t5-base-spanish-yoremnokki
Browse files- README.md +14 -13
- config.json +6 -6
- model.safetensors +2 -2
- runs/Oct04_03-28-34_6b1117a5b990/events.out.tfevents.1728012517.6b1117a5b990.298.0 +3 -0
- special_tokens_map.json +3 -21
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
license: apache-2.0
|
4 |
-
base_model: google-t5/t5-
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
metrics:
|
@@ -16,11 +16,11 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
# t5-small-spanish-yoremnokki
|
18 |
|
19 |
-
This model is a fine-tuned version of [google-t5/t5-
|
20 |
It achieves the following results on the evaluation set:
|
21 |
-
- Loss:
|
22 |
-
- Bleu:
|
23 |
-
- Gen Len:
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -39,7 +39,7 @@ More information needed
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
-
- learning_rate:
|
43 |
- train_batch_size: 16
|
44 |
- eval_batch_size: 16
|
45 |
- seed: 42
|
@@ -47,17 +47,18 @@ The following hyperparameters were used during training:
|
|
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:
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
-
| Training Loss | Epoch
|
56 |
-
|
57 |
-
|
|
58 |
-
|
|
59 |
-
|
|
60 |
-
|
|
|
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
1 |
---
|
2 |
library_name: transformers
|
3 |
license: apache-2.0
|
4 |
+
base_model: google-t5/t5-base
|
5 |
tags:
|
6 |
- generated_from_trainer
|
7 |
metrics:
|
|
|
16 |
|
17 |
# t5-small-spanish-yoremnokki
|
18 |
|
19 |
+
This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
+
- Loss: 1.8622
|
22 |
+
- Bleu: 10.7378
|
23 |
+
- Gen Len: 14.22
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
39 |
### Training hyperparameters
|
40 |
|
41 |
The following hyperparameters were used during training:
|
42 |
+
- learning_rate: 1e-05
|
43 |
- train_batch_size: 16
|
44 |
- eval_batch_size: 16
|
45 |
- seed: 42
|
|
|
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: 5
|
51 |
- mixed_precision_training: Native AMP
|
52 |
|
53 |
### Training results
|
54 |
|
55 |
+
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|
56 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|
|
57 |
+
| 3.4879 | 1.0 | 839 | 2.3617 | 0.2661 | 14.6218 |
|
58 |
+
| 2.4168 | 2.0 | 1678 | 2.0854 | 1.8065 | 14.3043 |
|
59 |
+
| 2.2109 | 3.0 | 2517 | 1.9512 | 5.2629 | 14.2827 |
|
60 |
+
| 2.1335 | 4.0 | 3356 | 1.8816 | 9.4622 | 14.23 |
|
61 |
+
| 2.0758 | 5.0 | 4195 | 1.8622 | 10.7378 | 14.22 |
|
62 |
|
63 |
|
64 |
### Framework versions
|
config.json
CHANGED
@@ -1,12 +1,12 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "google-t5/t5-
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
-
"d_ff":
|
8 |
"d_kv": 64,
|
9 |
-
"d_model":
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "relu",
|
12 |
"dropout_rate": 0.1,
|
@@ -18,9 +18,9 @@
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
-
"num_decoder_layers":
|
22 |
-
"num_heads":
|
23 |
-
"num_layers":
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "google-t5/t5-base",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 3072,
|
8 |
"d_kv": 64,
|
9 |
+
"d_model": 768,
|
10 |
"decoder_start_token_id": 0,
|
11 |
"dense_act_fn": "relu",
|
12 |
"dropout_rate": 0.1,
|
|
|
18 |
"layer_norm_epsilon": 1e-06,
|
19 |
"model_type": "t5",
|
20 |
"n_positions": 512,
|
21 |
+
"num_decoder_layers": 12,
|
22 |
+
"num_heads": 12,
|
23 |
+
"num_layers": 12,
|
24 |
"output_past": true,
|
25 |
"pad_token_id": 0,
|
26 |
"relative_attention_max_distance": 128,
|
model.safetensors
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 sha256:64f25b5668c1a82012682bd2bb466412ae03e4ef20a75ca327ef24a182db0ae9
|
3 |
+
size 891644712
|
runs/Oct04_03-28-34_6b1117a5b990/events.out.tfevents.1728012517.6b1117a5b990.298.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:96e926d1204caa71ccc8b4fe354a25c47a1e930f39c2e9a32e92cfa25e49c276
|
3 |
+
size 9821
|
special_tokens_map.json
CHANGED
@@ -101,25 +101,7 @@
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
-
"eos_token":
|
105 |
-
|
106 |
-
|
107 |
-
"normalized": false,
|
108 |
-
"rstrip": false,
|
109 |
-
"single_word": false
|
110 |
-
},
|
111 |
-
"pad_token": {
|
112 |
-
"content": "<pad>",
|
113 |
-
"lstrip": false,
|
114 |
-
"normalized": false,
|
115 |
-
"rstrip": false,
|
116 |
-
"single_word": false
|
117 |
-
},
|
118 |
-
"unk_token": {
|
119 |
-
"content": "<unk>",
|
120 |
-
"lstrip": false,
|
121 |
-
"normalized": false,
|
122 |
-
"rstrip": false,
|
123 |
-
"single_word": false
|
124 |
-
}
|
125 |
}
|
|
|
101 |
"<extra_id_98>",
|
102 |
"<extra_id_99>"
|
103 |
],
|
104 |
+
"eos_token": "</s>",
|
105 |
+
"pad_token": "<pad>",
|
106 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
107 |
}
|
tokenizer_config.json
CHANGED
@@ -930,7 +930,7 @@
|
|
930 |
"clean_up_tokenization_spaces": true,
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
933 |
-
"model_max_length":
|
934 |
"pad_token": "<pad>",
|
935 |
"tokenizer_class": "T5Tokenizer",
|
936 |
"unk_token": "<unk>"
|
|
|
930 |
"clean_up_tokenization_spaces": true,
|
931 |
"eos_token": "</s>",
|
932 |
"extra_ids": 100,
|
933 |
+
"model_max_length": 1000000000000000019884624838656,
|
934 |
"pad_token": "<pad>",
|
935 |
"tokenizer_class": "T5Tokenizer",
|
936 |
"unk_token": "<unk>"
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5368
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0bf69dc795cf26a94c7f4ba4f71d3d7c4ccc11b4e9d85f6612d5fe61a3d358ab
|
3 |
size 5368
|