Hugging Face's logo

MUsama100
/
Falcon-7b-Finetuned-MBPP-Dataset-base

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
MUsama100 commited on
Commit
ec86e15
•
1 Parent(s): d88beb9

End of training

Browse files
Files changed (8) hide show
  1. README.md +130 -0
  2. adapter_config.json +31 -0
  3. adapter_model.safetensors +3 -0
  4. runs/Apr27_13-55-20_6b52953bfd02/events.out.tfevents.1714226121.6b52953bfd02.770.0 +3 -0
  5. special_tokens_map.json +23 -0
  6. tokenizer.json +0 -0
  7. tokenizer_config.json +123 -0
  8. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,130 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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-Finetuned-MBPP-Dataset-base
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-Finetuned-MBPP-Dataset-base
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: 0.9306
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: 1e-06
41
+ - train_batch_size: 1
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: cosine
46
+ - lr_scheduler_warmup_ratio: 0.05
47
+ - num_epochs: 5
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-----:|:----:|:---------------:|
54
+ | 1.8233 | 0.07 | 50 | 1.5671 |
55
+ | 1.673 | 0.15 | 100 | 1.5646 |
56
+ | 1.635 | 0.22 | 150 | 1.5569 |
57
+ | 1.4232 | 0.29 | 200 | 1.5369 |
58
+ | 1.4397 | 0.37 | 250 | 1.5073 |
59
+ | 1.5663 | 0.44 | 300 | 1.4721 |
60
+ | 1.4632 | 0.51 | 350 | 1.4342 |
61
+ | 1.6059 | 0.59 | 400 | 1.3978 |
62
+ | 1.6951 | 0.66 | 450 | 1.3606 |
63
+ | 1.7563 | 0.73 | 500 | 1.3241 |
64
+ | 0.939 | 0.81 | 550 | 1.2867 |
65
+ | 0.8452 | 0.88 | 600 | 1.2481 |
66
+ | 1.1147 | 0.95 | 650 | 1.2084 |
67
+ | 0.8543 | 1.03 | 700 | 1.1682 |
68
+ | 0.6985 | 1.1 | 750 | 1.1356 |
69
+ | 1.0973 | 1.17 | 800 | 1.1100 |
70
+ | 2.0793 | 1.25 | 850 | 1.0892 |
71
+ | 0.9806 | 1.32 | 900 | 1.0713 |
72
+ | 0.8114 | 1.4 | 950 | 1.0555 |
73
+ | 1.4202 | 1.47 | 1000 | 1.0425 |
74
+ | 0.7755 | 1.54 | 1050 | 1.0314 |
75
+ | 0.8624 | 1.62 | 1100 | 1.0223 |
76
+ | 1.6017 | 1.69 | 1150 | 1.0143 |
77
+ | 1.069 | 1.76 | 1200 | 1.0071 |
78
+ | 1.2192 | 1.84 | 1250 | 1.0007 |
79
+ | 0.8816 | 1.91 | 1300 | 0.9944 |
80
+ | 0.9615 | 1.98 | 1350 | 0.9887 |
81
+ | 1.2626 | 2.06 | 1400 | 0.9833 |
82
+ | 1.0128 | 2.13 | 1450 | 0.9787 |
83
+ | 0.7951 | 2.2 | 1500 | 0.9741 |
84
+ | 1.0879 | 2.28 | 1550 | 0.9701 |
85
+ | 1.0546 | 2.35 | 1600 | 0.9661 |
86
+ | 0.9218 | 2.42 | 1650 | 0.9625 |
87
+ | 1.1159 | 2.5 | 1700 | 0.9591 |
88
+ | 0.6223 | 2.57 | 1750 | 0.9561 |
89
+ | 0.7334 | 2.64 | 1800 | 0.9536 |
90
+ | 0.9296 | 2.72 | 1850 | 0.9512 |
91
+ | 1.0653 | 2.79 | 1900 | 0.9489 |
92
+ | 0.8812 | 2.86 | 1950 | 0.9469 |
93
+ | 0.7767 | 2.94 | 2000 | 0.9452 |
94
+ | 0.9707 | 3.01 | 2050 | 0.9435 |
95
+ | 1.1393 | 3.08 | 2100 | 0.9420 |
96
+ | 0.8604 | 3.16 | 2150 | 0.9407 |
97
+ | 0.7592 | 3.23 | 2200 | 0.9396 |
98
+ | 0.8046 | 3.3 | 2250 | 0.9385 |
99
+ | 1.5882 | 3.38 | 2300 | 0.9375 |
100
+ | 1.0068 | 3.45 | 2350 | 0.9366 |
101
+ | 1.205 | 3.52 | 2400 | 0.9357 |
102
+ | 0.689 | 3.6 | 2450 | 0.9350 |
103
+ | 0.8573 | 3.67 | 2500 | 0.9344 |
104
+ | 1.072 | 3.74 | 2550 | 0.9338 |
105
+ | 0.9188 | 3.82 | 2600 | 0.9332 |
106
+ | 1.3385 | 3.89 | 2650 | 0.9327 |
107
+ | 0.9067 | 3.96 | 2700 | 0.9324 |
108
+ | 0.9993 | 4.04 | 2750 | 0.9321 |
109
+ | 0.8222 | 4.11 | 2800 | 0.9317 |
110
+ | 0.8129 | 4.19 | 2850 | 0.9315 |
111
+ | 0.7861 | 4.26 | 2900 | 0.9313 |
112
+ | 1.3126 | 4.33 | 2950 | 0.9311 |
113
+ | 0.9465 | 4.41 | 3000 | 0.9310 |
114
+ | 0.9444 | 4.48 | 3050 | 0.9309 |
115
+ | 0.5677 | 4.55 | 3100 | 0.9308 |
116
+ | 0.7046 | 4.63 | 3150 | 0.9307 |
117
+ | 1.5036 | 4.7 | 3200 | 0.9307 |
118
+ | 1.0087 | 4.77 | 3250 | 0.9307 |
119
+ | 0.6705 | 4.85 | 3300 | 0.9306 |
120
+ | 1.0425 | 4.92 | 3350 | 0.9306 |
121
+ | 0.3666 | 4.99 | 3400 | 0.9306 |
122
+
123
+
124
+ ### Framework versions
125
+
126
+ - PEFT 0.10.1.dev0
127
+ - Transformers 4.38.2
128
+ - Pytorch 2.2.1+cu121
129
+ - Datasets 2.19.0
130
+ - Tokenizers 0.15.2
adapter_config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 0.5,
15
+ "megatron_config": null,
16
+ "megatron_core": "megatron.core",
17
+ "modules_to_save": null,
18
+ "peft_type": "LORA",
19
+ "r": 32,
20
+ "rank_pattern": {},
21
+ "revision": null,
22
+ "target_modules": [
23
+ "query_key_value",
24
+ "dense",
25
+ "dense_h_to_4h",
26
+ "dense_4h_to_h"
27
+ ],
28
+ "task_type": "CAUSAL_LM",
29
+ "use_dora": false,
30
+ "use_rslora": false
31
+ }
adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf144c5555ad91afbd860bed62ea1454a6456e6f42c519cd42235d0316e767d7
3
+ size 261131840
runs/Apr27_13-55-20_6b52953bfd02/events.out.tfevents.1714226121.6b52953bfd02.770.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbb6ae5e408df57599ea0c9e52acbee9be6230a16fac5b3ee0bc2e60b5afb93
3
+ size 742425
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_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": 2048,
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:ea25bb4f2ea0747ec4d7d8b5df059fb0222350477a79689321ab9c84a6423025
3
+ size 4920