End of training
Browse files- README.md +10 -19
- config.json +1 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- tokenizer_config.json +1 -1
- training_args.bin +2 -2
README.md
CHANGED
@@ -12,14 +12,15 @@ model-index:
|
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
should probably proofread and complete it, then remove this comment. -->
|
14 |
|
|
|
15 |
# pegasus-x-large-booksum-16k
|
16 |
|
17 |
This model is a fine-tuned version of [ubaada/pegasus-x-large-booksum-16k](https://huggingface.co/ubaada/pegasus-x-large-booksum-16k) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 1.
|
20 |
-
- Rouge1: 0.
|
21 |
-
- Rouge2: 0.
|
22 |
-
- Rougel: 0.
|
23 |
|
24 |
## Model description
|
25 |
|
@@ -38,36 +39,26 @@ More information needed
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
-
- learning_rate:
|
42 |
- train_batch_size: 8
|
43 |
- eval_batch_size: 1
|
44 |
- seed: 42
|
45 |
-
- distributed_type: multi-GPU
|
46 |
-
- num_devices: 2
|
47 |
- gradient_accumulation_steps: 4
|
48 |
-
- total_train_batch_size:
|
49 |
-
- total_eval_batch_size: 2
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: linear
|
52 |
-
- num_epochs:
|
53 |
|
54 |
### Training results
|
55 |
|
56 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|
57 |
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
|
58 |
-
| 1.
|
59 |
-
| 1.1051 | 1.9992 | 628 | 1.9696 | 0.3354 | 0.0549 | 0.1373 |
|
60 |
-
| 1.0564 | 2.9992 | 942 | 1.9652 | 0.3215 | 0.0526 | 0.1427 |
|
61 |
-
| 1.0657 | 3.9992 | 1256 | 1.9545 | 0.3370 | 0.0579 | 0.1424 |
|
62 |
-
| 0.9694 | 4.9984 | 1570 | 1.9517 | 0.3766 | 0.0721 | 0.1532 |
|
63 |
-
| 1.0343 | 5.9976 | 1884 | 1.9474 | 0.3558 | 0.0638 | 0.1488 |
|
64 |
-
| 1.3146 | 7.0 | 2199 | 1.9475 | 0.3443 | 0.0568 | 0.1440 |
|
65 |
-
| 0.9008 | 7.9960 | 2512 | 1.9460 | 0.3363 | 0.0569 | 0.1490 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
69 |
|
70 |
-
- Transformers 4.
|
71 |
- Pytorch 2.2.0
|
72 |
- Datasets 2.19.1
|
73 |
- Tokenizers 0.19.1
|
|
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
should probably proofread and complete it, then remove this comment. -->
|
14 |
|
15 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/theubaada/huggingface/runs/fvqvjsw6)
|
16 |
# pegasus-x-large-booksum-16k
|
17 |
|
18 |
This model is a fine-tuned version of [ubaada/pegasus-x-large-booksum-16k](https://huggingface.co/ubaada/pegasus-x-large-booksum-16k) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.8948
|
21 |
+
- Rouge1: 0.3044
|
22 |
+
- Rouge2: 0.0517
|
23 |
+
- Rougel: 0.1398
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 8e-05
|
43 |
- train_batch_size: 8
|
44 |
- eval_batch_size: 1
|
45 |
- seed: 42
|
|
|
|
|
46 |
- gradient_accumulation_steps: 4
|
47 |
+
- total_train_batch_size: 32
|
|
|
48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
49 |
- lr_scheduler_type: linear
|
50 |
+
- num_epochs: 1
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|
55 |
|:-------------:|:------:|:----:|:---------------:|:------:|:------:|:------:|
|
56 |
+
| 1.3001 | 0.9992 | 314 | 1.8948 | 0.3044 | 0.0517 | 0.1398 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
57 |
|
58 |
|
59 |
### Framework versions
|
60 |
|
61 |
+
- Transformers 4.41.0
|
62 |
- Pytorch 2.2.0
|
63 |
- Datasets 2.19.1
|
64 |
- Tokenizers 0.19.1
|
config.json
CHANGED
@@ -54,7 +54,7 @@
|
|
54 |
"stagger_local_blocks": true,
|
55 |
"static_position_embeddings": true,
|
56 |
"torch_dtype": "float32",
|
57 |
-
"transformers_version": "4.
|
58 |
"use_cache": true,
|
59 |
"vocab_size": 96103
|
60 |
}
|
|
|
54 |
"stagger_local_blocks": true,
|
55 |
"static_position_embeddings": true,
|
56 |
"torch_dtype": "float32",
|
57 |
+
"transformers_version": "4.41.0",
|
58 |
"use_cache": true,
|
59 |
"vocab_size": 96103
|
60 |
}
|
generation_config.json
CHANGED
@@ -8,5 +8,5 @@
|
|
8 |
"num_beams": 5,
|
9 |
"pad_token_id": 0,
|
10 |
"repetition_penalty": 2.0,
|
11 |
-
"transformers_version": "4.
|
12 |
}
|
|
|
8 |
"num_beams": 5,
|
9 |
"pad_token_id": 0,
|
10 |
"repetition_penalty": 2.0,
|
11 |
+
"transformers_version": "4.41.0"
|
12 |
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2274730128
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce98531bc23515683731dfeb0728868c4635ee09df0b7311be52edc52a4d5fb9
|
3 |
size 2274730128
|
tokenizer_config.json
CHANGED
@@ -959,7 +959,7 @@
|
|
959 |
"mask_token": "<mask_2>",
|
960 |
"mask_token_sent": "<mask_1>",
|
961 |
"max_length": 16384,
|
962 |
-
"model_max_length":
|
963 |
"offset": 103,
|
964 |
"pad_to_multiple_of": null,
|
965 |
"pad_token": "<pad>",
|
|
|
959 |
"mask_token": "<mask_2>",
|
960 |
"mask_token_sent": "<mask_1>",
|
961 |
"max_length": 16384,
|
962 |
+
"model_max_length": 16384,
|
963 |
"offset": 103,
|
964 |
"pad_to_multiple_of": null,
|
965 |
"pad_token": "<pad>",
|
training_args.bin
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 sha256:9d7a58e5c136fc96f10523fd719d0eb94df70f3e8ae510a25cb6296f2fed8d8e
|
3 |
+
size 6968
|