Training in progress, epoch 1
Browse files- config.json +15 -17
- merges.txt +0 -0
- pytorch_model.bin +2 -2
- runs/Mar13_14-11-35_teesta/events.out.tfevents.1710319316.teesta.38365.0 +2 -2
- runs/Mar13_17-22-19_teesta/events.out.tfevents.1710330749.teesta.37879.0 +3 -0
- runs/Mar13_17-24-03_teesta/events.out.tfevents.1710330853.teesta.37346.0 +3 -0
- special_tokens_map.json +13 -5
- tokenizer.json +2 -2
- tokenizer_config.json +11 -9
- training_args.bin +1 -1
- vocab.json +0 -0
config.json
CHANGED
@@ -1,14 +1,16 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
|
|
7 |
"classifier_dropout": null,
|
8 |
-
"
|
|
|
9 |
"hidden_act": "gelu",
|
10 |
"hidden_dropout_prob": 0.1,
|
11 |
-
"hidden_size":
|
12 |
"id2label": {
|
13 |
"0": "center",
|
14 |
"1": "left",
|
@@ -16,28 +18,24 @@
|
|
16 |
"3": "roundup"
|
17 |
},
|
18 |
"initializer_range": 0.02,
|
19 |
-
"intermediate_size":
|
20 |
"label2id": {
|
21 |
"center": "0",
|
22 |
"left": "1",
|
23 |
"right": "2",
|
24 |
"roundup": "3"
|
25 |
},
|
26 |
-
"layer_norm_eps": 1e-
|
27 |
-
"max_position_embeddings":
|
28 |
-
"model_type": "
|
29 |
-
"num_attention_heads":
|
30 |
-
"num_hidden_layers":
|
31 |
-
"pad_token_id":
|
32 |
"position_embedding_type": "absolute",
|
33 |
"problem_type": "single_label_classification",
|
34 |
-
"summary_activation": "gelu",
|
35 |
-
"summary_last_dropout": 0.1,
|
36 |
-
"summary_type": "first",
|
37 |
-
"summary_use_proj": true,
|
38 |
"torch_dtype": "float32",
|
39 |
"transformers_version": "4.30.2",
|
40 |
-
"type_vocab_size":
|
41 |
"use_cache": true,
|
42 |
-
"vocab_size":
|
43 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "mrm8488/distilroberta-finetuned-financial-news-sentiment-analysis",
|
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 |
+
"gradient_checkpointing": false,
|
11 |
"hidden_act": "gelu",
|
12 |
"hidden_dropout_prob": 0.1,
|
13 |
+
"hidden_size": 768,
|
14 |
"id2label": {
|
15 |
"0": "center",
|
16 |
"1": "left",
|
|
|
18 |
"3": "roundup"
|
19 |
},
|
20 |
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 3072,
|
22 |
"label2id": {
|
23 |
"center": "0",
|
24 |
"left": "1",
|
25 |
"right": "2",
|
26 |
"roundup": "3"
|
27 |
},
|
28 |
+
"layer_norm_eps": 1e-05,
|
29 |
+
"max_position_embeddings": 514,
|
30 |
+
"model_type": "roberta",
|
31 |
+
"num_attention_heads": 12,
|
32 |
+
"num_hidden_layers": 6,
|
33 |
+
"pad_token_id": 1,
|
34 |
"position_embedding_type": "absolute",
|
35 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
|
|
36 |
"torch_dtype": "float32",
|
37 |
"transformers_version": "4.30.2",
|
38 |
+
"type_vocab_size": 1,
|
39 |
"use_cache": true,
|
40 |
+
"vocab_size": 50265
|
41 |
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
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:b03ab58a1423099bc3dd190f0bb3c9e773c06c49c6cdc5470667c2bfb470d4be
|
3 |
+
size 328526069
|
runs/Mar13_14-11-35_teesta/events.out.tfevents.1710319316.teesta.38365.0
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 sha256:9d01096efa0aa992d9dd78d4b76366101630b945187e61d06a4aa7b773748e46
|
3 |
+
size 14593
|
runs/Mar13_17-22-19_teesta/events.out.tfevents.1710330749.teesta.37879.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b56f4f47e7a50cabdfe19337c0617d9279bb158148a189b7537325cf66dc4a34
|
3 |
+
size 4806
|
runs/Mar13_17-24-03_teesta/events.out.tfevents.1710330853.teesta.37346.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c319c029c68d7ad19714390f18e8b632e625a971c274b58fdd14cb4f3043cdfd
|
3 |
+
size 4136
|
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
@@ -1,13 +1,15 @@
|
|
1 |
{
|
|
|
|
|
2 |
"clean_up_tokenization_spaces": true,
|
3 |
-
"cls_token": "
|
4 |
-
"
|
5 |
-
"
|
|
|
6 |
"model_max_length": 512,
|
7 |
-
"pad_token": "
|
8 |
-
"sep_token": "
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"unk_token": "[UNK]"
|
13 |
}
|
|
|
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 sha256:92e8f490195fb346895a624b81c42f7d14ba51ee6a9ff9b544e6c188eb7cd1a5
|
3 |
size 3963
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|