End of training
Browse files- README.md +110 -0
- adapter_config.json +73 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +41 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: llama2
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
base_model: meta-llama/Llama-2-7b-hf
|
7 |
+
model-index:
|
8 |
+
- name: llama_2_7b_Magiccoder_evol_downNupNgateNqNkNvNo_r8_lr0.0001_bg88_alpha8_0_41_normlayergrad
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
# llama_2_7b_Magiccoder_evol_downNupNgateNqNkNvNo_r8_lr0.0001_bg88_alpha8_0_41_normlayergrad
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on an unknown dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.1291
|
20 |
+
|
21 |
+
## Model description
|
22 |
+
|
23 |
+
More information needed
|
24 |
+
|
25 |
+
## Intended uses & limitations
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Training and evaluation data
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training procedure
|
34 |
+
|
35 |
+
### Training hyperparameters
|
36 |
+
|
37 |
+
The following hyperparameters were used during training:
|
38 |
+
- learning_rate: 0.0001
|
39 |
+
- train_batch_size: 8
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 8
|
43 |
+
- total_train_batch_size: 64
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- lr_scheduler_warmup_steps: 0.02
|
47 |
+
- num_epochs: 1
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:------:|:----:|:---------------:|
|
53 |
+
| 1.3048 | 0.0203 | 31 | 1.2412 |
|
54 |
+
| 1.1685 | 0.0405 | 62 | 1.2116 |
|
55 |
+
| 1.1585 | 0.0608 | 93 | 1.1957 |
|
56 |
+
| 1.1653 | 0.0810 | 124 | 1.1848 |
|
57 |
+
| 1.1337 | 0.1013 | 155 | 1.1766 |
|
58 |
+
| 1.1308 | 0.1215 | 186 | 1.1674 |
|
59 |
+
| 1.1602 | 0.1418 | 217 | 1.1661 |
|
60 |
+
| 1.1277 | 0.1620 | 248 | 1.1611 |
|
61 |
+
| 1.1375 | 0.1823 | 279 | 1.1615 |
|
62 |
+
| 1.1095 | 0.2025 | 310 | 1.1582 |
|
63 |
+
| 1.1043 | 0.2228 | 341 | 1.1551 |
|
64 |
+
| 1.1269 | 0.2431 | 372 | 1.1511 |
|
65 |
+
| 1.1175 | 0.2633 | 403 | 1.1533 |
|
66 |
+
| 1.1252 | 0.2836 | 434 | 1.1491 |
|
67 |
+
| 1.1192 | 0.3038 | 465 | 1.1513 |
|
68 |
+
| 1.1074 | 0.3241 | 496 | 1.1437 |
|
69 |
+
| 1.117 | 0.3443 | 527 | 1.1459 |
|
70 |
+
| 1.1058 | 0.3646 | 558 | 1.1427 |
|
71 |
+
| 1.1144 | 0.3848 | 589 | 1.1416 |
|
72 |
+
| 1.0913 | 0.4051 | 620 | 1.1435 |
|
73 |
+
| 1.111 | 0.4254 | 651 | 1.1388 |
|
74 |
+
| 1.1239 | 0.4456 | 682 | 1.1397 |
|
75 |
+
| 1.1074 | 0.4659 | 713 | 1.1402 |
|
76 |
+
| 1.1076 | 0.4861 | 744 | 1.1396 |
|
77 |
+
| 1.0887 | 0.5064 | 775 | 1.1374 |
|
78 |
+
| 1.0872 | 0.5266 | 806 | 1.1358 |
|
79 |
+
| 1.0802 | 0.5469 | 837 | 1.1351 |
|
80 |
+
| 1.0812 | 0.5671 | 868 | 1.1338 |
|
81 |
+
| 1.097 | 0.5874 | 899 | 1.1352 |
|
82 |
+
| 1.1052 | 0.6076 | 930 | 1.1352 |
|
83 |
+
| 1.088 | 0.6279 | 961 | 1.1328 |
|
84 |
+
| 1.0977 | 0.6482 | 992 | 1.1315 |
|
85 |
+
| 1.0902 | 0.6684 | 1023 | 1.1312 |
|
86 |
+
| 1.1085 | 0.6887 | 1054 | 1.1309 |
|
87 |
+
| 1.0956 | 0.7089 | 1085 | 1.1294 |
|
88 |
+
| 1.0897 | 0.7292 | 1116 | 1.1310 |
|
89 |
+
| 1.0816 | 0.7494 | 1147 | 1.1304 |
|
90 |
+
| 1.0995 | 0.7697 | 1178 | 1.1296 |
|
91 |
+
| 1.1032 | 0.7899 | 1209 | 1.1292 |
|
92 |
+
| 1.0878 | 0.8102 | 1240 | 1.1297 |
|
93 |
+
| 1.0988 | 0.8304 | 1271 | 1.1294 |
|
94 |
+
| 1.0915 | 0.8507 | 1302 | 1.1294 |
|
95 |
+
| 1.0823 | 0.8710 | 1333 | 1.1295 |
|
96 |
+
| 1.0867 | 0.8912 | 1364 | 1.1289 |
|
97 |
+
| 1.098 | 0.9115 | 1395 | 1.1290 |
|
98 |
+
| 1.1071 | 0.9317 | 1426 | 1.1292 |
|
99 |
+
| 1.061 | 0.9520 | 1457 | 1.1291 |
|
100 |
+
| 1.0708 | 0.9722 | 1488 | 1.1292 |
|
101 |
+
| 1.0977 | 0.9925 | 1519 | 1.1291 |
|
102 |
+
|
103 |
+
|
104 |
+
### Framework versions
|
105 |
+
|
106 |
+
- PEFT 0.7.1
|
107 |
+
- Transformers 4.40.2
|
108 |
+
- Pytorch 2.3.0+cu121
|
109 |
+
- Datasets 2.16.1
|
110 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": [
|
11 |
+
0,
|
12 |
+
1,
|
13 |
+
2,
|
14 |
+
3,
|
15 |
+
4,
|
16 |
+
5,
|
17 |
+
6,
|
18 |
+
7,
|
19 |
+
8,
|
20 |
+
9,
|
21 |
+
10,
|
22 |
+
11,
|
23 |
+
12,
|
24 |
+
13,
|
25 |
+
14,
|
26 |
+
15,
|
27 |
+
16,
|
28 |
+
17,
|
29 |
+
18,
|
30 |
+
19,
|
31 |
+
20,
|
32 |
+
21,
|
33 |
+
22,
|
34 |
+
23,
|
35 |
+
24,
|
36 |
+
25,
|
37 |
+
26,
|
38 |
+
27,
|
39 |
+
28,
|
40 |
+
29,
|
41 |
+
30,
|
42 |
+
31,
|
43 |
+
32,
|
44 |
+
33,
|
45 |
+
34,
|
46 |
+
35,
|
47 |
+
36,
|
48 |
+
37,
|
49 |
+
38,
|
50 |
+
39,
|
51 |
+
40
|
52 |
+
],
|
53 |
+
"loftq_config": {},
|
54 |
+
"lora_alpha": 8,
|
55 |
+
"lora_dropout": 0,
|
56 |
+
"megatron_config": null,
|
57 |
+
"megatron_core": "megatron.core",
|
58 |
+
"modules_to_save": null,
|
59 |
+
"peft_type": "LORA",
|
60 |
+
"r": 8,
|
61 |
+
"rank_pattern": {},
|
62 |
+
"revision": "unsloth",
|
63 |
+
"target_modules": [
|
64 |
+
"up_proj",
|
65 |
+
"down_proj",
|
66 |
+
"q_proj",
|
67 |
+
"gate_proj",
|
68 |
+
"v_proj",
|
69 |
+
"k_proj",
|
70 |
+
"o_proj"
|
71 |
+
],
|
72 |
+
"task_type": "CAUSAL_LM"
|
73 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fad8cc5aa525f30673e12e6fd993782559e7600cce3ebc596ef82f204958981
|
3 |
+
size 80013120
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
30 |
+
"bos_token": "<s>",
|
31 |
+
"clean_up_tokenization_spaces": false,
|
32 |
+
"eos_token": "</s>",
|
33 |
+
"legacy": false,
|
34 |
+
"model_max_length": 4096,
|
35 |
+
"pad_token": "<unk>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"tokenizer_class": "LlamaTokenizer",
|
39 |
+
"unk_token": "<unk>",
|
40 |
+
"use_default_system_prompt": false
|
41 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df6746ecece9c5f207e2a263b71f4a04936b5a35b31cbb45f7fccd2a6ff6ccb9
|
3 |
+
size 5304
|