Training in progress, epoch 1
Browse files- config.json +32 -0
- model.safetensors +3 -0
- special_tokens_map.json +7 -1
- tokenizer.json +2 -2
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "google/mt5-small",
|
3 |
+
"architectures": [
|
4 |
+
"MT5ForConditionalGeneration"
|
5 |
+
],
|
6 |
+
"classifier_dropout": 0.0,
|
7 |
+
"d_ff": 1024,
|
8 |
+
"d_kv": 64,
|
9 |
+
"d_model": 512,
|
10 |
+
"decoder_start_token_id": 0,
|
11 |
+
"dense_act_fn": "gelu_new",
|
12 |
+
"dropout_rate": 0.1,
|
13 |
+
"eos_token_id": 1,
|
14 |
+
"feed_forward_proj": "gated-gelu",
|
15 |
+
"initializer_factor": 1.0,
|
16 |
+
"is_encoder_decoder": true,
|
17 |
+
"is_gated_act": true,
|
18 |
+
"layer_norm_epsilon": 1e-06,
|
19 |
+
"model_type": "mt5",
|
20 |
+
"num_decoder_layers": 8,
|
21 |
+
"num_heads": 6,
|
22 |
+
"num_layers": 8,
|
23 |
+
"pad_token_id": 0,
|
24 |
+
"relative_attention_max_distance": 128,
|
25 |
+
"relative_attention_num_buckets": 32,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"tokenizer_class": "T5Tokenizer",
|
28 |
+
"torch_dtype": "float32",
|
29 |
+
"transformers_version": "4.49.0",
|
30 |
+
"use_cache": true,
|
31 |
+
"vocab_size": 250112
|
32 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99de2f120f1b94f3956bd40970879f24926f9da1393419681743bb6061f25a9f
|
3 |
+
size 1200729512
|
special_tokens_map.json
CHANGED
@@ -6,7 +6,13 @@
|
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
"unk_token": {
|
11 |
"content": "<unk>",
|
12 |
"lstrip": false,
|
|
|
6 |
"rstrip": false,
|
7 |
"single_word": false
|
8 |
},
|
9 |
+
"pad_token": {
|
10 |
+
"content": "<pad>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
"unk_token": {
|
17 |
"content": "<unk>",
|
18 |
"lstrip": false,
|
tokenizer.json
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 sha256:600b092f7e1e7b30c00e1277ba869fdc5770bde86a6ac0e277bec0c890f855c7
|
3 |
+
size 16350183
|
tokenizer_config.json
CHANGED
@@ -833,7 +833,7 @@
|
|
833 |
"extra_special_tokens": {},
|
834 |
"legacy": true,
|
835 |
"model_max_length": 1000000000000000019884624838656,
|
836 |
-
"pad_token": "
|
837 |
"sp_model_kwargs": {},
|
838 |
"tokenizer_class": "T5Tokenizer",
|
839 |
"unk_token": "<unk>"
|
|
|
833 |
"extra_special_tokens": {},
|
834 |
"legacy": true,
|
835 |
"model_max_length": 1000000000000000019884624838656,
|
836 |
+
"pad_token": "<pad>",
|
837 |
"sp_model_kwargs": {},
|
838 |
"tokenizer_class": "T5Tokenizer",
|
839 |
"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 5496
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcec12fe5418b20cbb3fad0d3a33ecf1ee275edc8230cd0ddd25a14c4f190570
|
3 |
size 5496
|