Upload 12 files
Browse files- config.json +32 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +103 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +902 -0
- trainer_state.json +1473 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "VietAI/vit5-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "relu",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"torch_dtype": "float32",
|
| 29 |
+
"transformers_version": "4.37.0",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 36096
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": 1,
|
| 4 |
+
"pad_token_id": 0,
|
| 5 |
+
"transformers_version": "4.37.0"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac794c0dfcafd5c0bc93e52a655961499777d6537d8932ff59f2ae10611c2a8b
|
| 3 |
+
size 903834408
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b5c937231a2c52323534a78ace841888baf038a3c01d18c5049e5d189ff0fc4a
|
| 3 |
+
size 1807824186
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d68b2068ee188272bde76715802f374a2ac0902fd019a321583d8943180c7cb
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d7850e60e1d70db02ff34128df1e02e6e90351becfeb0e5c2a59b4a2f875291
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<extra_id_0>",
|
| 4 |
+
"<extra_id_1>",
|
| 5 |
+
"<extra_id_2>",
|
| 6 |
+
"<extra_id_3>",
|
| 7 |
+
"<extra_id_4>",
|
| 8 |
+
"<extra_id_5>",
|
| 9 |
+
"<extra_id_6>",
|
| 10 |
+
"<extra_id_7>",
|
| 11 |
+
"<extra_id_8>",
|
| 12 |
+
"<extra_id_9>",
|
| 13 |
+
"<extra_id_10>",
|
| 14 |
+
"<extra_id_11>",
|
| 15 |
+
"<extra_id_12>",
|
| 16 |
+
"<extra_id_13>",
|
| 17 |
+
"<extra_id_14>",
|
| 18 |
+
"<extra_id_15>",
|
| 19 |
+
"<extra_id_16>",
|
| 20 |
+
"<extra_id_17>",
|
| 21 |
+
"<extra_id_18>",
|
| 22 |
+
"<extra_id_19>",
|
| 23 |
+
"<extra_id_20>",
|
| 24 |
+
"<extra_id_21>",
|
| 25 |
+
"<extra_id_22>",
|
| 26 |
+
"<extra_id_23>",
|
| 27 |
+
"<extra_id_24>",
|
| 28 |
+
"<extra_id_25>",
|
| 29 |
+
"<extra_id_26>",
|
| 30 |
+
"<extra_id_27>",
|
| 31 |
+
"<extra_id_28>",
|
| 32 |
+
"<extra_id_29>",
|
| 33 |
+
"<extra_id_30>",
|
| 34 |
+
"<extra_id_31>",
|
| 35 |
+
"<extra_id_32>",
|
| 36 |
+
"<extra_id_33>",
|
| 37 |
+
"<extra_id_34>",
|
| 38 |
+
"<extra_id_35>",
|
| 39 |
+
"<extra_id_36>",
|
| 40 |
+
"<extra_id_37>",
|
| 41 |
+
"<extra_id_38>",
|
| 42 |
+
"<extra_id_39>",
|
| 43 |
+
"<extra_id_40>",
|
| 44 |
+
"<extra_id_41>",
|
| 45 |
+
"<extra_id_42>",
|
| 46 |
+
"<extra_id_43>",
|
| 47 |
+
"<extra_id_44>",
|
| 48 |
+
"<extra_id_45>",
|
| 49 |
+
"<extra_id_46>",
|
| 50 |
+
"<extra_id_47>",
|
| 51 |
+
"<extra_id_48>",
|
| 52 |
+
"<extra_id_49>",
|
| 53 |
+
"<extra_id_50>",
|
| 54 |
+
"<extra_id_51>",
|
| 55 |
+
"<extra_id_52>",
|
| 56 |
+
"<extra_id_53>",
|
| 57 |
+
"<extra_id_54>",
|
| 58 |
+
"<extra_id_55>",
|
| 59 |
+
"<extra_id_56>",
|
| 60 |
+
"<extra_id_57>",
|
| 61 |
+
"<extra_id_58>",
|
| 62 |
+
"<extra_id_59>",
|
| 63 |
+
"<extra_id_60>",
|
| 64 |
+
"<extra_id_61>",
|
| 65 |
+
"<extra_id_62>",
|
| 66 |
+
"<extra_id_63>",
|
| 67 |
+
"<extra_id_64>",
|
| 68 |
+
"<extra_id_65>",
|
| 69 |
+
"<extra_id_66>",
|
| 70 |
+
"<extra_id_67>",
|
| 71 |
+
"<extra_id_68>",
|
| 72 |
+
"<extra_id_69>",
|
| 73 |
+
"<extra_id_70>",
|
| 74 |
+
"<extra_id_71>",
|
| 75 |
+
"<extra_id_72>",
|
| 76 |
+
"<extra_id_73>",
|
| 77 |
+
"<extra_id_74>",
|
| 78 |
+
"<extra_id_75>",
|
| 79 |
+
"<extra_id_76>",
|
| 80 |
+
"<extra_id_77>",
|
| 81 |
+
"<extra_id_78>",
|
| 82 |
+
"<extra_id_79>",
|
| 83 |
+
"<extra_id_80>",
|
| 84 |
+
"<extra_id_81>",
|
| 85 |
+
"<extra_id_82>",
|
| 86 |
+
"<extra_id_83>",
|
| 87 |
+
"<extra_id_84>",
|
| 88 |
+
"<extra_id_85>",
|
| 89 |
+
"<extra_id_86>",
|
| 90 |
+
"<extra_id_87>",
|
| 91 |
+
"<extra_id_88>",
|
| 92 |
+
"<extra_id_89>",
|
| 93 |
+
"<extra_id_90>",
|
| 94 |
+
"<extra_id_91>",
|
| 95 |
+
"<extra_id_92>",
|
| 96 |
+
"<extra_id_93>",
|
| 97 |
+
"<extra_id_94>",
|
| 98 |
+
"<extra_id_95>"
|
| 99 |
+
],
|
| 100 |
+
"eos_token": "</s>",
|
| 101 |
+
"pad_token": "<pad>",
|
| 102 |
+
"unk_token": "<unk>"
|
| 103 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59986b62f9f0b90edafb9b073ea7b93d21114a5841219a1ea2399ade73f729c6
|
| 3 |
+
size 820370
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,902 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<pad>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "</s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "<unk>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"36000": {
|
| 28 |
+
"content": "<extra_id_95>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"36001": {
|
| 36 |
+
"content": "<extra_id_94>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"36002": {
|
| 44 |
+
"content": "<extra_id_93>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"36003": {
|
| 52 |
+
"content": "<extra_id_92>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"36004": {
|
| 60 |
+
"content": "<extra_id_91>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"36005": {
|
| 68 |
+
"content": "<extra_id_90>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"36006": {
|
| 76 |
+
"content": "<extra_id_89>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"36007": {
|
| 84 |
+
"content": "<extra_id_88>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"36008": {
|
| 92 |
+
"content": "<extra_id_87>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"36009": {
|
| 100 |
+
"content": "<extra_id_86>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"36010": {
|
| 108 |
+
"content": "<extra_id_85>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"36011": {
|
| 116 |
+
"content": "<extra_id_84>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"36012": {
|
| 124 |
+
"content": "<extra_id_83>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"36013": {
|
| 132 |
+
"content": "<extra_id_82>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"36014": {
|
| 140 |
+
"content": "<extra_id_81>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"36015": {
|
| 148 |
+
"content": "<extra_id_80>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"36016": {
|
| 156 |
+
"content": "<extra_id_79>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"36017": {
|
| 164 |
+
"content": "<extra_id_78>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"36018": {
|
| 172 |
+
"content": "<extra_id_77>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"36019": {
|
| 180 |
+
"content": "<extra_id_76>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"36020": {
|
| 188 |
+
"content": "<extra_id_75>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"36021": {
|
| 196 |
+
"content": "<extra_id_74>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"36022": {
|
| 204 |
+
"content": "<extra_id_73>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"36023": {
|
| 212 |
+
"content": "<extra_id_72>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"36024": {
|
| 220 |
+
"content": "<extra_id_71>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"36025": {
|
| 228 |
+
"content": "<extra_id_70>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"36026": {
|
| 236 |
+
"content": "<extra_id_69>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"36027": {
|
| 244 |
+
"content": "<extra_id_68>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"36028": {
|
| 252 |
+
"content": "<extra_id_67>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"36029": {
|
| 260 |
+
"content": "<extra_id_66>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"36030": {
|
| 268 |
+
"content": "<extra_id_65>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"36031": {
|
| 276 |
+
"content": "<extra_id_64>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"36032": {
|
| 284 |
+
"content": "<extra_id_63>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"36033": {
|
| 292 |
+
"content": "<extra_id_62>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"36034": {
|
| 300 |
+
"content": "<extra_id_61>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"36035": {
|
| 308 |
+
"content": "<extra_id_60>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"36036": {
|
| 316 |
+
"content": "<extra_id_59>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"36037": {
|
| 324 |
+
"content": "<extra_id_58>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"36038": {
|
| 332 |
+
"content": "<extra_id_57>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"36039": {
|
| 340 |
+
"content": "<extra_id_56>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"36040": {
|
| 348 |
+
"content": "<extra_id_55>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"36041": {
|
| 356 |
+
"content": "<extra_id_54>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"36042": {
|
| 364 |
+
"content": "<extra_id_53>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"36043": {
|
| 372 |
+
"content": "<extra_id_52>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"36044": {
|
| 380 |
+
"content": "<extra_id_51>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"36045": {
|
| 388 |
+
"content": "<extra_id_50>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"36046": {
|
| 396 |
+
"content": "<extra_id_49>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"36047": {
|
| 404 |
+
"content": "<extra_id_48>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"36048": {
|
| 412 |
+
"content": "<extra_id_47>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"36049": {
|
| 420 |
+
"content": "<extra_id_46>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"36050": {
|
| 428 |
+
"content": "<extra_id_45>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"36051": {
|
| 436 |
+
"content": "<extra_id_44>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"36052": {
|
| 444 |
+
"content": "<extra_id_43>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"36053": {
|
| 452 |
+
"content": "<extra_id_42>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"36054": {
|
| 460 |
+
"content": "<extra_id_41>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"36055": {
|
| 468 |
+
"content": "<extra_id_40>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"36056": {
|
| 476 |
+
"content": "<extra_id_39>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"36057": {
|
| 484 |
+
"content": "<extra_id_38>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"36058": {
|
| 492 |
+
"content": "<extra_id_37>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"36059": {
|
| 500 |
+
"content": "<extra_id_36>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"36060": {
|
| 508 |
+
"content": "<extra_id_35>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"36061": {
|
| 516 |
+
"content": "<extra_id_34>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"36062": {
|
| 524 |
+
"content": "<extra_id_33>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"36063": {
|
| 532 |
+
"content": "<extra_id_32>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"36064": {
|
| 540 |
+
"content": "<extra_id_31>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"36065": {
|
| 548 |
+
"content": "<extra_id_30>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"36066": {
|
| 556 |
+
"content": "<extra_id_29>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"36067": {
|
| 564 |
+
"content": "<extra_id_28>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"36068": {
|
| 572 |
+
"content": "<extra_id_27>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"36069": {
|
| 580 |
+
"content": "<extra_id_26>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"36070": {
|
| 588 |
+
"content": "<extra_id_25>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"36071": {
|
| 596 |
+
"content": "<extra_id_24>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"36072": {
|
| 604 |
+
"content": "<extra_id_23>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"36073": {
|
| 612 |
+
"content": "<extra_id_22>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"36074": {
|
| 620 |
+
"content": "<extra_id_21>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"36075": {
|
| 628 |
+
"content": "<extra_id_20>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"36076": {
|
| 636 |
+
"content": "<extra_id_19>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"36077": {
|
| 644 |
+
"content": "<extra_id_18>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"36078": {
|
| 652 |
+
"content": "<extra_id_17>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"36079": {
|
| 660 |
+
"content": "<extra_id_16>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"36080": {
|
| 668 |
+
"content": "<extra_id_15>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"36081": {
|
| 676 |
+
"content": "<extra_id_14>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"36082": {
|
| 684 |
+
"content": "<extra_id_13>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"36083": {
|
| 692 |
+
"content": "<extra_id_12>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"36084": {
|
| 700 |
+
"content": "<extra_id_11>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"36085": {
|
| 708 |
+
"content": "<extra_id_10>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"36086": {
|
| 716 |
+
"content": "<extra_id_9>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"36087": {
|
| 724 |
+
"content": "<extra_id_8>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"36088": {
|
| 732 |
+
"content": "<extra_id_7>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"36089": {
|
| 740 |
+
"content": "<extra_id_6>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"36090": {
|
| 748 |
+
"content": "<extra_id_5>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"36091": {
|
| 756 |
+
"content": "<extra_id_4>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"36092": {
|
| 764 |
+
"content": "<extra_id_3>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"36093": {
|
| 772 |
+
"content": "<extra_id_2>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"36094": {
|
| 780 |
+
"content": "<extra_id_1>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"36095": {
|
| 788 |
+
"content": "<extra_id_0>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
}
|
| 795 |
+
},
|
| 796 |
+
"additional_special_tokens": [
|
| 797 |
+
"<extra_id_0>",
|
| 798 |
+
"<extra_id_1>",
|
| 799 |
+
"<extra_id_2>",
|
| 800 |
+
"<extra_id_3>",
|
| 801 |
+
"<extra_id_4>",
|
| 802 |
+
"<extra_id_5>",
|
| 803 |
+
"<extra_id_6>",
|
| 804 |
+
"<extra_id_7>",
|
| 805 |
+
"<extra_id_8>",
|
| 806 |
+
"<extra_id_9>",
|
| 807 |
+
"<extra_id_10>",
|
| 808 |
+
"<extra_id_11>",
|
| 809 |
+
"<extra_id_12>",
|
| 810 |
+
"<extra_id_13>",
|
| 811 |
+
"<extra_id_14>",
|
| 812 |
+
"<extra_id_15>",
|
| 813 |
+
"<extra_id_16>",
|
| 814 |
+
"<extra_id_17>",
|
| 815 |
+
"<extra_id_18>",
|
| 816 |
+
"<extra_id_19>",
|
| 817 |
+
"<extra_id_20>",
|
| 818 |
+
"<extra_id_21>",
|
| 819 |
+
"<extra_id_22>",
|
| 820 |
+
"<extra_id_23>",
|
| 821 |
+
"<extra_id_24>",
|
| 822 |
+
"<extra_id_25>",
|
| 823 |
+
"<extra_id_26>",
|
| 824 |
+
"<extra_id_27>",
|
| 825 |
+
"<extra_id_28>",
|
| 826 |
+
"<extra_id_29>",
|
| 827 |
+
"<extra_id_30>",
|
| 828 |
+
"<extra_id_31>",
|
| 829 |
+
"<extra_id_32>",
|
| 830 |
+
"<extra_id_33>",
|
| 831 |
+
"<extra_id_34>",
|
| 832 |
+
"<extra_id_35>",
|
| 833 |
+
"<extra_id_36>",
|
| 834 |
+
"<extra_id_37>",
|
| 835 |
+
"<extra_id_38>",
|
| 836 |
+
"<extra_id_39>",
|
| 837 |
+
"<extra_id_40>",
|
| 838 |
+
"<extra_id_41>",
|
| 839 |
+
"<extra_id_42>",
|
| 840 |
+
"<extra_id_43>",
|
| 841 |
+
"<extra_id_44>",
|
| 842 |
+
"<extra_id_45>",
|
| 843 |
+
"<extra_id_46>",
|
| 844 |
+
"<extra_id_47>",
|
| 845 |
+
"<extra_id_48>",
|
| 846 |
+
"<extra_id_49>",
|
| 847 |
+
"<extra_id_50>",
|
| 848 |
+
"<extra_id_51>",
|
| 849 |
+
"<extra_id_52>",
|
| 850 |
+
"<extra_id_53>",
|
| 851 |
+
"<extra_id_54>",
|
| 852 |
+
"<extra_id_55>",
|
| 853 |
+
"<extra_id_56>",
|
| 854 |
+
"<extra_id_57>",
|
| 855 |
+
"<extra_id_58>",
|
| 856 |
+
"<extra_id_59>",
|
| 857 |
+
"<extra_id_60>",
|
| 858 |
+
"<extra_id_61>",
|
| 859 |
+
"<extra_id_62>",
|
| 860 |
+
"<extra_id_63>",
|
| 861 |
+
"<extra_id_64>",
|
| 862 |
+
"<extra_id_65>",
|
| 863 |
+
"<extra_id_66>",
|
| 864 |
+
"<extra_id_67>",
|
| 865 |
+
"<extra_id_68>",
|
| 866 |
+
"<extra_id_69>",
|
| 867 |
+
"<extra_id_70>",
|
| 868 |
+
"<extra_id_71>",
|
| 869 |
+
"<extra_id_72>",
|
| 870 |
+
"<extra_id_73>",
|
| 871 |
+
"<extra_id_74>",
|
| 872 |
+
"<extra_id_75>",
|
| 873 |
+
"<extra_id_76>",
|
| 874 |
+
"<extra_id_77>",
|
| 875 |
+
"<extra_id_78>",
|
| 876 |
+
"<extra_id_79>",
|
| 877 |
+
"<extra_id_80>",
|
| 878 |
+
"<extra_id_81>",
|
| 879 |
+
"<extra_id_82>",
|
| 880 |
+
"<extra_id_83>",
|
| 881 |
+
"<extra_id_84>",
|
| 882 |
+
"<extra_id_85>",
|
| 883 |
+
"<extra_id_86>",
|
| 884 |
+
"<extra_id_87>",
|
| 885 |
+
"<extra_id_88>",
|
| 886 |
+
"<extra_id_89>",
|
| 887 |
+
"<extra_id_90>",
|
| 888 |
+
"<extra_id_91>",
|
| 889 |
+
"<extra_id_92>",
|
| 890 |
+
"<extra_id_93>",
|
| 891 |
+
"<extra_id_94>",
|
| 892 |
+
"<extra_id_95>"
|
| 893 |
+
],
|
| 894 |
+
"clean_up_tokenization_spaces": true,
|
| 895 |
+
"eos_token": "</s>",
|
| 896 |
+
"extra_ids": 96,
|
| 897 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 898 |
+
"pad_token": "<pad>",
|
| 899 |
+
"sp_model_kwargs": {},
|
| 900 |
+
"tokenizer_class": "T5Tokenizer",
|
| 901 |
+
"unk_token": "<unk>"
|
| 902 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1473 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 46.51162790697674,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 6000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 1.0,
|
| 13 |
+
"eval_bp": 0.4931128768931407,
|
| 14 |
+
"eval_counts": [
|
| 15 |
+
4260,
|
| 16 |
+
3433,
|
| 17 |
+
2947,
|
| 18 |
+
2467
|
| 19 |
+
],
|
| 20 |
+
"eval_loss": 0.1487731635570526,
|
| 21 |
+
"eval_precisions": [
|
| 22 |
+
90.31163875344498,
|
| 23 |
+
81.91362443330948,
|
| 24 |
+
80.40927694406548,
|
| 25 |
+
78.59190825103536
|
| 26 |
+
],
|
| 27 |
+
"eval_ref_len": 8052,
|
| 28 |
+
"eval_runtime": 17.1659,
|
| 29 |
+
"eval_samples_per_second": 30.642,
|
| 30 |
+
"eval_score": 40.77484395248702,
|
| 31 |
+
"eval_steps_per_second": 0.99,
|
| 32 |
+
"eval_sys_len": 4717,
|
| 33 |
+
"eval_totals": [
|
| 34 |
+
4717,
|
| 35 |
+
4191,
|
| 36 |
+
3665,
|
| 37 |
+
3139
|
| 38 |
+
],
|
| 39 |
+
"step": 129
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.0,
|
| 43 |
+
"eval_bp": 0.6247420950625343,
|
| 44 |
+
"eval_counts": [
|
| 45 |
+
4846,
|
| 46 |
+
4057,
|
| 47 |
+
3533,
|
| 48 |
+
3013
|
| 49 |
+
],
|
| 50 |
+
"eval_loss": 0.08066868782043457,
|
| 51 |
+
"eval_precisions": [
|
| 52 |
+
88.49525200876552,
|
| 53 |
+
81.95959595959596,
|
| 54 |
+
79.85985533453888,
|
| 55 |
+
77.29604925602874
|
| 56 |
+
],
|
| 57 |
+
"eval_ref_len": 8052,
|
| 58 |
+
"eval_runtime": 14.3341,
|
| 59 |
+
"eval_samples_per_second": 36.696,
|
| 60 |
+
"eval_score": 51.10367922657169,
|
| 61 |
+
"eval_steps_per_second": 1.186,
|
| 62 |
+
"eval_sys_len": 5476,
|
| 63 |
+
"eval_totals": [
|
| 64 |
+
5476,
|
| 65 |
+
4950,
|
| 66 |
+
4424,
|
| 67 |
+
3898
|
| 68 |
+
],
|
| 69 |
+
"step": 258
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 3.0,
|
| 73 |
+
"eval_bp": 0.5883063236903445,
|
| 74 |
+
"eval_counts": [
|
| 75 |
+
4902,
|
| 76 |
+
4207,
|
| 77 |
+
3677,
|
| 78 |
+
3156
|
| 79 |
+
],
|
| 80 |
+
"eval_loss": 0.054637473076581955,
|
| 81 |
+
"eval_precisions": [
|
| 82 |
+
93.1762022429196,
|
| 83 |
+
88.84899683210138,
|
| 84 |
+
87.36041815157995,
|
| 85 |
+
85.69101276133587
|
| 86 |
+
],
|
| 87 |
+
"eval_ref_len": 8052,
|
| 88 |
+
"eval_runtime": 14.8815,
|
| 89 |
+
"eval_samples_per_second": 35.346,
|
| 90 |
+
"eval_score": 52.19818413013667,
|
| 91 |
+
"eval_steps_per_second": 1.142,
|
| 92 |
+
"eval_sys_len": 5261,
|
| 93 |
+
"eval_totals": [
|
| 94 |
+
5261,
|
| 95 |
+
4735,
|
| 96 |
+
4209,
|
| 97 |
+
3683
|
| 98 |
+
],
|
| 99 |
+
"step": 387
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.88,
|
| 103 |
+
"learning_rate": 1.8449612403100777e-05,
|
| 104 |
+
"loss": 0.2341,
|
| 105 |
+
"step": 500
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 4.0,
|
| 109 |
+
"eval_bp": 0.5934338540178481,
|
| 110 |
+
"eval_counts": [
|
| 111 |
+
5055,
|
| 112 |
+
4418,
|
| 113 |
+
3890,
|
| 114 |
+
3363
|
| 115 |
+
],
|
| 116 |
+
"eval_loss": 0.03705175966024399,
|
| 117 |
+
"eval_precisions": [
|
| 118 |
+
95.53959553959554,
|
| 119 |
+
92.71773347324239,
|
| 120 |
+
91.76692616183063,
|
| 121 |
+
90.57366011311608
|
| 122 |
+
],
|
| 123 |
+
"eval_ref_len": 8052,
|
| 124 |
+
"eval_runtime": 14.3609,
|
| 125 |
+
"eval_samples_per_second": 36.627,
|
| 126 |
+
"eval_score": 54.97065288819127,
|
| 127 |
+
"eval_steps_per_second": 1.184,
|
| 128 |
+
"eval_sys_len": 5291,
|
| 129 |
+
"eval_totals": [
|
| 130 |
+
5291,
|
| 131 |
+
4765,
|
| 132 |
+
4239,
|
| 133 |
+
3713
|
| 134 |
+
],
|
| 135 |
+
"step": 516
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 5.0,
|
| 139 |
+
"eval_bp": 0.6060221334079605,
|
| 140 |
+
"eval_counts": [
|
| 141 |
+
5099,
|
| 142 |
+
4477,
|
| 143 |
+
3958,
|
| 144 |
+
3440
|
| 145 |
+
],
|
| 146 |
+
"eval_loss": 0.027972402051091194,
|
| 147 |
+
"eval_precisions": [
|
| 148 |
+
95.04193849021435,
|
| 149 |
+
92.51911551973548,
|
| 150 |
+
91.76907025272432,
|
| 151 |
+
90.83707420121468
|
| 152 |
+
],
|
| 153 |
+
"eval_ref_len": 8052,
|
| 154 |
+
"eval_runtime": 14.4334,
|
| 155 |
+
"eval_samples_per_second": 36.443,
|
| 156 |
+
"eval_score": 56.07445260593001,
|
| 157 |
+
"eval_steps_per_second": 1.178,
|
| 158 |
+
"eval_sys_len": 5365,
|
| 159 |
+
"eval_totals": [
|
| 160 |
+
5365,
|
| 161 |
+
4839,
|
| 162 |
+
4313,
|
| 163 |
+
3787
|
| 164 |
+
],
|
| 165 |
+
"step": 645
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 6.0,
|
| 169 |
+
"eval_bp": 0.6056830369973989,
|
| 170 |
+
"eval_counts": [
|
| 171 |
+
5166,
|
| 172 |
+
4567,
|
| 173 |
+
4044,
|
| 174 |
+
3524
|
| 175 |
+
],
|
| 176 |
+
"eval_loss": 0.023591596633195877,
|
| 177 |
+
"eval_precisions": [
|
| 178 |
+
96.32668282677606,
|
| 179 |
+
94.41802770312177,
|
| 180 |
+
93.80654140570633,
|
| 181 |
+
93.10435931307794
|
| 182 |
+
],
|
| 183 |
+
"eval_ref_len": 8052,
|
| 184 |
+
"eval_runtime": 14.4486,
|
| 185 |
+
"eval_samples_per_second": 36.405,
|
| 186 |
+
"eval_score": 57.18031955086815,
|
| 187 |
+
"eval_steps_per_second": 1.177,
|
| 188 |
+
"eval_sys_len": 5363,
|
| 189 |
+
"eval_totals": [
|
| 190 |
+
5363,
|
| 191 |
+
4837,
|
| 192 |
+
4311,
|
| 193 |
+
3785
|
| 194 |
+
],
|
| 195 |
+
"step": 774
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 7.0,
|
| 199 |
+
"eval_bp": 0.6017789050210954,
|
| 200 |
+
"eval_counts": [
|
| 201 |
+
5208,
|
| 202 |
+
4637,
|
| 203 |
+
4107,
|
| 204 |
+
3577
|
| 205 |
+
],
|
| 206 |
+
"eval_loss": 0.017074521631002426,
|
| 207 |
+
"eval_precisions": [
|
| 208 |
+
97.52808988764045,
|
| 209 |
+
96.32322393020357,
|
| 210 |
+
95.77891791044776,
|
| 211 |
+
95.08240297713982
|
| 212 |
+
],
|
| 213 |
+
"eval_ref_len": 8052,
|
| 214 |
+
"eval_runtime": 14.5209,
|
| 215 |
+
"eval_samples_per_second": 36.224,
|
| 216 |
+
"eval_score": 57.875487291552886,
|
| 217 |
+
"eval_steps_per_second": 1.171,
|
| 218 |
+
"eval_sys_len": 5340,
|
| 219 |
+
"eval_totals": [
|
| 220 |
+
5340,
|
| 221 |
+
4814,
|
| 222 |
+
4288,
|
| 223 |
+
3762
|
| 224 |
+
],
|
| 225 |
+
"step": 903
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 7.75,
|
| 229 |
+
"learning_rate": 1.689922480620155e-05,
|
| 230 |
+
"loss": 0.0502,
|
| 231 |
+
"step": 1000
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 8.0,
|
| 235 |
+
"eval_bp": 0.6116080889673632,
|
| 236 |
+
"eval_counts": [
|
| 237 |
+
5177,
|
| 238 |
+
4586,
|
| 239 |
+
4070,
|
| 240 |
+
3556
|
| 241 |
+
],
|
| 242 |
+
"eval_loss": 0.016343005001544952,
|
| 243 |
+
"eval_precisions": [
|
| 244 |
+
95.90589107076696,
|
| 245 |
+
94.12972085385879,
|
| 246 |
+
93.64933271974229,
|
| 247 |
+
93.08900523560209
|
| 248 |
+
],
|
| 249 |
+
"eval_ref_len": 8052,
|
| 250 |
+
"eval_runtime": 14.7374,
|
| 251 |
+
"eval_samples_per_second": 35.691,
|
| 252 |
+
"eval_score": 57.6059049756722,
|
| 253 |
+
"eval_steps_per_second": 1.154,
|
| 254 |
+
"eval_sys_len": 5398,
|
| 255 |
+
"eval_totals": [
|
| 256 |
+
5398,
|
| 257 |
+
4872,
|
| 258 |
+
4346,
|
| 259 |
+
3820
|
| 260 |
+
],
|
| 261 |
+
"step": 1032
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 9.0,
|
| 265 |
+
"eval_bp": 0.5990580978217462,
|
| 266 |
+
"eval_counts": [
|
| 267 |
+
5213,
|
| 268 |
+
4643,
|
| 269 |
+
4118,
|
| 270 |
+
3595
|
| 271 |
+
],
|
| 272 |
+
"eval_loss": 0.014382344670593739,
|
| 273 |
+
"eval_precisions": [
|
| 274 |
+
97.91510142749812,
|
| 275 |
+
96.76948728636933,
|
| 276 |
+
96.39513108614233,
|
| 277 |
+
95.96903363587828
|
| 278 |
+
],
|
| 279 |
+
"eval_ref_len": 8052,
|
| 280 |
+
"eval_runtime": 14.5245,
|
| 281 |
+
"eval_samples_per_second": 36.215,
|
| 282 |
+
"eval_score": 57.96455788198982,
|
| 283 |
+
"eval_steps_per_second": 1.17,
|
| 284 |
+
"eval_sys_len": 5324,
|
| 285 |
+
"eval_totals": [
|
| 286 |
+
5324,
|
| 287 |
+
4798,
|
| 288 |
+
4272,
|
| 289 |
+
3746
|
| 290 |
+
],
|
| 291 |
+
"step": 1161
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 10.0,
|
| 295 |
+
"eval_bp": 0.5983772718445015,
|
| 296 |
+
"eval_counts": [
|
| 297 |
+
5233,
|
| 298 |
+
4683,
|
| 299 |
+
4157,
|
| 300 |
+
3631
|
| 301 |
+
],
|
| 302 |
+
"eval_loss": 0.009321711026132107,
|
| 303 |
+
"eval_precisions": [
|
| 304 |
+
98.36466165413533,
|
| 305 |
+
97.6846057571965,
|
| 306 |
+
97.39925023430177,
|
| 307 |
+
97.03367183324426
|
| 308 |
+
],
|
| 309 |
+
"eval_ref_len": 8052,
|
| 310 |
+
"eval_runtime": 14.4914,
|
| 311 |
+
"eval_samples_per_second": 36.297,
|
| 312 |
+
"eval_score": 58.413189025316356,
|
| 313 |
+
"eval_steps_per_second": 1.173,
|
| 314 |
+
"eval_sys_len": 5320,
|
| 315 |
+
"eval_totals": [
|
| 316 |
+
5320,
|
| 317 |
+
4794,
|
| 318 |
+
4268,
|
| 319 |
+
3742
|
| 320 |
+
],
|
| 321 |
+
"step": 1290
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 11.0,
|
| 325 |
+
"eval_bp": 0.59309244908182,
|
| 326 |
+
"eval_counts": [
|
| 327 |
+
5230,
|
| 328 |
+
4686,
|
| 329 |
+
4155,
|
| 330 |
+
3625
|
| 331 |
+
],
|
| 332 |
+
"eval_loss": 0.008073785342276096,
|
| 333 |
+
"eval_precisions": [
|
| 334 |
+
98.88447721686519,
|
| 335 |
+
98.38337182448036,
|
| 336 |
+
98.06466839745103,
|
| 337 |
+
97.68256534626785
|
| 338 |
+
],
|
| 339 |
+
"eval_ref_len": 8052,
|
| 340 |
+
"eval_runtime": 14.7496,
|
| 341 |
+
"eval_samples_per_second": 35.662,
|
| 342 |
+
"eval_score": 58.272983799264466,
|
| 343 |
+
"eval_steps_per_second": 1.153,
|
| 344 |
+
"eval_sys_len": 5289,
|
| 345 |
+
"eval_totals": [
|
| 346 |
+
5289,
|
| 347 |
+
4763,
|
| 348 |
+
4237,
|
| 349 |
+
3711
|
| 350 |
+
],
|
| 351 |
+
"step": 1419
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 11.63,
|
| 355 |
+
"learning_rate": 1.5348837209302328e-05,
|
| 356 |
+
"loss": 0.0254,
|
| 357 |
+
"step": 1500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 12.0,
|
| 361 |
+
"eval_bp": 0.5936045333497635,
|
| 362 |
+
"eval_counts": [
|
| 363 |
+
5256,
|
| 364 |
+
4722,
|
| 365 |
+
4190,
|
| 366 |
+
3658
|
| 367 |
+
],
|
| 368 |
+
"eval_loss": 0.005859072785824537,
|
| 369 |
+
"eval_precisions": [
|
| 370 |
+
99.31972789115646,
|
| 371 |
+
99.07679395719681,
|
| 372 |
+
98.82075471698113,
|
| 373 |
+
98.49219170705439
|
| 374 |
+
],
|
| 375 |
+
"eval_ref_len": 8052,
|
| 376 |
+
"eval_runtime": 14.3696,
|
| 377 |
+
"eval_samples_per_second": 36.605,
|
| 378 |
+
"eval_score": 58.72345067822941,
|
| 379 |
+
"eval_steps_per_second": 1.183,
|
| 380 |
+
"eval_sys_len": 5292,
|
| 381 |
+
"eval_totals": [
|
| 382 |
+
5292,
|
| 383 |
+
4766,
|
| 384 |
+
4240,
|
| 385 |
+
3714
|
| 386 |
+
],
|
| 387 |
+
"step": 1548
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 13.0,
|
| 391 |
+
"eval_bp": 0.599228265363739,
|
| 392 |
+
"eval_counts": [
|
| 393 |
+
5238,
|
| 394 |
+
4695,
|
| 395 |
+
4172,
|
| 396 |
+
3649
|
| 397 |
+
],
|
| 398 |
+
"eval_loss": 0.004798234440386295,
|
| 399 |
+
"eval_precisions": [
|
| 400 |
+
98.36619718309859,
|
| 401 |
+
97.83288185038549,
|
| 402 |
+
97.63632108588814,
|
| 403 |
+
97.38457432612756
|
| 404 |
+
],
|
| 405 |
+
"eval_ref_len": 8052,
|
| 406 |
+
"eval_runtime": 14.4038,
|
| 407 |
+
"eval_samples_per_second": 36.518,
|
| 408 |
+
"eval_score": 58.607118219599144,
|
| 409 |
+
"eval_steps_per_second": 1.18,
|
| 410 |
+
"eval_sys_len": 5325,
|
| 411 |
+
"eval_totals": [
|
| 412 |
+
5325,
|
| 413 |
+
4799,
|
| 414 |
+
4273,
|
| 415 |
+
3747
|
| 416 |
+
],
|
| 417 |
+
"step": 1677
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 14.0,
|
| 421 |
+
"eval_bp": 0.5947988563367582,
|
| 422 |
+
"eval_counts": [
|
| 423 |
+
5250,
|
| 424 |
+
4716,
|
| 425 |
+
4190,
|
| 426 |
+
3664
|
| 427 |
+
],
|
| 428 |
+
"eval_loss": 0.0038494656328111887,
|
| 429 |
+
"eval_precisions": [
|
| 430 |
+
99.07529722589167,
|
| 431 |
+
98.80578252671276,
|
| 432 |
+
98.65787614786909,
|
| 433 |
+
98.4681537221177
|
| 434 |
+
],
|
| 435 |
+
"eval_ref_len": 8052,
|
| 436 |
+
"eval_runtime": 14.4328,
|
| 437 |
+
"eval_samples_per_second": 36.445,
|
| 438 |
+
"eval_score": 58.7372961131176,
|
| 439 |
+
"eval_steps_per_second": 1.178,
|
| 440 |
+
"eval_sys_len": 5299,
|
| 441 |
+
"eval_totals": [
|
| 442 |
+
5299,
|
| 443 |
+
4773,
|
| 444 |
+
4247,
|
| 445 |
+
3721
|
| 446 |
+
],
|
| 447 |
+
"step": 1806
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 15.0,
|
| 451 |
+
"eval_bp": 0.5980367654366966,
|
| 452 |
+
"eval_counts": [
|
| 453 |
+
5241,
|
| 454 |
+
4695,
|
| 455 |
+
4171,
|
| 456 |
+
3647
|
| 457 |
+
],
|
| 458 |
+
"eval_loss": 0.004494406748563051,
|
| 459 |
+
"eval_precisions": [
|
| 460 |
+
98.55208725084618,
|
| 461 |
+
97.97579298831386,
|
| 462 |
+
97.77308954524145,
|
| 463 |
+
97.51336898395722
|
| 464 |
+
],
|
| 465 |
+
"eval_ref_len": 8052,
|
| 466 |
+
"eval_runtime": 14.4623,
|
| 467 |
+
"eval_samples_per_second": 36.371,
|
| 468 |
+
"eval_score": 58.579399085547706,
|
| 469 |
+
"eval_steps_per_second": 1.175,
|
| 470 |
+
"eval_sys_len": 5318,
|
| 471 |
+
"eval_totals": [
|
| 472 |
+
5318,
|
| 473 |
+
4792,
|
| 474 |
+
4266,
|
| 475 |
+
3740
|
| 476 |
+
],
|
| 477 |
+
"step": 1935
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 15.5,
|
| 481 |
+
"learning_rate": 1.3798449612403102e-05,
|
| 482 |
+
"loss": 0.0149,
|
| 483 |
+
"step": 2000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 16.0,
|
| 487 |
+
"eval_bp": 0.5953104771654304,
|
| 488 |
+
"eval_counts": [
|
| 489 |
+
5251,
|
| 490 |
+
4717,
|
| 491 |
+
4192,
|
| 492 |
+
3667
|
| 493 |
+
],
|
| 494 |
+
"eval_loss": 0.002652836265042424,
|
| 495 |
+
"eval_precisions": [
|
| 496 |
+
99.03809883062995,
|
| 497 |
+
98.76465661641541,
|
| 498 |
+
98.63529411764706,
|
| 499 |
+
98.46938775510205
|
| 500 |
+
],
|
| 501 |
+
"eval_ref_len": 8052,
|
| 502 |
+
"eval_runtime": 14.3908,
|
| 503 |
+
"eval_samples_per_second": 36.551,
|
| 504 |
+
"eval_score": 58.77300342254795,
|
| 505 |
+
"eval_steps_per_second": 1.181,
|
| 506 |
+
"eval_sys_len": 5302,
|
| 507 |
+
"eval_totals": [
|
| 508 |
+
5302,
|
| 509 |
+
4776,
|
| 510 |
+
4250,
|
| 511 |
+
3724
|
| 512 |
+
],
|
| 513 |
+
"step": 2064
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 17.0,
|
| 517 |
+
"eval_bp": 0.5958219586747581,
|
| 518 |
+
"eval_counts": [
|
| 519 |
+
5248,
|
| 520 |
+
4711,
|
| 521 |
+
4182,
|
| 522 |
+
3653
|
| 523 |
+
],
|
| 524 |
+
"eval_loss": 0.002865839982405305,
|
| 525 |
+
"eval_precisions": [
|
| 526 |
+
98.92554194156456,
|
| 527 |
+
98.57710818162795,
|
| 528 |
+
98.33059017164355,
|
| 529 |
+
98.0144888650389
|
| 530 |
+
],
|
| 531 |
+
"eval_ref_len": 8052,
|
| 532 |
+
"eval_runtime": 14.4421,
|
| 533 |
+
"eval_samples_per_second": 36.421,
|
| 534 |
+
"eval_score": 58.665444298085596,
|
| 535 |
+
"eval_steps_per_second": 1.177,
|
| 536 |
+
"eval_sys_len": 5305,
|
| 537 |
+
"eval_totals": [
|
| 538 |
+
5305,
|
| 539 |
+
4779,
|
| 540 |
+
4253,
|
| 541 |
+
3727
|
| 542 |
+
],
|
| 543 |
+
"step": 2193
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 18.0,
|
| 547 |
+
"eval_bp": 0.5937751972509898,
|
| 548 |
+
"eval_counts": [
|
| 549 |
+
5261,
|
| 550 |
+
4727,
|
| 551 |
+
4202,
|
| 552 |
+
3677
|
| 553 |
+
],
|
| 554 |
+
"eval_loss": 0.002401716075837612,
|
| 555 |
+
"eval_precisions": [
|
| 556 |
+
99.39542792367277,
|
| 557 |
+
99.16089783931194,
|
| 558 |
+
99.0804055647253,
|
| 559 |
+
98.9771197846568
|
| 560 |
+
],
|
| 561 |
+
"eval_ref_len": 8052,
|
| 562 |
+
"eval_runtime": 14.3995,
|
| 563 |
+
"eval_samples_per_second": 36.529,
|
| 564 |
+
"eval_score": 58.87479582058116,
|
| 565 |
+
"eval_steps_per_second": 1.181,
|
| 566 |
+
"eval_sys_len": 5293,
|
| 567 |
+
"eval_totals": [
|
| 568 |
+
5293,
|
| 569 |
+
4767,
|
| 570 |
+
4241,
|
| 571 |
+
3715
|
| 572 |
+
],
|
| 573 |
+
"step": 2322
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 19.0,
|
| 577 |
+
"eval_bp": 0.59087181575089,
|
| 578 |
+
"eval_counts": [
|
| 579 |
+
5269,
|
| 580 |
+
4743,
|
| 581 |
+
4217,
|
| 582 |
+
3691
|
| 583 |
+
],
|
| 584 |
+
"eval_loss": 0.002938783960416913,
|
| 585 |
+
"eval_precisions": [
|
| 586 |
+
99.86732373009856,
|
| 587 |
+
99.85263157894737,
|
| 588 |
+
99.8342803030303,
|
| 589 |
+
99.81070849107626
|
| 590 |
+
],
|
| 591 |
+
"eval_ref_len": 8052,
|
| 592 |
+
"eval_runtime": 14.5031,
|
| 593 |
+
"eval_samples_per_second": 36.268,
|
| 594 |
+
"eval_score": 58.99337109259839,
|
| 595 |
+
"eval_steps_per_second": 1.172,
|
| 596 |
+
"eval_sys_len": 5276,
|
| 597 |
+
"eval_totals": [
|
| 598 |
+
5276,
|
| 599 |
+
4750,
|
| 600 |
+
4224,
|
| 601 |
+
3698
|
| 602 |
+
],
|
| 603 |
+
"step": 2451
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 19.38,
|
| 607 |
+
"learning_rate": 1.2248062015503876e-05,
|
| 608 |
+
"loss": 0.0093,
|
| 609 |
+
"step": 2500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 20.0,
|
| 613 |
+
"eval_bp": 0.592580226071992,
|
| 614 |
+
"eval_counts": [
|
| 615 |
+
5264,
|
| 616 |
+
4736,
|
| 617 |
+
4211,
|
| 618 |
+
3686
|
| 619 |
+
],
|
| 620 |
+
"eval_loss": 0.0010500611970201135,
|
| 621 |
+
"eval_precisions": [
|
| 622 |
+
99.58380628074158,
|
| 623 |
+
99.49579831932773,
|
| 624 |
+
99.45677846008502,
|
| 625 |
+
99.4066882416397
|
| 626 |
+
],
|
| 627 |
+
"eval_ref_len": 8052,
|
| 628 |
+
"eval_runtime": 14.451,
|
| 629 |
+
"eval_samples_per_second": 36.399,
|
| 630 |
+
"eval_score": 58.95328627800463,
|
| 631 |
+
"eval_steps_per_second": 1.176,
|
| 632 |
+
"eval_sys_len": 5286,
|
| 633 |
+
"eval_totals": [
|
| 634 |
+
5286,
|
| 635 |
+
4760,
|
| 636 |
+
4234,
|
| 637 |
+
3708
|
| 638 |
+
],
|
| 639 |
+
"step": 2580
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 21.0,
|
| 643 |
+
"eval_bp": 0.59087181575089,
|
| 644 |
+
"eval_counts": [
|
| 645 |
+
5269,
|
| 646 |
+
4743,
|
| 647 |
+
4217,
|
| 648 |
+
3691
|
| 649 |
+
],
|
| 650 |
+
"eval_loss": 0.0013304909225553274,
|
| 651 |
+
"eval_precisions": [
|
| 652 |
+
99.86732373009856,
|
| 653 |
+
99.85263157894737,
|
| 654 |
+
99.8342803030303,
|
| 655 |
+
99.81070849107626
|
| 656 |
+
],
|
| 657 |
+
"eval_ref_len": 8052,
|
| 658 |
+
"eval_runtime": 14.3918,
|
| 659 |
+
"eval_samples_per_second": 36.549,
|
| 660 |
+
"eval_score": 58.99337109259839,
|
| 661 |
+
"eval_steps_per_second": 1.181,
|
| 662 |
+
"eval_sys_len": 5276,
|
| 663 |
+
"eval_totals": [
|
| 664 |
+
5276,
|
| 665 |
+
4750,
|
| 666 |
+
4224,
|
| 667 |
+
3698
|
| 668 |
+
],
|
| 669 |
+
"step": 2709
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 22.0,
|
| 673 |
+
"eval_bp": 0.59087181575089,
|
| 674 |
+
"eval_counts": [
|
| 675 |
+
5269,
|
| 676 |
+
4741,
|
| 677 |
+
4213,
|
| 678 |
+
3685
|
| 679 |
+
],
|
| 680 |
+
"eval_loss": 0.0005288496031425893,
|
| 681 |
+
"eval_precisions": [
|
| 682 |
+
99.86732373009856,
|
| 683 |
+
99.81052631578947,
|
| 684 |
+
99.73958333333333,
|
| 685 |
+
99.64845862628448
|
| 686 |
+
],
|
| 687 |
+
"eval_ref_len": 8052,
|
| 688 |
+
"eval_runtime": 14.7249,
|
| 689 |
+
"eval_samples_per_second": 35.722,
|
| 690 |
+
"eval_score": 58.94917723823275,
|
| 691 |
+
"eval_steps_per_second": 1.155,
|
| 692 |
+
"eval_sys_len": 5276,
|
| 693 |
+
"eval_totals": [
|
| 694 |
+
5276,
|
| 695 |
+
4750,
|
| 696 |
+
4224,
|
| 697 |
+
3698
|
| 698 |
+
],
|
| 699 |
+
"step": 2838
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 23.0,
|
| 703 |
+
"eval_bp": 0.5937751972509898,
|
| 704 |
+
"eval_counts": [
|
| 705 |
+
5262,
|
| 706 |
+
4729,
|
| 707 |
+
4205,
|
| 708 |
+
3681
|
| 709 |
+
],
|
| 710 |
+
"eval_loss": 0.0014174942625686526,
|
| 711 |
+
"eval_precisions": [
|
| 712 |
+
99.414320801058,
|
| 713 |
+
99.20285294734634,
|
| 714 |
+
99.15114359820797,
|
| 715 |
+
99.08479138627187
|
| 716 |
+
],
|
| 717 |
+
"eval_ref_len": 8052,
|
| 718 |
+
"eval_runtime": 14.4608,
|
| 719 |
+
"eval_samples_per_second": 36.374,
|
| 720 |
+
"eval_score": 58.91033770144402,
|
| 721 |
+
"eval_steps_per_second": 1.176,
|
| 722 |
+
"eval_sys_len": 5293,
|
| 723 |
+
"eval_totals": [
|
| 724 |
+
5293,
|
| 725 |
+
4767,
|
| 726 |
+
4241,
|
| 727 |
+
3715
|
| 728 |
+
],
|
| 729 |
+
"step": 2967
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 23.26,
|
| 733 |
+
"learning_rate": 1.0697674418604651e-05,
|
| 734 |
+
"loss": 0.0067,
|
| 735 |
+
"step": 3000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 24.0,
|
| 739 |
+
"eval_bp": 0.592580226071992,
|
| 740 |
+
"eval_counts": [
|
| 741 |
+
5265,
|
| 742 |
+
4736,
|
| 743 |
+
4211,
|
| 744 |
+
3686
|
| 745 |
+
],
|
| 746 |
+
"eval_loss": 0.0005781701183877885,
|
| 747 |
+
"eval_precisions": [
|
| 748 |
+
99.60272417707151,
|
| 749 |
+
99.49579831932773,
|
| 750 |
+
99.45677846008502,
|
| 751 |
+
99.4066882416397
|
| 752 |
+
],
|
| 753 |
+
"eval_ref_len": 8052,
|
| 754 |
+
"eval_runtime": 14.6512,
|
| 755 |
+
"eval_samples_per_second": 35.901,
|
| 756 |
+
"eval_score": 58.956085911695446,
|
| 757 |
+
"eval_steps_per_second": 1.16,
|
| 758 |
+
"eval_sys_len": 5286,
|
| 759 |
+
"eval_totals": [
|
| 760 |
+
5286,
|
| 761 |
+
4760,
|
| 762 |
+
4234,
|
| 763 |
+
3708
|
| 764 |
+
],
|
| 765 |
+
"step": 3096
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 25.0,
|
| 769 |
+
"eval_bp": 0.59087181575089,
|
| 770 |
+
"eval_counts": [
|
| 771 |
+
5269,
|
| 772 |
+
4743,
|
| 773 |
+
4216,
|
| 774 |
+
3690
|
| 775 |
+
],
|
| 776 |
+
"eval_loss": 0.0011985599994659424,
|
| 777 |
+
"eval_precisions": [
|
| 778 |
+
99.86732373009856,
|
| 779 |
+
99.85263157894737,
|
| 780 |
+
99.81060606060606,
|
| 781 |
+
99.7836668469443
|
| 782 |
+
],
|
| 783 |
+
"eval_ref_len": 8052,
|
| 784 |
+
"eval_runtime": 14.8071,
|
| 785 |
+
"eval_samples_per_second": 35.524,
|
| 786 |
+
"eval_score": 58.98587750022716,
|
| 787 |
+
"eval_steps_per_second": 1.148,
|
| 788 |
+
"eval_sys_len": 5276,
|
| 789 |
+
"eval_totals": [
|
| 790 |
+
5276,
|
| 791 |
+
4750,
|
| 792 |
+
4224,
|
| 793 |
+
3698
|
| 794 |
+
],
|
| 795 |
+
"step": 3225
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 26.0,
|
| 799 |
+
"eval_bp": 0.5922386670531977,
|
| 800 |
+
"eval_counts": [
|
| 801 |
+
5266,
|
| 802 |
+
4736,
|
| 803 |
+
4211,
|
| 804 |
+
3686
|
| 805 |
+
],
|
| 806 |
+
"eval_loss": 0.0008205975755117834,
|
| 807 |
+
"eval_precisions": [
|
| 808 |
+
99.65934897804694,
|
| 809 |
+
99.53762084909626,
|
| 810 |
+
99.50378071833649,
|
| 811 |
+
99.46033459255261
|
| 812 |
+
],
|
| 813 |
+
"eval_ref_len": 8052,
|
| 814 |
+
"eval_runtime": 14.5488,
|
| 815 |
+
"eval_samples_per_second": 36.154,
|
| 816 |
+
"eval_score": 58.951581295937814,
|
| 817 |
+
"eval_steps_per_second": 1.168,
|
| 818 |
+
"eval_sys_len": 5284,
|
| 819 |
+
"eval_totals": [
|
| 820 |
+
5284,
|
| 821 |
+
4758,
|
| 822 |
+
4232,
|
| 823 |
+
3706
|
| 824 |
+
],
|
| 825 |
+
"step": 3354
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 27.0,
|
| 829 |
+
"eval_bp": 0.59087181575089,
|
| 830 |
+
"eval_counts": [
|
| 831 |
+
5269,
|
| 832 |
+
4743,
|
| 833 |
+
4217,
|
| 834 |
+
3691
|
| 835 |
+
],
|
| 836 |
+
"eval_loss": 0.0003399839624762535,
|
| 837 |
+
"eval_precisions": [
|
| 838 |
+
99.86732373009856,
|
| 839 |
+
99.85263157894737,
|
| 840 |
+
99.8342803030303,
|
| 841 |
+
99.81070849107626
|
| 842 |
+
],
|
| 843 |
+
"eval_ref_len": 8052,
|
| 844 |
+
"eval_runtime": 14.5408,
|
| 845 |
+
"eval_samples_per_second": 36.174,
|
| 846 |
+
"eval_score": 58.99337109259839,
|
| 847 |
+
"eval_steps_per_second": 1.169,
|
| 848 |
+
"eval_sys_len": 5276,
|
| 849 |
+
"eval_totals": [
|
| 850 |
+
5276,
|
| 851 |
+
4750,
|
| 852 |
+
4224,
|
| 853 |
+
3698
|
| 854 |
+
],
|
| 855 |
+
"step": 3483
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 27.13,
|
| 859 |
+
"learning_rate": 9.147286821705427e-06,
|
| 860 |
+
"loss": 0.005,
|
| 861 |
+
"step": 3500
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 28.0,
|
| 865 |
+
"eval_bp": 0.59087181575089,
|
| 866 |
+
"eval_counts": [
|
| 867 |
+
5269,
|
| 868 |
+
4743,
|
| 869 |
+
4217,
|
| 870 |
+
3691
|
| 871 |
+
],
|
| 872 |
+
"eval_loss": 0.00024222489446401596,
|
| 873 |
+
"eval_precisions": [
|
| 874 |
+
99.86732373009856,
|
| 875 |
+
99.85263157894737,
|
| 876 |
+
99.8342803030303,
|
| 877 |
+
99.81070849107626
|
| 878 |
+
],
|
| 879 |
+
"eval_ref_len": 8052,
|
| 880 |
+
"eval_runtime": 14.8483,
|
| 881 |
+
"eval_samples_per_second": 35.425,
|
| 882 |
+
"eval_score": 58.99337109259839,
|
| 883 |
+
"eval_steps_per_second": 1.145,
|
| 884 |
+
"eval_sys_len": 5276,
|
| 885 |
+
"eval_totals": [
|
| 886 |
+
5276,
|
| 887 |
+
4750,
|
| 888 |
+
4224,
|
| 889 |
+
3698
|
| 890 |
+
],
|
| 891 |
+
"step": 3612
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 29.0,
|
| 895 |
+
"eval_bp": 0.59087181575089,
|
| 896 |
+
"eval_counts": [
|
| 897 |
+
5269,
|
| 898 |
+
4743,
|
| 899 |
+
4217,
|
| 900 |
+
3691
|
| 901 |
+
],
|
| 902 |
+
"eval_loss": 0.0008496907539665699,
|
| 903 |
+
"eval_precisions": [
|
| 904 |
+
99.86732373009856,
|
| 905 |
+
99.85263157894737,
|
| 906 |
+
99.8342803030303,
|
| 907 |
+
99.81070849107626
|
| 908 |
+
],
|
| 909 |
+
"eval_ref_len": 8052,
|
| 910 |
+
"eval_runtime": 14.469,
|
| 911 |
+
"eval_samples_per_second": 36.354,
|
| 912 |
+
"eval_score": 58.99337109259839,
|
| 913 |
+
"eval_steps_per_second": 1.175,
|
| 914 |
+
"eval_sys_len": 5276,
|
| 915 |
+
"eval_totals": [
|
| 916 |
+
5276,
|
| 917 |
+
4750,
|
| 918 |
+
4224,
|
| 919 |
+
3698
|
| 920 |
+
],
|
| 921 |
+
"step": 3741
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 30.0,
|
| 925 |
+
"eval_bp": 0.59087181575089,
|
| 926 |
+
"eval_counts": [
|
| 927 |
+
5269,
|
| 928 |
+
4743,
|
| 929 |
+
4217,
|
| 930 |
+
3691
|
| 931 |
+
],
|
| 932 |
+
"eval_loss": 0.00035507275606505573,
|
| 933 |
+
"eval_precisions": [
|
| 934 |
+
99.86732373009856,
|
| 935 |
+
99.85263157894737,
|
| 936 |
+
99.8342803030303,
|
| 937 |
+
99.81070849107626
|
| 938 |
+
],
|
| 939 |
+
"eval_ref_len": 8052,
|
| 940 |
+
"eval_runtime": 14.3448,
|
| 941 |
+
"eval_samples_per_second": 36.668,
|
| 942 |
+
"eval_score": 58.99337109259839,
|
| 943 |
+
"eval_steps_per_second": 1.185,
|
| 944 |
+
"eval_sys_len": 5276,
|
| 945 |
+
"eval_totals": [
|
| 946 |
+
5276,
|
| 947 |
+
4750,
|
| 948 |
+
4224,
|
| 949 |
+
3698
|
| 950 |
+
],
|
| 951 |
+
"step": 3870
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 31.0,
|
| 955 |
+
"eval_bp": 0.59087181575089,
|
| 956 |
+
"eval_counts": [
|
| 957 |
+
5269,
|
| 958 |
+
4743,
|
| 959 |
+
4217,
|
| 960 |
+
3691
|
| 961 |
+
],
|
| 962 |
+
"eval_loss": 0.00018533450202085078,
|
| 963 |
+
"eval_precisions": [
|
| 964 |
+
99.86732373009856,
|
| 965 |
+
99.85263157894737,
|
| 966 |
+
99.8342803030303,
|
| 967 |
+
99.81070849107626
|
| 968 |
+
],
|
| 969 |
+
"eval_ref_len": 8052,
|
| 970 |
+
"eval_runtime": 14.6683,
|
| 971 |
+
"eval_samples_per_second": 35.86,
|
| 972 |
+
"eval_score": 58.99337109259839,
|
| 973 |
+
"eval_steps_per_second": 1.159,
|
| 974 |
+
"eval_sys_len": 5276,
|
| 975 |
+
"eval_totals": [
|
| 976 |
+
5276,
|
| 977 |
+
4750,
|
| 978 |
+
4224,
|
| 979 |
+
3698
|
| 980 |
+
],
|
| 981 |
+
"step": 3999
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 31.01,
|
| 985 |
+
"learning_rate": 7.596899224806202e-06,
|
| 986 |
+
"loss": 0.0037,
|
| 987 |
+
"step": 4000
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 32.0,
|
| 991 |
+
"eval_bp": 0.59087181575089,
|
| 992 |
+
"eval_counts": [
|
| 993 |
+
5269,
|
| 994 |
+
4743,
|
| 995 |
+
4217,
|
| 996 |
+
3691
|
| 997 |
+
],
|
| 998 |
+
"eval_loss": 0.00033950418583117425,
|
| 999 |
+
"eval_precisions": [
|
| 1000 |
+
99.86732373009856,
|
| 1001 |
+
99.85263157894737,
|
| 1002 |
+
99.8342803030303,
|
| 1003 |
+
99.81070849107626
|
| 1004 |
+
],
|
| 1005 |
+
"eval_ref_len": 8052,
|
| 1006 |
+
"eval_runtime": 14.3289,
|
| 1007 |
+
"eval_samples_per_second": 36.709,
|
| 1008 |
+
"eval_score": 58.99337109259839,
|
| 1009 |
+
"eval_steps_per_second": 1.186,
|
| 1010 |
+
"eval_sys_len": 5276,
|
| 1011 |
+
"eval_totals": [
|
| 1012 |
+
5276,
|
| 1013 |
+
4750,
|
| 1014 |
+
4224,
|
| 1015 |
+
3698
|
| 1016 |
+
],
|
| 1017 |
+
"step": 4128
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 33.0,
|
| 1021 |
+
"eval_bp": 0.59087181575089,
|
| 1022 |
+
"eval_counts": [
|
| 1023 |
+
5269,
|
| 1024 |
+
4743,
|
| 1025 |
+
4217,
|
| 1026 |
+
3691
|
| 1027 |
+
],
|
| 1028 |
+
"eval_loss": 0.0002313230506842956,
|
| 1029 |
+
"eval_precisions": [
|
| 1030 |
+
99.86732373009856,
|
| 1031 |
+
99.85263157894737,
|
| 1032 |
+
99.8342803030303,
|
| 1033 |
+
99.81070849107626
|
| 1034 |
+
],
|
| 1035 |
+
"eval_ref_len": 8052,
|
| 1036 |
+
"eval_runtime": 14.3892,
|
| 1037 |
+
"eval_samples_per_second": 36.555,
|
| 1038 |
+
"eval_score": 58.99337109259839,
|
| 1039 |
+
"eval_steps_per_second": 1.181,
|
| 1040 |
+
"eval_sys_len": 5276,
|
| 1041 |
+
"eval_totals": [
|
| 1042 |
+
5276,
|
| 1043 |
+
4750,
|
| 1044 |
+
4224,
|
| 1045 |
+
3698
|
| 1046 |
+
],
|
| 1047 |
+
"step": 4257
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 34.0,
|
| 1051 |
+
"eval_bp": 0.59087181575089,
|
| 1052 |
+
"eval_counts": [
|
| 1053 |
+
5269,
|
| 1054 |
+
4743,
|
| 1055 |
+
4217,
|
| 1056 |
+
3691
|
| 1057 |
+
],
|
| 1058 |
+
"eval_loss": 5.81590757064987e-05,
|
| 1059 |
+
"eval_precisions": [
|
| 1060 |
+
99.86732373009856,
|
| 1061 |
+
99.85263157894737,
|
| 1062 |
+
99.8342803030303,
|
| 1063 |
+
99.81070849107626
|
| 1064 |
+
],
|
| 1065 |
+
"eval_ref_len": 8052,
|
| 1066 |
+
"eval_runtime": 14.6979,
|
| 1067 |
+
"eval_samples_per_second": 35.787,
|
| 1068 |
+
"eval_score": 58.99337109259839,
|
| 1069 |
+
"eval_steps_per_second": 1.157,
|
| 1070 |
+
"eval_sys_len": 5276,
|
| 1071 |
+
"eval_totals": [
|
| 1072 |
+
5276,
|
| 1073 |
+
4750,
|
| 1074 |
+
4224,
|
| 1075 |
+
3698
|
| 1076 |
+
],
|
| 1077 |
+
"step": 4386
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 34.88,
|
| 1081 |
+
"learning_rate": 6.046511627906977e-06,
|
| 1082 |
+
"loss": 0.0027,
|
| 1083 |
+
"step": 4500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 35.0,
|
| 1087 |
+
"eval_bp": 0.59087181575089,
|
| 1088 |
+
"eval_counts": [
|
| 1089 |
+
5269,
|
| 1090 |
+
4743,
|
| 1091 |
+
4217,
|
| 1092 |
+
3691
|
| 1093 |
+
],
|
| 1094 |
+
"eval_loss": 1.8420163542032242e-05,
|
| 1095 |
+
"eval_precisions": [
|
| 1096 |
+
99.86732373009856,
|
| 1097 |
+
99.85263157894737,
|
| 1098 |
+
99.8342803030303,
|
| 1099 |
+
99.81070849107626
|
| 1100 |
+
],
|
| 1101 |
+
"eval_ref_len": 8052,
|
| 1102 |
+
"eval_runtime": 14.6994,
|
| 1103 |
+
"eval_samples_per_second": 35.784,
|
| 1104 |
+
"eval_score": 58.99337109259839,
|
| 1105 |
+
"eval_steps_per_second": 1.157,
|
| 1106 |
+
"eval_sys_len": 5276,
|
| 1107 |
+
"eval_totals": [
|
| 1108 |
+
5276,
|
| 1109 |
+
4750,
|
| 1110 |
+
4224,
|
| 1111 |
+
3698
|
| 1112 |
+
],
|
| 1113 |
+
"step": 4515
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 36.0,
|
| 1117 |
+
"eval_bp": 0.59087181575089,
|
| 1118 |
+
"eval_counts": [
|
| 1119 |
+
5269,
|
| 1120 |
+
4743,
|
| 1121 |
+
4217,
|
| 1122 |
+
3691
|
| 1123 |
+
],
|
| 1124 |
+
"eval_loss": 4.58808644907549e-05,
|
| 1125 |
+
"eval_precisions": [
|
| 1126 |
+
99.86732373009856,
|
| 1127 |
+
99.85263157894737,
|
| 1128 |
+
99.8342803030303,
|
| 1129 |
+
99.81070849107626
|
| 1130 |
+
],
|
| 1131 |
+
"eval_ref_len": 8052,
|
| 1132 |
+
"eval_runtime": 14.4112,
|
| 1133 |
+
"eval_samples_per_second": 36.5,
|
| 1134 |
+
"eval_score": 58.99337109259839,
|
| 1135 |
+
"eval_steps_per_second": 1.18,
|
| 1136 |
+
"eval_sys_len": 5276,
|
| 1137 |
+
"eval_totals": [
|
| 1138 |
+
5276,
|
| 1139 |
+
4750,
|
| 1140 |
+
4224,
|
| 1141 |
+
3698
|
| 1142 |
+
],
|
| 1143 |
+
"step": 4644
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 37.0,
|
| 1147 |
+
"eval_bp": 0.59087181575089,
|
| 1148 |
+
"eval_counts": [
|
| 1149 |
+
5269,
|
| 1150 |
+
4743,
|
| 1151 |
+
4217,
|
| 1152 |
+
3691
|
| 1153 |
+
],
|
| 1154 |
+
"eval_loss": 2.0950477846781723e-05,
|
| 1155 |
+
"eval_precisions": [
|
| 1156 |
+
99.86732373009856,
|
| 1157 |
+
99.85263157894737,
|
| 1158 |
+
99.8342803030303,
|
| 1159 |
+
99.81070849107626
|
| 1160 |
+
],
|
| 1161 |
+
"eval_ref_len": 8052,
|
| 1162 |
+
"eval_runtime": 14.7823,
|
| 1163 |
+
"eval_samples_per_second": 35.583,
|
| 1164 |
+
"eval_score": 58.99337109259839,
|
| 1165 |
+
"eval_steps_per_second": 1.15,
|
| 1166 |
+
"eval_sys_len": 5276,
|
| 1167 |
+
"eval_totals": [
|
| 1168 |
+
5276,
|
| 1169 |
+
4750,
|
| 1170 |
+
4224,
|
| 1171 |
+
3698
|
| 1172 |
+
],
|
| 1173 |
+
"step": 4773
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 38.0,
|
| 1177 |
+
"eval_bp": 0.59087181575089,
|
| 1178 |
+
"eval_counts": [
|
| 1179 |
+
5269,
|
| 1180 |
+
4743,
|
| 1181 |
+
4217,
|
| 1182 |
+
3691
|
| 1183 |
+
],
|
| 1184 |
+
"eval_loss": 4.088176865479909e-05,
|
| 1185 |
+
"eval_precisions": [
|
| 1186 |
+
99.86732373009856,
|
| 1187 |
+
99.85263157894737,
|
| 1188 |
+
99.8342803030303,
|
| 1189 |
+
99.81070849107626
|
| 1190 |
+
],
|
| 1191 |
+
"eval_ref_len": 8052,
|
| 1192 |
+
"eval_runtime": 14.5206,
|
| 1193 |
+
"eval_samples_per_second": 36.224,
|
| 1194 |
+
"eval_score": 58.99337109259839,
|
| 1195 |
+
"eval_steps_per_second": 1.171,
|
| 1196 |
+
"eval_sys_len": 5276,
|
| 1197 |
+
"eval_totals": [
|
| 1198 |
+
5276,
|
| 1199 |
+
4750,
|
| 1200 |
+
4224,
|
| 1201 |
+
3698
|
| 1202 |
+
],
|
| 1203 |
+
"step": 4902
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 38.76,
|
| 1207 |
+
"learning_rate": 4.4961240310077525e-06,
|
| 1208 |
+
"loss": 0.0019,
|
| 1209 |
+
"step": 5000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 39.0,
|
| 1213 |
+
"eval_bp": 0.59087181575089,
|
| 1214 |
+
"eval_counts": [
|
| 1215 |
+
5269,
|
| 1216 |
+
4743,
|
| 1217 |
+
4217,
|
| 1218 |
+
3691
|
| 1219 |
+
],
|
| 1220 |
+
"eval_loss": 4.002406421932392e-05,
|
| 1221 |
+
"eval_precisions": [
|
| 1222 |
+
99.86732373009856,
|
| 1223 |
+
99.85263157894737,
|
| 1224 |
+
99.8342803030303,
|
| 1225 |
+
99.81070849107626
|
| 1226 |
+
],
|
| 1227 |
+
"eval_ref_len": 8052,
|
| 1228 |
+
"eval_runtime": 14.4395,
|
| 1229 |
+
"eval_samples_per_second": 36.428,
|
| 1230 |
+
"eval_score": 58.99337109259839,
|
| 1231 |
+
"eval_steps_per_second": 1.177,
|
| 1232 |
+
"eval_sys_len": 5276,
|
| 1233 |
+
"eval_totals": [
|
| 1234 |
+
5276,
|
| 1235 |
+
4750,
|
| 1236 |
+
4224,
|
| 1237 |
+
3698
|
| 1238 |
+
],
|
| 1239 |
+
"step": 5031
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 40.0,
|
| 1243 |
+
"eval_bp": 0.59087181575089,
|
| 1244 |
+
"eval_counts": [
|
| 1245 |
+
5269,
|
| 1246 |
+
4743,
|
| 1247 |
+
4217,
|
| 1248 |
+
3691
|
| 1249 |
+
],
|
| 1250 |
+
"eval_loss": 8.237251313403249e-05,
|
| 1251 |
+
"eval_precisions": [
|
| 1252 |
+
99.86732373009856,
|
| 1253 |
+
99.85263157894737,
|
| 1254 |
+
99.8342803030303,
|
| 1255 |
+
99.81070849107626
|
| 1256 |
+
],
|
| 1257 |
+
"eval_ref_len": 8052,
|
| 1258 |
+
"eval_runtime": 14.4308,
|
| 1259 |
+
"eval_samples_per_second": 36.45,
|
| 1260 |
+
"eval_score": 58.99337109259839,
|
| 1261 |
+
"eval_steps_per_second": 1.178,
|
| 1262 |
+
"eval_sys_len": 5276,
|
| 1263 |
+
"eval_totals": [
|
| 1264 |
+
5276,
|
| 1265 |
+
4750,
|
| 1266 |
+
4224,
|
| 1267 |
+
3698
|
| 1268 |
+
],
|
| 1269 |
+
"step": 5160
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 41.0,
|
| 1273 |
+
"eval_bp": 0.59087181575089,
|
| 1274 |
+
"eval_counts": [
|
| 1275 |
+
5269,
|
| 1276 |
+
4743,
|
| 1277 |
+
4217,
|
| 1278 |
+
3691
|
| 1279 |
+
],
|
| 1280 |
+
"eval_loss": 0.0002036719670286402,
|
| 1281 |
+
"eval_precisions": [
|
| 1282 |
+
99.86732373009856,
|
| 1283 |
+
99.85263157894737,
|
| 1284 |
+
99.8342803030303,
|
| 1285 |
+
99.81070849107626
|
| 1286 |
+
],
|
| 1287 |
+
"eval_ref_len": 8052,
|
| 1288 |
+
"eval_runtime": 14.7863,
|
| 1289 |
+
"eval_samples_per_second": 35.573,
|
| 1290 |
+
"eval_score": 58.99337109259839,
|
| 1291 |
+
"eval_steps_per_second": 1.15,
|
| 1292 |
+
"eval_sys_len": 5276,
|
| 1293 |
+
"eval_totals": [
|
| 1294 |
+
5276,
|
| 1295 |
+
4750,
|
| 1296 |
+
4224,
|
| 1297 |
+
3698
|
| 1298 |
+
],
|
| 1299 |
+
"step": 5289
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 42.0,
|
| 1303 |
+
"eval_bp": 0.59087181575089,
|
| 1304 |
+
"eval_counts": [
|
| 1305 |
+
5269,
|
| 1306 |
+
4743,
|
| 1307 |
+
4217,
|
| 1308 |
+
3691
|
| 1309 |
+
],
|
| 1310 |
+
"eval_loss": 1.1326089406793471e-05,
|
| 1311 |
+
"eval_precisions": [
|
| 1312 |
+
99.86732373009856,
|
| 1313 |
+
99.85263157894737,
|
| 1314 |
+
99.8342803030303,
|
| 1315 |
+
99.81070849107626
|
| 1316 |
+
],
|
| 1317 |
+
"eval_ref_len": 8052,
|
| 1318 |
+
"eval_runtime": 14.4103,
|
| 1319 |
+
"eval_samples_per_second": 36.502,
|
| 1320 |
+
"eval_score": 58.99337109259839,
|
| 1321 |
+
"eval_steps_per_second": 1.18,
|
| 1322 |
+
"eval_sys_len": 5276,
|
| 1323 |
+
"eval_totals": [
|
| 1324 |
+
5276,
|
| 1325 |
+
4750,
|
| 1326 |
+
4224,
|
| 1327 |
+
3698
|
| 1328 |
+
],
|
| 1329 |
+
"step": 5418
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 42.64,
|
| 1333 |
+
"learning_rate": 2.9457364341085276e-06,
|
| 1334 |
+
"loss": 0.0017,
|
| 1335 |
+
"step": 5500
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 43.0,
|
| 1339 |
+
"eval_bp": 0.59087181575089,
|
| 1340 |
+
"eval_counts": [
|
| 1341 |
+
5269,
|
| 1342 |
+
4743,
|
| 1343 |
+
4217,
|
| 1344 |
+
3691
|
| 1345 |
+
],
|
| 1346 |
+
"eval_loss": 2.215807580796536e-05,
|
| 1347 |
+
"eval_precisions": [
|
| 1348 |
+
99.86732373009856,
|
| 1349 |
+
99.85263157894737,
|
| 1350 |
+
99.8342803030303,
|
| 1351 |
+
99.81070849107626
|
| 1352 |
+
],
|
| 1353 |
+
"eval_ref_len": 8052,
|
| 1354 |
+
"eval_runtime": 14.3532,
|
| 1355 |
+
"eval_samples_per_second": 36.647,
|
| 1356 |
+
"eval_score": 58.99337109259839,
|
| 1357 |
+
"eval_steps_per_second": 1.184,
|
| 1358 |
+
"eval_sys_len": 5276,
|
| 1359 |
+
"eval_totals": [
|
| 1360 |
+
5276,
|
| 1361 |
+
4750,
|
| 1362 |
+
4224,
|
| 1363 |
+
3698
|
| 1364 |
+
],
|
| 1365 |
+
"step": 5547
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 44.0,
|
| 1369 |
+
"eval_bp": 0.59087181575089,
|
| 1370 |
+
"eval_counts": [
|
| 1371 |
+
5269,
|
| 1372 |
+
4743,
|
| 1373 |
+
4217,
|
| 1374 |
+
3691
|
| 1375 |
+
],
|
| 1376 |
+
"eval_loss": 3.5351615224499255e-05,
|
| 1377 |
+
"eval_precisions": [
|
| 1378 |
+
99.86732373009856,
|
| 1379 |
+
99.85263157894737,
|
| 1380 |
+
99.8342803030303,
|
| 1381 |
+
99.81070849107626
|
| 1382 |
+
],
|
| 1383 |
+
"eval_ref_len": 8052,
|
| 1384 |
+
"eval_runtime": 14.751,
|
| 1385 |
+
"eval_samples_per_second": 35.659,
|
| 1386 |
+
"eval_score": 58.99337109259839,
|
| 1387 |
+
"eval_steps_per_second": 1.152,
|
| 1388 |
+
"eval_sys_len": 5276,
|
| 1389 |
+
"eval_totals": [
|
| 1390 |
+
5276,
|
| 1391 |
+
4750,
|
| 1392 |
+
4224,
|
| 1393 |
+
3698
|
| 1394 |
+
],
|
| 1395 |
+
"step": 5676
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 45.0,
|
| 1399 |
+
"eval_bp": 0.59087181575089,
|
| 1400 |
+
"eval_counts": [
|
| 1401 |
+
5269,
|
| 1402 |
+
4743,
|
| 1403 |
+
4217,
|
| 1404 |
+
3691
|
| 1405 |
+
],
|
| 1406 |
+
"eval_loss": 7.774249752401374e-06,
|
| 1407 |
+
"eval_precisions": [
|
| 1408 |
+
99.86732373009856,
|
| 1409 |
+
99.85263157894737,
|
| 1410 |
+
99.8342803030303,
|
| 1411 |
+
99.81070849107626
|
| 1412 |
+
],
|
| 1413 |
+
"eval_ref_len": 8052,
|
| 1414 |
+
"eval_runtime": 14.758,
|
| 1415 |
+
"eval_samples_per_second": 35.642,
|
| 1416 |
+
"eval_score": 58.99337109259839,
|
| 1417 |
+
"eval_steps_per_second": 1.152,
|
| 1418 |
+
"eval_sys_len": 5276,
|
| 1419 |
+
"eval_totals": [
|
| 1420 |
+
5276,
|
| 1421 |
+
4750,
|
| 1422 |
+
4224,
|
| 1423 |
+
3698
|
| 1424 |
+
],
|
| 1425 |
+
"step": 5805
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 46.0,
|
| 1429 |
+
"eval_bp": 0.59087181575089,
|
| 1430 |
+
"eval_counts": [
|
| 1431 |
+
5269,
|
| 1432 |
+
4743,
|
| 1433 |
+
4217,
|
| 1434 |
+
3691
|
| 1435 |
+
],
|
| 1436 |
+
"eval_loss": 9.12705854716478e-06,
|
| 1437 |
+
"eval_precisions": [
|
| 1438 |
+
99.86732373009856,
|
| 1439 |
+
99.85263157894737,
|
| 1440 |
+
99.8342803030303,
|
| 1441 |
+
99.81070849107626
|
| 1442 |
+
],
|
| 1443 |
+
"eval_ref_len": 8052,
|
| 1444 |
+
"eval_runtime": 14.4396,
|
| 1445 |
+
"eval_samples_per_second": 36.428,
|
| 1446 |
+
"eval_score": 58.99337109259839,
|
| 1447 |
+
"eval_steps_per_second": 1.177,
|
| 1448 |
+
"eval_sys_len": 5276,
|
| 1449 |
+
"eval_totals": [
|
| 1450 |
+
5276,
|
| 1451 |
+
4750,
|
| 1452 |
+
4224,
|
| 1453 |
+
3698
|
| 1454 |
+
],
|
| 1455 |
+
"step": 5934
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 46.51,
|
| 1459 |
+
"learning_rate": 1.3953488372093025e-06,
|
| 1460 |
+
"loss": 0.0013,
|
| 1461 |
+
"step": 6000
|
| 1462 |
+
}
|
| 1463 |
+
],
|
| 1464 |
+
"logging_steps": 500,
|
| 1465 |
+
"max_steps": 6450,
|
| 1466 |
+
"num_input_tokens_seen": 0,
|
| 1467 |
+
"num_train_epochs": 50,
|
| 1468 |
+
"save_steps": 500,
|
| 1469 |
+
"total_flos": 2.345330191113216e+16,
|
| 1470 |
+
"train_batch_size": 32,
|
| 1471 |
+
"trial_name": null,
|
| 1472 |
+
"trial_params": null
|
| 1473 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e0f1e99ecf29b90910ca3e6390a4867baa27762792983d2d278d9a415cd26e81
|
| 3 |
+
size 4856
|