sajjadhadi commited on
Commit
2315af6
·
verified ·
1 Parent(s): cbf70ee

Training in progress, step 5000

Browse files
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
+ "eva_config": null,
7
+ "exclude_modules": null,
8
+ "fan_in_fan_out": false,
9
+ "inference_mode": true,
10
+ "init_lora_weights": true,
11
+ "layer_replication": null,
12
+ "layers_pattern": null,
13
+ "layers_to_transform": null,
14
+ "loftq_config": {},
15
+ "lora_alpha": 64,
16
+ "lora_bias": false,
17
+ "lora_dropout": 0.1,
18
+ "megatron_config": null,
19
+ "megatron_core": "megatron.core",
20
+ "modules_to_save": null,
21
+ "peft_type": "LORA",
22
+ "r": 32,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "q_proj",
27
+ "v_proj",
28
+ "o_proj",
29
+ "k_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 sha256:7c3807a956cf96cee9eefa34c83870f32729f878dfffa75d71623b0930d82b63
3
+ size 109086416
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
+ }
tokenized_dataset/data-00000-of-00001.arrow ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93d2f55720a9a9107206242fdddeee5844efdac239b4dc92adc6dd51df9a69b2
3
+ size 232226680
tokenized_dataset/dataset_info.json ADDED
@@ -0,0 +1,62 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "builder_name": "parquet",
3
+ "citation": "",
4
+ "config_name": "default",
5
+ "dataset_name": "disease-diagnosis-dataset",
6
+ "dataset_size": 126706598,
7
+ "description": "",
8
+ "download_checksums": {
9
+ "hf://datasets/sajjadhadi/disease-diagnosis-dataset@d6112cea985c4219069791c7c20010d81e945698/data/train-00000-of-00001.parquet": {
10
+ "num_bytes": 27292179,
11
+ "checksum": null
12
+ },
13
+ "hf://datasets/sajjadhadi/disease-diagnosis-dataset@d6112cea985c4219069791c7c20010d81e945698/data/test-00000-of-00001.parquet": {
14
+ "num_bytes": 1151308,
15
+ "checksum": null
16
+ }
17
+ },
18
+ "download_size": 28443487,
19
+ "features": {
20
+ "diagnosis": {
21
+ "dtype": "string",
22
+ "_type": "Value"
23
+ },
24
+ "input_ids": {
25
+ "feature": {
26
+ "dtype": "int32",
27
+ "_type": "Value"
28
+ },
29
+ "_type": "Sequence"
30
+ },
31
+ "attention_mask": {
32
+ "feature": {
33
+ "dtype": "int8",
34
+ "_type": "Value"
35
+ },
36
+ "_type": "Sequence"
37
+ }
38
+ },
39
+ "homepage": "",
40
+ "license": "",
41
+ "size_in_bytes": 155150085,
42
+ "splits": {
43
+ "train": {
44
+ "name": "train",
45
+ "num_bytes": 120825750,
46
+ "num_examples": 469195,
47
+ "dataset_name": "disease-diagnosis-dataset"
48
+ },
49
+ "test": {
50
+ "name": "test",
51
+ "num_bytes": 5880848,
52
+ "num_examples": 24695,
53
+ "dataset_name": "disease-diagnosis-dataset"
54
+ }
55
+ },
56
+ "version": {
57
+ "version_str": "0.0.0",
58
+ "major": 0,
59
+ "minor": 0,
60
+ "patch": 0
61
+ }
62
+ }
tokenized_dataset/state.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_data_files": [
3
+ {
4
+ "filename": "data-00000-of-00001.arrow"
5
+ }
6
+ ],
7
+ "_fingerprint": "52f34413087e7b4b",
8
+ "_format_columns": null,
9
+ "_format_kwargs": {},
10
+ "_format_type": null,
11
+ "_output_all_columns": false,
12
+ "_split": "train"
13
+ }
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 sha256:24441d97e761dfbc5690848cbd81d62dfb1de543e0ac30865a1ad7ef95837af7
3
+ size 5560