Commit
•
11da8ba
1
Parent(s):
e1a4f37
Training in progress epoch 0
Browse files- README.md +6 -6
- config.json +4 -1
- special_tokens_map.json +5 -1
- tf_model.h5 +2 -2
- tokenizer_config.json +11 -1
README.md
CHANGED
@@ -14,8 +14,8 @@ 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: 4.
|
19 |
- Epoch: 0
|
20 |
|
21 |
## Model description
|
@@ -42,12 +42,12 @@ The following hyperparameters were used during training:
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
-
|
|
46 |
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
-
- Transformers 4.
|
51 |
-
- TensorFlow 2.
|
52 |
-
- Datasets
|
53 |
- Tokenizers 0.11.0
|
|
|
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: 10.2613
|
18 |
+
- Validation Loss: 4.5342
|
19 |
- Epoch: 0
|
20 |
|
21 |
## Model description
|
|
|
42 |
|
43 |
| Train Loss | Validation Loss | Epoch |
|
44 |
|:----------:|:---------------:|:-----:|
|
45 |
+
| 10.2613 | 4.5342 | 0 |
|
46 |
|
47 |
|
48 |
### Framework versions
|
49 |
|
50 |
+
- Transformers 4.24.0.dev0
|
51 |
+
- TensorFlow 2.10.0
|
52 |
+
- Datasets 2.6.1
|
53 |
- Tokenizers 0.11.0
|
config.json
CHANGED
@@ -7,21 +7,24 @@
|
|
7 |
"d_kv": 64,
|
8 |
"d_model": 512,
|
9 |
"decoder_start_token_id": 0,
|
|
|
10 |
"dropout_rate": 0.1,
|
11 |
"eos_token_id": 1,
|
12 |
"feed_forward_proj": "gated-gelu",
|
13 |
"initializer_factor": 1.0,
|
14 |
"is_encoder_decoder": true,
|
|
|
15 |
"layer_norm_epsilon": 1e-06,
|
16 |
"model_type": "mt5",
|
17 |
"num_decoder_layers": 8,
|
18 |
"num_heads": 6,
|
19 |
"num_layers": 8,
|
20 |
"pad_token_id": 0,
|
|
|
21 |
"relative_attention_num_buckets": 32,
|
22 |
"tie_word_embeddings": false,
|
23 |
"tokenizer_class": "T5Tokenizer",
|
24 |
-
"transformers_version": "4.
|
25 |
"use_cache": true,
|
26 |
"vocab_size": 250112
|
27 |
}
|
|
|
7 |
"d_kv": 64,
|
8 |
"d_model": 512,
|
9 |
"decoder_start_token_id": 0,
|
10 |
+
"dense_act_fn": "gelu_new",
|
11 |
"dropout_rate": 0.1,
|
12 |
"eos_token_id": 1,
|
13 |
"feed_forward_proj": "gated-gelu",
|
14 |
"initializer_factor": 1.0,
|
15 |
"is_encoder_decoder": true,
|
16 |
+
"is_gated_act": true,
|
17 |
"layer_norm_epsilon": 1e-06,
|
18 |
"model_type": "mt5",
|
19 |
"num_decoder_layers": 8,
|
20 |
"num_heads": 6,
|
21 |
"num_layers": 8,
|
22 |
"pad_token_id": 0,
|
23 |
+
"relative_attention_max_distance": 128,
|
24 |
"relative_attention_num_buckets": 32,
|
25 |
"tie_word_embeddings": false,
|
26 |
"tokenizer_class": "T5Tokenizer",
|
27 |
+
"transformers_version": "4.24.0.dev0",
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 250112
|
30 |
}
|
special_tokens_map.json
CHANGED
@@ -1 +1,5 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>",
|
4 |
+
"unk_token": "<unk>"
|
5 |
+
}
|
tf_model.h5
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 sha256:73be4e9d8d3df22db6675a2f0bbc6738efe6f1f79533417b3739ba7caf3e9d02
|
3 |
+
size 2225556432
|
tokenizer_config.json
CHANGED
@@ -1 +1,11 @@
|
|
1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": null,
|
3 |
+
"eos_token": "</s>",
|
4 |
+
"extra_ids": 0,
|
5 |
+
"name_or_path": "google/mt5-small",
|
6 |
+
"pad_token": "<pad>",
|
7 |
+
"sp_model_kwargs": {},
|
8 |
+
"special_tokens_map_file": "/home/matt/.cache/huggingface/hub/models--google--mt5-small/snapshots/f03a52d3eaa650878b6f52e443bc4d5b385e786e/special_tokens_map.json",
|
9 |
+
"tokenizer_class": "T5Tokenizer",
|
10 |
+
"unk_token": "<unk>"
|
11 |
+
}
|