Training in progress, step 500
Browse files- config.json +13 -10
- model.safetensors +2 -2
- runs/Oct30_15-05-05_1c87d08eaa77/events.out.tfevents.1761836707.1c87d08eaa77.12744.0 +2 -2
- runs/Oct30_15-05-05_1c87d08eaa77/events.out.tfevents.1761837714.1c87d08eaa77.12744.1 +3 -0
- runs/Oct30_15-31-56_1c87d08eaa77/events.out.tfevents.1761838317.1c87d08eaa77.12744.2 +3 -0
- training_args.bin +1 -1
config.json
CHANGED
|
@@ -1,27 +1,30 @@
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
-
"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
| 6 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"classifier_dropout": null,
|
| 8 |
"dtype": "float32",
|
| 9 |
-
"emb_size": 312,
|
| 10 |
"hidden_act": "gelu",
|
| 11 |
"hidden_dropout_prob": 0.1,
|
| 12 |
-
"hidden_size":
|
| 13 |
"initializer_range": 0.02,
|
| 14 |
-
"intermediate_size":
|
| 15 |
"layer_norm_eps": 1e-12,
|
| 16 |
"max_position_embeddings": 512,
|
| 17 |
-
"model_type": "
|
| 18 |
-
"num_attention_heads":
|
| 19 |
-
"num_hidden_layers":
|
| 20 |
"pad_token_id": 0,
|
| 21 |
"position_embedding_type": "absolute",
|
| 22 |
-
"pre_trained": "",
|
| 23 |
"problem_type": "single_label_classification",
|
| 24 |
-
"
|
| 25 |
"transformers_version": "4.57.1",
|
| 26 |
"type_vocab_size": 2,
|
| 27 |
"use_cache": true,
|
|
|
|
| 1 |
{
|
| 2 |
"architectures": [
|
| 3 |
+
"BertHashForSequenceClassification"
|
| 4 |
],
|
| 5 |
"attention_probs_dropout_prob": 0.1,
|
| 6 |
+
"auto_map": {
|
| 7 |
+
"AutoConfig": "configuration_bert_hash.BertHashConfig",
|
| 8 |
+
"AutoModel": "modeling_bert_hash.BertHashModel",
|
| 9 |
+
"AutoModelForMaskedLM": "modeling_bert_hash.BertHashForMaskedLM",
|
| 10 |
+
"AutoModelForSequenceClassification": "modeling_bert_hash.BertHashForSequenceClassification"
|
| 11 |
+
},
|
| 12 |
"classifier_dropout": null,
|
| 13 |
"dtype": "float32",
|
|
|
|
| 14 |
"hidden_act": "gelu",
|
| 15 |
"hidden_dropout_prob": 0.1,
|
| 16 |
+
"hidden_size": 128,
|
| 17 |
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 512,
|
| 19 |
"layer_norm_eps": 1e-12,
|
| 20 |
"max_position_embeddings": 512,
|
| 21 |
+
"model_type": "bert_hash",
|
| 22 |
+
"num_attention_heads": 2,
|
| 23 |
+
"num_hidden_layers": 2,
|
| 24 |
"pad_token_id": 0,
|
| 25 |
"position_embedding_type": "absolute",
|
|
|
|
| 26 |
"problem_type": "single_label_classification",
|
| 27 |
+
"projections": 16,
|
| 28 |
"transformers_version": "4.57.1",
|
| 29 |
"type_vocab_size": 2,
|
| 30 |
"use_cache": true,
|
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 sha256:7b659715adb4fedd682a28e2471ec8428c19cb1da4645a35b425db3ffdca4685
|
| 3 |
+
size 3884328
|
runs/Oct30_15-05-05_1c87d08eaa77/events.out.tfevents.1761836707.1c87d08eaa77.12744.0
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 sha256:5fea5a883220a4fa5ea51041ca920a52ad781e3c8893db2d668c33ee0be4a053
|
| 3 |
+
size 16946
|
runs/Oct30_15-05-05_1c87d08eaa77/events.out.tfevents.1761837714.1c87d08eaa77.12744.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bed31a3da029568e5f0c8022461c7ece8a15ecd5c916bba2b31e7cbb17ce5af0
|
| 3 |
+
size 746
|
runs/Oct30_15-31-56_1c87d08eaa77/events.out.tfevents.1761838317.1c87d08eaa77.12744.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d86769006f2f4d2b7227728abe1ea8786eceb0dd952fb6e03a78de3ceb46429
|
| 3 |
+
size 5492
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 5841
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce87105d69a78a3e8703d40cc3c476d66477c4472a7e485e02dcb7d6e743cfe2
|
| 3 |
size 5841
|