Hugging Face's logo

silvente93
/
tfm_rev6

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
silvente93 commited on
Commit
a1dc86a
•
1 Parent(s): 5a9cf4b

End of training

Browse files
Files changed (22) hide show
  1. README.md +54 -0
  2. adapter_config.json +26 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Jan27_18-53-48_c89cf178032f/events.out.tfevents.1706381636.c89cf178032f.324.0 +3 -0
  5. runs/Jan27_19-11-51_c89cf178032f/events.out.tfevents.1706382716.c89cf178032f.5377.0 +3 -0
  6. runs/Jan27_19-12-28_c89cf178032f/events.out.tfevents.1706382758.c89cf178032f.5377.1 +3 -0
  7. runs/Jan27_19-13-15_c89cf178032f/events.out.tfevents.1706382800.c89cf178032f.5377.2 +3 -0
  8. runs/Jan27_19-13-54_c89cf178032f/events.out.tfevents.1706382841.c89cf178032f.5377.3 +3 -0
  9. runs/Jan27_19-15-26_c89cf178032f/events.out.tfevents.1706382935.c89cf178032f.5377.4 +3 -0
  10. runs/Jan27_19-15-52_c89cf178032f/events.out.tfevents.1706382959.c89cf178032f.5377.5 +3 -0
  11. runs/Jan27_19-16-12_c89cf178032f/events.out.tfevents.1706382977.c89cf178032f.5377.6 +3 -0
  12. runs/Jan27_19-16-37_c89cf178032f/events.out.tfevents.1706383003.c89cf178032f.5377.7 +3 -0
  13. runs/Jan27_19-16-54_c89cf178032f/events.out.tfevents.1706383019.c89cf178032f.5377.8 +3 -0
  14. runs/Jan27_19-19-30_c89cf178032f/events.out.tfevents.1706383175.c89cf178032f.7875.0 +3 -0
  15. runs/Jan27_19-21-23_c89cf178032f/events.out.tfevents.1706383288.c89cf178032f.7875.1 +3 -0
  16. runs/Jan27_19-21-42_c89cf178032f/events.out.tfevents.1706383308.c89cf178032f.7875.2 +3 -0
  17. runs/Jan27_19-31-58_c89cf178032f/events.out.tfevents.1706383929.c89cf178032f.7875.3 +3 -0
  18. special_tokens_map.json +24 -0
  19. tokenizer.json +0 -0
  20. tokenizer.model +3 -0
  21. tokenizer_config.json +43 -0
  22. training_args.bin +3 -0
README.md CHANGED
@@ -1,3 +1,57 @@
1
  ---
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
  license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: TheBloke/Mistral-7B-Instruct-v0.2-GPTQ
9
+ model-index:
10
+ - name: tfm_rev6
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
+ # tfm_rev6
18
+
19
+ This model is a fine-tuned version of [TheBloke/Mistral-7B-Instruct-v0.2-GPTQ](https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.2-GPTQ) 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: 0.0003
39
+ - train_batch_size: 32
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: cosine
44
+ - num_epochs: 2
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+
50
+
51
+ ### Framework versions
52
+
53
+ - PEFT 0.7.1
54
+ - Transformers 4.38.0.dev0
55
+ - Pytorch 2.1.0+cu121
56
+ - Datasets 2.16.1
57
+ - Tokenizers 0.15.1
adapter_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TheBloke/Mistral-7B-Instruct-v0.2-GPTQ",
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": 0.05,
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
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa710d2ba40988f0db89fd1fbff354081d38820005d5a34cbc9ba31f344d7523
3
+ size 27280152
runs/Jan27_18-53-48_c89cf178032f/events.out.tfevents.1706381636.c89cf178032f.324.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:796fa587be13b3f04281b1b1e01ff38dd2a79bbe67bdd1cc7cf61c8879d9150a
3
+ size 6102
runs/Jan27_19-11-51_c89cf178032f/events.out.tfevents.1706382716.c89cf178032f.5377.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:902143a4d5a04613119784de969872465f02c956af95f4ff09afeea8e757635d
3
+ size 5794
runs/Jan27_19-12-28_c89cf178032f/events.out.tfevents.1706382758.c89cf178032f.5377.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6838a2dff29a5445eefed0687355e9c799f76c587c1a4bbd3b77d434877bdc9
3
+ size 5794
runs/Jan27_19-13-15_c89cf178032f/events.out.tfevents.1706382800.c89cf178032f.5377.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6135167f021b0f0726cba3561bcfb7b4722b07e03c65ef80265d8b7cbf88f54
3
+ size 5333
runs/Jan27_19-13-54_c89cf178032f/events.out.tfevents.1706382841.c89cf178032f.5377.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13f18a489daa00e86cb67ce7875d6f712a25111d5c5df33e18a54dd0e65ae13b
3
+ size 5333
runs/Jan27_19-15-26_c89cf178032f/events.out.tfevents.1706382935.c89cf178032f.5377.4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b611296d4a41aaa075b0503d1f09ba433c2ac7e601867f63c79792e34b4000d
3
+ size 4184
runs/Jan27_19-15-52_c89cf178032f/events.out.tfevents.1706382959.c89cf178032f.5377.5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf478c66afa954eb030478dc0e0eab2b35086fcbcdbfbebb89116558654cd628
3
+ size 4184
runs/Jan27_19-16-12_c89cf178032f/events.out.tfevents.1706382977.c89cf178032f.5377.6 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bac99db36bd80ed5618814d4bf8e9b98ace1aeb924c7c4abad4b1902a472a264
3
+ size 4184
runs/Jan27_19-16-37_c89cf178032f/events.out.tfevents.1706383003.c89cf178032f.5377.7 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0da5f1c3da51b52f2013669aaeaccf9d5d313280654e350346f9c222a1adac9
3
+ size 4184
runs/Jan27_19-16-54_c89cf178032f/events.out.tfevents.1706383019.c89cf178032f.5377.8 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3162d9f6aba9fbfdf04b3122e9fbd9771e623773a0ef12ffc872e06b7531fc8
3
+ size 4184
runs/Jan27_19-19-30_c89cf178032f/events.out.tfevents.1706383175.c89cf178032f.7875.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dfae2faa6b87eb54f31de326178dc417590460db4606b6dfe7b7f7e73ef44d2
3
+ size 5026
runs/Jan27_19-21-23_c89cf178032f/events.out.tfevents.1706383288.c89cf178032f.7875.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f1cfa54af6ce18c869a69646134c95cbc802e092e0821a4e8c1941b5ab6b902
3
+ size 5025
runs/Jan27_19-21-42_c89cf178032f/events.out.tfevents.1706383308.c89cf178032f.7875.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83ab9f0071278b6bd22f725051ace44b93601147cb853a8d641f47088e60256c
3
+ size 10723
runs/Jan27_19-31-58_c89cf178032f/events.out.tfevents.1706383929.c89cf178032f.7875.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e7a5d99099c464f1f655db07f0be1ad9be47d050a27815dee37eb3e13831747
3
+ size 12149
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2df4892f8d93e184470cb8bd8d39f9db225e57a9d8d0e3fb83838cf4548640f3
3
+ size 4728