Hugging Face's logo

tigerbhai
/
Mixtral_texmin

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
 Metrics Community
tigerbhai commited on
Commit
0e93883
·
1 Parent(s): 368fc04

tigerbhai/mistral-instruct-generation

Browse files
Files changed (13) hide show
  1. .ipynb_checkpoints/emissions-checkpoint.csv +2 -0
  2. README.md +163 -0
  3. adapter_config.json +32 -0
  4. adapter_model.safetensors +3 -0
  5. emissions.csv +2 -0
  6. runs/Dec26_11-08-31_d8955a52ad75/events.out.tfevents.1703588934.d8955a52ad75.1150.0 +3 -0
  7. runs/Dec26_12-06-54_d8955a52ad75/events.out.tfevents.1703592428.d8955a52ad75.1150.1 +3 -0
  8. runs/Dec26_12-06-54_d8955a52ad75/events.out.tfevents.1703592627.d8955a52ad75.1150.2 +3 -0
  9. special_tokens_map.json +24 -0
  10. tokenizer.json +0 -0
  11. tokenizer.model +3 -0
  12. tokenizer_config.json +42 -0
  13. training_args.bin +3 -0
.ipynb_checkpoints/emissions-checkpoint.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
2
+ 2023-12-26T15:10:53,codecarbon,468bbc4d-36b4-4877-a8c7-2705a9a27378,10825.342874526978,1.279440122027548,0.00011818933929919095,114.40438153486924,254.83100000000002,141.57512140274048,0.2613732887759636,1.324491652037195,0.42210157743052923,2.0079665182436854,India,IND,gujarat,,,Linux-5.15.0-1041-nvidia-x86_64-with-glibc2.35,3.10.12,2.2.3,128,AMD EPYC 7742 64-Core Processor,4,4 x NVIDIA A100-SXM4-40GB,72.8293,21.1888,377.5336570739746,machine,N,1.0
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
+ datasets:
9
+ - generator
10
+ base_model: mistralai/Mixtral-8x7B-v0.1
11
+ model-index:
12
+ - name: Mixtral_texmin
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
+ # Mixtral_texmin
20
+
21
+ This model is a fine-tuned version of [mistralai/Mixtral-8x7B-v0.1](https://huggingface.co/mistralai/Mixtral-8x7B-v0.1) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 0.0053
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: 2.5e-05
43
+ - train_batch_size: 32
44
+ - eval_batch_size: 8
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 0.03
49
+ - training_steps: 1000
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:----:|:---------------:|
55
+ | 1.1336 | 10.0 | 10 | 0.9527 |
56
+ | 0.994 | 20.0 | 20 | 0.8577 |
57
+ | 0.8959 | 30.0 | 30 | 0.7932 |
58
+ | 0.8284 | 40.0 | 40 | 0.7371 |
59
+ | 0.7632 | 50.0 | 50 | 0.6634 |
60
+ | 0.6947 | 60.0 | 60 | 0.6000 |
61
+ | 0.6178 | 70.0 | 70 | 0.5247 |
62
+ | 0.5351 | 80.0 | 80 | 0.4482 |
63
+ | 0.4532 | 90.0 | 90 | 0.3783 |
64
+ | 0.3764 | 100.0 | 100 | 0.3120 |
65
+ | 0.3038 | 110.0 | 110 | 0.2446 |
66
+ | 0.232 | 120.0 | 120 | 0.1830 |
67
+ | 0.1668 | 130.0 | 130 | 0.1273 |
68
+ | 0.1111 | 140.0 | 140 | 0.0854 |
69
+ | 0.0722 | 150.0 | 150 | 0.0608 |
70
+ | 0.0506 | 160.0 | 160 | 0.0479 |
71
+ | 0.0406 | 170.0 | 170 | 0.0422 |
72
+ | 0.0351 | 180.0 | 180 | 0.0386 |
73
+ | 0.0316 | 190.0 | 190 | 0.0364 |
74
+ | 0.0292 | 200.0 | 200 | 0.0350 |
75
+ | 0.0271 | 210.0 | 210 | 0.0329 |
76
+ | 0.0253 | 220.0 | 220 | 0.0311 |
77
+ | 0.0238 | 230.0 | 230 | 0.0303 |
78
+ | 0.0223 | 240.0 | 240 | 0.0285 |
79
+ | 0.021 | 250.0 | 250 | 0.0276 |
80
+ | 0.0196 | 260.0 | 260 | 0.0262 |
81
+ | 0.0184 | 270.0 | 270 | 0.0246 |
82
+ | 0.0174 | 280.0 | 280 | 0.0234 |
83
+ | 0.0165 | 290.0 | 290 | 0.0223 |
84
+ | 0.0153 | 300.0 | 300 | 0.0214 |
85
+ | 0.0147 | 310.0 | 310 | 0.0218 |
86
+ | 0.0137 | 320.0 | 320 | 0.0203 |
87
+ | 0.0129 | 330.0 | 330 | 0.0198 |
88
+ | 0.012 | 340.0 | 340 | 0.0190 |
89
+ | 0.0114 | 350.0 | 350 | 0.0217 |
90
+ | 0.0107 | 360.0 | 360 | 0.0183 |
91
+ | 0.0101 | 370.0 | 370 | 0.0149 |
92
+ | 0.0097 | 380.0 | 380 | 0.0149 |
93
+ | 0.0094 | 390.0 | 390 | 0.0145 |
94
+ | 0.0088 | 400.0 | 400 | 0.0140 |
95
+ | 0.0082 | 410.0 | 410 | 0.0132 |
96
+ | 0.0072 | 420.0 | 420 | 0.0122 |
97
+ | 0.0067 | 430.0 | 430 | 0.0115 |
98
+ | 0.0061 | 440.0 | 440 | 0.0106 |
99
+ | 0.0057 | 450.0 | 450 | 0.0102 |
100
+ | 0.0053 | 460.0 | 460 | 0.0095 |
101
+ | 0.005 | 470.0 | 470 | 0.0088 |
102
+ | 0.0048 | 480.0 | 480 | 0.0086 |
103
+ | 0.0047 | 490.0 | 490 | 0.0081 |
104
+ | 0.0045 | 500.0 | 500 | 0.0085 |
105
+ | 0.0045 | 510.0 | 510 | 0.0080 |
106
+ | 0.0043 | 520.0 | 520 | 0.0082 |
107
+ | 0.0042 | 530.0 | 530 | 0.0078 |
108
+ | 0.0041 | 540.0 | 540 | 0.0076 |
109
+ | 0.004 | 550.0 | 550 | 0.0075 |
110
+ | 0.0039 | 560.0 | 560 | 0.0074 |
111
+ | 0.0038 | 570.0 | 570 | 0.0072 |
112
+ | 0.0038 | 580.0 | 580 | 0.0072 |
113
+ | 0.0038 | 590.0 | 590 | 0.0070 |
114
+ | 0.0037 | 600.0 | 600 | 0.0070 |
115
+ | 0.0036 | 610.0 | 610 | 0.0069 |
116
+ | 0.0036 | 620.0 | 620 | 0.0068 |
117
+ | 0.0035 | 630.0 | 630 | 0.0067 |
118
+ | 0.0035 | 640.0 | 640 | 0.0066 |
119
+ | 0.0034 | 650.0 | 650 | 0.0064 |
120
+ | 0.0034 | 660.0 | 660 | 0.0064 |
121
+ | 0.0033 | 670.0 | 670 | 0.0064 |
122
+ | 0.0033 | 680.0 | 680 | 0.0064 |
123
+ | 0.0032 | 690.0 | 690 | 0.0062 |
124
+ | 0.0032 | 700.0 | 700 | 0.0062 |
125
+ | 0.0032 | 710.0 | 710 | 0.0061 |
126
+ | 0.0032 | 720.0 | 720 | 0.0060 |
127
+ | 0.0031 | 730.0 | 730 | 0.0060 |
128
+ | 0.0031 | 740.0 | 740 | 0.0060 |
129
+ | 0.0031 | 750.0 | 750 | 0.0059 |
130
+ | 0.003 | 760.0 | 760 | 0.0058 |
131
+ | 0.003 | 770.0 | 770 | 0.0057 |
132
+ | 0.003 | 780.0 | 780 | 0.0058 |
133
+ | 0.003 | 790.0 | 790 | 0.0057 |
134
+ | 0.0029 | 800.0 | 800 | 0.0056 |
135
+ | 0.0029 | 810.0 | 810 | 0.0055 |
136
+ | 0.0029 | 820.0 | 820 | 0.0056 |
137
+ | 0.0029 | 830.0 | 830 | 0.0055 |
138
+ | 0.0029 | 840.0 | 840 | 0.0054 |
139
+ | 0.0029 | 850.0 | 850 | 0.0055 |
140
+ | 0.0028 | 860.0 | 860 | 0.0055 |
141
+ | 0.0028 | 870.0 | 870 | 0.0055 |
142
+ | 0.0028 | 880.0 | 880 | 0.0054 |
143
+ | 0.0028 | 890.0 | 890 | 0.0053 |
144
+ | 0.0028 | 900.0 | 900 | 0.0053 |
145
+ | 0.0028 | 910.0 | 910 | 0.0054 |
146
+ | 0.0027 | 920.0 | 920 | 0.0053 |
147
+ | 0.0027 | 930.0 | 930 | 0.0053 |
148
+ | 0.0027 | 940.0 | 940 | 0.0052 |
149
+ | 0.0027 | 950.0 | 950 | 0.0052 |
150
+ | 0.0027 | 960.0 | 960 | 0.0053 |
151
+ | 0.0027 | 970.0 | 970 | 0.0052 |
152
+ | 0.0027 | 980.0 | 980 | 0.0053 |
153
+ | 0.0027 | 990.0 | 990 | 0.0052 |
154
+ | 0.0027 | 1000.0 | 1000 | 0.0053 |
155
+
156
+
157
+ ### Framework versions
158
+
159
+ - PEFT 0.7.2.dev0
160
+ - Transformers 4.37.0.dev0
161
+ - Pytorch 2.1.2+cu121
162
+ - Datasets 2.16.0
163
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": null,
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": 16,
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": 64,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "v_proj",
23
+ "down_proj",
24
+ "gate_proj",
25
+ "o_proj",
26
+ "k_proj",
27
+ "lm_head",
28
+ "up_proj",
29
+ "q_proj"
30
+ ],
31
+ "task_type": "CAUSAL_LM"
32
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44ce263e6fd885f50d82ca515b9325375b43ee36ededb75acf161ce88bc2e41
3
+ size 48
emissions.csv ADDED
@@ -0,0 +1,2 @@
 
 
 
1
+ timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
2
+ 2023-12-26T15:10:53,codecarbon,468bbc4d-36b4-4877-a8c7-2705a9a27378,10825.342874526978,1.279440122027548,0.00011818933929919095,114.40438153486924,254.83100000000002,141.57512140274048,0.2613732887759636,1.324491652037195,0.42210157743052923,2.0079665182436854,India,IND,gujarat,,,Linux-5.15.0-1041-nvidia-x86_64-with-glibc2.35,3.10.12,2.2.3,128,AMD EPYC 7742 64-Core Processor,4,4 x NVIDIA A100-SXM4-40GB,72.8293,21.1888,377.5336570739746,machine,N,1.0
runs/Dec26_11-08-31_d8955a52ad75/events.out.tfevents.1703588934.d8955a52ad75.1150.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcb38990f5e0575282ff9b2bdcfa061a51e7d399f132aedef5b64071992af6ab
3
+ size 5049
runs/Dec26_12-06-54_d8955a52ad75/events.out.tfevents.1703592428.d8955a52ad75.1150.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:990e4ce29489bb0f375675025dc79b794ff0bd4a1039188b7dc6a0cf6a0d090b
3
+ size 5049
runs/Dec26_12-06-54_d8955a52ad75/events.out.tfevents.1703592627.d8955a52ad75.1150.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92eab19d7143e352f07206bfc7586b05e2898b50bdba8f18f222b7f1b0ad3179
3
+ size 47953
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "</s>",
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 sha256:6f74d065c96774ef280db23ccc40d344e950f9fcc56f090843ae2490b3ef40cd
3
+ size 4728