Upload folder using huggingface_hub
Browse files- README.md +88 -0
- adapter_config.json +28 -0
- adapter_model.bin +3 -0
- added_tokens.json +5 -0
- config.json +40 -0
- special_tokens_map.json +6 -0
- tokenizer.model +3 -0
- tokenizer_config.json +45 -0
README.md
ADDED
@@ -0,0 +1,88 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
model-index:
|
5 |
+
- name: lora-out
|
6 |
+
results: []
|
7 |
+
---
|
8 |
+
|
9 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
+
should probably proofread and complete it, then remove this comment. -->
|
11 |
+
|
12 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
13 |
+
# lora-out
|
14 |
+
|
15 |
+
This model was trained from scratch on the None dataset.
|
16 |
+
It achieves the following results on the evaluation set:
|
17 |
+
- Loss: 1.2973
|
18 |
+
|
19 |
+
## Model description
|
20 |
+
|
21 |
+
More information needed
|
22 |
+
|
23 |
+
## Intended uses & limitations
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Training and evaluation data
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training procedure
|
32 |
+
|
33 |
+
### Training hyperparameters
|
34 |
+
|
35 |
+
The following hyperparameters were used during training:
|
36 |
+
- learning_rate: 0.00065
|
37 |
+
- train_batch_size: 2
|
38 |
+
- eval_batch_size: 2
|
39 |
+
- seed: 42
|
40 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
41 |
+
- lr_scheduler_type: constant
|
42 |
+
- lr_scheduler_warmup_steps: 10
|
43 |
+
- num_epochs: 1
|
44 |
+
|
45 |
+
### Training results
|
46 |
+
|
47 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 1.5404 | 0.03 | 20 | 1.2764 |
|
50 |
+
| 1.4523 | 0.06 | 40 | 1.2571 |
|
51 |
+
| 1.5608 | 0.09 | 60 | 1.2465 |
|
52 |
+
| 1.5921 | 0.12 | 80 | 1.2575 |
|
53 |
+
| 1.6043 | 0.15 | 100 | 1.2432 |
|
54 |
+
| 1.5496 | 0.18 | 120 | 1.2504 |
|
55 |
+
| 1.348 | 0.21 | 140 | 1.2452 |
|
56 |
+
| 1.4638 | 0.24 | 160 | 1.2661 |
|
57 |
+
| 1.5733 | 0.27 | 180 | 1.2548 |
|
58 |
+
| 1.5397 | 0.3 | 200 | 1.2674 |
|
59 |
+
| 1.6154 | 0.33 | 220 | 1.2626 |
|
60 |
+
| 1.5058 | 0.36 | 240 | 1.2672 |
|
61 |
+
| 1.3974 | 0.4 | 260 | 1.2659 |
|
62 |
+
| 1.6654 | 0.43 | 280 | 1.2648 |
|
63 |
+
| 1.8051 | 0.46 | 300 | 1.2585 |
|
64 |
+
| 1.7487 | 0.49 | 320 | 1.2736 |
|
65 |
+
| 1.3612 | 0.52 | 340 | 1.2717 |
|
66 |
+
| 1.5048 | 0.55 | 360 | 1.2809 |
|
67 |
+
| 1.7134 | 0.58 | 380 | 1.2885 |
|
68 |
+
| 1.5524 | 0.61 | 400 | 1.2805 |
|
69 |
+
| 1.3705 | 0.64 | 420 | 1.2860 |
|
70 |
+
| 1.4335 | 0.67 | 440 | 1.2896 |
|
71 |
+
| 1.3642 | 0.7 | 460 | 1.2911 |
|
72 |
+
| 1.6546 | 0.73 | 480 | 1.2888 |
|
73 |
+
| 1.5345 | 0.76 | 500 | 1.2973 |
|
74 |
+
| 1.5968 | 0.79 | 520 | 1.2885 |
|
75 |
+
| 1.5694 | 0.82 | 540 | 1.2939 |
|
76 |
+
| 1.5474 | 0.85 | 560 | 1.2892 |
|
77 |
+
| 1.6981 | 0.88 | 580 | 1.2949 |
|
78 |
+
| 1.5451 | 0.91 | 600 | 1.2886 |
|
79 |
+
| 1.5845 | 0.94 | 620 | 1.2941 |
|
80 |
+
| 1.5143 | 0.97 | 640 | 1.2973 |
|
81 |
+
|
82 |
+
|
83 |
+
### Framework versions
|
84 |
+
|
85 |
+
- Transformers 4.34.0.dev0
|
86 |
+
- Pytorch 2.0.1+cu118
|
87 |
+
- Datasets 2.14.5
|
88 |
+
- Tokenizers 0.14.0
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": null,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"lora_alpha": 16,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 256,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"gate_proj",
|
20 |
+
"k_proj",
|
21 |
+
"up_proj",
|
22 |
+
"q_proj",
|
23 |
+
"v_proj",
|
24 |
+
"down_proj",
|
25 |
+
"o_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fda1086566badda7ec0876d5d8d9d016416fca1ca16e9d778397fc619aa9282e
|
3 |
+
size 2684516749
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"</s>": 2,
|
3 |
+
"<s>": 1,
|
4 |
+
"<unk>": 0
|
5 |
+
}
|
config.json
ADDED
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "./mistralai_Mistral-7B-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"pretraining_tp": 1,
|
19 |
+
"quantization_config": {
|
20 |
+
"bnb_4bit_compute_dtype": "float32",
|
21 |
+
"bnb_4bit_quant_type": "fp4",
|
22 |
+
"bnb_4bit_use_double_quant": false,
|
23 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
24 |
+
"llm_int8_has_fp16_weight": false,
|
25 |
+
"llm_int8_skip_modules": null,
|
26 |
+
"llm_int8_threshold": 6.0,
|
27 |
+
"load_in_4bit": false,
|
28 |
+
"load_in_8bit": true,
|
29 |
+
"quant_method": "bitsandbytes"
|
30 |
+
},
|
31 |
+
"rms_norm_eps": 1e-05,
|
32 |
+
"rope_scaling": null,
|
33 |
+
"rope_theta": 10000.0,
|
34 |
+
"sliding_window": 4096,
|
35 |
+
"tie_word_embeddings": false,
|
36 |
+
"torch_dtype": "bfloat16",
|
37 |
+
"transformers_version": "4.34.0.dev0",
|
38 |
+
"use_cache": false,
|
39 |
+
"vocab_size": 32000
|
40 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"pad_token": "</s>",
|
5 |
+
"unk_token": "<unk>"
|
6 |
+
}
|
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 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": true,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": true,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": true,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": true,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": true,
|
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": null,
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"tokenizer_file": "./mistralai_Mistral-7B-v0.1/tokenizer.json",
|
41 |
+
"trust_remote_code": false,
|
42 |
+
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": true,
|
44 |
+
"use_fast": true
|
45 |
+
}
|