Commit
•
9cf7050
1
Parent(s):
dcd2dcd
End of training
Browse files- README.md +19 -16
- config.json +70 -0
- generation_config.json +16 -0
- model.safetensors +3 -0
- runs/Mar12_18-08-40_52479658638a/events.out.tfevents.1710266932.52479658638a.683.1 +3 -0
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,9 +1,8 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
|
4 |
tags:
|
5 |
- generated_from_trainer
|
6 |
-
base_model: duancleypaul/bart-cnn-samsum-finetuned
|
7 |
model-index:
|
8 |
- name: bart-cnn-samsum-peft
|
9 |
results: []
|
@@ -16,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [duancleypaul/bart-cnn-samsum-finetuned](https://huggingface.co/duancleypaul/bart-cnn-samsum-finetuned) on an unknown dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -41,28 +40,32 @@ The following hyperparameters were used during training:
|
|
41 |
- seed: 42
|
42 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
43 |
- lr_scheduler_type: linear
|
44 |
-
- num_epochs:
|
45 |
|
46 |
### Training results
|
47 |
|
48 |
| Training Loss | Epoch | Step | Validation Loss |
|
49 |
|:-------------:|:-----:|:----:|:---------------:|
|
50 |
-
| 0.1088 | 1.0 | 148 | 0.
|
51 |
-
| 0.0754 | 2.0 | 296 | 0.
|
52 |
-
| 0.0947 | 3.0 | 444 | 0.
|
53 |
-
| 0.
|
54 |
-
| 0.0704 | 5.0 | 740 | 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
60 |
|
61 |
|
62 |
### Framework versions
|
63 |
|
64 |
-
- PEFT 0.9.0
|
65 |
- Transformers 4.38.2
|
66 |
- Pytorch 2.1.0+cu121
|
67 |
- Datasets 2.18.0
|
68 |
-
- Tokenizers 0.15.2
|
|
|
1 |
---
|
2 |
license: mit
|
3 |
+
base_model: duancleypaul/bart-cnn-samsum-finetuned
|
4 |
tags:
|
5 |
- generated_from_trainer
|
|
|
6 |
model-index:
|
7 |
- name: bart-cnn-samsum-peft
|
8 |
results: []
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [duancleypaul/bart-cnn-samsum-finetuned](https://huggingface.co/duancleypaul/bart-cnn-samsum-finetuned) on an unknown dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.1351
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
40 |
- seed: 42
|
41 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
42 |
- lr_scheduler_type: linear
|
43 |
+
- num_epochs: 15
|
44 |
|
45 |
### Training results
|
46 |
|
47 |
| Training Loss | Epoch | Step | Validation Loss |
|
48 |
|:-------------:|:-----:|:----:|:---------------:|
|
49 |
+
| 0.1088 | 1.0 | 148 | 0.1342 |
|
50 |
+
| 0.0754 | 2.0 | 296 | 0.1341 |
|
51 |
+
| 0.0947 | 3.0 | 444 | 0.1340 |
|
52 |
+
| 0.0982 | 4.0 | 592 | 0.1344 |
|
53 |
+
| 0.0704 | 5.0 | 740 | 0.1346 |
|
54 |
+
| 0.1018 | 6.0 | 888 | 0.1345 |
|
55 |
+
| 0.0904 | 7.0 | 1036 | 0.1341 |
|
56 |
+
| 0.091 | 8.0 | 1184 | 0.1346 |
|
57 |
+
| 0.0957 | 9.0 | 1332 | 0.1346 |
|
58 |
+
| 0.0785 | 10.0 | 1480 | 0.1345 |
|
59 |
+
| 0.104 | 11.0 | 1628 | 0.1348 |
|
60 |
+
| 0.1111 | 12.0 | 1776 | 0.1349 |
|
61 |
+
| 0.0839 | 13.0 | 1924 | 0.1350 |
|
62 |
+
| 0.0828 | 14.0 | 2072 | 0.1351 |
|
63 |
+
| 0.0925 | 15.0 | 2220 | 0.1351 |
|
64 |
|
65 |
|
66 |
### Framework versions
|
67 |
|
|
|
68 |
- Transformers 4.38.2
|
69 |
- Pytorch 2.1.0+cu121
|
70 |
- Datasets 2.18.0
|
71 |
+
- Tokenizers 0.15.2
|
config.json
ADDED
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "duancleypaul/bart-cnn-samsum-finetuned",
|
3 |
+
"_num_labels": 3,
|
4 |
+
"activation_dropout": 0.0,
|
5 |
+
"activation_function": "gelu",
|
6 |
+
"add_final_layer_norm": false,
|
7 |
+
"architectures": [
|
8 |
+
"BartForConditionalGeneration"
|
9 |
+
],
|
10 |
+
"attention_dropout": 0.0,
|
11 |
+
"bos_token_id": 0,
|
12 |
+
"classif_dropout": 0.0,
|
13 |
+
"classifier_dropout": 0.0,
|
14 |
+
"d_model": 1024,
|
15 |
+
"decoder_attention_heads": 16,
|
16 |
+
"decoder_ffn_dim": 4096,
|
17 |
+
"decoder_layerdrop": 0.0,
|
18 |
+
"decoder_layers": 12,
|
19 |
+
"decoder_start_token_id": 2,
|
20 |
+
"dropout": 0.1,
|
21 |
+
"early_stopping": true,
|
22 |
+
"encoder_attention_heads": 16,
|
23 |
+
"encoder_ffn_dim": 4096,
|
24 |
+
"encoder_layerdrop": 0.0,
|
25 |
+
"encoder_layers": 12,
|
26 |
+
"eos_token_id": 2,
|
27 |
+
"force_bos_token_to_be_generated": true,
|
28 |
+
"forced_bos_token_id": 0,
|
29 |
+
"forced_eos_token_id": 2,
|
30 |
+
"gradient_checkpointing": false,
|
31 |
+
"id2label": {
|
32 |
+
"0": "LABEL_0",
|
33 |
+
"1": "LABEL_1",
|
34 |
+
"2": "LABEL_2"
|
35 |
+
},
|
36 |
+
"init_std": 0.02,
|
37 |
+
"is_encoder_decoder": true,
|
38 |
+
"label2id": {
|
39 |
+
"LABEL_0": 0,
|
40 |
+
"LABEL_1": 1,
|
41 |
+
"LABEL_2": 2
|
42 |
+
},
|
43 |
+
"length_penalty": 2.0,
|
44 |
+
"max_length": 142,
|
45 |
+
"max_position_embeddings": 1024,
|
46 |
+
"min_length": 56,
|
47 |
+
"model_type": "bart",
|
48 |
+
"no_repeat_ngram_size": 3,
|
49 |
+
"normalize_before": false,
|
50 |
+
"num_beams": 4,
|
51 |
+
"num_hidden_layers": 12,
|
52 |
+
"output_past": true,
|
53 |
+
"pad_token_id": 1,
|
54 |
+
"prefix": " ",
|
55 |
+
"scale_embedding": false,
|
56 |
+
"task_specific_params": {
|
57 |
+
"summarization": {
|
58 |
+
"early_stopping": true,
|
59 |
+
"length_penalty": 2.0,
|
60 |
+
"max_length": 142,
|
61 |
+
"min_length": 56,
|
62 |
+
"no_repeat_ngram_size": 3,
|
63 |
+
"num_beams": 4
|
64 |
+
}
|
65 |
+
},
|
66 |
+
"torch_dtype": "float32",
|
67 |
+
"transformers_version": "4.38.2",
|
68 |
+
"use_cache": true,
|
69 |
+
"vocab_size": 50264
|
70 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 0,
|
4 |
+
"decoder_start_token_id": 2,
|
5 |
+
"early_stopping": true,
|
6 |
+
"eos_token_id": 2,
|
7 |
+
"forced_bos_token_id": 0,
|
8 |
+
"forced_eos_token_id": 2,
|
9 |
+
"length_penalty": 2.0,
|
10 |
+
"max_length": 142,
|
11 |
+
"min_length": 56,
|
12 |
+
"no_repeat_ngram_size": 3,
|
13 |
+
"num_beams": 4,
|
14 |
+
"pad_token_id": 1,
|
15 |
+
"transformers_version": "4.38.2"
|
16 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7cc3d61ed4528ff017b3207e17a311c07bb5e42199ee6c5a36a63a790ccacef
|
3 |
+
size 1644318512
|
runs/Mar12_18-08-40_52479658638a/events.out.tfevents.1710266932.52479658638a.683.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:935e6f45c3a19b4244350983298bc82b1a507278c1fc9d298bc467cec6a0c369
|
3 |
+
size 73493
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55f47ec515836d60d916965a7fcbb9e13568677a0f5ca25d4d91dac90d4e2a84
|
3 |
size 4920
|