Hugging Face's logo

thaisonatk
/
aac

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
thaisonatk commited on
Commit
455848b
·
verified ·
1 Parent(s): 489b789

End of training

Browse files
Files changed (11) hide show
  1. README.md +60 -0
  2. adapter_config.json +139 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Jun25_16-52-59_gpuhpc06/events.out.tfevents.1719301981.gpuhpc06 +3 -0
  5. runs/Jun25_16-57-16_gpuhpc06/events.out.tfevents.1719302238.gpuhpc06 +3 -0
  6. runs/Jun25_17-19-41_gpuhpc06/events.out.tfevents.1719303584.gpuhpc06 +3 -0
  7. runs/Jun25_17-40-53_gpuhpc06/events.out.tfevents.1719304870.gpuhpc06 +3 -0
  8. special_tokens_map.json +30 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +40 -0
  11. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: apple/OpenELM-1_1B
9
+ model-index:
10
+ - name: aac
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/thaisonatk/huggingface/runs/7v4qlhkz)
18
+ # aac
19
+
20
+ This model is a fine-tuned version of [apple/OpenELM-1_1B](https://huggingface.co/apple/OpenELM-1_1B) on the None dataset.
21
+
22
+ ## Model description
23
+
24
+ More information needed
25
+
26
+ ## Intended uses & limitations
27
+
28
+ More information needed
29
+
30
+ ## Training and evaluation data
31
+
32
+ More information needed
33
+
34
+ ## Training procedure
35
+
36
+ ### Training hyperparameters
37
+
38
+ The following hyperparameters were used during training:
39
+ - learning_rate: 0.0002
40
+ - train_batch_size: 16
41
+ - eval_batch_size: 16
42
+ - seed: 3407
43
+ - gradient_accumulation_steps: 4
44
+ - total_train_batch_size: 64
45
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
46
+ - lr_scheduler_type: cosine
47
+ - lr_scheduler_warmup_steps: 5
48
+ - num_epochs: 3
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - PEFT 0.10.0
57
+ - Transformers 4.41.0.dev0
58
+ - Pytorch 2.3.1+cu121
59
+ - Datasets 2.19.0
60
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,139 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "apple/OpenELM-1_1B",
5
+ "bias": "none",
6
+ "fan_in_fan_out": false,
7
+ "inference_mode": true,
8
+ "init_lora_weights": true,
9
+ "layer_replication": null,
10
+ "layers_pattern": null,
11
+ "layers_to_transform": null,
12
+ "loftq_config": {},
13
+ "lora_alpha": 16,
14
+ "lora_dropout": 0.1,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 16,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "transformer.layers.20.attn.qkv_proj",
24
+ "transformer.layers.21.ffn.proj_1",
25
+ "transformer.layers.1.ffn.proj_2",
26
+ "transformer.layers.23.ffn.proj_2",
27
+ "transformer.layers.15.attn.out_proj",
28
+ "transformer.layers.17.attn.qkv_proj",
29
+ "transformer.layers.3.attn.out_proj",
30
+ "transformer.layers.14.attn.out_proj",
31
+ "transformer.layers.12.attn.qkv_proj",
32
+ "transformer.layers.9.ffn.proj_1",
33
+ "transformer.layers.10.attn.qkv_proj",
34
+ "transformer.layers.17.ffn.proj_1",
35
+ "transformer.layers.7.attn.qkv_proj",
36
+ "transformer.layers.0.ffn.proj_2",
37
+ "transformer.layers.7.attn.out_proj",
38
+ "transformer.layers.23.attn.qkv_proj",
39
+ "transformer.layers.27.attn.out_proj",
40
+ "transformer.layers.23.attn.out_proj",
41
+ "transformer.layers.0.attn.qkv_proj",
42
+ "transformer.layers.4.ffn.proj_2",
43
+ "transformer.layers.13.attn.out_proj",
44
+ "transformer.layers.25.ffn.proj_2",
45
+ "transformer.layers.18.attn.qkv_proj",
46
+ "transformer.layers.18.ffn.proj_1",
47
+ "transformer.layers.24.attn.out_proj",
48
+ "transformer.layers.25.attn.qkv_proj",
49
+ "transformer.layers.4.ffn.proj_1",
50
+ "transformer.layers.23.ffn.proj_1",
51
+ "transformer.layers.16.ffn.proj_2",
52
+ "transformer.layers.10.attn.out_proj",
53
+ "transformer.layers.13.ffn.proj_1",
54
+ "transformer.layers.4.attn.qkv_proj",
55
+ "transformer.layers.3.attn.qkv_proj",
56
+ "transformer.layers.9.attn.qkv_proj",
57
+ "transformer.layers.0.attn.out_proj",
58
+ "transformer.layers.24.ffn.proj_2",
59
+ "transformer.layers.25.attn.out_proj",
60
+ "transformer.layers.14.attn.qkv_proj",
61
+ "transformer.layers.11.attn.qkv_proj",
62
+ "transformer.layers.19.attn.out_proj",
63
+ "transformer.layers.22.ffn.proj_2",
64
+ "transformer.layers.0.ffn.proj_1",
65
+ "transformer.layers.18.attn.out_proj",
66
+ "transformer.layers.14.ffn.proj_1",
67
+ "transformer.layers.6.attn.out_proj",
68
+ "transformer.layers.12.attn.out_proj",
69
+ "transformer.layers.26.ffn.proj_2",
70
+ "transformer.layers.27.ffn.proj_2",
71
+ "transformer.layers.26.attn.qkv_proj",
72
+ "transformer.layers.21.ffn.proj_2",
73
+ "transformer.layers.8.attn.out_proj",
74
+ "transformer.layers.21.attn.out_proj",
75
+ "transformer.layers.15.ffn.proj_2",
76
+ "transformer.layers.22.attn.out_proj",
77
+ "transformer.layers.14.ffn.proj_2",
78
+ "transformer.layers.11.attn.out_proj",
79
+ "transformer.layers.8.attn.qkv_proj",
80
+ "transformer.layers.15.attn.qkv_proj",
81
+ "transformer.layers.1.attn.qkv_proj",
82
+ "transformer.layers.5.ffn.proj_1",
83
+ "transformer.layers.18.ffn.proj_2",
84
+ "transformer.layers.16.ffn.proj_1",
85
+ "transformer.layers.6.ffn.proj_1",
86
+ "transformer.layers.7.ffn.proj_1",
87
+ "transformer.layers.21.attn.qkv_proj",
88
+ "transformer.layers.22.ffn.proj_1",
89
+ "transformer.layers.7.ffn.proj_2",
90
+ "transformer.layers.1.ffn.proj_1",
91
+ "transformer.layers.9.attn.out_proj",
92
+ "transformer.layers.3.ffn.proj_2",
93
+ "transformer.layers.20.ffn.proj_1",
94
+ "transformer.layers.25.ffn.proj_1",
95
+ "transformer.layers.10.ffn.proj_1",
96
+ "transformer.layers.17.attn.out_proj",
97
+ "transformer.layers.12.ffn.proj_1",
98
+ "transformer.layers.15.ffn.proj_1",
99
+ "transformer.layers.16.attn.qkv_proj",
100
+ "transformer.layers.19.ffn.proj_1",
101
+ "transformer.layers.24.attn.qkv_proj",
102
+ "transformer.layers.8.ffn.proj_1",
103
+ "transformer.layers.6.ffn.proj_2",
104
+ "transformer.layers.19.attn.qkv_proj",
105
+ "transformer.layers.24.ffn.proj_1",
106
+ "transformer.layers.9.ffn.proj_2",
107
+ "transformer.layers.2.attn.qkv_proj",
108
+ "transformer.layers.4.attn.out_proj",
109
+ "transformer.layers.16.attn.out_proj",
110
+ "transformer.layers.13.ffn.proj_2",
111
+ "transformer.layers.11.ffn.proj_1",
112
+ "transformer.layers.20.ffn.proj_2",
113
+ "transformer.layers.2.ffn.proj_2",
114
+ "transformer.layers.12.ffn.proj_2",
115
+ "transformer.layers.17.ffn.proj_2",
116
+ "transformer.layers.27.ffn.proj_1",
117
+ "transformer.layers.8.ffn.proj_2",
118
+ "transformer.layers.13.attn.qkv_proj",
119
+ "transformer.layers.5.attn.qkv_proj",
120
+ "transformer.layers.6.attn.qkv_proj",
121
+ "transformer.layers.27.attn.qkv_proj",
122
+ "transformer.layers.5.ffn.proj_2",
123
+ "transformer.layers.22.attn.qkv_proj",
124
+ "transformer.layers.1.attn.out_proj",
125
+ "transformer.layers.2.ffn.proj_1",
126
+ "transformer.layers.3.ffn.proj_1",
127
+ "transformer.layers.19.ffn.proj_2",
128
+ "transformer.layers.10.ffn.proj_2",
129
+ "transformer.layers.26.ffn.proj_1",
130
+ "transformer.layers.11.ffn.proj_2",
131
+ "transformer.layers.2.attn.out_proj",
132
+ "transformer.layers.5.attn.out_proj",
133
+ "transformer.layers.20.attn.out_proj",
134
+ "transformer.layers.26.attn.out_proj"
135
+ ],
136
+ "task_type": "CAUSAL_LM",
137
+ "use_dora": false,
138
+ "use_rslora": false
139
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd83f1ca7fe6961161cd1395af82917fa42bd27080331703646b3a7c10580c46
3
+ size 46405320
runs/Jun25_16-52-59_gpuhpc06/events.out.tfevents.1719301981.gpuhpc06 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af6611c3aec877368a1d1060ff58fd9a8e57531a4aa2f08e5e61fad90cda8baf
3
+ size 6353
runs/Jun25_16-57-16_gpuhpc06/events.out.tfevents.1719302238.gpuhpc06 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e6c1b3c9acdee23148a068036a28174653fbcc3e32aeb94e29b489850671d52
3
+ size 6354
runs/Jun25_17-19-41_gpuhpc06/events.out.tfevents.1719303584.gpuhpc06 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3607fa3bb1e15688d76d4f15277fe93c5be344e185f7e1660764429ab31ac9a
3
+ size 6354
runs/Jun25_17-40-53_gpuhpc06/events.out.tfevents.1719304870.gpuhpc06 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15f5b8d55a029166aeea1e165bf901f48e7a5abeef8dd9577598633c7c0b89bf
3
+ size 6713
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "</s>",
35
+ "padding_side": "right",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": false
40
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:847c456bda4ebf6d3adef92f85d1433d2cf8dae2b0f979dbedb387937300543f
3
+ size 5112