Hugging Face's logo

Mestopholis
/
llama2-gov-finetuning

Text Generation
TensorBoard
Trained with AutoTrain
Model card Files
xet
 Metrics Community
Mestopholis commited on
Commit
eec6d0a
·
1 Parent(s): 05060e2

Upload folder using huggingface_hub

Browse files
Files changed (37) hide show
  1. README.md +9 -0
  2. adapter_config.json +23 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-81/README.md +34 -0
  5. checkpoint-81/adapter_config.json +23 -0
  6. checkpoint-81/adapter_model.bin +3 -0
  7. checkpoint-81/optimizer.pt +3 -0
  8. checkpoint-81/rng_state_0.pth +3 -0
  9. checkpoint-81/rng_state_1.pth +3 -0
  10. checkpoint-81/rng_state_2.pth +3 -0
  11. checkpoint-81/rng_state_3.pth +3 -0
  12. checkpoint-81/rng_state_4.pth +3 -0
  13. checkpoint-81/rng_state_5.pth +3 -0
  14. checkpoint-81/rng_state_6.pth +3 -0
  15. checkpoint-81/rng_state_7.pth +3 -0
  16. checkpoint-81/scheduler.pt +3 -0
  17. checkpoint-81/special_tokens_map.json +6 -0
  18. checkpoint-81/tokenizer.json +0 -0
  19. checkpoint-81/tokenizer.model +3 -0
  20. checkpoint-81/tokenizer_config.json +38 -0
  21. checkpoint-81/trainer_state.json +18 -0
  22. checkpoint-81/training_args.bin +3 -0
  23. runs/Sep23_14-11-18_104-171-202-121/events.out.tfevents.1695478283.104-171-202-121.69930.0 +3 -0
  24. runs/Sep23_15-34-27_104-171-202-121/events.out.tfevents.1695483273.104-171-202-121.71971.0 +3 -0
  25. runs/Sep23_15-37-28_104-171-202-121/events.out.tfevents.1695483453.104-171-202-121.72860.0 +3 -0
  26. runs/Sep23_15-40-23_104-171-202-121/events.out.tfevents.1695483627.104-171-202-121.73747.0 +3 -0
  27. runs/Sep23_15-46-42_104-171-202-121/events.out.tfevents.1695484004.104-171-202-121.74717.0 +3 -0
  28. runs/Sep23_15-52-13_104-171-202-121/events.out.tfevents.1695484338.104-171-202-121.75607.0 +3 -0
  29. runs/Sep23_20-32-04_104-171-202-121/events.out.tfevents.1695501130.104-171-202-121.80352.0 +3 -0
  30. runs/Sep23_20-47-11_104-171-202-121/events.out.tfevents.1695502033.104-171-202-121.81255.0 +3 -0
  31. runs/Sep23_21-10-01_104-171-202-121/events.out.tfevents.1695503408.104-171-202-121.85549.0 +3 -0
  32. special_tokens_map.json +6 -0
  33. tokenizer.json +0 -0
  34. tokenizer.model +3 -0
  35. tokenizer_config.json +38 -0
  36. training_args.bin +3 -0
  37. 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 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
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": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be011ff2d8564675e1c5b21531b27deb93f93e2ac1325cb6343b253459771ef
3
+ size 33600461
checkpoint-81/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.6.0.dev0
33
+
34
+ - PEFT 0.6.0.dev0
checkpoint-81/adapter_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
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": 32,
12
+ "lora_dropout": 0.05,
13
+ "modules_to_save": null,
14
+ "peft_type": "LORA",
15
+ "r": 16,
16
+ "rank_pattern": {},
17
+ "revision": null,
18
+ "target_modules": [
19
+ "q_proj",
20
+ "v_proj"
21
+ ],
22
+ "task_type": "CAUSAL_LM"
23
+ }
checkpoint-81/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be011ff2d8564675e1c5b21531b27deb93f93e2ac1325cb6343b253459771ef
3
+ size 33600461
checkpoint-81/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c51901d93bf52b277e86a747a865877fec0adf4cc51057a73767bd41a200a6f9
3
+ size 67216581
checkpoint-81/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f58b105cc8f526bd09d66029d6ee80f585554a57c28d1994d44a4cc5ef805b
3
+ size 21687
checkpoint-81/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ba7e9f8cd1e2cc4836d1b00b39da6f7ce06c364b5e9904fdabd4fadbd0761f2
3
+ size 21687
checkpoint-81/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:82b76c77ea765f174a379aa5fd1e0e46c1eaba82990eb1a0972d7c48bd0e3b94
3
+ size 21687
checkpoint-81/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6a6b53c5395de257d0a55b3d1831268364033ae68ed65109505ca58d03636fd
3
+ size 21687
checkpoint-81/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33435a0afff36c612d4510ea4f3e301689db53e10b371a9bb76ffc65e5e59c36
3
+ size 21687
checkpoint-81/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6415679d4287405de031c237a8ffa5ffb4a22bcba49a5f1cd60a4681d912b8
3
+ size 21687
checkpoint-81/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d54d6c83b551e82aeb9ff35a23b988e9825b222cc1412b8e402a2582f16e4028
3
+ size 21687
checkpoint-81/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46572b34cc0613af2d5f6d5c7c5ba4ea0db4dbc3151fe214ee3000fb34c1c8e7
3
+ size 21687
checkpoint-81/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f14c5a5a857e1231e22f2706f3382b07e1a1b8f17b3024bfda0c2cbe76c2249
3
+ size 627
checkpoint-81/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
6
+ }
checkpoint-81/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-81/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-81/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "model_max_length": 2048,
33
+ "pad_token": null,
34
+ "sp_model_kwargs": {},
35
+ "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
37
+ "use_default_system_prompt": true
38
+ }
checkpoint-81/trainer_state.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0703125,
5
+ "eval_steps": 500,
6
+ "global_step": 81,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 613,
12
+ "max_steps": 1152,
13
+ "num_train_epochs": 3,
14
+ "save_steps": 500,
15
+ "total_flos": 1.0535717556348518e+17,
16
+ "trial_name": null,
17
+ "trial_params": null
18
+ }
checkpoint-81/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61faf55bc62e8ac9bde1f27193ebf9b403b0e5f33bf26b2eb033887c8776229c
3
+ size 4091
runs/Sep23_14-11-18_104-171-202-121/events.out.tfevents.1695478283.104-171-202-121.69930.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7099af38aa492ab984eac37baa5bc485411bfc3f37321c49d21f667bcbe1dc8e
3
+ size 4527
runs/Sep23_15-34-27_104-171-202-121/events.out.tfevents.1695483273.104-171-202-121.71971.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:335ec7b370a789ad018d528593b23a45d44f35caf891d16c69c830d3a87ce69d
3
+ size 4525
runs/Sep23_15-37-28_104-171-202-121/events.out.tfevents.1695483453.104-171-202-121.72860.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e07e0a2cfa15072ab9fe2803a6e9dedd00d5d70f6017d834c858e6a8f1550b9e
3
+ size 4525
runs/Sep23_15-40-23_104-171-202-121/events.out.tfevents.1695483627.104-171-202-121.73747.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92074cab65f191dccc871dc90e9e12477d5df9719bb542fbf9e15666345e7051
3
+ size 4525
runs/Sep23_15-46-42_104-171-202-121/events.out.tfevents.1695484004.104-171-202-121.74717.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68fb74c2649c8b465ee7d8755c651b777bbc26a7edf483d9785050f6aeaa4186
3
+ size 4525
runs/Sep23_15-52-13_104-171-202-121/events.out.tfevents.1695484338.104-171-202-121.75607.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e6db47f590b8f3dc93d91bd69403ffda1fd20ee6ea07e7d3c4aaebc73e9f82f
3
+ size 4525
runs/Sep23_20-32-04_104-171-202-121/events.out.tfevents.1695501130.104-171-202-121.80352.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e498d5262d23a822b5722d30866ad714d6dff03e82571477a554d441372657f1
3
+ size 4525
runs/Sep23_20-47-11_104-171-202-121/events.out.tfevents.1695502033.104-171-202-121.81255.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0482e660d53e7d70945bfb67cdd4c291c27e8e3f6c99d62a1f9b0ac6aa1c2c57
3
+ size 4875
runs/Sep23_21-10-01_104-171-202-121/events.out.tfevents.1695503408.104-171-202-121.85549.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4998cec6d8a808b9227070590ecfdfaf3a033961949c2b8f5fc2a64a5c662ada
3
+ size 4875
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
6
+ }
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 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "model_max_length": 2048,
33
+ "pad_token": null,
34
+ "sp_model_kwargs": {},
35
+ "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
37
+ "use_default_system_prompt": true
38
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61faf55bc62e8ac9bde1f27193ebf9b403b0e5f33bf26b2eb033887c8776229c
3
+ size 4091
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "TinyPixel/Llama-2-7B-bf16-sharded", "data_path": "Mestopholis/test-prompts", "project_name": "testing-llama2-finetuning-2", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 3, "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": 2048, "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": 2048, "repo_id": "Mestopholis/llama2-gov-finetuning", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null}