Training in progress, epoch 1
Browse files- config.json +16 -15
- logs/events.out.tfevents.1715759447.spartan-gpgpu093.hpc.unimelb.edu.au +3 -0
- model.safetensors +2 -2
- tokenizer.json +6 -1
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,31 +1,32 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "distilbert-base-uncased",
|
3 |
-
"activation": "gelu",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
|
|
|
|
11 |
"id2label": {
|
12 |
"0": "LABEL_0"
|
13 |
},
|
14 |
"initializer_range": 0.02,
|
|
|
15 |
"label2id": {
|
16 |
"LABEL_0": 0
|
17 |
},
|
|
|
18 |
"max_position_embeddings": 512,
|
19 |
-
"model_type": "
|
20 |
-
"
|
21 |
-
"
|
22 |
"pad_token_id": 0,
|
|
|
23 |
"problem_type": "regression",
|
24 |
-
"qa_dropout": 0.1,
|
25 |
-
"seq_classif_dropout": 0.2,
|
26 |
-
"sinusoidal_pos_embds": false,
|
27 |
-
"tie_weights_": true,
|
28 |
"torch_dtype": "float32",
|
29 |
-
"transformers_version": "4.
|
|
|
|
|
30 |
"vocab_size": 30522
|
31 |
}
|
|
|
1 |
{
|
|
|
|
|
2 |
"architectures": [
|
3 |
+
"BertForSequenceClassification"
|
4 |
],
|
5 |
+
"attention_probs_dropout_prob": 0.1,
|
6 |
+
"classifier_dropout": null,
|
7 |
+
"gradient_checkpointing": false,
|
8 |
+
"hidden_act": "gelu",
|
9 |
+
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 512,
|
11 |
"id2label": {
|
12 |
"0": "LABEL_0"
|
13 |
},
|
14 |
"initializer_range": 0.02,
|
15 |
+
"intermediate_size": 3072,
|
16 |
"label2id": {
|
17 |
"LABEL_0": 0
|
18 |
},
|
19 |
+
"layer_norm_eps": 1e-12,
|
20 |
"max_position_embeddings": 512,
|
21 |
+
"model_type": "bert",
|
22 |
+
"num_attention_heads": 8,
|
23 |
+
"num_hidden_layers": 8,
|
24 |
"pad_token_id": 0,
|
25 |
+
"position_embedding_type": "absolute",
|
26 |
"problem_type": "regression",
|
|
|
|
|
|
|
|
|
27 |
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.39.0",
|
29 |
+
"type_vocab_size": 2,
|
30 |
+
"use_cache": true,
|
31 |
"vocab_size": 30522
|
32 |
}
|
logs/events.out.tfevents.1715759447.spartan-gpgpu093.hpc.unimelb.edu.au
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a0dbeaa461c33057215f1e1ce3ccc23cef35475686abce4add8abd94dbfc5999
|
3 |
+
size 5138
|
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 sha256:1d8f98e1f70337b57674080b4a54bb7f8885002db4750b07d30347cc11c8c8db
|
3 |
+
size 199097892
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4a3adc92e35ac6fe8366358cca44d9d096ebff8968ce23ed37bc9b904879fad
|
3 |
+
size 4984
|