Hugging Face's logo

johaanm
/
llama2-openassistant-studyplanner

Text Generation
Transformers
PyTorch
TensorBoard
Trained with AutoTrain
Model card Files
xet
Metrics Community
1
johaanm commited on
Commit
ec31dca
·
1 Parent(s): 75ca7b1

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-48/README.md +32 -0
  5. checkpoint-48/adapter_config.json +21 -0
  6. checkpoint-48/adapter_model.bin +3 -0
  7. checkpoint-48/optimizer.pt +3 -0
  8. checkpoint-48/rng_state.pth +3 -0
  9. checkpoint-48/scheduler.pt +3 -0
  10. checkpoint-48/special_tokens_map.json +24 -0
  11. checkpoint-48/tokenizer.json +0 -0
  12. checkpoint-48/tokenizer.model +3 -0
  13. checkpoint-48/tokenizer_config.json +33 -0
  14. checkpoint-48/trainer_state.json +160 -0
  15. checkpoint-48/training_args.bin +3 -0
  16. runs/Aug21_22-02-39_a60da81ce041/events.out.tfevents.1692655360.a60da81ce041.3435.0 +3 -0
  17. special_tokens_map.json +24 -0
  18. tokenizer.json +0 -0
  19. tokenizer.model +3 -0
  20. tokenizer_config.json +33 -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-chat-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 sha256:5e4b54ad78a585050ccd204ccdbf1a5fc34e2594f2e3ddd8e5fe189188d74c78
3
+ size 33600461
checkpoint-48/README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0
31
+
32
+ - PEFT 0.4.0
checkpoint-48/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-chat-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-48/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e4b54ad78a585050ccd204ccdbf1a5fc34e2594f2e3ddd8e5fe189188d74c78
3
+ size 33600461
checkpoint-48/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eb43e43f97805afac2fd55b89b4d9a0ad1c12f25a169433e5a8b5b8da5b3459
3
+ size 67216581
checkpoint-48/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-48/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:473be4db9f4fc1f3137bcd6f393f6bf53db57d0216bd83a5bf1d9a333d0ab3ca
3
+ size 627
checkpoint-48/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-48/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-48/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-48/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
checkpoint-48/trainer_state.json ADDED
@@ -0,0 +1,160 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 7.461538461538462,
5
+ "global_step": 48,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.15,
12
+ "learning_rate": 5.454545454545454e-05,
13
+ "loss": 0.8622,
14
+ "step": 2
15
+ },
16
+ {
17
+ "epoch": 0.31,
18
+ "learning_rate": 0.00010909090909090908,
19
+ "loss": 0.8607,
20
+ "step": 4
21
+ },
22
+ {
23
+ "epoch": 0.46,
24
+ "learning_rate": 0.0001636363636363636,
25
+ "loss": 0.8091,
26
+ "step": 6
27
+ },
28
+ {
29
+ "epoch": 1.15,
30
+ "learning_rate": 0.00021818181818181816,
31
+ "loss": 0.738,
32
+ "step": 8
33
+ },
34
+ {
35
+ "epoch": 1.31,
36
+ "learning_rate": 0.0002727272727272727,
37
+ "loss": 0.6651,
38
+ "step": 10
39
+ },
40
+ {
41
+ "epoch": 1.46,
42
+ "learning_rate": 0.0002967741935483871,
43
+ "loss": 0.5799,
44
+ "step": 12
45
+ },
46
+ {
47
+ "epoch": 2.15,
48
+ "learning_rate": 0.00029032258064516127,
49
+ "loss": 0.4795,
50
+ "step": 14
51
+ },
52
+ {
53
+ "epoch": 2.31,
54
+ "learning_rate": 0.00028387096774193545,
55
+ "loss": 0.4095,
56
+ "step": 16
57
+ },
58
+ {
59
+ "epoch": 2.46,
60
+ "learning_rate": 0.0002774193548387096,
61
+ "loss": 0.2854,
62
+ "step": 18
63
+ },
64
+ {
65
+ "epoch": 3.15,
66
+ "learning_rate": 0.00027096774193548386,
67
+ "loss": 0.2146,
68
+ "step": 20
69
+ },
70
+ {
71
+ "epoch": 3.31,
72
+ "learning_rate": 0.00026451612903225804,
73
+ "loss": 0.176,
74
+ "step": 22
75
+ },
76
+ {
77
+ "epoch": 3.46,
78
+ "learning_rate": 0.0002580645161290322,
79
+ "loss": 0.1498,
80
+ "step": 24
81
+ },
82
+ {
83
+ "epoch": 4.15,
84
+ "learning_rate": 0.00025161290322580645,
85
+ "loss": 0.1382,
86
+ "step": 26
87
+ },
88
+ {
89
+ "epoch": 4.31,
90
+ "learning_rate": 0.0002451612903225806,
91
+ "loss": 0.1273,
92
+ "step": 28
93
+ },
94
+ {
95
+ "epoch": 4.46,
96
+ "learning_rate": 0.0002387096774193548,
97
+ "loss": 0.1222,
98
+ "step": 30
99
+ },
100
+ {
101
+ "epoch": 5.15,
102
+ "learning_rate": 0.000232258064516129,
103
+ "loss": 0.1074,
104
+ "step": 32
105
+ },
106
+ {
107
+ "epoch": 5.31,
108
+ "learning_rate": 0.00022580645161290321,
109
+ "loss": 0.1078,
110
+ "step": 34
111
+ },
112
+ {
113
+ "epoch": 5.46,
114
+ "learning_rate": 0.0002193548387096774,
115
+ "loss": 0.1087,
116
+ "step": 36
117
+ },
118
+ {
119
+ "epoch": 6.15,
120
+ "learning_rate": 0.0002129032258064516,
121
+ "loss": 0.0975,
122
+ "step": 38
123
+ },
124
+ {
125
+ "epoch": 6.31,
126
+ "learning_rate": 0.0002064516129032258,
127
+ "loss": 0.0958,
128
+ "step": 40
129
+ },
130
+ {
131
+ "epoch": 6.46,
132
+ "learning_rate": 0.00019999999999999998,
133
+ "loss": 0.0843,
134
+ "step": 42
135
+ },
136
+ {
137
+ "epoch": 7.15,
138
+ "learning_rate": 0.00019354838709677416,
139
+ "loss": 0.0783,
140
+ "step": 44
141
+ },
142
+ {
143
+ "epoch": 7.31,
144
+ "learning_rate": 0.00018709677419354837,
145
+ "loss": 0.0781,
146
+ "step": 46
147
+ },
148
+ {
149
+ "epoch": 7.46,
150
+ "learning_rate": 0.00018064516129032257,
151
+ "loss": 0.079,
152
+ "step": 48
153
+ }
154
+ ],
155
+ "max_steps": 104,
156
+ "num_train_epochs": 8,
157
+ "total_flos": 3984531891683328.0,
158
+ "trial_name": null,
159
+ "trial_params": null
160
+ }
checkpoint-48/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945e493b64c7a168b12e4f0c5961f6be2ec1d5474c76963526ac2808e8fb4f23
3
+ size 3963
runs/Aug21_22-02-39_a60da81ce041/events.out.tfevents.1692655360.a60da81ce041.3435.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139f28246ae53033c9e27660a341c30bc6a84314c4a108f1699262652e6eb7cd
3
+ size 8418
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 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:945e493b64c7a168b12e4f0c5961f6be2ec1d5474c76963526ac2808e8fb4f23
3
+ size 3963
training_params.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"model": "meta-llama/Llama-2-7b-chat-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": 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": 1024, "repo_id": "johaanm/llama2-openassistant-studyplanner", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false}