Training in progress, step 380
Browse files- config.json +17 -26
- model.safetensors +2 -2
- training_args.bin +2 -2
config.json
CHANGED
|
@@ -1,37 +1,28 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
-
"activation_dropout": 0.0,
|
| 4 |
-
"activation_function": "gelu",
|
| 5 |
"architectures": [
|
| 6 |
-
"
|
| 7 |
],
|
| 8 |
-
"
|
| 9 |
"bos_token_id": 0,
|
| 10 |
-
"classifier_dropout":
|
| 11 |
-
"d_model": 1024,
|
| 12 |
-
"decoder_attention_heads": 16,
|
| 13 |
-
"decoder_ffn_dim": 4096,
|
| 14 |
-
"decoder_layerdrop": 0.0,
|
| 15 |
-
"decoder_layers": 12,
|
| 16 |
-
"decoder_start_token_id": 2,
|
| 17 |
-
"dropout": 0.1,
|
| 18 |
-
"encoder_attention_heads": 16,
|
| 19 |
-
"encoder_ffn_dim": 4096,
|
| 20 |
-
"encoder_layerdrop": 0.0,
|
| 21 |
-
"encoder_layers": 12,
|
| 22 |
"eos_token_id": 2,
|
| 23 |
-
"
|
| 24 |
-
"
|
| 25 |
-
"
|
| 26 |
-
"
|
| 27 |
-
"
|
| 28 |
-
"
|
|
|
|
|
|
|
|
|
|
| 29 |
"num_hidden_layers": 12,
|
|
|
|
| 30 |
"pad_token_id": 1,
|
| 31 |
-
"
|
| 32 |
-
"tokenizer_class": "BartphoTokenizer",
|
| 33 |
"torch_dtype": "float32",
|
| 34 |
"transformers_version": "4.47.0",
|
|
|
|
| 35 |
"use_cache": true,
|
| 36 |
-
"vocab_size":
|
| 37 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "xlm-roberta-base",
|
|
|
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
+
"XLMRobertaForQuestionAnswering"
|
| 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 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "xlm-roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
"num_hidden_layers": 12,
|
| 20 |
+
"output_past": true,
|
| 21 |
"pad_token_id": 1,
|
| 22 |
+
"position_embedding_type": "absolute",
|
|
|
|
| 23 |
"torch_dtype": "float32",
|
| 24 |
"transformers_version": "4.47.0",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
"use_cache": true,
|
| 27 |
+
"vocab_size": 250002
|
| 28 |
}
|
model.safetensors
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:f7929ff08837832f88c88ed7a64dbc6b9d50747b2c82d7fc2b68414454ce8744
|
| 3 |
+
size 1109842416
|
training_args.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:e5ad27806d5c4073f5dbf15dfc51c64da9257c8ebc692cfaeba9ded534035870
|
| 3 |
+
size 5240
|