Hugging Face's logo

madhan2301
/
LLAMA_2_finetuned-v2

Text Generation
TensorBoard
Trained with AutoTrain
Model card Files
xet
 Metrics Community
madhan2301 commited on
Commit
4604f7c
·
1 Parent(s): 68d582e

Upload folder using huggingface_hub

Browse files
Files changed (27) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. added_tokens.json +3 -0
  5. checkpoint-6/README.md +104 -0
  6. checkpoint-6/adapter_config.json +21 -0
  7. checkpoint-6/adapter_model.bin +3 -0
  8. checkpoint-6/added_tokens.json +3 -0
  9. checkpoint-6/optimizer.pt +3 -0
  10. checkpoint-6/rng_state.pth +3 -0
  11. checkpoint-6/scheduler.pt +3 -0
  12. checkpoint-6/special_tokens_map.json +24 -0
  13. checkpoint-6/tokenizer.json +0 -0
  14. checkpoint-6/tokenizer.model +3 -0
  15. checkpoint-6/tokenizer_config.json +32 -0
  16. checkpoint-6/trainer_state.json +15 -0
  17. checkpoint-6/training_args.bin +3 -0
  18. runs/Aug22_13-32-35_1319221bbe2c/events.out.tfevents.1692711155.1319221bbe2c.6201.0 +3 -0
  19. runs/Aug22_13-37-54_1319221bbe2c/events.out.tfevents.1692711474.1319221bbe2c.8097.0 +3 -0
  20. runs/Aug22_13-50-56_1319221bbe2c/events.out.tfevents.1692712257.1319221bbe2c.11350.0 +3 -0
  21. runs/Aug22_13-56-54_1319221bbe2c/events.out.tfevents.1692712614.1319221bbe2c.12834.0 +3 -0
  22. special_tokens_map.json +24 -0
  23. tokenizer.json +0 -0
  24. tokenizer.model +3 -0
  25. tokenizer_config.json +32 -0
  26. training_args.bin +3 -0
  27. training_params.json +1 -0
README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - autotrain
4
+ - text-generation
5
+ widget:
6
+ - text: "I love AutoTrain because "
7
+ ---
8
+
9
+ # Model Trained Using AutoTrain
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
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": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:166fef073f600a9122c196ae55091dff0ad4e488437fdda32b2d68b6c3e46b07
3
+ size 33600461
added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-6/README.md ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+
29
+ The following `bitsandbytes` quantization config was used during training:
30
+ - load_in_8bit: False
31
+ - load_in_4bit: True
32
+ - llm_int8_threshold: 6.0
33
+ - llm_int8_skip_modules: None
34
+ - llm_int8_enable_fp32_cpu_offload: False
35
+ - llm_int8_has_fp16_weight: False
36
+ - bnb_4bit_quant_type: nf4
37
+ - bnb_4bit_use_double_quant: False
38
+ - bnb_4bit_compute_dtype: float16
39
+
40
+ The following `bitsandbytes` quantization config was used during training:
41
+ - load_in_8bit: False
42
+ - load_in_4bit: True
43
+ - llm_int8_threshold: 6.0
44
+ - llm_int8_skip_modules: None
45
+ - llm_int8_enable_fp32_cpu_offload: False
46
+ - llm_int8_has_fp16_weight: False
47
+ - bnb_4bit_quant_type: nf4
48
+ - bnb_4bit_use_double_quant: False
49
+ - bnb_4bit_compute_dtype: float16
50
+
51
+ The following `bitsandbytes` quantization config was used during training:
52
+ - load_in_8bit: False
53
+ - load_in_4bit: True
54
+ - llm_int8_threshold: 6.0
55
+ - llm_int8_skip_modules: None
56
+ - llm_int8_enable_fp32_cpu_offload: False
57
+ - llm_int8_has_fp16_weight: False
58
+ - bnb_4bit_quant_type: nf4
59
+ - bnb_4bit_use_double_quant: False
60
+ - bnb_4bit_compute_dtype: float16
61
+
62
+ The following `bitsandbytes` quantization config was used during training:
63
+ - load_in_8bit: False
64
+ - load_in_4bit: True
65
+ - llm_int8_threshold: 6.0
66
+ - llm_int8_skip_modules: None
67
+ - llm_int8_enable_fp32_cpu_offload: False
68
+ - llm_int8_has_fp16_weight: False
69
+ - bnb_4bit_quant_type: nf4
70
+ - bnb_4bit_use_double_quant: False
71
+ - bnb_4bit_compute_dtype: float16
72
+
73
+ The following `bitsandbytes` quantization config was used during training:
74
+ - load_in_8bit: False
75
+ - load_in_4bit: True
76
+ - llm_int8_threshold: 6.0
77
+ - llm_int8_skip_modules: None
78
+ - llm_int8_enable_fp32_cpu_offload: False
79
+ - llm_int8_has_fp16_weight: False
80
+ - bnb_4bit_quant_type: nf4
81
+ - bnb_4bit_use_double_quant: False
82
+ - bnb_4bit_compute_dtype: float16
83
+
84
+ The following `bitsandbytes` quantization config was used during training:
85
+ - load_in_8bit: False
86
+ - load_in_4bit: True
87
+ - llm_int8_threshold: 6.0
88
+ - llm_int8_skip_modules: None
89
+ - llm_int8_enable_fp32_cpu_offload: False
90
+ - llm_int8_has_fp16_weight: False
91
+ - bnb_4bit_quant_type: nf4
92
+ - bnb_4bit_use_double_quant: False
93
+ - bnb_4bit_compute_dtype: float16
94
+ ### Framework versions
95
+
96
+ - PEFT 0.5.0
97
+ - PEFT 0.5.0
98
+ - PEFT 0.5.0
99
+ - PEFT 0.5.0
100
+ - PEFT 0.5.0
101
+ - PEFT 0.5.0
102
+ - PEFT 0.5.0
103
+
104
+ - PEFT 0.5.0
checkpoint-6/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
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": 32,
11
+ "lora_dropout": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-6/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:166fef073f600a9122c196ae55091dff0ad4e488437fdda32b2d68b6c3e46b07
3
+ size 33600461
checkpoint-6/added_tokens.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "<pad>": 32000
3
+ }
checkpoint-6/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d6ae6cae5fe8b62d39deb03ca3f507268c53a363db0ceadd1a1ae5764b90d58
3
+ size 67216581
checkpoint-6/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9c27dfa3839956276123154d9dcd825429b93416277e6b9ddc2013a9c107110
3
+ size 14575
checkpoint-6/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:41ecd2fbe1b8f6aa58297dfb7c99825739c34a2e6aa391842acd5a91d681ceb7
3
+ size 627
checkpoint-6/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-6/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-6/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-6/tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1024,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
checkpoint-6/trainer_state.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.1,
5
+ "global_step": 6,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [],
10
+ "max_steps": 60,
11
+ "num_train_epochs": 1,
12
+ "total_flos": 228280749785088.0,
13
+ "trial_name": null,
14
+ "trial_params": null
15
+ }
checkpoint-6/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98544ff17d6dd5245cf4b17b002b03c560ed68a567203d483ba640b84abd03b3
3
+ size 3963
runs/Aug22_13-32-35_1319221bbe2c/events.out.tfevents.1692711155.1319221bbe2c.6201.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9bbfa63ea6351272dfa0b818cd0848ca77bb63f79cf779030e344b46c7df87a
3
+ size 4699
runs/Aug22_13-37-54_1319221bbe2c/events.out.tfevents.1692711474.1319221bbe2c.8097.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aadc729884ec159e0dadd24bf38d2e2b48025121eaf299334fe953fe236a162
3
+ size 4699
runs/Aug22_13-50-56_1319221bbe2c/events.out.tfevents.1692712257.1319221bbe2c.11350.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0246588385402f2036f9ea6b362f6d5966bc7c404277c926cc4ac0084e344c07
3
+ size 4699
runs/Aug22_13-56-54_1319221bbe2c/events.out.tfevents.1692712614.1319221bbe2c.12834.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9023cc9c4a621aae8edd4c50030f9a277b7e19b82e42c41c1bf93bcc212be7f5
3
+ size 4699
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1024,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98544ff17d6dd5245cf4b17b002b03c560ed68a567203d483ba640b84abd03b3
3
+ size 3963
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "NousResearch/Llama-2-7b-hf", "data_path": "aboonaji/alpaca_micro_demo", "project_name": "TuneLLM", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 1, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 1024, "repo_id": "madhan2301/LLAMA_2_finetuned-v2", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false}