version 1
Browse files
README.md
ADDED
@@ -0,0 +1,73 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
base_model: facebook/bart-large
|
4 |
+
tags:
|
5 |
+
- text2text-generation
|
6 |
+
- generated_from_trainer
|
7 |
+
metrics:
|
8 |
+
- sacrebleu
|
9 |
+
model-index:
|
10 |
+
- name: model_v1e_5_8_8_4
|
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 |
+
# model_v1e_5_8_8_4
|
18 |
+
|
19 |
+
This model is a fine-tuned version of [facebook/bart-large](https://huggingface.co/facebook/bart-large) on the None dataset.
|
20 |
+
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 0.5522
|
22 |
+
- Sacrebleu: 66.9834
|
23 |
+
|
24 |
+
## Model description
|
25 |
+
|
26 |
+
More information needed
|
27 |
+
|
28 |
+
## Intended uses & limitations
|
29 |
+
|
30 |
+
More information needed
|
31 |
+
|
32 |
+
## Training and evaluation data
|
33 |
+
|
34 |
+
More information needed
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
+
|
38 |
+
### Training hyperparameters
|
39 |
+
|
40 |
+
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 1e-05
|
42 |
+
- train_batch_size: 16
|
43 |
+
- eval_batch_size: 16
|
44 |
+
- seed: 42
|
45 |
+
- gradient_accumulation_steps: 4
|
46 |
+
- total_train_batch_size: 64
|
47 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
48 |
+
- lr_scheduler_type: linear
|
49 |
+
- num_epochs: 10
|
50 |
+
- mixed_precision_training: Native AMP
|
51 |
+
|
52 |
+
### Training results
|
53 |
+
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:---------:|
|
56 |
+
| No log | 1.0 | 218 | 0.5616 | 66.0295 |
|
57 |
+
| No log | 2.0 | 437 | 0.5691 | 66.6355 |
|
58 |
+
| No log | 3.0 | 656 | 0.5544 | 66.8901 |
|
59 |
+
| No log | 4.0 | 875 | 0.5522 | 66.9834 |
|
60 |
+
| No log | 5.0 | 1093 | 0.5686 | 67.0746 |
|
61 |
+
| No log | 6.0 | 1312 | 0.5995 | 67.1015 |
|
62 |
+
| No log | 7.0 | 1531 | 0.5663 | 67.1106 |
|
63 |
+
| No log | 8.0 | 1750 | 0.5860 | 67.0824 |
|
64 |
+
| No log | 9.0 | 1968 | 0.6075 | 67.1805 |
|
65 |
+
| No log | 9.97 | 2180 | 0.6105 | 67.1350 |
|
66 |
+
|
67 |
+
|
68 |
+
### Framework versions
|
69 |
+
|
70 |
+
- Transformers 4.39.3
|
71 |
+
- Pytorch 2.1.2
|
72 |
+
- Datasets 2.18.0
|
73 |
+
- Tokenizers 0.15.2
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 0,
|
3 |
+
"decoder_start_token_id": 2,
|
4 |
+
"early_stopping": true,
|
5 |
+
"eos_token_id": 2,
|
6 |
+
"forced_bos_token_id": 0,
|
7 |
+
"forced_eos_token_id": 2,
|
8 |
+
"no_repeat_ngram_size": 3,
|
9 |
+
"num_beams": 4,
|
10 |
+
"pad_token_id": 1,
|
11 |
+
"transformers_version": "4.39.3"
|
12 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1625426996
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36c98fe37cd55d3778c5bf00e50f049d1d930042f089ade270e2f6af7d379984
|
3 |
size 1625426996
|
runs/May26_20-35-18_130b07e1ed31/events.out.tfevents.1716755900.130b07e1ed31.25.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a138b47f9fb16f370338285d8e6ec30ab83beb37a4b257333f671f1a721544ac
|
3 |
+
size 9645
|
runs/May26_20-35-18_130b07e1ed31/events.out.tfevents.1716763807.130b07e1ed31.25.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ed537fef514c676cea9eccb7023488e926039bbcfbdad53ebf1785db741c7a2
|
3 |
+
size 412
|