Saving weights and logs of epoch 0
Browse files- config.json +7 -8
- events.out.tfevents.1667661211.t1v-n-2c92ac13-w-0.1502470.0.v2 +3 -0
- flax_model.msgpack +2 -2
- special_tokens_map.json +5 -1
- tokenizer.json +0 -0
- tokenizer_config.json +8 -5
config.json
CHANGED
@@ -1,22 +1,21 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
-
"d_ff":
|
7 |
"d_kv": 64,
|
8 |
"d_model": 768,
|
9 |
"decoder_start_token_id": 0,
|
10 |
-
"dense_act_fn": "
|
11 |
"dropout_rate": 0.1,
|
12 |
"eos_token_id": 1,
|
13 |
-
"feed_forward_proj": "
|
14 |
"initializer_factor": 1.0,
|
15 |
"is_encoder_decoder": true,
|
16 |
-
"is_gated_act":
|
17 |
"layer_norm_epsilon": 1e-06,
|
18 |
"model_type": "t5",
|
19 |
-
"n_positions": 512,
|
20 |
"num_decoder_layers": 12,
|
21 |
"num_heads": 12,
|
22 |
"num_layers": 12,
|
@@ -24,8 +23,8 @@
|
|
24 |
"pad_token_id": 0,
|
25 |
"relative_attention_max_distance": 128,
|
26 |
"relative_attention_num_buckets": 32,
|
27 |
-
"
|
28 |
"transformers_version": "4.23.1",
|
29 |
"use_cache": true,
|
30 |
-
"vocab_size":
|
31 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "nhanv/vit5-v1.1-base-vietnews-1024",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
+
"d_ff": 2048,
|
7 |
"d_kv": 64,
|
8 |
"d_model": 768,
|
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": "t5",
|
|
|
19 |
"num_decoder_layers": 12,
|
20 |
"num_heads": 12,
|
21 |
"num_layers": 12,
|
|
|
23 |
"pad_token_id": 0,
|
24 |
"relative_attention_max_distance": 128,
|
25 |
"relative_attention_num_buckets": 32,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
"transformers_version": "4.23.1",
|
28 |
"use_cache": true,
|
29 |
+
"vocab_size": 32100
|
30 |
}
|
events.out.tfevents.1667661211.t1v-n-2c92ac13-w-0.1502470.0.v2
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bf47b9076bc5048f8441ac753aff0bd0b8199050e9609af215cb0b5c4ac5ef97
|
3 |
+
size 19396
|
flax_model.msgpack
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:e49de8f274f99b5e11cfe0a2af9f7eb04eafe9d82b26bc55afbfdbe60cbad0b4
|
3 |
+
size 990151583
|
special_tokens_map.json
CHANGED
@@ -95,7 +95,11 @@
|
|
95 |
"<extra_id_92>",
|
96 |
"<extra_id_93>",
|
97 |
"<extra_id_94>",
|
98 |
-
"<extra_id_95>"
|
|
|
|
|
|
|
|
|
99 |
],
|
100 |
"eos_token": "</s>",
|
101 |
"pad_token": "<pad>",
|
|
|
95 |
"<extra_id_92>",
|
96 |
"<extra_id_93>",
|
97 |
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
],
|
104 |
"eos_token": "</s>",
|
105 |
"pad_token": "<pad>",
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
@@ -95,14 +95,17 @@
|
|
95 |
"<extra_id_92>",
|
96 |
"<extra_id_93>",
|
97 |
"<extra_id_94>",
|
98 |
-
"<extra_id_95>"
|
|
|
|
|
|
|
|
|
99 |
],
|
100 |
"eos_token": "</s>",
|
101 |
-
"extra_ids":
|
102 |
-
"name_or_path": "
|
103 |
"pad_token": "<pad>",
|
104 |
-
"
|
105 |
-
"special_tokens_map_file": "/home/dauvannha/.cache/huggingface/hub/models--VietAI--vit5-base/snapshots/2209a38d735ede63e88f5aa52bcdc11a05a37b85/special_tokens_map.json",
|
106 |
"tokenizer_class": "T5Tokenizer",
|
107 |
"unk_token": "<unk>"
|
108 |
}
|
|
|
95 |
"<extra_id_92>",
|
96 |
"<extra_id_93>",
|
97 |
"<extra_id_94>",
|
98 |
+
"<extra_id_95>",
|
99 |
+
"<extra_id_96>",
|
100 |
+
"<extra_id_97>",
|
101 |
+
"<extra_id_98>",
|
102 |
+
"<extra_id_99>"
|
103 |
],
|
104 |
"eos_token": "</s>",
|
105 |
+
"extra_ids": 100,
|
106 |
+
"name_or_path": "nhanv/vit5-v1.1-base-vietnews-1024",
|
107 |
"pad_token": "<pad>",
|
108 |
+
"special_tokens_map_file": null,
|
|
|
109 |
"tokenizer_class": "T5Tokenizer",
|
110 |
"unk_token": "<unk>"
|
111 |
}
|