Hugging Face's logo

emptyngton
/
tmp_trainer

TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
emptyngton commited on
Commit
8ed1a87
•
1 Parent(s): d4fa978

emptyngton/mistral_voxtainference

Browse files
Files changed (19) hide show
  1. README.md +49 -0
  2. adapter_config.json +23 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Nov27_03-55-05_ad8f21fbd7ed/events.out.tfevents.1701057313.ad8f21fbd7ed.1602.0 +3 -0
  5. runs/Nov27_03-57-06_ad8f21fbd7ed/events.out.tfevents.1701057430.ad8f21fbd7ed.1602.1 +3 -0
  6. runs/Nov27_03-57-56_ad8f21fbd7ed/events.out.tfevents.1701057479.ad8f21fbd7ed.1602.2 +3 -0
  7. runs/Nov27_04-04-32_ad8f21fbd7ed/events.out.tfevents.1701057885.ad8f21fbd7ed.1602.3 +3 -0
  8. runs/Nov27_04-12-00_ad8f21fbd7ed/events.out.tfevents.1701058325.ad8f21fbd7ed.1602.4 +3 -0
  9. runs/Nov27_04-21-42_ad8f21fbd7ed/events.out.tfevents.1701058907.ad8f21fbd7ed.1602.5 +3 -0
  10. runs/Nov27_04-25-17_ad8f21fbd7ed/events.out.tfevents.1701059120.ad8f21fbd7ed.1602.6 +3 -0
  11. runs/Nov27_04-27-25_ad8f21fbd7ed/events.out.tfevents.1701059248.ad8f21fbd7ed.1602.7 +3 -0
  12. runs/Nov27_04-28-05_ad8f21fbd7ed/events.out.tfevents.1701059288.ad8f21fbd7ed.1602.8 +3 -0
  13. runs/Nov27_04-28-51_ad8f21fbd7ed/events.out.tfevents.1701059333.ad8f21fbd7ed.1602.9 +3 -0
  14. runs/Nov27_04-29-28_ad8f21fbd7ed/events.out.tfevents.1701059372.ad8f21fbd7ed.1602.10 +3 -0
  15. runs/Nov27_04-30-09_ad8f21fbd7ed/events.out.tfevents.1701059412.ad8f21fbd7ed.1602.11 +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 CHANGED
@@ -1,3 +1,52 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ base_model: mistralai/Mistral-7B-Instruct-v0.1
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: tmp_trainer
8
+ results: []
9
  ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # tmp_trainer
15
+
16
+ This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.1](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1) on an unknown dataset.
17
+
18
+ ## Model description
19
+
20
+ More information needed
21
+
22
+ ## Intended uses & limitations
23
+
24
+ More information needed
25
+
26
+ ## Training and evaluation data
27
+
28
+ More information needed
29
+
30
+ ## Training procedure
31
+
32
+ ### Training hyperparameters
33
+
34
+ The following hyperparameters were used during training:
35
+ - learning_rate: 5e-05
36
+ - train_batch_size: 8
37
+ - eval_batch_size: 8
38
+ - seed: 42
39
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
40
+ - lr_scheduler_type: linear
41
+ - num_epochs: 3.0
42
+
43
+ ### Training results
44
+
45
+
46
+
47
+ ### Framework versions
48
+
49
+ - Transformers 4.36.0.dev0
50
+ - Pytorch 2.1.0+cu118
51
+ - Datasets 2.15.0
52
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.1",
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
+ "lora_alpha": 16,
12
+ "lora_dropout": 0.1,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 64,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "v_proj",
20
+ "q_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d56ddce001af4dd76917bf09e4b604be0ff145024d1ad61af10d9952e1bcf28
3
+ size 109069176
runs/Nov27_03-55-05_ad8f21fbd7ed/events.out.tfevents.1701057313.ad8f21fbd7ed.1602.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e8e07d9382f870c1bd8c91cd06859891f213fdaaa34d5b5c12f71cea33427a
3
+ size 4706
runs/Nov27_03-57-06_ad8f21fbd7ed/events.out.tfevents.1701057430.ad8f21fbd7ed.1602.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b10c71f8c8b67b6a22d0e87c53241a8a92dbdcf542cc4906c197d6ec2bf5893e
3
+ size 4706
runs/Nov27_03-57-56_ad8f21fbd7ed/events.out.tfevents.1701057479.ad8f21fbd7ed.1602.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1df6c47418db4e85e5058e947ee1e9cc4ed5bc2b82693d78047e651e4c16ecfa
3
+ size 4706
runs/Nov27_04-04-32_ad8f21fbd7ed/events.out.tfevents.1701057885.ad8f21fbd7ed.1602.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c660c1fd5942eed772313e568a67cda4a1a251be9fbf0dc1aa4701378009f748
3
+ size 5054
runs/Nov27_04-12-00_ad8f21fbd7ed/events.out.tfevents.1701058325.ad8f21fbd7ed.1602.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1932aef6bf7e724fe76595b609c14a1deb8286ba943d953ba2cacbaf9e82aaaf
3
+ size 5054
runs/Nov27_04-21-42_ad8f21fbd7ed/events.out.tfevents.1701058907.ad8f21fbd7ed.1602.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3127dfc32a8573f78c5384fe48406136cc1e8aabe3b2b471a1c7a1635bf69e5
3
+ size 5054
runs/Nov27_04-25-17_ad8f21fbd7ed/events.out.tfevents.1701059120.ad8f21fbd7ed.1602.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e4ef9b1c950de6cb8c713424fb3ba9ebbaf1ec353107fc8e6667906b791a18c
3
+ size 5054
runs/Nov27_04-27-25_ad8f21fbd7ed/events.out.tfevents.1701059248.ad8f21fbd7ed.1602.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304d67adebf3305128a97a1212e391f49d39a01f1c9d10397fadb1f1fd4f721a
3
+ size 5054
runs/Nov27_04-28-05_ad8f21fbd7ed/events.out.tfevents.1701059288.ad8f21fbd7ed.1602.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f756073e2409c3eb7e9f5242cc1c47c3f9d03984c200e40dd50d2714699f8fc
3
+ size 5054
runs/Nov27_04-28-51_ad8f21fbd7ed/events.out.tfevents.1701059333.ad8f21fbd7ed.1602.9 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa85e0af7e0b148f3b3d09f09738c8bbfdf90542c2a54b91096d149aeab49384
3
+ size 5054
runs/Nov27_04-29-28_ad8f21fbd7ed/events.out.tfevents.1701059372.ad8f21fbd7ed.1602.10 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8797cf7fe8dd2489287aa96020992b90380256eab71b01bf56867e7222c253b7
3
+ size 5054
runs/Nov27_04-30-09_ad8f21fbd7ed/events.out.tfevents.1701059412.ad8f21fbd7ed.1602.11 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76933a7c17caf086527cbbde91b0c6065193251ec09fbfd87c8ff67d64648bea
3
+ size 5054
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
+ "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": true
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac9190f415126f9309d8639ab3c94a0422656ab2a49916d9b72b04e830e0df69
3
+ size 4664