f12186f
 
 
 
8c41747
f12186f
 
 
 
 
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": 0.10116337885685382,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0020232675771370764,
      "eval_loss": 1.7532789707183838,
      "eval_runtime": 22.6911,
      "eval_samples_per_second": 9.211,
      "eval_steps_per_second": 4.627,
      "step": 1
    },
    {
      "epoch": 0.010116337885685382,
      "grad_norm": 2.5933752059936523,
      "learning_rate": 5e-05,
      "loss": 1.5813,
      "step": 5
    },
    {
      "epoch": 0.020232675771370764,
      "grad_norm": 1.89445161819458,
      "learning_rate": 0.0001,
      "loss": 1.1502,
      "step": 10
    },
    {
      "epoch": 0.020232675771370764,
      "eval_loss": 0.7085664868354797,
      "eval_runtime": 23.9995,
      "eval_samples_per_second": 8.709,
      "eval_steps_per_second": 4.375,
      "step": 10
    },
    {
      "epoch": 0.030349013657056147,
      "grad_norm": 0.9080146551132202,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.5644,
      "step": 15
    },
    {
      "epoch": 0.04046535154274153,
      "grad_norm": 0.6127835512161255,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.3534,
      "step": 20
    },
    {
      "epoch": 0.04046535154274153,
      "eval_loss": 0.32802435755729675,
      "eval_runtime": 24.4681,
      "eval_samples_per_second": 8.542,
      "eval_steps_per_second": 4.291,
      "step": 20
    },
    {
      "epoch": 0.05058168942842691,
      "grad_norm": 0.552888035774231,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.2888,
      "step": 25
    },
    {
      "epoch": 0.06069802731411229,
      "grad_norm": 0.5705128908157349,
      "learning_rate": 5e-05,
      "loss": 0.2478,
      "step": 30
    },
    {
      "epoch": 0.06069802731411229,
      "eval_loss": 0.24784217774868011,
      "eval_runtime": 24.6368,
      "eval_samples_per_second": 8.483,
      "eval_steps_per_second": 4.262,
      "step": 30
    },
    {
      "epoch": 0.07081436519979767,
      "grad_norm": 0.3076908588409424,
      "learning_rate": 3.086582838174551e-05,
      "loss": 0.2376,
      "step": 35
    },
    {
      "epoch": 0.08093070308548306,
      "grad_norm": 0.36699753999710083,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 0.2272,
      "step": 40
    },
    {
      "epoch": 0.08093070308548306,
      "eval_loss": 0.233597069978714,
      "eval_runtime": 24.746,
      "eval_samples_per_second": 8.446,
      "eval_steps_per_second": 4.243,
      "step": 40
    },
    {
      "epoch": 0.09104704097116843,
      "grad_norm": 0.36897045373916626,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 0.2495,
      "step": 45
    },
    {
      "epoch": 0.10116337885685382,
      "grad_norm": 0.26886501908302307,
      "learning_rate": 0.0,
      "loss": 0.2033,
      "step": 50
    },
    {
      "epoch": 0.10116337885685382,
      "eval_loss": 0.23070070147514343,
      "eval_runtime": 24.7663,
      "eval_samples_per_second": 8.439,
      "eval_steps_per_second": 4.24,
      "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": 1.27706276560896e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}