eryk-mazus
commited on
Commit
•
68199bd
1
Parent(s):
ec5ce3f
Upload 7 files
Browse files- README.md +219 -18
- config.json +28 -0
- generation_config.json +6 -0
- pytorch_model-001.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +41 -0
README.md
CHANGED
@@ -1,29 +1,230 @@
|
|
1 |
---
|
2 |
-
|
3 |
-
|
4 |
-
-
|
5 |
-
-
|
6 |
-
|
7 |
-
|
8 |
-
- en
|
9 |
-
pipeline_tag: text-generation
|
10 |
---
|
11 |
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
|
14 |
-
|
15 |
|
|
|
16 |
|
17 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
18 |
|
19 |
-
|
20 |
|
21 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
|
23 |
-
...
|
24 |
|
25 |
-
|
26 |
|
27 |
-
|
28 |
-
|
29 |
-
|
|
|
|
1 |
---
|
2 |
+
base_model: eryk-mazus/tinyllama-with-custom-tokenizer
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
model-index:
|
6 |
+
- name: workspace/tmp/
|
7 |
+
results: []
|
|
|
|
|
8 |
---
|
9 |
|
10 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
11 |
+
should probably proofread and complete it, then remove this comment. -->
|
12 |
+
|
13 |
+
[<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)
|
14 |
+
<details><summary>See axolotl config</summary>
|
15 |
+
|
16 |
+
axolotl version: `0.3.0`
|
17 |
+
```yaml
|
18 |
+
base_model: eryk-mazus/tinyllama-with-custom-tokenizer
|
19 |
+
|
20 |
+
model_type: LlamaForCausalLM
|
21 |
+
tokenizer_type: AutoTokenizer
|
22 |
+
is_llama_derived_model: true
|
23 |
+
|
24 |
+
load_in_8bit: false
|
25 |
+
load_in_4bit: false
|
26 |
+
strict: false
|
27 |
+
|
28 |
+
datasets:
|
29 |
+
- path: eryk-mazus/polka-pretrain-en-pl-v1
|
30 |
+
type: completion # format from earlier
|
31 |
+
field: text # Optional[str] default: text, field to use for completion data
|
32 |
+
|
33 |
+
dataset_prepared_path:
|
34 |
+
val_set_size: 0.05
|
35 |
+
output_dir: /workspace/tmp/
|
36 |
+
|
37 |
+
sequence_len: 2048
|
38 |
+
sample_packing: false
|
39 |
+
|
40 |
+
adapter:
|
41 |
+
lora_model_dir:
|
42 |
+
lora_r: 32
|
43 |
+
lora_alpha: 16
|
44 |
+
lora_dropout: 0.05
|
45 |
+
lora_target_linear: true
|
46 |
+
lora_fan_in_fan_out:
|
47 |
+
|
48 |
+
wandb_project: polka
|
49 |
+
wandb_entity:
|
50 |
+
wandb_watch:
|
51 |
+
wandb_name:
|
52 |
+
wandb_log_model:
|
53 |
+
|
54 |
+
gradient_accumulation_steps: 2
|
55 |
+
micro_batch_size: 4
|
56 |
+
num_epochs: 1
|
57 |
+
lr_scheduler:
|
58 |
+
learning_rate: 0.00005
|
59 |
+
|
60 |
+
optimizer: adamw_torch
|
61 |
+
adam_beta1: 0.9
|
62 |
+
adam_beta2: 0.95
|
63 |
+
adam_epsilon: 0.00001
|
64 |
+
max_grad_norm: 1.0
|
65 |
+
|
66 |
+
train_on_inputs: false
|
67 |
+
group_by_length: false
|
68 |
+
bf16: true
|
69 |
+
fp16: false
|
70 |
+
tf32: false
|
71 |
+
|
72 |
+
warmup_steps: 0
|
73 |
+
gradient_checkpointing: true
|
74 |
+
early_stopping_patience:
|
75 |
+
resume_from_checkpoint:
|
76 |
+
local_rank:
|
77 |
+
logging_steps: 1
|
78 |
+
xformers_attention:
|
79 |
+
flash_attention: true
|
80 |
+
|
81 |
+
eval_steps: 1000
|
82 |
+
save_steps: 1000
|
83 |
+
save_total_limit: 2
|
84 |
+
|
85 |
+
debug:
|
86 |
+
deepspeed:
|
87 |
+
fsdp:
|
88 |
+
fsdp_config:
|
89 |
+
special_tokens:
|
90 |
+
bos_token: "<s>"
|
91 |
+
eos_token: "</s>"
|
92 |
+
unk_token: "<unk>"
|
93 |
+
|
94 |
+
```
|
95 |
+
|
96 |
+
</details><br>
|
97 |
+
|
98 |
+
# workspace/tmp/
|
99 |
+
|
100 |
+
This model is a fine-tuned version of [eryk-mazus/tinyllama-with-custom-tokenizer](https://huggingface.co/eryk-mazus/tinyllama-with-custom-tokenizer) on the None dataset.
|
101 |
+
It achieves the following results on the evaluation set:
|
102 |
+
- Loss: 1.8795
|
103 |
+
|
104 |
+
## Model description
|
105 |
+
|
106 |
+
More information needed
|
107 |
+
|
108 |
+
## Intended uses & limitations
|
109 |
+
|
110 |
+
More information needed
|
111 |
+
|
112 |
+
## Training and evaluation data
|
113 |
+
|
114 |
+
More information needed
|
115 |
|
116 |
+
## Training procedure
|
117 |
|
118 |
+
### Training hyperparameters
|
119 |
|
120 |
+
The following hyperparameters were used during training:
|
121 |
+
- learning_rate: 5e-05
|
122 |
+
- train_batch_size: 4
|
123 |
+
- eval_batch_size: 4
|
124 |
+
- seed: 42
|
125 |
+
- distributed_type: multi-GPU
|
126 |
+
- num_devices: 8
|
127 |
+
- gradient_accumulation_steps: 2
|
128 |
+
- total_train_batch_size: 64
|
129 |
+
- total_eval_batch_size: 32
|
130 |
+
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
|
131 |
+
- lr_scheduler_type: cosine
|
132 |
+
- num_epochs: 1
|
133 |
|
134 |
+
### Training results
|
135 |
|
136 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
137 |
+
|:-------------:|:-----:|:-----:|:---------------:|
|
138 |
+
| 3.0469 | 0.01 | 1000 | 3.0497 |
|
139 |
+
| 2.664 | 0.02 | 2000 | 2.6586 |
|
140 |
+
| 2.5018 | 0.04 | 3000 | 2.4944 |
|
141 |
+
| 2.5955 | 0.05 | 4000 | 2.3988 |
|
142 |
+
| 2.2783 | 0.06 | 5000 | 2.3338 |
|
143 |
+
| 2.3171 | 0.07 | 6000 | 2.2852 |
|
144 |
+
| 2.189 | 0.08 | 7000 | 2.2459 |
|
145 |
+
| 2.3594 | 0.09 | 8000 | 2.2153 |
|
146 |
+
| 2.1882 | 0.11 | 9000 | 2.1882 |
|
147 |
+
| 2.2699 | 0.12 | 10000 | 2.1659 |
|
148 |
+
| 2.1273 | 0.13 | 11000 | 2.1469 |
|
149 |
+
| 2.1041 | 0.14 | 12000 | 2.1291 |
|
150 |
+
| 2.1698 | 0.15 | 13000 | 2.1138 |
|
151 |
+
| 2.2126 | 0.16 | 14000 | 2.1004 |
|
152 |
+
| 2.1065 | 0.18 | 15000 | 2.0886 |
|
153 |
+
| 2.0589 | 0.19 | 16000 | 2.0764 |
|
154 |
+
| 2.0537 | 0.2 | 17000 | 2.0663 |
|
155 |
+
| 1.9746 | 0.21 | 18000 | 2.0569 |
|
156 |
+
| 2.2128 | 0.22 | 19000 | 2.0477 |
|
157 |
+
| 2.1342 | 0.23 | 20000 | 2.0393 |
|
158 |
+
| 2.0643 | 0.25 | 21000 | 2.0312 |
|
159 |
+
| 2.2776 | 0.26 | 22000 | 2.0240 |
|
160 |
+
| 1.94 | 0.27 | 23000 | 2.0173 |
|
161 |
+
| 1.8249 | 0.28 | 24000 | 2.0111 |
|
162 |
+
| 1.966 | 0.29 | 25000 | 2.0049 |
|
163 |
+
| 1.9351 | 0.31 | 26000 | 1.9994 |
|
164 |
+
| 1.9563 | 0.32 | 27000 | 1.9947 |
|
165 |
+
| 1.9496 | 0.33 | 28000 | 1.9878 |
|
166 |
+
| 2.0127 | 0.34 | 29000 | 1.9835 |
|
167 |
+
| 2.0043 | 0.35 | 30000 | 1.9794 |
|
168 |
+
| 2.0227 | 0.36 | 31000 | 1.9748 |
|
169 |
+
| 1.9308 | 0.38 | 32000 | 1.9704 |
|
170 |
+
| 1.9183 | 0.39 | 33000 | 1.9655 |
|
171 |
+
| 1.9919 | 0.4 | 34000 | 1.9620 |
|
172 |
+
| 1.9351 | 0.41 | 35000 | 1.9580 |
|
173 |
+
| 1.9103 | 0.42 | 36000 | 1.9537 |
|
174 |
+
| 1.7521 | 0.43 | 37000 | 1.9512 |
|
175 |
+
| 1.9567 | 0.45 | 38000 | 1.9454 |
|
176 |
+
| 2.022 | 0.46 | 39000 | 1.9426 |
|
177 |
+
| 1.8526 | 0.47 | 40000 | 1.9398 |
|
178 |
+
| 1.8912 | 0.48 | 41000 | 1.9370 |
|
179 |
+
| 2.0546 | 0.49 | 42000 | 1.9334 |
|
180 |
+
| 2.0607 | 0.5 | 43000 | 1.9308 |
|
181 |
+
| 2.0078 | 0.52 | 44000 | 1.9279 |
|
182 |
+
| 1.889 | 0.53 | 45000 | 1.9253 |
|
183 |
+
| 1.8587 | 0.54 | 46000 | 1.9222 |
|
184 |
+
| 1.8571 | 0.55 | 47000 | 1.9199 |
|
185 |
+
| 1.8806 | 0.56 | 48000 | 1.9178 |
|
186 |
+
| 1.8483 | 0.58 | 49000 | 1.9150 |
|
187 |
+
| 1.7862 | 0.59 | 50000 | 1.9130 |
|
188 |
+
| 1.8989 | 0.6 | 51000 | 1.9102 |
|
189 |
+
| 1.9389 | 0.61 | 52000 | 1.9083 |
|
190 |
+
| 1.9301 | 0.62 | 53000 | 1.9065 |
|
191 |
+
| 1.9522 | 0.63 | 54000 | 1.9046 |
|
192 |
+
| 1.883 | 0.65 | 55000 | 1.9027 |
|
193 |
+
| 1.9647 | 0.66 | 56000 | 1.9002 |
|
194 |
+
| 1.9284 | 0.67 | 57000 | 1.8988 |
|
195 |
+
| 1.8836 | 0.68 | 58000 | 1.8974 |
|
196 |
+
| 1.8472 | 0.69 | 59000 | 1.8956 |
|
197 |
+
| 2.1232 | 0.7 | 60000 | 1.8945 |
|
198 |
+
| 1.8571 | 0.72 | 61000 | 1.8933 |
|
199 |
+
| 1.8043 | 0.73 | 62000 | 1.8918 |
|
200 |
+
| 1.9468 | 0.74 | 63000 | 1.8906 |
|
201 |
+
| 1.9173 | 0.75 | 64000 | 1.8896 |
|
202 |
+
| 1.7762 | 0.76 | 65000 | 1.8880 |
|
203 |
+
| 2.032 | 0.77 | 66000 | 1.8876 |
|
204 |
+
| 1.9362 | 0.79 | 67000 | 1.8867 |
|
205 |
+
| 1.8308 | 0.8 | 68000 | 1.8854 |
|
206 |
+
| 1.9289 | 0.81 | 69000 | 1.8847 |
|
207 |
+
| 1.9467 | 0.82 | 70000 | 1.8841 |
|
208 |
+
| 1.8798 | 0.83 | 71000 | 1.8835 |
|
209 |
+
| 1.8868 | 0.84 | 72000 | 1.8828 |
|
210 |
+
| 1.8905 | 0.86 | 73000 | 1.8820 |
|
211 |
+
| 1.9508 | 0.87 | 74000 | 1.8816 |
|
212 |
+
| 1.7983 | 0.88 | 75000 | 1.8813 |
|
213 |
+
| 1.7693 | 0.89 | 76000 | 1.8806 |
|
214 |
+
| 1.7371 | 0.9 | 77000 | 1.8804 |
|
215 |
+
| 1.8705 | 0.92 | 78000 | 1.8802 |
|
216 |
+
| 1.8707 | 0.93 | 79000 | 1.8799 |
|
217 |
+
| 1.9113 | 0.94 | 80000 | 1.8799 |
|
218 |
+
| 2.1314 | 0.95 | 81000 | 1.8797 |
|
219 |
+
| 1.9132 | 0.96 | 82000 | 1.8795 |
|
220 |
+
| 2.0349 | 0.97 | 83000 | 1.8796 |
|
221 |
+
| 1.7939 | 0.99 | 84000 | 1.8795 |
|
222 |
+
| 1.8357 | 1.0 | 85000 | 1.8795 |
|
223 |
|
|
|
224 |
|
225 |
+
### Framework versions
|
226 |
|
227 |
+
- Transformers 4.36.2
|
228 |
+
- Pytorch 2.1.2+cu121
|
229 |
+
- Datasets 2.16.1
|
230 |
+
- Tokenizers 0.15.0
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "eryk-mazus/tinyllama-with-custom-tokenizer",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 2048,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 5632,
|
14 |
+
"max_position_embeddings": 2048,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_hidden_layers": 22,
|
18 |
+
"num_key_value_heads": 4,
|
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": "4.36.2",
|
26 |
+
"use_cache": false,
|
27 |
+
"vocab_size": 43904
|
28 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.36.2"
|
6 |
+
}
|
pytorch_model-001.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aa585b9221266e354bf136da9aab42bc6d22e1ba7fa6f295e910e8a48adf5cb3
|
3 |
+
size 2297641916
|
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_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": 1000000000000000019884624838656,
|
35 |
+
"pad_token": "</s>",
|
36 |
+
"padding_side": "right",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"tokenizer_class": "LlamaTokenizer",
|
39 |
+
"unk_token": "<unk>",
|
40 |
+
"use_default_system_prompt": false
|
41 |
+
}
|