Upload 9 files
Browse files- adapter_config.json +34 -0
- adapter_model.safetensors +3 -0
- runs/Oct31_20-36-44_asulab-kubuntu-ai/events.out.tfevents.1730396235.asulab-kubuntu-ai.39641.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
- training_args.bin +3 -0
- training_params.json +49 -0
adapter_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.3",
|
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": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"q_proj",
|
24 |
+
"up_proj",
|
25 |
+
"v_proj",
|
26 |
+
"o_proj",
|
27 |
+
"gate_proj",
|
28 |
+
"k_proj",
|
29 |
+
"down_proj"
|
30 |
+
],
|
31 |
+
"task_type": "CAUSAL_LM",
|
32 |
+
"use_dora": false,
|
33 |
+
"use_rslora": false
|
34 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4e4c47f13e8e196aa1fdcf07373a50a4f2052a269e891af60cd2a4008abd0ad
|
3 |
+
size 167832240
|
runs/Oct31_20-36-44_asulab-kubuntu-ai/events.out.tfevents.1730396235.asulab-kubuntu-ai.39641.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ec5e61bb2d00b41e867405f876414faa7e5e0577f4cdb47c7380ae1042c2a494
|
3 |
+
size 26785
|
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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
|
3 |
+
size 587404
|
tokenizer_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0c59092a62d24c5613d8c1b9ae0413b30d6eb7464526cb862b398f9016842ac
|
3 |
+
size 5496
|
training_params.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "mistralai/Mistral-7B-v0.3",
|
3 |
+
"project_name": "Mistral-7B-RAG-ruen",
|
4 |
+
"data_path": "./RAGv1_ruen_text",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"add_eos_token": true,
|
8 |
+
"block_size": 4096,
|
9 |
+
"model_max_length": 8192,
|
10 |
+
"padding": "right",
|
11 |
+
"trainer": "sft",
|
12 |
+
"use_flash_attention_2": false,
|
13 |
+
"log": "tensorboard",
|
14 |
+
"disable_gradient_checkpointing": false,
|
15 |
+
"logging_steps": -1,
|
16 |
+
"eval_strategy": "epoch",
|
17 |
+
"save_total_limit": 1,
|
18 |
+
"auto_find_batch_size": false,
|
19 |
+
"mixed_precision": "None",
|
20 |
+
"lr": 0.00001,
|
21 |
+
"epochs": 1,
|
22 |
+
"batch_size": 2,
|
23 |
+
"warmup_ratio": 0.1,
|
24 |
+
"gradient_accumulation": 4,
|
25 |
+
"optimizer": "paged_adamw_8bit",
|
26 |
+
"scheduler": "cosine",
|
27 |
+
"weight_decay": 0.0,
|
28 |
+
"max_grad_norm": 1.0,
|
29 |
+
"seed": 42,
|
30 |
+
"chat_template": null,
|
31 |
+
"quantization": "int4",
|
32 |
+
"target_modules": "all-linear",
|
33 |
+
"merge_adapter": false,
|
34 |
+
"peft": true,
|
35 |
+
"lora_r": 16,
|
36 |
+
"lora_alpha": 32,
|
37 |
+
"lora_dropout": 0.05,
|
38 |
+
"model_ref": null,
|
39 |
+
"dpo_beta": 0.1,
|
40 |
+
"max_prompt_length": 128,
|
41 |
+
"max_completion_length": null,
|
42 |
+
"prompt_text_column": null,
|
43 |
+
"text_column": "text",
|
44 |
+
"rejected_text_column": null,
|
45 |
+
"push_to_hub": false,
|
46 |
+
"username": "MexIvanov",
|
47 |
+
"unsloth": false,
|
48 |
+
"distributed_backend": null
|
49 |
+
}
|