End of training
Browse files- README.md +219 -0
- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +3 -0
- runs/Aug04_13-36-40_0d6c6470f9b3/events.out.tfevents.1722778612.0d6c6470f9b3.3512.0 +3 -0
- special_tokens_map.json +36 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +92 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,219 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: codellama/CodeLlama-7b-Instruct-hf
|
3 |
+
library_name: peft
|
4 |
+
license: llama2
|
5 |
+
tags:
|
6 |
+
- trl
|
7 |
+
- sft
|
8 |
+
- generated_from_trainer
|
9 |
+
model-index:
|
10 |
+
- name: ECS-Codellama-7b-lora-rps-adapter
|
11 |
+
results: []
|
12 |
+
---
|
13 |
+
|
14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
15 |
+
should probably proofread and complete it, then remove this comment. -->
|
16 |
+
|
17 |
+
# ECS-Codellama-7b-lora-rps-adapter
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [codellama/CodeLlama-7b-Instruct-hf](https://huggingface.co/codellama/CodeLlama-7b-Instruct-hf) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.2955
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0002
|
41 |
+
- train_batch_size: 2
|
42 |
+
- eval_batch_size: 2
|
43 |
+
- seed: 42
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: linear
|
46 |
+
- lr_scheduler_warmup_ratio: 0.03
|
47 |
+
- num_epochs: 4
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:------:|:-----:|:---------------:|
|
53 |
+
| 0.1784 | 2.6210 | 15000 | 0.2849 |
|
54 |
+
| 0.2039 | 2.6297 | 15050 | 0.2825 |
|
55 |
+
| 0.194 | 2.6385 | 15100 | 0.2842 |
|
56 |
+
| 0.2073 | 2.6472 | 15150 | 0.2844 |
|
57 |
+
| 0.1818 | 2.6559 | 15200 | 0.2841 |
|
58 |
+
| 0.1858 | 2.6647 | 15250 | 0.2837 |
|
59 |
+
| 0.191 | 2.6734 | 15300 | 0.2821 |
|
60 |
+
| 0.2024 | 2.6822 | 15350 | 0.2814 |
|
61 |
+
| 0.1699 | 2.6909 | 15400 | 0.2832 |
|
62 |
+
| 0.1782 | 2.6996 | 15450 | 0.2813 |
|
63 |
+
| 0.1971 | 2.7084 | 15500 | 0.2818 |
|
64 |
+
| 0.1974 | 2.7171 | 15550 | 0.2811 |
|
65 |
+
| 0.1867 | 2.7258 | 15600 | 0.2818 |
|
66 |
+
| 0.1843 | 2.7346 | 15650 | 0.2836 |
|
67 |
+
| 0.192 | 2.7433 | 15700 | 0.2834 |
|
68 |
+
| 0.2191 | 2.7521 | 15750 | 0.2800 |
|
69 |
+
| 0.1797 | 2.7608 | 15800 | 0.2797 |
|
70 |
+
| 0.1871 | 2.7695 | 15850 | 0.2817 |
|
71 |
+
| 0.1893 | 2.7783 | 15900 | 0.2817 |
|
72 |
+
| 0.1845 | 2.7870 | 15950 | 0.2824 |
|
73 |
+
| 0.1954 | 2.7957 | 16000 | 0.2828 |
|
74 |
+
| 0.1752 | 2.8045 | 16050 | 0.2824 |
|
75 |
+
| 0.213 | 2.8132 | 16100 | 0.2803 |
|
76 |
+
| 0.1953 | 2.8219 | 16150 | 0.2818 |
|
77 |
+
| 0.1959 | 2.8307 | 16200 | 0.2807 |
|
78 |
+
| 0.1904 | 2.8394 | 16250 | 0.2814 |
|
79 |
+
| 0.191 | 2.8482 | 16300 | 0.2806 |
|
80 |
+
| 0.1783 | 2.8569 | 16350 | 0.2803 |
|
81 |
+
| 0.1997 | 2.8656 | 16400 | 0.2802 |
|
82 |
+
| 0.2195 | 2.8744 | 16450 | 0.2787 |
|
83 |
+
| 0.189 | 2.8831 | 16500 | 0.2800 |
|
84 |
+
| 0.1951 | 2.8918 | 16550 | 0.2788 |
|
85 |
+
| 0.1985 | 2.9006 | 16600 | 0.2789 |
|
86 |
+
| 0.2169 | 2.9093 | 16650 | 0.2785 |
|
87 |
+
| 0.195 | 2.9180 | 16700 | 0.2788 |
|
88 |
+
| 0.1744 | 2.9268 | 16750 | 0.2800 |
|
89 |
+
| 0.1635 | 2.9355 | 16800 | 0.2800 |
|
90 |
+
| 0.1877 | 2.9443 | 16850 | 0.2782 |
|
91 |
+
| 0.1977 | 2.9530 | 16900 | 0.2770 |
|
92 |
+
| 0.1808 | 2.9617 | 16950 | 0.2781 |
|
93 |
+
| 0.1824 | 2.9705 | 17000 | 0.2784 |
|
94 |
+
| 0.1947 | 2.9792 | 17050 | 0.2781 |
|
95 |
+
| 0.1946 | 2.9879 | 17100 | 0.2767 |
|
96 |
+
| 0.1742 | 2.9967 | 17150 | 0.2770 |
|
97 |
+
| 0.1527 | 3.0054 | 17200 | 0.2886 |
|
98 |
+
| 0.1205 | 3.0142 | 17250 | 0.2929 |
|
99 |
+
| 0.1261 | 3.0229 | 17300 | 0.2981 |
|
100 |
+
| 0.1122 | 3.0316 | 17350 | 0.2997 |
|
101 |
+
| 0.1441 | 3.0404 | 17400 | 0.2979 |
|
102 |
+
| 0.1202 | 3.0491 | 17450 | 0.3007 |
|
103 |
+
| 0.1285 | 3.0578 | 17500 | 0.2983 |
|
104 |
+
| 0.149 | 3.0666 | 17550 | 0.3007 |
|
105 |
+
| 0.1369 | 3.0753 | 17600 | 0.2968 |
|
106 |
+
| 0.1225 | 3.0840 | 17650 | 0.2994 |
|
107 |
+
| 0.132 | 3.0928 | 17700 | 0.3007 |
|
108 |
+
| 0.1296 | 3.1015 | 17750 | 0.3006 |
|
109 |
+
| 0.1207 | 3.1103 | 17800 | 0.3000 |
|
110 |
+
| 0.1385 | 3.1190 | 17850 | 0.2981 |
|
111 |
+
| 0.1347 | 3.1277 | 17900 | 0.3000 |
|
112 |
+
| 0.114 | 3.1365 | 17950 | 0.2994 |
|
113 |
+
| 0.1233 | 3.1452 | 18000 | 0.2991 |
|
114 |
+
| 0.1284 | 3.1539 | 18050 | 0.2991 |
|
115 |
+
| 0.1222 | 3.1627 | 18100 | 0.3005 |
|
116 |
+
| 0.1367 | 3.1714 | 18150 | 0.2988 |
|
117 |
+
| 0.1308 | 3.1802 | 18200 | 0.2992 |
|
118 |
+
| 0.1138 | 3.1889 | 18250 | 0.3001 |
|
119 |
+
| 0.1259 | 3.1976 | 18300 | 0.2979 |
|
120 |
+
| 0.1383 | 3.2064 | 18350 | 0.2993 |
|
121 |
+
| 0.1288 | 3.2151 | 18400 | 0.2989 |
|
122 |
+
| 0.1364 | 3.2238 | 18450 | 0.2974 |
|
123 |
+
| 0.1232 | 3.2326 | 18500 | 0.2989 |
|
124 |
+
| 0.1348 | 3.2413 | 18550 | 0.3012 |
|
125 |
+
| 0.1168 | 3.2500 | 18600 | 0.2998 |
|
126 |
+
| 0.1342 | 3.2588 | 18650 | 0.3026 |
|
127 |
+
| 0.1385 | 3.2675 | 18700 | 0.2979 |
|
128 |
+
| 0.1298 | 3.2763 | 18750 | 0.2962 |
|
129 |
+
| 0.1373 | 3.2850 | 18800 | 0.2950 |
|
130 |
+
| 0.1292 | 3.2937 | 18850 | 0.2986 |
|
131 |
+
| 0.1329 | 3.3025 | 18900 | 0.2965 |
|
132 |
+
| 0.1324 | 3.3112 | 18950 | 0.3016 |
|
133 |
+
| 0.1176 | 3.3199 | 19000 | 0.2991 |
|
134 |
+
| 0.1444 | 3.3287 | 19050 | 0.2940 |
|
135 |
+
| 0.1395 | 3.3374 | 19100 | 0.2960 |
|
136 |
+
| 0.1247 | 3.3461 | 19150 | 0.2975 |
|
137 |
+
| 0.1313 | 3.3549 | 19200 | 0.2976 |
|
138 |
+
| 0.1299 | 3.3636 | 19250 | 0.2967 |
|
139 |
+
| 0.1339 | 3.3724 | 19300 | 0.2969 |
|
140 |
+
| 0.128 | 3.3811 | 19350 | 0.2949 |
|
141 |
+
| 0.1296 | 3.3898 | 19400 | 0.2978 |
|
142 |
+
| 0.1346 | 3.3986 | 19450 | 0.2961 |
|
143 |
+
| 0.1388 | 3.4073 | 19500 | 0.2960 |
|
144 |
+
| 0.1236 | 3.4160 | 19550 | 0.2951 |
|
145 |
+
| 0.1203 | 3.4248 | 19600 | 0.2952 |
|
146 |
+
| 0.1161 | 3.4335 | 19650 | 0.2977 |
|
147 |
+
| 0.1158 | 3.4423 | 19700 | 0.2955 |
|
148 |
+
| 0.1292 | 3.4510 | 19750 | 0.2979 |
|
149 |
+
| 0.1224 | 3.4597 | 19800 | 0.2976 |
|
150 |
+
| 0.1241 | 3.4685 | 19850 | 0.2979 |
|
151 |
+
| 0.1411 | 3.4772 | 19900 | 0.2953 |
|
152 |
+
| 0.1337 | 3.4859 | 19950 | 0.2966 |
|
153 |
+
| 0.1298 | 3.4947 | 20000 | 0.2964 |
|
154 |
+
| 0.1176 | 3.5034 | 20050 | 0.2958 |
|
155 |
+
| 0.1175 | 3.5121 | 20100 | 0.2966 |
|
156 |
+
| 0.1409 | 3.5209 | 20150 | 0.2952 |
|
157 |
+
| 0.1339 | 3.5296 | 20200 | 0.2951 |
|
158 |
+
| 0.1348 | 3.5384 | 20250 | 0.2956 |
|
159 |
+
| 0.1281 | 3.5471 | 20300 | 0.2956 |
|
160 |
+
| 0.1293 | 3.5558 | 20350 | 0.2981 |
|
161 |
+
| 0.1257 | 3.5646 | 20400 | 0.2969 |
|
162 |
+
| 0.1152 | 3.5733 | 20450 | 0.2955 |
|
163 |
+
| 0.1276 | 3.5820 | 20500 | 0.2960 |
|
164 |
+
| 0.1366 | 3.5908 | 20550 | 0.2977 |
|
165 |
+
| 0.1364 | 3.5995 | 20600 | 0.2982 |
|
166 |
+
| 0.134 | 3.6082 | 20650 | 0.2967 |
|
167 |
+
| 0.1266 | 3.6170 | 20700 | 0.2965 |
|
168 |
+
| 0.1215 | 3.6257 | 20750 | 0.2970 |
|
169 |
+
| 0.1253 | 3.6345 | 20800 | 0.2991 |
|
170 |
+
| 0.116 | 3.6432 | 20850 | 0.2976 |
|
171 |
+
| 0.1255 | 3.6519 | 20900 | 0.2972 |
|
172 |
+
| 0.1271 | 3.6607 | 20950 | 0.2969 |
|
173 |
+
| 0.1155 | 3.6694 | 21000 | 0.2970 |
|
174 |
+
| 0.1223 | 3.6781 | 21050 | 0.2968 |
|
175 |
+
| 0.1317 | 3.6869 | 21100 | 0.2956 |
|
176 |
+
| 0.1257 | 3.6956 | 21150 | 0.2957 |
|
177 |
+
| 0.1262 | 3.7044 | 21200 | 0.2952 |
|
178 |
+
| 0.1215 | 3.7131 | 21250 | 0.2957 |
|
179 |
+
| 0.1285 | 3.7218 | 21300 | 0.2955 |
|
180 |
+
| 0.1264 | 3.7306 | 21350 | 0.2956 |
|
181 |
+
| 0.1364 | 3.7393 | 21400 | 0.2967 |
|
182 |
+
| 0.1213 | 3.7480 | 21450 | 0.2966 |
|
183 |
+
| 0.1316 | 3.7568 | 21500 | 0.2972 |
|
184 |
+
| 0.1174 | 3.7655 | 21550 | 0.2991 |
|
185 |
+
| 0.1167 | 3.7742 | 21600 | 0.2982 |
|
186 |
+
| 0.1274 | 3.7830 | 21650 | 0.2974 |
|
187 |
+
| 0.1302 | 3.7917 | 21700 | 0.2960 |
|
188 |
+
| 0.118 | 3.8005 | 21750 | 0.2958 |
|
189 |
+
| 0.1264 | 3.8092 | 21800 | 0.2977 |
|
190 |
+
| 0.1115 | 3.8179 | 21850 | 0.2971 |
|
191 |
+
| 0.1128 | 3.8267 | 21900 | 0.2973 |
|
192 |
+
| 0.1186 | 3.8354 | 21950 | 0.2965 |
|
193 |
+
| 0.1173 | 3.8441 | 22000 | 0.2965 |
|
194 |
+
| 0.1293 | 3.8529 | 22050 | 0.2963 |
|
195 |
+
| 0.1226 | 3.8616 | 22100 | 0.2964 |
|
196 |
+
| 0.1173 | 3.8703 | 22150 | 0.2964 |
|
197 |
+
| 0.1343 | 3.8791 | 22200 | 0.2966 |
|
198 |
+
| 0.1365 | 3.8878 | 22250 | 0.2962 |
|
199 |
+
| 0.1187 | 3.8966 | 22300 | 0.2963 |
|
200 |
+
| 0.1132 | 3.9053 | 22350 | 0.2963 |
|
201 |
+
| 0.1328 | 3.9140 | 22400 | 0.2961 |
|
202 |
+
| 0.1394 | 3.9228 | 22450 | 0.2956 |
|
203 |
+
| 0.1312 | 3.9315 | 22500 | 0.2959 |
|
204 |
+
| 0.1256 | 3.9402 | 22550 | 0.2958 |
|
205 |
+
| 0.1272 | 3.9490 | 22600 | 0.2955 |
|
206 |
+
| 0.1128 | 3.9577 | 22650 | 0.2954 |
|
207 |
+
| 0.1193 | 3.9665 | 22700 | 0.2955 |
|
208 |
+
| 0.1169 | 3.9752 | 22750 | 0.2954 |
|
209 |
+
| 0.1308 | 3.9839 | 22800 | 0.2954 |
|
210 |
+
| 0.1185 | 3.9927 | 22850 | 0.2955 |
|
211 |
+
|
212 |
+
|
213 |
+
### Framework versions
|
214 |
+
|
215 |
+
- PEFT 0.12.0
|
216 |
+
- Transformers 4.43.3
|
217 |
+
- Pytorch 2.3.1+cu121
|
218 |
+
- Datasets 2.20.0
|
219 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "codellama/CodeLlama-7b-Instruct-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 8,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 128,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"down_proj",
|
24 |
+
"v_proj",
|
25 |
+
"k_proj",
|
26 |
+
"o_proj",
|
27 |
+
"up_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"q_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": true
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2712c5b37aaa5d7e34ec99b45db14dd31473a2dc10e4dfbea3c18dba19b557a4
|
3 |
+
size 2332095256
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<PAD>": 32016
|
3 |
+
}
|
runs/Aug04_13-36-40_0d6c6470f9b3/events.out.tfevents.1722778612.0d6c6470f9b3.3512.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5767ded8cd6ecef1437227db09fc3f9a3f15337f98c3d4c5b4f728eb8f029f1
|
3 |
+
size 146631
|
special_tokens_map.json
ADDED
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"β<PRE>",
|
4 |
+
"β<MID>",
|
5 |
+
"β<SUF>",
|
6 |
+
"β<EOT>"
|
7 |
+
],
|
8 |
+
"bos_token": {
|
9 |
+
"content": "<s>",
|
10 |
+
"lstrip": false,
|
11 |
+
"normalized": false,
|
12 |
+
"rstrip": false,
|
13 |
+
"single_word": false
|
14 |
+
},
|
15 |
+
"eos_token": {
|
16 |
+
"content": "</s>",
|
17 |
+
"lstrip": false,
|
18 |
+
"normalized": false,
|
19 |
+
"rstrip": false,
|
20 |
+
"single_word": false
|
21 |
+
},
|
22 |
+
"pad_token": {
|
23 |
+
"content": "<PAD>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false
|
28 |
+
},
|
29 |
+
"unk_token": {
|
30 |
+
"content": "<unk>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
}
|
36 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45ccb9c8b6b561889acea59191d66986d314e7cbd6a78abc6e49b139ca91c1e6
|
3 |
+
size 500058
|
tokenizer_config.json
ADDED
@@ -0,0 +1,92 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32007": {
|
30 |
+
"content": "β<PRE>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32008": {
|
38 |
+
"content": "β<SUF>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32009": {
|
46 |
+
"content": "β<MID>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32010": {
|
54 |
+
"content": "β<EOT>",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32016": {
|
62 |
+
"content": "<PAD>",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
}
|
69 |
+
},
|
70 |
+
"additional_special_tokens": [
|
71 |
+
"β<PRE>",
|
72 |
+
"β<MID>",
|
73 |
+
"β<SUF>",
|
74 |
+
"β<EOT>"
|
75 |
+
],
|
76 |
+
"bos_token": "<s>",
|
77 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content | trim + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content | trim + ' ' + eos_token }}{% endif %}{% endfor %}",
|
78 |
+
"clean_up_tokenization_spaces": false,
|
79 |
+
"eos_token": "</s>",
|
80 |
+
"eot_token": "β<EOT>",
|
81 |
+
"fill_token": "<FILL_ME>",
|
82 |
+
"legacy": null,
|
83 |
+
"middle_token": "β<MID>",
|
84 |
+
"model_max_length": 1000000000000000019884624838656,
|
85 |
+
"pad_token": "<PAD>",
|
86 |
+
"prefix_token": "β<PRE>",
|
87 |
+
"sp_model_kwargs": {},
|
88 |
+
"suffix_token": "β<SUF>",
|
89 |
+
"tokenizer_class": "CodeLlamaTokenizer",
|
90 |
+
"unk_token": "<unk>",
|
91 |
+
"use_default_system_prompt": false
|
92 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e7c904905085e0075baf404f3edf4d53d0a090289d4108a987eed95d4b997698
|
3 |
+
size 5496
|