Model save
Browse files- README.md +83 -0
- pytorch_model.bin +1 -1
README.md
ADDED
|
@@ -0,0 +1,83 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: microsoft/deberta-v3-large
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: checkpoints_3_14
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# checkpoints_3_14
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [microsoft/deberta-v3-large](https://huggingface.co/microsoft/deberta-v3-large) on the None dataset.
|
| 17 |
+
It achieves the following results on the evaluation set:
|
| 18 |
+
- Loss: 0.9950
|
| 19 |
+
- Map@3: 0.7360
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- learning_rate: 2e-05
|
| 39 |
+
- train_batch_size: 1
|
| 40 |
+
- eval_batch_size: 1
|
| 41 |
+
- seed: 0
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 8
|
| 44 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
+
- lr_scheduler_type: cosine
|
| 46 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 47 |
+
- num_epochs: 1
|
| 48 |
+
|
| 49 |
+
### Training results
|
| 50 |
+
|
| 51 |
+
| Training Loss | Epoch | Step | Validation Loss | Map@3 |
|
| 52 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 53 |
+
| 1.6075 | 0.04 | 200 | 1.6074 | 0.6027 |
|
| 54 |
+
| 1.5444 | 0.08 | 400 | 1.3248 | 0.6428 |
|
| 55 |
+
| 1.4506 | 0.13 | 600 | 1.2670 | 0.6707 |
|
| 56 |
+
| 1.3635 | 0.17 | 800 | 1.1671 | 0.6850 |
|
| 57 |
+
| 1.3478 | 0.21 | 1000 | 1.0909 | 0.7003 |
|
| 58 |
+
| 1.3021 | 0.25 | 1200 | 1.0701 | 0.6923 |
|
| 59 |
+
| 1.3284 | 0.29 | 1400 | 1.0627 | 0.7085 |
|
| 60 |
+
| 1.2869 | 0.34 | 1600 | 1.0645 | 0.7003 |
|
| 61 |
+
| 1.2735 | 0.38 | 1800 | 1.1617 | 0.7043 |
|
| 62 |
+
| 1.3019 | 0.42 | 2000 | 1.0272 | 0.7120 |
|
| 63 |
+
| 1.2824 | 0.46 | 2200 | 1.0781 | 0.7123 |
|
| 64 |
+
| 1.2882 | 0.51 | 2400 | 1.0454 | 0.7178 |
|
| 65 |
+
| 1.2699 | 0.55 | 2600 | 1.0439 | 0.7225 |
|
| 66 |
+
| 1.2165 | 0.59 | 2800 | 1.0208 | 0.7260 |
|
| 67 |
+
| 1.2419 | 0.63 | 3000 | 1.0166 | 0.7292 |
|
| 68 |
+
| 1.2395 | 0.67 | 3200 | 1.0065 | 0.7310 |
|
| 69 |
+
| 1.2368 | 0.72 | 3400 | 1.0429 | 0.7275 |
|
| 70 |
+
| 1.2232 | 0.76 | 3600 | 1.0105 | 0.7353 |
|
| 71 |
+
| 1.1969 | 0.8 | 3800 | 1.0017 | 0.7370 |
|
| 72 |
+
| 1.2451 | 0.84 | 4000 | 0.9982 | 0.7383 |
|
| 73 |
+
| 1.2088 | 0.88 | 4200 | 0.9977 | 0.7372 |
|
| 74 |
+
| 1.2229 | 0.93 | 4400 | 0.9953 | 0.7367 |
|
| 75 |
+
| 1.2612 | 0.97 | 4600 | 0.9950 | 0.7360 |
|
| 76 |
+
|
| 77 |
+
|
| 78 |
+
### Framework versions
|
| 79 |
+
|
| 80 |
+
- Transformers 4.33.2
|
| 81 |
+
- Pytorch 2.0.1+cu118
|
| 82 |
+
- Datasets 2.14.5
|
| 83 |
+
- Tokenizers 0.13.3
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 1740387701
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f470ee1903395f191af8613895c745a7e7414cea6de5e6c8769f97562c1d6d36
|
| 3 |
size 1740387701
|