Training in progress, step 500
Browse files- config.json +36 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +5 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +18 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "IlyaGusev/rut5_base_sum_gazeta",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 2,
|
| 7 |
+
"classifier_dropout": 0.0,
|
| 8 |
+
"d_ff": 2048,
|
| 9 |
+
"d_kv": 64,
|
| 10 |
+
"d_model": 768,
|
| 11 |
+
"decoder_start_token_id": 2,
|
| 12 |
+
"dense_act_fn": "gelu_new",
|
| 13 |
+
"dropout_rate": 0.1,
|
| 14 |
+
"eos_token_id": 1,
|
| 15 |
+
"feed_forward_proj": "gated-gelu",
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"max_length": 200,
|
| 21 |
+
"model_type": "t5",
|
| 22 |
+
"num_beams": 5,
|
| 23 |
+
"num_decoder_layers": 12,
|
| 24 |
+
"num_heads": 12,
|
| 25 |
+
"num_layers": 12,
|
| 26 |
+
"output_past": true,
|
| 27 |
+
"pad_token_id": 0,
|
| 28 |
+
"relative_attention_max_distance": 128,
|
| 29 |
+
"relative_attention_num_buckets": 32,
|
| 30 |
+
"tie_word_embeddings": false,
|
| 31 |
+
"tokenizer_class": "T5Tokenizer",
|
| 32 |
+
"torch_dtype": "float32",
|
| 33 |
+
"transformers_version": "4.33.0",
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 30000
|
| 36 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce5ab4d5886e53e91f8feb9a4c3393e8db9fff7d728627e863900ba9d80890aa
|
| 3 |
+
size 977330485
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "</s>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>"
|
| 5 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76927654c70c667e967c8caca165a3bb1311b415316b6aed8037ed5ede86b10e
|
| 3 |
+
size 827566
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": null,
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"extra_ids": 0,
|
| 6 |
+
"max_length": 200,
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"pad_to_multiple_of": null,
|
| 9 |
+
"pad_token": "<pad>",
|
| 10 |
+
"pad_token_type_id": 0,
|
| 11 |
+
"padding_side": "right",
|
| 12 |
+
"sp_model_kwargs": {},
|
| 13 |
+
"stride": 0,
|
| 14 |
+
"tokenizer_class": "T5Tokenizer",
|
| 15 |
+
"truncation_side": "right",
|
| 16 |
+
"truncation_strategy": "longest_first",
|
| 17 |
+
"unk_token": "<unk>"
|
| 18 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:090982de85a2a5f5c08dd470f40a06d164206a0d00cee1b369ca7d19d6a27742
|
| 3 |
+
size 4219
|