Hugging Face's logo

TanviGupta
/
results

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
TanviGupta commited on
Commit
db1b21c
·
1 Parent(s): edd443c

End of training

Browse files
Files changed (17) hide show
  1. README.md +59 -0
  2. adapter_config.json +30 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Dec25_14-41-51_ip-172-31-28-206/events.out.tfevents.1703515347.ip-172-31-28-206.3823.0 +3 -0
  5. runs/Dec25_15-07-08_ip-172-31-28-206/events.out.tfevents.1703516840.ip-172-31-28-206.4585.0 +3 -0
  6. runs/Dec27_00-11-34_ip-172-31-28-206/events.out.tfevents.1703635992.ip-172-31-28-206.1706.0 +3 -0
  7. runs/Dec27_00-14-49_ip-172-31-28-206/events.out.tfevents.1703636169.ip-172-31-28-206.1706.1 +3 -0
  8. runs/Jan02_20-24-33_ip-172-31-28-206/events.out.tfevents.1704227162.ip-172-31-28-206.1729.0 +3 -0
  9. runs/Jan03_06-18-41_ip-172-31-28-206/events.out.tfevents.1704262731.ip-172-31-28-206.2007.0 +3 -0
  10. runs/Jan04_04-41-06_ip-172-31-28-206/events.out.tfevents.1704343289.ip-172-31-28-206.2082.0 +3 -0
  11. runs/Jan04_04-52-07_ip-172-31-28-206/events.out.tfevents.1704343935.ip-172-31-28-206.2324.0 +3 -0
  12. runs/Jan04_05-31-53_ip-172-31-28-206/events.out.tfevents.1704346320.ip-172-31-28-206.3755.0 +3 -0
  13. special_tokens_map.json +24 -0
  14. tokenizer.json +0 -0
  15. tokenizer.model +3 -0
  16. tokenizer_config.json +42 -0
  17. 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: mistralai/Mistral-7B-v0.1
9
+ model-index:
10
+ - name: results
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
+ # results
18
+
19
+ This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on an unknown 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: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 16
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: constant
46
+ - lr_scheduler_warmup_ratio: 0.3
47
+ - num_epochs: 1
48
+
49
+ ### Training results
50
+
51
+
52
+
53
+ ### Framework versions
54
+
55
+ - PEFT 0.7.2.dev0
56
+ - Transformers 4.37.0.dev0
57
+ - Pytorch 2.1.1+cu121
58
+ - Datasets 2.16.1
59
+ - Tokenizers 0.15.0
adapter_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "mistralai/Mistral-7B-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
+ "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": 16,
19
+ "rank_pattern": {},
20
+ "revision": null,
21
+ "target_modules": [
22
+ "k_proj",
23
+ "v_proj",
24
+ "q_proj",
25
+ "o_proj",
26
+ "gate_proj"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_rslora": false
30
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a4dad282f6dbc6cb198fafe17cec539b20c5e665e365184c5c53cbf65667682c
3
+ size 92317600
runs/Dec25_14-41-51_ip-172-31-28-206/events.out.tfevents.1703515347.ip-172-31-28-206.3823.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b04c4ed056555be05e028e6093182ace6530a443102aa6acac969ea7a913468e
3
+ size 6283
runs/Dec25_15-07-08_ip-172-31-28-206/events.out.tfevents.1703516840.ip-172-31-28-206.4585.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4725537ec824fd8921cdfbb9a9a30a260dc91ddc1ae2db08293380bdaf6c869
3
+ size 6283
runs/Dec27_00-11-34_ip-172-31-28-206/events.out.tfevents.1703635992.ip-172-31-28-206.1706.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc70985eac82fa07feb31e5f161b02085b346232c36ae195a704755d766f2821
3
+ size 4768
runs/Dec27_00-14-49_ip-172-31-28-206/events.out.tfevents.1703636169.ip-172-31-28-206.1706.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c66451c7d2cb0817b3a9fbc1209045485c5a3ef135627422635b2a8111bf39ee
3
+ size 6326
runs/Jan02_20-24-33_ip-172-31-28-206/events.out.tfevents.1704227162.ip-172-31-28-206.1729.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de9993a4eb0471cd4e79207d53eca2333837a7708b6462209f0e9ea6482757f4
3
+ size 19043
runs/Jan03_06-18-41_ip-172-31-28-206/events.out.tfevents.1704262731.ip-172-31-28-206.2007.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b956315f56fad1817fee76601d29741e7c70a5ca70dca7ce9d914ac912ef09d7
3
+ size 5424
runs/Jan04_04-41-06_ip-172-31-28-206/events.out.tfevents.1704343289.ip-172-31-28-206.2082.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db92955c9d980f03b60b968dd9d5fcb0db94645216594947c2c9c385d90fcea2
3
+ size 4768
runs/Jan04_04-52-07_ip-172-31-28-206/events.out.tfevents.1704343935.ip-172-31-28-206.2324.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a69d1157bef5e7374f6996efd2b3757a57ac42bbb47b426ba2b1513e6d67df83
3
+ size 5424
runs/Jan04_05-31-53_ip-172-31-28-206/events.out.tfevents.1704346320.ip-172-31-28-206.3755.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6e2a6c355b9d9d7941f4eb476e45b589d63b77cfb93c3641e558e679ea8be8
3
+ size 5424
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b669163959a46ab00d8635154393a6615b209eaa8b3caf48ec3c4e180c0265b
3
+ size 4728