Hugging Face's logo

jonathanjordan21
/
outputs

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
jonathanjordan21 commited on
Commit
92752bc
•
1 Parent(s): 5e27782

TinyLlama-kompres

Browse files
Files changed (19) hide show
  1. README.md +53 -0
  2. adapter_config.json +33 -0
  3. adapter_model.safetensors +3 -0
  4. added_tokens.json +3 -0
  5. runs/May13_15-44-22_7227ea33cbdb/events.out.tfevents.1715615072.7227ea33cbdb.809.0 +3 -0
  6. runs/May13_15-45-34_7227ea33cbdb/events.out.tfevents.1715615136.7227ea33cbdb.809.1 +3 -0
  7. runs/May13_15-46-02_7227ea33cbdb/events.out.tfevents.1715615164.7227ea33cbdb.809.2 +3 -0
  8. runs/May13_15-49-06_7227ea33cbdb/events.out.tfevents.1715615349.7227ea33cbdb.1378.0 +3 -0
  9. runs/May13_15-50-50_7227ea33cbdb/events.out.tfevents.1715615500.7227ea33cbdb.1491.0 +3 -0
  10. runs/May13_15-54-31_7227ea33cbdb/events.out.tfevents.1715615720.7227ea33cbdb.1491.1 +3 -0
  11. runs/May13_16-01-13_7227ea33cbdb/events.out.tfevents.1715616123.7227ea33cbdb.1491.2 +3 -0
  12. runs/May13_16-03-19_7227ea33cbdb/events.out.tfevents.1715616249.7227ea33cbdb.1491.3 +3 -0
  13. runs/May13_16-08-41_7227ea33cbdb/events.out.tfevents.1715616537.7227ea33cbdb.1491.4 +3 -0
  14. runs/May13_16-23-51_7227ea33cbdb/events.out.tfevents.1715617438.7227ea33cbdb.1491.5 +3 -0
  15. special_tokens_map.json +30 -0
  16. tokenizer.json +0 -0
  17. tokenizer.model +3 -0
  18. tokenizer_config.json +49 -0
  19. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,53 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-v0.1
9
+ model-index:
10
+ - name: outputs
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
+ # outputs
18
+
19
+ This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v0.1](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v0.1) 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: 5e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - num_epochs: 3.0
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Framework versions
48
+
49
+ - PEFT 0.10.0
50
+ - Transformers 4.40.2
51
+ - Pytorch 2.1.2
52
+ - Datasets 2.19.1
53
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 32,
14
+ "lora_dropout": 0.01,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 8,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "k_proj",
24
+ "q_proj",
25
+ "up_proj",
26
+ "v_proj",
27
+ "down_proj",
28
+ "o_proj"
29
+ ],
30
+ "task_type": "CAUSAL_LM",
31
+ "use_dora": false,
32
+ "use_rslora": false
33
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:090d762725b6c79552fe41ebe8a71d8b143aa5d8653536489b2ceefa5aaf47cd
3
+ size 19868224
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "[PAD]": 32000
3
+ }
runs/May13_15-44-22_7227ea33cbdb/events.out.tfevents.1715615072.7227ea33cbdb.809.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:612490149094d4ae9375e61b095048bcd35235c5ac9babedd1c739d7de781157
3
+ size 5190
runs/May13_15-45-34_7227ea33cbdb/events.out.tfevents.1715615136.7227ea33cbdb.809.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aaba8bfbd2770dcfeae5054d74eb869e8b1619b128ed15b785c4745e55e089f
3
+ size 4184
runs/May13_15-46-02_7227ea33cbdb/events.out.tfevents.1715615164.7227ea33cbdb.809.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67699cd1bafc54901dc0dc9f785ba9b398d5aa71de4680d6f2743102e5dce6df
3
+ size 8280
runs/May13_15-49-06_7227ea33cbdb/events.out.tfevents.1715615349.7227ea33cbdb.1378.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e399349f29366ee9566d54b8c29ad94398a56668933ea27f81d401c7240e38eb
3
+ size 4184
runs/May13_15-50-50_7227ea33cbdb/events.out.tfevents.1715615500.7227ea33cbdb.1491.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a540480a1d7f5ca006a9830daa46a4b78f7a2d31501f9a2bb2c984fdbb73c18
3
+ size 5586
runs/May13_15-54-31_7227ea33cbdb/events.out.tfevents.1715615720.7227ea33cbdb.1491.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26e5dba4b13cbdf45170bc45fb411ed80568364a8c2dbc9f04bd878e654792b3
3
+ size 20424
runs/May13_16-01-13_7227ea33cbdb/events.out.tfevents.1715616123.7227ea33cbdb.1491.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80541b0d0adb0d35de468d6a0a867b1d8d71ba84910f8658c1a4c08cfc5bbd11
3
+ size 25508
runs/May13_16-03-19_7227ea33cbdb/events.out.tfevents.1715616249.7227ea33cbdb.1491.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56483a0e2522747cacfbeef108214b1b9fd5c62d48295dcf41ef519daa1ea0e5
3
+ size 21236
runs/May13_16-08-41_7227ea33cbdb/events.out.tfevents.1715616537.7227ea33cbdb.1491.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a67f4fac2b291e9417e4a52fc4dc6d55a893b11ac7cf3932817f678982a9ff4e
3
+ size 22271
runs/May13_16-23-51_7227ea33cbdb/events.out.tfevents.1715617438.7227ea33cbdb.1491.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3496bba14ec0d78336f89367a9578053c2320f89bda65782686c58cf2a1757e6
3
+ size 38936
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "32000": {
30
+ "content": "[PAD]",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ }
37
+ },
38
+ "bos_token": "<s>",
39
+ "clean_up_tokenization_spaces": false,
40
+ "eos_token": "</s>",
41
+ "legacy": false,
42
+ "model_max_length": 1000000000000000019884624838656,
43
+ "pad_token": "[PAD]",
44
+ "padding_side": "right",
45
+ "sp_model_kwargs": {},
46
+ "tokenizer_class": "LlamaTokenizer",
47
+ "unk_token": "<unk>",
48
+ "use_default_system_prompt": true
49
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ce2eb543bd9dd5c3ceb22856b057a4a873376353a95d9530bcdfdefc3aba681
3
+ size 4984