CaptainLazarus
commited on
Commit
•
f0b400d
1
Parent(s):
70b5cfe
Initial
Browse filesburrnesha. ask token
- README.md +75 -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
CHANGED
@@ -1,3 +1,78 @@
|
|
1 |
---
|
2 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: apache-2.0
|
3 |
+
base_model: openlm-research/open_llama_3b_v2
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: qlora-out
|
8 |
+
results: []
|
9 |
---
|
10 |
+
|
11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
12 |
+
should probably proofread and complete it, then remove this comment. -->
|
13 |
+
|
14 |
+
[<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)
|
15 |
+
# qlora-out
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [openlm-research/open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.9901
|
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: 0.0002
|
39 |
+
- train_batch_size: 2
|
40 |
+
- eval_batch_size: 2
|
41 |
+
- seed: 42
|
42 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
+
- lr_scheduler_type: cosine
|
44 |
+
- lr_scheduler_warmup_steps: 20
|
45 |
+
- num_epochs: 1
|
46 |
+
|
47 |
+
### Training results
|
48 |
+
|
49 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
50 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
51 |
+
| 1.419 | 0.0 | 1 | 1.6021 |
|
52 |
+
| 1.1683 | 0.05 | 282 | 1.1232 |
|
53 |
+
| 1.0823 | 0.1 | 564 | 1.0956 |
|
54 |
+
| 0.9881 | 0.15 | 846 | 1.0733 |
|
55 |
+
| 0.5434 | 0.2 | 1128 | 1.0653 |
|
56 |
+
| 1.0669 | 0.25 | 1410 | 1.0520 |
|
57 |
+
| 1.2484 | 0.3 | 1692 | 1.0401 |
|
58 |
+
| 1.3012 | 0.35 | 1974 | 1.0445 |
|
59 |
+
| 1.2746 | 0.4 | 2256 | 1.0243 |
|
60 |
+
| 1.2341 | 0.45 | 2538 | 1.0230 |
|
61 |
+
| 1.0461 | 0.5 | 2820 | 1.0148 |
|
62 |
+
| 1.0813 | 0.55 | 3102 | 1.0070 |
|
63 |
+
| 1.1375 | 0.6 | 3384 | 1.0061 |
|
64 |
+
| 1.0052 | 0.65 | 3666 | 1.0007 |
|
65 |
+
| 1.171 | 0.7 | 3948 | 0.9966 |
|
66 |
+
| 1.0764 | 0.75 | 4230 | 0.9948 |
|
67 |
+
| 1.146 | 0.8 | 4512 | 0.9924 |
|
68 |
+
| 1.2213 | 0.85 | 4794 | 0.9918 |
|
69 |
+
| 1.1138 | 0.9 | 5076 | 0.9907 |
|
70 |
+
| 1.0635 | 0.95 | 5358 | 0.9901 |
|
71 |
+
|
72 |
+
|
73 |
+
### Framework versions
|
74 |
+
|
75 |
+
- Transformers 4.35.0.dev0
|
76 |
+
- Pytorch 2.0.1+cu118
|
77 |
+
- Datasets 2.14.5
|
78 |
+
- Tokenizers 0.14.1
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "openlm-research/open_llama_3b_v2",
|
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": 32,
|
12 |
+
"lora_dropout": 0.05,
|
13 |
+
"modules_to_save": null,
|
14 |
+
"peft_type": "LORA",
|
15 |
+
"r": 8,
|
16 |
+
"rank_pattern": {},
|
17 |
+
"revision": null,
|
18 |
+
"target_modules": [
|
19 |
+
"up_proj",
|
20 |
+
"o_proj",
|
21 |
+
"down_proj",
|
22 |
+
"gate_proj",
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"q_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 sha256:625224832803048a1f79e960aac383be3e1649c7eb98e6bce136000d3c61ddb7
|
3 |
+
size 50982397
|
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": "openlm-research/open_llama_3b_v2",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 3200,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 8640,
|
13 |
+
"max_position_embeddings": 2048,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 26,
|
17 |
+
"num_key_value_heads": 32,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"quantization_config": {
|
21 |
+
"bnb_4bit_compute_dtype": "float16",
|
22 |
+
"bnb_4bit_quant_type": "nf4",
|
23 |
+
"bnb_4bit_use_double_quant": true,
|
24 |
+
"llm_int8_enable_fp32_cpu_offload": false,
|
25 |
+
"llm_int8_has_fp16_weight": false,
|
26 |
+
"llm_int8_skip_modules": null,
|
27 |
+
"llm_int8_threshold": 6.0,
|
28 |
+
"load_in_4bit": true,
|
29 |
+
"load_in_8bit": false,
|
30 |
+
"quant_method": "bitsandbytes"
|
31 |
+
},
|
32 |
+
"rms_norm_eps": 1e-06,
|
33 |
+
"rope_scaling": null,
|
34 |
+
"rope_theta": 10000.0,
|
35 |
+
"tie_word_embeddings": false,
|
36 |
+
"torch_dtype": "float16",
|
37 |
+
"transformers_version": "4.35.0.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 sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
|
3 |
+
size 511574
|
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": 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": 2048,
|
36 |
+
"pad_token": "</s>",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"tokenizer_file": null,
|
41 |
+
"trust_remote_code": false,
|
42 |
+
"unk_token": "<unk>",
|
43 |
+
"use_default_system_prompt": true,
|
44 |
+
"use_fast": true
|
45 |
+
}
|