ManthanKulakarni
commited on
Commit
•
7a83895
1
Parent(s):
b2e5bb0
ManthanKulakarni/falcon-rw-1_sql_v1
Browse files- README.md +7 -7
- config.json +25 -22
- generation_config.json +3 -2
- model.safetensors +2 -2
- runs/Dec22_08-52-16_cac675d344ec/events.out.tfevents.1703235153.cac675d344ec.42.0 +3 -0
- runs/Dec22_09-07-27_cac675d344ec/events.out.tfevents.1703236051.cac675d344ec.239.0 +3 -0
- special_tokens_map.json +3 -21
- tokenizer.json +2 -353
- tokenizer_config.json +2 -306
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
-
license:
|
3 |
-
base_model:
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
@@ -13,7 +13,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
13 |
|
14 |
# working
|
15 |
|
16 |
-
This model is a fine-tuned version of [
|
17 |
|
18 |
## Model description
|
19 |
|
@@ -33,15 +33,15 @@ More information needed
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 0.0002
|
36 |
-
- train_batch_size:
|
37 |
-
- eval_batch_size:
|
38 |
- seed: 42
|
39 |
- gradient_accumulation_steps: 4
|
40 |
-
- total_train_batch_size:
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: cosine
|
43 |
- lr_scheduler_warmup_ratio: 0.05
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
|
|
1 |
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: tiiuae/falcon-rw-1b
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
model-index:
|
|
|
13 |
|
14 |
# working
|
15 |
|
16 |
+
This model is a fine-tuned version of [tiiuae/falcon-rw-1b](https://huggingface.co/tiiuae/falcon-rw-1b) on the None dataset.
|
17 |
|
18 |
## Model description
|
19 |
|
|
|
33 |
|
34 |
The following hyperparameters were used during training:
|
35 |
- learning_rate: 0.0002
|
36 |
+
- train_batch_size: 30
|
37 |
+
- eval_batch_size: 30
|
38 |
- seed: 42
|
39 |
- gradient_accumulation_steps: 4
|
40 |
+
- total_train_batch_size: 120
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: cosine
|
43 |
- lr_scheduler_warmup_ratio: 0.05
|
44 |
+
- num_epochs: 1
|
45 |
|
46 |
### Training results
|
47 |
|
config.json
CHANGED
@@ -1,32 +1,35 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"
|
|
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"
|
8 |
"auto_map": {
|
9 |
-
"AutoConfig": "
|
10 |
-
"
|
|
|
|
|
|
|
|
|
11 |
},
|
12 |
-
"
|
13 |
-
"
|
14 |
-
"
|
15 |
-
"
|
|
|
16 |
"initializer_range": 0.02,
|
17 |
"layer_norm_epsilon": 1e-05,
|
18 |
-
"model_type": "
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"
|
26 |
-
"rotary_dim": 32,
|
27 |
-
"tie_word_embeddings": false,
|
28 |
-
"torch_dtype": "float16",
|
29 |
"transformers_version": "4.36.0",
|
30 |
"use_cache": false,
|
31 |
-
"vocab_size":
|
32 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "tiiuae/falcon-rw-1b",
|
3 |
+
"alibi": true,
|
4 |
+
"apply_residual_connection_post_layernorm": false,
|
5 |
"architectures": [
|
6 |
+
"FalconForCausalLM"
|
7 |
],
|
8 |
+
"attention_dropout": 0.0,
|
9 |
"auto_map": {
|
10 |
+
"AutoConfig": "tiiuae/falcon-rw-1b--configuration_falcon.FalconConfig",
|
11 |
+
"AutoModel": "tiiuae/falcon-rw-1b--modeling_falcon.FalconModel",
|
12 |
+
"AutoModelForCausalLM": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForCausalLM",
|
13 |
+
"AutoModelForQuestionAnswering": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForQuestionAnswering",
|
14 |
+
"AutoModelForSequenceClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForSequenceClassification",
|
15 |
+
"AutoModelForTokenClassification": "tiiuae/falcon-rw-1b--modeling_falcon.FalconForTokenClassification"
|
16 |
},
|
17 |
+
"bias": true,
|
18 |
+
"bos_token_id": 1,
|
19 |
+
"eos_token_id": 2,
|
20 |
+
"hidden_dropout": 0.0,
|
21 |
+
"hidden_size": 2048,
|
22 |
"initializer_range": 0.02,
|
23 |
"layer_norm_epsilon": 1e-05,
|
24 |
+
"model_type": "falcon",
|
25 |
+
"multi_query": false,
|
26 |
+
"new_decoder_architecture": false,
|
27 |
+
"num_attention_heads": 32,
|
28 |
+
"num_hidden_layers": 24,
|
29 |
+
"num_kv_heads": 32,
|
30 |
+
"parallel_attn": false,
|
31 |
+
"torch_dtype": "bfloat16",
|
|
|
|
|
|
|
32 |
"transformers_version": "4.36.0",
|
33 |
"use_cache": false,
|
34 |
+
"vocab_size": 50304
|
35 |
}
|
generation_config.json
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
-
"
|
4 |
-
"
|
|
|
5 |
}
|
|
|
1 |
{
|
2 |
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.36.0"
|
6 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7699a3ed8683fef29c48b38d918faf22191d08a26cea3b9f890322eabbb56ef4
|
3 |
+
size 2623284688
|
runs/Dec22_08-52-16_cac675d344ec/events.out.tfevents.1703235153.cac675d344ec.42.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b8be1bb1ccd862d425f6c44b1e0b17ac8dafe29935e53af648ee2d5c849f4c9
|
3 |
+
size 4945
|
runs/Dec22_09-07-27_cac675d344ec/events.out.tfevents.1703236051.cac675d344ec.239.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e147c38dccf7e85b52522e8724c150cac1e0a1cbc228572b4b0970cab18e181
|
3 |
+
size 5755
|
special_tokens_map.json
CHANGED
@@ -1,24 +1,6 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|endoftext|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
},
|
16 |
"pad_token": "<|endoftext|>",
|
17 |
-
"unk_token":
|
18 |
-
"content": "<|endoftext|>",
|
19 |
-
"lstrip": false,
|
20 |
-
"normalized": false,
|
21 |
-
"rstrip": false,
|
22 |
-
"single_word": false
|
23 |
-
}
|
24 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
6 |
}
|
tokenizer.json
CHANGED
@@ -2,20 +2,11 @@
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
-
"max_length":
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
-
"padding":
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 512
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 50256,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "<|endoftext|>"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 50256,
|
@@ -25,348 +16,6 @@
|
|
25 |
"rstrip": false,
|
26 |
"normalized": false,
|
27 |
"special": true
|
28 |
-
},
|
29 |
-
{
|
30 |
-
"id": 50257,
|
31 |
-
"content": " ",
|
32 |
-
"single_word": false,
|
33 |
-
"lstrip": false,
|
34 |
-
"rstrip": false,
|
35 |
-
"normalized": true,
|
36 |
-
"special": false
|
37 |
-
},
|
38 |
-
{
|
39 |
-
"id": 50258,
|
40 |
-
"content": " ",
|
41 |
-
"single_word": false,
|
42 |
-
"lstrip": false,
|
43 |
-
"rstrip": false,
|
44 |
-
"normalized": true,
|
45 |
-
"special": false
|
46 |
-
},
|
47 |
-
{
|
48 |
-
"id": 50259,
|
49 |
-
"content": " ",
|
50 |
-
"single_word": false,
|
51 |
-
"lstrip": false,
|
52 |
-
"rstrip": false,
|
53 |
-
"normalized": true,
|
54 |
-
"special": false
|
55 |
-
},
|
56 |
-
{
|
57 |
-
"id": 50260,
|
58 |
-
"content": " ",
|
59 |
-
"single_word": false,
|
60 |
-
"lstrip": false,
|
61 |
-
"rstrip": false,
|
62 |
-
"normalized": true,
|
63 |
-
"special": false
|
64 |
-
},
|
65 |
-
{
|
66 |
-
"id": 50261,
|
67 |
-
"content": " ",
|
68 |
-
"single_word": false,
|
69 |
-
"lstrip": false,
|
70 |
-
"rstrip": false,
|
71 |
-
"normalized": true,
|
72 |
-
"special": false
|
73 |
-
},
|
74 |
-
{
|
75 |
-
"id": 50262,
|
76 |
-
"content": " ",
|
77 |
-
"single_word": false,
|
78 |
-
"lstrip": false,
|
79 |
-
"rstrip": false,
|
80 |
-
"normalized": true,
|
81 |
-
"special": false
|
82 |
-
},
|
83 |
-
{
|
84 |
-
"id": 50263,
|
85 |
-
"content": " ",
|
86 |
-
"single_word": false,
|
87 |
-
"lstrip": false,
|
88 |
-
"rstrip": false,
|
89 |
-
"normalized": true,
|
90 |
-
"special": false
|
91 |
-
},
|
92 |
-
{
|
93 |
-
"id": 50264,
|
94 |
-
"content": " ",
|
95 |
-
"single_word": false,
|
96 |
-
"lstrip": false,
|
97 |
-
"rstrip": false,
|
98 |
-
"normalized": true,
|
99 |
-
"special": false
|
100 |
-
},
|
101 |
-
{
|
102 |
-
"id": 50265,
|
103 |
-
"content": " ",
|
104 |
-
"single_word": false,
|
105 |
-
"lstrip": false,
|
106 |
-
"rstrip": false,
|
107 |
-
"normalized": true,
|
108 |
-
"special": false
|
109 |
-
},
|
110 |
-
{
|
111 |
-
"id": 50266,
|
112 |
-
"content": " ",
|
113 |
-
"single_word": false,
|
114 |
-
"lstrip": false,
|
115 |
-
"rstrip": false,
|
116 |
-
"normalized": true,
|
117 |
-
"special": false
|
118 |
-
},
|
119 |
-
{
|
120 |
-
"id": 50267,
|
121 |
-
"content": " ",
|
122 |
-
"single_word": false,
|
123 |
-
"lstrip": false,
|
124 |
-
"rstrip": false,
|
125 |
-
"normalized": true,
|
126 |
-
"special": false
|
127 |
-
},
|
128 |
-
{
|
129 |
-
"id": 50268,
|
130 |
-
"content": " ",
|
131 |
-
"single_word": false,
|
132 |
-
"lstrip": false,
|
133 |
-
"rstrip": false,
|
134 |
-
"normalized": true,
|
135 |
-
"special": false
|
136 |
-
},
|
137 |
-
{
|
138 |
-
"id": 50269,
|
139 |
-
"content": " ",
|
140 |
-
"single_word": false,
|
141 |
-
"lstrip": false,
|
142 |
-
"rstrip": false,
|
143 |
-
"normalized": true,
|
144 |
-
"special": false
|
145 |
-
},
|
146 |
-
{
|
147 |
-
"id": 50270,
|
148 |
-
"content": " ",
|
149 |
-
"single_word": false,
|
150 |
-
"lstrip": false,
|
151 |
-
"rstrip": false,
|
152 |
-
"normalized": true,
|
153 |
-
"special": false
|
154 |
-
},
|
155 |
-
{
|
156 |
-
"id": 50271,
|
157 |
-
"content": " ",
|
158 |
-
"single_word": false,
|
159 |
-
"lstrip": false,
|
160 |
-
"rstrip": false,
|
161 |
-
"normalized": true,
|
162 |
-
"special": false
|
163 |
-
},
|
164 |
-
{
|
165 |
-
"id": 50272,
|
166 |
-
"content": " ",
|
167 |
-
"single_word": false,
|
168 |
-
"lstrip": false,
|
169 |
-
"rstrip": false,
|
170 |
-
"normalized": true,
|
171 |
-
"special": false
|
172 |
-
},
|
173 |
-
{
|
174 |
-
"id": 50273,
|
175 |
-
"content": " ",
|
176 |
-
"single_word": false,
|
177 |
-
"lstrip": false,
|
178 |
-
"rstrip": false,
|
179 |
-
"normalized": true,
|
180 |
-
"special": false
|
181 |
-
},
|
182 |
-
{
|
183 |
-
"id": 50274,
|
184 |
-
"content": " ",
|
185 |
-
"single_word": false,
|
186 |
-
"lstrip": false,
|
187 |
-
"rstrip": false,
|
188 |
-
"normalized": true,
|
189 |
-
"special": false
|
190 |
-
},
|
191 |
-
{
|
192 |
-
"id": 50275,
|
193 |
-
"content": " ",
|
194 |
-
"single_word": false,
|
195 |
-
"lstrip": false,
|
196 |
-
"rstrip": false,
|
197 |
-
"normalized": true,
|
198 |
-
"special": false
|
199 |
-
},
|
200 |
-
{
|
201 |
-
"id": 50276,
|
202 |
-
"content": " ",
|
203 |
-
"single_word": false,
|
204 |
-
"lstrip": false,
|
205 |
-
"rstrip": false,
|
206 |
-
"normalized": true,
|
207 |
-
"special": false
|
208 |
-
},
|
209 |
-
{
|
210 |
-
"id": 50277,
|
211 |
-
"content": " ",
|
212 |
-
"single_word": false,
|
213 |
-
"lstrip": false,
|
214 |
-
"rstrip": false,
|
215 |
-
"normalized": true,
|
216 |
-
"special": false
|
217 |
-
},
|
218 |
-
{
|
219 |
-
"id": 50278,
|
220 |
-
"content": " ",
|
221 |
-
"single_word": false,
|
222 |
-
"lstrip": false,
|
223 |
-
"rstrip": false,
|
224 |
-
"normalized": true,
|
225 |
-
"special": false
|
226 |
-
},
|
227 |
-
{
|
228 |
-
"id": 50279,
|
229 |
-
"content": " ",
|
230 |
-
"single_word": false,
|
231 |
-
"lstrip": false,
|
232 |
-
"rstrip": false,
|
233 |
-
"normalized": true,
|
234 |
-
"special": false
|
235 |
-
},
|
236 |
-
{
|
237 |
-
"id": 50280,
|
238 |
-
"content": " ",
|
239 |
-
"single_word": false,
|
240 |
-
"lstrip": false,
|
241 |
-
"rstrip": false,
|
242 |
-
"normalized": true,
|
243 |
-
"special": false
|
244 |
-
},
|
245 |
-
{
|
246 |
-
"id": 50281,
|
247 |
-
"content": " ",
|
248 |
-
"single_word": false,
|
249 |
-
"lstrip": false,
|
250 |
-
"rstrip": false,
|
251 |
-
"normalized": true,
|
252 |
-
"special": false
|
253 |
-
},
|
254 |
-
{
|
255 |
-
"id": 50282,
|
256 |
-
"content": " ",
|
257 |
-
"single_word": false,
|
258 |
-
"lstrip": false,
|
259 |
-
"rstrip": false,
|
260 |
-
"normalized": true,
|
261 |
-
"special": false
|
262 |
-
},
|
263 |
-
{
|
264 |
-
"id": 50283,
|
265 |
-
"content": " ",
|
266 |
-
"single_word": false,
|
267 |
-
"lstrip": false,
|
268 |
-
"rstrip": false,
|
269 |
-
"normalized": true,
|
270 |
-
"special": false
|
271 |
-
},
|
272 |
-
{
|
273 |
-
"id": 50284,
|
274 |
-
"content": " ",
|
275 |
-
"single_word": false,
|
276 |
-
"lstrip": false,
|
277 |
-
"rstrip": false,
|
278 |
-
"normalized": true,
|
279 |
-
"special": false
|
280 |
-
},
|
281 |
-
{
|
282 |
-
"id": 50285,
|
283 |
-
"content": " ",
|
284 |
-
"single_word": false,
|
285 |
-
"lstrip": false,
|
286 |
-
"rstrip": false,
|
287 |
-
"normalized": true,
|
288 |
-
"special": false
|
289 |
-
},
|
290 |
-
{
|
291 |
-
"id": 50286,
|
292 |
-
"content": " ",
|
293 |
-
"single_word": false,
|
294 |
-
"lstrip": false,
|
295 |
-
"rstrip": false,
|
296 |
-
"normalized": true,
|
297 |
-
"special": false
|
298 |
-
},
|
299 |
-
{
|
300 |
-
"id": 50287,
|
301 |
-
"content": "\t\t\t\t\t\t\t\t\t",
|
302 |
-
"single_word": false,
|
303 |
-
"lstrip": false,
|
304 |
-
"rstrip": false,
|
305 |
-
"normalized": true,
|
306 |
-
"special": false
|
307 |
-
},
|
308 |
-
{
|
309 |
-
"id": 50288,
|
310 |
-
"content": "\t\t\t\t\t\t\t\t",
|
311 |
-
"single_word": false,
|
312 |
-
"lstrip": false,
|
313 |
-
"rstrip": false,
|
314 |
-
"normalized": true,
|
315 |
-
"special": false
|
316 |
-
},
|
317 |
-
{
|
318 |
-
"id": 50289,
|
319 |
-
"content": "\t\t\t\t\t\t\t",
|
320 |
-
"single_word": false,
|
321 |
-
"lstrip": false,
|
322 |
-
"rstrip": false,
|
323 |
-
"normalized": true,
|
324 |
-
"special": false
|
325 |
-
},
|
326 |
-
{
|
327 |
-
"id": 50290,
|
328 |
-
"content": "\t\t\t\t\t\t",
|
329 |
-
"single_word": false,
|
330 |
-
"lstrip": false,
|
331 |
-
"rstrip": false,
|
332 |
-
"normalized": true,
|
333 |
-
"special": false
|
334 |
-
},
|
335 |
-
{
|
336 |
-
"id": 50291,
|
337 |
-
"content": "\t\t\t\t\t",
|
338 |
-
"single_word": false,
|
339 |
-
"lstrip": false,
|
340 |
-
"rstrip": false,
|
341 |
-
"normalized": true,
|
342 |
-
"special": false
|
343 |
-
},
|
344 |
-
{
|
345 |
-
"id": 50292,
|
346 |
-
"content": "\t\t\t\t",
|
347 |
-
"single_word": false,
|
348 |
-
"lstrip": false,
|
349 |
-
"rstrip": false,
|
350 |
-
"normalized": true,
|
351 |
-
"special": false
|
352 |
-
},
|
353 |
-
{
|
354 |
-
"id": 50293,
|
355 |
-
"content": "\t\t\t",
|
356 |
-
"single_word": false,
|
357 |
-
"lstrip": false,
|
358 |
-
"rstrip": false,
|
359 |
-
"normalized": true,
|
360 |
-
"special": false
|
361 |
-
},
|
362 |
-
{
|
363 |
-
"id": 50294,
|
364 |
-
"content": "\t\t",
|
365 |
-
"single_word": false,
|
366 |
-
"lstrip": false,
|
367 |
-
"rstrip": false,
|
368 |
-
"normalized": true,
|
369 |
-
"special": false
|
370 |
}
|
371 |
],
|
372 |
"normalizer": null,
|
|
|
2 |
"version": "1.0",
|
3 |
"truncation": {
|
4 |
"direction": "Right",
|
5 |
+
"max_length": 256,
|
6 |
"strategy": "LongestFirst",
|
7 |
"stride": 0
|
8 |
},
|
9 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"added_tokens": [
|
11 |
{
|
12 |
"id": 50256,
|
|
|
16 |
"rstrip": false,
|
17 |
"normalized": false,
|
18 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
}
|
20 |
],
|
21 |
"normalizer": null,
|
tokenizer_config.json
CHANGED
@@ -8,318 +8,14 @@
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
11 |
-
},
|
12 |
-
"50257": {
|
13 |
-
"content": " ",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": true,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false,
|
18 |
-
"special": false
|
19 |
-
},
|
20 |
-
"50258": {
|
21 |
-
"content": " ",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": true,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false,
|
26 |
-
"special": false
|
27 |
-
},
|
28 |
-
"50259": {
|
29 |
-
"content": " ",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": true,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false,
|
34 |
-
"special": false
|
35 |
-
},
|
36 |
-
"50260": {
|
37 |
-
"content": " ",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": true,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false,
|
42 |
-
"special": false
|
43 |
-
},
|
44 |
-
"50261": {
|
45 |
-
"content": " ",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": true,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false,
|
50 |
-
"special": false
|
51 |
-
},
|
52 |
-
"50262": {
|
53 |
-
"content": " ",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": true,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false,
|
58 |
-
"special": false
|
59 |
-
},
|
60 |
-
"50263": {
|
61 |
-
"content": " ",
|
62 |
-
"lstrip": false,
|
63 |
-
"normalized": true,
|
64 |
-
"rstrip": false,
|
65 |
-
"single_word": false,
|
66 |
-
"special": false
|
67 |
-
},
|
68 |
-
"50264": {
|
69 |
-
"content": " ",
|
70 |
-
"lstrip": false,
|
71 |
-
"normalized": true,
|
72 |
-
"rstrip": false,
|
73 |
-
"single_word": false,
|
74 |
-
"special": false
|
75 |
-
},
|
76 |
-
"50265": {
|
77 |
-
"content": " ",
|
78 |
-
"lstrip": false,
|
79 |
-
"normalized": true,
|
80 |
-
"rstrip": false,
|
81 |
-
"single_word": false,
|
82 |
-
"special": false
|
83 |
-
},
|
84 |
-
"50266": {
|
85 |
-
"content": " ",
|
86 |
-
"lstrip": false,
|
87 |
-
"normalized": true,
|
88 |
-
"rstrip": false,
|
89 |
-
"single_word": false,
|
90 |
-
"special": false
|
91 |
-
},
|
92 |
-
"50267": {
|
93 |
-
"content": " ",
|
94 |
-
"lstrip": false,
|
95 |
-
"normalized": true,
|
96 |
-
"rstrip": false,
|
97 |
-
"single_word": false,
|
98 |
-
"special": false
|
99 |
-
},
|
100 |
-
"50268": {
|
101 |
-
"content": " ",
|
102 |
-
"lstrip": false,
|
103 |
-
"normalized": true,
|
104 |
-
"rstrip": false,
|
105 |
-
"single_word": false,
|
106 |
-
"special": false
|
107 |
-
},
|
108 |
-
"50269": {
|
109 |
-
"content": " ",
|
110 |
-
"lstrip": false,
|
111 |
-
"normalized": true,
|
112 |
-
"rstrip": false,
|
113 |
-
"single_word": false,
|
114 |
-
"special": false
|
115 |
-
},
|
116 |
-
"50270": {
|
117 |
-
"content": " ",
|
118 |
-
"lstrip": false,
|
119 |
-
"normalized": true,
|
120 |
-
"rstrip": false,
|
121 |
-
"single_word": false,
|
122 |
-
"special": false
|
123 |
-
},
|
124 |
-
"50271": {
|
125 |
-
"content": " ",
|
126 |
-
"lstrip": false,
|
127 |
-
"normalized": true,
|
128 |
-
"rstrip": false,
|
129 |
-
"single_word": false,
|
130 |
-
"special": false
|
131 |
-
},
|
132 |
-
"50272": {
|
133 |
-
"content": " ",
|
134 |
-
"lstrip": false,
|
135 |
-
"normalized": true,
|
136 |
-
"rstrip": false,
|
137 |
-
"single_word": false,
|
138 |
-
"special": false
|
139 |
-
},
|
140 |
-
"50273": {
|
141 |
-
"content": " ",
|
142 |
-
"lstrip": false,
|
143 |
-
"normalized": true,
|
144 |
-
"rstrip": false,
|
145 |
-
"single_word": false,
|
146 |
-
"special": false
|
147 |
-
},
|
148 |
-
"50274": {
|
149 |
-
"content": " ",
|
150 |
-
"lstrip": false,
|
151 |
-
"normalized": true,
|
152 |
-
"rstrip": false,
|
153 |
-
"single_word": false,
|
154 |
-
"special": false
|
155 |
-
},
|
156 |
-
"50275": {
|
157 |
-
"content": " ",
|
158 |
-
"lstrip": false,
|
159 |
-
"normalized": true,
|
160 |
-
"rstrip": false,
|
161 |
-
"single_word": false,
|
162 |
-
"special": false
|
163 |
-
},
|
164 |
-
"50276": {
|
165 |
-
"content": " ",
|
166 |
-
"lstrip": false,
|
167 |
-
"normalized": true,
|
168 |
-
"rstrip": false,
|
169 |
-
"single_word": false,
|
170 |
-
"special": false
|
171 |
-
},
|
172 |
-
"50277": {
|
173 |
-
"content": " ",
|
174 |
-
"lstrip": false,
|
175 |
-
"normalized": true,
|
176 |
-
"rstrip": false,
|
177 |
-
"single_word": false,
|
178 |
-
"special": false
|
179 |
-
},
|
180 |
-
"50278": {
|
181 |
-
"content": " ",
|
182 |
-
"lstrip": false,
|
183 |
-
"normalized": true,
|
184 |
-
"rstrip": false,
|
185 |
-
"single_word": false,
|
186 |
-
"special": false
|
187 |
-
},
|
188 |
-
"50279": {
|
189 |
-
"content": " ",
|
190 |
-
"lstrip": false,
|
191 |
-
"normalized": true,
|
192 |
-
"rstrip": false,
|
193 |
-
"single_word": false,
|
194 |
-
"special": false
|
195 |
-
},
|
196 |
-
"50280": {
|
197 |
-
"content": " ",
|
198 |
-
"lstrip": false,
|
199 |
-
"normalized": true,
|
200 |
-
"rstrip": false,
|
201 |
-
"single_word": false,
|
202 |
-
"special": false
|
203 |
-
},
|
204 |
-
"50281": {
|
205 |
-
"content": " ",
|
206 |
-
"lstrip": false,
|
207 |
-
"normalized": true,
|
208 |
-
"rstrip": false,
|
209 |
-
"single_word": false,
|
210 |
-
"special": false
|
211 |
-
},
|
212 |
-
"50282": {
|
213 |
-
"content": " ",
|
214 |
-
"lstrip": false,
|
215 |
-
"normalized": true,
|
216 |
-
"rstrip": false,
|
217 |
-
"single_word": false,
|
218 |
-
"special": false
|
219 |
-
},
|
220 |
-
"50283": {
|
221 |
-
"content": " ",
|
222 |
-
"lstrip": false,
|
223 |
-
"normalized": true,
|
224 |
-
"rstrip": false,
|
225 |
-
"single_word": false,
|
226 |
-
"special": false
|
227 |
-
},
|
228 |
-
"50284": {
|
229 |
-
"content": " ",
|
230 |
-
"lstrip": false,
|
231 |
-
"normalized": true,
|
232 |
-
"rstrip": false,
|
233 |
-
"single_word": false,
|
234 |
-
"special": false
|
235 |
-
},
|
236 |
-
"50285": {
|
237 |
-
"content": " ",
|
238 |
-
"lstrip": false,
|
239 |
-
"normalized": true,
|
240 |
-
"rstrip": false,
|
241 |
-
"single_word": false,
|
242 |
-
"special": false
|
243 |
-
},
|
244 |
-
"50286": {
|
245 |
-
"content": " ",
|
246 |
-
"lstrip": false,
|
247 |
-
"normalized": true,
|
248 |
-
"rstrip": false,
|
249 |
-
"single_word": false,
|
250 |
-
"special": false
|
251 |
-
},
|
252 |
-
"50287": {
|
253 |
-
"content": "\t\t\t\t\t\t\t\t\t",
|
254 |
-
"lstrip": false,
|
255 |
-
"normalized": true,
|
256 |
-
"rstrip": false,
|
257 |
-
"single_word": false,
|
258 |
-
"special": false
|
259 |
-
},
|
260 |
-
"50288": {
|
261 |
-
"content": "\t\t\t\t\t\t\t\t",
|
262 |
-
"lstrip": false,
|
263 |
-
"normalized": true,
|
264 |
-
"rstrip": false,
|
265 |
-
"single_word": false,
|
266 |
-
"special": false
|
267 |
-
},
|
268 |
-
"50289": {
|
269 |
-
"content": "\t\t\t\t\t\t\t",
|
270 |
-
"lstrip": false,
|
271 |
-
"normalized": true,
|
272 |
-
"rstrip": false,
|
273 |
-
"single_word": false,
|
274 |
-
"special": false
|
275 |
-
},
|
276 |
-
"50290": {
|
277 |
-
"content": "\t\t\t\t\t\t",
|
278 |
-
"lstrip": false,
|
279 |
-
"normalized": true,
|
280 |
-
"rstrip": false,
|
281 |
-
"single_word": false,
|
282 |
-
"special": false
|
283 |
-
},
|
284 |
-
"50291": {
|
285 |
-
"content": "\t\t\t\t\t",
|
286 |
-
"lstrip": false,
|
287 |
-
"normalized": true,
|
288 |
-
"rstrip": false,
|
289 |
-
"single_word": false,
|
290 |
-
"special": false
|
291 |
-
},
|
292 |
-
"50292": {
|
293 |
-
"content": "\t\t\t\t",
|
294 |
-
"lstrip": false,
|
295 |
-
"normalized": true,
|
296 |
-
"rstrip": false,
|
297 |
-
"single_word": false,
|
298 |
-
"special": false
|
299 |
-
},
|
300 |
-
"50293": {
|
301 |
-
"content": "\t\t\t",
|
302 |
-
"lstrip": false,
|
303 |
-
"normalized": true,
|
304 |
-
"rstrip": false,
|
305 |
-
"single_word": false,
|
306 |
-
"special": false
|
307 |
-
},
|
308 |
-
"50294": {
|
309 |
-
"content": "\t\t",
|
310 |
-
"lstrip": false,
|
311 |
-
"normalized": true,
|
312 |
-
"rstrip": false,
|
313 |
-
"single_word": false,
|
314 |
-
"special": false
|
315 |
}
|
316 |
},
|
317 |
"bos_token": "<|endoftext|>",
|
318 |
"clean_up_tokenization_spaces": true,
|
319 |
"eos_token": "<|endoftext|>",
|
320 |
-
"model_max_length":
|
321 |
"pad_token": "<|endoftext|>",
|
322 |
-
"tokenizer_class": "
|
323 |
"torch_dtype": "auto",
|
324 |
"unk_token": "<|endoftext|>"
|
325 |
}
|
|
|
8 |
"rstrip": false,
|
9 |
"single_word": false,
|
10 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
}
|
12 |
},
|
13 |
"bos_token": "<|endoftext|>",
|
14 |
"clean_up_tokenization_spaces": true,
|
15 |
"eos_token": "<|endoftext|>",
|
16 |
+
"model_max_length": 1024,
|
17 |
"pad_token": "<|endoftext|>",
|
18 |
+
"tokenizer_class": "GPT2Tokenizer",
|
19 |
"torch_dtype": "auto",
|
20 |
"unk_token": "<|endoftext|>"
|
21 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4283
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c6107fe494cce67604f477c6e3ddb0c7eef565a136c71951dc32799619dd52a
|
3 |
size 4283
|