Training in progress, epoch 1
Browse files- config.json +5 -5
- logs/events.out.tfevents.1715836386.spartan-gpgpu093.hpc.unimelb.edu.au +2 -2
- logs/events.out.tfevents.1715837284.spartan-gpgpu093.hpc.unimelb.edu.au +3 -0
- logs/events.out.tfevents.1724059259.spartan-gpgpu095.hpc.unimelb.edu.au.131842.5 +3 -0
- model.safetensors +2 -2
- training_args.bin +1 -1
config.json
CHANGED
@@ -1,20 +1,20 @@
|
|
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":
|
11 |
"initializer_range": 0.02,
|
12 |
-
"intermediate_size":
|
13 |
"layer_norm_eps": 1e-12,
|
14 |
"max_position_embeddings": 512,
|
15 |
"model_type": "bert",
|
16 |
-
"num_attention_heads":
|
17 |
-
"num_hidden_layers":
|
18 |
"pad_token_id": 0,
|
19 |
"position_embedding_type": "absolute",
|
20 |
"problem_type": "single_label_classification",
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/data/projects/punim0478/sayantand/Checkpoints/BERT/minilm/12_384",
|
3 |
"architectures": [
|
4 |
"BertForSequenceClassification"
|
5 |
],
|
6 |
"attention_probs_dropout_prob": 0.1,
|
7 |
"classifier_dropout": null,
|
|
|
8 |
"hidden_act": "gelu",
|
9 |
"hidden_dropout_prob": 0.1,
|
10 |
+
"hidden_size": 384,
|
11 |
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 1536,
|
13 |
"layer_norm_eps": 1e-12,
|
14 |
"max_position_embeddings": 512,
|
15 |
"model_type": "bert",
|
16 |
+
"num_attention_heads": 12,
|
17 |
+
"num_hidden_layers": 12,
|
18 |
"pad_token_id": 0,
|
19 |
"position_embedding_type": "absolute",
|
20 |
"problem_type": "single_label_classification",
|
logs/events.out.tfevents.1715836386.spartan-gpgpu093.hpc.unimelb.edu.au
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 sha256:7ab39ae3f70f19b3238b0dcce00c0807a89ecb3110ccb971046178943608bb7a
|
3 |
+
size 10989
|
logs/events.out.tfevents.1715837284.spartan-gpgpu093.hpc.unimelb.edu.au
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3827f33ce341dcc2c10430ea26ae3c34af33c2684bf7bc66e75be17152c81502
|
3 |
+
size 778
|
logs/events.out.tfevents.1724059259.spartan-gpgpu095.hpc.unimelb.edu.au.131842.5
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93ea262ac08710a3a6f5a09b17cfcd7f4148e0991112a82cb1ac13ffe72a86da
|
3 |
+
size 5481
|
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:afe29913b4d4787fdbb5384ae4b337223d842f298fa8bb2dd7714d491caabcab
|
3 |
+
size 133466376
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4984
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8df7b752e96ee1b6193621a5975c138daf9c0f536edb61eae2e185a57e4ddd33
|
3 |
size 4984
|