End of training
Browse files- README.md +125 -0
- loss_plot.png +0 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer_config.json +194 -0
README.md
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: other
|
| 4 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-base
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:deepseek-ai/deepseek-coder-6.7b-base
|
| 7 |
+
- lora
|
| 8 |
+
- transformers
|
| 9 |
+
pipeline_tag: text-generation
|
| 10 |
+
model-index:
|
| 11 |
+
- name: lemexp-task1-v3-lemma_object_full_nodefs-deepseek-coder-6.7b-base
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# lemexp-task1-v3-lemma_object_full_nodefs-deepseek-coder-6.7b-base
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [deepseek-ai/deepseek-coder-6.7b-base](https://huggingface.co/deepseek-ai/deepseek-coder-6.7b-base) on an unknown dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.1302
|
| 23 |
+
|
| 24 |
+
## Model description
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Intended uses & limitations
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training and evaluation data
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training procedure
|
| 37 |
+
|
| 38 |
+
### Training hyperparameters
|
| 39 |
+
|
| 40 |
+
The following hyperparameters were used during training:
|
| 41 |
+
- learning_rate: 0.0004
|
| 42 |
+
- train_batch_size: 4
|
| 43 |
+
- eval_batch_size: 2
|
| 44 |
+
- seed: 42
|
| 45 |
+
- distributed_type: multi-GPU
|
| 46 |
+
- num_devices: 4
|
| 47 |
+
- total_train_batch_size: 16
|
| 48 |
+
- total_eval_batch_size: 8
|
| 49 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 50 |
+
- lr_scheduler_type: linear
|
| 51 |
+
- num_epochs: 12
|
| 52 |
+
- mixed_precision_training: Native AMP
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:-------:|:------:|:---------------:|
|
| 58 |
+
| 0.3108 | 0.2000 | 3114 | 0.3017 |
|
| 59 |
+
| 0.2685 | 0.4000 | 6228 | 0.2551 |
|
| 60 |
+
| 0.2493 | 0.6000 | 9342 | 0.2313 |
|
| 61 |
+
| 0.2335 | 0.8001 | 12456 | 0.2242 |
|
| 62 |
+
| 0.2223 | 1.0001 | 15570 | 0.2162 |
|
| 63 |
+
| 0.2042 | 1.2001 | 18684 | 0.2044 |
|
| 64 |
+
| 0.1984 | 1.4001 | 21798 | 0.1986 |
|
| 65 |
+
| 0.1993 | 1.6001 | 24912 | 0.1940 |
|
| 66 |
+
| 0.1931 | 1.8001 | 28026 | 0.1886 |
|
| 67 |
+
| 0.1887 | 2.0001 | 31140 | 0.1876 |
|
| 68 |
+
| 0.1712 | 2.2001 | 34254 | 0.1830 |
|
| 69 |
+
| 0.1751 | 2.4002 | 37368 | 0.1793 |
|
| 70 |
+
| 0.1714 | 2.6002 | 40482 | 0.1794 |
|
| 71 |
+
| 0.1736 | 2.8002 | 43596 | 0.1795 |
|
| 72 |
+
| 0.168 | 3.0002 | 46710 | 0.1722 |
|
| 73 |
+
| 0.1564 | 3.2002 | 49824 | 0.1717 |
|
| 74 |
+
| 0.156 | 3.4002 | 52938 | 0.1695 |
|
| 75 |
+
| 0.154 | 3.6002 | 56052 | 0.1673 |
|
| 76 |
+
| 0.1538 | 3.8002 | 59166 | 0.1666 |
|
| 77 |
+
| 0.1539 | 4.0003 | 62280 | 0.1657 |
|
| 78 |
+
| 0.1388 | 4.2003 | 65394 | 0.1624 |
|
| 79 |
+
| 0.1406 | 4.4003 | 68508 | 0.1634 |
|
| 80 |
+
| 0.1379 | 4.6003 | 71622 | 0.1573 |
|
| 81 |
+
| 0.1407 | 4.8003 | 74736 | 0.1580 |
|
| 82 |
+
| 0.1395 | 5.0003 | 77850 | 0.1577 |
|
| 83 |
+
| 0.1245 | 5.2003 | 80964 | 0.1550 |
|
| 84 |
+
| 0.1286 | 5.4003 | 84078 | 0.1559 |
|
| 85 |
+
| 0.1283 | 5.6004 | 87192 | 0.1521 |
|
| 86 |
+
| 0.1254 | 5.8004 | 90306 | 0.1480 |
|
| 87 |
+
| 0.1254 | 6.0004 | 93420 | 0.1445 |
|
| 88 |
+
| 0.1129 | 6.2004 | 96534 | 0.1441 |
|
| 89 |
+
| 0.1146 | 6.4004 | 99648 | 0.1441 |
|
| 90 |
+
| 0.1166 | 6.6004 | 102762 | 0.1420 |
|
| 91 |
+
| 0.1159 | 6.8004 | 105876 | 0.1436 |
|
| 92 |
+
| 0.1155 | 7.0004 | 108990 | 0.1407 |
|
| 93 |
+
| 0.1012 | 7.2005 | 112104 | 0.1419 |
|
| 94 |
+
| 0.0994 | 7.4005 | 115218 | 0.1419 |
|
| 95 |
+
| 0.1012 | 7.6005 | 118332 | 0.1383 |
|
| 96 |
+
| 0.1027 | 7.8005 | 121446 | 0.1381 |
|
| 97 |
+
| 0.1014 | 8.0005 | 124560 | 0.1354 |
|
| 98 |
+
| 0.0896 | 8.2005 | 127674 | 0.1385 |
|
| 99 |
+
| 0.0893 | 8.4005 | 130788 | 0.1377 |
|
| 100 |
+
| 0.0918 | 8.6006 | 133902 | 0.1349 |
|
| 101 |
+
| 0.0915 | 8.8006 | 137016 | 0.1312 |
|
| 102 |
+
| 0.0878 | 9.0006 | 140130 | 0.1323 |
|
| 103 |
+
| 0.0757 | 9.2006 | 143244 | 0.1349 |
|
| 104 |
+
| 0.0772 | 9.4006 | 146358 | 0.1326 |
|
| 105 |
+
| 0.0779 | 9.6006 | 149472 | 0.1308 |
|
| 106 |
+
| 0.0757 | 9.8006 | 152586 | 0.1293 |
|
| 107 |
+
| 0.0768 | 10.0006 | 155700 | 0.1298 |
|
| 108 |
+
| 0.0661 | 10.2007 | 158814 | 0.1355 |
|
| 109 |
+
| 0.0648 | 10.4007 | 161928 | 0.1330 |
|
| 110 |
+
| 0.0661 | 10.6007 | 165042 | 0.1313 |
|
| 111 |
+
| 0.0643 | 10.8007 | 168156 | 0.1283 |
|
| 112 |
+
| 0.0627 | 11.0007 | 171270 | 0.1300 |
|
| 113 |
+
| 0.0567 | 11.2007 | 174384 | 0.1335 |
|
| 114 |
+
| 0.0569 | 11.4007 | 177498 | 0.1327 |
|
| 115 |
+
| 0.0553 | 11.6007 | 180612 | 0.1323 |
|
| 116 |
+
| 0.0558 | 11.8008 | 183726 | 0.1302 |
|
| 117 |
+
|
| 118 |
+
|
| 119 |
+
### Framework versions
|
| 120 |
+
|
| 121 |
+
- PEFT 0.17.1
|
| 122 |
+
- Transformers 4.55.4
|
| 123 |
+
- Pytorch 2.8.0+cu128
|
| 124 |
+
- Datasets 4.0.0
|
| 125 |
+
- Tokenizers 0.21.4
|
loss_plot.png
ADDED
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,194 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": false
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"clean_up_tokenization_spaces": false,
|
| 185 |
+
"eos_token": "<｜end▁of▁sentence｜>",
|
| 186 |
+
"extra_special_tokens": {},
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"sp_model_kwargs": {},
|
| 191 |
+
"tokenizer_class": "LlamaTokenizerFast",
|
| 192 |
+
"unk_token": null,
|
| 193 |
+
"use_default_system_prompt": false
|
| 194 |
+
}
|