Hugging Face's logo

gayathrimanoj
/
llama2-7b-shell-alpaca

Text Generation
TensorBoard
Trained with AutoTrain
Model card Files Metrics Community
gayathrimanoj commited on
Commit
131948e
·
1 Parent(s): 5666d9f

Upload folder using huggingface_hub

Browse files
Files changed (26) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. added_tokens.json +5 -0
  5. checkpoint-120/README.md +34 -0
  6. checkpoint-120/adapter_config.json +21 -0
  7. checkpoint-120/adapter_model.bin +3 -0
  8. checkpoint-120/added_tokens.json +5 -0
  9. checkpoint-120/optimizer.pt +3 -0
  10. checkpoint-120/rng_state.pth +3 -0
  11. checkpoint-120/scheduler.pt +3 -0
  12. checkpoint-120/special_tokens_map.json +6 -0
  13. checkpoint-120/tokenizer.json +0 -0
  14. checkpoint-120/tokenizer.model +3 -0
  15. checkpoint-120/tokenizer_config.json +38 -0
  16. checkpoint-120/trainer_state.json +31 -0
  17. checkpoint-120/training_args.bin +3 -0
  18. runs/Oct18_06-36-32_e12809ebe8f9/events.out.tfevents.1697610993.e12809ebe8f9.1309.0 +3 -0
  19. runs/Oct18_06-41-34_e12809ebe8f9/events.out.tfevents.1697611294.e12809ebe8f9.3594.0 +3 -0
  20. runs/Oct18_06-54-32_e12809ebe8f9/events.out.tfevents.1697612073.e12809ebe8f9.6897.0 +3 -0
  21. special_tokens_map.json +6 -0
  22. tokenizer.json +0 -0
  23. tokenizer.model +3 -0
  24. tokenizer_config.json +38 -0
  25. training_args.bin +3 -0
  26. training_params.json +43 -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": "TinyPixel/Llama-2-7B-bf16-sharded",
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 sha256:24343c7a3c90bf8edb0ea13a713b5e58c9e944f62f592c17901d7614c5582db0
3
+ size 33600461
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
+ }
checkpoint-120/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 0.5.0
33
+
34
+ - PEFT 0.5.0
checkpoint-120/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "TinyPixel/Llama-2-7B-bf16-sharded",
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-120/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24343c7a3c90bf8edb0ea13a713b5e58c9e944f62f592c17901d7614c5582db0
3
+ size 33600461
checkpoint-120/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
+ }
checkpoint-120/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47b1d11d62dea0f23e7fb1b2a9425ab36de522add5d089fa6a35e0f104678656
3
+ size 67216581
checkpoint-120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c431ee2909b1507a15f9f8cb1c59ed55f5722e3e817bbed9c4e68ebdcbc54fc
3
+ size 14575
checkpoint-120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a60c461a20f728e4a3da52a70796821d1f2de760f8247b50fa2e6662a9d8c41
3
+ size 627
checkpoint-120/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-120/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-120/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-120/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": "</s>",
34
+ "sp_model_kwargs": {},
35
+ "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
37
+ "use_default_system_prompt": true
38
+ }
checkpoint-120/trainer_state.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.044776119402986,
5
+ "eval_steps": 500,
6
+ "global_step": 120,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 4.02,
13
+ "learning_rate": 3.9552238805970146e-05,
14
+ "loss": 1.2273,
15
+ "step": 53
16
+ },
17
+ {
18
+ "epoch": 8.04,
19
+ "learning_rate": 7.910447761194029e-05,
20
+ "loss": 0.5642,
21
+ "step": 106
22
+ }
23
+ ],
24
+ "logging_steps": 53,
25
+ "max_steps": 2680,
26
+ "num_train_epochs": 10,
27
+ "save_steps": 500,
28
+ "total_flos": 9755294108221440.0,
29
+ "trial_name": null,
30
+ "trial_params": null
31
+ }
checkpoint-120/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c096b37e8f725064c3af2a4cba04acab3024b3ec2ae6a148c7659529770cf5
3
+ size 4091
runs/Oct18_06-36-32_e12809ebe8f9/events.out.tfevents.1697610993.e12809ebe8f9.1309.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a54645e3a216a51335c3fea12f83c1707917ddb4aa445888f01e6404833d63f
3
+ size 5212
runs/Oct18_06-41-34_e12809ebe8f9/events.out.tfevents.1697611294.e12809ebe8f9.3594.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03a1767872ca26ec00d8f0c76b4a157b1ea90169b6a23012e55d724df5832a66
3
+ size 5212
runs/Oct18_06-54-32_e12809ebe8f9/events.out.tfevents.1697612073.e12809ebe8f9.6897.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2b37759466096002f8b29f846f75c84a1f94b80282132c8317bdfce53848eee
3
+ size 5212
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": "</s>",
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:e8c096b37e8f725064c3af2a4cba04acab3024b3ec2ae6a148c7659529770cf5
3
+ size 4091
training_params.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model": "TinyPixel/Llama-2-7B-bf16-sharded",
3
+ "data_path": "gayathrimanoj/dataset_shell_alpaca",
4
+ "project_name": "llama2-7b-shell",
5
+ "train_split": "train",
6
+ "valid_split": null,
7
+ "text_column": "text",
8
+ "rejected_text_column": "rejected",
9
+ "token": null,
10
+ "lr": 0.0002,
11
+ "epochs": 10,
12
+ "batch_size": 2,
13
+ "warmup_ratio": 0.1,
14
+ "gradient_accumulation": 1,
15
+ "optimizer": "adamw_torch",
16
+ "scheduler": "linear",
17
+ "weight_decay": 0.0,
18
+ "max_grad_norm": 1.0,
19
+ "seed": 42,
20
+ "add_eos_token": false,
21
+ "block_size": -1,
22
+ "use_peft": true,
23
+ "lora_r": 16,
24
+ "lora_alpha": 32,
25
+ "lora_dropout": 0.05,
26
+ "logging_steps": -1,
27
+ "evaluation_strategy": "epoch",
28
+ "save_total_limit": 1,
29
+ "save_strategy": "epoch",
30
+ "auto_find_batch_size": false,
31
+ "fp16": false,
32
+ "push_to_hub": false,
33
+ "use_int8": false,
34
+ "model_max_length": 2048,
35
+ "repo_id": null,
36
+ "use_int4": true,
37
+ "trainer": "sft",
38
+ "target_modules": null,
39
+ "merge_adapter": false,
40
+ "username": null,
41
+ "use_flash_attention_2": false,
42
+ "disable_gradient_checkpointing": false
43
+ }