Hugging Face's logo

johaanm
/
llama2-openassistant-studyplannerV2

Text Generation
Transformers
PyTorch
TensorBoard
Trained with AutoTrain
Model card Files
xet
Metrics Community
1
johaanm commited on
Commit
e3f3ffa
·
1 Parent(s): 4a9a7e2

Upload folder using huggingface_hub

Browse files
Files changed (22) hide show
  1. README.md +9 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-24/README.md +34 -0
  5. checkpoint-24/adapter_config.json +21 -0
  6. checkpoint-24/adapter_model.bin +3 -0
  7. checkpoint-24/optimizer.pt +3 -0
  8. checkpoint-24/rng_state.pth +3 -0
  9. checkpoint-24/scheduler.pt +3 -0
  10. checkpoint-24/special_tokens_map.json +24 -0
  11. checkpoint-24/tokenizer.json +0 -0
  12. checkpoint-24/tokenizer.model +3 -0
  13. checkpoint-24/tokenizer_config.json +34 -0
  14. checkpoint-24/trainer_state.json +163 -0
  15. checkpoint-24/training_args.bin +3 -0
  16. runs/Aug25_05-23-07_0d015406e0dd/events.out.tfevents.1692940987.0d015406e0dd.4861.0 +3 -0
  17. special_tokens_map.json +24 -0
  18. tokenizer.json +0 -0
  19. tokenizer.model +3 -0
  20. tokenizer_config.json +34 -0
  21. training_args.bin +3 -0
  22. 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": "meta-llama/Llama-2-7b-hf",
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:be0cf9cdcc44e2286eba49ad3f60c149b87061355a4f17a957c714fcf84a2de5
3
+ size 33600461
checkpoint-24/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-24/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
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-24/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be0cf9cdcc44e2286eba49ad3f60c149b87061355a4f17a957c714fcf84a2de5
3
+ size 33600461
checkpoint-24/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4cfbb280e668cd7ad0e172f2bd1de97cf09fd462bdb42c7e98e0eab4bf7c3e13
3
+ size 67216581
checkpoint-24/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18f55f528bdf77873e47f9f7ebfea3b611ab91c7618f8ae2616e7abb68d1eed0
3
+ size 14575
checkpoint-24/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:055a74578ed5fe510c2b7214ce8504cca7e249bab9e63cda2a148ebab0b651d5
3
+ size 627
checkpoint-24/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-24/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-24/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-24/tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
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": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1024,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "use_default_system_prompt": true
34
+ }
checkpoint-24/trainer_state.json ADDED
@@ -0,0 +1,163 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.428571428571429,
5
+ "eval_steps": 500,
6
+ "global_step": 24,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.14,
13
+ "learning_rate": 4.9999999999999996e-05,
14
+ "loss": 1.0283,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.29,
19
+ "learning_rate": 9.999999999999999e-05,
20
+ "loss": 1.0447,
21
+ "step": 2
22
+ },
23
+ {
24
+ "epoch": 0.43,
25
+ "learning_rate": 0.00015,
26
+ "loss": 1.0075,
27
+ "step": 3
28
+ },
29
+ {
30
+ "epoch": 1.14,
31
+ "learning_rate": 0.00019999999999999998,
32
+ "loss": 0.9604,
33
+ "step": 4
34
+ },
35
+ {
36
+ "epoch": 1.29,
37
+ "learning_rate": 0.00025,
38
+ "loss": 0.8964,
39
+ "step": 5
40
+ },
41
+ {
42
+ "epoch": 1.43,
43
+ "learning_rate": 0.0003,
44
+ "loss": 0.8099,
45
+ "step": 6
46
+ },
47
+ {
48
+ "epoch": 2.14,
49
+ "learning_rate": 0.000294,
50
+ "loss": 0.7356,
51
+ "step": 7
52
+ },
53
+ {
54
+ "epoch": 2.29,
55
+ "learning_rate": 0.00028799999999999995,
56
+ "loss": 0.6955,
57
+ "step": 8
58
+ },
59
+ {
60
+ "epoch": 2.43,
61
+ "learning_rate": 0.00028199999999999997,
62
+ "loss": 0.6318,
63
+ "step": 9
64
+ },
65
+ {
66
+ "epoch": 3.14,
67
+ "learning_rate": 0.000276,
68
+ "loss": 0.594,
69
+ "step": 10
70
+ },
71
+ {
72
+ "epoch": 3.29,
73
+ "learning_rate": 0.00027,
74
+ "loss": 0.5653,
75
+ "step": 11
76
+ },
77
+ {
78
+ "epoch": 3.43,
79
+ "learning_rate": 0.00026399999999999997,
80
+ "loss": 0.5067,
81
+ "step": 12
82
+ },
83
+ {
84
+ "epoch": 4.14,
85
+ "learning_rate": 0.000258,
86
+ "loss": 0.4433,
87
+ "step": 13
88
+ },
89
+ {
90
+ "epoch": 4.29,
91
+ "learning_rate": 0.00025199999999999995,
92
+ "loss": 0.3947,
93
+ "step": 14
94
+ },
95
+ {
96
+ "epoch": 4.43,
97
+ "learning_rate": 0.00024599999999999996,
98
+ "loss": 0.3413,
99
+ "step": 15
100
+ },
101
+ {
102
+ "epoch": 5.14,
103
+ "learning_rate": 0.00023999999999999998,
104
+ "loss": 0.2837,
105
+ "step": 16
106
+ },
107
+ {
108
+ "epoch": 5.29,
109
+ "learning_rate": 0.000234,
110
+ "loss": 0.2606,
111
+ "step": 17
112
+ },
113
+ {
114
+ "epoch": 5.43,
115
+ "learning_rate": 0.00022799999999999999,
116
+ "loss": 0.2437,
117
+ "step": 18
118
+ },
119
+ {
120
+ "epoch": 6.14,
121
+ "learning_rate": 0.00022199999999999998,
122
+ "loss": 0.2033,
123
+ "step": 19
124
+ },
125
+ {
126
+ "epoch": 6.29,
127
+ "learning_rate": 0.00021599999999999996,
128
+ "loss": 0.187,
129
+ "step": 20
130
+ },
131
+ {
132
+ "epoch": 6.43,
133
+ "learning_rate": 0.00020999999999999998,
134
+ "loss": 0.162,
135
+ "step": 21
136
+ },
137
+ {
138
+ "epoch": 7.14,
139
+ "learning_rate": 0.000204,
140
+ "loss": 0.1494,
141
+ "step": 22
142
+ },
143
+ {
144
+ "epoch": 7.29,
145
+ "learning_rate": 0.000198,
146
+ "loss": 0.1454,
147
+ "step": 23
148
+ },
149
+ {
150
+ "epoch": 7.43,
151
+ "learning_rate": 0.00019199999999999998,
152
+ "loss": 0.1422,
153
+ "step": 24
154
+ }
155
+ ],
156
+ "logging_steps": 1,
157
+ "max_steps": 56,
158
+ "num_train_epochs": 8,
159
+ "save_steps": 500,
160
+ "total_flos": 3984531891683328.0,
161
+ "trial_name": null,
162
+ "trial_params": null
163
+ }
checkpoint-24/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a9ef1f7ad542078f4d9d3c9f40d83127f5560f421854b792cca625cb9015ddc
3
+ size 4027
runs/Aug25_05-23-07_0d015406e0dd/events.out.tfevents.1692940987.0d015406e0dd.4861.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73ae62bdbd0a200fbf39cc0dca15310d5cfd5cca8c52aee34e7a684c7fd9d11b
3
+ size 8476
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 sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
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": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1024,
21
+ "pad_token": null,
22
+ "padding_side": "right",
23
+ "sp_model_kwargs": {},
24
+ "tokenizer_class": "LlamaTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<unk>",
28
+ "lstrip": false,
29
+ "normalized": false,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ },
33
+ "use_default_system_prompt": true
34
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a9ef1f7ad542078f4d9d3c9f40d83127f5560f421854b792cca625cb9015ddc
3
+ size 4027
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "meta-llama/Llama-2-7b-hf", "data_path": "/content/train", "project_name": "llama2-planner", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0003, "epochs": 8, "batch_size": 8, "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": "johaanm/llama2-openassistant-studyplannerV2", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false}