abdiharyadi
commited on
Commit
•
19d3b47
1
Parent(s):
4e745ed
Model save
Browse files- README.md +93 -0
- generation_config.json +12 -0
- last-checkpoint/model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +0 -0
- run-2024-10-28T15:22:08+00:00.log +4 -0
README.md
ADDED
@@ -0,0 +1,93 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- generated_from_trainer
|
4 |
+
datasets:
|
5 |
+
- data
|
6 |
+
metrics:
|
7 |
+
- bleu
|
8 |
+
model-index:
|
9 |
+
- name: mbart-en-id-smaller-indo-amr-generation-fted-with-prefix
|
10 |
+
results:
|
11 |
+
- task:
|
12 |
+
name: Sequence-to-sequence Language Modeling
|
13 |
+
type: text2text-generation
|
14 |
+
dataset:
|
15 |
+
name: data
|
16 |
+
type: data
|
17 |
+
config: default
|
18 |
+
split: validation
|
19 |
+
args: default
|
20 |
+
metrics:
|
21 |
+
- name: Bleu
|
22 |
+
type: bleu
|
23 |
+
value: 13.717
|
24 |
+
---
|
25 |
+
|
26 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
27 |
+
should probably proofread and complete it, then remove this comment. -->
|
28 |
+
|
29 |
+
# mbart-en-id-smaller-indo-amr-generation-fted-with-prefix
|
30 |
+
|
31 |
+
This model was trained from scratch on the data dataset.
|
32 |
+
It achieves the following results on the evaluation set:
|
33 |
+
- Loss: 2.3974
|
34 |
+
- Bleu: 13.717
|
35 |
+
- Gen Len: 36.5221
|
36 |
+
|
37 |
+
## Model description
|
38 |
+
|
39 |
+
More information needed
|
40 |
+
|
41 |
+
## Intended uses & limitations
|
42 |
+
|
43 |
+
More information needed
|
44 |
+
|
45 |
+
## Training and evaluation data
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Training procedure
|
50 |
+
|
51 |
+
### Training hyperparameters
|
52 |
+
|
53 |
+
The following hyperparameters were used during training:
|
54 |
+
- learning_rate: 2e-07
|
55 |
+
- train_batch_size: 2
|
56 |
+
- eval_batch_size: 2
|
57 |
+
- seed: 42
|
58 |
+
- gradient_accumulation_steps: 12
|
59 |
+
- total_train_batch_size: 24
|
60 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
61 |
+
- lr_scheduler_type: polynomial
|
62 |
+
- lr_scheduler_warmup_steps: 200
|
63 |
+
- num_epochs: 16.0
|
64 |
+
- label_smoothing_factor: 0.1
|
65 |
+
|
66 |
+
### Training results
|
67 |
+
|
68 |
+
| Training Loss | Epoch | Step | Bleu | Gen Len | Validation Loss |
|
69 |
+
|:-------------:|:-------:|:-----:|:-------:|:--------:|:---------------:|
|
70 |
+
| 3.0219 | 0.9999 | 3869 | 0.0741 | 114.8177 | 2.9798 |
|
71 |
+
| 2.8978 | 2.0 | 7739 | 0.0747 | 113.0081 | 2.8610 |
|
72 |
+
| 2.8109 | 2.9999 | 11608 | 0.0795 | 111.475 | 2.7648 |
|
73 |
+
| 2.7623 | 4.0 | 15478 | 0.1685 | 105.7747 | 2.6956 |
|
74 |
+
| 2.7116 | 4.9999 | 19347 | 0.5081 | 92.4187 | 2.6404 |
|
75 |
+
| 2.6331 | 5.9999 | 23214 | 1.6991 | 66.9245 | 2.5961 |
|
76 |
+
| 2.5716 | 7.0 | 27084 | 5.2201 | 46.1405 | 2.5611 |
|
77 |
+
| 2.5943 | 7.9999 | 30953 | 8.0263 | 40.7538 | 2.5300 |
|
78 |
+
| 2.5622 | 9.0 | 34823 | 10.2353 | 38.2607 | 2.5050 |
|
79 |
+
| 2.537 | 9.9999 | 38692 | 11.3364 | 36.0732 | 2.4840 |
|
80 |
+
| 2.5345 | 11.0 | 42562 | 12.1716 | 36.4367 | 2.4645 |
|
81 |
+
| 2.4706 | 11.9999 | 46428 | 2.4479 | 12.51 | 37.4146 |
|
82 |
+
| 2.4558 | 13.0 | 50298 | 2.4330 | 12.8144 | 37.2979 |
|
83 |
+
| 2.4125 | 13.9999 | 54167 | 2.4199 | 13.0772 | 37.0436 |
|
84 |
+
| 2.4053 | 15.0 | 58037 | 2.4081 | 13.5764 | 36.1492 |
|
85 |
+
| 2.439 | 15.9994 | 61904 | 2.3974 | 13.717 | 36.5221 |
|
86 |
+
|
87 |
+
|
88 |
+
### Framework versions
|
89 |
+
|
90 |
+
- Transformers 4.44.0
|
91 |
+
- Pytorch 2.4.0+cu121
|
92 |
+
- Datasets 2.20.0
|
93 |
+
- Tokenizers 0.19.1
|
generation_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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_eos_token_id": 2,
|
8 |
+
"max_length": 200,
|
9 |
+
"num_beams": 5,
|
10 |
+
"pad_token_id": 1,
|
11 |
+
"transformers_version": "4.44.0"
|
12 |
+
}
|
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1575259780
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b35a3bc2ac180ed070b42029c9a9dd327a1a9559e81df276f329c07eb21d04fc
|
3 |
size 1575259780
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3150397656
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ba79276529acf6b7fcac21ab5be5fc5756c900e697415161ce71f7759f9fa8e0
|
3 |
size 3150397656
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2e52ca2f5b1048c2984d9cb01ff8bc5c06ec7e6e1ac850eb54ef8fe7147dcf65
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:df05e968bcb6cb9f8c607bdaf90fbac1131121f0efd29f2e5e7bc42c79c2d577
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
run-2024-10-28T15:22:08+00:00.log
CHANGED
@@ -5374,3 +5374,7 @@ Non-default generation parameters: {'max_length': 200, 'early_stopping': True, '
|
|
5374 |
[WARNING|trainer.py:2764] 2024-10-29 00:01:14,086 >> There were missing keys in the checkpoint model loaded: ['model.encoder.embed_tokens.weight', 'model.decoder.embed_tokens.weight', 'lm_head.weight'].
|
5375 |
|
5376 |
|
5377 |
|
|
|
|
|
|
|
|
|
|
5374 |
[WARNING|trainer.py:2764] 2024-10-29 00:01:14,086 >> There were missing keys in the checkpoint model loaded: ['model.encoder.embed_tokens.weight', 'model.decoder.embed_tokens.weight', 'lm_head.weight'].
|
5375 |
|
5376 |
|
5377 |
|
5378 |
+
[WARNING|configuration_utils.py:448] 2024-10-29 00:01:47,338 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
|
5379 |
+
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
|
5380 |
+
[WARNING|configuration_utils.py:448] 2024-10-29 00:01:58,952 >> Some non-default generation parameters are set in the model config. These should go into a GenerationConfig file (https://huggingface.co/docs/transformers/generation_strategies#save-a-custom-decoding-strategy-with-your-model) instead. This warning will be raised to an exception in v4.41.
|
5381 |
+
Non-default generation parameters: {'max_length': 200, 'early_stopping': True, 'num_beams': 5, 'forced_eos_token_id': 2}
|