Training in progress, step 2000
Browse files- config.json +37 -0
- model.safetensors +3 -0
- runs/Jan23_04-21-20_567074e731e3/events.out.tfevents.1737606093.567074e731e3.109.0 +3 -0
- runs/Jan23_04-21-20_567074e731e3/events.out.tfevents.1737606250.567074e731e3.109.1 +3 -0
- runs/Jan23_04-24-33_567074e731e3/events.out.tfevents.1737606280.567074e731e3.109.2 +3 -0
- runs/Jan23_04-25-37_567074e731e3/events.out.tfevents.1737606348.567074e731e3.109.3 +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "vinai/bartpho-word",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MBartForQuestionAnswering"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"classifier_dropout": 0.0,
|
| 11 |
+
"d_model": 1024,
|
| 12 |
+
"decoder_attention_heads": 16,
|
| 13 |
+
"decoder_ffn_dim": 4096,
|
| 14 |
+
"decoder_layerdrop": 0.0,
|
| 15 |
+
"decoder_layers": 12,
|
| 16 |
+
"decoder_start_token_id": 2,
|
| 17 |
+
"dropout": 0.1,
|
| 18 |
+
"encoder_attention_heads": 16,
|
| 19 |
+
"encoder_ffn_dim": 4096,
|
| 20 |
+
"encoder_layerdrop": 0.0,
|
| 21 |
+
"encoder_layers": 12,
|
| 22 |
+
"eos_token_id": 2,
|
| 23 |
+
"forced_eos_token_id": 2,
|
| 24 |
+
"gradient_checkpointing": false,
|
| 25 |
+
"init_std": 0.02,
|
| 26 |
+
"is_encoder_decoder": true,
|
| 27 |
+
"max_position_embeddings": 1024,
|
| 28 |
+
"model_type": "mbart",
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 1,
|
| 31 |
+
"scale_embedding": false,
|
| 32 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.47.0",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 66120
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f340af2ef73d8a940290e52e088ac6d3cd63ac25971848d394cbbb80eeb6ad54
|
| 3 |
+
size 1690193088
|
runs/Jan23_04-21-20_567074e731e3/events.out.tfevents.1737606093.567074e731e3.109.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ae4ad1d03ff387b961510b21deccbb4e19b5826b7e39c131067fda2241b8197
|
| 3 |
+
size 5365
|
runs/Jan23_04-21-20_567074e731e3/events.out.tfevents.1737606250.567074e731e3.109.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c28186adade396d53ade22dbcf3193b78e93a945c2de9095fb82b6150c4f00a
|
| 3 |
+
size 5365
|
runs/Jan23_04-24-33_567074e731e3/events.out.tfevents.1737606280.567074e731e3.109.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a793b2c43736fb6fa6c310199a0bc5ca6f30ab1fafab2421930fedb9c5fbf0ba
|
| 3 |
+
size 5329
|
runs/Jan23_04-25-37_567074e731e3/events.out.tfevents.1737606348.567074e731e3.109.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:715eb3595c335941f7b9fc3666f91eb66436202ecf16f4b05c7c89ac6d00718a
|
| 3 |
+
size 5365
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da1a8756812929a9a469c110a4ee0937496b3a2cb31793d4b3a8d1ea87c9c5d6
|
| 3 |
+
size 5368
|