vijayk2000 commited on
Commit
306cc09
·
verified ·
1 Parent(s): 39f62df

Model save

Browse files
README.md ADDED
@@ -0,0 +1,69 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ license: apache-2.0
4
+ base_model: ministral/Ministral-3b-instruct
5
+ tags:
6
+ - trl
7
+ - sft
8
+ - generated_from_trainer
9
+ datasets:
10
+ - generator
11
+ model-index:
12
+ - name: lora_sentiment_analysis
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
+ # lora_sentiment_analysis
20
+
21
+ This model is a fine-tuned version of [ministral/Ministral-3b-instruct](https://huggingface.co/ministral/Ministral-3b-instruct) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.7821
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: 0.0005
43
+ - train_batch_size: 1
44
+ - eval_batch_size: 1
45
+ - seed: 42
46
+ - gradient_accumulation_steps: 8
47
+ - total_train_batch_size: 8
48
+ - optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
49
+ - lr_scheduler_type: cosine
50
+ - lr_scheduler_warmup_ratio: 0.1
51
+ - num_epochs: 3
52
+ - mixed_precision_training: Native AMP
53
+
54
+ ### Training results
55
+
56
+ | Training Loss | Epoch | Step | Validation Loss |
57
+ |:-------------:|:------:|:----:|:---------------:|
58
+ | 9.3704 | 1.0 | 262 | 1.1464 |
59
+ | 7.0922 | 2.0 | 524 | 0.8622 |
60
+ | 5.1725 | 2.9890 | 783 | 0.7821 |
61
+
62
+
63
+ ### Framework versions
64
+
65
+ - PEFT 0.14.0
66
+ - Transformers 4.48.0
67
+ - Pytorch 2.1.1+cu121
68
+ - Datasets 3.2.0
69
+ - Tokenizers 0.21.0
adapter_config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "ministral/Ministral-3b-instruct",
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": 16,
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": 8,
23
+ "rank_pattern": {},
24
+ "revision": null,
25
+ "target_modules": [
26
+ "o_proj",
27
+ "v_proj",
28
+ "down_proj",
29
+ "k_proj",
30
+ "q_proj",
31
+ "up_proj",
32
+ "embed_tokens",
33
+ "gate_proj",
34
+ "lm_head"
35
+ ],
36
+ "task_type": "CAUSAL_LM",
37
+ "use_dora": false,
38
+ "use_rslora": false
39
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d800908469efead3b42b393e6b11ca14eec8bf67a33615b69254ebea5d9d924
3
+ size 563407064
runs/Jan19_07-20-26_4bad3d33b4af/events.out.tfevents.1737271266.4bad3d33b4af.4581.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:498babb0da4974fe56f5d94391b67e32f22c8e5f1d5dc64de40f4c129a15374b
3
+ size 11776
runs/Jan19_07-40-21_4bad3d33b4af/events.out.tfevents.1737272439.4bad3d33b4af.4581.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94cb94a45954e506a1ffd1bf95b5a5ebbed8db5b36e04e198cda2f12d37bb7cd
3
+ size 39106
special_tokens_map.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>user",
4
+ "<|im_start|>assistant",
5
+ "<|im_start|>system",
6
+ "<|im_end|>",
7
+ "<s>",
8
+ "<pad>"
9
+ ],
10
+ "bos_token": {
11
+ "content": "<s>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "eos_token": "<|im_end|>",
18
+ "pad_token": "<pad>",
19
+ "unk_token": {
20
+ "content": "<unk>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false
25
+ }
26
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
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
+ "32000": {
31
+ "content": "<|im_end|>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false,
36
+ "special": true
37
+ },
38
+ "32001": {
39
+ "content": "<pad>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false,
44
+ "special": true
45
+ },
46
+ "32002": {
47
+ "content": "<|im_start|>user",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false,
52
+ "special": true
53
+ },
54
+ "32003": {
55
+ "content": "<|im_start|>assistant",
56
+ "lstrip": false,
57
+ "normalized": false,
58
+ "rstrip": false,
59
+ "single_word": false,
60
+ "special": true
61
+ },
62
+ "32004": {
63
+ "content": "<|im_start|>system",
64
+ "lstrip": false,
65
+ "normalized": false,
66
+ "rstrip": false,
67
+ "single_word": false,
68
+ "special": true
69
+ }
70
+ },
71
+ "additional_special_tokens": [
72
+ "<|im_start|>user",
73
+ "<|im_start|>assistant",
74
+ "<|im_start|>system",
75
+ "<|im_end|>",
76
+ "<s>",
77
+ "<pad>"
78
+ ],
79
+ "bos_token": "<s>",
80
+ "chat_template": "{% for message in messages %}\n{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% if loop.last and add_generation_prompt %}{{'<|im_start|>assistant\n' }}{% endif %}{% endfor %}",
81
+ "clean_up_tokenization_spaces": false,
82
+ "eos_token": "<|im_end|>",
83
+ "extra_special_tokens": {},
84
+ "legacy": true,
85
+ "max_length": 512,
86
+ "model_max_length": 1000000000000000019884624838656,
87
+ "pad_to_multiple_of": null,
88
+ "pad_token": "<pad>",
89
+ "pad_token_type_id": 0,
90
+ "padding_side": "left",
91
+ "sp_model_kwargs": {},
92
+ "spaces_between_special_tokens": false,
93
+ "stride": 0,
94
+ "tokenizer_class": "LlamaTokenizer",
95
+ "truncation_side": "right",
96
+ "truncation_strategy": "longest_first",
97
+ "unk_token": "<unk>",
98
+ "use_default_system_prompt": true
99
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:803751c47f951610b9726fbbfb04d4d0dff734be1d7b51b5ac89fa84cb561d18
3
+ size 5368