cphienanda
commited on
Training in progress, step 1000
Browse files- config.json +20 -16
- model.safetensors +2 -2
- runs/Dec05_22-57-45_xtaco/events.out.tfevents.1733468268.xtaco.28020.0 +3 -0
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,29 +1,33 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_probs_dropout_prob": 0
|
7 |
-
"
|
8 |
-
"
|
9 |
-
"
|
10 |
-
"
|
11 |
-
"
|
12 |
-
"
|
|
|
|
|
|
|
13 |
"initializer_range": 0.02,
|
14 |
-
"
|
|
|
15 |
"layer_norm_eps": 1e-12,
|
16 |
"max_position_embeddings": 512,
|
17 |
-
"model_type": "
|
|
|
18 |
"num_attention_heads": 12,
|
19 |
-
"
|
|
|
|
|
20 |
"pad_token_id": 0,
|
21 |
"position_embedding_type": "absolute",
|
22 |
-
"pre_trained": "",
|
23 |
-
"structure": [],
|
24 |
"torch_dtype": "float32",
|
25 |
"transformers_version": "4.46.3",
|
26 |
"type_vocab_size": 2,
|
27 |
-
"
|
28 |
-
"vocab_size": 30522
|
29 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "albert-base-v2",
|
3 |
"architectures": [
|
4 |
+
"AlbertForMaskedLM"
|
5 |
],
|
6 |
+
"attention_probs_dropout_prob": 0,
|
7 |
+
"bos_token_id": 2,
|
8 |
+
"classifier_dropout_prob": 0.1,
|
9 |
+
"down_scale_factor": 1,
|
10 |
+
"embedding_size": 128,
|
11 |
+
"eos_token_id": 3,
|
12 |
+
"gap_size": 0,
|
13 |
+
"hidden_act": "gelu_new",
|
14 |
+
"hidden_dropout_prob": 0,
|
15 |
+
"hidden_size": 768,
|
16 |
"initializer_range": 0.02,
|
17 |
+
"inner_group_num": 1,
|
18 |
+
"intermediate_size": 3072,
|
19 |
"layer_norm_eps": 1e-12,
|
20 |
"max_position_embeddings": 512,
|
21 |
+
"model_type": "albert",
|
22 |
+
"net_structure_type": 0,
|
23 |
"num_attention_heads": 12,
|
24 |
+
"num_hidden_groups": 1,
|
25 |
+
"num_hidden_layers": 12,
|
26 |
+
"num_memory_blocks": 0,
|
27 |
"pad_token_id": 0,
|
28 |
"position_embedding_type": "absolute",
|
|
|
|
|
29 |
"torch_dtype": "float32",
|
30 |
"transformers_version": "4.46.3",
|
31 |
"type_vocab_size": 2,
|
32 |
+
"vocab_size": 30000
|
|
|
33 |
}
|
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:f86afc6c561e505ec762ab02ab31727c01cedcef378f85451880f7363e9e8bf6
|
3 |
+
size 44890256
|
runs/Dec05_22-57-45_xtaco/events.out.tfevents.1733468268.xtaco.28020.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aadd6abd171d51786cffd7d47d72fb4fdfb2808a8c2f1d88fb6b7dec6d47bd6a
|
3 |
+
size 5699
|
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:d5bbdf4ea24a625fe59894b27bc699e2932a8a1e4833d846718e25a53ccc74e6
|
3 |
+
size 4847
|