Commit
·
a7cb93e
1
Parent(s):
be21fad
Training in progress, step 500
Browse files- config.json +20 -38
- pytorch_model.bin +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,46 +1,28 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"_num_labels": 1,
|
4 |
-
"activation_function": "gelu_new",
|
5 |
"architectures": [
|
6 |
-
"
|
7 |
],
|
8 |
-
"
|
9 |
-
"bos_token_id":
|
10 |
-
"
|
11 |
-
"eos_token_id":
|
12 |
-
"
|
13 |
-
|
14 |
-
|
15 |
"initializer_range": 0.02,
|
16 |
-
"
|
17 |
-
|
18 |
-
|
19 |
-
"
|
20 |
-
"model_type": "
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
-
"n_layer": 6,
|
26 |
-
"n_positions": 1024,
|
27 |
-
"reorder_and_upcast_attn": false,
|
28 |
-
"resid_pdrop": 0.1,
|
29 |
-
"scale_attn_by_inverse_layer_idx": false,
|
30 |
-
"scale_attn_weights": true,
|
31 |
-
"summary_activation": null,
|
32 |
-
"summary_first_dropout": 0.1,
|
33 |
-
"summary_proj_to_labels": true,
|
34 |
-
"summary_type": "cls_index",
|
35 |
-
"summary_use_proj": true,
|
36 |
-
"task_specific_params": {
|
37 |
-
"text-generation": {
|
38 |
-
"do_sample": true,
|
39 |
-
"max_length": 50
|
40 |
-
}
|
41 |
-
},
|
42 |
"torch_dtype": "float32",
|
43 |
"transformers_version": "4.31.0",
|
|
|
44 |
"use_cache": true,
|
45 |
-
"vocab_size":
|
46 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "roberta-base",
|
|
|
|
|
3 |
"architectures": [
|
4 |
+
"RobertaForCausalLM"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"is_decoder": true,
|
16 |
+
"layer_norm_eps": 1e-05,
|
17 |
+
"max_position_embeddings": 514,
|
18 |
+
"model_type": "roberta",
|
19 |
+
"num_attention_heads": 12,
|
20 |
+
"num_hidden_layers": 12,
|
21 |
+
"pad_token_id": 1,
|
22 |
+
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"torch_dtype": "float32",
|
24 |
"transformers_version": "4.31.0",
|
25 |
+
"type_vocab_size": 1,
|
26 |
"use_cache": true,
|
27 |
+
"vocab_size": 50265
|
28 |
}
|
pytorch_model.bin
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:c62f40fc03b05d5b5dfa7375d10d8ea97e2e7a912ccda2e999c80b7e9dee2104
|
3 |
+
size 520105733
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3963
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a122654c2c0655749d839619cb69919159ce3b15fd289169efb9eaa97cf78c5f
|
3 |
size 3963
|