Training in progress, epoch 1
Browse files
config.json
CHANGED
|
@@ -1,21 +1,19 @@
|
|
| 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": "entailment",
|
| 15 |
"1": "not_entailment"
|
| 16 |
},
|
| 17 |
"initializer_range": 0.02,
|
| 18 |
-
"intermediate_size":
|
| 19 |
"label2id": {
|
| 20 |
"entailment": "0",
|
| 21 |
"not_entailment": "1"
|
|
@@ -23,13 +21,11 @@
|
|
| 23 |
"layer_norm_eps": 1e-12,
|
| 24 |
"max_position_embeddings": 512,
|
| 25 |
"model_type": "bert",
|
| 26 |
-
"num_attention_heads":
|
| 27 |
-
"num_hidden_layers":
|
| 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,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
|
| 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": 128,
|
| 11 |
"id2label": {
|
| 12 |
"0": "entailment",
|
| 13 |
"1": "not_entailment"
|
| 14 |
},
|
| 15 |
"initializer_range": 0.02,
|
| 16 |
+
"intermediate_size": 512,
|
| 17 |
"label2id": {
|
| 18 |
"entailment": "0",
|
| 19 |
"not_entailment": "1"
|
|
|
|
| 21 |
"layer_norm_eps": 1e-12,
|
| 22 |
"max_position_embeddings": 512,
|
| 23 |
"model_type": "bert",
|
| 24 |
+
"num_attention_heads": 2,
|
| 25 |
+
"num_hidden_layers": 2,
|
| 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,
|
logs/1657033504.45278/events.out.tfevents.1657033504.3e31b05f9f01.82.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:295c9bd3566479f23aa599577ad4f114a6567e25248d18d36ab4068ff25af7c9
|
| 3 |
+
size 5347
|
logs/events.out.tfevents.1657033504.3e31b05f9f01.82.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b86ee81a49e3aa7183f310a072863db2855b8ea550519676e7322b3dcf1fd57
|
| 3 |
+
size 4170
|
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 sha256:73b9febeddcd149250a19fd4cf601d8278ea8e673e03dca5c8730baf265088ff
|
| 3 |
+
size 17561831
|
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 sha256:4133bee11eb1fbcc7dd17cd762065dd1c2a31a8c83ab02dcbef4f2ecc12fa2f3
|
| 3 |
size 3375
|