Training in progress, epoch 9
Browse files- config.json +9 -10
- model.safetensors +2 -2
- runs/May29_17-44-30_219e479bd474/events.out.tfevents.1717004671.219e479bd474.447.1 +2 -2
- tokenizer.json +0 -0
- tokenizer_config.json +1 -1
- training_args.bin +1 -1
- vocab.txt +0 -0
config.json
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
-
"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
-
"
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
|
@@ -47,19 +47,18 @@
|
|
| 47 |
},
|
| 48 |
"layer_norm_eps": 1e-12,
|
| 49 |
"max_position_embeddings": 512,
|
| 50 |
-
"model_type": "
|
| 51 |
"num_attention_heads": 12,
|
| 52 |
"num_hidden_layers": 12,
|
| 53 |
"pad_token_id": 0,
|
| 54 |
-
"pooler_fc_size": 768,
|
| 55 |
-
"pooler_num_attention_heads": 12,
|
| 56 |
-
"pooler_num_fc_layers": 3,
|
| 57 |
-
"pooler_size_per_head": 128,
|
| 58 |
-
"pooler_type": "first_token_transform",
|
| 59 |
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
"torch_dtype": "float32",
|
| 61 |
"transformers_version": "4.41.1",
|
| 62 |
"type_vocab_size": 2,
|
| 63 |
"use_cache": true,
|
| 64 |
-
"vocab_size":
|
| 65 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "google/electra-base-discriminator",
|
| 3 |
"architectures": [
|
| 4 |
+
"ElectraForTokenClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
+
"embedding_size": 768,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
| 11 |
"hidden_size": 768,
|
|
|
|
| 47 |
},
|
| 48 |
"layer_norm_eps": 1e-12,
|
| 49 |
"max_position_embeddings": 512,
|
| 50 |
+
"model_type": "electra",
|
| 51 |
"num_attention_heads": 12,
|
| 52 |
"num_hidden_layers": 12,
|
| 53 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 54 |
"position_embedding_type": "absolute",
|
| 55 |
+
"summary_activation": "gelu",
|
| 56 |
+
"summary_last_dropout": 0.1,
|
| 57 |
+
"summary_type": "first",
|
| 58 |
+
"summary_use_proj": true,
|
| 59 |
"torch_dtype": "float32",
|
| 60 |
"transformers_version": "4.41.1",
|
| 61 |
"type_vocab_size": 2,
|
| 62 |
"use_cache": true,
|
| 63 |
+
"vocab_size": 30522
|
| 64 |
}
|
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 sha256:40c9ec49a4ef7cd43af444ade86516f5a5d29ad922a744b8aebdb678c034a526
|
| 3 |
+
size 435636652
|
runs/May29_17-44-30_219e479bd474/events.out.tfevents.1717004671.219e479bd474.447.1
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 sha256:94f2729cc8b70332b79aa185d1278525331e53d7badd1586a1aa1a4d5ea1cb73
|
| 3 |
+
size 10574
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -50,6 +50,6 @@
|
|
| 50 |
"sep_token": "[SEP]",
|
| 51 |
"strip_accents": null,
|
| 52 |
"tokenize_chinese_chars": true,
|
| 53 |
-
"tokenizer_class": "
|
| 54 |
"unk_token": "[UNK]"
|
| 55 |
}
|
|
|
|
| 50 |
"sep_token": "[SEP]",
|
| 51 |
"strip_accents": null,
|
| 52 |
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "ElectraTokenizer",
|
| 54 |
"unk_token": "[UNK]"
|
| 55 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5176
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:672c1c7f26e8dfc64ecf520924627d7a9f342f35c14072bbd18d7c4cb3368875
|
| 3 |
size 5176
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|