Training in progress epoch 0
Browse files- README.md +5 -12
- config.json +1 -1
- generation_config.json +1 -1
- tf_model.h5 +1 -1
- tokenizer_config.json +1 -1
README.md
CHANGED
@@ -14,9 +14,9 @@ probably proofread and complete it, then remove this comment. -->
|
|
14 |
|
15 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
-
- Train Loss:
|
18 |
-
- Validation Loss: 3.
|
19 |
-
- Epoch:
|
20 |
|
21 |
## Model description
|
22 |
|
@@ -42,19 +42,12 @@ The following hyperparameters were used during training:
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
-
|
|
46 |
-
| 3.5390 | 3.2203 | 1 |
|
47 |
-
| 3.5489 | 3.2203 | 2 |
|
48 |
-
| 3.5476 | 3.2203 | 3 |
|
49 |
-
| 3.5542 | 3.2203 | 4 |
|
50 |
-
| 3.5526 | 3.2203 | 5 |
|
51 |
-
| 3.5545 | 3.2203 | 6 |
|
52 |
-
| 3.5481 | 3.2203 | 7 |
|
53 |
|
54 |
|
55 |
### Framework versions
|
56 |
|
57 |
-
- Transformers 4.
|
58 |
- TensorFlow 2.12.0
|
59 |
- Datasets 2.11.0
|
60 |
- Tokenizers 0.13.2
|
|
|
14 |
|
15 |
This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
|
16 |
It achieves the following results on the evaluation set:
|
17 |
+
- Train Loss: 7.9634
|
18 |
+
- Validation Loss: 3.7626
|
19 |
+
- Epoch: 0
|
20 |
|
21 |
## Model description
|
22 |
|
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
+
| 7.9634 | 3.7626 | 0 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
+
- Transformers 4.28.0
|
51 |
- TensorFlow 2.12.0
|
52 |
- Datasets 2.11.0
|
53 |
- Tokenizers 0.13.2
|
config.json
CHANGED
@@ -24,7 +24,7 @@
|
|
24 |
"relative_attention_num_buckets": 32,
|
25 |
"tie_word_embeddings": false,
|
26 |
"tokenizer_class": "T5Tokenizer",
|
27 |
-
"transformers_version": "4.
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 250112
|
30 |
}
|
|
|
24 |
"relative_attention_num_buckets": 32,
|
25 |
"tie_word_embeddings": false,
|
26 |
"tokenizer_class": "T5Tokenizer",
|
27 |
+
"transformers_version": "4.28.0",
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 250112
|
30 |
}
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
-
"transformers_version": "4.
|
7 |
}
|
|
|
3 |
"decoder_start_token_id": 0,
|
4 |
"eos_token_id": 1,
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.28.0"
|
7 |
}
|
tf_model.h5
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2225556280
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b64bb48d0de0a5079b8b126d1e057517cf129cfa14f3d9796f2c085692a5f358
|
3 |
size 2225556280
|
tokenizer_config.json
CHANGED
@@ -1,11 +1,11 @@
|
|
1 |
{
|
2 |
"additional_special_tokens": null,
|
|
|
3 |
"eos_token": "</s>",
|
4 |
"extra_ids": 0,
|
5 |
"model_max_length": 1000000000000000019884624838656,
|
6 |
"pad_token": "<pad>",
|
7 |
"sp_model_kwargs": {},
|
8 |
-
"special_tokens_map_file": "/home/pio/.cache/huggingface/hub/models--google--mt5-small/snapshots/38f23af8ec210eb6c376d40e9c56bd25a80f195d/special_tokens_map.json",
|
9 |
"tokenizer_class": "T5Tokenizer",
|
10 |
"unk_token": "<unk>"
|
11 |
}
|
|
|
1 |
{
|
2 |
"additional_special_tokens": null,
|
3 |
+
"clean_up_tokenization_spaces": true,
|
4 |
"eos_token": "</s>",
|
5 |
"extra_ids": 0,
|
6 |
"model_max_length": 1000000000000000019884624838656,
|
7 |
"pad_token": "<pad>",
|
8 |
"sp_model_kwargs": {},
|
|
|
9 |
"tokenizer_class": "T5Tokenizer",
|
10 |
"unk_token": "<unk>"
|
11 |
}
|