Hugging Face's logo

ranonrat
/
mistral-first-test

Text Generation
Transformers
mistral
Trained with AutoTrain
Model card Files
xet
Community
ranonrat commited on
Commit
4fc9b2c
·
1 Parent(s): e1288e6

Upload folder using huggingface_hub

Browse files
Files changed (21) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-20/README.md +34 -0
  5. checkpoint-20/adapter_config.json +21 -0
  6. checkpoint-20/adapter_model.bin +3 -0
  7. checkpoint-20/optimizer.pt +3 -0
  8. checkpoint-20/rng_state.pth +3 -0
  9. checkpoint-20/scheduler.pt +3 -0
  10. checkpoint-20/special_tokens_map.json +24 -0
  11. checkpoint-20/tokenizer.json +0 -0
  12. checkpoint-20/tokenizer.model +3 -0
  13. checkpoint-20/tokenizer_config.json +40 -0
  14. checkpoint-20/trainer_state.json +139 -0
  15. checkpoint-20/training_args.bin +3 -0
  16. special_tokens_map.json +24 -0
  17. tokenizer.json +0 -0
  18. tokenizer.model +3 -0
  19. tokenizer_config.json +40 -0
  20. training_args.bin +3 -0
  21. 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": "mistralai/Mistral-7B-v0.1",
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 sha256:818f965b38527ec090710488f2ed539eb29a308e9a6e978084d2799726d0b761
3
+ size 27309386
checkpoint-20/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-20/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
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-20/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:818f965b38527ec090710488f2ed539eb29a308e9a6e978084d2799726d0b761
3
+ size 27309386
checkpoint-20/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b092ab42c6c0c0871cbdadfdac9aa848de4830e5a4346bf786bbc540de53047
3
+ size 54633978
checkpoint-20/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:552f477bc0da287482f92f8b95ec9881fdef2d97597b91da7d42d068a8681bd1
3
+ size 14244
checkpoint-20/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf4c18cd380d4d2c0ee2aa76d8e22b68a563fc85f1cea7dbf7872a16aaf8dd2d
3
+ size 1064
checkpoint-20/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-20/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-20/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
checkpoint-20/tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
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
+ "legacy": true,
33
+ "model_max_length": 1024,
34
+ "pad_token": "</s>",
35
+ "sp_model_kwargs": {},
36
+ "spaces_between_special_tokens": false,
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
+ }
checkpoint-20/trainer_state.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 19.5,
5
+ "eval_steps": 500,
6
+ "global_step": 20,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.5,
13
+ "learning_rate": 5e-05,
14
+ "loss": 1.7498,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 1.5,
19
+ "learning_rate": 0.0001,
20
+ "loss": 1.7498,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 2.5,
25
+ "learning_rate": 0.00015000000000000001,
26
+ "loss": 1.7179,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 3.5,
31
+ "learning_rate": 0.0002,
32
+ "loss": 1.6526,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 4.5,
37
+ "learning_rate": 0.00019444444444444446,
38
+ "loss": 1.5549,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 5.5,
43
+ "learning_rate": 0.00018888888888888888,
44
+ "loss": 1.4428,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 6.5,
49
+ "learning_rate": 0.00018333333333333334,
50
+ "loss": 1.3413,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 7.5,
55
+ "learning_rate": 0.00017777777777777779,
56
+ "loss": 1.2458,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 8.5,
61
+ "learning_rate": 0.00017222222222222224,
62
+ "loss": 1.1408,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 9.5,
67
+ "learning_rate": 0.0001666666666666667,
68
+ "loss": 1.0299,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 10.5,
73
+ "learning_rate": 0.0001611111111111111,
74
+ "loss": 0.9223,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 11.5,
79
+ "learning_rate": 0.00015555555555555556,
80
+ "loss": 0.8215,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 12.5,
85
+ "learning_rate": 0.00015000000000000001,
86
+ "loss": 0.7281,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 13.5,
91
+ "learning_rate": 0.00014444444444444444,
92
+ "loss": 0.6339,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 14.5,
97
+ "learning_rate": 0.0001388888888888889,
98
+ "loss": 0.5883,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 15.5,
103
+ "learning_rate": 0.00013333333333333334,
104
+ "loss": 0.4937,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 16.5,
109
+ "learning_rate": 0.00012777777777777776,
110
+ "loss": 0.4356,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 17.5,
115
+ "learning_rate": 0.00012222222222222224,
116
+ "loss": 0.3726,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 18.5,
121
+ "learning_rate": 0.00011666666666666668,
122
+ "loss": 0.319,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 19.5,
127
+ "learning_rate": 0.00011111111111111112,
128
+ "loss": 0.2746,
129
+ "step": 20
130
+ }
131
+ ],
132
+ "logging_steps": 1,
133
+ "max_steps": 40,
134
+ "num_train_epochs": 20,
135
+ "save_steps": 500,
136
+ "total_flos": 1749190862438400.0,
137
+ "trial_name": null,
138
+ "trial_params": null
139
+ }
checkpoint-20/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e352f5102aa074e2fa31d00ee7ee152a0cf64d79c772f18405817be11c3ae30a
3
+ size 4536
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
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
+ "legacy": true,
33
+ "model_max_length": 1024,
34
+ "pad_token": "</s>",
35
+ "sp_model_kwargs": {},
36
+ "spaces_between_special_tokens": false,
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e352f5102aa074e2fa31d00ee7ee152a0cf64d79c772f18405817be11c3ae30a
3
+ size 4536
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "mistralai/Mistral-7B-v0.1", "data_path": ".", "project_name": "mistral-7b-sapiens-2", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 20, "batch_size": 12, "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": "ranonrat/mistral-7b-sapiens-3", "use_int4": true, "trainer": "sft", "target_modules": "q_proj,v_proj", "merge_adapter": false, "username": null, "use_flash_attention_2": false, "log": "none", "disable_gradient_checkpointing": false, "model_ref": null, "dpo_beta": 0.1, "prompt_text_column": "prompt"}