Hugging Face's logo

Katochh
/
GenAI-task-2-ModelD-DS

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
Katochh commited on
Commit
f41f5d6
•
1 Parent(s): c1ca8cb

End of training

Browse files
Files changed (2) hide show
  1. README.md +126 -0
  2. runs/Apr28_16-46-03_de2c6d0141be/events.out.tfevents.1714322806.de2c6d0141be.999.0 +2 -2
README.md ADDED
@@ -0,0 +1,126 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: peft
4
+ tags:
5
+ - trl
6
+ - sft
7
+ - generated_from_trainer
8
+ base_model: petals-team/falcon-rw-1b
9
+ model-index:
10
+ - name: GenAI-task-2-ModelD-DS
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
+ # GenAI-task-2-ModelD-DS
18
+
19
+ This model is a fine-tuned version of [petals-team/falcon-rw-1b](https://huggingface.co/petals-team/falcon-rw-1b) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 0.8551
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: 2
42
+ - eval_batch_size: 8
43
+ - seed: 42
44
+ - gradient_accumulation_steps: 2
45
+ - total_train_batch_size: 4
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: cosine
48
+ - lr_scheduler_warmup_ratio: 0.01
49
+ - num_epochs: 2
50
+
51
+ ### Training results
52
+
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:------:|:----:|:---------------:|
55
+ | 1.538 | 0.0316 | 20 | 1.4898 |
56
+ | 2.1944 | 0.0631 | 40 | 1.4676 |
57
+ | 2.2479 | 0.0947 | 60 | 1.4396 |
58
+ | 1.7654 | 0.1263 | 80 | 1.3892 |
59
+ | 2.1763 | 0.1579 | 100 | 1.3834 |
60
+ | 1.3644 | 0.1894 | 120 | 1.3282 |
61
+ | 1.6781 | 0.2210 | 140 | 1.3058 |
62
+ | 1.7429 | 0.2526 | 160 | 1.2880 |
63
+ | 1.37 | 0.2841 | 180 | 1.2483 |
64
+ | 1.8196 | 0.3157 | 200 | 1.2511 |
65
+ | 1.223 | 0.3473 | 220 | 1.2120 |
66
+ | 1.5357 | 0.3788 | 240 | 1.2171 |
67
+ | 1.6471 | 0.4104 | 260 | 1.1906 |
68
+ | 1.271 | 0.4420 | 280 | 1.1818 |
69
+ | 1.7222 | 0.4736 | 300 | 1.1788 |
70
+ | 1.2022 | 0.5051 | 320 | 1.1170 |
71
+ | 1.4455 | 0.5367 | 340 | 1.1633 |
72
+ | 1.7014 | 0.5683 | 360 | 1.1011 |
73
+ | 1.1309 | 0.5998 | 380 | 1.0815 |
74
+ | 1.6978 | 0.6314 | 400 | 1.0966 |
75
+ | 1.0796 | 0.6630 | 420 | 1.0325 |
76
+ | 1.4504 | 0.6946 | 440 | 1.0429 |
77
+ | 1.4698 | 0.7261 | 460 | 1.0216 |
78
+ | 1.0858 | 0.7577 | 480 | 1.0031 |
79
+ | 1.4275 | 0.7893 | 500 | 1.0115 |
80
+ | 0.9607 | 0.8208 | 520 | 0.9771 |
81
+ | 1.2579 | 0.8524 | 540 | 0.9792 |
82
+ | 1.3363 | 0.8840 | 560 | 0.9608 |
83
+ | 1.0551 | 0.9155 | 580 | 0.9471 |
84
+ | 1.531 | 0.9471 | 600 | 0.9530 |
85
+ | 0.9776 | 0.9787 | 620 | 0.9321 |
86
+ | 1.374 | 1.0103 | 640 | 0.9257 |
87
+ | 0.9688 | 1.0418 | 660 | 0.9217 |
88
+ | 1.464 | 1.0734 | 680 | 0.9278 |
89
+ | 1.0608 | 1.1050 | 700 | 0.9040 |
90
+ | 1.0711 | 1.1365 | 720 | 0.9017 |
91
+ | 1.2806 | 1.1681 | 740 | 0.8954 |
92
+ | 0.9129 | 1.1997 | 760 | 0.8877 |
93
+ | 1.2161 | 1.2313 | 780 | 0.8907 |
94
+ | 1.0221 | 1.2628 | 800 | 0.8794 |
95
+ | 1.1306 | 1.2944 | 820 | 0.8782 |
96
+ | 1.3235 | 1.3260 | 840 | 0.8768 |
97
+ | 0.9663 | 1.3575 | 860 | 0.8711 |
98
+ | 1.3124 | 1.3891 | 880 | 0.8716 |
99
+ | 1.0169 | 1.4207 | 900 | 0.8663 |
100
+ | 1.1686 | 1.4522 | 920 | 0.8658 |
101
+ | 1.2976 | 1.4838 | 940 | 0.8656 |
102
+ | 0.8896 | 1.5154 | 960 | 0.8620 |
103
+ | 1.3252 | 1.5470 | 980 | 0.8623 |
104
+ | 1.0821 | 1.5785 | 1000 | 0.8601 |
105
+ | 1.1595 | 1.6101 | 1020 | 0.8594 |
106
+ | 1.4023 | 1.6417 | 1040 | 0.8591 |
107
+ | 0.8901 | 1.6732 | 1060 | 0.8574 |
108
+ | 1.2387 | 1.7048 | 1080 | 0.8575 |
109
+ | 0.9921 | 1.7364 | 1100 | 0.8564 |
110
+ | 1.0593 | 1.7680 | 1120 | 0.8558 |
111
+ | 1.3434 | 1.7995 | 1140 | 0.8558 |
112
+ | 0.8345 | 1.8311 | 1160 | 0.8554 |
113
+ | 1.3537 | 1.8627 | 1180 | 0.8554 |
114
+ | 1.0417 | 1.8942 | 1200 | 0.8552 |
115
+ | 1.0643 | 1.9258 | 1220 | 0.8551 |
116
+ | 1.2218 | 1.9574 | 1240 | 0.8551 |
117
+ | 1.1633 | 1.9890 | 1260 | 0.8551 |
118
+
119
+
120
+ ### Framework versions
121
+
122
+ - PEFT 0.10.0
123
+ - Transformers 4.40.0
124
+ - Pytorch 2.2.1+cu121
125
+ - Datasets 2.19.0
126
+ - Tokenizers 0.19.1
runs/Apr28_16-46-03_de2c6d0141be/events.out.tfevents.1714322806.de2c6d0141be.999.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45437adb6a2d4c9ce99d7994e2a330cc451d878175f7aab7c8fc70bafc678fe5
3
- size 36195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b61944af85ab79a288d9613deace2988008d9588dffcc1a7d181ba52ed2b330e
3
+ size 36549