End of training
Browse files- README.md +113 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: mistralai/Mistral-7B-v0.1
|
9 |
+
model-index:
|
10 |
+
- name: mistral-7b-autextification2024
|
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 |
+
# mistral-7b-autextification2024
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.6422
|
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: 4
|
42 |
+
- eval_batch_size: 8
|
43 |
+
- seed: 42
|
44 |
+
- gradient_accumulation_steps: 4
|
45 |
+
- total_train_batch_size: 16
|
46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
47 |
+
- lr_scheduler_type: constant
|
48 |
+
- lr_scheduler_warmup_ratio: 0.03
|
49 |
+
- training_steps: 500
|
50 |
+
|
51 |
+
### Training results
|
52 |
+
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
55 |
+
| 1.4251 | 0.0 | 10 | 1.7924 |
|
56 |
+
| 1.3175 | 0.01 | 20 | 1.7542 |
|
57 |
+
| 1.7841 | 0.01 | 30 | 1.7322 |
|
58 |
+
| 2.0421 | 0.01 | 40 | 1.7294 |
|
59 |
+
| 2.669 | 0.02 | 50 | 1.7471 |
|
60 |
+
| 1.314 | 0.02 | 60 | 1.7153 |
|
61 |
+
| 1.4678 | 0.02 | 70 | 1.6989 |
|
62 |
+
| 1.7679 | 0.03 | 80 | 1.6928 |
|
63 |
+
| 2.0057 | 0.03 | 90 | 1.7002 |
|
64 |
+
| 2.5086 | 0.03 | 100 | 1.7053 |
|
65 |
+
| 1.3326 | 0.04 | 110 | 1.6931 |
|
66 |
+
| 1.3984 | 0.04 | 120 | 1.6823 |
|
67 |
+
| 1.8045 | 0.04 | 130 | 1.6807 |
|
68 |
+
| 1.8764 | 0.05 | 140 | 1.6812 |
|
69 |
+
| 2.5524 | 0.05 | 150 | 1.6825 |
|
70 |
+
| 1.2854 | 0.05 | 160 | 1.6766 |
|
71 |
+
| 1.3712 | 0.06 | 170 | 1.6709 |
|
72 |
+
| 1.8211 | 0.06 | 180 | 1.6660 |
|
73 |
+
| 2.0365 | 0.06 | 190 | 1.6778 |
|
74 |
+
| 2.4664 | 0.07 | 200 | 1.6938 |
|
75 |
+
| 1.3405 | 0.07 | 210 | 1.6712 |
|
76 |
+
| 1.3856 | 0.07 | 220 | 1.6666 |
|
77 |
+
| 1.5553 | 0.08 | 230 | 1.6586 |
|
78 |
+
| 1.8616 | 0.08 | 240 | 1.6613 |
|
79 |
+
| 2.4064 | 0.09 | 250 | 1.6666 |
|
80 |
+
| 1.3446 | 0.09 | 260 | 1.6681 |
|
81 |
+
| 1.386 | 0.09 | 270 | 1.6645 |
|
82 |
+
| 1.6508 | 0.1 | 280 | 1.6582 |
|
83 |
+
| 1.8588 | 0.1 | 290 | 1.6600 |
|
84 |
+
| 2.3148 | 0.1 | 300 | 1.6524 |
|
85 |
+
| 1.2785 | 0.11 | 310 | 1.6549 |
|
86 |
+
| 1.2727 | 0.11 | 320 | 1.6517 |
|
87 |
+
| 1.5971 | 0.11 | 330 | 1.6486 |
|
88 |
+
| 1.7811 | 0.12 | 340 | 1.6540 |
|
89 |
+
| 2.3368 | 0.12 | 350 | 1.6596 |
|
90 |
+
| 1.2513 | 0.12 | 360 | 1.6578 |
|
91 |
+
| 1.4403 | 0.13 | 370 | 1.6429 |
|
92 |
+
| 1.8051 | 0.13 | 380 | 1.6462 |
|
93 |
+
| 1.8214 | 0.13 | 390 | 1.6469 |
|
94 |
+
| 2.4691 | 0.14 | 400 | 1.6654 |
|
95 |
+
| 1.2895 | 0.14 | 410 | 1.6543 |
|
96 |
+
| 1.3192 | 0.14 | 420 | 1.6435 |
|
97 |
+
| 1.7031 | 0.15 | 430 | 1.6438 |
|
98 |
+
| 1.8647 | 0.15 | 440 | 1.6402 |
|
99 |
+
| 2.398 | 0.15 | 450 | 1.6444 |
|
100 |
+
| 1.3195 | 0.16 | 460 | 1.6445 |
|
101 |
+
| 1.4008 | 0.16 | 470 | 1.6407 |
|
102 |
+
| 1.6925 | 0.16 | 480 | 1.6380 |
|
103 |
+
| 1.8432 | 0.17 | 490 | 1.6396 |
|
104 |
+
| 2.5103 | 0.17 | 500 | 1.6422 |
|
105 |
+
|
106 |
+
|
107 |
+
### Framework versions
|
108 |
+
|
109 |
+
- PEFT 0.10.0
|
110 |
+
- Transformers 4.39.1
|
111 |
+
- Pytorch 2.2.1+cu121
|
112 |
+
- Datasets 2.18.0
|
113 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
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": 16,
|
14 |
+
"lora_dropout": 0.1,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 64,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"v_proj",
|
24 |
+
"q_proj"
|
25 |
+
],
|
26 |
+
"task_type": "CAUSAL_LM",
|
27 |
+
"use_dora": false,
|
28 |
+
"use_rslora": false
|
29 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2ebe45d9e47893a884b73aa6d878b24829c68dd02843f9877ae359af4f446f31
|
3 |
+
size 109069176
|
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": "</s>",
|
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43863effd625af264afb55bbe9e2cde9ad142c5b2686dd57ffd4c9a1aac9b502
|
3 |
+
size 4920
|