Upload folder using huggingface_hub
Browse files- README.md +58 -0
- adapter_config.json +27 -0
- adapter_model.safetensors +3 -0
- all_results.json +7 -0
- special_tokens_map.json +24 -0
- tokenizer.model +3 -0
- tokenizer_config.json +46 -0
- train_results.json +7 -0
- trainer_log.jsonl +8 -0
- trainer_state.json +79 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: other
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- llama-factory
|
6 |
+
- lora
|
7 |
+
- generated_from_trainer
|
8 |
+
base_model: mistralai/Mistral-7B-Instruct-v0.2
|
9 |
+
model-index:
|
10 |
+
- name: train_2024-02-26-06-49-61
|
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_2024-02-26-06-49-61
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) 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: 0.0002
|
39 |
+
- train_batch_size: 16
|
40 |
+
- eval_batch_size: 8
|
41 |
+
- seed: 42
|
42 |
+
- gradient_accumulation_steps: 4
|
43 |
+
- total_train_batch_size: 64
|
44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
45 |
+
- lr_scheduler_type: cosine
|
46 |
+
- num_epochs: 1.0
|
47 |
+
|
48 |
+
### Training results
|
49 |
+
|
50 |
+
|
51 |
+
|
52 |
+
### Framework versions
|
53 |
+
|
54 |
+
- PEFT 0.8.2
|
55 |
+
- Transformers 4.38.1
|
56 |
+
- Pytorch 2.2.0+cu121
|
57 |
+
- Datasets 2.17.1
|
58 |
+
- Tokenizers 0.15.2
|
adapter_config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.2",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layers_pattern": null,
|
10 |
+
"layers_to_transform": null,
|
11 |
+
"loftq_config": {},
|
12 |
+
"lora_alpha": 16,
|
13 |
+
"lora_dropout": 0.1,
|
14 |
+
"megatron_config": null,
|
15 |
+
"megatron_core": "megatron.core",
|
16 |
+
"modules_to_save": null,
|
17 |
+
"peft_type": "LORA",
|
18 |
+
"r": 8,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"v_proj",
|
23 |
+
"q_proj"
|
24 |
+
],
|
25 |
+
"task_type": "CAUSAL_LM",
|
26 |
+
"use_rslora": false
|
27 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3cd3151bb7c7ce1116954ee0374daa59f7805b534e2d75bc0f524c9fd1a5c3a8
|
3 |
+
size 13648432
|
all_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.98,
|
3 |
+
"train_loss": 0.3938806479847109,
|
4 |
+
"train_runtime": 8367.9218,
|
5 |
+
"train_samples_per_second": 0.289,
|
6 |
+
"train_steps_per_second": 0.004
|
7 |
+
}
|
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
},
|
31 |
+
"additional_special_tokens": [],
|
32 |
+
"bos_token": "<s>",
|
33 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
34 |
+
"clean_up_tokenization_spaces": false,
|
35 |
+
"eos_token": "</s>",
|
36 |
+
"legacy": true,
|
37 |
+
"model_max_length": 1000000000000000019884624838656,
|
38 |
+
"pad_token": "</s>",
|
39 |
+
"padding_side": "right",
|
40 |
+
"sp_model_kwargs": {},
|
41 |
+
"spaces_between_special_tokens": false,
|
42 |
+
"split_special_tokens": false,
|
43 |
+
"tokenizer_class": "LlamaTokenizer",
|
44 |
+
"unk_token": "<unk>",
|
45 |
+
"use_default_system_prompt": false
|
46 |
+
}
|
train_results.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"epoch": 0.98,
|
3 |
+
"train_loss": 0.3938806479847109,
|
4 |
+
"train_runtime": 8367.9218,
|
5 |
+
"train_samples_per_second": 0.289,
|
6 |
+
"train_steps_per_second": 0.004
|
7 |
+
}
|
trainer_log.jsonl
ADDED
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{"current_steps": 5, "total_steps": 37, "loss": 1.8153, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001911228490388136, "epoch": 0.13, "percentage": 13.51, "elapsed_time": "0:21:30", "remaining_time": "2:17:40"}
|
2 |
+
{"current_steps": 10, "total_steps": 37, "loss": 0.3952, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016606747233900815, "epoch": 0.26, "percentage": 27.03, "elapsed_time": "0:43:46", "remaining_time": "1:58:11"}
|
3 |
+
{"current_steps": 15, "total_steps": 37, "loss": 0.2029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012928227712765504, "epoch": 0.4, "percentage": 40.54, "elapsed_time": "1:01:48", "remaining_time": "1:30:39"}
|
4 |
+
{"current_steps": 20, "total_steps": 37, "loss": 0.1657, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.729821802531212e-05, "epoch": 0.53, "percentage": 54.05, "elapsed_time": "1:18:50", "remaining_time": "1:07:00"}
|
5 |
+
{"current_steps": 25, "total_steps": 37, "loss": 0.1042, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.756927164427685e-05, "epoch": 0.66, "percentage": 67.57, "elapsed_time": "1:36:32", "remaining_time": "0:46:20"}
|
6 |
+
{"current_steps": 30, "total_steps": 37, "loss": 0.1004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7149035075615794e-05, "epoch": 0.79, "percentage": 81.08, "elapsed_time": "1:53:48", "remaining_time": "0:26:33"}
|
7 |
+
{"current_steps": 35, "total_steps": 37, "loss": 0.0942, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4384089652291543e-06, "epoch": 0.93, "percentage": 94.59, "elapsed_time": "2:12:01", "remaining_time": "0:07:32"}
|
8 |
+
{"current_steps": 37, "total_steps": 37, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.98, "percentage": 100.0, "elapsed_time": "2:19:27", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.9801324503311258,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 37,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.13,
|
13 |
+
"grad_norm": 5.132448196411133,
|
14 |
+
"learning_rate": 0.0001911228490388136,
|
15 |
+
"loss": 1.8153,
|
16 |
+
"step": 5
|
17 |
+
},
|
18 |
+
{
|
19 |
+
"epoch": 0.26,
|
20 |
+
"grad_norm": 2.215226411819458,
|
21 |
+
"learning_rate": 0.00016606747233900815,
|
22 |
+
"loss": 0.3952,
|
23 |
+
"step": 10
|
24 |
+
},
|
25 |
+
{
|
26 |
+
"epoch": 0.4,
|
27 |
+
"grad_norm": 1.2212655544281006,
|
28 |
+
"learning_rate": 0.00012928227712765504,
|
29 |
+
"loss": 0.2029,
|
30 |
+
"step": 15
|
31 |
+
},
|
32 |
+
{
|
33 |
+
"epoch": 0.53,
|
34 |
+
"grad_norm": 1.6850711107254028,
|
35 |
+
"learning_rate": 8.729821802531212e-05,
|
36 |
+
"loss": 0.1657,
|
37 |
+
"step": 20
|
38 |
+
},
|
39 |
+
{
|
40 |
+
"epoch": 0.66,
|
41 |
+
"grad_norm": 1.355529546737671,
|
42 |
+
"learning_rate": 4.756927164427685e-05,
|
43 |
+
"loss": 0.1042,
|
44 |
+
"step": 25
|
45 |
+
},
|
46 |
+
{
|
47 |
+
"epoch": 0.79,
|
48 |
+
"grad_norm": 0.9691661596298218,
|
49 |
+
"learning_rate": 1.7149035075615794e-05,
|
50 |
+
"loss": 0.1004,
|
51 |
+
"step": 30
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.93,
|
55 |
+
"grad_norm": 0.6373167037963867,
|
56 |
+
"learning_rate": 1.4384089652291543e-06,
|
57 |
+
"loss": 0.0942,
|
58 |
+
"step": 35
|
59 |
+
},
|
60 |
+
{
|
61 |
+
"epoch": 0.98,
|
62 |
+
"step": 37,
|
63 |
+
"total_flos": 7654509483393024.0,
|
64 |
+
"train_loss": 0.3938806479847109,
|
65 |
+
"train_runtime": 8367.9218,
|
66 |
+
"train_samples_per_second": 0.289,
|
67 |
+
"train_steps_per_second": 0.004
|
68 |
+
}
|
69 |
+
],
|
70 |
+
"logging_steps": 5,
|
71 |
+
"max_steps": 37,
|
72 |
+
"num_input_tokens_seen": 0,
|
73 |
+
"num_train_epochs": 1,
|
74 |
+
"save_steps": 100,
|
75 |
+
"total_flos": 7654509483393024.0,
|
76 |
+
"train_batch_size": 16,
|
77 |
+
"trial_name": null,
|
78 |
+
"trial_params": null
|
79 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:676e2e32c98aff8e05bed7cbaa5a643536ab49031698861283f6ee682c1fefd0
|
3 |
+
size 5048
|