Training in progress, epoch 1
Browse files- config.json +37 -0
- generation_config.json +37 -0
- model.safetensors +3 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"MBartForConditionalGeneration"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"bos_token_id": 0,
|
| 9 |
+
"classifier_dropout": 0.0,
|
| 10 |
+
"d_model": 1024,
|
| 11 |
+
"decoder_attention_heads": 16,
|
| 12 |
+
"decoder_ffn_dim": 4096,
|
| 13 |
+
"decoder_layerdrop": 0.0,
|
| 14 |
+
"decoder_layers": 12,
|
| 15 |
+
"decoder_start_token_id": 2,
|
| 16 |
+
"dropout": 0.1,
|
| 17 |
+
"dtype": "float32",
|
| 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 |
+
"gradient_checkpointing": false,
|
| 24 |
+
"init_std": 0.02,
|
| 25 |
+
"is_decoder": false,
|
| 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 |
+
"tie_word_embeddings": true,
|
| 33 |
+
"tokenizer_class": "BartphoTokenizer",
|
| 34 |
+
"transformers_version": "5.0.0",
|
| 35 |
+
"use_cache": false,
|
| 36 |
+
"vocab_size": 40030
|
| 37 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": false,
|
| 3 |
+
"assistant_confidence_threshold": 0.4,
|
| 4 |
+
"assistant_lookbehind": 10,
|
| 5 |
+
"bos_token_id": 0,
|
| 6 |
+
"decoder_start_token_id": 2,
|
| 7 |
+
"diversity_penalty": 0.0,
|
| 8 |
+
"do_sample": false,
|
| 9 |
+
"early_stopping": false,
|
| 10 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 11 |
+
"encoder_repetition_penalty": 1.0,
|
| 12 |
+
"eos_token_id": 2,
|
| 13 |
+
"epsilon_cutoff": 0.0,
|
| 14 |
+
"eta_cutoff": 0.0,
|
| 15 |
+
"forced_eos_token_id": 2,
|
| 16 |
+
"length_penalty": 1.0,
|
| 17 |
+
"max_length": 20,
|
| 18 |
+
"min_length": 0,
|
| 19 |
+
"no_repeat_ngram_size": 0,
|
| 20 |
+
"num_assistant_tokens": 20,
|
| 21 |
+
"num_assistant_tokens_schedule": "constant",
|
| 22 |
+
"num_beam_groups": 1,
|
| 23 |
+
"num_beams": 1,
|
| 24 |
+
"num_return_sequences": 1,
|
| 25 |
+
"output_scores": false,
|
| 26 |
+
"pad_token_id": 1,
|
| 27 |
+
"remove_invalid_values": false,
|
| 28 |
+
"repetition_penalty": 1.0,
|
| 29 |
+
"return_dict_in_generate": false,
|
| 30 |
+
"target_lookbehind": 10,
|
| 31 |
+
"temperature": 1.0,
|
| 32 |
+
"top_k": 50,
|
| 33 |
+
"top_p": 1.0,
|
| 34 |
+
"transformers_version": "5.0.0",
|
| 35 |
+
"typical_p": 1.0,
|
| 36 |
+
"use_cache": true
|
| 37 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78757e043d042ab7a48717692fcddc8ddb9dd15bbc580cac2516a35857b26dd1
|
| 3 |
+
size 1583480280
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5ab4c7c94f13f1be7b2db7608186417a294fe5171b197fe80b0f4d1a0721335
|
| 3 |
+
size 5329
|