Hugging Face's logo

minmingzhu02
/
Mistral-7B-v0.1-habana-lora

PEFT
TensorBoard
Safetensors
Habana
Model card Files Metrics Community
minmingzhu02 commited on
Commit
8c2b929
•
1 Parent(s): 171f3ab

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.safetensors +3 -0
  4. all_results.json +17 -0
  5. eval_results.json +13 -0
  6. gaudi_config.json +10 -0
  7. runs/Jun01_01-29-09_98fb9b040efd/events.out.tfevents.1717207299.98fb9b040efd.26963.0 +3 -0
  8. runs/Jun01_07-30-18_98fb9b040efd/events.out.tfevents.1717228943.98fb9b040efd.42641.0 +3 -0
  9. runs/Jun01_08-34-26_98fb9b040efd/events.out.tfevents.1717232794.98fb9b040efd.55437.0 +3 -0
  10. runs/Jun01_14-10-09_98fb9b040efd/events.out.tfevents.1717252914.98fb9b040efd.70147.0 +3 -0
  11. runs/Jun01_15-44-47_98fb9b040efd/events.out.tfevents.1717258594.98fb9b040efd.78814.0 +3 -0
  12. runs/Jun04_14-46-44_9d340316bc35/events.out.tfevents.1717513705.9d340316bc35.3442.0 +3 -0
  13. runs/Jun04_14-46-44_9d340316bc35/events.out.tfevents.1717523881.9d340316bc35.3442.1 +3 -0
  14. runs/May31_07-36-23_168983ccfa2d/events.out.tfevents.1717142911.168983ccfa2d.16647.0 +3 -0
  15. runs/May31_10-09-07_168983ccfa2d/events.out.tfevents.1717152071.168983ccfa2d.39530.0 +3 -0
  16. runs/May31_14-13-18_98fb9b040efd/events.out.tfevents.1717166745.98fb9b040efd.388.0 +3 -0
  17. runs/May31_15-18-30_98fb9b040efd/events.out.tfevents.1717170636.98fb9b040efd.18218.0 +3 -0
  18. special_tokens_map.json +12 -0
  19. tokenizer.json +0 -0
  20. tokenizer.model +3 -0
  21. tokenizer_config.json +42 -0
  22. train_results.json +10 -0
  23. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 8,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e5e6f12137445a7824c154a682d97f46030c9f7bb5987a97293f75617cc5b7b
3
+ size 6832728
all_results.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.4639155611944004,
4
+ "eval_loss": 1.0861796140670776,
5
+ "eval_runtime": 144.8,
6
+ "eval_samples": 25899,
7
+ "eval_samples_per_second": 183.416,
8
+ "eval_steps_per_second": 2.868,
9
+ "max_memory_allocated (GB)": 91.29,
10
+ "memory_allocated (GB)": 20.51,
11
+ "perplexity": 2.96293287540469,
12
+ "total_memory_available (GB)": 94.62,
13
+ "train_loss": 1.0007781735929895,
14
+ "train_runtime": 10023.6622,
15
+ "train_samples_per_second": 148.487,
16
+ "train_steps_per_second": 1.16
17
+ }
eval_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "eval_accuracy": 0.4639155611944004,
4
+ "eval_loss": 1.0861796140670776,
5
+ "eval_runtime": 144.8,
6
+ "eval_samples": 25899,
7
+ "eval_samples_per_second": 183.416,
8
+ "eval_steps_per_second": 2.868,
9
+ "max_memory_allocated (GB)": 91.29,
10
+ "memory_allocated (GB)": 20.51,
11
+ "perplexity": 2.96293287540469,
12
+ "total_memory_available (GB)": 94.62
13
+ }
gaudi_config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "autocast_bf16_ops": null,
3
+ "autocast_fp32_ops": null,
4
+ "optimum_version": "1.20.0",
5
+ "transformers_version": "4.38.2",
6
+ "use_dynamic_shapes": false,
7
+ "use_fused_adam": true,
8
+ "use_fused_clip_norm": true,
9
+ "use_torch_autocast": false
10
+ }
runs/Jun01_01-29-09_98fb9b040efd/events.out.tfevents.1717207299.98fb9b040efd.26963.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eed67111f12e0e3d741aadbd91aa1c3d20df829cac22f93c206e9815d613719b
3
+ size 5275
runs/Jun01_07-30-18_98fb9b040efd/events.out.tfevents.1717228943.98fb9b040efd.42641.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:725fcddf3a66f6aedddc46541eeda5291b51ec507d57beebc104207b553f9bb7
3
+ size 5288
runs/Jun01_08-34-26_98fb9b040efd/events.out.tfevents.1717232794.98fb9b040efd.55437.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fad9097d3e535503cff782bdbd47aca18ab98f0c52724ea76d0d2d519da73664
3
+ size 5288
runs/Jun01_14-10-09_98fb9b040efd/events.out.tfevents.1717252914.98fb9b040efd.70147.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:553b002cd8532a819193bf0ec1f47365d6feec36b1c96cb8bd3752acb28bf256
3
+ size 5264
runs/Jun01_15-44-47_98fb9b040efd/events.out.tfevents.1717258594.98fb9b040efd.78814.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2b7bdf7efe095669b06a4aea6f9fc998db78dfe02c525939fd9f5f97514187c
3
+ size 5264
runs/Jun04_14-46-44_9d340316bc35/events.out.tfevents.1717513705.9d340316bc35.3442.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6bd131bcfa2f099bc59418adbca09e06c1a8f57f6ed06ae9392201ed54c26a44
3
+ size 4836774
runs/Jun04_14-46-44_9d340316bc35/events.out.tfevents.1717523881.9d340316bc35.3442.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6771408d1b1d9da84b899589709148c7927b7c74bc05e5c2ddbf7a15cc737ac
3
+ size 571
runs/May31_07-36-23_168983ccfa2d/events.out.tfevents.1717142911.168983ccfa2d.16647.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3500bfbaf350a5473d12d2602ee1e8ae0bf1e4a5d5b99795ddc6826a039f8f2c
3
+ size 5204
runs/May31_10-09-07_168983ccfa2d/events.out.tfevents.1717152071.168983ccfa2d.39530.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe5495619d4d0586fa13ff7ca48d47f59f02769311cb81b1b08bcb447dd35622
3
+ size 5204
runs/May31_14-13-18_98fb9b040efd/events.out.tfevents.1717166745.98fb9b040efd.388.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:930d34b01f3551fb6f451e82a0c7605548828382f4c9559cae17226dac219531
3
+ size 5204
runs/May31_15-18-30_98fb9b040efd/events.out.tfevents.1717170636.98fb9b040efd.18218.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a5383770fa886d321dba2cda038c99d55718f47e3a109bffc9bd7d60a967594
3
+ size 5204
special_tokens_map.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ }
12
+ }
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false
42
+ }
train_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "max_memory_allocated (GB)": 91.29,
4
+ "memory_allocated (GB)": 20.51,
5
+ "total_memory_available (GB)": 94.62,
6
+ "train_loss": 1.0007781735929895,
7
+ "train_runtime": 10023.6622,
8
+ "train_samples_per_second": 148.487,
9
+ "train_steps_per_second": 1.16
10
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49580d318555f90ea2a27a0a15c9bd5e89af013379c376f36a54dec7cb029fce
3
+ size 4792