Commit
•
57063a3
1
Parent(s):
b44770a
Training in progress, epoch 1
Browse files
config.json
CHANGED
@@ -1,12 +1,14 @@
|
|
1 |
{
|
2 |
-
"activation": "gelu",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
|
|
|
|
|
|
10 |
"id2label": {
|
11 |
"0": "sadness",
|
12 |
"1": "joy",
|
@@ -16,6 +18,9 @@
|
|
16 |
"5": "surprise"
|
17 |
},
|
18 |
"initializer_range": 0.02,
|
|
|
|
|
|
|
19 |
"label2id": {
|
20 |
"anger": 3,
|
21 |
"fear": 4,
|
@@ -24,17 +29,22 @@
|
|
24 |
"sadness": 0,
|
25 |
"surprise": 5
|
26 |
},
|
|
|
27 |
"max_length": 128,
|
28 |
"max_position_embeddings": 512,
|
29 |
-
"model_type": "
|
30 |
-
"
|
31 |
-
"
|
|
|
|
|
32 |
"pad_token_id": 0,
|
33 |
"problem_type": "single_label_classification",
|
34 |
-
"qa_dropout": 0.1,
|
35 |
-
"seq_classif_dropout": 0.2,
|
36 |
-
"sinusoidal_pos_embds": false,
|
37 |
"torch_dtype": "float32",
|
38 |
"transformers_version": "4.35.0",
|
|
|
|
|
|
|
|
|
|
|
39 |
"vocab_size": 30522
|
40 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
+
"MobileBertForSequenceClassification"
|
4 |
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_activation": true,
|
7 |
+
"classifier_dropout": null,
|
8 |
+
"embedding_size": 128,
|
9 |
+
"hidden_act": "relu",
|
10 |
+
"hidden_dropout_prob": 0.0,
|
11 |
+
"hidden_size": 512,
|
12 |
"id2label": {
|
13 |
"0": "sadness",
|
14 |
"1": "joy",
|
|
|
18 |
"5": "surprise"
|
19 |
},
|
20 |
"initializer_range": 0.02,
|
21 |
+
"intermediate_size": 512,
|
22 |
+
"intra_bottleneck_size": 128,
|
23 |
+
"key_query_shared_bottleneck": true,
|
24 |
"label2id": {
|
25 |
"anger": 3,
|
26 |
"fear": 4,
|
|
|
29 |
"sadness": 0,
|
30 |
"surprise": 5
|
31 |
},
|
32 |
+
"layer_norm_eps": 1e-12,
|
33 |
"max_length": 128,
|
34 |
"max_position_embeddings": 512,
|
35 |
+
"model_type": "mobilebert",
|
36 |
+
"normalization_type": "no_norm",
|
37 |
+
"num_attention_heads": 4,
|
38 |
+
"num_feedforward_networks": 4,
|
39 |
+
"num_hidden_layers": 24,
|
40 |
"pad_token_id": 0,
|
41 |
"problem_type": "single_label_classification",
|
|
|
|
|
|
|
42 |
"torch_dtype": "float32",
|
43 |
"transformers_version": "4.35.0",
|
44 |
+
"trigram_input": true,
|
45 |
+
"true_hidden_size": 128,
|
46 |
+
"type_vocab_size": 2,
|
47 |
+
"use_bottleneck": true,
|
48 |
+
"use_bottleneck_attention": false,
|
49 |
"vocab_size": 30522
|
50 |
}
|
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 sha256:07ed248e3e3488549af736a163f3f604df5dd273b50088da9a56eccaafe6234a
|
3 |
+
size 99529152
|
runs/Apr26_10-01-20_58a95f8b215f/events.out.tfevents.1714125681.58a95f8b215f.47.4
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4ae848e43e2eb6ee30550458f5ec64c444f095b0ae4a96501d1ca6c4b670769b
|
3 |
+
size 5255
|
tokenizer_config.json
CHANGED
@@ -45,11 +45,11 @@
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
-
"model_max_length":
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
52 |
"tokenize_chinese_chars": true,
|
53 |
-
"tokenizer_class": "
|
54 |
"unk_token": "[UNK]"
|
55 |
}
|
|
|
45 |
"cls_token": "[CLS]",
|
46 |
"do_lower_case": true,
|
47 |
"mask_token": "[MASK]",
|
48 |
+
"model_max_length": 1000000000000000019884624838656,
|
49 |
"pad_token": "[PAD]",
|
50 |
"sep_token": "[SEP]",
|
51 |
"strip_accents": null,
|
52 |
"tokenize_chinese_chars": true,
|
53 |
+
"tokenizer_class": "MobileBertTokenizer",
|
54 |
"unk_token": "[UNK]"
|
55 |
}
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4219
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e6fcef131e7aaa57e5438e3ad675f2df95f008602518b504dc9830b169f517f
|
3 |
size 4219
|