Hugging Face's logo

gizemgg
/
results

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
gizemgg commited on
Commit
ee7f8b3
•
1 Parent(s): e4fefb3

gizemgg/Llama-2-7b-chat-hf-finetuned-wiki-eng-summary-trial-gen6_adapter_test_epimelesi

Browse files
Files changed (29) hide show
  1. README.md +67 -0
  2. adapter_config.json +27 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Jul12_18-35-39_epimelesi/events.out.tfevents.1720802141.epimelesi.1623326.0 +3 -0
  5. runs/Jul12_18-37-02_epimelesi/events.out.tfevents.1720802223.epimelesi.1623661.0 +3 -0
  6. runs/Jul12_18-40-55_epimelesi/events.out.tfevents.1720802456.epimelesi.1624208.0 +3 -0
  7. runs/Jul12_18-44-13_epimelesi/events.out.tfevents.1720802654.epimelesi.1624683.0 +3 -0
  8. runs/Jul12_18-49-48_epimelesi/events.out.tfevents.1720802989.epimelesi.1625642.0 +3 -0
  9. runs/Jul13_12-03-49_epimelesi/events.out.tfevents.1720865030.epimelesi.1692642.0 +3 -0
  10. runs/Jul13_14-33-16_epimelesi/events.out.tfevents.1720873997.epimelesi.1700907.0 +3 -0
  11. runs/Jul13_14-35-25_epimelesi/events.out.tfevents.1720874125.epimelesi.1701742.0 +3 -0
  12. runs/Jul13_14-36-30_epimelesi/events.out.tfevents.1720874190.epimelesi.1701849.0 +3 -0
  13. runs/Jul13_14-38-10_epimelesi/events.out.tfevents.1720874290.epimelesi.1701960.0 +3 -0
  14. runs/Jul13_15-10-59_epimelesi/events.out.tfevents.1720876260.epimelesi.1704360.0 +3 -0
  15. runs/Jul13_15-13-16_epimelesi/events.out.tfevents.1720876396.epimelesi.1704518.0 +3 -0
  16. runs/Jul13_15-26-25_epimelesi/events.out.tfevents.1720877186.epimelesi.1705623.0 +3 -0
  17. runs/Jul13_16-16-26_epimelesi/events.out.tfevents.1720880187.epimelesi.1708831.0 +3 -0
  18. runs/Jul17_15-42-40_epimelesi/events.out.tfevents.1721223761.epimelesi.2235307.0 +3 -0
  19. runs/Jul17_15-50-24_epimelesi/events.out.tfevents.1721224225.epimelesi.2236716.0 +3 -0
  20. runs/Jul23_12-38-29_epimelesi/events.out.tfevents.1721731110.epimelesi.3760655.0 +3 -0
  21. runs/Jul23_15-39-50_epimelesi/events.out.tfevents.1721741990.epimelesi.3784070.0 +3 -0
  22. runs/Jul23_16-00-33_epimelesi/events.out.tfevents.1721743233.epimelesi.3784070.1 +3 -0
  23. runs/Jul23_16-14-49_epimelesi/events.out.tfevents.1721744089.epimelesi.3784070.2 +3 -0
  24. runs/Jul23_19-00-03_epimelesi/events.out.tfevents.1721754004.epimelesi.3817747.0 +3 -0
  25. runs/Jul24_11-58-40_epimelesi/events.out.tfevents.1721815121.epimelesi.3955857.0 +3 -0
  26. special_tokens_map.json +24 -0
  27. tokenizer.json +0 -0
  28. tokenizer_config.json +41 -0
  29. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ tags:
4
+ - trl
5
+ - sft
6
+ - generated_from_trainer
7
+ base_model: gizemgg/Llama-2-7b-chat-hf-finetuned-wiki-eng-summary-trial-gen5
8
+ model-index:
9
+ - name: results
10
+ results: []
11
+ ---
12
+
13
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
+ should probably proofread and complete it, then remove this comment. -->
15
+
16
+ # results
17
+
18
+ This model is a fine-tuned version of [gizemgg/Llama-2-7b-chat-hf-finetuned-wiki-eng-summary-trial-gen5](https://huggingface.co/gizemgg/Llama-2-7b-chat-hf-finetuned-wiki-eng-summary-trial-gen5) on an unknown dataset.
19
+ It achieves the following results on the evaluation set:
20
+ - Loss: 0.8774
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 3e-05
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 16
42
+ - seed: 42
43
+ - gradient_accumulation_steps: 16
44
+ - total_train_batch_size: 256
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: constant
47
+ - lr_scheduler_warmup_ratio: 0.03
48
+ - num_epochs: 5
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 1.0487 | 0.93 | 6 | 0.9595 |
55
+ | 1.0306 | 1.86 | 12 | 0.9414 |
56
+ | 0.8627 | 2.95 | 19 | 0.9183 |
57
+ | 0.9787 | 3.88 | 25 | 0.8934 |
58
+ | 0.7588 | 4.66 | 30 | 0.8774 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - PEFT 0.8.2
64
+ - Transformers 4.39.3
65
+ - Pytorch 2.1.2+cu121
66
+ - Datasets 2.17.0
67
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "gizemgg/Llama-2-7b-chat-hf-finetuned-wiki-eng-summary-trial-gen5",
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": 32,
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
+ "q_proj",
23
+ "v_proj"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_rslora": false
27
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbdfdc38beddfcc17276862eb15c637fbd3a296f11be52c3a61a9174f6650a8a
3
+ size 33571624
runs/Jul12_18-35-39_epimelesi/events.out.tfevents.1720802141.epimelesi.1623326.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:480a704b8f446547657830766c2de6ae2510350f4fce98ea5d081e7ca63ef668
3
+ size 5124
runs/Jul12_18-37-02_epimelesi/events.out.tfevents.1720802223.epimelesi.1623661.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebf9566873e8bc8cc2217cc8fde537c425e8ccdf8a996f9d383fbba8e9459963
3
+ size 5124
runs/Jul12_18-40-55_epimelesi/events.out.tfevents.1720802456.epimelesi.1624208.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb66635d8df3a907671ad605c3025183d524dbf7072badbab0bd7f0d04ae8dc8
3
+ size 5123
runs/Jul12_18-44-13_epimelesi/events.out.tfevents.1720802654.epimelesi.1624683.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bbf88ca29f68aab6f16279a96013cdd827e7a85a31a0cf6f0dd7a146a0166cc
3
+ size 5123
runs/Jul12_18-49-48_epimelesi/events.out.tfevents.1720802989.epimelesi.1625642.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b00f613ff9a3d699ee2de780b246b56e9299ff3ef2348cb22a47335d2263da1d
3
+ size 5123
runs/Jul13_12-03-49_epimelesi/events.out.tfevents.1720865030.epimelesi.1692642.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fbd0453bb69f476beed6d3b27e48a2632fb5d8ef0b9bfb0b582a64bc4272ab5
3
+ size 5122
runs/Jul13_14-33-16_epimelesi/events.out.tfevents.1720873997.epimelesi.1700907.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d76bac552158db1abc3354bb4cf1322b5faa312dcff32771b3f774afcad8fd1
3
+ size 5122
runs/Jul13_14-35-25_epimelesi/events.out.tfevents.1720874125.epimelesi.1701742.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20f7cc1fcfe9d9271a2de1a1518dfd51ea56613b2ac6f4fa249714efe5c57180
3
+ size 5122
runs/Jul13_14-36-30_epimelesi/events.out.tfevents.1720874190.epimelesi.1701849.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ef830fb1ea3f26f28ff5ae377a1e3d5d75c5c4e626b1ac64f7cafad39cfa3db
3
+ size 5122
runs/Jul13_14-38-10_epimelesi/events.out.tfevents.1720874290.epimelesi.1701960.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15bcec28201acf349919f240ec42a0a8987b62850f49e09182fa2ac8d8c81f67
3
+ size 7566
runs/Jul13_15-10-59_epimelesi/events.out.tfevents.1720876260.epimelesi.1704360.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:104a8c0323a9b570662c871c343729e19a61be293afbe8da11aa51696bd573a2
3
+ size 5122
runs/Jul13_15-13-16_epimelesi/events.out.tfevents.1720876396.epimelesi.1704518.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62fc5de77e525f3a3dc75c29e6caecb1c256daf920b30c38c7a520b7e910d712
3
+ size 7566
runs/Jul13_15-26-25_epimelesi/events.out.tfevents.1720877186.epimelesi.1705623.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d37280e715c922cc26762e09a62bf2b9b730bd8b2939891f20e04e444c64e4
3
+ size 7566
runs/Jul13_16-16-26_epimelesi/events.out.tfevents.1720880187.epimelesi.1708831.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63e18eee860655de0133d096ff6e4651fcce7d7b05d338bcc639f3748c4dbb54
3
+ size 7566
runs/Jul17_15-42-40_epimelesi/events.out.tfevents.1721223761.epimelesi.2235307.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf987c4eb8fa8df8871b1f9a5d3ec1539888ecc62dbaf4edf9145323b1833063
3
+ size 7566
runs/Jul17_15-50-24_epimelesi/events.out.tfevents.1721224225.epimelesi.2236716.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45f8c625ccdb4420f25b5c8d7b3bd2def64e70ae0c0e47f6b5683f231d746e26
3
+ size 7566
runs/Jul23_12-38-29_epimelesi/events.out.tfevents.1721731110.epimelesi.3760655.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b6ba5721479ba0111cc1f437e3e8b2b54e851693e953d02e4ac963436338111
3
+ size 6511
runs/Jul23_15-39-50_epimelesi/events.out.tfevents.1721741990.epimelesi.3784070.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7fb28adc3d69a123a07a853bb4278267ee11bbb71cb44d3feafd1d8b70064311
3
+ size 5470
runs/Jul23_16-00-33_epimelesi/events.out.tfevents.1721743233.epimelesi.3784070.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecd5963603c61aed1f91b0e657622c2983dd271ea3f097137f205f3d60f0b76d
3
+ size 5464
runs/Jul23_16-14-49_epimelesi/events.out.tfevents.1721744089.epimelesi.3784070.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:689be4f78bdb99d40d734faf442e2c171632b56b7c6198edda2064e40efcdf43
3
+ size 5465
runs/Jul23_19-00-03_epimelesi/events.out.tfevents.1721754004.epimelesi.3817747.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8633bc199c32919f6cd1c2c1f8756190d0ac32b5f4e4777419dccbb993b8680
3
+ size 5465
runs/Jul24_11-58-40_epimelesi/events.out.tfevents.1721815121.epimelesi.3955857.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1d8fa97af1f5ede1f64cf3cc63f949bb219e64aebeb739dd5d628db5fd635f
3
+ size 5465
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_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<unk>",
36
+ "padding_side": "right",
37
+ "sp_model_kwargs": {},
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34338fca95506119ca6587d505be9c973c584afc7196872b02ddecdd561d7aa0
3
+ size 4856