Update model (trained for one more epoch)
Browse files- adapter_config.json +0 -2
- adapter_model.bin +3 -0
- config.json +1 -1
- generation_config.json +1 -1
- pytorch_model.bin +3 -0
- tokenizer.json +1 -6
- tokenizer_config.json +2 -4
- training_args.bin +2 -2
- training_params.json +47 -1
adapter_config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"alpha_pattern": {},
|
3 |
"auto_mapping": null,
|
4 |
"base_model_name_or_path": "Locutusque/TinyMistral-248M",
|
5 |
"bias": "none",
|
@@ -13,7 +12,6 @@
|
|
13 |
"modules_to_save": null,
|
14 |
"peft_type": "LORA",
|
15 |
"r": 16,
|
16 |
-
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"q_proj",
|
|
|
1 |
{
|
|
|
2 |
"auto_mapping": null,
|
3 |
"base_model_name_or_path": "Locutusque/TinyMistral-248M",
|
4 |
"bias": "none",
|
|
|
12 |
"modules_to_save": null,
|
13 |
"peft_type": "LORA",
|
14 |
"r": 16,
|
|
|
15 |
"revision": null,
|
16 |
"target_modules": [
|
17 |
"q_proj",
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ebf4afe44da097b7e5503ecdf06c785e87db2e054f5d7996d4bfae76d298e60f
|
3 |
+
size 2572670
|
config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
"sliding_window": 32,
|
20 |
"tie_word_embeddings": false,
|
21 |
"torch_dtype": "float16",
|
22 |
-
"transformers_version": "4.
|
23 |
"use_cache": true,
|
24 |
"vocab_size": 32003
|
25 |
}
|
|
|
19 |
"sliding_window": 32,
|
20 |
"tie_word_embeddings": false,
|
21 |
"torch_dtype": "float16",
|
22 |
+
"transformers_version": "4.34.1",
|
23 |
"use_cache": true,
|
24 |
"vocab_size": 32003
|
25 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,5 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
-
"transformers_version": "4.
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"transformers_version": "4.34.1"
|
6 |
}
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e2167bd8b9ea40693c70afbc71422c46e75dcad1b616f2cac3c7c157c5ce157b
|
3 |
+
size 496075846
|
tokenizer.json
CHANGED
@@ -1,11 +1,6 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
"direction": "Right",
|
5 |
-
"max_length": 1536,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
tokenizer_config.json
CHANGED
@@ -1,4 +1,6 @@
|
|
1 |
{
|
|
|
|
|
2 |
"added_tokens_decoder": {
|
3 |
"0": {
|
4 |
"content": "<unk>",
|
@@ -54,15 +56,11 @@
|
|
54 |
"clean_up_tokenization_spaces": false,
|
55 |
"eos_token": "<|endoftext|>",
|
56 |
"legacy": true,
|
57 |
-
"max_length": 1536,
|
58 |
"model_max_length": 1000000000000000019884624838656,
|
59 |
"pad_token": "[PAD]",
|
60 |
"sp_model_kwargs": {},
|
61 |
"spaces_between_special_tokens": false,
|
62 |
-
"stride": 0,
|
63 |
"tokenizer_class": "LlamaTokenizer",
|
64 |
-
"truncation_side": "right",
|
65 |
-
"truncation_strategy": "longest_first",
|
66 |
"unk_token": "<unk>",
|
67 |
"use_default_system_prompt": true
|
68 |
}
|
|
|
1 |
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
"added_tokens_decoder": {
|
5 |
"0": {
|
6 |
"content": "<unk>",
|
|
|
56 |
"clean_up_tokenization_spaces": false,
|
57 |
"eos_token": "<|endoftext|>",
|
58 |
"legacy": true,
|
|
|
59 |
"model_max_length": 1000000000000000019884624838656,
|
60 |
"pad_token": "[PAD]",
|
61 |
"sp_model_kwargs": {},
|
62 |
"spaces_between_special_tokens": false,
|
|
|
63 |
"tokenizer_class": "LlamaTokenizer",
|
|
|
|
|
64 |
"unk_token": "<unk>",
|
65 |
"use_default_system_prompt": true
|
66 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:21eae65f4c26b0c16e3e46446fd425ca78580db9e0a0f97b3315795b3d2a65fd
|
3 |
+
size 4536
|
training_params.json
CHANGED
@@ -1 +1,47 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "Felladrin/TinyMistral-248M-Evol-Instruct",
|
3 |
+
"data_path": "data/",
|
4 |
+
"project_name": "TinyMistral-248M-Evol-Instruct",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"text_column": "text",
|
8 |
+
"rejected_text_column": "rejected",
|
9 |
+
"token": null,
|
10 |
+
"lr": 0.0002,
|
11 |
+
"epochs": 1,
|
12 |
+
"batch_size": 12,
|
13 |
+
"warmup_ratio": 0.1,
|
14 |
+
"gradient_accumulation": 4,
|
15 |
+
"optimizer": "adamw_torch",
|
16 |
+
"scheduler": "linear",
|
17 |
+
"weight_decay": 0.01,
|
18 |
+
"max_grad_norm": 1.0,
|
19 |
+
"seed": 42,
|
20 |
+
"add_eos_token": false,
|
21 |
+
"block_size": 1024,
|
22 |
+
"use_peft": false,
|
23 |
+
"lora_r": 16,
|
24 |
+
"lora_alpha": 32,
|
25 |
+
"lora_dropout": 0.05,
|
26 |
+
"logging_steps": -1,
|
27 |
+
"evaluation_strategy": "epoch",
|
28 |
+
"save_total_limit": 1,
|
29 |
+
"save_strategy": "epoch",
|
30 |
+
"auto_find_batch_size": false,
|
31 |
+
"fp16": false,
|
32 |
+
"push_to_hub": false,
|
33 |
+
"use_int8": true,
|
34 |
+
"model_max_length": 1024,
|
35 |
+
"repo_id": null,
|
36 |
+
"use_int4": false,
|
37 |
+
"trainer": "sft",
|
38 |
+
"target_modules": null,
|
39 |
+
"merge_adapter": true,
|
40 |
+
"username": null,
|
41 |
+
"use_flash_attention_2": false,
|
42 |
+
"log": "none",
|
43 |
+
"disable_gradient_checkpointing": false,
|
44 |
+
"model_ref": null,
|
45 |
+
"dpo_beta": 0.1,
|
46 |
+
"prompt_text_column": "prompt"
|
47 |
+
}
|