Upload 12 files
Browse files- config.json +33 -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 +125 -0
- spiece.model +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +945 -0
- trainer_state.json +2421 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "UBC-NLP/AraT5v2-base-1024",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 2048,
|
| 8 |
+
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
+
"decoder_start_token_id": 0,
|
| 11 |
+
"dense_act_fn": "gelu_new",
|
| 12 |
+
"dropout_rate": 0.1,
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": true,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"num_decoder_layers": 12,
|
| 21 |
+
"num_heads": 12,
|
| 22 |
+
"num_layers": 12,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"tokenizer_class": "T5Tokenizer",
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.36.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 110208
|
| 33 |
+
}
|
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": "4.36.2"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6fca9b0be8c6fdc2a275af4fa3f6c6318ad50538963697a969bfacad33a73262
|
| 3 |
+
size 1470068592
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75153d17b0487ded3d18df6578aa43eb827bfddef9176bf7c63c664a13c4ee66
|
| 3 |
+
size 2940307013
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be5f96a15f297fdb04ea3833b15b93290ede8dfc0538e6ab755cbf1b155a0a23
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24b8222ab04b39f4d208edd90f7cd4beede5c56192523404234e2d461a6cf264
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"<extra_id_96>",
|
| 100 |
+
"<extra_id_97>",
|
| 101 |
+
"<extra_id_98>",
|
| 102 |
+
"<extra_id_99>"
|
| 103 |
+
],
|
| 104 |
+
"eos_token": {
|
| 105 |
+
"content": "</s>",
|
| 106 |
+
"lstrip": false,
|
| 107 |
+
"normalized": false,
|
| 108 |
+
"rstrip": false,
|
| 109 |
+
"single_word": false
|
| 110 |
+
},
|
| 111 |
+
"pad_token": {
|
| 112 |
+
"content": "<pad>",
|
| 113 |
+
"lstrip": false,
|
| 114 |
+
"normalized": false,
|
| 115 |
+
"rstrip": false,
|
| 116 |
+
"single_word": false
|
| 117 |
+
},
|
| 118 |
+
"unk_token": {
|
| 119 |
+
"content": "<unk>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": false,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false
|
| 124 |
+
}
|
| 125 |
+
}
|
spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:180428eb8e88be6c7d259fb04c9eb3a1c552d799a76741bcd6ee34fa0bf64386
|
| 3 |
+
size 2353338
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,945 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"110000": {
|
| 28 |
+
"content": "<extra_id_99>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"110001": {
|
| 36 |
+
"content": "<extra_id_98>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"110002": {
|
| 44 |
+
"content": "<extra_id_97>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"110003": {
|
| 52 |
+
"content": "<extra_id_96>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"110004": {
|
| 60 |
+
"content": "<extra_id_95>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"110005": {
|
| 68 |
+
"content": "<extra_id_94>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"110006": {
|
| 76 |
+
"content": "<extra_id_93>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"110007": {
|
| 84 |
+
"content": "<extra_id_92>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"110008": {
|
| 92 |
+
"content": "<extra_id_91>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"110009": {
|
| 100 |
+
"content": "<extra_id_90>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"110010": {
|
| 108 |
+
"content": "<extra_id_89>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"110011": {
|
| 116 |
+
"content": "<extra_id_88>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"110012": {
|
| 124 |
+
"content": "<extra_id_87>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"110013": {
|
| 132 |
+
"content": "<extra_id_86>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"110014": {
|
| 140 |
+
"content": "<extra_id_85>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"110015": {
|
| 148 |
+
"content": "<extra_id_84>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"110016": {
|
| 156 |
+
"content": "<extra_id_83>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"110017": {
|
| 164 |
+
"content": "<extra_id_82>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"110018": {
|
| 172 |
+
"content": "<extra_id_81>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"110019": {
|
| 180 |
+
"content": "<extra_id_80>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"110020": {
|
| 188 |
+
"content": "<extra_id_79>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"110021": {
|
| 196 |
+
"content": "<extra_id_78>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"110022": {
|
| 204 |
+
"content": "<extra_id_77>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"110023": {
|
| 212 |
+
"content": "<extra_id_76>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"110024": {
|
| 220 |
+
"content": "<extra_id_75>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"110025": {
|
| 228 |
+
"content": "<extra_id_74>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"110026": {
|
| 236 |
+
"content": "<extra_id_73>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"110027": {
|
| 244 |
+
"content": "<extra_id_72>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"110028": {
|
| 252 |
+
"content": "<extra_id_71>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"110029": {
|
| 260 |
+
"content": "<extra_id_70>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"110030": {
|
| 268 |
+
"content": "<extra_id_69>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"110031": {
|
| 276 |
+
"content": "<extra_id_68>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"110032": {
|
| 284 |
+
"content": "<extra_id_67>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"110033": {
|
| 292 |
+
"content": "<extra_id_66>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"110034": {
|
| 300 |
+
"content": "<extra_id_65>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"110035": {
|
| 308 |
+
"content": "<extra_id_64>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"110036": {
|
| 316 |
+
"content": "<extra_id_63>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"110037": {
|
| 324 |
+
"content": "<extra_id_62>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"110038": {
|
| 332 |
+
"content": "<extra_id_61>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"110039": {
|
| 340 |
+
"content": "<extra_id_60>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"110040": {
|
| 348 |
+
"content": "<extra_id_59>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"110041": {
|
| 356 |
+
"content": "<extra_id_58>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"110042": {
|
| 364 |
+
"content": "<extra_id_57>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"110043": {
|
| 372 |
+
"content": "<extra_id_56>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"110044": {
|
| 380 |
+
"content": "<extra_id_55>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"110045": {
|
| 388 |
+
"content": "<extra_id_54>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"110046": {
|
| 396 |
+
"content": "<extra_id_53>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"110047": {
|
| 404 |
+
"content": "<extra_id_52>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"110048": {
|
| 412 |
+
"content": "<extra_id_51>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"110049": {
|
| 420 |
+
"content": "<extra_id_50>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"110050": {
|
| 428 |
+
"content": "<extra_id_49>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"110051": {
|
| 436 |
+
"content": "<extra_id_48>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"110052": {
|
| 444 |
+
"content": "<extra_id_47>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"110053": {
|
| 452 |
+
"content": "<extra_id_46>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"110054": {
|
| 460 |
+
"content": "<extra_id_45>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"110055": {
|
| 468 |
+
"content": "<extra_id_44>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"110056": {
|
| 476 |
+
"content": "<extra_id_43>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"110057": {
|
| 484 |
+
"content": "<extra_id_42>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"110058": {
|
| 492 |
+
"content": "<extra_id_41>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"110059": {
|
| 500 |
+
"content": "<extra_id_40>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"110060": {
|
| 508 |
+
"content": "<extra_id_39>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"110061": {
|
| 516 |
+
"content": "<extra_id_38>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"110062": {
|
| 524 |
+
"content": "<extra_id_37>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"110063": {
|
| 532 |
+
"content": "<extra_id_36>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"110064": {
|
| 540 |
+
"content": "<extra_id_35>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"110065": {
|
| 548 |
+
"content": "<extra_id_34>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"110066": {
|
| 556 |
+
"content": "<extra_id_33>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"110067": {
|
| 564 |
+
"content": "<extra_id_32>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"110068": {
|
| 572 |
+
"content": "<extra_id_31>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"110069": {
|
| 580 |
+
"content": "<extra_id_30>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"110070": {
|
| 588 |
+
"content": "<extra_id_29>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"110071": {
|
| 596 |
+
"content": "<extra_id_28>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"110072": {
|
| 604 |
+
"content": "<extra_id_27>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"110073": {
|
| 612 |
+
"content": "<extra_id_26>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"110074": {
|
| 620 |
+
"content": "<extra_id_25>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"110075": {
|
| 628 |
+
"content": "<extra_id_24>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"110076": {
|
| 636 |
+
"content": "<extra_id_23>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"110077": {
|
| 644 |
+
"content": "<extra_id_22>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"110078": {
|
| 652 |
+
"content": "<extra_id_21>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"110079": {
|
| 660 |
+
"content": "<extra_id_20>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"110080": {
|
| 668 |
+
"content": "<extra_id_19>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"110081": {
|
| 676 |
+
"content": "<extra_id_18>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"110082": {
|
| 684 |
+
"content": "<extra_id_17>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"110083": {
|
| 692 |
+
"content": "<extra_id_16>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"110084": {
|
| 700 |
+
"content": "<extra_id_15>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"110085": {
|
| 708 |
+
"content": "<extra_id_14>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"110086": {
|
| 716 |
+
"content": "<extra_id_13>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"110087": {
|
| 724 |
+
"content": "<extra_id_12>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"110088": {
|
| 732 |
+
"content": "<extra_id_11>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"110089": {
|
| 740 |
+
"content": "<extra_id_10>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"110090": {
|
| 748 |
+
"content": "<extra_id_9>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"110091": {
|
| 756 |
+
"content": "<extra_id_8>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"110092": {
|
| 764 |
+
"content": "<extra_id_7>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"110093": {
|
| 772 |
+
"content": "<extra_id_6>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"110094": {
|
| 780 |
+
"content": "<extra_id_5>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"110095": {
|
| 788 |
+
"content": "<extra_id_4>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"110096": {
|
| 796 |
+
"content": "<extra_id_3>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"110097": {
|
| 804 |
+
"content": "<extra_id_2>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"110098": {
|
| 812 |
+
"content": "<extra_id_1>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"110099": {
|
| 820 |
+
"content": "<extra_id_0>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
}
|
| 827 |
+
},
|
| 828 |
+
"additional_special_tokens": [
|
| 829 |
+
"<extra_id_0>",
|
| 830 |
+
"<extra_id_1>",
|
| 831 |
+
"<extra_id_2>",
|
| 832 |
+
"<extra_id_3>",
|
| 833 |
+
"<extra_id_4>",
|
| 834 |
+
"<extra_id_5>",
|
| 835 |
+
"<extra_id_6>",
|
| 836 |
+
"<extra_id_7>",
|
| 837 |
+
"<extra_id_8>",
|
| 838 |
+
"<extra_id_9>",
|
| 839 |
+
"<extra_id_10>",
|
| 840 |
+
"<extra_id_11>",
|
| 841 |
+
"<extra_id_12>",
|
| 842 |
+
"<extra_id_13>",
|
| 843 |
+
"<extra_id_14>",
|
| 844 |
+
"<extra_id_15>",
|
| 845 |
+
"<extra_id_16>",
|
| 846 |
+
"<extra_id_17>",
|
| 847 |
+
"<extra_id_18>",
|
| 848 |
+
"<extra_id_19>",
|
| 849 |
+
"<extra_id_20>",
|
| 850 |
+
"<extra_id_21>",
|
| 851 |
+
"<extra_id_22>",
|
| 852 |
+
"<extra_id_23>",
|
| 853 |
+
"<extra_id_24>",
|
| 854 |
+
"<extra_id_25>",
|
| 855 |
+
"<extra_id_26>",
|
| 856 |
+
"<extra_id_27>",
|
| 857 |
+
"<extra_id_28>",
|
| 858 |
+
"<extra_id_29>",
|
| 859 |
+
"<extra_id_30>",
|
| 860 |
+
"<extra_id_31>",
|
| 861 |
+
"<extra_id_32>",
|
| 862 |
+
"<extra_id_33>",
|
| 863 |
+
"<extra_id_34>",
|
| 864 |
+
"<extra_id_35>",
|
| 865 |
+
"<extra_id_36>",
|
| 866 |
+
"<extra_id_37>",
|
| 867 |
+
"<extra_id_38>",
|
| 868 |
+
"<extra_id_39>",
|
| 869 |
+
"<extra_id_40>",
|
| 870 |
+
"<extra_id_41>",
|
| 871 |
+
"<extra_id_42>",
|
| 872 |
+
"<extra_id_43>",
|
| 873 |
+
"<extra_id_44>",
|
| 874 |
+
"<extra_id_45>",
|
| 875 |
+
"<extra_id_46>",
|
| 876 |
+
"<extra_id_47>",
|
| 877 |
+
"<extra_id_48>",
|
| 878 |
+
"<extra_id_49>",
|
| 879 |
+
"<extra_id_50>",
|
| 880 |
+
"<extra_id_51>",
|
| 881 |
+
"<extra_id_52>",
|
| 882 |
+
"<extra_id_53>",
|
| 883 |
+
"<extra_id_54>",
|
| 884 |
+
"<extra_id_55>",
|
| 885 |
+
"<extra_id_56>",
|
| 886 |
+
"<extra_id_57>",
|
| 887 |
+
"<extra_id_58>",
|
| 888 |
+
"<extra_id_59>",
|
| 889 |
+
"<extra_id_60>",
|
| 890 |
+
"<extra_id_61>",
|
| 891 |
+
"<extra_id_62>",
|
| 892 |
+
"<extra_id_63>",
|
| 893 |
+
"<extra_id_64>",
|
| 894 |
+
"<extra_id_65>",
|
| 895 |
+
"<extra_id_66>",
|
| 896 |
+
"<extra_id_67>",
|
| 897 |
+
"<extra_id_68>",
|
| 898 |
+
"<extra_id_69>",
|
| 899 |
+
"<extra_id_70>",
|
| 900 |
+
"<extra_id_71>",
|
| 901 |
+
"<extra_id_72>",
|
| 902 |
+
"<extra_id_73>",
|
| 903 |
+
"<extra_id_74>",
|
| 904 |
+
"<extra_id_75>",
|
| 905 |
+
"<extra_id_76>",
|
| 906 |
+
"<extra_id_77>",
|
| 907 |
+
"<extra_id_78>",
|
| 908 |
+
"<extra_id_79>",
|
| 909 |
+
"<extra_id_80>",
|
| 910 |
+
"<extra_id_81>",
|
| 911 |
+
"<extra_id_82>",
|
| 912 |
+
"<extra_id_83>",
|
| 913 |
+
"<extra_id_84>",
|
| 914 |
+
"<extra_id_85>",
|
| 915 |
+
"<extra_id_86>",
|
| 916 |
+
"<extra_id_87>",
|
| 917 |
+
"<extra_id_88>",
|
| 918 |
+
"<extra_id_89>",
|
| 919 |
+
"<extra_id_90>",
|
| 920 |
+
"<extra_id_91>",
|
| 921 |
+
"<extra_id_92>",
|
| 922 |
+
"<extra_id_93>",
|
| 923 |
+
"<extra_id_94>",
|
| 924 |
+
"<extra_id_95>",
|
| 925 |
+
"<extra_id_96>",
|
| 926 |
+
"<extra_id_97>",
|
| 927 |
+
"<extra_id_98>",
|
| 928 |
+
"<extra_id_99>"
|
| 929 |
+
],
|
| 930 |
+
"clean_up_tokenization_spaces": true,
|
| 931 |
+
"eos_token": "</s>",
|
| 932 |
+
"extra_ids": 100,
|
| 933 |
+
"max_length": 30,
|
| 934 |
+
"model_max_length": 1024,
|
| 935 |
+
"pad_to_multiple_of": null,
|
| 936 |
+
"pad_token": "<pad>",
|
| 937 |
+
"pad_token_type_id": 0,
|
| 938 |
+
"padding_side": "right",
|
| 939 |
+
"sp_model_kwargs": {},
|
| 940 |
+
"stride": 0,
|
| 941 |
+
"tokenizer_class": "T5Tokenizer",
|
| 942 |
+
"truncation_side": "right",
|
| 943 |
+
"truncation_strategy": "longest_first",
|
| 944 |
+
"unk_token": "<unk>"
|
| 945 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2421 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 85.6858,
|
| 3 |
+
"best_model_checkpoint": "AraT5_FT_MSA_Transaltion/checkpoint-74500",
|
| 4 |
+
"epoch": 60.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 75000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.4,
|
| 13 |
+
"learning_rate": 4.9836065573770496e-05,
|
| 14 |
+
"loss": 3.9102,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.4,
|
| 19 |
+
"eval_bleu": 18.6972,
|
| 20 |
+
"eval_gen_len": 9.4035,
|
| 21 |
+
"eval_loss": 1.9062472581863403,
|
| 22 |
+
"eval_runtime": 106.2615,
|
| 23 |
+
"eval_samples_per_second": 94.107,
|
| 24 |
+
"eval_steps_per_second": 1.477,
|
| 25 |
+
"step": 500
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.8,
|
| 29 |
+
"learning_rate": 4.967213114754098e-05,
|
| 30 |
+
"loss": 2.3273,
|
| 31 |
+
"step": 1000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.8,
|
| 35 |
+
"eval_bleu": 22.5788,
|
| 36 |
+
"eval_gen_len": 9.3259,
|
| 37 |
+
"eval_loss": 1.6005295515060425,
|
| 38 |
+
"eval_runtime": 107.2854,
|
| 39 |
+
"eval_samples_per_second": 93.209,
|
| 40 |
+
"eval_steps_per_second": 1.463,
|
| 41 |
+
"step": 1000
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 1.2,
|
| 45 |
+
"learning_rate": 4.9508196721311476e-05,
|
| 46 |
+
"loss": 1.996,
|
| 47 |
+
"step": 1500
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 1.2,
|
| 51 |
+
"eval_bleu": 25.6973,
|
| 52 |
+
"eval_gen_len": 9.4844,
|
| 53 |
+
"eval_loss": 1.413317084312439,
|
| 54 |
+
"eval_runtime": 107.9077,
|
| 55 |
+
"eval_samples_per_second": 92.672,
|
| 56 |
+
"eval_steps_per_second": 1.455,
|
| 57 |
+
"step": 1500
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.6,
|
| 61 |
+
"learning_rate": 4.934426229508197e-05,
|
| 62 |
+
"loss": 1.7747,
|
| 63 |
+
"step": 2000
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 1.6,
|
| 67 |
+
"eval_bleu": 29.1098,
|
| 68 |
+
"eval_gen_len": 9.4334,
|
| 69 |
+
"eval_loss": 1.2736828327178955,
|
| 70 |
+
"eval_runtime": 108.0256,
|
| 71 |
+
"eval_samples_per_second": 92.571,
|
| 72 |
+
"eval_steps_per_second": 1.453,
|
| 73 |
+
"step": 2000
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 2.0,
|
| 77 |
+
"learning_rate": 4.918032786885246e-05,
|
| 78 |
+
"loss": 1.6363,
|
| 79 |
+
"step": 2500
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 2.0,
|
| 83 |
+
"eval_bleu": 32.4975,
|
| 84 |
+
"eval_gen_len": 9.5307,
|
| 85 |
+
"eval_loss": 1.154405951499939,
|
| 86 |
+
"eval_runtime": 108.0346,
|
| 87 |
+
"eval_samples_per_second": 92.563,
|
| 88 |
+
"eval_steps_per_second": 1.453,
|
| 89 |
+
"step": 2500
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 2.4,
|
| 93 |
+
"learning_rate": 4.9016393442622957e-05,
|
| 94 |
+
"loss": 1.4614,
|
| 95 |
+
"step": 3000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.4,
|
| 99 |
+
"eval_bleu": 35.6534,
|
| 100 |
+
"eval_gen_len": 9.5125,
|
| 101 |
+
"eval_loss": 1.0677547454833984,
|
| 102 |
+
"eval_runtime": 106.6888,
|
| 103 |
+
"eval_samples_per_second": 93.731,
|
| 104 |
+
"eval_steps_per_second": 1.472,
|
| 105 |
+
"step": 3000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 2.8,
|
| 109 |
+
"learning_rate": 4.885245901639344e-05,
|
| 110 |
+
"loss": 1.3627,
|
| 111 |
+
"step": 3500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 2.8,
|
| 115 |
+
"eval_bleu": 39.0667,
|
| 116 |
+
"eval_gen_len": 9.5759,
|
| 117 |
+
"eval_loss": 0.9860268235206604,
|
| 118 |
+
"eval_runtime": 108.9156,
|
| 119 |
+
"eval_samples_per_second": 91.814,
|
| 120 |
+
"eval_steps_per_second": 1.441,
|
| 121 |
+
"step": 3500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 3.2,
|
| 125 |
+
"learning_rate": 4.868852459016394e-05,
|
| 126 |
+
"loss": 1.2627,
|
| 127 |
+
"step": 4000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 3.2,
|
| 131 |
+
"eval_bleu": 42.4036,
|
| 132 |
+
"eval_gen_len": 9.6225,
|
| 133 |
+
"eval_loss": 0.9212129712104797,
|
| 134 |
+
"eval_runtime": 108.2436,
|
| 135 |
+
"eval_samples_per_second": 92.384,
|
| 136 |
+
"eval_steps_per_second": 1.45,
|
| 137 |
+
"step": 4000
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.6,
|
| 141 |
+
"learning_rate": 4.852459016393443e-05,
|
| 142 |
+
"loss": 1.1616,
|
| 143 |
+
"step": 4500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 3.6,
|
| 147 |
+
"eval_bleu": 44.7376,
|
| 148 |
+
"eval_gen_len": 9.6448,
|
| 149 |
+
"eval_loss": 0.8675327897071838,
|
| 150 |
+
"eval_runtime": 109.0598,
|
| 151 |
+
"eval_samples_per_second": 91.693,
|
| 152 |
+
"eval_steps_per_second": 1.44,
|
| 153 |
+
"step": 4500
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 4.0,
|
| 157 |
+
"learning_rate": 4.836065573770492e-05,
|
| 158 |
+
"loss": 1.1226,
|
| 159 |
+
"step": 5000
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 4.0,
|
| 163 |
+
"eval_bleu": 47.2213,
|
| 164 |
+
"eval_gen_len": 9.6337,
|
| 165 |
+
"eval_loss": 0.816310703754425,
|
| 166 |
+
"eval_runtime": 106.4424,
|
| 167 |
+
"eval_samples_per_second": 93.947,
|
| 168 |
+
"eval_steps_per_second": 1.475,
|
| 169 |
+
"step": 5000
|
| 170 |
+
},
|
| 171 |
+
{
|
| 172 |
+
"epoch": 4.4,
|
| 173 |
+
"learning_rate": 4.819672131147541e-05,
|
| 174 |
+
"loss": 1.006,
|
| 175 |
+
"step": 5500
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"epoch": 4.4,
|
| 179 |
+
"eval_bleu": 49.5563,
|
| 180 |
+
"eval_gen_len": 9.7168,
|
| 181 |
+
"eval_loss": 0.7709316611289978,
|
| 182 |
+
"eval_runtime": 112.4236,
|
| 183 |
+
"eval_samples_per_second": 88.949,
|
| 184 |
+
"eval_steps_per_second": 1.397,
|
| 185 |
+
"step": 5500
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 4.8,
|
| 189 |
+
"learning_rate": 4.8032786885245904e-05,
|
| 190 |
+
"loss": 0.978,
|
| 191 |
+
"step": 6000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 4.8,
|
| 195 |
+
"eval_bleu": 50.775,
|
| 196 |
+
"eval_gen_len": 9.6925,
|
| 197 |
+
"eval_loss": 0.7373432517051697,
|
| 198 |
+
"eval_runtime": 109.2099,
|
| 199 |
+
"eval_samples_per_second": 91.567,
|
| 200 |
+
"eval_steps_per_second": 1.438,
|
| 201 |
+
"step": 6000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 5.2,
|
| 205 |
+
"learning_rate": 4.78688524590164e-05,
|
| 206 |
+
"loss": 0.9099,
|
| 207 |
+
"step": 6500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 5.2,
|
| 211 |
+
"eval_bleu": 52.697,
|
| 212 |
+
"eval_gen_len": 9.7017,
|
| 213 |
+
"eval_loss": 0.7020449042320251,
|
| 214 |
+
"eval_runtime": 109.0697,
|
| 215 |
+
"eval_samples_per_second": 91.684,
|
| 216 |
+
"eval_steps_per_second": 1.439,
|
| 217 |
+
"step": 6500
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 5.6,
|
| 221 |
+
"learning_rate": 4.770491803278689e-05,
|
| 222 |
+
"loss": 0.8483,
|
| 223 |
+
"step": 7000
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.6,
|
| 227 |
+
"eval_bleu": 53.9571,
|
| 228 |
+
"eval_gen_len": 9.693,
|
| 229 |
+
"eval_loss": 0.6663933992385864,
|
| 230 |
+
"eval_runtime": 109.7349,
|
| 231 |
+
"eval_samples_per_second": 91.129,
|
| 232 |
+
"eval_steps_per_second": 1.431,
|
| 233 |
+
"step": 7000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 6.0,
|
| 237 |
+
"learning_rate": 4.754098360655738e-05,
|
| 238 |
+
"loss": 0.8293,
|
| 239 |
+
"step": 7500
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 6.0,
|
| 243 |
+
"eval_bleu": 55.874,
|
| 244 |
+
"eval_gen_len": 9.7475,
|
| 245 |
+
"eval_loss": 0.630104124546051,
|
| 246 |
+
"eval_runtime": 109.6322,
|
| 247 |
+
"eval_samples_per_second": 91.214,
|
| 248 |
+
"eval_steps_per_second": 1.432,
|
| 249 |
+
"step": 7500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 6.4,
|
| 253 |
+
"learning_rate": 4.737704918032787e-05,
|
| 254 |
+
"loss": 0.7493,
|
| 255 |
+
"step": 8000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 6.4,
|
| 259 |
+
"eval_bleu": 56.7427,
|
| 260 |
+
"eval_gen_len": 9.7239,
|
| 261 |
+
"eval_loss": 0.6072443723678589,
|
| 262 |
+
"eval_runtime": 113.2863,
|
| 263 |
+
"eval_samples_per_second": 88.272,
|
| 264 |
+
"eval_steps_per_second": 1.386,
|
| 265 |
+
"step": 8000
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 6.8,
|
| 269 |
+
"learning_rate": 4.7213114754098365e-05,
|
| 270 |
+
"loss": 0.7294,
|
| 271 |
+
"step": 8500
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 6.8,
|
| 275 |
+
"eval_bleu": 57.9936,
|
| 276 |
+
"eval_gen_len": 9.7521,
|
| 277 |
+
"eval_loss": 0.5758106112480164,
|
| 278 |
+
"eval_runtime": 110.1034,
|
| 279 |
+
"eval_samples_per_second": 90.824,
|
| 280 |
+
"eval_steps_per_second": 1.426,
|
| 281 |
+
"step": 8500
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 7.2,
|
| 285 |
+
"learning_rate": 4.704918032786885e-05,
|
| 286 |
+
"loss": 0.6904,
|
| 287 |
+
"step": 9000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 7.2,
|
| 291 |
+
"eval_bleu": 59.0065,
|
| 292 |
+
"eval_gen_len": 9.7544,
|
| 293 |
+
"eval_loss": 0.5612244606018066,
|
| 294 |
+
"eval_runtime": 117.8275,
|
| 295 |
+
"eval_samples_per_second": 84.87,
|
| 296 |
+
"eval_steps_per_second": 1.332,
|
| 297 |
+
"step": 9000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 7.6,
|
| 301 |
+
"learning_rate": 4.6885245901639345e-05,
|
| 302 |
+
"loss": 0.6478,
|
| 303 |
+
"step": 9500
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 7.6,
|
| 307 |
+
"eval_bleu": 60.1129,
|
| 308 |
+
"eval_gen_len": 9.7827,
|
| 309 |
+
"eval_loss": 0.525496780872345,
|
| 310 |
+
"eval_runtime": 119.5262,
|
| 311 |
+
"eval_samples_per_second": 83.664,
|
| 312 |
+
"eval_steps_per_second": 1.314,
|
| 313 |
+
"step": 9500
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 8.0,
|
| 317 |
+
"learning_rate": 4.672131147540984e-05,
|
| 318 |
+
"loss": 0.6257,
|
| 319 |
+
"step": 10000
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 8.0,
|
| 323 |
+
"eval_bleu": 61.0568,
|
| 324 |
+
"eval_gen_len": 9.7663,
|
| 325 |
+
"eval_loss": 0.5063189268112183,
|
| 326 |
+
"eval_runtime": 118.6711,
|
| 327 |
+
"eval_samples_per_second": 84.267,
|
| 328 |
+
"eval_steps_per_second": 1.323,
|
| 329 |
+
"step": 10000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 8.4,
|
| 333 |
+
"learning_rate": 4.655737704918033e-05,
|
| 334 |
+
"loss": 0.5696,
|
| 335 |
+
"step": 10500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 8.4,
|
| 339 |
+
"eval_bleu": 61.9169,
|
| 340 |
+
"eval_gen_len": 9.776,
|
| 341 |
+
"eval_loss": 0.4885226786136627,
|
| 342 |
+
"eval_runtime": 121.031,
|
| 343 |
+
"eval_samples_per_second": 82.623,
|
| 344 |
+
"eval_steps_per_second": 1.297,
|
| 345 |
+
"step": 10500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 8.8,
|
| 349 |
+
"learning_rate": 4.6393442622950825e-05,
|
| 350 |
+
"loss": 0.5636,
|
| 351 |
+
"step": 11000
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 8.8,
|
| 355 |
+
"eval_bleu": 62.5974,
|
| 356 |
+
"eval_gen_len": 9.7975,
|
| 357 |
+
"eval_loss": 0.471066951751709,
|
| 358 |
+
"eval_runtime": 119.0897,
|
| 359 |
+
"eval_samples_per_second": 83.97,
|
| 360 |
+
"eval_steps_per_second": 1.318,
|
| 361 |
+
"step": 11000
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 9.2,
|
| 365 |
+
"learning_rate": 4.622950819672132e-05,
|
| 366 |
+
"loss": 0.5258,
|
| 367 |
+
"step": 11500
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 9.2,
|
| 371 |
+
"eval_bleu": 63.7967,
|
| 372 |
+
"eval_gen_len": 9.8122,
|
| 373 |
+
"eval_loss": 0.449593722820282,
|
| 374 |
+
"eval_runtime": 120.8927,
|
| 375 |
+
"eval_samples_per_second": 82.718,
|
| 376 |
+
"eval_steps_per_second": 1.299,
|
| 377 |
+
"step": 11500
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 9.6,
|
| 381 |
+
"learning_rate": 4.6065573770491805e-05,
|
| 382 |
+
"loss": 0.4979,
|
| 383 |
+
"step": 12000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 9.6,
|
| 387 |
+
"eval_bleu": 64.6212,
|
| 388 |
+
"eval_gen_len": 9.7674,
|
| 389 |
+
"eval_loss": 0.43481728434562683,
|
| 390 |
+
"eval_runtime": 119.3174,
|
| 391 |
+
"eval_samples_per_second": 83.81,
|
| 392 |
+
"eval_steps_per_second": 1.316,
|
| 393 |
+
"step": 12000
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 10.0,
|
| 397 |
+
"learning_rate": 4.59016393442623e-05,
|
| 398 |
+
"loss": 0.4987,
|
| 399 |
+
"step": 12500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 10.0,
|
| 403 |
+
"eval_bleu": 65.3736,
|
| 404 |
+
"eval_gen_len": 9.8562,
|
| 405 |
+
"eval_loss": 0.4133751392364502,
|
| 406 |
+
"eval_runtime": 122.0111,
|
| 407 |
+
"eval_samples_per_second": 81.96,
|
| 408 |
+
"eval_steps_per_second": 1.287,
|
| 409 |
+
"step": 12500
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 10.4,
|
| 413 |
+
"learning_rate": 4.5737704918032786e-05,
|
| 414 |
+
"loss": 0.4497,
|
| 415 |
+
"step": 13000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 10.4,
|
| 419 |
+
"eval_bleu": 66.4415,
|
| 420 |
+
"eval_gen_len": 9.8254,
|
| 421 |
+
"eval_loss": 0.39948710799217224,
|
| 422 |
+
"eval_runtime": 121.3113,
|
| 423 |
+
"eval_samples_per_second": 82.433,
|
| 424 |
+
"eval_steps_per_second": 1.294,
|
| 425 |
+
"step": 13000
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 10.8,
|
| 429 |
+
"learning_rate": 4.557377049180328e-05,
|
| 430 |
+
"loss": 0.4382,
|
| 431 |
+
"step": 13500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 10.8,
|
| 435 |
+
"eval_bleu": 66.8785,
|
| 436 |
+
"eval_gen_len": 9.8152,
|
| 437 |
+
"eval_loss": 0.3892167806625366,
|
| 438 |
+
"eval_runtime": 120.977,
|
| 439 |
+
"eval_samples_per_second": 82.66,
|
| 440 |
+
"eval_steps_per_second": 1.298,
|
| 441 |
+
"step": 13500
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 11.2,
|
| 445 |
+
"learning_rate": 4.540983606557377e-05,
|
| 446 |
+
"loss": 0.4146,
|
| 447 |
+
"step": 14000
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 11.2,
|
| 451 |
+
"eval_bleu": 67.6836,
|
| 452 |
+
"eval_gen_len": 9.8031,
|
| 453 |
+
"eval_loss": 0.374174565076828,
|
| 454 |
+
"eval_runtime": 123.4198,
|
| 455 |
+
"eval_samples_per_second": 81.024,
|
| 456 |
+
"eval_steps_per_second": 1.272,
|
| 457 |
+
"step": 14000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 11.6,
|
| 461 |
+
"learning_rate": 4.524590163934426e-05,
|
| 462 |
+
"loss": 0.3895,
|
| 463 |
+
"step": 14500
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 11.6,
|
| 467 |
+
"eval_bleu": 68.4895,
|
| 468 |
+
"eval_gen_len": 9.8325,
|
| 469 |
+
"eval_loss": 0.3638547658920288,
|
| 470 |
+
"eval_runtime": 123.9996,
|
| 471 |
+
"eval_samples_per_second": 80.645,
|
| 472 |
+
"eval_steps_per_second": 1.266,
|
| 473 |
+
"step": 14500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 12.0,
|
| 477 |
+
"learning_rate": 4.508196721311476e-05,
|
| 478 |
+
"loss": 0.3881,
|
| 479 |
+
"step": 15000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 12.0,
|
| 483 |
+
"eval_bleu": 68.9665,
|
| 484 |
+
"eval_gen_len": 9.8444,
|
| 485 |
+
"eval_loss": 0.3532446026802063,
|
| 486 |
+
"eval_runtime": 123.044,
|
| 487 |
+
"eval_samples_per_second": 81.272,
|
| 488 |
+
"eval_steps_per_second": 1.276,
|
| 489 |
+
"step": 15000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 12.4,
|
| 493 |
+
"learning_rate": 4.491803278688525e-05,
|
| 494 |
+
"loss": 0.3495,
|
| 495 |
+
"step": 15500
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 12.4,
|
| 499 |
+
"eval_bleu": 69.8231,
|
| 500 |
+
"eval_gen_len": 9.8346,
|
| 501 |
+
"eval_loss": 0.34260880947113037,
|
| 502 |
+
"eval_runtime": 122.4901,
|
| 503 |
+
"eval_samples_per_second": 81.639,
|
| 504 |
+
"eval_steps_per_second": 1.282,
|
| 505 |
+
"step": 15500
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 12.8,
|
| 509 |
+
"learning_rate": 4.475409836065574e-05,
|
| 510 |
+
"loss": 0.3474,
|
| 511 |
+
"step": 16000
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 12.8,
|
| 515 |
+
"eval_bleu": 70.4124,
|
| 516 |
+
"eval_gen_len": 9.8408,
|
| 517 |
+
"eval_loss": 0.3283344805240631,
|
| 518 |
+
"eval_runtime": 122.1563,
|
| 519 |
+
"eval_samples_per_second": 81.862,
|
| 520 |
+
"eval_steps_per_second": 1.285,
|
| 521 |
+
"step": 16000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 13.2,
|
| 525 |
+
"learning_rate": 4.459016393442623e-05,
|
| 526 |
+
"loss": 0.3264,
|
| 527 |
+
"step": 16500
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 13.2,
|
| 531 |
+
"eval_bleu": 70.991,
|
| 532 |
+
"eval_gen_len": 9.8374,
|
| 533 |
+
"eval_loss": 0.3219762444496155,
|
| 534 |
+
"eval_runtime": 122.3026,
|
| 535 |
+
"eval_samples_per_second": 81.764,
|
| 536 |
+
"eval_steps_per_second": 1.284,
|
| 537 |
+
"step": 16500
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 13.6,
|
| 541 |
+
"learning_rate": 4.442622950819673e-05,
|
| 542 |
+
"loss": 0.3095,
|
| 543 |
+
"step": 17000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 13.6,
|
| 547 |
+
"eval_bleu": 71.7934,
|
| 548 |
+
"eval_gen_len": 9.8704,
|
| 549 |
+
"eval_loss": 0.3138624131679535,
|
| 550 |
+
"eval_runtime": 124.2274,
|
| 551 |
+
"eval_samples_per_second": 80.498,
|
| 552 |
+
"eval_steps_per_second": 1.264,
|
| 553 |
+
"step": 17000
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 14.0,
|
| 557 |
+
"learning_rate": 4.426229508196721e-05,
|
| 558 |
+
"loss": 0.3138,
|
| 559 |
+
"step": 17500
|
| 560 |
+
},
|
| 561 |
+
{
|
| 562 |
+
"epoch": 14.0,
|
| 563 |
+
"eval_bleu": 72.3896,
|
| 564 |
+
"eval_gen_len": 9.8585,
|
| 565 |
+
"eval_loss": 0.3009161949157715,
|
| 566 |
+
"eval_runtime": 122.1372,
|
| 567 |
+
"eval_samples_per_second": 81.875,
|
| 568 |
+
"eval_steps_per_second": 1.285,
|
| 569 |
+
"step": 17500
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 14.4,
|
| 573 |
+
"learning_rate": 4.409836065573771e-05,
|
| 574 |
+
"loss": 0.2828,
|
| 575 |
+
"step": 18000
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 14.4,
|
| 579 |
+
"eval_bleu": 72.6457,
|
| 580 |
+
"eval_gen_len": 9.8585,
|
| 581 |
+
"eval_loss": 0.301722913980484,
|
| 582 |
+
"eval_runtime": 123.5238,
|
| 583 |
+
"eval_samples_per_second": 80.956,
|
| 584 |
+
"eval_steps_per_second": 1.271,
|
| 585 |
+
"step": 18000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 14.8,
|
| 589 |
+
"learning_rate": 4.3934426229508194e-05,
|
| 590 |
+
"loss": 0.2776,
|
| 591 |
+
"step": 18500
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 14.8,
|
| 595 |
+
"eval_bleu": 73.1631,
|
| 596 |
+
"eval_gen_len": 9.8606,
|
| 597 |
+
"eval_loss": 0.2890518307685852,
|
| 598 |
+
"eval_runtime": 123.7854,
|
| 599 |
+
"eval_samples_per_second": 80.785,
|
| 600 |
+
"eval_steps_per_second": 1.268,
|
| 601 |
+
"step": 18500
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"epoch": 15.2,
|
| 605 |
+
"learning_rate": 4.377049180327869e-05,
|
| 606 |
+
"loss": 0.2653,
|
| 607 |
+
"step": 19000
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 15.2,
|
| 611 |
+
"eval_bleu": 73.6086,
|
| 612 |
+
"eval_gen_len": 9.8775,
|
| 613 |
+
"eval_loss": 0.2824092507362366,
|
| 614 |
+
"eval_runtime": 122.3472,
|
| 615 |
+
"eval_samples_per_second": 81.735,
|
| 616 |
+
"eval_steps_per_second": 1.283,
|
| 617 |
+
"step": 19000
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 15.6,
|
| 621 |
+
"learning_rate": 4.360655737704919e-05,
|
| 622 |
+
"loss": 0.2561,
|
| 623 |
+
"step": 19500
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 15.6,
|
| 627 |
+
"eval_bleu": 74.2558,
|
| 628 |
+
"eval_gen_len": 9.8651,
|
| 629 |
+
"eval_loss": 0.27599573135375977,
|
| 630 |
+
"eval_runtime": 123.4989,
|
| 631 |
+
"eval_samples_per_second": 80.972,
|
| 632 |
+
"eval_steps_per_second": 1.271,
|
| 633 |
+
"step": 19500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 16.0,
|
| 637 |
+
"learning_rate": 4.3442622950819674e-05,
|
| 638 |
+
"loss": 0.2534,
|
| 639 |
+
"step": 20000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 16.0,
|
| 643 |
+
"eval_bleu": 74.6646,
|
| 644 |
+
"eval_gen_len": 9.8609,
|
| 645 |
+
"eval_loss": 0.2678174674510956,
|
| 646 |
+
"eval_runtime": 121.7684,
|
| 647 |
+
"eval_samples_per_second": 82.123,
|
| 648 |
+
"eval_steps_per_second": 1.289,
|
| 649 |
+
"step": 20000
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 16.4,
|
| 653 |
+
"learning_rate": 4.327868852459017e-05,
|
| 654 |
+
"loss": 0.229,
|
| 655 |
+
"step": 20500
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 16.4,
|
| 659 |
+
"eval_bleu": 75.1771,
|
| 660 |
+
"eval_gen_len": 9.8587,
|
| 661 |
+
"eval_loss": 0.26594653725624084,
|
| 662 |
+
"eval_runtime": 122.704,
|
| 663 |
+
"eval_samples_per_second": 81.497,
|
| 664 |
+
"eval_steps_per_second": 1.28,
|
| 665 |
+
"step": 20500
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 16.8,
|
| 669 |
+
"learning_rate": 4.311475409836066e-05,
|
| 670 |
+
"loss": 0.23,
|
| 671 |
+
"step": 21000
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 16.8,
|
| 675 |
+
"eval_bleu": 75.2663,
|
| 676 |
+
"eval_gen_len": 9.8656,
|
| 677 |
+
"eval_loss": 0.25894829630851746,
|
| 678 |
+
"eval_runtime": 123.4498,
|
| 679 |
+
"eval_samples_per_second": 81.005,
|
| 680 |
+
"eval_steps_per_second": 1.272,
|
| 681 |
+
"step": 21000
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 17.2,
|
| 685 |
+
"learning_rate": 4.295081967213115e-05,
|
| 686 |
+
"loss": 0.2177,
|
| 687 |
+
"step": 21500
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 17.2,
|
| 691 |
+
"eval_bleu": 75.7616,
|
| 692 |
+
"eval_gen_len": 9.8622,
|
| 693 |
+
"eval_loss": 0.260859876871109,
|
| 694 |
+
"eval_runtime": 124.3613,
|
| 695 |
+
"eval_samples_per_second": 80.411,
|
| 696 |
+
"eval_steps_per_second": 1.262,
|
| 697 |
+
"step": 21500
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 17.6,
|
| 701 |
+
"learning_rate": 4.278688524590164e-05,
|
| 702 |
+
"loss": 0.2069,
|
| 703 |
+
"step": 22000
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 17.6,
|
| 707 |
+
"eval_bleu": 76.485,
|
| 708 |
+
"eval_gen_len": 9.8688,
|
| 709 |
+
"eval_loss": 0.25088420510292053,
|
| 710 |
+
"eval_runtime": 124.1311,
|
| 711 |
+
"eval_samples_per_second": 80.56,
|
| 712 |
+
"eval_steps_per_second": 1.265,
|
| 713 |
+
"step": 22000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 18.0,
|
| 717 |
+
"learning_rate": 4.262295081967213e-05,
|
| 718 |
+
"loss": 0.2092,
|
| 719 |
+
"step": 22500
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 18.0,
|
| 723 |
+
"eval_bleu": 76.8358,
|
| 724 |
+
"eval_gen_len": 9.8662,
|
| 725 |
+
"eval_loss": 0.24580596387386322,
|
| 726 |
+
"eval_runtime": 123.4291,
|
| 727 |
+
"eval_samples_per_second": 81.018,
|
| 728 |
+
"eval_steps_per_second": 1.272,
|
| 729 |
+
"step": 22500
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 18.4,
|
| 733 |
+
"learning_rate": 4.245901639344262e-05,
|
| 734 |
+
"loss": 0.1882,
|
| 735 |
+
"step": 23000
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 18.4,
|
| 739 |
+
"eval_bleu": 77.0551,
|
| 740 |
+
"eval_gen_len": 9.885,
|
| 741 |
+
"eval_loss": 0.24451805651187897,
|
| 742 |
+
"eval_runtime": 124.2811,
|
| 743 |
+
"eval_samples_per_second": 80.463,
|
| 744 |
+
"eval_steps_per_second": 1.263,
|
| 745 |
+
"step": 23000
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 18.8,
|
| 749 |
+
"learning_rate": 4.229508196721312e-05,
|
| 750 |
+
"loss": 0.1896,
|
| 751 |
+
"step": 23500
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"epoch": 18.8,
|
| 755 |
+
"eval_bleu": 77.6142,
|
| 756 |
+
"eval_gen_len": 9.8917,
|
| 757 |
+
"eval_loss": 0.23918285965919495,
|
| 758 |
+
"eval_runtime": 123.8288,
|
| 759 |
+
"eval_samples_per_second": 80.757,
|
| 760 |
+
"eval_steps_per_second": 1.268,
|
| 761 |
+
"step": 23500
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 19.2,
|
| 765 |
+
"learning_rate": 4.213114754098361e-05,
|
| 766 |
+
"loss": 0.1789,
|
| 767 |
+
"step": 24000
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 19.2,
|
| 771 |
+
"eval_bleu": 77.6144,
|
| 772 |
+
"eval_gen_len": 9.8919,
|
| 773 |
+
"eval_loss": 0.2408699244260788,
|
| 774 |
+
"eval_runtime": 122.8605,
|
| 775 |
+
"eval_samples_per_second": 81.393,
|
| 776 |
+
"eval_steps_per_second": 1.278,
|
| 777 |
+
"step": 24000
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 19.6,
|
| 781 |
+
"learning_rate": 4.19672131147541e-05,
|
| 782 |
+
"loss": 0.175,
|
| 783 |
+
"step": 24500
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 19.6,
|
| 787 |
+
"eval_bleu": 78.0091,
|
| 788 |
+
"eval_gen_len": 9.8878,
|
| 789 |
+
"eval_loss": 0.23325826227664948,
|
| 790 |
+
"eval_runtime": 123.7004,
|
| 791 |
+
"eval_samples_per_second": 80.841,
|
| 792 |
+
"eval_steps_per_second": 1.269,
|
| 793 |
+
"step": 24500
|
| 794 |
+
},
|
| 795 |
+
{
|
| 796 |
+
"epoch": 20.0,
|
| 797 |
+
"learning_rate": 4.1803278688524595e-05,
|
| 798 |
+
"loss": 0.1734,
|
| 799 |
+
"step": 25000
|
| 800 |
+
},
|
| 801 |
+
{
|
| 802 |
+
"epoch": 20.0,
|
| 803 |
+
"eval_bleu": 78.4943,
|
| 804 |
+
"eval_gen_len": 9.9012,
|
| 805 |
+
"eval_loss": 0.2311151772737503,
|
| 806 |
+
"eval_runtime": 124.6349,
|
| 807 |
+
"eval_samples_per_second": 80.234,
|
| 808 |
+
"eval_steps_per_second": 1.26,
|
| 809 |
+
"step": 25000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 20.4,
|
| 813 |
+
"learning_rate": 4.163934426229508e-05,
|
| 814 |
+
"loss": 0.1543,
|
| 815 |
+
"step": 25500
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 20.4,
|
| 819 |
+
"eval_bleu": 78.4902,
|
| 820 |
+
"eval_gen_len": 9.8748,
|
| 821 |
+
"eval_loss": 0.22952136397361755,
|
| 822 |
+
"eval_runtime": 125.3963,
|
| 823 |
+
"eval_samples_per_second": 79.747,
|
| 824 |
+
"eval_steps_per_second": 1.252,
|
| 825 |
+
"step": 25500
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 20.8,
|
| 829 |
+
"learning_rate": 4.1475409836065575e-05,
|
| 830 |
+
"loss": 0.1585,
|
| 831 |
+
"step": 26000
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 20.8,
|
| 835 |
+
"eval_bleu": 79.0041,
|
| 836 |
+
"eval_gen_len": 9.8936,
|
| 837 |
+
"eval_loss": 0.22459650039672852,
|
| 838 |
+
"eval_runtime": 125.0293,
|
| 839 |
+
"eval_samples_per_second": 79.981,
|
| 840 |
+
"eval_steps_per_second": 1.256,
|
| 841 |
+
"step": 26000
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 21.2,
|
| 845 |
+
"learning_rate": 4.131147540983607e-05,
|
| 846 |
+
"loss": 0.1476,
|
| 847 |
+
"step": 26500
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 21.2,
|
| 851 |
+
"eval_bleu": 78.922,
|
| 852 |
+
"eval_gen_len": 9.8887,
|
| 853 |
+
"eval_loss": 0.22683905065059662,
|
| 854 |
+
"eval_runtime": 124.4553,
|
| 855 |
+
"eval_samples_per_second": 80.35,
|
| 856 |
+
"eval_steps_per_second": 1.261,
|
| 857 |
+
"step": 26500
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 21.6,
|
| 861 |
+
"learning_rate": 4.1147540983606556e-05,
|
| 862 |
+
"loss": 0.1425,
|
| 863 |
+
"step": 27000
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 21.6,
|
| 867 |
+
"eval_bleu": 79.2218,
|
| 868 |
+
"eval_gen_len": 9.9064,
|
| 869 |
+
"eval_loss": 0.2226884663105011,
|
| 870 |
+
"eval_runtime": 124.563,
|
| 871 |
+
"eval_samples_per_second": 80.281,
|
| 872 |
+
"eval_steps_per_second": 1.26,
|
| 873 |
+
"step": 27000
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 22.0,
|
| 877 |
+
"learning_rate": 4.098360655737705e-05,
|
| 878 |
+
"loss": 0.1452,
|
| 879 |
+
"step": 27500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 22.0,
|
| 883 |
+
"eval_bleu": 79.6707,
|
| 884 |
+
"eval_gen_len": 9.9056,
|
| 885 |
+
"eval_loss": 0.21725259721279144,
|
| 886 |
+
"eval_runtime": 124.3401,
|
| 887 |
+
"eval_samples_per_second": 80.425,
|
| 888 |
+
"eval_steps_per_second": 1.263,
|
| 889 |
+
"step": 27500
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 22.4,
|
| 893 |
+
"learning_rate": 4.081967213114754e-05,
|
| 894 |
+
"loss": 0.1321,
|
| 895 |
+
"step": 28000
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 22.4,
|
| 899 |
+
"eval_bleu": 79.7907,
|
| 900 |
+
"eval_gen_len": 9.898,
|
| 901 |
+
"eval_loss": 0.21729987859725952,
|
| 902 |
+
"eval_runtime": 125.8166,
|
| 903 |
+
"eval_samples_per_second": 79.481,
|
| 904 |
+
"eval_steps_per_second": 1.248,
|
| 905 |
+
"step": 28000
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 22.8,
|
| 909 |
+
"learning_rate": 4.0655737704918036e-05,
|
| 910 |
+
"loss": 0.1361,
|
| 911 |
+
"step": 28500
|
| 912 |
+
},
|
| 913 |
+
{
|
| 914 |
+
"epoch": 22.8,
|
| 915 |
+
"eval_bleu": 80.2256,
|
| 916 |
+
"eval_gen_len": 9.911,
|
| 917 |
+
"eval_loss": 0.20989477634429932,
|
| 918 |
+
"eval_runtime": 126.9115,
|
| 919 |
+
"eval_samples_per_second": 78.795,
|
| 920 |
+
"eval_steps_per_second": 1.237,
|
| 921 |
+
"step": 28500
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 23.2,
|
| 925 |
+
"learning_rate": 4.049180327868853e-05,
|
| 926 |
+
"loss": 0.128,
|
| 927 |
+
"step": 29000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 23.2,
|
| 931 |
+
"eval_bleu": 80.2837,
|
| 932 |
+
"eval_gen_len": 9.9044,
|
| 933 |
+
"eval_loss": 0.21322031319141388,
|
| 934 |
+
"eval_runtime": 126.5113,
|
| 935 |
+
"eval_samples_per_second": 79.044,
|
| 936 |
+
"eval_steps_per_second": 1.241,
|
| 937 |
+
"step": 29000
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 23.6,
|
| 941 |
+
"learning_rate": 4.0327868852459016e-05,
|
| 942 |
+
"loss": 0.1218,
|
| 943 |
+
"step": 29500
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 23.6,
|
| 947 |
+
"eval_bleu": 80.6259,
|
| 948 |
+
"eval_gen_len": 9.9151,
|
| 949 |
+
"eval_loss": 0.21201317012310028,
|
| 950 |
+
"eval_runtime": 124.3696,
|
| 951 |
+
"eval_samples_per_second": 80.405,
|
| 952 |
+
"eval_steps_per_second": 1.262,
|
| 953 |
+
"step": 29500
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 24.0,
|
| 957 |
+
"learning_rate": 4.016393442622951e-05,
|
| 958 |
+
"loss": 0.1248,
|
| 959 |
+
"step": 30000
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 24.0,
|
| 963 |
+
"eval_bleu": 81.0878,
|
| 964 |
+
"eval_gen_len": 9.9092,
|
| 965 |
+
"eval_loss": 0.20630747079849243,
|
| 966 |
+
"eval_runtime": 126.764,
|
| 967 |
+
"eval_samples_per_second": 78.887,
|
| 968 |
+
"eval_steps_per_second": 1.239,
|
| 969 |
+
"step": 30000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 24.4,
|
| 973 |
+
"learning_rate": 4e-05,
|
| 974 |
+
"loss": 0.1113,
|
| 975 |
+
"step": 30500
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 24.4,
|
| 979 |
+
"eval_bleu": 81.0524,
|
| 980 |
+
"eval_gen_len": 9.8915,
|
| 981 |
+
"eval_loss": 0.2094167023897171,
|
| 982 |
+
"eval_runtime": 125.0054,
|
| 983 |
+
"eval_samples_per_second": 79.997,
|
| 984 |
+
"eval_steps_per_second": 1.256,
|
| 985 |
+
"step": 30500
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 24.8,
|
| 989 |
+
"learning_rate": 3.983606557377049e-05,
|
| 990 |
+
"loss": 0.1149,
|
| 991 |
+
"step": 31000
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 24.8,
|
| 995 |
+
"eval_bleu": 81.0803,
|
| 996 |
+
"eval_gen_len": 9.9123,
|
| 997 |
+
"eval_loss": 0.20733323693275452,
|
| 998 |
+
"eval_runtime": 125.3281,
|
| 999 |
+
"eval_samples_per_second": 79.791,
|
| 1000 |
+
"eval_steps_per_second": 1.253,
|
| 1001 |
+
"step": 31000
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 25.2,
|
| 1005 |
+
"learning_rate": 3.9672131147540983e-05,
|
| 1006 |
+
"loss": 0.1085,
|
| 1007 |
+
"step": 31500
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 25.2,
|
| 1011 |
+
"eval_bleu": 81.1504,
|
| 1012 |
+
"eval_gen_len": 9.8832,
|
| 1013 |
+
"eval_loss": 0.2083030790090561,
|
| 1014 |
+
"eval_runtime": 126.8593,
|
| 1015 |
+
"eval_samples_per_second": 78.828,
|
| 1016 |
+
"eval_steps_per_second": 1.238,
|
| 1017 |
+
"step": 31500
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 25.6,
|
| 1021 |
+
"learning_rate": 3.950819672131148e-05,
|
| 1022 |
+
"loss": 0.1057,
|
| 1023 |
+
"step": 32000
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 25.6,
|
| 1027 |
+
"eval_bleu": 81.4995,
|
| 1028 |
+
"eval_gen_len": 9.901,
|
| 1029 |
+
"eval_loss": 0.20488029718399048,
|
| 1030 |
+
"eval_runtime": 124.973,
|
| 1031 |
+
"eval_samples_per_second": 80.017,
|
| 1032 |
+
"eval_steps_per_second": 1.256,
|
| 1033 |
+
"step": 32000
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 26.0,
|
| 1037 |
+
"learning_rate": 3.934426229508197e-05,
|
| 1038 |
+
"loss": 0.1075,
|
| 1039 |
+
"step": 32500
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 26.0,
|
| 1043 |
+
"eval_bleu": 81.5477,
|
| 1044 |
+
"eval_gen_len": 9.9016,
|
| 1045 |
+
"eval_loss": 0.20381322503089905,
|
| 1046 |
+
"eval_runtime": 122.9039,
|
| 1047 |
+
"eval_samples_per_second": 81.364,
|
| 1048 |
+
"eval_steps_per_second": 1.277,
|
| 1049 |
+
"step": 32500
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 26.4,
|
| 1053 |
+
"learning_rate": 3.9180327868852464e-05,
|
| 1054 |
+
"loss": 0.0964,
|
| 1055 |
+
"step": 33000
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 26.4,
|
| 1059 |
+
"eval_bleu": 81.7251,
|
| 1060 |
+
"eval_gen_len": 9.8988,
|
| 1061 |
+
"eval_loss": 0.20466774702072144,
|
| 1062 |
+
"eval_runtime": 124.1671,
|
| 1063 |
+
"eval_samples_per_second": 80.537,
|
| 1064 |
+
"eval_steps_per_second": 1.264,
|
| 1065 |
+
"step": 33000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 26.8,
|
| 1069 |
+
"learning_rate": 3.901639344262295e-05,
|
| 1070 |
+
"loss": 0.0969,
|
| 1071 |
+
"step": 33500
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 26.8,
|
| 1075 |
+
"eval_bleu": 81.8982,
|
| 1076 |
+
"eval_gen_len": 9.8988,
|
| 1077 |
+
"eval_loss": 0.20009790360927582,
|
| 1078 |
+
"eval_runtime": 123.4229,
|
| 1079 |
+
"eval_samples_per_second": 81.022,
|
| 1080 |
+
"eval_steps_per_second": 1.272,
|
| 1081 |
+
"step": 33500
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 27.2,
|
| 1085 |
+
"learning_rate": 3.8852459016393444e-05,
|
| 1086 |
+
"loss": 0.095,
|
| 1087 |
+
"step": 34000
|
| 1088 |
+
},
|
| 1089 |
+
{
|
| 1090 |
+
"epoch": 27.2,
|
| 1091 |
+
"eval_bleu": 82.1864,
|
| 1092 |
+
"eval_gen_len": 9.9051,
|
| 1093 |
+
"eval_loss": 0.2042824774980545,
|
| 1094 |
+
"eval_runtime": 128.3513,
|
| 1095 |
+
"eval_samples_per_second": 77.911,
|
| 1096 |
+
"eval_steps_per_second": 1.223,
|
| 1097 |
+
"step": 34000
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 27.6,
|
| 1101 |
+
"learning_rate": 3.868852459016394e-05,
|
| 1102 |
+
"loss": 0.0898,
|
| 1103 |
+
"step": 34500
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 27.6,
|
| 1107 |
+
"eval_bleu": 82.2154,
|
| 1108 |
+
"eval_gen_len": 9.9245,
|
| 1109 |
+
"eval_loss": 0.2033461481332779,
|
| 1110 |
+
"eval_runtime": 126.5658,
|
| 1111 |
+
"eval_samples_per_second": 79.01,
|
| 1112 |
+
"eval_steps_per_second": 1.24,
|
| 1113 |
+
"step": 34500
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 28.0,
|
| 1117 |
+
"learning_rate": 3.8524590163934424e-05,
|
| 1118 |
+
"loss": 0.0915,
|
| 1119 |
+
"step": 35000
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 28.0,
|
| 1123 |
+
"eval_bleu": 82.3736,
|
| 1124 |
+
"eval_gen_len": 9.9161,
|
| 1125 |
+
"eval_loss": 0.19727951288223267,
|
| 1126 |
+
"eval_runtime": 105.7319,
|
| 1127 |
+
"eval_samples_per_second": 94.579,
|
| 1128 |
+
"eval_steps_per_second": 1.485,
|
| 1129 |
+
"step": 35000
|
| 1130 |
+
},
|
| 1131 |
+
{
|
| 1132 |
+
"epoch": 28.4,
|
| 1133 |
+
"learning_rate": 3.836065573770492e-05,
|
| 1134 |
+
"loss": 0.0848,
|
| 1135 |
+
"step": 35500
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 28.4,
|
| 1139 |
+
"eval_bleu": 82.495,
|
| 1140 |
+
"eval_gen_len": 9.9302,
|
| 1141 |
+
"eval_loss": 0.19799815118312836,
|
| 1142 |
+
"eval_runtime": 104.9507,
|
| 1143 |
+
"eval_samples_per_second": 95.283,
|
| 1144 |
+
"eval_steps_per_second": 1.496,
|
| 1145 |
+
"step": 35500
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 28.8,
|
| 1149 |
+
"learning_rate": 3.819672131147541e-05,
|
| 1150 |
+
"loss": 0.0845,
|
| 1151 |
+
"step": 36000
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 28.8,
|
| 1155 |
+
"eval_bleu": 82.4837,
|
| 1156 |
+
"eval_gen_len": 9.9116,
|
| 1157 |
+
"eval_loss": 0.19767090678215027,
|
| 1158 |
+
"eval_runtime": 106.5888,
|
| 1159 |
+
"eval_samples_per_second": 93.818,
|
| 1160 |
+
"eval_steps_per_second": 1.473,
|
| 1161 |
+
"step": 36000
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 29.2,
|
| 1165 |
+
"learning_rate": 3.8032786885245905e-05,
|
| 1166 |
+
"loss": 0.0815,
|
| 1167 |
+
"step": 36500
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 29.2,
|
| 1171 |
+
"eval_bleu": 82.4047,
|
| 1172 |
+
"eval_gen_len": 9.9089,
|
| 1173 |
+
"eval_loss": 0.19588139653205872,
|
| 1174 |
+
"eval_runtime": 107.9278,
|
| 1175 |
+
"eval_samples_per_second": 92.655,
|
| 1176 |
+
"eval_steps_per_second": 1.455,
|
| 1177 |
+
"step": 36500
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 29.6,
|
| 1181 |
+
"learning_rate": 3.78688524590164e-05,
|
| 1182 |
+
"loss": 0.0795,
|
| 1183 |
+
"step": 37000
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 29.6,
|
| 1187 |
+
"eval_bleu": 82.722,
|
| 1188 |
+
"eval_gen_len": 9.9046,
|
| 1189 |
+
"eval_loss": 0.1979523003101349,
|
| 1190 |
+
"eval_runtime": 109.3961,
|
| 1191 |
+
"eval_samples_per_second": 91.411,
|
| 1192 |
+
"eval_steps_per_second": 1.435,
|
| 1193 |
+
"step": 37000
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 30.0,
|
| 1197 |
+
"learning_rate": 3.7704918032786885e-05,
|
| 1198 |
+
"loss": 0.0808,
|
| 1199 |
+
"step": 37500
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 30.0,
|
| 1203 |
+
"eval_bleu": 82.6578,
|
| 1204 |
+
"eval_gen_len": 9.8982,
|
| 1205 |
+
"eval_loss": 0.19637715816497803,
|
| 1206 |
+
"eval_runtime": 109.5695,
|
| 1207 |
+
"eval_samples_per_second": 91.266,
|
| 1208 |
+
"eval_steps_per_second": 1.433,
|
| 1209 |
+
"step": 37500
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 30.4,
|
| 1213 |
+
"learning_rate": 3.754098360655738e-05,
|
| 1214 |
+
"loss": 0.0732,
|
| 1215 |
+
"step": 38000
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 30.4,
|
| 1219 |
+
"eval_bleu": 82.9919,
|
| 1220 |
+
"eval_gen_len": 9.9044,
|
| 1221 |
+
"eval_loss": 0.19727516174316406,
|
| 1222 |
+
"eval_runtime": 114.1436,
|
| 1223 |
+
"eval_samples_per_second": 87.609,
|
| 1224 |
+
"eval_steps_per_second": 1.375,
|
| 1225 |
+
"step": 38000
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 30.8,
|
| 1229 |
+
"learning_rate": 3.737704918032787e-05,
|
| 1230 |
+
"loss": 0.0746,
|
| 1231 |
+
"step": 38500
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 30.8,
|
| 1235 |
+
"eval_bleu": 82.6143,
|
| 1236 |
+
"eval_gen_len": 9.9165,
|
| 1237 |
+
"eval_loss": 0.19912780821323395,
|
| 1238 |
+
"eval_runtime": 111.6449,
|
| 1239 |
+
"eval_samples_per_second": 89.57,
|
| 1240 |
+
"eval_steps_per_second": 1.406,
|
| 1241 |
+
"step": 38500
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 31.2,
|
| 1245 |
+
"learning_rate": 3.721311475409836e-05,
|
| 1246 |
+
"loss": 0.0707,
|
| 1247 |
+
"step": 39000
|
| 1248 |
+
},
|
| 1249 |
+
{
|
| 1250 |
+
"epoch": 31.2,
|
| 1251 |
+
"eval_bleu": 82.9765,
|
| 1252 |
+
"eval_gen_len": 9.9001,
|
| 1253 |
+
"eval_loss": 0.19909825921058655,
|
| 1254 |
+
"eval_runtime": 116.7381,
|
| 1255 |
+
"eval_samples_per_second": 85.662,
|
| 1256 |
+
"eval_steps_per_second": 1.345,
|
| 1257 |
+
"step": 39000
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 31.6,
|
| 1261 |
+
"learning_rate": 3.704918032786885e-05,
|
| 1262 |
+
"loss": 0.0709,
|
| 1263 |
+
"step": 39500
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 31.6,
|
| 1267 |
+
"eval_bleu": 83.0914,
|
| 1268 |
+
"eval_gen_len": 9.8965,
|
| 1269 |
+
"eval_loss": 0.19552859663963318,
|
| 1270 |
+
"eval_runtime": 112.5699,
|
| 1271 |
+
"eval_samples_per_second": 88.834,
|
| 1272 |
+
"eval_steps_per_second": 1.395,
|
| 1273 |
+
"step": 39500
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 32.0,
|
| 1277 |
+
"learning_rate": 3.6885245901639346e-05,
|
| 1278 |
+
"loss": 0.0719,
|
| 1279 |
+
"step": 40000
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 32.0,
|
| 1283 |
+
"eval_bleu": 83.2552,
|
| 1284 |
+
"eval_gen_len": 9.9192,
|
| 1285 |
+
"eval_loss": 0.1897631287574768,
|
| 1286 |
+
"eval_runtime": 111.6178,
|
| 1287 |
+
"eval_samples_per_second": 89.591,
|
| 1288 |
+
"eval_steps_per_second": 1.407,
|
| 1289 |
+
"step": 40000
|
| 1290 |
+
},
|
| 1291 |
+
{
|
| 1292 |
+
"epoch": 32.4,
|
| 1293 |
+
"learning_rate": 3.672131147540984e-05,
|
| 1294 |
+
"loss": 0.0645,
|
| 1295 |
+
"step": 40500
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 32.4,
|
| 1299 |
+
"eval_bleu": 83.2469,
|
| 1300 |
+
"eval_gen_len": 9.9243,
|
| 1301 |
+
"eval_loss": 0.19487988948822021,
|
| 1302 |
+
"eval_runtime": 113.1976,
|
| 1303 |
+
"eval_samples_per_second": 88.341,
|
| 1304 |
+
"eval_steps_per_second": 1.387,
|
| 1305 |
+
"step": 40500
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 32.8,
|
| 1309 |
+
"learning_rate": 3.655737704918033e-05,
|
| 1310 |
+
"loss": 0.0668,
|
| 1311 |
+
"step": 41000
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 32.8,
|
| 1315 |
+
"eval_bleu": 83.554,
|
| 1316 |
+
"eval_gen_len": 9.927,
|
| 1317 |
+
"eval_loss": 0.19293373823165894,
|
| 1318 |
+
"eval_runtime": 115.9999,
|
| 1319 |
+
"eval_samples_per_second": 86.207,
|
| 1320 |
+
"eval_steps_per_second": 1.353,
|
| 1321 |
+
"step": 41000
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 33.2,
|
| 1325 |
+
"learning_rate": 3.6393442622950826e-05,
|
| 1326 |
+
"loss": 0.0626,
|
| 1327 |
+
"step": 41500
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 33.2,
|
| 1331 |
+
"eval_bleu": 83.451,
|
| 1332 |
+
"eval_gen_len": 9.919,
|
| 1333 |
+
"eval_loss": 0.19273407757282257,
|
| 1334 |
+
"eval_runtime": 118.7666,
|
| 1335 |
+
"eval_samples_per_second": 84.199,
|
| 1336 |
+
"eval_steps_per_second": 1.322,
|
| 1337 |
+
"step": 41500
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 33.6,
|
| 1341 |
+
"learning_rate": 3.622950819672131e-05,
|
| 1342 |
+
"loss": 0.0616,
|
| 1343 |
+
"step": 42000
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 33.6,
|
| 1347 |
+
"eval_bleu": 83.7799,
|
| 1348 |
+
"eval_gen_len": 9.9142,
|
| 1349 |
+
"eval_loss": 0.1896318793296814,
|
| 1350 |
+
"eval_runtime": 119.0485,
|
| 1351 |
+
"eval_samples_per_second": 83.999,
|
| 1352 |
+
"eval_steps_per_second": 1.319,
|
| 1353 |
+
"step": 42000
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 34.0,
|
| 1357 |
+
"learning_rate": 3.6065573770491806e-05,
|
| 1358 |
+
"loss": 0.0636,
|
| 1359 |
+
"step": 42500
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 34.0,
|
| 1363 |
+
"eval_bleu": 83.5126,
|
| 1364 |
+
"eval_gen_len": 9.8988,
|
| 1365 |
+
"eval_loss": 0.19057811796665192,
|
| 1366 |
+
"eval_runtime": 119.0601,
|
| 1367 |
+
"eval_samples_per_second": 83.991,
|
| 1368 |
+
"eval_steps_per_second": 1.319,
|
| 1369 |
+
"step": 42500
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 34.4,
|
| 1373 |
+
"learning_rate": 3.590163934426229e-05,
|
| 1374 |
+
"loss": 0.0576,
|
| 1375 |
+
"step": 43000
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 34.4,
|
| 1379 |
+
"eval_bleu": 83.5655,
|
| 1380 |
+
"eval_gen_len": 9.9154,
|
| 1381 |
+
"eval_loss": 0.19394218921661377,
|
| 1382 |
+
"eval_runtime": 119.5237,
|
| 1383 |
+
"eval_samples_per_second": 83.665,
|
| 1384 |
+
"eval_steps_per_second": 1.314,
|
| 1385 |
+
"step": 43000
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 34.8,
|
| 1389 |
+
"learning_rate": 3.5737704918032786e-05,
|
| 1390 |
+
"loss": 0.0585,
|
| 1391 |
+
"step": 43500
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 34.8,
|
| 1395 |
+
"eval_bleu": 83.6287,
|
| 1396 |
+
"eval_gen_len": 9.9233,
|
| 1397 |
+
"eval_loss": 0.19454576075077057,
|
| 1398 |
+
"eval_runtime": 119.4134,
|
| 1399 |
+
"eval_samples_per_second": 83.743,
|
| 1400 |
+
"eval_steps_per_second": 1.315,
|
| 1401 |
+
"step": 43500
|
| 1402 |
+
},
|
| 1403 |
+
{
|
| 1404 |
+
"epoch": 35.2,
|
| 1405 |
+
"learning_rate": 3.557377049180328e-05,
|
| 1406 |
+
"loss": 0.0568,
|
| 1407 |
+
"step": 44000
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 35.2,
|
| 1411 |
+
"eval_bleu": 83.6904,
|
| 1412 |
+
"eval_gen_len": 9.907,
|
| 1413 |
+
"eval_loss": 0.19391930103302002,
|
| 1414 |
+
"eval_runtime": 119.702,
|
| 1415 |
+
"eval_samples_per_second": 83.541,
|
| 1416 |
+
"eval_steps_per_second": 1.312,
|
| 1417 |
+
"step": 44000
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 35.6,
|
| 1421 |
+
"learning_rate": 3.5409836065573773e-05,
|
| 1422 |
+
"loss": 0.0551,
|
| 1423 |
+
"step": 44500
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"epoch": 35.6,
|
| 1427 |
+
"eval_bleu": 83.9373,
|
| 1428 |
+
"eval_gen_len": 9.9202,
|
| 1429 |
+
"eval_loss": 0.19054347276687622,
|
| 1430 |
+
"eval_runtime": 118.199,
|
| 1431 |
+
"eval_samples_per_second": 84.603,
|
| 1432 |
+
"eval_steps_per_second": 1.328,
|
| 1433 |
+
"step": 44500
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 36.0,
|
| 1437 |
+
"learning_rate": 3.524590163934427e-05,
|
| 1438 |
+
"loss": 0.0563,
|
| 1439 |
+
"step": 45000
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 36.0,
|
| 1443 |
+
"eval_bleu": 84.1348,
|
| 1444 |
+
"eval_gen_len": 9.9207,
|
| 1445 |
+
"eval_loss": 0.1921459436416626,
|
| 1446 |
+
"eval_runtime": 119.546,
|
| 1447 |
+
"eval_samples_per_second": 83.65,
|
| 1448 |
+
"eval_steps_per_second": 1.313,
|
| 1449 |
+
"step": 45000
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 36.4,
|
| 1453 |
+
"learning_rate": 3.508196721311476e-05,
|
| 1454 |
+
"loss": 0.0514,
|
| 1455 |
+
"step": 45500
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 36.4,
|
| 1459 |
+
"eval_bleu": 84.1097,
|
| 1460 |
+
"eval_gen_len": 9.9185,
|
| 1461 |
+
"eval_loss": 0.19464583694934845,
|
| 1462 |
+
"eval_runtime": 119.8131,
|
| 1463 |
+
"eval_samples_per_second": 83.463,
|
| 1464 |
+
"eval_steps_per_second": 1.31,
|
| 1465 |
+
"step": 45500
|
| 1466 |
+
},
|
| 1467 |
+
{
|
| 1468 |
+
"epoch": 36.8,
|
| 1469 |
+
"learning_rate": 3.491803278688525e-05,
|
| 1470 |
+
"loss": 0.0534,
|
| 1471 |
+
"step": 46000
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 36.8,
|
| 1475 |
+
"eval_bleu": 84.0075,
|
| 1476 |
+
"eval_gen_len": 9.9111,
|
| 1477 |
+
"eval_loss": 0.19089433550834656,
|
| 1478 |
+
"eval_runtime": 118.1118,
|
| 1479 |
+
"eval_samples_per_second": 84.666,
|
| 1480 |
+
"eval_steps_per_second": 1.329,
|
| 1481 |
+
"step": 46000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 37.2,
|
| 1485 |
+
"learning_rate": 3.475409836065574e-05,
|
| 1486 |
+
"loss": 0.05,
|
| 1487 |
+
"step": 46500
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 37.2,
|
| 1491 |
+
"eval_bleu": 84.0187,
|
| 1492 |
+
"eval_gen_len": 9.9198,
|
| 1493 |
+
"eval_loss": 0.1975044161081314,
|
| 1494 |
+
"eval_runtime": 118.0704,
|
| 1495 |
+
"eval_samples_per_second": 84.695,
|
| 1496 |
+
"eval_steps_per_second": 1.33,
|
| 1497 |
+
"step": 46500
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 37.6,
|
| 1501 |
+
"learning_rate": 3.459016393442623e-05,
|
| 1502 |
+
"loss": 0.0498,
|
| 1503 |
+
"step": 47000
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 37.6,
|
| 1507 |
+
"eval_bleu": 84.0124,
|
| 1508 |
+
"eval_gen_len": 9.9205,
|
| 1509 |
+
"eval_loss": 0.19323572516441345,
|
| 1510 |
+
"eval_runtime": 117.9012,
|
| 1511 |
+
"eval_samples_per_second": 84.817,
|
| 1512 |
+
"eval_steps_per_second": 1.332,
|
| 1513 |
+
"step": 47000
|
| 1514 |
+
},
|
| 1515 |
+
{
|
| 1516 |
+
"epoch": 38.0,
|
| 1517 |
+
"learning_rate": 3.442622950819672e-05,
|
| 1518 |
+
"loss": 0.0496,
|
| 1519 |
+
"step": 47500
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 38.0,
|
| 1523 |
+
"eval_bleu": 84.2227,
|
| 1524 |
+
"eval_gen_len": 9.9151,
|
| 1525 |
+
"eval_loss": 0.1907936930656433,
|
| 1526 |
+
"eval_runtime": 118.1549,
|
| 1527 |
+
"eval_samples_per_second": 84.635,
|
| 1528 |
+
"eval_steps_per_second": 1.329,
|
| 1529 |
+
"step": 47500
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 38.4,
|
| 1533 |
+
"learning_rate": 3.4262295081967214e-05,
|
| 1534 |
+
"loss": 0.0474,
|
| 1535 |
+
"step": 48000
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 38.4,
|
| 1539 |
+
"eval_bleu": 84.1768,
|
| 1540 |
+
"eval_gen_len": 9.9068,
|
| 1541 |
+
"eval_loss": 0.192445769906044,
|
| 1542 |
+
"eval_runtime": 121.5905,
|
| 1543 |
+
"eval_samples_per_second": 82.243,
|
| 1544 |
+
"eval_steps_per_second": 1.291,
|
| 1545 |
+
"step": 48000
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 38.8,
|
| 1549 |
+
"learning_rate": 3.409836065573771e-05,
|
| 1550 |
+
"loss": 0.0473,
|
| 1551 |
+
"step": 48500
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 38.8,
|
| 1555 |
+
"eval_bleu": 84.2946,
|
| 1556 |
+
"eval_gen_len": 9.9193,
|
| 1557 |
+
"eval_loss": 0.1934969127178192,
|
| 1558 |
+
"eval_runtime": 119.2854,
|
| 1559 |
+
"eval_samples_per_second": 83.833,
|
| 1560 |
+
"eval_steps_per_second": 1.316,
|
| 1561 |
+
"step": 48500
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 39.2,
|
| 1565 |
+
"learning_rate": 3.39344262295082e-05,
|
| 1566 |
+
"loss": 0.0454,
|
| 1567 |
+
"step": 49000
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 39.2,
|
| 1571 |
+
"eval_bleu": 84.3262,
|
| 1572 |
+
"eval_gen_len": 9.9164,
|
| 1573 |
+
"eval_loss": 0.1953597515821457,
|
| 1574 |
+
"eval_runtime": 119.0304,
|
| 1575 |
+
"eval_samples_per_second": 84.012,
|
| 1576 |
+
"eval_steps_per_second": 1.319,
|
| 1577 |
+
"step": 49000
|
| 1578 |
+
},
|
| 1579 |
+
{
|
| 1580 |
+
"epoch": 39.6,
|
| 1581 |
+
"learning_rate": 3.3770491803278695e-05,
|
| 1582 |
+
"loss": 0.0453,
|
| 1583 |
+
"step": 49500
|
| 1584 |
+
},
|
| 1585 |
+
{
|
| 1586 |
+
"epoch": 39.6,
|
| 1587 |
+
"eval_bleu": 84.4165,
|
| 1588 |
+
"eval_gen_len": 9.9107,
|
| 1589 |
+
"eval_loss": 0.19031359255313873,
|
| 1590 |
+
"eval_runtime": 120.2198,
|
| 1591 |
+
"eval_samples_per_second": 83.181,
|
| 1592 |
+
"eval_steps_per_second": 1.306,
|
| 1593 |
+
"step": 49500
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 40.0,
|
| 1597 |
+
"learning_rate": 3.360655737704918e-05,
|
| 1598 |
+
"loss": 0.0461,
|
| 1599 |
+
"step": 50000
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 40.0,
|
| 1603 |
+
"eval_bleu": 84.4289,
|
| 1604 |
+
"eval_gen_len": 9.9216,
|
| 1605 |
+
"eval_loss": 0.1906299889087677,
|
| 1606 |
+
"eval_runtime": 118.8797,
|
| 1607 |
+
"eval_samples_per_second": 84.119,
|
| 1608 |
+
"eval_steps_per_second": 1.321,
|
| 1609 |
+
"step": 50000
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 40.4,
|
| 1613 |
+
"learning_rate": 3.3442622950819675e-05,
|
| 1614 |
+
"loss": 0.0415,
|
| 1615 |
+
"step": 50500
|
| 1616 |
+
},
|
| 1617 |
+
{
|
| 1618 |
+
"epoch": 40.4,
|
| 1619 |
+
"eval_bleu": 84.4636,
|
| 1620 |
+
"eval_gen_len": 9.9082,
|
| 1621 |
+
"eval_loss": 0.19302137196063995,
|
| 1622 |
+
"eval_runtime": 118.8718,
|
| 1623 |
+
"eval_samples_per_second": 84.124,
|
| 1624 |
+
"eval_steps_per_second": 1.321,
|
| 1625 |
+
"step": 50500
|
| 1626 |
+
},
|
| 1627 |
+
{
|
| 1628 |
+
"epoch": 40.8,
|
| 1629 |
+
"learning_rate": 3.327868852459017e-05,
|
| 1630 |
+
"loss": 0.044,
|
| 1631 |
+
"step": 51000
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 40.8,
|
| 1635 |
+
"eval_bleu": 84.5092,
|
| 1636 |
+
"eval_gen_len": 9.9237,
|
| 1637 |
+
"eval_loss": 0.18893210589885712,
|
| 1638 |
+
"eval_runtime": 120.9835,
|
| 1639 |
+
"eval_samples_per_second": 82.656,
|
| 1640 |
+
"eval_steps_per_second": 1.298,
|
| 1641 |
+
"step": 51000
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 41.2,
|
| 1645 |
+
"learning_rate": 3.3114754098360655e-05,
|
| 1646 |
+
"loss": 0.043,
|
| 1647 |
+
"step": 51500
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 41.2,
|
| 1651 |
+
"eval_bleu": 84.5908,
|
| 1652 |
+
"eval_gen_len": 9.9221,
|
| 1653 |
+
"eval_loss": 0.1906319111585617,
|
| 1654 |
+
"eval_runtime": 122.6906,
|
| 1655 |
+
"eval_samples_per_second": 81.506,
|
| 1656 |
+
"eval_steps_per_second": 1.28,
|
| 1657 |
+
"step": 51500
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 41.6,
|
| 1661 |
+
"learning_rate": 3.295081967213115e-05,
|
| 1662 |
+
"loss": 0.0413,
|
| 1663 |
+
"step": 52000
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 41.6,
|
| 1667 |
+
"eval_bleu": 84.7197,
|
| 1668 |
+
"eval_gen_len": 9.9113,
|
| 1669 |
+
"eval_loss": 0.19282755255699158,
|
| 1670 |
+
"eval_runtime": 121.4487,
|
| 1671 |
+
"eval_samples_per_second": 82.339,
|
| 1672 |
+
"eval_steps_per_second": 1.293,
|
| 1673 |
+
"step": 52000
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 42.0,
|
| 1677 |
+
"learning_rate": 3.2786885245901635e-05,
|
| 1678 |
+
"loss": 0.0401,
|
| 1679 |
+
"step": 52500
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 42.0,
|
| 1683 |
+
"eval_bleu": 84.7895,
|
| 1684 |
+
"eval_gen_len": 9.9215,
|
| 1685 |
+
"eval_loss": 0.19361305236816406,
|
| 1686 |
+
"eval_runtime": 120.7154,
|
| 1687 |
+
"eval_samples_per_second": 82.839,
|
| 1688 |
+
"eval_steps_per_second": 1.301,
|
| 1689 |
+
"step": 52500
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 42.4,
|
| 1693 |
+
"learning_rate": 3.2622950819672136e-05,
|
| 1694 |
+
"loss": 0.0385,
|
| 1695 |
+
"step": 53000
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 42.4,
|
| 1699 |
+
"eval_bleu": 84.7187,
|
| 1700 |
+
"eval_gen_len": 9.9239,
|
| 1701 |
+
"eval_loss": 0.19195546209812164,
|
| 1702 |
+
"eval_runtime": 119.559,
|
| 1703 |
+
"eval_samples_per_second": 83.641,
|
| 1704 |
+
"eval_steps_per_second": 1.313,
|
| 1705 |
+
"step": 53000
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 42.8,
|
| 1709 |
+
"learning_rate": 3.245901639344263e-05,
|
| 1710 |
+
"loss": 0.0387,
|
| 1711 |
+
"step": 53500
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 42.8,
|
| 1715 |
+
"eval_bleu": 84.7193,
|
| 1716 |
+
"eval_gen_len": 9.9146,
|
| 1717 |
+
"eval_loss": 0.19131682813167572,
|
| 1718 |
+
"eval_runtime": 121.1877,
|
| 1719 |
+
"eval_samples_per_second": 82.517,
|
| 1720 |
+
"eval_steps_per_second": 1.296,
|
| 1721 |
+
"step": 53500
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 43.2,
|
| 1725 |
+
"learning_rate": 3.2295081967213116e-05,
|
| 1726 |
+
"loss": 0.0389,
|
| 1727 |
+
"step": 54000
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 43.2,
|
| 1731 |
+
"eval_bleu": 84.6862,
|
| 1732 |
+
"eval_gen_len": 9.9225,
|
| 1733 |
+
"eval_loss": 0.19187390804290771,
|
| 1734 |
+
"eval_runtime": 120.9642,
|
| 1735 |
+
"eval_samples_per_second": 82.669,
|
| 1736 |
+
"eval_steps_per_second": 1.298,
|
| 1737 |
+
"step": 54000
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 43.6,
|
| 1741 |
+
"learning_rate": 3.213114754098361e-05,
|
| 1742 |
+
"loss": 0.0372,
|
| 1743 |
+
"step": 54500
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 43.6,
|
| 1747 |
+
"eval_bleu": 84.7769,
|
| 1748 |
+
"eval_gen_len": 9.9285,
|
| 1749 |
+
"eval_loss": 0.19241966307163239,
|
| 1750 |
+
"eval_runtime": 125.5973,
|
| 1751 |
+
"eval_samples_per_second": 79.62,
|
| 1752 |
+
"eval_steps_per_second": 1.25,
|
| 1753 |
+
"step": 54500
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 44.0,
|
| 1757 |
+
"learning_rate": 3.19672131147541e-05,
|
| 1758 |
+
"loss": 0.0383,
|
| 1759 |
+
"step": 55000
|
| 1760 |
+
},
|
| 1761 |
+
{
|
| 1762 |
+
"epoch": 44.0,
|
| 1763 |
+
"eval_bleu": 84.9535,
|
| 1764 |
+
"eval_gen_len": 9.9347,
|
| 1765 |
+
"eval_loss": 0.19236235320568085,
|
| 1766 |
+
"eval_runtime": 122.9448,
|
| 1767 |
+
"eval_samples_per_second": 81.337,
|
| 1768 |
+
"eval_steps_per_second": 1.277,
|
| 1769 |
+
"step": 55000
|
| 1770 |
+
},
|
| 1771 |
+
{
|
| 1772 |
+
"epoch": 44.4,
|
| 1773 |
+
"learning_rate": 3.180327868852459e-05,
|
| 1774 |
+
"loss": 0.0347,
|
| 1775 |
+
"step": 55500
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 44.4,
|
| 1779 |
+
"eval_bleu": 84.9326,
|
| 1780 |
+
"eval_gen_len": 9.9288,
|
| 1781 |
+
"eval_loss": 0.1917337328195572,
|
| 1782 |
+
"eval_runtime": 121.8141,
|
| 1783 |
+
"eval_samples_per_second": 82.092,
|
| 1784 |
+
"eval_steps_per_second": 1.289,
|
| 1785 |
+
"step": 55500
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 44.8,
|
| 1789 |
+
"learning_rate": 3.163934426229508e-05,
|
| 1790 |
+
"loss": 0.0364,
|
| 1791 |
+
"step": 56000
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 44.8,
|
| 1795 |
+
"eval_bleu": 85.0653,
|
| 1796 |
+
"eval_gen_len": 9.9159,
|
| 1797 |
+
"eval_loss": 0.19078262150287628,
|
| 1798 |
+
"eval_runtime": 122.743,
|
| 1799 |
+
"eval_samples_per_second": 81.471,
|
| 1800 |
+
"eval_steps_per_second": 1.279,
|
| 1801 |
+
"step": 56000
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 45.2,
|
| 1805 |
+
"learning_rate": 3.1475409836065576e-05,
|
| 1806 |
+
"loss": 0.035,
|
| 1807 |
+
"step": 56500
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 45.2,
|
| 1811 |
+
"eval_bleu": 84.8097,
|
| 1812 |
+
"eval_gen_len": 9.9093,
|
| 1813 |
+
"eval_loss": 0.19484488666057587,
|
| 1814 |
+
"eval_runtime": 121.3548,
|
| 1815 |
+
"eval_samples_per_second": 82.403,
|
| 1816 |
+
"eval_steps_per_second": 1.294,
|
| 1817 |
+
"step": 56500
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 45.6,
|
| 1821 |
+
"learning_rate": 3.131147540983606e-05,
|
| 1822 |
+
"loss": 0.0338,
|
| 1823 |
+
"step": 57000
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 45.6,
|
| 1827 |
+
"eval_bleu": 84.9659,
|
| 1828 |
+
"eval_gen_len": 9.9217,
|
| 1829 |
+
"eval_loss": 0.1974213719367981,
|
| 1830 |
+
"eval_runtime": 120.7302,
|
| 1831 |
+
"eval_samples_per_second": 82.829,
|
| 1832 |
+
"eval_steps_per_second": 1.3,
|
| 1833 |
+
"step": 57000
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 46.0,
|
| 1837 |
+
"learning_rate": 3.114754098360656e-05,
|
| 1838 |
+
"loss": 0.0353,
|
| 1839 |
+
"step": 57500
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 46.0,
|
| 1843 |
+
"eval_bleu": 85.0476,
|
| 1844 |
+
"eval_gen_len": 9.9244,
|
| 1845 |
+
"eval_loss": 0.19343513250350952,
|
| 1846 |
+
"eval_runtime": 118.747,
|
| 1847 |
+
"eval_samples_per_second": 84.213,
|
| 1848 |
+
"eval_steps_per_second": 1.322,
|
| 1849 |
+
"step": 57500
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 46.4,
|
| 1853 |
+
"learning_rate": 3.098360655737705e-05,
|
| 1854 |
+
"loss": 0.0331,
|
| 1855 |
+
"step": 58000
|
| 1856 |
+
},
|
| 1857 |
+
{
|
| 1858 |
+
"epoch": 46.4,
|
| 1859 |
+
"eval_bleu": 85.0708,
|
| 1860 |
+
"eval_gen_len": 9.9146,
|
| 1861 |
+
"eval_loss": 0.19627127051353455,
|
| 1862 |
+
"eval_runtime": 121.8836,
|
| 1863 |
+
"eval_samples_per_second": 82.046,
|
| 1864 |
+
"eval_steps_per_second": 1.288,
|
| 1865 |
+
"step": 58000
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 46.8,
|
| 1869 |
+
"learning_rate": 3.0819672131147544e-05,
|
| 1870 |
+
"loss": 0.0333,
|
| 1871 |
+
"step": 58500
|
| 1872 |
+
},
|
| 1873 |
+
{
|
| 1874 |
+
"epoch": 46.8,
|
| 1875 |
+
"eval_bleu": 84.9386,
|
| 1876 |
+
"eval_gen_len": 9.9224,
|
| 1877 |
+
"eval_loss": 0.19614210724830627,
|
| 1878 |
+
"eval_runtime": 121.7048,
|
| 1879 |
+
"eval_samples_per_second": 82.166,
|
| 1880 |
+
"eval_steps_per_second": 1.29,
|
| 1881 |
+
"step": 58500
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 47.2,
|
| 1885 |
+
"learning_rate": 3.065573770491804e-05,
|
| 1886 |
+
"loss": 0.0326,
|
| 1887 |
+
"step": 59000
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 47.2,
|
| 1891 |
+
"eval_bleu": 84.9433,
|
| 1892 |
+
"eval_gen_len": 9.918,
|
| 1893 |
+
"eval_loss": 0.19616641104221344,
|
| 1894 |
+
"eval_runtime": 120.7919,
|
| 1895 |
+
"eval_samples_per_second": 82.787,
|
| 1896 |
+
"eval_steps_per_second": 1.3,
|
| 1897 |
+
"step": 59000
|
| 1898 |
+
},
|
| 1899 |
+
{
|
| 1900 |
+
"epoch": 47.6,
|
| 1901 |
+
"learning_rate": 3.0491803278688524e-05,
|
| 1902 |
+
"loss": 0.0312,
|
| 1903 |
+
"step": 59500
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"epoch": 47.6,
|
| 1907 |
+
"eval_bleu": 84.8756,
|
| 1908 |
+
"eval_gen_len": 9.9365,
|
| 1909 |
+
"eval_loss": 0.1943608969449997,
|
| 1910 |
+
"eval_runtime": 120.9831,
|
| 1911 |
+
"eval_samples_per_second": 82.656,
|
| 1912 |
+
"eval_steps_per_second": 1.298,
|
| 1913 |
+
"step": 59500
|
| 1914 |
+
},
|
| 1915 |
+
{
|
| 1916 |
+
"epoch": 48.0,
|
| 1917 |
+
"learning_rate": 3.0327868852459017e-05,
|
| 1918 |
+
"loss": 0.0327,
|
| 1919 |
+
"step": 60000
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 48.0,
|
| 1923 |
+
"eval_bleu": 84.8764,
|
| 1924 |
+
"eval_gen_len": 9.9289,
|
| 1925 |
+
"eval_loss": 0.19547414779663086,
|
| 1926 |
+
"eval_runtime": 120.3613,
|
| 1927 |
+
"eval_samples_per_second": 83.083,
|
| 1928 |
+
"eval_steps_per_second": 1.304,
|
| 1929 |
+
"step": 60000
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 48.4,
|
| 1933 |
+
"learning_rate": 3.016393442622951e-05,
|
| 1934 |
+
"loss": 0.0303,
|
| 1935 |
+
"step": 60500
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 48.4,
|
| 1939 |
+
"eval_bleu": 85.0585,
|
| 1940 |
+
"eval_gen_len": 9.9279,
|
| 1941 |
+
"eval_loss": 0.19307781755924225,
|
| 1942 |
+
"eval_runtime": 121.2016,
|
| 1943 |
+
"eval_samples_per_second": 82.507,
|
| 1944 |
+
"eval_steps_per_second": 1.295,
|
| 1945 |
+
"step": 60500
|
| 1946 |
+
},
|
| 1947 |
+
{
|
| 1948 |
+
"epoch": 48.8,
|
| 1949 |
+
"learning_rate": 3e-05,
|
| 1950 |
+
"loss": 0.0305,
|
| 1951 |
+
"step": 61000
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 48.8,
|
| 1955 |
+
"eval_bleu": 85.2865,
|
| 1956 |
+
"eval_gen_len": 9.9287,
|
| 1957 |
+
"eval_loss": 0.19452740252017975,
|
| 1958 |
+
"eval_runtime": 123.6999,
|
| 1959 |
+
"eval_samples_per_second": 80.841,
|
| 1960 |
+
"eval_steps_per_second": 1.269,
|
| 1961 |
+
"step": 61000
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 49.2,
|
| 1965 |
+
"learning_rate": 2.9836065573770494e-05,
|
| 1966 |
+
"loss": 0.0296,
|
| 1967 |
+
"step": 61500
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 49.2,
|
| 1971 |
+
"eval_bleu": 85.1538,
|
| 1972 |
+
"eval_gen_len": 9.9253,
|
| 1973 |
+
"eval_loss": 0.19456754624843597,
|
| 1974 |
+
"eval_runtime": 123.3373,
|
| 1975 |
+
"eval_samples_per_second": 81.078,
|
| 1976 |
+
"eval_steps_per_second": 1.273,
|
| 1977 |
+
"step": 61500
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 49.6,
|
| 1981 |
+
"learning_rate": 2.967213114754098e-05,
|
| 1982 |
+
"loss": 0.0295,
|
| 1983 |
+
"step": 62000
|
| 1984 |
+
},
|
| 1985 |
+
{
|
| 1986 |
+
"epoch": 49.6,
|
| 1987 |
+
"eval_bleu": 85.3376,
|
| 1988 |
+
"eval_gen_len": 9.9427,
|
| 1989 |
+
"eval_loss": 0.19405782222747803,
|
| 1990 |
+
"eval_runtime": 122.2953,
|
| 1991 |
+
"eval_samples_per_second": 81.769,
|
| 1992 |
+
"eval_steps_per_second": 1.284,
|
| 1993 |
+
"step": 62000
|
| 1994 |
+
},
|
| 1995 |
+
{
|
| 1996 |
+
"epoch": 50.0,
|
| 1997 |
+
"learning_rate": 2.9508196721311478e-05,
|
| 1998 |
+
"loss": 0.03,
|
| 1999 |
+
"step": 62500
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 50.0,
|
| 2003 |
+
"eval_bleu": 85.0825,
|
| 2004 |
+
"eval_gen_len": 9.918,
|
| 2005 |
+
"eval_loss": 0.19235928356647491,
|
| 2006 |
+
"eval_runtime": 121.5967,
|
| 2007 |
+
"eval_samples_per_second": 82.239,
|
| 2008 |
+
"eval_steps_per_second": 1.291,
|
| 2009 |
+
"step": 62500
|
| 2010 |
+
},
|
| 2011 |
+
{
|
| 2012 |
+
"epoch": 50.4,
|
| 2013 |
+
"learning_rate": 2.934426229508197e-05,
|
| 2014 |
+
"loss": 0.028,
|
| 2015 |
+
"step": 63000
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 50.4,
|
| 2019 |
+
"eval_bleu": 85.2126,
|
| 2020 |
+
"eval_gen_len": 9.9178,
|
| 2021 |
+
"eval_loss": 0.1952826976776123,
|
| 2022 |
+
"eval_runtime": 121.3203,
|
| 2023 |
+
"eval_samples_per_second": 82.426,
|
| 2024 |
+
"eval_steps_per_second": 1.294,
|
| 2025 |
+
"step": 63000
|
| 2026 |
+
},
|
| 2027 |
+
{
|
| 2028 |
+
"epoch": 50.8,
|
| 2029 |
+
"learning_rate": 2.9180327868852458e-05,
|
| 2030 |
+
"loss": 0.0295,
|
| 2031 |
+
"step": 63500
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 50.8,
|
| 2035 |
+
"eval_bleu": 85.1624,
|
| 2036 |
+
"eval_gen_len": 9.9343,
|
| 2037 |
+
"eval_loss": 0.1901182234287262,
|
| 2038 |
+
"eval_runtime": 122.2317,
|
| 2039 |
+
"eval_samples_per_second": 81.812,
|
| 2040 |
+
"eval_steps_per_second": 1.284,
|
| 2041 |
+
"step": 63500
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 51.2,
|
| 2045 |
+
"learning_rate": 2.901639344262295e-05,
|
| 2046 |
+
"loss": 0.028,
|
| 2047 |
+
"step": 64000
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 51.2,
|
| 2051 |
+
"eval_bleu": 85.092,
|
| 2052 |
+
"eval_gen_len": 9.9193,
|
| 2053 |
+
"eval_loss": 0.19715240597724915,
|
| 2054 |
+
"eval_runtime": 121.6797,
|
| 2055 |
+
"eval_samples_per_second": 82.183,
|
| 2056 |
+
"eval_steps_per_second": 1.29,
|
| 2057 |
+
"step": 64000
|
| 2058 |
+
},
|
| 2059 |
+
{
|
| 2060 |
+
"epoch": 51.6,
|
| 2061 |
+
"learning_rate": 2.8852459016393445e-05,
|
| 2062 |
+
"loss": 0.0279,
|
| 2063 |
+
"step": 64500
|
| 2064 |
+
},
|
| 2065 |
+
{
|
| 2066 |
+
"epoch": 51.6,
|
| 2067 |
+
"eval_bleu": 85.3237,
|
| 2068 |
+
"eval_gen_len": 9.9341,
|
| 2069 |
+
"eval_loss": 0.19140399992465973,
|
| 2070 |
+
"eval_runtime": 122.9196,
|
| 2071 |
+
"eval_samples_per_second": 81.354,
|
| 2072 |
+
"eval_steps_per_second": 1.277,
|
| 2073 |
+
"step": 64500
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 52.0,
|
| 2077 |
+
"learning_rate": 2.8688524590163935e-05,
|
| 2078 |
+
"loss": 0.0275,
|
| 2079 |
+
"step": 65000
|
| 2080 |
+
},
|
| 2081 |
+
{
|
| 2082 |
+
"epoch": 52.0,
|
| 2083 |
+
"eval_bleu": 85.3125,
|
| 2084 |
+
"eval_gen_len": 9.9184,
|
| 2085 |
+
"eval_loss": 0.19335660338401794,
|
| 2086 |
+
"eval_runtime": 120.7401,
|
| 2087 |
+
"eval_samples_per_second": 82.823,
|
| 2088 |
+
"eval_steps_per_second": 1.3,
|
| 2089 |
+
"step": 65000
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 52.4,
|
| 2093 |
+
"learning_rate": 2.852459016393443e-05,
|
| 2094 |
+
"loss": 0.0266,
|
| 2095 |
+
"step": 65500
|
| 2096 |
+
},
|
| 2097 |
+
{
|
| 2098 |
+
"epoch": 52.4,
|
| 2099 |
+
"eval_bleu": 85.3497,
|
| 2100 |
+
"eval_gen_len": 9.9376,
|
| 2101 |
+
"eval_loss": 0.19615261256694794,
|
| 2102 |
+
"eval_runtime": 122.3086,
|
| 2103 |
+
"eval_samples_per_second": 81.76,
|
| 2104 |
+
"eval_steps_per_second": 1.284,
|
| 2105 |
+
"step": 65500
|
| 2106 |
+
},
|
| 2107 |
+
{
|
| 2108 |
+
"epoch": 52.8,
|
| 2109 |
+
"learning_rate": 2.8360655737704922e-05,
|
| 2110 |
+
"loss": 0.0269,
|
| 2111 |
+
"step": 66000
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 52.8,
|
| 2115 |
+
"eval_bleu": 85.2571,
|
| 2116 |
+
"eval_gen_len": 9.9076,
|
| 2117 |
+
"eval_loss": 0.19512337446212769,
|
| 2118 |
+
"eval_runtime": 122.2496,
|
| 2119 |
+
"eval_samples_per_second": 81.8,
|
| 2120 |
+
"eval_steps_per_second": 1.284,
|
| 2121 |
+
"step": 66000
|
| 2122 |
+
},
|
| 2123 |
+
{
|
| 2124 |
+
"epoch": 53.2,
|
| 2125 |
+
"learning_rate": 2.819672131147541e-05,
|
| 2126 |
+
"loss": 0.026,
|
| 2127 |
+
"step": 66500
|
| 2128 |
+
},
|
| 2129 |
+
{
|
| 2130 |
+
"epoch": 53.2,
|
| 2131 |
+
"eval_bleu": 85.3837,
|
| 2132 |
+
"eval_gen_len": 9.9211,
|
| 2133 |
+
"eval_loss": 0.195496067404747,
|
| 2134 |
+
"eval_runtime": 122.1131,
|
| 2135 |
+
"eval_samples_per_second": 81.891,
|
| 2136 |
+
"eval_steps_per_second": 1.286,
|
| 2137 |
+
"step": 66500
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 53.6,
|
| 2141 |
+
"learning_rate": 2.8032786885245906e-05,
|
| 2142 |
+
"loss": 0.0257,
|
| 2143 |
+
"step": 67000
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 53.6,
|
| 2147 |
+
"eval_bleu": 85.3563,
|
| 2148 |
+
"eval_gen_len": 9.9245,
|
| 2149 |
+
"eval_loss": 0.19710040092468262,
|
| 2150 |
+
"eval_runtime": 125.1877,
|
| 2151 |
+
"eval_samples_per_second": 79.88,
|
| 2152 |
+
"eval_steps_per_second": 1.254,
|
| 2153 |
+
"step": 67000
|
| 2154 |
+
},
|
| 2155 |
+
{
|
| 2156 |
+
"epoch": 54.0,
|
| 2157 |
+
"learning_rate": 2.7868852459016392e-05,
|
| 2158 |
+
"loss": 0.0263,
|
| 2159 |
+
"step": 67500
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 54.0,
|
| 2163 |
+
"eval_bleu": 85.3548,
|
| 2164 |
+
"eval_gen_len": 9.9285,
|
| 2165 |
+
"eval_loss": 0.19391243159770966,
|
| 2166 |
+
"eval_runtime": 121.9609,
|
| 2167 |
+
"eval_samples_per_second": 81.993,
|
| 2168 |
+
"eval_steps_per_second": 1.287,
|
| 2169 |
+
"step": 67500
|
| 2170 |
+
},
|
| 2171 |
+
{
|
| 2172 |
+
"epoch": 54.4,
|
| 2173 |
+
"learning_rate": 2.7704918032786886e-05,
|
| 2174 |
+
"loss": 0.0251,
|
| 2175 |
+
"step": 68000
|
| 2176 |
+
},
|
| 2177 |
+
{
|
| 2178 |
+
"epoch": 54.4,
|
| 2179 |
+
"eval_bleu": 85.3867,
|
| 2180 |
+
"eval_gen_len": 9.9223,
|
| 2181 |
+
"eval_loss": 0.19642965495586395,
|
| 2182 |
+
"eval_runtime": 122.2878,
|
| 2183 |
+
"eval_samples_per_second": 81.774,
|
| 2184 |
+
"eval_steps_per_second": 1.284,
|
| 2185 |
+
"step": 68000
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 54.8,
|
| 2189 |
+
"learning_rate": 2.754098360655738e-05,
|
| 2190 |
+
"loss": 0.0258,
|
| 2191 |
+
"step": 68500
|
| 2192 |
+
},
|
| 2193 |
+
{
|
| 2194 |
+
"epoch": 54.8,
|
| 2195 |
+
"eval_bleu": 85.3325,
|
| 2196 |
+
"eval_gen_len": 9.9353,
|
| 2197 |
+
"eval_loss": 0.19264063239097595,
|
| 2198 |
+
"eval_runtime": 123.3008,
|
| 2199 |
+
"eval_samples_per_second": 81.103,
|
| 2200 |
+
"eval_steps_per_second": 1.273,
|
| 2201 |
+
"step": 68500
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 55.2,
|
| 2205 |
+
"learning_rate": 2.737704918032787e-05,
|
| 2206 |
+
"loss": 0.0251,
|
| 2207 |
+
"step": 69000
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 55.2,
|
| 2211 |
+
"eval_bleu": 85.4551,
|
| 2212 |
+
"eval_gen_len": 9.9308,
|
| 2213 |
+
"eval_loss": 0.19382888078689575,
|
| 2214 |
+
"eval_runtime": 126.2193,
|
| 2215 |
+
"eval_samples_per_second": 79.227,
|
| 2216 |
+
"eval_steps_per_second": 1.244,
|
| 2217 |
+
"step": 69000
|
| 2218 |
+
},
|
| 2219 |
+
{
|
| 2220 |
+
"epoch": 55.6,
|
| 2221 |
+
"learning_rate": 2.7213114754098363e-05,
|
| 2222 |
+
"loss": 0.0244,
|
| 2223 |
+
"step": 69500
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 55.6,
|
| 2227 |
+
"eval_bleu": 85.309,
|
| 2228 |
+
"eval_gen_len": 9.9219,
|
| 2229 |
+
"eval_loss": 0.19579891860485077,
|
| 2230 |
+
"eval_runtime": 117.3342,
|
| 2231 |
+
"eval_samples_per_second": 85.227,
|
| 2232 |
+
"eval_steps_per_second": 1.338,
|
| 2233 |
+
"step": 69500
|
| 2234 |
+
},
|
| 2235 |
+
{
|
| 2236 |
+
"epoch": 56.0,
|
| 2237 |
+
"learning_rate": 2.7049180327868856e-05,
|
| 2238 |
+
"loss": 0.0255,
|
| 2239 |
+
"step": 70000
|
| 2240 |
+
},
|
| 2241 |
+
{
|
| 2242 |
+
"epoch": 56.0,
|
| 2243 |
+
"eval_bleu": 85.3467,
|
| 2244 |
+
"eval_gen_len": 9.9309,
|
| 2245 |
+
"eval_loss": 0.19363795220851898,
|
| 2246 |
+
"eval_runtime": 117.3138,
|
| 2247 |
+
"eval_samples_per_second": 85.241,
|
| 2248 |
+
"eval_steps_per_second": 1.338,
|
| 2249 |
+
"step": 70000
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 56.4,
|
| 2253 |
+
"learning_rate": 2.6885245901639343e-05,
|
| 2254 |
+
"loss": 0.0237,
|
| 2255 |
+
"step": 70500
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 56.4,
|
| 2259 |
+
"eval_bleu": 85.4309,
|
| 2260 |
+
"eval_gen_len": 9.919,
|
| 2261 |
+
"eval_loss": 0.19596821069717407,
|
| 2262 |
+
"eval_runtime": 116.9886,
|
| 2263 |
+
"eval_samples_per_second": 85.478,
|
| 2264 |
+
"eval_steps_per_second": 1.342,
|
| 2265 |
+
"step": 70500
|
| 2266 |
+
},
|
| 2267 |
+
{
|
| 2268 |
+
"epoch": 56.8,
|
| 2269 |
+
"learning_rate": 2.6721311475409837e-05,
|
| 2270 |
+
"loss": 0.0239,
|
| 2271 |
+
"step": 71000
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 56.8,
|
| 2275 |
+
"eval_bleu": 85.4014,
|
| 2276 |
+
"eval_gen_len": 9.934,
|
| 2277 |
+
"eval_loss": 0.1943485587835312,
|
| 2278 |
+
"eval_runtime": 121.5859,
|
| 2279 |
+
"eval_samples_per_second": 82.246,
|
| 2280 |
+
"eval_steps_per_second": 1.291,
|
| 2281 |
+
"step": 71000
|
| 2282 |
+
},
|
| 2283 |
+
{
|
| 2284 |
+
"epoch": 57.2,
|
| 2285 |
+
"learning_rate": 2.6557377049180327e-05,
|
| 2286 |
+
"loss": 0.0231,
|
| 2287 |
+
"step": 71500
|
| 2288 |
+
},
|
| 2289 |
+
{
|
| 2290 |
+
"epoch": 57.2,
|
| 2291 |
+
"eval_bleu": 85.621,
|
| 2292 |
+
"eval_gen_len": 9.9301,
|
| 2293 |
+
"eval_loss": 0.19711793959140778,
|
| 2294 |
+
"eval_runtime": 118.739,
|
| 2295 |
+
"eval_samples_per_second": 84.218,
|
| 2296 |
+
"eval_steps_per_second": 1.322,
|
| 2297 |
+
"step": 71500
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 57.6,
|
| 2301 |
+
"learning_rate": 2.639344262295082e-05,
|
| 2302 |
+
"loss": 0.0229,
|
| 2303 |
+
"step": 72000
|
| 2304 |
+
},
|
| 2305 |
+
{
|
| 2306 |
+
"epoch": 57.6,
|
| 2307 |
+
"eval_bleu": 85.5557,
|
| 2308 |
+
"eval_gen_len": 9.9331,
|
| 2309 |
+
"eval_loss": 0.19833779335021973,
|
| 2310 |
+
"eval_runtime": 119.0068,
|
| 2311 |
+
"eval_samples_per_second": 84.029,
|
| 2312 |
+
"eval_steps_per_second": 1.319,
|
| 2313 |
+
"step": 72000
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 58.0,
|
| 2317 |
+
"learning_rate": 2.6229508196721314e-05,
|
| 2318 |
+
"loss": 0.0231,
|
| 2319 |
+
"step": 72500
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 58.0,
|
| 2323 |
+
"eval_bleu": 85.6012,
|
| 2324 |
+
"eval_gen_len": 9.9243,
|
| 2325 |
+
"eval_loss": 0.1915123611688614,
|
| 2326 |
+
"eval_runtime": 115.0294,
|
| 2327 |
+
"eval_samples_per_second": 86.934,
|
| 2328 |
+
"eval_steps_per_second": 1.365,
|
| 2329 |
+
"step": 72500
|
| 2330 |
+
},
|
| 2331 |
+
{
|
| 2332 |
+
"epoch": 58.4,
|
| 2333 |
+
"learning_rate": 2.6065573770491804e-05,
|
| 2334 |
+
"loss": 0.0219,
|
| 2335 |
+
"step": 73000
|
| 2336 |
+
},
|
| 2337 |
+
{
|
| 2338 |
+
"epoch": 58.4,
|
| 2339 |
+
"eval_bleu": 85.4561,
|
| 2340 |
+
"eval_gen_len": 9.9202,
|
| 2341 |
+
"eval_loss": 0.19812047481536865,
|
| 2342 |
+
"eval_runtime": 114.3888,
|
| 2343 |
+
"eval_samples_per_second": 87.421,
|
| 2344 |
+
"eval_steps_per_second": 1.373,
|
| 2345 |
+
"step": 73000
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 58.8,
|
| 2349 |
+
"learning_rate": 2.5901639344262297e-05,
|
| 2350 |
+
"loss": 0.0227,
|
| 2351 |
+
"step": 73500
|
| 2352 |
+
},
|
| 2353 |
+
{
|
| 2354 |
+
"epoch": 58.8,
|
| 2355 |
+
"eval_bleu": 85.442,
|
| 2356 |
+
"eval_gen_len": 9.9242,
|
| 2357 |
+
"eval_loss": 0.19562363624572754,
|
| 2358 |
+
"eval_runtime": 112.3308,
|
| 2359 |
+
"eval_samples_per_second": 89.023,
|
| 2360 |
+
"eval_steps_per_second": 1.398,
|
| 2361 |
+
"step": 73500
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 59.2,
|
| 2365 |
+
"learning_rate": 2.573770491803279e-05,
|
| 2366 |
+
"loss": 0.0226,
|
| 2367 |
+
"step": 74000
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 59.2,
|
| 2371 |
+
"eval_bleu": 85.4558,
|
| 2372 |
+
"eval_gen_len": 9.9199,
|
| 2373 |
+
"eval_loss": 0.19775182008743286,
|
| 2374 |
+
"eval_runtime": 112.3894,
|
| 2375 |
+
"eval_samples_per_second": 88.976,
|
| 2376 |
+
"eval_steps_per_second": 1.397,
|
| 2377 |
+
"step": 74000
|
| 2378 |
+
},
|
| 2379 |
+
{
|
| 2380 |
+
"epoch": 59.6,
|
| 2381 |
+
"learning_rate": 2.5573770491803277e-05,
|
| 2382 |
+
"loss": 0.0213,
|
| 2383 |
+
"step": 74500
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 59.6,
|
| 2387 |
+
"eval_bleu": 85.6858,
|
| 2388 |
+
"eval_gen_len": 9.9401,
|
| 2389 |
+
"eval_loss": 0.19891192018985748,
|
| 2390 |
+
"eval_runtime": 111.4365,
|
| 2391 |
+
"eval_samples_per_second": 89.737,
|
| 2392 |
+
"eval_steps_per_second": 1.409,
|
| 2393 |
+
"step": 74500
|
| 2394 |
+
},
|
| 2395 |
+
{
|
| 2396 |
+
"epoch": 60.0,
|
| 2397 |
+
"learning_rate": 2.540983606557377e-05,
|
| 2398 |
+
"loss": 0.0222,
|
| 2399 |
+
"step": 75000
|
| 2400 |
+
},
|
| 2401 |
+
{
|
| 2402 |
+
"epoch": 60.0,
|
| 2403 |
+
"eval_bleu": 85.5013,
|
| 2404 |
+
"eval_gen_len": 9.9235,
|
| 2405 |
+
"eval_loss": 0.19413892924785614,
|
| 2406 |
+
"eval_runtime": 107.6887,
|
| 2407 |
+
"eval_samples_per_second": 92.86,
|
| 2408 |
+
"eval_steps_per_second": 1.458,
|
| 2409 |
+
"step": 75000
|
| 2410 |
+
}
|
| 2411 |
+
],
|
| 2412 |
+
"logging_steps": 500,
|
| 2413 |
+
"max_steps": 152500,
|
| 2414 |
+
"num_input_tokens_seen": 0,
|
| 2415 |
+
"num_train_epochs": 122,
|
| 2416 |
+
"save_steps": 500,
|
| 2417 |
+
"total_flos": 2.3617192120005427e+17,
|
| 2418 |
+
"train_batch_size": 64,
|
| 2419 |
+
"trial_name": null,
|
| 2420 |
+
"trial_params": null
|
| 2421 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72e2629cf428038fa0a8f7e39998d050de66034a894884dad7521238f2d34e0d
|
| 3 |
+
size 4411
|