Training in progress, epoch 1
Browse files
config.json
CHANGED
|
@@ -1,15 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
| 7 |
-
"cell": {},
|
| 8 |
"classifier_dropout": null,
|
| 9 |
-
"emb_size": 312,
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
-
"hidden_size":
|
| 13 |
"id2label": {
|
| 14 |
"0": "holdings",
|
| 15 |
"1": "capital_gains",
|
|
@@ -26,7 +24,7 @@
|
|
| 26 |
"12": "None_module"
|
| 27 |
},
|
| 28 |
"initializer_range": 0.02,
|
| 29 |
-
"intermediate_size":
|
| 30 |
"label2id": {
|
| 31 |
"Current Year": 5,
|
| 32 |
"Daily": 7,
|
|
@@ -45,13 +43,11 @@
|
|
| 45 |
"layer_norm_eps": 1e-12,
|
| 46 |
"max_position_embeddings": 512,
|
| 47 |
"model_type": "bert",
|
| 48 |
-
"num_attention_heads":
|
| 49 |
"num_hidden_layers": 4,
|
| 50 |
"pad_token_id": 0,
|
| 51 |
"position_embedding_type": "absolute",
|
| 52 |
-
"pre_trained": "",
|
| 53 |
"problem_type": "multi_label_classification",
|
| 54 |
-
"structure": [],
|
| 55 |
"torch_dtype": "float32",
|
| 56 |
"transformers_version": "4.46.2",
|
| 57 |
"type_vocab_size": 2,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "gaunernst/bert-mini-uncased",
|
| 3 |
"architectures": [
|
| 4 |
"BertForSequenceClassification"
|
| 5 |
],
|
| 6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
|
| 7 |
"classifier_dropout": null,
|
|
|
|
| 8 |
"hidden_act": "gelu",
|
| 9 |
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 256,
|
| 11 |
"id2label": {
|
| 12 |
"0": "holdings",
|
| 13 |
"1": "capital_gains",
|
|
|
|
| 24 |
"12": "None_module"
|
| 25 |
},
|
| 26 |
"initializer_range": 0.02,
|
| 27 |
+
"intermediate_size": 1024,
|
| 28 |
"label2id": {
|
| 29 |
"Current Year": 5,
|
| 30 |
"Daily": 7,
|
|
|
|
| 43 |
"layer_norm_eps": 1e-12,
|
| 44 |
"max_position_embeddings": 512,
|
| 45 |
"model_type": "bert",
|
| 46 |
+
"num_attention_heads": 4,
|
| 47 |
"num_hidden_layers": 4,
|
| 48 |
"pad_token_id": 0,
|
| 49 |
"position_embedding_type": "absolute",
|
|
|
|
| 50 |
"problem_type": "multi_label_classification",
|
|
|
|
| 51 |
"torch_dtype": "float32",
|
| 52 |
"transformers_version": "4.46.2",
|
| 53 |
"type_vocab_size": 2,
|
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 sha256:9c04956a47e86cf0b8b9349cdb1c524ae19e3aea7e262c0c762ea2f1996f4595
|
| 3 |
+
size 44703916
|
runs/Nov07_08-28-00_6433661c917b/events.out.tfevents.1730968105.6433661c917b.2405.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0a87bf2d135148fe1ba4f210a549281729f2686536f0b5bd0deb2106c8d10b0
|
| 3 |
+
size 6394
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5304
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98e0ce5d81378faa54fe5934a832f5d49ab6d1f4118d9be8c096908833cd893c
|
| 3 |
size 5304
|