Saving weights and logs of step 2501
Browse files
config.json
CHANGED
@@ -1,10 +1,11 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
-
"
|
4 |
],
|
5 |
-
"d_ff":
|
6 |
"d_kv": 64,
|
7 |
-
"d_model":
|
8 |
"decoder_start_token_id": 0,
|
9 |
"dropout_rate": 0.1,
|
10 |
"eos_token_id": 1,
|
@@ -14,14 +15,15 @@
|
|
14 |
"is_encoder_decoder": true,
|
15 |
"layer_norm_epsilon": 1e-06,
|
16 |
"model_type": "t5",
|
17 |
-
"num_decoder_layers":
|
18 |
-
"num_heads":
|
19 |
-
"num_layers":
|
|
|
20 |
"pad_token_id": 0,
|
21 |
"relative_attention_num_buckets": 32,
|
22 |
"tie_word_embeddings": false,
|
23 |
"tokenizer_class": "T5Tokenizer",
|
24 |
"transformers_version": "4.9.0.dev0",
|
25 |
"use_cache": true,
|
26 |
-
"vocab_size":
|
27 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/home/patrick/hugging_face/t5/mt5-base",
|
3 |
"architectures": [
|
4 |
+
"T5ForConditionalGeneration"
|
5 |
],
|
6 |
+
"d_ff": 2048,
|
7 |
"d_kv": 64,
|
8 |
+
"d_model": 768,
|
9 |
"decoder_start_token_id": 0,
|
10 |
"dropout_rate": 0.1,
|
11 |
"eos_token_id": 1,
|
|
|
15 |
"is_encoder_decoder": true,
|
16 |
"layer_norm_epsilon": 1e-06,
|
17 |
"model_type": "t5",
|
18 |
+
"num_decoder_layers": 12,
|
19 |
+
"num_heads": 12,
|
20 |
+
"num_layers": 12,
|
21 |
+
"output_past": true,
|
22 |
"pad_token_id": 0,
|
23 |
"relative_attention_num_buckets": 32,
|
24 |
"tie_word_embeddings": false,
|
25 |
"tokenizer_class": "T5Tokenizer",
|
26 |
"transformers_version": "4.9.0.dev0",
|
27 |
"use_cache": true,
|
28 |
+
"vocab_size": 250100
|
29 |
}
|
events.out.tfevents.1626337452.t1v-n-e90463ba-w-0.346366.3.v2
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:daf45f7d020f0820534490777fb0f82a542b551d7a0408f99c3dec3f785e8808
|
3 |
+
size 367912
|
flax_model.msgpack
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eebcfd158857e5611833eb9b765d1fc8099c984715785481483dec6782fecdd3
|
3 |
+
size 2329543587
|