Upload folder using huggingface_hub
Browse files- README.md +59 -0
- adapter_config.json +29 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +4 -0
- all_results.json +7 -0
- special_tokens_map.json +30 -0
- tokenizer.model +3 -0
- tokenizer_config.json +62 -0
- train_results.json +7 -0
- trainer_log.jsonl +4 -0
- trainer_state.json +63 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- llama-factory
|
6 |
+
- lora
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: MediaTek-Research/Breeze-7B-Instruct-v1_0
|
9 |
+
model-index:
|
10 |
+
- name: train_2024-05-03-06-11-08
|
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 |
+
# train_2024-05-03-06-11-08
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [MediaTek-Research/Breeze-7B-Instruct-v1_0](https://huggingface.co/MediaTek-Research/Breeze-7B-Instruct-v1_0) on the docker_NL dataset.
|
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: 5e-05
|
39 |
+
- train_batch_size: 16
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 8
|
43 |
+
- total_train_batch_size: 128
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- num_epochs: 1.0
|
47 |
+
- mixed_precision_training: Native AMP
|
48 |
+
|
49 |
+
### Training results
|
50 |
+
|
51 |
+
|
52 |
+
|
53 |
+
### Framework versions
|
54 |
+
|
55 |
+
- PEFT 0.10.0
|
56 |
+
- Transformers 4.41.0.dev0
|
57 |
+
- Pytorch 2.1.0+cu121
|
58 |
+
- Datasets 2.19.0
|
59 |
+
- Tokenizers 0.19.1
|
adapter_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "MediaTek-Research/Breeze-7B-Instruct-v1_0",
|
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": 8,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"v_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 sha256:6e2fbfb2fb610baa2d235961b84c091ff83f84ac86d44ea50e6f345eea4ce2ef
|
3 |
+
size 13648432
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<EOD>": 61873,
|
3 |
+
"<PAD>": 61874
|
4 |
+
}
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9536423841059603,
|
3 |
+
"train_loss": 0.8629565901226468,
|
4 |
+
"train_runtime": 640.3959,
|
5 |
+
"train_samples_per_second": 3.771,
|
6 |
+
"train_steps_per_second": 0.028
|
7 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9298e56c094f0d30431b0e52ad53287f0cadc99ac8ca17cc2144b0eb4753f130
|
3 |
+
size 911034
|
tokenizer_config.json
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": true,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
},
|
30 |
+
"61873": {
|
31 |
+
"content": "<EOD>",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false,
|
36 |
+
"special": true
|
37 |
+
},
|
38 |
+
"61874": {
|
39 |
+
"content": "<PAD>",
|
40 |
+
"lstrip": false,
|
41 |
+
"normalized": false,
|
42 |
+
"rstrip": false,
|
43 |
+
"single_word": false,
|
44 |
+
"special": true
|
45 |
+
}
|
46 |
+
},
|
47 |
+
"bos_token": "<s>",
|
48 |
+
"chat_template": "{% set system_message = 'You are a helpful AI assistant built by MediaTek Research. The user you are helping speaks Traditional Chinese and comes from Taiwan.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<s>' + system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '[INST] ' + content + ' [/INST] ' }}{% elif message['role'] == 'assistant' %}{{ content }}{% endif %}{% endfor %}",
|
49 |
+
"clean_up_tokenization_spaces": false,
|
50 |
+
"eos_token": "</s>",
|
51 |
+
"legacy": true,
|
52 |
+
"model_max_length": 1000000000000000019884624838656,
|
53 |
+
"pad_token": "</s>",
|
54 |
+
"padding_side": "right",
|
55 |
+
"sp_model_kwargs": {},
|
56 |
+
"spaces_between_special_tokens": false,
|
57 |
+
"split_special_tokens": false,
|
58 |
+
"tokenizer_class": "LlamaTokenizer",
|
59 |
+
"unk_token": "<unk>",
|
60 |
+
"use_default_system_prompt": false,
|
61 |
+
"use_fast": true
|
62 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.9536423841059603,
|
3 |
+
"train_loss": 0.8629565901226468,
|
4 |
+
"train_runtime": 640.3959,
|
5 |
+
"train_samples_per_second": 3.771,
|
6 |
+
"train_steps_per_second": 0.028
|
7 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 5, "total_steps": 18, "loss": 1.2805, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 4.1069690242163484e-05, "epoch": 0.26490066225165565, "percentage": 27.78, "elapsed_time": "0:02:56", "remaining_time": "0:07:38"}
|
2 |
+
{"current_steps": 10, "total_steps": 18, "loss": 0.8658, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 2.0658795558326743e-05, "epoch": 0.5298013245033113, "percentage": 55.56, "elapsed_time": "0:05:52", "remaining_time": "0:04:41"}
|
3 |
+
{"current_steps": 15, "total_steps": 18, "loss": 0.6177, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": 3.3493649053890326e-06, "epoch": 0.7947019867549668, "percentage": 83.33, "elapsed_time": "0:08:50", "remaining_time": "0:01:46"}
|
4 |
+
{"current_steps": 18, "total_steps": 18, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "accuracy": null, "learning_rate": null, "epoch": 0.9536423841059603, "percentage": 100.0, "elapsed_time": "0:10:40", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9536423841059603,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 18,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.26490066225165565,
|
13 |
+
"grad_norm": 4.038422107696533,
|
14 |
+
"learning_rate": 4.1069690242163484e-05,
|
15 |
+
"loss": 1.2805,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.5298013245033113,
|
20 |
+
"grad_norm": 4.315277576446533,
|
21 |
+
"learning_rate": 2.0658795558326743e-05,
|
22 |
+
"loss": 0.8658,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.7947019867549668,
|
27 |
+
"grad_norm": 4.228354454040527,
|
28 |
+
"learning_rate": 3.3493649053890326e-06,
|
29 |
+
"loss": 0.6177,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.9536423841059603,
|
34 |
+
"step": 18,
|
35 |
+
"total_flos": 1.039869065822208e+16,
|
36 |
+
"train_loss": 0.8629565901226468,
|
37 |
+
"train_runtime": 640.3959,
|
38 |
+
"train_samples_per_second": 3.771,
|
39 |
+
"train_steps_per_second": 0.028
|
40 |
+
}
|
41 |
+
],
|
42 |
+
"logging_steps": 5,
|
43 |
+
"max_steps": 18,
|
44 |
+
"num_input_tokens_seen": 0,
|
45 |
+
"num_train_epochs": 1,
|
46 |
+
"save_steps": 100,
|
47 |
+
"stateful_callbacks": {
|
48 |
+
"TrainerControl": {
|
49 |
+
"args": {
|
50 |
+
"should_epoch_stop": false,
|
51 |
+
"should_evaluate": false,
|
52 |
+
"should_log": false,
|
53 |
+
"should_save": false,
|
54 |
+
"should_training_stop": false
|
55 |
+
},
|
56 |
+
"attributes": {}
|
57 |
+
}
|
58 |
+
},
|
59 |
+
"total_flos": 1.039869065822208e+16,
|
60 |
+
"train_batch_size": 16,
|
61 |
+
"trial_name": null,
|
62 |
+
"trial_params": null
|
63 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea7c932516ca79a8d77640ac79deba41fd4efd5f54cc9e369f4472b5ca883493
|
3 |
+
size 5304
|