Training in progress, epoch 1
Browse files
config.json
CHANGED
|
@@ -1,19 +1,21 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 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":
|
| 11 |
"id2label": {
|
| 12 |
"0": "not_entailment",
|
| 13 |
"1": "entailment"
|
| 14 |
},
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
-
"intermediate_size":
|
| 17 |
"label2id": {
|
| 18 |
"entailment": "1",
|
| 19 |
"not_entailment": "0"
|
|
@@ -21,11 +23,13 @@
|
|
| 21 |
"layer_norm_eps": 1e-12,
|
| 22 |
"max_position_embeddings": 512,
|
| 23 |
"model_type": "bert",
|
| 24 |
-
"num_attention_heads":
|
| 25 |
-
"num_hidden_layers":
|
| 26 |
"pad_token_id": 0,
|
| 27 |
"position_embedding_type": "absolute",
|
|
|
|
| 28 |
"problem_type": "single_label_classification",
|
|
|
|
| 29 |
"torch_dtype": "float32",
|
| 30 |
"transformers_version": "4.20.1",
|
| 31 |
"type_vocab_size": 2,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "huawei-noah/TinyBERT_General_4L_312D",
|
| 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": 312,
|
| 13 |
"id2label": {
|
| 14 |
"0": "not_entailment",
|
| 15 |
"1": "entailment"
|
| 16 |
},
|
| 17 |
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 1200,
|
| 19 |
"label2id": {
|
| 20 |
"entailment": "1",
|
| 21 |
"not_entailment": "0"
|
|
|
|
| 23 |
"layer_norm_eps": 1e-12,
|
| 24 |
"max_position_embeddings": 512,
|
| 25 |
"model_type": "bert",
|
| 26 |
+
"num_attention_heads": 12,
|
| 27 |
+
"num_hidden_layers": 4,
|
| 28 |
"pad_token_id": 0,
|
| 29 |
"position_embedding_type": "absolute",
|
| 30 |
+
"pre_trained": "",
|
| 31 |
"problem_type": "single_label_classification",
|
| 32 |
+
"structure": [],
|
| 33 |
"torch_dtype": "float32",
|
| 34 |
"transformers_version": "4.20.1",
|
| 35 |
"type_vocab_size": 2,
|
logs/1656602941.8444355/events.out.tfevents.1656602941.88ba90b02f04.36521.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8564172619fcc99ce6f391fb01b5795a932de3762f91c5aad55009d612ef5316
|
| 3 |
+
size 5343
|
logs/events.out.tfevents.1656602941.88ba90b02f04.36521.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:833d3638bc974995a7b8472332f8fb7c0997768b9318d4b107c932a9b56ba0f2
|
| 3 |
+
size 4237
|
pytorch_model.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:e63769a9249ba8abff24c6ab06fd10b7c6f54f3bc1411794f5c1d08df412413f
|
| 3 |
+
size 57430535
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3375
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5552416892dbc85972acf192c74fa4c8fc5d8834d3c89025579a47506fce9f76
|
| 3 |
size 3375
|