Hugging Face's logo

MiguelCB
/
results

Generated from Trainer
Model card Files Community
MiguelCB commited on
Commit
31eba61
•
1 Parent(s): f3ba0f7

MiguelCB/trainer-testv1

Browse files
Files changed (7) hide show
  1. README.md +55 -0
  2. adapter_config.json +179 -0
  3. adapter_model.bin +3 -0
  4. special_tokens_map.json +24 -0
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +32 -0
  7. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ base_model: garage-bAInd/Stable-Platypus2-13B
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: results
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # results
15
+
16
+ This model is a fine-tuned version of [garage-bAInd/Stable-Platypus2-13B](https://huggingface.co/garage-bAInd/Stable-Platypus2-13B) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 0.0002
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - gradient_accumulation_steps: 32
40
+ - total_train_batch_size: 256
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: constant
43
+ - lr_scheduler_warmup_ratio: 0.03
44
+ - num_epochs: 1
45
+
46
+ ### Training results
47
+
48
+
49
+
50
+ ### Framework versions
51
+
52
+ - Transformers 4.33.0.dev0
53
+ - Pytorch 2.0.1+cu118
54
+ - Datasets 2.14.4
55
+ - Tokenizers 0.13.3
adapter_config.json ADDED
@@ -0,0 +1,179 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "garage-bAInd/Stable-Platypus2-13B",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "model.layers.0.self_attn.q_proj",
18
+ "model.layers.1.self_attn.q_proj",
19
+ "model.layers.2.self_attn.q_proj",
20
+ "model.layers.3.self_attn.q_proj",
21
+ "model.layers.4.self_attn.q_proj",
22
+ "model.layers.5.self_attn.q_proj",
23
+ "model.layers.6.self_attn.q_proj",
24
+ "model.layers.7.self_attn.q_proj",
25
+ "model.layers.8.self_attn.q_proj",
26
+ "model.layers.9.self_attn.q_proj",
27
+ "model.layers.10.self_attn.q_proj",
28
+ "model.layers.11.self_attn.q_proj",
29
+ "model.layers.12.self_attn.q_proj",
30
+ "model.layers.13.self_attn.q_proj",
31
+ "model.layers.14.self_attn.q_proj",
32
+ "model.layers.15.self_attn.q_proj",
33
+ "model.layers.16.self_attn.q_proj",
34
+ "model.layers.17.self_attn.q_proj",
35
+ "model.layers.18.self_attn.q_proj",
36
+ "model.layers.19.self_attn.q_proj",
37
+ "model.layers.20.self_attn.q_proj",
38
+ "model.layers.21.self_attn.q_proj",
39
+ "model.layers.22.self_attn.q_proj",
40
+ "model.layers.23.self_attn.q_proj",
41
+ "model.layers.24.self_attn.q_proj",
42
+ "model.layers.25.self_attn.q_proj",
43
+ "model.layers.26.self_attn.q_proj",
44
+ "model.layers.27.self_attn.q_proj",
45
+ "model.layers.28.self_attn.q_proj",
46
+ "model.layers.29.self_attn.q_proj",
47
+ "model.layers.30.self_attn.q_proj",
48
+ "model.layers.31.self_attn.q_proj",
49
+ "model.layers.32.self_attn.q_proj",
50
+ "model.layers.33.self_attn.q_proj",
51
+ "model.layers.34.self_attn.q_proj",
52
+ "model.layers.35.self_attn.q_proj",
53
+ "model.layers.36.self_attn.q_proj",
54
+ "model.layers.37.self_attn.q_proj",
55
+ "model.layers.38.self_attn.q_proj",
56
+ "model.layers.39.self_attn.q_proj",
57
+ "model.layers.0.self_attn.k_proj",
58
+ "model.layers.1.self_attn.k_proj",
59
+ "model.layers.2.self_attn.k_proj",
60
+ "model.layers.3.self_attn.k_proj",
61
+ "model.layers.4.self_attn.k_proj",
62
+ "model.layers.5.self_attn.k_proj",
63
+ "model.layers.6.self_attn.k_proj",
64
+ "model.layers.7.self_attn.k_proj",
65
+ "model.layers.8.self_attn.k_proj",
66
+ "model.layers.9.self_attn.k_proj",
67
+ "model.layers.10.self_attn.k_proj",
68
+ "model.layers.11.self_attn.k_proj",
69
+ "model.layers.12.self_attn.k_proj",
70
+ "model.layers.13.self_attn.k_proj",
71
+ "model.layers.14.self_attn.k_proj",
72
+ "model.layers.15.self_attn.k_proj",
73
+ "model.layers.16.self_attn.k_proj",
74
+ "model.layers.17.self_attn.k_proj",
75
+ "model.layers.18.self_attn.k_proj",
76
+ "model.layers.19.self_attn.k_proj",
77
+ "model.layers.20.self_attn.k_proj",
78
+ "model.layers.21.self_attn.k_proj",
79
+ "model.layers.22.self_attn.k_proj",
80
+ "model.layers.23.self_attn.k_proj",
81
+ "model.layers.24.self_attn.k_proj",
82
+ "model.layers.25.self_attn.k_proj",
83
+ "model.layers.26.self_attn.k_proj",
84
+ "model.layers.27.self_attn.k_proj",
85
+ "model.layers.28.self_attn.k_proj",
86
+ "model.layers.29.self_attn.k_proj",
87
+ "model.layers.30.self_attn.k_proj",
88
+ "model.layers.31.self_attn.k_proj",
89
+ "model.layers.32.self_attn.k_proj",
90
+ "model.layers.33.self_attn.k_proj",
91
+ "model.layers.34.self_attn.k_proj",
92
+ "model.layers.35.self_attn.k_proj",
93
+ "model.layers.36.self_attn.k_proj",
94
+ "model.layers.37.self_attn.k_proj",
95
+ "model.layers.38.self_attn.k_proj",
96
+ "model.layers.39.self_attn.k_proj",
97
+ "model.layers.0.self_attn.v_proj",
98
+ "model.layers.1.self_attn.v_proj",
99
+ "model.layers.2.self_attn.v_proj",
100
+ "model.layers.3.self_attn.v_proj",
101
+ "model.layers.4.self_attn.v_proj",
102
+ "model.layers.5.self_attn.v_proj",
103
+ "model.layers.6.self_attn.v_proj",
104
+ "model.layers.7.self_attn.v_proj",
105
+ "model.layers.8.self_attn.v_proj",
106
+ "model.layers.9.self_attn.v_proj",
107
+ "model.layers.10.self_attn.v_proj",
108
+ "model.layers.11.self_attn.v_proj",
109
+ "model.layers.12.self_attn.v_proj",
110
+ "model.layers.13.self_attn.v_proj",
111
+ "model.layers.14.self_attn.v_proj",
112
+ "model.layers.15.self_attn.v_proj",
113
+ "model.layers.16.self_attn.v_proj",
114
+ "model.layers.17.self_attn.v_proj",
115
+ "model.layers.18.self_attn.v_proj",
116
+ "model.layers.19.self_attn.v_proj",
117
+ "model.layers.20.self_attn.v_proj",
118
+ "model.layers.21.self_attn.v_proj",
119
+ "model.layers.22.self_attn.v_proj",
120
+ "model.layers.23.self_attn.v_proj",
121
+ "model.layers.24.self_attn.v_proj",
122
+ "model.layers.25.self_attn.v_proj",
123
+ "model.layers.26.self_attn.v_proj",
124
+ "model.layers.27.self_attn.v_proj",
125
+ "model.layers.28.self_attn.v_proj",
126
+ "model.layers.29.self_attn.v_proj",
127
+ "model.layers.30.self_attn.v_proj",
128
+ "model.layers.31.self_attn.v_proj",
129
+ "model.layers.32.self_attn.v_proj",
130
+ "model.layers.33.self_attn.v_proj",
131
+ "model.layers.34.self_attn.v_proj",
132
+ "model.layers.35.self_attn.v_proj",
133
+ "model.layers.36.self_attn.v_proj",
134
+ "model.layers.37.self_attn.v_proj",
135
+ "model.layers.38.self_attn.v_proj",
136
+ "model.layers.39.self_attn.v_proj",
137
+ "model.layers.0.self_attn.o_proj",
138
+ "model.layers.1.self_attn.o_proj",
139
+ "model.layers.2.self_attn.o_proj",
140
+ "model.layers.3.self_attn.o_proj",
141
+ "model.layers.4.self_attn.o_proj",
142
+ "model.layers.5.self_attn.o_proj",
143
+ "model.layers.6.self_attn.o_proj",
144
+ "model.layers.7.self_attn.o_proj",
145
+ "model.layers.8.self_attn.o_proj",
146
+ "model.layers.9.self_attn.o_proj",
147
+ "model.layers.10.self_attn.o_proj",
148
+ "model.layers.11.self_attn.o_proj",
149
+ "model.layers.12.self_attn.o_proj",
150
+ "model.layers.13.self_attn.o_proj",
151
+ "model.layers.14.self_attn.o_proj",
152
+ "model.layers.15.self_attn.o_proj",
153
+ "model.layers.16.self_attn.o_proj",
154
+ "model.layers.17.self_attn.o_proj",
155
+ "model.layers.18.self_attn.o_proj",
156
+ "model.layers.19.self_attn.o_proj",
157
+ "model.layers.20.self_attn.o_proj",
158
+ "model.layers.21.self_attn.o_proj",
159
+ "model.layers.22.self_attn.o_proj",
160
+ "model.layers.23.self_attn.o_proj",
161
+ "model.layers.24.self_attn.o_proj",
162
+ "model.layers.25.self_attn.o_proj",
163
+ "model.layers.26.self_attn.o_proj",
164
+ "model.layers.27.self_attn.o_proj",
165
+ "model.layers.28.self_attn.o_proj",
166
+ "model.layers.29.self_attn.o_proj",
167
+ "model.layers.30.self_attn.o_proj",
168
+ "model.layers.31.self_attn.o_proj",
169
+ "model.layers.32.self_attn.o_proj",
170
+ "model.layers.33.self_attn.o_proj",
171
+ "model.layers.34.self_attn.o_proj",
172
+ "model.layers.35.self_attn.o_proj",
173
+ "model.layers.36.self_attn.o_proj",
174
+ "model.layers.37.self_attn.o_proj",
175
+ "model.layers.38.self_attn.o_proj",
176
+ "model.layers.39.self_attn.o_proj"
177
+ ],
178
+ "task_type": "CAUSAL_LM"
179
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9cea5f7b235fcd9b0697b2d71cee7feeac98658840c523e7dfd2c7901afa8d4
3
+ size 419546189
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "model_max_length": 4096,
20
+ "pad_token": null,
21
+ "sp_model_kwargs": {},
22
+ "tokenizer_class": "LlamaTokenizer",
23
+ "unk_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ "use_default_system_prompt": true
32
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e04c1665de6e3882ea9d5858c386cb1f5c77c7b0113fcfa4a4ab3255e8abc43
3
+ size 4027