Upload 7 files
Browse files- README.md +98 -0
- config.json +28 -0
- generation_config.json +7 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
README.md
ADDED
@@ -0,0 +1,98 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: princeton-nlp/Sheared-LLaMA-1.3B
|
4 |
+
tags:
|
5 |
+
- generated_from_trainer
|
6 |
+
model-index:
|
7 |
+
- name: 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 |
+
# out
|
16 |
+
|
17 |
+
This model is a fine-tuned version of [princeton-nlp/Sheared-LLaMA-1.3B](https://huggingface.co/princeton-nlp/Sheared-LLaMA-1.3B) on the None dataset.
|
18 |
+
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 1.5764
|
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: 2.5e-05
|
39 |
+
- train_batch_size: 3
|
40 |
+
- eval_batch_size: 3
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 3
|
43 |
+
- total_train_batch_size: 9
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: constant
|
46 |
+
- lr_scheduler_warmup_steps: 300
|
47 |
+
- num_epochs: 1
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 2.0341 | 0.03 | 30 | 1.7322 |
|
54 |
+
| 1.7952 | 0.05 | 60 | 1.7122 |
|
55 |
+
| 1.8476 | 0.08 | 90 | 1.7011 |
|
56 |
+
| 2.1762 | 0.1 | 120 | 1.6919 |
|
57 |
+
| 2.0459 | 0.13 | 150 | 1.6838 |
|
58 |
+
| 1.7417 | 0.16 | 180 | 1.6761 |
|
59 |
+
| 1.7508 | 0.18 | 210 | 1.6685 |
|
60 |
+
| 1.8539 | 0.21 | 240 | 1.6612 |
|
61 |
+
| 1.7672 | 0.24 | 270 | 1.6559 |
|
62 |
+
| 1.7327 | 0.26 | 300 | 1.6521 |
|
63 |
+
| 1.9346 | 0.29 | 330 | 1.6458 |
|
64 |
+
| 1.8972 | 0.31 | 360 | 1.6432 |
|
65 |
+
| 1.545 | 0.34 | 390 | 1.6394 |
|
66 |
+
| 1.6737 | 0.37 | 420 | 1.6351 |
|
67 |
+
| 1.9233 | 0.39 | 450 | 1.6305 |
|
68 |
+
| 1.6822 | 0.42 | 480 | 1.6274 |
|
69 |
+
| 1.3781 | 0.44 | 510 | 1.6243 |
|
70 |
+
| 1.8232 | 0.47 | 540 | 1.6209 |
|
71 |
+
| 1.6995 | 0.5 | 570 | 1.6178 |
|
72 |
+
| 1.9164 | 0.52 | 600 | 1.6145 |
|
73 |
+
| 1.8104 | 0.55 | 630 | 1.6116 |
|
74 |
+
| 1.9563 | 0.58 | 660 | 1.6098 |
|
75 |
+
| 1.9536 | 0.6 | 690 | 1.6063 |
|
76 |
+
| 1.9269 | 0.63 | 720 | 1.6043 |
|
77 |
+
| 1.6234 | 0.65 | 750 | 1.6026 |
|
78 |
+
| 1.7635 | 0.68 | 780 | 1.5994 |
|
79 |
+
| 1.2534 | 0.71 | 810 | 1.5966 |
|
80 |
+
| 1.8849 | 0.73 | 840 | 1.5951 |
|
81 |
+
| 1.8618 | 0.76 | 870 | 1.5925 |
|
82 |
+
| 1.8688 | 0.79 | 900 | 1.5896 |
|
83 |
+
| 1.9419 | 0.81 | 930 | 1.5877 |
|
84 |
+
| 1.637 | 0.84 | 960 | 1.5878 |
|
85 |
+
| 1.4612 | 0.86 | 990 | 1.5848 |
|
86 |
+
| 1.5509 | 0.89 | 1020 | 1.5832 |
|
87 |
+
| 1.706 | 0.92 | 1050 | 1.5816 |
|
88 |
+
| 1.8552 | 0.94 | 1080 | 1.5797 |
|
89 |
+
| 1.7589 | 0.97 | 1110 | 1.5791 |
|
90 |
+
| 1.4988 | 0.99 | 1140 | 1.5764 |
|
91 |
+
|
92 |
+
|
93 |
+
### Framework versions
|
94 |
+
|
95 |
+
- Transformers 4.35.2
|
96 |
+
- Pytorch 2.0.1+cu117
|
97 |
+
- Datasets 2.15.0
|
98 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "princeton-nlp/Sheared-LLaMA-1.3B",
|
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": 2048,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 5504,
|
13 |
+
"max_position_embeddings": 4096,
|
14 |
+
"model_type": "llama",
|
15 |
+
"num_attention_heads": 16,
|
16 |
+
"num_hidden_layers": 24,
|
17 |
+
"num_key_value_heads": 16,
|
18 |
+
"pad_token_id": 0,
|
19 |
+
"pretraining_tp": 1,
|
20 |
+
"rms_norm_eps": 1e-05,
|
21 |
+
"rope_scaling": null,
|
22 |
+
"rope_theta": 10000.0,
|
23 |
+
"tie_word_embeddings": false,
|
24 |
+
"torch_dtype": "bfloat16",
|
25 |
+
"transformers_version": "4.35.2",
|
26 |
+
"use_cache": false,
|
27 |
+
"vocab_size": 32000
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.35.2"
|
7 |
+
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2eae6dc609e085b5f005091644a3edb30afbe41c2d85d5a031a9d9969829484b
|
3 |
+
size 2690915481
|
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.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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
34 |
+
"model_max_length": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "</s>",
|
36 |
+
"sp_model_kwargs": {},
|
37 |
+
"spaces_between_special_tokens": false,
|
38 |
+
"tokenizer_class": "LlamaTokenizer",
|
39 |
+
"trust_remote_code": false,
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false,
|
42 |
+
"use_fast": true
|
43 |
+
}
|