BayesTensor
commited on
Training in progress, epoch 1
Browse files- config.json +46 -0
- model.safetensors +3 -0
- runs/Jan11_00-20-25_9d281a23029a/events.out.tfevents.1736554827.9d281a23029a.13232.0 +3 -0
- runs/Jan11_00-21-22_9d281a23029a/events.out.tfevents.1736554884.9d281a23029a.13939.0 +3 -0
- runs/Jan11_00-22-16_9d281a23029a/events.out.tfevents.1736554937.9d281a23029a.14323.0 +3 -0
- training_args.bin +3 -0
config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "microsoft/deberta-v3-base",
|
3 |
+
"architectures": [
|
4 |
+
"DebertaV2ForSequenceClassification"
|
5 |
+
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"hidden_act": "gelu",
|
8 |
+
"hidden_dropout_prob": 0.1,
|
9 |
+
"hidden_size": 768,
|
10 |
+
"id2label": {
|
11 |
+
"0": "no",
|
12 |
+
"1": "undetermined",
|
13 |
+
"2": "yes"
|
14 |
+
},
|
15 |
+
"initializer_range": 0.02,
|
16 |
+
"intermediate_size": 3072,
|
17 |
+
"label2id": {
|
18 |
+
"no": 0,
|
19 |
+
"undetermined": 1,
|
20 |
+
"yes": 2
|
21 |
+
},
|
22 |
+
"layer_norm_eps": 1e-07,
|
23 |
+
"legacy": true,
|
24 |
+
"max_position_embeddings": 512,
|
25 |
+
"max_relative_positions": -1,
|
26 |
+
"model_type": "deberta-v2",
|
27 |
+
"norm_rel_ebd": "layer_norm",
|
28 |
+
"num_attention_heads": 12,
|
29 |
+
"num_hidden_layers": 12,
|
30 |
+
"pad_token_id": 0,
|
31 |
+
"pooler_dropout": 0,
|
32 |
+
"pooler_hidden_act": "gelu",
|
33 |
+
"pooler_hidden_size": 768,
|
34 |
+
"pos_att_type": [
|
35 |
+
"p2c",
|
36 |
+
"c2p"
|
37 |
+
],
|
38 |
+
"position_biased_input": false,
|
39 |
+
"position_buckets": 256,
|
40 |
+
"relative_attention": true,
|
41 |
+
"share_att_key": true,
|
42 |
+
"torch_dtype": "float32",
|
43 |
+
"transformers_version": "4.48.0",
|
44 |
+
"type_vocab_size": 0,
|
45 |
+
"vocab_size": 128100
|
46 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3a748c1ab33837bc3a63346bb1a609553c03ec298903d57127fbdc8ae41d7d4
|
3 |
+
size 737722356
|
runs/Jan11_00-20-25_9d281a23029a/events.out.tfevents.1736554827.9d281a23029a.13232.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb1c6c344870efdfedd1348c9f40b707b74b837624173fca14b32ddd7812f7ab
|
3 |
+
size 4184
|
runs/Jan11_00-21-22_9d281a23029a/events.out.tfevents.1736554884.9d281a23029a.13939.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:48e3661a3bd92c1eef40700dabbfb1ce03c819f3b1115d080512000a9e70416d
|
3 |
+
size 4184
|
runs/Jan11_00-22-16_9d281a23029a/events.out.tfevents.1736554937.9d281a23029a.14323.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:07bb07e6c024e1efaac2ae138dc202c533ad4edbf19d491990959973213bf755
|
3 |
+
size 5951
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a4cef7ab6f4ff209dd756db3bbb721abd11ddfea5e6d59d89d58906d87bc93f
|
3 |
+
size 5432
|