Training in progress, step 2500
Browse files
config.json
CHANGED
@@ -1,13 +1,17 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
|
|
|
|
|
|
|
|
11 |
"hidden_size": 768,
|
12 |
"id2label": {
|
13 |
"0": "LABEL_0",
|
@@ -18,6 +22,7 @@
|
|
18 |
"5": "LABEL_5"
|
19 |
},
|
20 |
"initializer_range": 0.02,
|
|
|
21 |
"intermediate_size": 3072,
|
22 |
"label2id": {
|
23 |
"LABEL_0": 0,
|
@@ -29,15 +34,17 @@
|
|
29 |
},
|
30 |
"layer_norm_eps": 1e-12,
|
31 |
"max_position_embeddings": 512,
|
32 |
-
"model_type": "
|
|
|
33 |
"num_attention_heads": 12,
|
|
|
34 |
"num_hidden_layers": 12,
|
|
|
35 |
"pad_token_id": 0,
|
36 |
"position_embedding_type": "absolute",
|
37 |
"problem_type": "single_label_classification",
|
38 |
"torch_dtype": "float32",
|
39 |
"transformers_version": "4.38.2",
|
40 |
"type_vocab_size": 2,
|
41 |
-
"
|
42 |
-
"vocab_size": 30522
|
43 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
"architectures": [
|
4 |
+
"AlbertForSequenceClassification"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
"hidden_size": 768,
|
16 |
"id2label": {
|
17 |
"0": "LABEL_0",
|
|
|
22 |
"5": "LABEL_5"
|
23 |
},
|
24 |
"initializer_range": 0.02,
|
25 |
+
"inner_group_num": 1,
|
26 |
"intermediate_size": 3072,
|
27 |
"label2id": {
|
28 |
"LABEL_0": 0,
|
|
|
34 |
},
|
35 |
"layer_norm_eps": 1e-12,
|
36 |
"max_position_embeddings": 512,
|
37 |
+
"model_type": "albert",
|
38 |
+
"net_structure_type": 0,
|
39 |
"num_attention_heads": 12,
|
40 |
+
"num_hidden_groups": 1,
|
41 |
"num_hidden_layers": 12,
|
42 |
+
"num_memory_blocks": 0,
|
43 |
"pad_token_id": 0,
|
44 |
"position_embedding_type": "absolute",
|
45 |
"problem_type": "single_label_classification",
|
46 |
"torch_dtype": "float32",
|
47 |
"transformers_version": "4.38.2",
|
48 |
"type_vocab_size": 2,
|
49 |
+
"vocab_size": 30000
|
|
|
50 |
}
|
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 sha256:99be2d9e1c53daba2ac6063be0125fd4fcd9182cb41dff875f908ac7a37c1e8b
|
3 |
+
size 46756216
|
runs/Mar11_02-54-15_ebad219a5e6d/events.out.tfevents.1710125656.ebad219a5e6d.2185.4
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:a16d6015ecc15b755937028f50999f7cda85103c0dba46f4dd02a71e41be0f55
|
3 |
+
size 6861
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4920
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7341803b24e9f8352aa2346b85e246be75ca1f3bc0be5ae2dd30dab8a232c7e
|
3 |
size 4920
|