Hugging Face's logo

amztheory
/
falcon-7b-code-python

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files
xet
Metrics Community
amztheory commited on
Commit
95e6446
·
verified ·
1 Parent(s): 47a3833

Model save

Browse files
Files changed (19) hide show
  1. README.md +71 -0
  2. adapter_config.json +28 -0
  3. adapter_model.safetensors +3 -0
  4. runs/May24_05-06-15_eb729ab69650/events.out.tfevents.1716527183.eb729ab69650.6573.0 +3 -0
  5. runs/May24_05-07-25_eb729ab69650/events.out.tfevents.1716527252.eb729ab69650.6946.0 +3 -0
  6. runs/May24_05-08-48_eb729ab69650/events.out.tfevents.1716527335.eb729ab69650.7379.0 +3 -0
  7. runs/May24_05-11-32_eb729ab69650/events.out.tfevents.1716527499.eb729ab69650.8194.0 +3 -0
  8. runs/May24_05-14-18_eb729ab69650/events.out.tfevents.1716527665.eb729ab69650.8970.0 +3 -0
  9. runs/May24_05-19-09_eb729ab69650/events.out.tfevents.1716527956.eb729ab69650.10277.0 +3 -0
  10. runs/May24_05-21-12_eb729ab69650/events.out.tfevents.1716528079.eb729ab69650.10876.0 +3 -0
  11. runs/May24_05-23-22_eb729ab69650/events.out.tfevents.1716528209.eb729ab69650.11507.0 +3 -0
  12. runs/May24_06-24-01_eb729ab69650/events.out.tfevents.1716531848.eb729ab69650.27550.0 +3 -0
  13. runs/May24_07-06-31_eb729ab69650/events.out.tfevents.1716534425.eb729ab69650.38261.0 +3 -0
  14. runs/May24_08-16-01_eb729ab69650/events.out.tfevents.1716538633.eb729ab69650.55891.0 +3 -0
  15. special_tokens_map.json +23 -0
  16. tokenizer.json +0 -0
  17. tokenizer.model +3 -0
  18. tokenizer_config.json +123 -0
  19. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: tiiuae/falcon-7b-instruct
9
+ model-index:
10
+ - name: falcon-7b-code-python
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
+ # falcon-7b-code-python
18
+
19
+ This model is a fine-tuned version of [tiiuae/falcon-7b-instruct](https://huggingface.co/tiiuae/falcon-7b-instruct) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.1486
22
+
23
+ ## Model description
24
+
25
+ More information needed
26
+
27
+ ## Intended uses & limitations
28
+
29
+ More information needed
30
+
31
+ ## Training and evaluation data
32
+
33
+ More information needed
34
+
35
+ ## Training procedure
36
+
37
+ ### Training hyperparameters
38
+
39
+ The following hyperparameters were used during training:
40
+ - learning_rate: 2e-05
41
+ - train_batch_size: 6
42
+ - eval_batch_size: 6
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 4
45
+ - total_train_batch_size: 24
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - num_epochs: 3
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:------:|:----:|:---------------:|
54
+ | 1.3986 | 0.3183 | 30 | 1.4874 |
55
+ | 1.3762 | 0.6366 | 60 | 1.4038 |
56
+ | 1.2544 | 0.9549 | 90 | 1.3065 |
57
+ | 1.1233 | 1.2732 | 120 | 1.2405 |
58
+ | 1.1611 | 1.5915 | 150 | 1.1918 |
59
+ | 1.1243 | 1.9098 | 180 | 1.1603 |
60
+ | 1.0911 | 2.2281 | 210 | 1.1504 |
61
+ | 1.1027 | 2.5464 | 240 | 1.1489 |
62
+ | 1.1615 | 2.8647 | 270 | 1.1486 |
63
+
64
+
65
+ ### Framework versions
66
+
67
+ - PEFT 0.11.1
68
+ - Transformers 4.41.0
69
+ - Pytorch 2.3.0+cu121
70
+ - Datasets 2.19.1
71
+ - Tokenizers 0.19.1
adapter_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alpha_pattern": {},
3
+ "auto_mapping": null,
4
+ "base_model_name_or_path": "tiiuae/falcon-7b-instruct",
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": 64,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "query_key_value"
24
+ ],
25
+ "task_type": "CAUSAL_LM",
26
+ "use_dora": false,
27
+ "use_rslora": false
28
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:883bac4f0d3f6db65c50e6cf5ebdaac82e826046849b7d4993cf99bb0d89ec96
3
+ size 37758384
runs/May24_05-06-15_eb729ab69650/events.out.tfevents.1716527183.eb729ab69650.6573.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39d0db223f26cd4b2dfad89d6407746c7e858f8dc8324c45350225a7fcff34b9
3
+ size 6056
runs/May24_05-07-25_eb729ab69650/events.out.tfevents.1716527252.eb729ab69650.6946.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a41624668392e92ef023773f4a19aa63974a4aa6fc4fabd5edbd0998fa0b79b4
3
+ size 6056
runs/May24_05-08-48_eb729ab69650/events.out.tfevents.1716527335.eb729ab69650.7379.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:063b4a502ff06007cd427d9026abcea81c9b5b9423552731f03929ce4bea300b
3
+ size 7002
runs/May24_05-11-32_eb729ab69650/events.out.tfevents.1716527499.eb729ab69650.8194.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9737526ce7d3c020a01d9a25d842d55b1e8a6fc1e7c1f6f434e3d20c37caa6a5
3
+ size 6404
runs/May24_05-14-18_eb729ab69650/events.out.tfevents.1716527665.eb729ab69650.8970.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4298d4359f90412a07bc9636a6132dddb2d5cc75862000c0e9d388d0d1522d37
3
+ size 7945
runs/May24_05-19-09_eb729ab69650/events.out.tfevents.1716527956.eb729ab69650.10277.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b5cb4dda68dc125b5f329619e07234aabacb29adea34234487b9da04e84f113
3
+ size 6468
runs/May24_05-21-12_eb729ab69650/events.out.tfevents.1716528079.eb729ab69650.10876.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1690855beb96755a538ec3ea57e42b73f31175296c5e8dd6da3da0060e190694
3
+ size 6263
runs/May24_05-23-22_eb729ab69650/events.out.tfevents.1716528209.eb729ab69650.11507.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11b2dfad60ac11ff95a51375b9ed680dd01dec75f38d51ac303a72c770156d00
3
+ size 20543
runs/May24_06-24-01_eb729ab69650/events.out.tfevents.1716531848.eb729ab69650.27550.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d5b2bfb94cd2ded40614e57bc131bd177c0a42a2f49240a48722b37c2eac7e4
3
+ size 11545
runs/May24_07-06-31_eb729ab69650/events.out.tfevents.1716534425.eb729ab69650.38261.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13215d4cf533545ef94f1b88ad0e0c74744fbef11838b85334b79b3216900573
3
+ size 19874
runs/May24_08-16-01_eb729ab69650/events.out.tfevents.1716538633.eb729ab69650.55891.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24709ddb8e8ae329efa95b85ee5f5d887008071abf252e90b7257f73025e02ff
3
+ size 20616
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ ">>TITLE<<",
4
+ ">>ABSTRACT<<",
5
+ ">>INTRODUCTION<<",
6
+ ">>SUMMARY<<",
7
+ ">>COMMENT<<",
8
+ ">>ANSWER<<",
9
+ ">>QUESTION<<",
10
+ ">>DOMAIN<<",
11
+ ">>PREFIX<<",
12
+ ">>SUFFIX<<",
13
+ ">>MIDDLE<<"
14
+ ],
15
+ "eos_token": {
16
+ "content": "<|endoftext|>",
17
+ "lstrip": false,
18
+ "normalized": false,
19
+ "rstrip": false,
20
+ "single_word": false
21
+ },
22
+ "pad_token": "<|endoftext|>"
23
+ }
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 +1,123 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": ">>TITLE<<",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": ">>ABSTRACT<<",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": ">>INTRODUCTION<<",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": ">>SUMMARY<<",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": ">>COMMENT<<",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": ">>ANSWER<<",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": ">>QUESTION<<",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": ">>DOMAIN<<",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": ">>PREFIX<<",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": ">>SUFFIX<<",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": ">>MIDDLE<<",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<|endoftext|>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ }
100
+ },
101
+ "additional_special_tokens": [
102
+ ">>TITLE<<",
103
+ ">>ABSTRACT<<",
104
+ ">>INTRODUCTION<<",
105
+ ">>SUMMARY<<",
106
+ ">>COMMENT<<",
107
+ ">>ANSWER<<",
108
+ ">>QUESTION<<",
109
+ ">>DOMAIN<<",
110
+ ">>PREFIX<<",
111
+ ">>SUFFIX<<",
112
+ ">>MIDDLE<<"
113
+ ],
114
+ "clean_up_tokenization_spaces": true,
115
+ "eos_token": "<|endoftext|>",
116
+ "model_input_names": [
117
+ "input_ids",
118
+ "attention_mask"
119
+ ],
120
+ "model_max_length": 512,
121
+ "pad_token": "<|endoftext|>",
122
+ "tokenizer_class": "PreTrainedTokenizerFast"
123
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0af1836a121709c3b1331a8150f460b160a58873a6136f141fc4be2d3a3788c3
3
+ size 5112