Hugging Face's logo

Pravincoder
/
Llama-finetune

Text Generation
Transformers
TensorBoard
gpt_neox
Trained with AutoTrain
Inference Endpoints
Model card Files Metrics Community
Pravincoder commited on
Commit
09a68f7
•
1 Parent(s): e109f47

Upload folder using huggingface_hub

Browse files
Files changed (24) hide show
  1. README.md +9 -0
  2. adapter_config.json +20 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-30/README.md +34 -0
  5. checkpoint-30/adapter_config.json +20 -0
  6. checkpoint-30/adapter_model.bin +3 -0
  7. checkpoint-30/optimizer.pt +3 -0
  8. checkpoint-30/rng_state.pth +3 -0
  9. checkpoint-30/scheduler.pt +3 -0
  10. checkpoint-30/special_tokens_map.json +6 -0
  11. checkpoint-30/tokenizer.json +0 -0
  12. checkpoint-30/tokenizer_config.json +9 -0
  13. checkpoint-30/trainer_state.json +37 -0
  14. checkpoint-30/training_args.bin +3 -0
  15. runs/Sep13_05-10-57_64379f8fcfe0/events.out.tfevents.1694581858.64379f8fcfe0.7685.0 +3 -0
  16. runs/Sep13_05-14-00_64379f8fcfe0/events.out.tfevents.1694582040.64379f8fcfe0.8987.0 +3 -0
  17. runs/Sep13_05-15-21_64379f8fcfe0/events.out.tfevents.1694582121.64379f8fcfe0.9583.0 +3 -0
  18. runs/Sep13_05-15-38_64379f8fcfe0/events.out.tfevents.1694582139.64379f8fcfe0.9723.0 +3 -0
  19. runs/Sep13_05-17-33_64379f8fcfe0/events.out.tfevents.1694582253.64379f8fcfe0.10582.0 +3 -0
  20. special_tokens_map.json +6 -0
  21. tokenizer.json +0 -0
  22. tokenizer_config.json +9 -0
  23. training_args.bin +3 -0
  24. 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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "EleutherAI/pythia-160m",
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
+ "query_key_value"
18
+ ],
19
+ "task_type": "CAUSAL_LM"
20
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c9cb6b2955032d587d1d205058ca82d783c0bcc718e1b69c58d0fcf551b0815
3
+ size 2368057
checkpoint-30/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-30/adapter_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "EleutherAI/pythia-160m",
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
+ "query_key_value"
18
+ ],
19
+ "task_type": "CAUSAL_LM"
20
+ }
checkpoint-30/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c9cb6b2955032d587d1d205058ca82d783c0bcc718e1b69c58d0fcf551b0815
3
+ size 2368057
checkpoint-30/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5d08178c3ec02c5dfbdbba6bed6697ea4cf0bc36af2af65b21b4153e7e7c38a
3
+ size 4738785
checkpoint-30/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fbc8de0648e883c9a98743c7791580c5a577188dd93ac1c1fb1e2aa6430427f5
3
+ size 14575
checkpoint-30/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f3f55e579ec02770ba0f1f668efa7d57c012f50ec04a9f4621feb021e25130
3
+ size 627
checkpoint-30/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-30/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-30/tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 2048,
7
+ "tokenizer_class": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
checkpoint-30/trainer_state.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.058823529411764,
5
+ "eval_steps": 500,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 3.02,
13
+ "learning_rate": 3.9215686274509805e-05,
14
+ "loss": 3.1171,
15
+ "step": 10
16
+ },
17
+ {
18
+ "epoch": 6.04,
19
+ "learning_rate": 7.843137254901961e-05,
20
+ "loss": 2.8933,
21
+ "step": 20
22
+ },
23
+ {
24
+ "epoch": 9.06,
25
+ "learning_rate": 0.00011764705882352942,
26
+ "loss": 2.6916,
27
+ "step": 30
28
+ }
29
+ ],
30
+ "logging_steps": 10,
31
+ "max_steps": 510,
32
+ "num_train_epochs": 10,
33
+ "save_steps": 500,
34
+ "total_flos": 50252532940800.0,
35
+ "trial_name": null,
36
+ "trial_params": null
37
+ }
checkpoint-30/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8629e8a7aa08f15b4b9c374efc1dfa1f820a0f6fdaa9964f532c04e2921d1938
3
+ size 4027
runs/Sep13_05-10-57_64379f8fcfe0/events.out.tfevents.1694581858.64379f8fcfe0.7685.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8fccf613e375eeade82ecb1e81310328b615669ce7f3e2c47779d62ed32a169
3
+ size 4565
runs/Sep13_05-14-00_64379f8fcfe0/events.out.tfevents.1694582040.64379f8fcfe0.8987.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14c2fd209cb1c7761770f0514490d41e8ccfa40df8c11be2c5acde6e3c3a6030
3
+ size 4913
runs/Sep13_05-15-21_64379f8fcfe0/events.out.tfevents.1694582121.64379f8fcfe0.9583.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af68377db4ef23c32f005563ba2e10a9269b84800a5cb737f049c0813ca80d9e
3
+ size 4565
runs/Sep13_05-15-38_64379f8fcfe0/events.out.tfevents.1694582139.64379f8fcfe0.9723.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b36d6d4f29c9743298a36c7fc96198da0431460bd5d1e240ae327f01a4186ce7
3
+ size 5376
runs/Sep13_05-17-33_64379f8fcfe0/events.out.tfevents.1694582253.64379f8fcfe0.10582.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e783a065009daeebdf5bc4e4e15a4d1fd1f0a847c8f8052d395c7a7242d68ad
3
+ size 5376
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": "<|endoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|endoftext|>",
6
+ "model_max_length": 2048,
7
+ "tokenizer_class": "GPTNeoXTokenizer",
8
+ "unk_token": "<|endoftext|>"
9
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8629e8a7aa08f15b4b9c374efc1dfa1f820a0f6fdaa9964f532c04e2921d1938
3
+ size 4027
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "EleutherAI/pythia-160m", "data_path": "Pravincoder/law_llm_dataSample", "project_name": "DocAi", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 10, "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": "Pravincoder/Llama-finetune", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null}