Training in progress, step 500
Browse files
config.json
CHANGED
|
@@ -1,24 +1,26 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "
|
| 3 |
-
"activation": "gelu",
|
| 4 |
"architectures": [
|
| 5 |
-
"
|
| 6 |
],
|
| 7 |
-
"
|
| 8 |
-
"
|
| 9 |
-
"
|
| 10 |
-
"
|
|
|
|
|
|
|
| 11 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
| 12 |
"max_position_embeddings": 512,
|
| 13 |
-
"model_type": "
|
| 14 |
-
"
|
| 15 |
-
"
|
| 16 |
"pad_token_id": 0,
|
| 17 |
-
"
|
| 18 |
-
"seq_classif_dropout": 0.2,
|
| 19 |
-
"sinusoidal_pos_embds": false,
|
| 20 |
-
"tie_weights_": true,
|
| 21 |
"torch_dtype": "float32",
|
| 22 |
"transformers_version": "4.17.0",
|
|
|
|
|
|
|
| 23 |
"vocab_size": 30522
|
| 24 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "bert-base-uncased",
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
+
"BertForMaskedLM"
|
| 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,
|
| 11 |
+
"hidden_size": 512,
|
| 12 |
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 2048,
|
| 14 |
+
"layer_norm_eps": 1e-12,
|
| 15 |
"max_position_embeddings": 512,
|
| 16 |
+
"model_type": "bert",
|
| 17 |
+
"num_attention_heads": 8,
|
| 18 |
+
"num_hidden_layers": 12,
|
| 19 |
"pad_token_id": 0,
|
| 20 |
+
"position_embedding_type": "absolute",
|
|
|
|
|
|
|
|
|
|
| 21 |
"torch_dtype": "float32",
|
| 22 |
"transformers_version": "4.17.0",
|
| 23 |
+
"type_vocab_size": 2,
|
| 24 |
+
"use_cache": true,
|
| 25 |
"vocab_size": 30522
|
| 26 |
}
|
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 sha256:86086f55e1fef2a19097cc135b100e1771b00abb39d72ca0c156f1a5925b062a
|
| 3 |
+
size 216142827
|
runs/Mar24_00-12-44_b5dfe0604ac8/1648080861.7717943/events.out.tfevents.1648080861.b5dfe0604ac8.71.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5da00f593ad343f025112fbf4bc18a1c02d26a79e87031bb6315a689f0856b63
|
| 3 |
+
size 4758
|
runs/Mar24_00-12-44_b5dfe0604ac8/events.out.tfevents.1648080861.b5dfe0604ac8.71.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:720914800a33ac9f322127aaf8496787ba02346b7da42b5b5d6d3bb4b6336c20
|
| 3 |
+
size 3452
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 3055
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e5e43409ccbbf310cc2aaa5fedd56be0caf9d0f3a868ec4b8cc04dc42652dc9
|
| 3 |
size 3055
|