Hugging Face's logo

Sameera827
/
try111

Text Generation
TensorBoard
Trained with AutoTrain
Model card Files
xet
 Metrics Community
Sameera827 commited on
Commit
c3fffb3
·
1 Parent(s): 8fe5733

Upload folder using huggingface_hub

Browse files
Files changed (23) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-264/README.md +34 -0
  5. checkpoint-264/adapter_config.json +21 -0
  6. checkpoint-264/adapter_model.bin +3 -0
  7. checkpoint-264/optimizer.pt +3 -0
  8. checkpoint-264/rng_state.pth +3 -0
  9. checkpoint-264/scheduler.pt +3 -0
  10. checkpoint-264/special_tokens_map.json +24 -0
  11. checkpoint-264/tokenizer.json +0 -0
  12. checkpoint-264/tokenizer.model +3 -0
  13. checkpoint-264/tokenizer_config.json +31 -0
  14. checkpoint-264/trainer_state.json +109 -0
  15. checkpoint-264/training_args.bin +3 -0
  16. runs/Aug17_11-16-46_7a99b650c2d1/events.out.tfevents.1692271007.7a99b650c2d1.3718.0 +3 -0
  17. runs/Aug17_11-33-03_7a99b650c2d1/events.out.tfevents.1692271983.7a99b650c2d1.8265.0 +3 -0
  18. special_tokens_map.json +24 -0
  19. tokenizer.json +0 -0
  20. tokenizer.model +3 -0
  21. tokenizer_config.json +31 -0
  22. training_args.bin +3 -0
  23. 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": "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 sha256:86e1dc9dc058e68c53d1b1248d03f207a022c9be725a23f230fb96759fc5cf57
3
+ size 33600461
checkpoint-264/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.dev0
33
+
34
+ - PEFT 0.5.0.dev0
checkpoint-264/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-264/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86e1dc9dc058e68c53d1b1248d03f207a022c9be725a23f230fb96759fc5cf57
3
+ size 33600461
checkpoint-264/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0af33773013b6d0185d34d66502435c22ac3411c8f5f48f6c3ed8c62397bcc
3
+ size 67216581
checkpoint-264/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28e5d25a032d09c4a3d6718b3173abf845c1cb0042c567f3f4f76ad7e2d2ff2
3
+ size 14575
checkpoint-264/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0a41ab85c58558fee6dcd0228f4fae0e20458d44f07c60df8063fa029dff7c7
3
+ size 627
checkpoint-264/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": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-264/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-264/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-264/tokenizer_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 2048,
20
+ "pad_token": null,
21
+ "sp_model_kwargs": {},
22
+ "tokenizer_class": "LlamaTokenizer",
23
+ "unk_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
checkpoint-264/trainer_state.json ADDED
@@ -0,0 +1,109 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.8181818181818183,
5
+ "eval_steps": 500,
6
+ "global_step": 264,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.19,
13
+ "learning_rate": 0.00012592592592592592,
14
+ "loss": 1.7865,
15
+ "step": 17
16
+ },
17
+ {
18
+ "epoch": 0.39,
19
+ "learning_rate": 0.00019409282700421943,
20
+ "loss": 1.5839,
21
+ "step": 34
22
+ },
23
+ {
24
+ "epoch": 0.58,
25
+ "learning_rate": 0.000179746835443038,
26
+ "loss": 1.3442,
27
+ "step": 51
28
+ },
29
+ {
30
+ "epoch": 0.77,
31
+ "learning_rate": 0.00016540084388185655,
32
+ "loss": 1.2967,
33
+ "step": 68
34
+ },
35
+ {
36
+ "epoch": 0.97,
37
+ "learning_rate": 0.0001510548523206751,
38
+ "loss": 1.2723,
39
+ "step": 85
40
+ },
41
+ {
42
+ "epoch": 1.07,
43
+ "learning_rate": 0.00013670886075949366,
44
+ "loss": 1.2075,
45
+ "step": 102
46
+ },
47
+ {
48
+ "epoch": 1.26,
49
+ "learning_rate": 0.00012236286919831225,
50
+ "loss": 1.1807,
51
+ "step": 119
52
+ },
53
+ {
54
+ "epoch": 1.45,
55
+ "learning_rate": 0.00010801687763713079,
56
+ "loss": 1.0787,
57
+ "step": 136
58
+ },
59
+ {
60
+ "epoch": 1.65,
61
+ "learning_rate": 9.367088607594936e-05,
62
+ "loss": 1.0961,
63
+ "step": 153
64
+ },
65
+ {
66
+ "epoch": 1.84,
67
+ "learning_rate": 7.932489451476794e-05,
68
+ "loss": 1.0747,
69
+ "step": 170
70
+ },
71
+ {
72
+ "epoch": 2.03,
73
+ "learning_rate": 6.49789029535865e-05,
74
+ "loss": 1.0936,
75
+ "step": 187
76
+ },
77
+ {
78
+ "epoch": 2.14,
79
+ "learning_rate": 5.0632911392405066e-05,
80
+ "loss": 1.0467,
81
+ "step": 204
82
+ },
83
+ {
84
+ "epoch": 2.33,
85
+ "learning_rate": 3.628691983122363e-05,
86
+ "loss": 0.9777,
87
+ "step": 221
88
+ },
89
+ {
90
+ "epoch": 2.52,
91
+ "learning_rate": 2.1940928270042196e-05,
92
+ "loss": 1.0002,
93
+ "step": 238
94
+ },
95
+ {
96
+ "epoch": 2.72,
97
+ "learning_rate": 7.5949367088607605e-06,
98
+ "loss": 0.948,
99
+ "step": 255
100
+ }
101
+ ],
102
+ "logging_steps": 17,
103
+ "max_steps": 264,
104
+ "num_train_epochs": 3,
105
+ "save_steps": 500,
106
+ "total_flos": 2.1873419863719936e+16,
107
+ "trial_name": null,
108
+ "trial_params": null
109
+ }
checkpoint-264/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02dffcfd2d7df20620d35ee2def64a55115ff4f48f64180e213ba26e8f941c07
3
+ size 4027
runs/Aug17_11-16-46_7a99b650c2d1/events.out.tfevents.1692271007.7a99b650c2d1.3718.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4eb213892dffd7667c7215f191e35ae5acb1e94e6140f77f9e7cec7a8db5ee58
3
+ size 4465
runs/Aug17_11-33-03_7a99b650c2d1/events.out.tfevents.1692271983.7a99b650c2d1.8265.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:475b6a3549bfb5e721d5c32f1e27eee703d39fa8188d0903d5faee43c12457d6
3
+ size 7153
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": "</s>",
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 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 2048,
20
+ "pad_token": null,
21
+ "sp_model_kwargs": {},
22
+ "tokenizer_class": "LlamaTokenizer",
23
+ "unk_token": {
24
+ "__type": "AddedToken",
25
+ "content": "<unk>",
26
+ "lstrip": false,
27
+ "normalized": true,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:02dffcfd2d7df20620d35ee2def64a55115ff4f48f64180e213ba26e8f941c07
3
+ size 4027
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "TinyPixel/Llama-2-7B-bf16-sharded", "data_path": "dataset", "project_name": "llama2-test", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0002, "epochs": 3, "batch_size": 4, "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": 2048, "repo_id": "Sameera827/try111", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false}