Commit
•
6c7aa1f
1
Parent(s):
345dabc
Training in progress, epoch 1
Browse files- config.json +8 -2
- model.safetensors +2 -2
- runs/May01_05-47-15_cb68db7316ff/events.out.tfevents.1714542448.cb68db7316ff.1865.5 +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +3 -1
- training_args.bin +1 -1
- vocab.txt +0 -0
config.json
CHANGED
|
@@ -1,10 +1,11 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "bert-base-
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
|
|
|
| 8 |
"gradient_checkpointing": false,
|
| 9 |
"hidden_act": "gelu",
|
| 10 |
"hidden_dropout_prob": 0.1,
|
|
@@ -25,11 +26,16 @@
|
|
| 25 |
"num_attention_heads": 12,
|
| 26 |
"num_hidden_layers": 12,
|
| 27 |
"pad_token_id": 0,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
"position_embedding_type": "absolute",
|
| 29 |
"problem_type": "single_label_classification",
|
| 30 |
"torch_dtype": "float32",
|
| 31 |
"transformers_version": "4.40.1",
|
| 32 |
"type_vocab_size": 2,
|
| 33 |
"use_cache": true,
|
| 34 |
-
"vocab_size":
|
| 35 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Davlan/bert-base-multilingual-cased-finetuned-hausa",
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
"classifier_dropout": null,
|
| 8 |
+
"directionality": "bidi",
|
| 9 |
"gradient_checkpointing": false,
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
|
|
|
| 26 |
"num_attention_heads": 12,
|
| 27 |
"num_hidden_layers": 12,
|
| 28 |
"pad_token_id": 0,
|
| 29 |
+
"pooler_fc_size": 768,
|
| 30 |
+
"pooler_num_attention_heads": 12,
|
| 31 |
+
"pooler_num_fc_layers": 3,
|
| 32 |
+
"pooler_size_per_head": 128,
|
| 33 |
+
"pooler_type": "first_token_transform",
|
| 34 |
"position_embedding_type": "absolute",
|
| 35 |
"problem_type": "single_label_classification",
|
| 36 |
"torch_dtype": "float32",
|
| 37 |
"transformers_version": "4.40.1",
|
| 38 |
"type_vocab_size": 2,
|
| 39 |
"use_cache": true,
|
| 40 |
+
"vocab_size": 119547
|
| 41 |
}
|
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 sha256:8dc831d1a89659a9757ec6dd98d92c556998450f218408e50fa4b389835ff3af
|
| 3 |
+
size 711443456
|
runs/May01_05-47-15_cb68db7316ff/events.out.tfevents.1714542448.cb68db7316ff.1865.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:642c993b498ae3f3df5a14e4aa4e528d73aff95b7adeb14a67273815630f2e84
|
| 3 |
+
size 4184
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -43,9 +43,11 @@
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
-
"
|
|
|
|
| 47 |
"mask_token": "[MASK]",
|
| 48 |
"model_max_length": 512,
|
|
|
|
| 49 |
"pad_token": "[PAD]",
|
| 50 |
"sep_token": "[SEP]",
|
| 51 |
"strip_accents": null,
|
|
|
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
+
"do_basic_tokenize": true,
|
| 47 |
+
"do_lower_case": false,
|
| 48 |
"mask_token": "[MASK]",
|
| 49 |
"model_max_length": 512,
|
| 50 |
+
"never_split": null,
|
| 51 |
"pad_token": "[PAD]",
|
| 52 |
"sep_token": "[SEP]",
|
| 53 |
"strip_accents": null,
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5048
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d47c2e41b81573cf04a816cf196222cf4b544c9c0602755c4bbbb79ffe2158a2
|
| 3 |
size 5048
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|