Training in progress, step 500
Browse files- config.json +4 -3
- model.safetensors +2 -2
- training_args.bin +2 -2
config.json
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"T5ForConditionalGeneration"
|
4 |
],
|
@@ -15,16 +16,16 @@
|
|
15 |
"is_encoder_decoder": true,
|
16 |
"is_gated_act": false,
|
17 |
"layer_norm_epsilon": 1e-09,
|
18 |
-
"max_length":
|
19 |
"model_type": "t5",
|
20 |
"num_decoder_layers": 8,
|
21 |
"num_heads": 8,
|
22 |
-
"num_layers":
|
23 |
"pad_token_id": 0,
|
24 |
"relative_attention_max_distance": 128,
|
25 |
"relative_attention_num_buckets": 32,
|
26 |
"torch_dtype": "float32",
|
27 |
-
"transformers_version": "4.
|
28 |
"use_cache": true,
|
29 |
"vocab_size": 15100
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "Samuael/ethiopic-sec2sec-tigrinya",
|
3 |
"architectures": [
|
4 |
"T5ForConditionalGeneration"
|
5 |
],
|
|
|
16 |
"is_encoder_decoder": true,
|
17 |
"is_gated_act": false,
|
18 |
"layer_norm_epsilon": 1e-09,
|
19 |
+
"max_length": null,
|
20 |
"model_type": "t5",
|
21 |
"num_decoder_layers": 8,
|
22 |
"num_heads": 8,
|
23 |
+
"num_layers": 6,
|
24 |
"pad_token_id": 0,
|
25 |
"relative_attention_max_distance": 128,
|
26 |
"relative_attention_num_buckets": 32,
|
27 |
"torch_dtype": "float32",
|
28 |
+
"transformers_version": "4.46.3",
|
29 |
"use_cache": true,
|
30 |
"vocab_size": 15100
|
31 |
}
|
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:ed7db500a336eb91bfc135c27f94f55116c0f27d4d22df914291fc5f631d7810
|
3 |
+
size 240738368
|
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 sha256:0e5c54bb775b754ca568de85f6cbc4d3a88b148e5792d67fb6391aae6bb9ecf9
|
3 |
+
size 5432
|