Model save
Browse files- README.md +69 -0
- adapter_config.json +28 -0
- adapter_model.safetensors +3 -0
- runs/Jan24_13-42-28_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706103771.pedro-morel-rosa-workspace-cuda-0.782.0 +3 -0
- runs/Jan24_13-57-25_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706104653.pedro-morel-rosa-workspace-cuda-0.782.1 +3 -0
- runs/Jan25_11-18-08_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706181789.pedro-morel-rosa-workspace-cuda-0.860.0 +3 -0
- runs/Jan25_14-45-52_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706193978.pedro-morel-rosa-workspace-cuda-0.517.0 +3 -0
- runs/Jan25_15-10-12_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706195607.pedro-morel-rosa-workspace-cuda-0.526.0 +3 -0
- runs/Jan25_22-56-20_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706223457.pedro-morel-rosa-workspace-cuda-0.1047.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
README.md
ADDED
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
library_name: peft
|
4 |
+
tags:
|
5 |
+
- trl
|
6 |
+
- sft
|
7 |
+
- generated_from_trainer
|
8 |
+
datasets:
|
9 |
+
- generator
|
10 |
+
base_model: mistralai/Mistral-7B-v0.1
|
11 |
+
model-index:
|
12 |
+
- name: Mistral-7B-v0.1-ICD-Expert-QLoRA-test-2
|
13 |
+
results: []
|
14 |
+
---
|
15 |
+
|
16 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
+
should probably proofread and complete it, then remove this comment. -->
|
18 |
+
|
19 |
+
# Mistral-7B-v0.1-ICD-Expert-QLoRA-test-2
|
20 |
+
|
21 |
+
This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
|
22 |
+
It achieves the following results on the evaluation set:
|
23 |
+
- Loss: 1.5534
|
24 |
+
|
25 |
+
## Model description
|
26 |
+
|
27 |
+
More information needed
|
28 |
+
|
29 |
+
## Intended uses & limitations
|
30 |
+
|
31 |
+
More information needed
|
32 |
+
|
33 |
+
## Training and evaluation data
|
34 |
+
|
35 |
+
More information needed
|
36 |
+
|
37 |
+
## Training procedure
|
38 |
+
|
39 |
+
### Training hyperparameters
|
40 |
+
|
41 |
+
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 2e-05
|
43 |
+
- train_batch_size: 4
|
44 |
+
- eval_batch_size: 4
|
45 |
+
- seed: 42
|
46 |
+
- gradient_accumulation_steps: 128
|
47 |
+
- total_train_batch_size: 512
|
48 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
+
- lr_scheduler_type: cosine
|
50 |
+
- num_epochs: 4
|
51 |
+
- mixed_precision_training: Native AMP
|
52 |
+
|
53 |
+
### Training results
|
54 |
+
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
57 |
+
| 1.8212 | 0.97 | 18 | 1.7546 |
|
58 |
+
| 1.6305 | 1.99 | 37 | 1.6045 |
|
59 |
+
| 1.5805 | 2.96 | 55 | 1.5591 |
|
60 |
+
| 1.5579 | 3.88 | 72 | 1.5534 |
|
61 |
+
|
62 |
+
|
63 |
+
### Framework versions
|
64 |
+
|
65 |
+
- PEFT 0.7.1
|
66 |
+
- Transformers 4.37.0
|
67 |
+
- Pytorch 2.1.2+cu121
|
68 |
+
- Datasets 2.16.1
|
69 |
+
- Tokenizers 0.15.0
|
adapter_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
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": 64,
|
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": 128,
|
19 |
+
"rank_pattern": {},
|
20 |
+
"revision": null,
|
21 |
+
"target_modules": [
|
22 |
+
"q_proj",
|
23 |
+
"k_proj",
|
24 |
+
"v_proj",
|
25 |
+
"o_proj"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM"
|
28 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c341a178bc67585cb14e59d2ca720ca273ecadad3c9b8e74b088399475c074c
|
3 |
+
size 436242776
|
runs/Jan24_13-42-28_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706103771.pedro-morel-rosa-workspace-cuda-0.782.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8dfec1f8e890381a630fc074569c568b147466f966fafde78c6db5c3cf93634f
|
3 |
+
size 5553
|
runs/Jan24_13-57-25_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706104653.pedro-morel-rosa-workspace-cuda-0.782.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:307b6f51aedd62733a05701d548925ab4f1eb98c9923f4fbc5258508081ee04b
|
3 |
+
size 6663
|
runs/Jan25_11-18-08_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706181789.pedro-morel-rosa-workspace-cuda-0.860.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8b6fb582af60e361aeaa8547f953b4a01832c9d74b67ea75c2d764f92c71f6f3
|
3 |
+
size 6287
|
runs/Jan25_14-45-52_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706193978.pedro-morel-rosa-workspace-cuda-0.517.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3af2d47b3be47434b81591f2c97388bd52cbdfff046ae3d762306362eab21a81
|
3 |
+
size 4943
|
runs/Jan25_15-10-12_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706195607.pedro-morel-rosa-workspace-cuda-0.526.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a937f2921fecda84fa0c111018ea37b69af4056a2367f3cdaa89ccc5ecee6fc8
|
3 |
+
size 8205
|
runs/Jan25_22-56-20_pedro-morel-rosa-workspace-cuda-0/events.out.tfevents.1706223457.pedro-morel-rosa-workspace-cuda-0.1047.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1367b0abd18ff9280aa7b68d286cdf1ce8c8a9b9a9ca926dfbf0694845d4fbe3
|
3 |
+
size 9127
|
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 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"additional_special_tokens": [],
|
31 |
+
"bos_token": "<s>",
|
32 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
33 |
+
"clean_up_tokenization_spaces": false,
|
34 |
+
"eos_token": "</s>",
|
35 |
+
"legacy": true,
|
36 |
+
"model_max_length": 2048,
|
37 |
+
"pad_token": "</s>",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d8fe4796ddb8c437ba51b7be4550a6de44c4579075525eb284de0b5ac7e60fa9
|
3 |
+
size 4856
|