Hugging Face's logo

reeddg
/
tinyllama-colorist-v1

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
reeddg commited on
Commit
e8876bb
•
1 Parent(s): 54a6ad4

reeddg/colorsis

Browse files
Files changed (19) hide show
  1. README.md +59 -0
  2. adapter_config.json +27 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Feb09_00-44-53_DESKTOP-AGIMF38/events.out.tfevents.1707461125.DESKTOP-AGIMF38.18996.0 +3 -0
  5. runs/Feb09_01-07-37_DESKTOP-AGIMF38/events.out.tfevents.1707462473.DESKTOP-AGIMF38.18796.0 +3 -0
  6. runs/Feb09_01-17-54_DESKTOP-AGIMF38/events.out.tfevents.1707463082.DESKTOP-AGIMF38.4372.0 +3 -0
  7. runs/Feb09_08-01-18_DESKTOP-AGIMF38/events.out.tfevents.1707487291.DESKTOP-AGIMF38.9420.0 +3 -0
  8. runs/Feb09_08-35-01_DESKTOP-AGIMF38/events.out.tfevents.1707489304.DESKTOP-AGIMF38.19028.0 +3 -0
  9. runs/Feb09_08-51-58_DESKTOP-AGIMF38/events.out.tfevents.1707490339.DESKTOP-AGIMF38.16032.0 +3 -0
  10. runs/Feb09_09-05-33_DESKTOP-AGIMF38/events.out.tfevents.1707491150.DESKTOP-AGIMF38.3576.0 +3 -0
  11. runs/Feb09_15-56-43_DESKTOP-AGIMF38/events.out.tfevents.1707515821.DESKTOP-AGIMF38.21324.0 +3 -0
  12. runs/Feb09_16-10-37_DESKTOP-AGIMF38/events.out.tfevents.1707516661.DESKTOP-AGIMF38.22076.0 +3 -0
  13. runs/Feb09_16-17-51_DESKTOP-AGIMF38/events.out.tfevents.1707517083.DESKTOP-AGIMF38.18288.0 +3 -0
  14. runs/Feb09_16-23-42_DESKTOP-AGIMF38/events.out.tfevents.1707517435.DESKTOP-AGIMF38.18344.0 +3 -0
  15. runs/Feb09_16-53-48_DESKTOP-AGIMF38/events.out.tfevents.1707519240.DESKTOP-AGIMF38.2984.0 +3 -0
  16. special_tokens_map.json +24 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +42 -0
  19. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ model-index:
10
+ - name: tinyllama-colorist-v1
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
+ # tinyllama-colorist-v1
18
+
19
+ 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 None dataset.
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0002
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - num_epochs: 3
47
+ - mixed_precision_training: Native AMP
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - PEFT 0.8.2
56
+ - Transformers 4.37.2
57
+ - Pytorch 2.1.2+cu118
58
+ - Datasets 2.16.1
59
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
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": 0.05,
14
+ "megatron_config": null,
15
+ "megatron_core": "megatron.core",
16
+ "modules_to_save": null,
17
+ "peft_type": "LORA",
18
+ "r": 8,
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 sha256:4bd3a747a05500a3a90b81d8111f84d515155890a7bdf865de801ce1ec5ba0ec
3
+ size 4517152
runs/Feb09_00-44-53_DESKTOP-AGIMF38/events.out.tfevents.1707461125.DESKTOP-AGIMF38.18996.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:051e8e70c062c83f0af78f4ceb013e26021f0fb7b89f8d1e48c31185114e43a9
3
+ size 4811
runs/Feb09_01-07-37_DESKTOP-AGIMF38/events.out.tfevents.1707462473.DESKTOP-AGIMF38.18796.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c56b11b04d80e33fffbaf37d7adada7f0bb93695c4f65433827bea19c915f80d
3
+ size 4811
runs/Feb09_01-17-54_DESKTOP-AGIMF38/events.out.tfevents.1707463082.DESKTOP-AGIMF38.4372.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcc3d53098f89b79b2bca497e2dce80c3b7903259e2a4353a4053213386c6a21
3
+ size 4811
runs/Feb09_08-01-18_DESKTOP-AGIMF38/events.out.tfevents.1707487291.DESKTOP-AGIMF38.9420.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52074a302132bb5458ff9bc8fe656f2782a46cf06403a9b557d3bd66af6275d5
3
+ size 4811
runs/Feb09_08-35-01_DESKTOP-AGIMF38/events.out.tfevents.1707489304.DESKTOP-AGIMF38.19028.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:205929fbef3703bc5493f8bac7a7c1dde3f43f0fa1c3cb4f0b13e201f67893c7
3
+ size 4811
runs/Feb09_08-51-58_DESKTOP-AGIMF38/events.out.tfevents.1707490339.DESKTOP-AGIMF38.16032.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02c0e13f467ef1857d0ed42baeefd2ef425f75b5a3ae9325723843af0c51937f
3
+ size 4811
runs/Feb09_09-05-33_DESKTOP-AGIMF38/events.out.tfevents.1707491150.DESKTOP-AGIMF38.3576.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fac9b11fbcd88372c147643bdcf4c4d0bd27d89a3bbce866b7d1148a75d10374
3
+ size 4811
runs/Feb09_15-56-43_DESKTOP-AGIMF38/events.out.tfevents.1707515821.DESKTOP-AGIMF38.21324.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4aa99ff660b5f79d2a787aca6ed0b8c61035334057014b91efdc5603651daae8
3
+ size 4812
runs/Feb09_16-10-37_DESKTOP-AGIMF38/events.out.tfevents.1707516661.DESKTOP-AGIMF38.22076.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bed943ca8bb443f37217b23aa8b02306d5bc88c07e6436a39f0c56c97bbe29fb
3
+ size 4812
runs/Feb09_16-17-51_DESKTOP-AGIMF38/events.out.tfevents.1707517083.DESKTOP-AGIMF38.18288.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08ea91e80439c9bc476339e253f6602097ebd9c2333f7ccffe748c1ff416fee8
3
+ size 4812
runs/Feb09_16-23-42_DESKTOP-AGIMF38/events.out.tfevents.1707517435.DESKTOP-AGIMF38.18344.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7db289d097502085f6edbd3122832d25800979a03789c9076964e5a07d029d0
3
+ size 4810
runs/Feb09_16-53-48_DESKTOP-AGIMF38/events.out.tfevents.1707519240.DESKTOP-AGIMF38.2984.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5860a3754681a685c2f6c3450e22d058cbad7d88b8785c3e765732937b00cf1d
3
+ size 5312
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_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 sha256:700f4822c71336cdcdd6822f875194906a198089bd2b13d8475ab213defddae5
3
+ size 4728