Hugging Face's logo

francesco12357
/
results_mixtral_sft

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
francesco12357 commited on
Commit
9d1f853
•
1 Parent(s): 7e846ac

francesco12357/mixtral_fine_tuned_test

Browse files
Files changed (9) hide show
  1. README.md +163 -0
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Feb01_13-40-16_240793099e75/events.out.tfevents.1706794834.240793099e75.961.0 +3 -0
  5. special_tokens_map.json +24 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +42 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: mistralai/Mixtral-8x7B-v0.1
9
+ model-index:
10
+ - name: results_mixtral_sft
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # results_mixtral_sft
18
+
19
+ This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the None dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.2331
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 10
42
+ - eval_batch_size: 10
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 20
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 25
49
+ - num_epochs: 100
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:----:|:---------------:|
55
+ | No log | 1.0 | 1 | 2.4533 |
56
+ | No log | 2.0 | 2 | 2.4493 |
57
+ | No log | 3.0 | 3 | 2.4436 |
58
+ | No log | 4.0 | 4 | 2.4352 |
59
+ | No log | 5.0 | 5 | 2.4249 |
60
+ | No log | 6.0 | 6 | 2.4215 |
61
+ | No log | 7.0 | 7 | 2.4047 |
62
+ | No log | 8.0 | 8 | 2.3842 |
63
+ | No log | 9.0 | 9 | 2.3561 |
64
+ | No log | 10.0 | 10 | 2.3295 |
65
+ | No log | 11.0 | 11 | 2.3004 |
66
+ | No log | 12.0 | 12 | 2.2563 |
67
+ | No log | 13.0 | 13 | 2.2130 |
68
+ | No log | 14.0 | 14 | 2.1715 |
69
+ | No log | 15.0 | 15 | 2.1203 |
70
+ | No log | 16.0 | 16 | 2.0893 |
71
+ | No log | 17.0 | 17 | 2.0458 |
72
+ | No log | 18.0 | 18 | 1.9937 |
73
+ | No log | 19.0 | 19 | 1.9469 |
74
+ | No log | 20.0 | 20 | 1.9085 |
75
+ | No log | 21.0 | 21 | 1.9413 |
76
+ | No log | 22.0 | 22 | 1.8690 |
77
+ | No log | 23.0 | 23 | 1.8139 |
78
+ | No log | 24.0 | 24 | 1.7389 |
79
+ | 1.0996 | 25.0 | 25 | 1.6836 |
80
+ | 1.0996 | 26.0 | 26 | 1.6236 |
81
+ | 1.0996 | 27.0 | 27 | 1.5705 |
82
+ | 1.0996 | 28.0 | 28 | 1.5261 |
83
+ | 1.0996 | 29.0 | 29 | 1.4790 |
84
+ | 1.0996 | 30.0 | 30 | 1.4240 |
85
+ | 1.0996 | 31.0 | 31 | 1.3674 |
86
+ | 1.0996 | 32.0 | 32 | 1.3182 |
87
+ | 1.0996 | 33.0 | 33 | 1.2769 |
88
+ | 1.0996 | 34.0 | 34 | 1.2321 |
89
+ | 1.0996 | 35.0 | 35 | 1.1885 |
90
+ | 1.0996 | 36.0 | 36 | 1.1445 |
91
+ | 1.0996 | 37.0 | 37 | 1.0878 |
92
+ | 1.0996 | 38.0 | 38 | 1.0237 |
93
+ | 1.0996 | 39.0 | 39 | 0.9748 |
94
+ | 1.0996 | 40.0 | 40 | 0.9294 |
95
+ | 1.0996 | 41.0 | 41 | 0.8806 |
96
+ | 1.0996 | 42.0 | 42 | 0.8457 |
97
+ | 1.0996 | 43.0 | 43 | 0.7969 |
98
+ | 1.0996 | 44.0 | 44 | 0.7599 |
99
+ | 1.0996 | 45.0 | 45 | 0.7189 |
100
+ | 1.0996 | 46.0 | 46 | 0.6952 |
101
+ | 1.0996 | 47.0 | 47 | 0.6570 |
102
+ | 1.0996 | 48.0 | 48 | 0.6316 |
103
+ | 1.0996 | 49.0 | 49 | 0.6212 |
104
+ | 0.548 | 50.0 | 50 | 0.5764 |
105
+ | 0.548 | 51.0 | 51 | 0.5113 |
106
+ | 0.548 | 52.0 | 52 | 0.4868 |
107
+ | 0.548 | 53.0 | 53 | 0.4585 |
108
+ | 0.548 | 54.0 | 54 | 0.4334 |
109
+ | 0.548 | 55.0 | 55 | 0.4208 |
110
+ | 0.548 | 56.0 | 56 | 0.4087 |
111
+ | 0.548 | 57.0 | 57 | 0.3945 |
112
+ | 0.548 | 58.0 | 58 | 0.3722 |
113
+ | 0.548 | 59.0 | 59 | 0.3588 |
114
+ | 0.548 | 60.0 | 60 | 0.3414 |
115
+ | 0.548 | 61.0 | 61 | 0.3235 |
116
+ | 0.548 | 62.0 | 62 | 0.3157 |
117
+ | 0.548 | 63.0 | 63 | 0.3050 |
118
+ | 0.548 | 64.0 | 64 | 0.2969 |
119
+ | 0.548 | 65.0 | 65 | 0.2893 |
120
+ | 0.548 | 66.0 | 66 | 0.2802 |
121
+ | 0.548 | 67.0 | 67 | 0.2746 |
122
+ | 0.548 | 68.0 | 68 | 0.2688 |
123
+ | 0.548 | 69.0 | 69 | 0.2643 |
124
+ | 0.548 | 70.0 | 70 | 0.2581 |
125
+ | 0.548 | 71.0 | 71 | 0.2523 |
126
+ | 0.548 | 72.0 | 72 | 0.2490 |
127
+ | 0.548 | 73.0 | 73 | 0.2468 |
128
+ | 0.548 | 74.0 | 74 | 0.2404 |
129
+ | 0.1741 | 75.0 | 75 | 0.2394 |
130
+ | 0.1741 | 76.0 | 76 | 0.2382 |
131
+ | 0.1741 | 77.0 | 77 | 0.2373 |
132
+ | 0.1741 | 78.0 | 78 | 0.2366 |
133
+ | 0.1741 | 79.0 | 79 | 0.2361 |
134
+ | 0.1741 | 80.0 | 80 | 0.2358 |
135
+ | 0.1741 | 81.0 | 81 | 0.2355 |
136
+ | 0.1741 | 82.0 | 82 | 0.2352 |
137
+ | 0.1741 | 83.0 | 83 | 0.2350 |
138
+ | 0.1741 | 84.0 | 84 | 0.2348 |
139
+ | 0.1741 | 85.0 | 85 | 0.2345 |
140
+ | 0.1741 | 86.0 | 86 | 0.2343 |
141
+ | 0.1741 | 87.0 | 87 | 0.2342 |
142
+ | 0.1741 | 88.0 | 88 | 0.2340 |
143
+ | 0.1741 | 89.0 | 89 | 0.2339 |
144
+ | 0.1741 | 90.0 | 90 | 0.2337 |
145
+ | 0.1741 | 91.0 | 91 | 0.2336 |
146
+ | 0.1741 | 92.0 | 92 | 0.2335 |
147
+ | 0.1741 | 93.0 | 93 | 0.2334 |
148
+ | 0.1741 | 94.0 | 94 | 0.2333 |
149
+ | 0.1741 | 95.0 | 95 | 0.2333 |
150
+ | 0.1741 | 96.0 | 96 | 0.2332 |
151
+ | 0.1741 | 97.0 | 97 | 0.2331 |
152
+ | 0.1741 | 98.0 | 98 | 0.2331 |
153
+ | 0.1741 | 99.0 | 99 | 0.2331 |
154
+ | 0.1174 | 100.0 | 100 | 0.2331 |
155
+
156
+
157
+ ### Framework versions
158
+
159
+ - PEFT 0.8.1
160
+ - Transformers 4.37.2
161
+ - Pytorch 2.1.0+cu121
162
+ - Datasets 2.16.1
163
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mixtral-8x7B-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": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "k_proj",
23
+ "v_proj",
24
+ "q_proj",
25
+ "o_proj"
26
+ ],
27
+ "task_type": "CAUSAL_LM",
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c72c8b3f591f6e779884b26d156032892a55f1a8578872534b148a1a1871f78
3
+ size 54560368
runs/Feb01_13-40-16_240793099e75/events.out.tfevents.1706794834.240793099e75.961.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af24159fcb37a3fb55634e98f331999553a6cd29c6c87e8ef6d42bc2792db4d5
3
+ size 32464
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": "<unk>",
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
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
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "<unk>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fb88393d8e27e4b730fe4d705fe98ed7cd647c17d5f49e1c1d0b5a9408a8f38
3
+ size 4728