Training in progress, epoch 1
Browse files- config.json +24 -27
- pytorch_model.bin +2 -2
- runs/Mar13_18-15-07_teesta/events.out.tfevents.1710333917.teesta.29250.0 +2 -2
- runs/Mar13_18-15-07_teesta/events.out.tfevents.1710335295.teesta.29250.1 +3 -0
- runs/Mar14_10-35-48_teesta/events.out.tfevents.1710392759.teesta.11955.0 +3 -0
- special_tokens_map.json +13 -5
- tokenizer.json +2 -2
- tokenizer_config.json +11 -11
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,39 +1,36 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
-
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
|
|
|
|
12 |
"id2label": {
|
13 |
-
"0": "
|
14 |
-
"1": "
|
15 |
-
"2": "right",
|
16 |
-
"3": "roundup"
|
17 |
},
|
18 |
"initializer_range": 0.02,
|
|
|
19 |
"label2id": {
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"right": "2",
|
23 |
-
"roundup": "3"
|
24 |
},
|
25 |
-
"
|
26 |
-
"
|
27 |
-
"
|
28 |
-
"
|
29 |
-
"
|
30 |
-
"pad_token_id":
|
|
|
31 |
"problem_type": "single_label_classification",
|
32 |
-
"qa_dropout": 0.1,
|
33 |
-
"seq_classif_dropout": 0.2,
|
34 |
-
"sinusoidal_pos_embds": false,
|
35 |
-
"tie_weights_": true,
|
36 |
"torch_dtype": "float32",
|
37 |
"transformers_version": "4.30.2",
|
38 |
-
"
|
|
|
|
|
39 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "FacebookAI/roberta-base",
|
|
|
3 |
"architectures": [
|
4 |
+
"RobertaForSequenceClassification"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0.1,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"classifier_dropout": null,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_dropout_prob": 0.1,
|
12 |
+
"hidden_size": 768,
|
13 |
"id2label": {
|
14 |
+
"0": "left",
|
15 |
+
"1": "right"
|
|
|
|
|
16 |
},
|
17 |
"initializer_range": 0.02,
|
18 |
+
"intermediate_size": 3072,
|
19 |
"label2id": {
|
20 |
+
"left": "0",
|
21 |
+
"right": "1"
|
|
|
|
|
22 |
},
|
23 |
+
"layer_norm_eps": 1e-05,
|
24 |
+
"max_position_embeddings": 514,
|
25 |
+
"model_type": "roberta",
|
26 |
+
"num_attention_heads": 12,
|
27 |
+
"num_hidden_layers": 12,
|
28 |
+
"pad_token_id": 1,
|
29 |
+
"position_embedding_type": "absolute",
|
30 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
31 |
"torch_dtype": "float32",
|
32 |
"transformers_version": "4.30.2",
|
33 |
+
"type_vocab_size": 1,
|
34 |
+
"use_cache": true,
|
35 |
+
"vocab_size": 50265
|
36 |
}
|
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:fc78a62e21b5c394c71b72a3289cf3a2095b280ca34b45f4bfa00b8f43ad564e
|
3 |
+
size 498662069
|
runs/Mar13_18-15-07_teesta/events.out.tfevents.1710333917.teesta.29250.0
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 sha256:557613949f79518e015b302e78607a570dc9732eafdd17e68a049233ce46abd8
|
3 |
+
size 10154
|
runs/Mar13_18-15-07_teesta/events.out.tfevents.1710335295.teesta.29250.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d5f5c054794c63c4779a5cdc6b40673003309135680dc6304e554e083aef562
|
3 |
+
size 512
|
runs/Mar14_10-35-48_teesta/events.out.tfevents.1710392759.teesta.11955.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b0d89ab43d15b06629c53fcae34fad4ded045bccddd4a38a46f862be4b77350f
|
3 |
+
size 4561
|
special_tokens_map.json
CHANGED
@@ -1,7 +1,15 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"
|
4 |
-
"
|
5 |
-
"
|
6 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
7 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<s>",
|
3 |
+
"cls_token": "<s>",
|
4 |
+
"eos_token": "</s>",
|
5 |
+
"mask_token": {
|
6 |
+
"content": "<mask>",
|
7 |
+
"lstrip": true,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false
|
11 |
+
},
|
12 |
+
"pad_token": "<pad>",
|
13 |
+
"sep_token": "</s>",
|
14 |
+
"unk_token": "<unk>"
|
15 |
}
|
tokenizer.json
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 sha256:9998497c20af9c1781238365d53dcfd56a2793fa480957aafb0ecd51ff4839be
|
3 |
+
size 2108700
|
tokenizer_config.json
CHANGED
@@ -1,15 +1,15 @@
|
|
1 |
{
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
-
"cls_token": "
|
4 |
-
"
|
5 |
-
"
|
6 |
-
"mask_token": "
|
7 |
"model_max_length": 512,
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
13 |
-
"tokenizer_class": "DistilBertTokenizer",
|
14 |
-
"unk_token": "[UNK]"
|
15 |
}
|
|
|
1 |
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<s>",
|
4 |
"clean_up_tokenization_spaces": true,
|
5 |
+
"cls_token": "<s>",
|
6 |
+
"eos_token": "</s>",
|
7 |
+
"errors": "replace",
|
8 |
+
"mask_token": "<mask>",
|
9 |
"model_max_length": 512,
|
10 |
+
"pad_token": "<pad>",
|
11 |
+
"sep_token": "</s>",
|
12 |
+
"tokenizer_class": "RobertaTokenizer",
|
13 |
+
"trim_offsets": true,
|
14 |
+
"unk_token": "<unk>"
|
|
|
|
|
15 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3963
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ceb5e470702c5777118adb25a4a9b898b9d570b47fa64e75710f88268efe3ea7
|
3 |
size 3963
|