Training in progress, step 500
Browse files
config.json
CHANGED
@@ -2,17 +2,12 @@
|
|
2 |
"_name_or_path": "HooshvareLab/distilbert-fa-zwnj-base",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
"attention_dropout": 0.1,
|
8 |
-
"attention_probs_dropout_prob": 0.1,
|
9 |
-
"classifier_dropout": null,
|
10 |
"dim": 768,
|
11 |
"dropout": 0.1,
|
12 |
-
"hidden_act": "gelu",
|
13 |
"hidden_dim": 3072,
|
14 |
-
"hidden_dropout_prob": 0.1,
|
15 |
-
"hidden_size": 768,
|
16 |
"id2label": {
|
17 |
"0": "O",
|
18 |
"1": "B-DAT",
|
@@ -37,7 +32,6 @@
|
|
37 |
"20": "I-TIM"
|
38 |
},
|
39 |
"initializer_range": 0.02,
|
40 |
-
"intermediate_size": 3072,
|
41 |
"label2id": {
|
42 |
"B-DAT": 1,
|
43 |
"B-EVE": 3,
|
@@ -61,23 +55,17 @@
|
|
61 |
"I-TIM": 20,
|
62 |
"O": 0
|
63 |
},
|
64 |
-
"layer_norm_eps": 1e-12,
|
65 |
"max_position_embeddings": 512,
|
66 |
-
"model_type": "
|
67 |
"n_heads": 12,
|
68 |
"n_layers": 6,
|
69 |
-
"num_attention_heads": 12,
|
70 |
-
"num_hidden_layers": 12,
|
71 |
"output_past": true,
|
72 |
"pad_token_id": 0,
|
73 |
-
"position_embedding_type": "absolute",
|
74 |
"qa_dropout": 0.1,
|
75 |
"seq_classif_dropout": 0.2,
|
76 |
"sinusoidal_pos_embds": false,
|
77 |
"tie_weights_": true,
|
78 |
"torch_dtype": "float32",
|
79 |
"transformers_version": "4.21.2",
|
80 |
-
"type_vocab_size": 2,
|
81 |
-
"use_cache": true,
|
82 |
"vocab_size": 42000
|
83 |
}
|
|
|
2 |
"_name_or_path": "HooshvareLab/distilbert-fa-zwnj-base",
|
3 |
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
+
"DistilBertForTokenClassification"
|
6 |
],
|
7 |
"attention_dropout": 0.1,
|
|
|
|
|
8 |
"dim": 768,
|
9 |
"dropout": 0.1,
|
|
|
10 |
"hidden_dim": 3072,
|
|
|
|
|
11 |
"id2label": {
|
12 |
"0": "O",
|
13 |
"1": "B-DAT",
|
|
|
32 |
"20": "I-TIM"
|
33 |
},
|
34 |
"initializer_range": 0.02,
|
|
|
35 |
"label2id": {
|
36 |
"B-DAT": 1,
|
37 |
"B-EVE": 3,
|
|
|
55 |
"I-TIM": 20,
|
56 |
"O": 0
|
57 |
},
|
|
|
58 |
"max_position_embeddings": 512,
|
59 |
+
"model_type": "distilbert",
|
60 |
"n_heads": 12,
|
61 |
"n_layers": 6,
|
|
|
|
|
62 |
"output_past": true,
|
63 |
"pad_token_id": 0,
|
|
|
64 |
"qa_dropout": 0.1,
|
65 |
"seq_classif_dropout": 0.2,
|
66 |
"sinusoidal_pos_embds": false,
|
67 |
"tie_weights_": true,
|
68 |
"torch_dtype": "float32",
|
69 |
"transformers_version": "4.21.2",
|
|
|
|
|
70 |
"vocab_size": 42000
|
71 |
}
|
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 sha256:08c698b7122d80715ba4f59f06542d3fd744ef37722489c9083475d67c3e151c
|
3 |
+
size 300810165
|
runs/Sep03_01-14-34_330500caa281/1662167876.3330314/events.out.tfevents.1662167876.330500caa281.70.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5137e7da004cb45023726c417725539fe0d68d80478765b7c45aa4195f0afb1c
|
3 |
+
size 5472
|
runs/Sep03_01-14-34_330500caa281/events.out.tfevents.1662167876.330500caa281.70.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:25131c33e10214dc90e5fae01d5ae444ac6d481abde86e2b3e83afd141d3e710
|
3 |
+
size 4136
|
tokenizer.json
CHANGED
@@ -1,6 +1,11 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
|
|
|
|
|
|
|
|
|
|
4 |
"padding": null,
|
5 |
"added_tokens": [
|
6 |
{
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": {
|
4 |
+
"direction": "Right",
|
5 |
+
"max_length": 512,
|
6 |
+
"strategy": "LongestFirst",
|
7 |
+
"stride": 0
|
8 |
+
},
|
9 |
"padding": null,
|
10 |
"added_tokens": [
|
11 |
{
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3375
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ff19d2172b2b834a2fa8c121f158c3ff46938c64ed0e9917814bc4b8efe7d8e
|
3 |
size 3375
|