Upload 13 files
Browse files- added_tokens.json +3 -0
- all_results.json +14 -0
- bpe.codes +0 -0
- config.json +37 -0
- eval_results.json +9 -0
- generation_config.json +9 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +9 -0
- tokenizer_config.json +12 -0
- train_results.json +8 -0
- trainer_state.json +652 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<mask>": 64000
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.5,
|
| 3 |
+
"eval_cer": 9.473777688613003,
|
| 4 |
+
"eval_loss": 0.10590499639511108,
|
| 5 |
+
"eval_runtime": 201.8893,
|
| 6 |
+
"eval_samples": 5369,
|
| 7 |
+
"eval_samples_per_second": 26.594,
|
| 8 |
+
"eval_steps_per_second": 1.664,
|
| 9 |
+
"train_loss": 0.23776370769836302,
|
| 10 |
+
"train_runtime": 7748.8771,
|
| 11 |
+
"train_samples": 1068245,
|
| 12 |
+
"train_samples_per_second": 68.929,
|
| 13 |
+
"train_steps_per_second": 0.135
|
| 14 |
+
}
|
bpe.codes
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "bmd1905/vietnamese-correction",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"MBartForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.2,
|
| 9 |
+
"bos_token_id": 0,
|
| 10 |
+
"classifier_dropout": 0.4,
|
| 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": 0.2,
|
| 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": "4.33.0",
|
| 35 |
+
"use_cache": true,
|
| 36 |
+
"vocab_size": 64001
|
| 37 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.5,
|
| 3 |
+
"eval_cer": 9.473777688613003,
|
| 4 |
+
"eval_loss": 0.10590499639511108,
|
| 5 |
+
"eval_runtime": 201.8893,
|
| 6 |
+
"eval_samples": 5369,
|
| 7 |
+
"eval_samples_per_second": 26.594,
|
| 8 |
+
"eval_steps_per_second": 1.664
|
| 9 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"forced_eos_token_id": 2,
|
| 7 |
+
"pad_token_id": 1,
|
| 8 |
+
"transformers_version": "4.33.0"
|
| 9 |
+
}
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a45abbc3b7a681a070ae2834b695a37b0cc0df6699faa285f204e6578f508770
|
| 3 |
+
size 1681876701
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": "<mask>",
|
| 6 |
+
"pad_token": "<pad>",
|
| 7 |
+
"sep_token": "</s>",
|
| 8 |
+
"unk_token": "<unk>"
|
| 9 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"mask_token": "<mask>",
|
| 7 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
+
"pad_token": "<pad>",
|
| 9 |
+
"sep_token": "</s>",
|
| 10 |
+
"tokenizer_class": "PhobertTokenizer",
|
| 11 |
+
"unk_token": "<unk>"
|
| 12 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 0.5,
|
| 3 |
+
"train_loss": 0.23776370769836302,
|
| 4 |
+
"train_runtime": 7748.8771,
|
| 5 |
+
"train_samples": 1068245,
|
| 6 |
+
"train_samples_per_second": 68.929,
|
| 7 |
+
"train_steps_per_second": 0.135
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,652 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.4998951562172363,
|
| 5 |
+
"eval_steps": 10000,
|
| 6 |
+
"global_step": 1043,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 9.904122722914669e-05,
|
| 14 |
+
"loss": 2.4783,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 9.80824544582934e-05,
|
| 20 |
+
"loss": 0.9534,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 9.712368168744008e-05,
|
| 26 |
+
"loss": 0.6314,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.02,
|
| 31 |
+
"learning_rate": 9.616490891658677e-05,
|
| 32 |
+
"loss": 0.5312,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 9.520613614573348e-05,
|
| 38 |
+
"loss": 0.4806,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.03,
|
| 43 |
+
"learning_rate": 9.424736337488016e-05,
|
| 44 |
+
"loss": 0.4198,
|
| 45 |
+
"step": 60
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03,
|
| 49 |
+
"learning_rate": 9.328859060402684e-05,
|
| 50 |
+
"loss": 0.414,
|
| 51 |
+
"step": 70
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.04,
|
| 55 |
+
"learning_rate": 9.232981783317354e-05,
|
| 56 |
+
"loss": 0.3727,
|
| 57 |
+
"step": 80
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.04,
|
| 61 |
+
"learning_rate": 9.137104506232024e-05,
|
| 62 |
+
"loss": 0.3566,
|
| 63 |
+
"step": 90
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.05,
|
| 67 |
+
"learning_rate": 9.041227229146692e-05,
|
| 68 |
+
"loss": 0.3575,
|
| 69 |
+
"step": 100
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.05,
|
| 73 |
+
"learning_rate": 8.945349952061362e-05,
|
| 74 |
+
"loss": 0.3312,
|
| 75 |
+
"step": 110
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.06,
|
| 79 |
+
"learning_rate": 8.849472674976032e-05,
|
| 80 |
+
"loss": 0.3349,
|
| 81 |
+
"step": 120
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.06,
|
| 85 |
+
"learning_rate": 8.7535953978907e-05,
|
| 86 |
+
"loss": 0.3095,
|
| 87 |
+
"step": 130
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07,
|
| 91 |
+
"learning_rate": 8.65771812080537e-05,
|
| 92 |
+
"loss": 0.3227,
|
| 93 |
+
"step": 140
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.07,
|
| 97 |
+
"learning_rate": 8.56184084372004e-05,
|
| 98 |
+
"loss": 0.3074,
|
| 99 |
+
"step": 150
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.08,
|
| 103 |
+
"learning_rate": 8.465963566634708e-05,
|
| 104 |
+
"loss": 0.2834,
|
| 105 |
+
"step": 160
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.08,
|
| 109 |
+
"learning_rate": 8.370086289549378e-05,
|
| 110 |
+
"loss": 0.2855,
|
| 111 |
+
"step": 170
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.09,
|
| 115 |
+
"learning_rate": 8.274209012464046e-05,
|
| 116 |
+
"loss": 0.2981,
|
| 117 |
+
"step": 180
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.09,
|
| 121 |
+
"learning_rate": 8.178331735378716e-05,
|
| 122 |
+
"loss": 0.2834,
|
| 123 |
+
"step": 190
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.1,
|
| 127 |
+
"learning_rate": 8.082454458293385e-05,
|
| 128 |
+
"loss": 0.264,
|
| 129 |
+
"step": 200
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1,
|
| 133 |
+
"learning_rate": 7.986577181208054e-05,
|
| 134 |
+
"loss": 0.2732,
|
| 135 |
+
"step": 210
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.11,
|
| 139 |
+
"learning_rate": 7.890699904122723e-05,
|
| 140 |
+
"loss": 0.2758,
|
| 141 |
+
"step": 220
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.11,
|
| 145 |
+
"learning_rate": 7.794822627037393e-05,
|
| 146 |
+
"loss": 0.2626,
|
| 147 |
+
"step": 230
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.12,
|
| 151 |
+
"learning_rate": 7.698945349952061e-05,
|
| 152 |
+
"loss": 0.2516,
|
| 153 |
+
"step": 240
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.12,
|
| 157 |
+
"learning_rate": 7.603068072866731e-05,
|
| 158 |
+
"loss": 0.2575,
|
| 159 |
+
"step": 250
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.12,
|
| 163 |
+
"learning_rate": 7.507190795781401e-05,
|
| 164 |
+
"loss": 0.2565,
|
| 165 |
+
"step": 260
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.13,
|
| 169 |
+
"learning_rate": 7.411313518696069e-05,
|
| 170 |
+
"loss": 0.2382,
|
| 171 |
+
"step": 270
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.13,
|
| 175 |
+
"learning_rate": 7.315436241610739e-05,
|
| 176 |
+
"loss": 0.2489,
|
| 177 |
+
"step": 280
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.14,
|
| 181 |
+
"learning_rate": 7.219558964525409e-05,
|
| 182 |
+
"loss": 0.2308,
|
| 183 |
+
"step": 290
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.14,
|
| 187 |
+
"learning_rate": 7.123681687440077e-05,
|
| 188 |
+
"loss": 0.2299,
|
| 189 |
+
"step": 300
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.15,
|
| 193 |
+
"learning_rate": 7.027804410354745e-05,
|
| 194 |
+
"loss": 0.2479,
|
| 195 |
+
"step": 310
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.15,
|
| 199 |
+
"learning_rate": 6.931927133269415e-05,
|
| 200 |
+
"loss": 0.2288,
|
| 201 |
+
"step": 320
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.16,
|
| 205 |
+
"learning_rate": 6.836049856184085e-05,
|
| 206 |
+
"loss": 0.2394,
|
| 207 |
+
"step": 330
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.16,
|
| 211 |
+
"learning_rate": 6.740172579098753e-05,
|
| 212 |
+
"loss": 0.2239,
|
| 213 |
+
"step": 340
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.17,
|
| 217 |
+
"learning_rate": 6.644295302013423e-05,
|
| 218 |
+
"loss": 0.2282,
|
| 219 |
+
"step": 350
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.17,
|
| 223 |
+
"learning_rate": 6.548418024928093e-05,
|
| 224 |
+
"loss": 0.2227,
|
| 225 |
+
"step": 360
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.18,
|
| 229 |
+
"learning_rate": 6.452540747842761e-05,
|
| 230 |
+
"loss": 0.2181,
|
| 231 |
+
"step": 370
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.18,
|
| 235 |
+
"learning_rate": 6.356663470757431e-05,
|
| 236 |
+
"loss": 0.2211,
|
| 237 |
+
"step": 380
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.19,
|
| 241 |
+
"learning_rate": 6.2607861936721e-05,
|
| 242 |
+
"loss": 0.2157,
|
| 243 |
+
"step": 390
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.19,
|
| 247 |
+
"learning_rate": 6.164908916586769e-05,
|
| 248 |
+
"loss": 0.2097,
|
| 249 |
+
"step": 400
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.2,
|
| 253 |
+
"learning_rate": 6.069031639501438e-05,
|
| 254 |
+
"loss": 0.2006,
|
| 255 |
+
"step": 410
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.2,
|
| 259 |
+
"learning_rate": 5.973154362416108e-05,
|
| 260 |
+
"loss": 0.1968,
|
| 261 |
+
"step": 420
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.21,
|
| 265 |
+
"learning_rate": 5.8772770853307766e-05,
|
| 266 |
+
"loss": 0.2052,
|
| 267 |
+
"step": 430
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.21,
|
| 271 |
+
"learning_rate": 5.7813998082454456e-05,
|
| 272 |
+
"loss": 0.1958,
|
| 273 |
+
"step": 440
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.22,
|
| 277 |
+
"learning_rate": 5.6855225311601154e-05,
|
| 278 |
+
"loss": 0.1923,
|
| 279 |
+
"step": 450
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.22,
|
| 283 |
+
"learning_rate": 5.5896452540747844e-05,
|
| 284 |
+
"loss": 0.1968,
|
| 285 |
+
"step": 460
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.23,
|
| 289 |
+
"learning_rate": 5.4937679769894534e-05,
|
| 290 |
+
"loss": 0.1862,
|
| 291 |
+
"step": 470
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.23,
|
| 295 |
+
"learning_rate": 5.397890699904123e-05,
|
| 296 |
+
"loss": 0.1957,
|
| 297 |
+
"step": 480
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.23,
|
| 301 |
+
"learning_rate": 5.302013422818792e-05,
|
| 302 |
+
"loss": 0.1863,
|
| 303 |
+
"step": 490
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.24,
|
| 307 |
+
"learning_rate": 5.206136145733461e-05,
|
| 308 |
+
"loss": 0.1894,
|
| 309 |
+
"step": 500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.24,
|
| 313 |
+
"learning_rate": 5.110258868648131e-05,
|
| 314 |
+
"loss": 0.1837,
|
| 315 |
+
"step": 510
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.25,
|
| 319 |
+
"learning_rate": 5.0143815915628e-05,
|
| 320 |
+
"loss": 0.1836,
|
| 321 |
+
"step": 520
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.25,
|
| 325 |
+
"learning_rate": 4.918504314477469e-05,
|
| 326 |
+
"loss": 0.1871,
|
| 327 |
+
"step": 530
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.26,
|
| 331 |
+
"learning_rate": 4.822627037392138e-05,
|
| 332 |
+
"loss": 0.1795,
|
| 333 |
+
"step": 540
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.26,
|
| 337 |
+
"learning_rate": 4.726749760306807e-05,
|
| 338 |
+
"loss": 0.1846,
|
| 339 |
+
"step": 550
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.27,
|
| 343 |
+
"learning_rate": 4.630872483221477e-05,
|
| 344 |
+
"loss": 0.1825,
|
| 345 |
+
"step": 560
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.27,
|
| 349 |
+
"learning_rate": 4.534995206136146e-05,
|
| 350 |
+
"loss": 0.1704,
|
| 351 |
+
"step": 570
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.28,
|
| 355 |
+
"learning_rate": 4.439117929050815e-05,
|
| 356 |
+
"loss": 0.1781,
|
| 357 |
+
"step": 580
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.28,
|
| 361 |
+
"learning_rate": 4.3432406519654846e-05,
|
| 362 |
+
"loss": 0.1773,
|
| 363 |
+
"step": 590
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.29,
|
| 367 |
+
"learning_rate": 4.2473633748801537e-05,
|
| 368 |
+
"loss": 0.1742,
|
| 369 |
+
"step": 600
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.29,
|
| 373 |
+
"learning_rate": 4.151486097794823e-05,
|
| 374 |
+
"loss": 0.1683,
|
| 375 |
+
"step": 610
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.3,
|
| 379 |
+
"learning_rate": 4.0556088207094924e-05,
|
| 380 |
+
"loss": 0.1634,
|
| 381 |
+
"step": 620
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.3,
|
| 385 |
+
"learning_rate": 3.959731543624161e-05,
|
| 386 |
+
"loss": 0.161,
|
| 387 |
+
"step": 630
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.31,
|
| 391 |
+
"learning_rate": 3.8638542665388305e-05,
|
| 392 |
+
"loss": 0.166,
|
| 393 |
+
"step": 640
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.31,
|
| 397 |
+
"learning_rate": 3.7679769894535e-05,
|
| 398 |
+
"loss": 0.1689,
|
| 399 |
+
"step": 650
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.32,
|
| 403 |
+
"learning_rate": 3.6720997123681686e-05,
|
| 404 |
+
"loss": 0.1726,
|
| 405 |
+
"step": 660
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.32,
|
| 409 |
+
"learning_rate": 3.576222435282838e-05,
|
| 410 |
+
"loss": 0.1509,
|
| 411 |
+
"step": 670
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.33,
|
| 415 |
+
"learning_rate": 3.480345158197507e-05,
|
| 416 |
+
"loss": 0.1588,
|
| 417 |
+
"step": 680
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.33,
|
| 421 |
+
"learning_rate": 3.3844678811121764e-05,
|
| 422 |
+
"loss": 0.1558,
|
| 423 |
+
"step": 690
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.34,
|
| 427 |
+
"learning_rate": 3.288590604026846e-05,
|
| 428 |
+
"loss": 0.1522,
|
| 429 |
+
"step": 700
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.34,
|
| 433 |
+
"learning_rate": 3.192713326941515e-05,
|
| 434 |
+
"loss": 0.1568,
|
| 435 |
+
"step": 710
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.35,
|
| 439 |
+
"learning_rate": 3.096836049856184e-05,
|
| 440 |
+
"loss": 0.1471,
|
| 441 |
+
"step": 720
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.35,
|
| 445 |
+
"learning_rate": 3.0009587727708532e-05,
|
| 446 |
+
"loss": 0.1437,
|
| 447 |
+
"step": 730
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.35,
|
| 451 |
+
"learning_rate": 2.9050814956855226e-05,
|
| 452 |
+
"loss": 0.1507,
|
| 453 |
+
"step": 740
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.36,
|
| 457 |
+
"learning_rate": 2.8092042186001923e-05,
|
| 458 |
+
"loss": 0.1398,
|
| 459 |
+
"step": 750
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.36,
|
| 463 |
+
"learning_rate": 2.713326941514861e-05,
|
| 464 |
+
"loss": 0.1429,
|
| 465 |
+
"step": 760
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.37,
|
| 469 |
+
"learning_rate": 2.6174496644295304e-05,
|
| 470 |
+
"loss": 0.151,
|
| 471 |
+
"step": 770
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.37,
|
| 475 |
+
"learning_rate": 2.5215723873441994e-05,
|
| 476 |
+
"loss": 0.1419,
|
| 477 |
+
"step": 780
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.38,
|
| 481 |
+
"learning_rate": 2.4256951102588688e-05,
|
| 482 |
+
"loss": 0.1482,
|
| 483 |
+
"step": 790
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.38,
|
| 487 |
+
"learning_rate": 2.3298178331735378e-05,
|
| 488 |
+
"loss": 0.1395,
|
| 489 |
+
"step": 800
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.39,
|
| 493 |
+
"learning_rate": 2.2339405560882072e-05,
|
| 494 |
+
"loss": 0.1465,
|
| 495 |
+
"step": 810
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.39,
|
| 499 |
+
"learning_rate": 2.1380632790028766e-05,
|
| 500 |
+
"loss": 0.144,
|
| 501 |
+
"step": 820
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.4,
|
| 505 |
+
"learning_rate": 2.0421860019175456e-05,
|
| 506 |
+
"loss": 0.1484,
|
| 507 |
+
"step": 830
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.4,
|
| 511 |
+
"learning_rate": 1.946308724832215e-05,
|
| 512 |
+
"loss": 0.1367,
|
| 513 |
+
"step": 840
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.41,
|
| 517 |
+
"learning_rate": 1.850431447746884e-05,
|
| 518 |
+
"loss": 0.1342,
|
| 519 |
+
"step": 850
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.41,
|
| 523 |
+
"learning_rate": 1.7545541706615534e-05,
|
| 524 |
+
"loss": 0.1293,
|
| 525 |
+
"step": 860
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.42,
|
| 529 |
+
"learning_rate": 1.6586768935762224e-05,
|
| 530 |
+
"loss": 0.1346,
|
| 531 |
+
"step": 870
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.42,
|
| 535 |
+
"learning_rate": 1.5627996164908918e-05,
|
| 536 |
+
"loss": 0.1351,
|
| 537 |
+
"step": 880
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.43,
|
| 541 |
+
"learning_rate": 1.4669223394055609e-05,
|
| 542 |
+
"loss": 0.1289,
|
| 543 |
+
"step": 890
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.43,
|
| 547 |
+
"learning_rate": 1.37104506232023e-05,
|
| 548 |
+
"loss": 0.1312,
|
| 549 |
+
"step": 900
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.44,
|
| 553 |
+
"learning_rate": 1.2751677852348994e-05,
|
| 554 |
+
"loss": 0.1309,
|
| 555 |
+
"step": 910
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.44,
|
| 559 |
+
"learning_rate": 1.1792905081495687e-05,
|
| 560 |
+
"loss": 0.1225,
|
| 561 |
+
"step": 920
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.45,
|
| 565 |
+
"learning_rate": 1.0834132310642379e-05,
|
| 566 |
+
"loss": 0.1255,
|
| 567 |
+
"step": 930
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.45,
|
| 571 |
+
"learning_rate": 9.87535953978907e-06,
|
| 572 |
+
"loss": 0.1341,
|
| 573 |
+
"step": 940
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.46,
|
| 577 |
+
"learning_rate": 8.916586768935763e-06,
|
| 578 |
+
"loss": 0.1299,
|
| 579 |
+
"step": 950
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.46,
|
| 583 |
+
"learning_rate": 7.957813998082455e-06,
|
| 584 |
+
"loss": 0.1346,
|
| 585 |
+
"step": 960
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.46,
|
| 589 |
+
"learning_rate": 6.999041227229147e-06,
|
| 590 |
+
"loss": 0.1261,
|
| 591 |
+
"step": 970
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.47,
|
| 595 |
+
"learning_rate": 6.04026845637584e-06,
|
| 596 |
+
"loss": 0.1239,
|
| 597 |
+
"step": 980
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.47,
|
| 601 |
+
"learning_rate": 5.081495685522531e-06,
|
| 602 |
+
"loss": 0.1185,
|
| 603 |
+
"step": 990
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.48,
|
| 607 |
+
"learning_rate": 4.122722914669223e-06,
|
| 608 |
+
"loss": 0.1228,
|
| 609 |
+
"step": 1000
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.48,
|
| 613 |
+
"learning_rate": 3.1639501438159157e-06,
|
| 614 |
+
"loss": 0.1243,
|
| 615 |
+
"step": 1010
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.49,
|
| 619 |
+
"learning_rate": 2.2051773729626078e-06,
|
| 620 |
+
"loss": 0.1243,
|
| 621 |
+
"step": 1020
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.49,
|
| 625 |
+
"learning_rate": 1.2464046021093003e-06,
|
| 626 |
+
"loss": 0.1259,
|
| 627 |
+
"step": 1030
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.5,
|
| 631 |
+
"learning_rate": 2.876318312559924e-07,
|
| 632 |
+
"loss": 0.1258,
|
| 633 |
+
"step": 1040
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.5,
|
| 637 |
+
"step": 1043,
|
| 638 |
+
"total_flos": 3.162519559471104e+16,
|
| 639 |
+
"train_loss": 0.23776370769836302,
|
| 640 |
+
"train_runtime": 7748.8771,
|
| 641 |
+
"train_samples_per_second": 68.929,
|
| 642 |
+
"train_steps_per_second": 0.135
|
| 643 |
+
}
|
| 644 |
+
],
|
| 645 |
+
"logging_steps": 10,
|
| 646 |
+
"max_steps": 1043,
|
| 647 |
+
"num_train_epochs": 1,
|
| 648 |
+
"save_steps": 500,
|
| 649 |
+
"total_flos": 3.162519559471104e+16,
|
| 650 |
+
"trial_name": null,
|
| 651 |
+
"trial_params": null
|
| 652 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e461652a3a0fd008fafcf196eafec211bd830e758740f1cf849f620be2ae7dbb
|
| 3 |
+
size 4219
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|