Hugging Face's logo

tcarwash
/
tinyllama_instruct

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
tcarwash commited on
Commit
96e6338
•
1 Parent(s): e6f70f0

tcarwash/tinyllama-instruct

Browse files
Files changed (34) hide show
  1. README.md +67 -0
  2. adapter_config.json +29 -0
  3. adapter_model.safetensors +3 -0
  4. runs/May03_16-28-17_6e578374fda8/events.out.tfevents.1714753725.6e578374fda8.360.0 +3 -0
  5. runs/May03_16-52-19_6e578374fda8/events.out.tfevents.1714755159.6e578374fda8.360.1 +3 -0
  6. runs/May03_17-10-59_6e578374fda8/events.out.tfevents.1714756259.6e578374fda8.360.2 +3 -0
  7. runs/May03_17-15-43_6e578374fda8/events.out.tfevents.1714756547.6e578374fda8.360.3 +3 -0
  8. runs/May03_17-37-49_6e578374fda8/events.out.tfevents.1714757873.6e578374fda8.360.4 +3 -0
  9. runs/May03_17-56-55_6e578374fda8/events.out.tfevents.1714759019.6e578374fda8.360.5 +3 -0
  10. runs/May03_18-00-28_6e578374fda8/events.out.tfevents.1714759229.6e578374fda8.360.6 +3 -0
  11. runs/May03_18-04-27_6e578374fda8/events.out.tfevents.1714759471.6e578374fda8.360.7 +3 -0
  12. runs/May03_18-08-22_6e578374fda8/events.out.tfevents.1714759706.6e578374fda8.360.8 +3 -0
  13. runs/May03_18-12-13_6e578374fda8/events.out.tfevents.1714759936.6e578374fda8.360.9 +3 -0
  14. runs/May03_18-15-53_6e578374fda8/events.out.tfevents.1714760153.6e578374fda8.360.10 +3 -0
  15. runs/May03_18-16-37_6e578374fda8/events.out.tfevents.1714760198.6e578374fda8.360.11 +3 -0
  16. runs/May03_18-17-51_6e578374fda8/events.out.tfevents.1714760272.6e578374fda8.360.12 +3 -0
  17. runs/May03_18-32-14_6e578374fda8/events.out.tfevents.1714761138.6e578374fda8.360.13 +3 -0
  18. runs/May03_18-35-02_6e578374fda8/events.out.tfevents.1714761303.6e578374fda8.360.14 +3 -0
  19. runs/May03_18-45-53_6e578374fda8/events.out.tfevents.1714761958.6e578374fda8.360.15 +3 -0
  20. runs/May03_19-04-27_6e578374fda8/events.out.tfevents.1714763071.6e578374fda8.360.16 +3 -0
  21. runs/May03_19-07-48_6e578374fda8/events.out.tfevents.1714763271.6e578374fda8.360.17 +3 -0
  22. runs/May03_19-08-35_6e578374fda8/events.out.tfevents.1714763315.6e578374fda8.360.18 +3 -0
  23. runs/May03_19-08-57_6e578374fda8/events.out.tfevents.1714763338.6e578374fda8.360.19 +3 -0
  24. runs/May03_19-11-06_6e578374fda8/events.out.tfevents.1714763467.6e578374fda8.360.20 +3 -0
  25. runs/May03_19-11-26_6e578374fda8/events.out.tfevents.1714763490.6e578374fda8.360.21 +3 -0
  26. runs/May03_19-11-56_6e578374fda8/events.out.tfevents.1714763516.6e578374fda8.360.22 +3 -0
  27. runs/May03_19-23-04_6e578374fda8/events.out.tfevents.1714764187.6e578374fda8.360.23 +3 -0
  28. runs/May03_19-26-56_6e578374fda8/events.out.tfevents.1714764421.6e578374fda8.360.24 +3 -0
  29. runs/May03_19-27-18_6e578374fda8/events.out.tfevents.1714764438.6e578374fda8.360.25 +3 -0
  30. special_tokens_map.json +24 -0
  31. tokenizer.json +0 -0
  32. tokenizer.model +3 -0
  33. tokenizer_config.json +42 -0
  34. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,67 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: tinyllama/tinyllama-1.1b-chat-v1.0
9
+ datasets:
10
+ - generator
11
+ model-index:
12
+ - name: tinyllama_instruct
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
+ # tinyllama_instruct
20
+
21
+ This model is a fine-tuned version of [tinyllama/tinyllama-1.1b-chat-v1.0](https://huggingface.co/tinyllama/tinyllama-1.1b-chat-v1.0) on the generator dataset.
22
+ It achieves the following results on the evaluation set:
23
+ - Loss: 1.2777
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: 0.0002
43
+ - train_batch_size: 1
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: constant
48
+ - lr_scheduler_warmup_steps: 0.03
49
+ - training_steps: 100
50
+ - mixed_precision_training: Native AMP
51
+
52
+ ### Training results
53
+
54
+ | Training Loss | Epoch | Step | Validation Loss |
55
+ |:-------------:|:------:|:----:|:---------------:|
56
+ | 1.5934 | 0.0281 | 30 | 1.3952 |
57
+ | 1.4781 | 0.0561 | 60 | 1.2923 |
58
+ | 1.3692 | 0.0842 | 90 | 1.2777 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - PEFT 0.10.0
64
+ - Transformers 4.40.1
65
+ - Pytorch 2.2.1+cu121
66
+ - Datasets 2.19.0
67
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "v_proj",
24
+ "q_proj"
25
+ ],
26
+ "task_type": "CAUSAL_LM",
27
+ "use_dora": false,
28
+ "use_rslora": false
29
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4204c41fd9cf7cf80f2f626bab7e8536e11fb9511d25dfeb0a19218a764feba6
3
+ size 36070072
runs/May03_16-28-17_6e578374fda8/events.out.tfevents.1714753725.6e578374fda8.360.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef21814facef2f0bdeed022609174800c44fc119aea7390596048b10d5d9068
3
+ size 8958
runs/May03_16-52-19_6e578374fda8/events.out.tfevents.1714755159.6e578374fda8.360.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a0847e0d7094ee19ba4007085588c9f26596eb8c96c1761e28142aeef4f04a9b
3
+ size 8958
runs/May03_17-10-59_6e578374fda8/events.out.tfevents.1714756259.6e578374fda8.360.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa1d5a2e63d837f4e106e8babc73da9764a2d08c264e642155fabc795d1d5317
3
+ size 5210
runs/May03_17-15-43_6e578374fda8/events.out.tfevents.1714756547.6e578374fda8.360.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1c39fed8a358c0bf3ce24bc50fc58fc1192e039f1a7384af31e44bd967897b4
3
+ size 8957
runs/May03_17-37-49_6e578374fda8/events.out.tfevents.1714757873.6e578374fda8.360.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ebf6350cb0a378ba486c744a23013413383fb2cd3d2c6bbb1a1b90323a2ccde
3
+ size 8957
runs/May03_17-56-55_6e578374fda8/events.out.tfevents.1714759019.6e578374fda8.360.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:235e515e392cbc754838a5cd2131117758ef1d4158ef94d2e49eb7a86eff3b39
3
+ size 6236
runs/May03_18-00-28_6e578374fda8/events.out.tfevents.1714759229.6e578374fda8.360.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:facf5d522bba2fcb53304e36b92b87e9b1397cce6855ed6a6fdc5d09f9409d12
3
+ size 6236
runs/May03_18-04-27_6e578374fda8/events.out.tfevents.1714759471.6e578374fda8.360.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff8d8c17880202b854273be1f0ecc8b140660e67c54ae8e3e415054736c19070
3
+ size 6236
runs/May03_18-08-22_6e578374fda8/events.out.tfevents.1714759706.6e578374fda8.360.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b4fe18d70212db92cdd861374029305e040d6561fcc3ae1a6f585386574a795
3
+ size 6236
runs/May03_18-12-13_6e578374fda8/events.out.tfevents.1714759936.6e578374fda8.360.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9244d0a1df5a362aea3f9e657807c593a7a923a00b66881aab6dda5817cef39b
3
+ size 6236
runs/May03_18-15-53_6e578374fda8/events.out.tfevents.1714760153.6e578374fda8.360.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bead5e21f7cf798e321cfc84aae54aab60c6e13e6175fc2641c5afc0c44e993c
3
+ size 5208
runs/May03_18-16-37_6e578374fda8/events.out.tfevents.1714760198.6e578374fda8.360.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9d99afdf15cc44bb698eb59339eabc723c4b9e71b430d83be760897fd1b46cf
3
+ size 5209
runs/May03_18-17-51_6e578374fda8/events.out.tfevents.1714760272.6e578374fda8.360.12 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe2dbf4374b55361dcc1446c7650d45dce26a4a0b5c121bb69e61aef75b703e7
3
+ size 6236
runs/May03_18-32-14_6e578374fda8/events.out.tfevents.1714761138.6e578374fda8.360.13 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:916d039790ae178647fbba7d411a94684015e057d49ef026a0e72b917b86570c
3
+ size 6236
runs/May03_18-35-02_6e578374fda8/events.out.tfevents.1714761303.6e578374fda8.360.14 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51aea9519c6b89ee1d89bf932adaf95f184c154e13160c3641fb8e7de590ad90
3
+ size 6236
runs/May03_18-45-53_6e578374fda8/events.out.tfevents.1714761958.6e578374fda8.360.15 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:412354da3178f1484d623c7a33726cb6b25108b06e2e0a65e9a6d705121b71a2
3
+ size 6236
runs/May03_19-04-27_6e578374fda8/events.out.tfevents.1714763071.6e578374fda8.360.16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df908f890db4277f68419bdc7a8a8e652a1ab9376b339c942cbcd1ed86b494de
3
+ size 6237
runs/May03_19-07-48_6e578374fda8/events.out.tfevents.1714763271.6e578374fda8.360.17 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a06dec2724c5323eb37b5bc7c18acd1f8f510b4028c579d745199d15288866a5
3
+ size 6237
runs/May03_19-08-35_6e578374fda8/events.out.tfevents.1714763315.6e578374fda8.360.18 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:130c085a86f19175a24b09bda2984cdd0c0ddfa81c311637fcce3e30a5425644
3
+ size 6237
runs/May03_19-08-57_6e578374fda8/events.out.tfevents.1714763338.6e578374fda8.360.19 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:208f1c4faab15420e88083eb77bbaa671bf14681b5d18b3bf1aa6e22c8df63fe
3
+ size 8958
runs/May03_19-11-06_6e578374fda8/events.out.tfevents.1714763467.6e578374fda8.360.20 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c279f66678bab49d2812cb67709dda863c7c67d44827e5d051705d504fdd1411
3
+ size 5417
runs/May03_19-11-26_6e578374fda8/events.out.tfevents.1714763490.6e578374fda8.360.21 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4af2dbedb773e4c2077460fe47d698021a9d2bb4ab11bce41318544f6802fbe6
3
+ size 5210
runs/May03_19-11-56_6e578374fda8/events.out.tfevents.1714763516.6e578374fda8.360.22 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4755982ec08ba3a15f35da293aa17975c6961347787e4247434ffafca18addf5
3
+ size 8958
runs/May03_19-23-04_6e578374fda8/events.out.tfevents.1714764187.6e578374fda8.360.23 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8980a0632215160fdf4986b0bd2fcb35557b215fcb65c6032119d575045f13c8
3
+ size 8958
runs/May03_19-26-56_6e578374fda8/events.out.tfevents.1714764421.6e578374fda8.360.24 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e7beaf07dc02dea5fde2fe515c5670782dd5c731797444c5e22ec0897a2d46
3
+ size 5624
runs/May03_19-27-18_6e578374fda8/events.out.tfevents.1714764438.6e578374fda8.360.25 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2831ceafc91fc953b555927fb236066a8507395e5c4fc74b966f559dca98ab07
3
+ size 8426
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
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
+ "bos_token": "<s>",
31
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": false,
35
+ "model_max_length": 2048,
36
+ "pad_token": "</s>",
37
+ "padding_side": "right",
38
+ "sp_model_kwargs": {},
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 sha256:46039041093a7531d7e7d2a5693d18a64f1d1ba79cd53dd8c85c15a48434605b
3
+ size 4984