dagrodiluksha
commited on
Commit
•
c9e11ce
1
Parent(s):
b6898cb
Training in progress, epoch 1
Browse files
config.json
CHANGED
@@ -1,33 +1,52 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
11 |
"id2label": {
|
12 |
"0": "NEGATIVE",
|
13 |
"1": "POSITIVE"
|
14 |
},
|
|
|
15 |
"initializer_range": 0.02,
|
|
|
16 |
"label2id": {
|
17 |
"NEGATIVE": 0,
|
18 |
"POSITIVE": 1
|
19 |
},
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
|
|
|
|
25 |
"problem_type": "single_label_classification",
|
26 |
-
"
|
27 |
-
"seq_classif_dropout": 0.2,
|
28 |
-
"sinusoidal_pos_embds": false,
|
29 |
-
"tie_weights_": true,
|
30 |
"torch_dtype": "float32",
|
31 |
"transformers_version": "4.44.2",
|
32 |
-
"
|
|
|
33 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "allenai/longformer-base-4096",
|
|
|
3 |
"architectures": [
|
4 |
+
"LongformerForSequenceClassification"
|
5 |
],
|
6 |
+
"attention_mode": "longformer",
|
7 |
+
"attention_probs_dropout_prob": 0.1,
|
8 |
+
"attention_window": [
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
512,
|
12 |
+
512,
|
13 |
+
512,
|
14 |
+
512,
|
15 |
+
512,
|
16 |
+
512,
|
17 |
+
512,
|
18 |
+
512,
|
19 |
+
512,
|
20 |
+
512
|
21 |
+
],
|
22 |
+
"bos_token_id": 0,
|
23 |
+
"eos_token_id": 2,
|
24 |
+
"gradient_checkpointing": false,
|
25 |
+
"hidden_act": "gelu",
|
26 |
+
"hidden_dropout_prob": 0.1,
|
27 |
+
"hidden_size": 768,
|
28 |
"id2label": {
|
29 |
"0": "NEGATIVE",
|
30 |
"1": "POSITIVE"
|
31 |
},
|
32 |
+
"ignore_attention_mask": false,
|
33 |
"initializer_range": 0.02,
|
34 |
+
"intermediate_size": 3072,
|
35 |
"label2id": {
|
36 |
"NEGATIVE": 0,
|
37 |
"POSITIVE": 1
|
38 |
},
|
39 |
+
"layer_norm_eps": 1e-05,
|
40 |
+
"max_position_embeddings": 4098,
|
41 |
+
"model_type": "longformer",
|
42 |
+
"num_attention_heads": 12,
|
43 |
+
"num_hidden_layers": 12,
|
44 |
+
"onnx_export": false,
|
45 |
+
"pad_token_id": 1,
|
46 |
"problem_type": "single_label_classification",
|
47 |
+
"sep_token_id": 2,
|
|
|
|
|
|
|
48 |
"torch_dtype": "float32",
|
49 |
"transformers_version": "4.44.2",
|
50 |
+
"type_vocab_size": 1,
|
51 |
+
"vocab_size": 50265
|
52 |
}
|
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:bdbf22eba9e43f584f4749d654eee94ce321b1a30d1f596b0f07a62c7d556b65
|
3 |
+
size 594678184
|
runs/Sep24_12-04-54_BISTECNB049/events.out.tfevents.1727159697.BISTECNB049.1040.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bf17894a4a7b6a0c06285f3ae52dd59b454103541f6ecb9be0236e3424eeffb
|
3 |
+
size 5186
|
runs/Sep24_13-18-31_BISTECNB049/events.out.tfevents.1727164115.BISTECNB049.30644.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:91b57d9f7d5ffda939955a37687764c8f9de5c5f06c7f712e1c2c8395595c686
|
3 |
+
size 5503
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 5176
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:61a94ce1268ead8118ce3c25a474e730b1a26b25885b79f78ad3fbcee9c72320
|
3 |
size 5176
|