Upload folder using huggingface_hub
Browse files- config.json +33 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +125 -0
- tokenizer.json +0 -0
- tokenizer_config.json +937 -0
- trainer_state.json +833 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "gsarti/it5-base",
|
| 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 |
+
"gradient_checkpointing": false,
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"model_type": "t5",
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.40.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32103
|
| 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": "4.40.2"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:611b21381560e9fd9a7b0539d77efd0836ab363b73e89b81a15fd8ab50a44493
|
| 3 |
+
size 990191464
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f37b2238b5df0d4b1d3d9e7d56e9ef9567783f4b380559da0fd6c5a9a4f32fc2
|
| 3 |
+
size 2371194
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:11ac951fadf9e1bc66d4a4cc407fe1195727946e8f626f217d959919ad3e8e77
|
| 3 |
+
size 14512
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7ad2ce33d00c4ab96d22b351b21d56344636f302ee6511f4348011bf751d1fcd
|
| 3 |
+
size 14512
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23f20678261b4d3aec8e15f20dc242caffe416d552628789709ba225f2bb44bf
|
| 3 |
+
size 1000
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,937 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"32003": {
|
| 28 |
+
"content": "<extra_id_0>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32004": {
|
| 36 |
+
"content": "<extra_id_1>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32005": {
|
| 44 |
+
"content": "<extra_id_2>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32006": {
|
| 52 |
+
"content": "<extra_id_3>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"32007": {
|
| 60 |
+
"content": "<extra_id_4>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"32008": {
|
| 68 |
+
"content": "<extra_id_5>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"32009": {
|
| 76 |
+
"content": "<extra_id_6>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"32010": {
|
| 84 |
+
"content": "<extra_id_7>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"32011": {
|
| 92 |
+
"content": "<extra_id_8>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"32012": {
|
| 100 |
+
"content": "<extra_id_9>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"32013": {
|
| 108 |
+
"content": "<extra_id_10>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"32014": {
|
| 116 |
+
"content": "<extra_id_11>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"32015": {
|
| 124 |
+
"content": "<extra_id_12>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"32016": {
|
| 132 |
+
"content": "<extra_id_13>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"32017": {
|
| 140 |
+
"content": "<extra_id_14>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"32018": {
|
| 148 |
+
"content": "<extra_id_15>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"32019": {
|
| 156 |
+
"content": "<extra_id_16>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"32020": {
|
| 164 |
+
"content": "<extra_id_17>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"32021": {
|
| 172 |
+
"content": "<extra_id_18>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"32022": {
|
| 180 |
+
"content": "<extra_id_19>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"32023": {
|
| 188 |
+
"content": "<extra_id_20>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"32024": {
|
| 196 |
+
"content": "<extra_id_21>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"32025": {
|
| 204 |
+
"content": "<extra_id_22>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"32026": {
|
| 212 |
+
"content": "<extra_id_23>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"32027": {
|
| 220 |
+
"content": "<extra_id_24>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"32028": {
|
| 228 |
+
"content": "<extra_id_25>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"32029": {
|
| 236 |
+
"content": "<extra_id_26>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"32030": {
|
| 244 |
+
"content": "<extra_id_27>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"32031": {
|
| 252 |
+
"content": "<extra_id_28>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"32032": {
|
| 260 |
+
"content": "<extra_id_29>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"32033": {
|
| 268 |
+
"content": "<extra_id_30>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"32034": {
|
| 276 |
+
"content": "<extra_id_31>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"32035": {
|
| 284 |
+
"content": "<extra_id_32>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"32036": {
|
| 292 |
+
"content": "<extra_id_33>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"32037": {
|
| 300 |
+
"content": "<extra_id_34>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"32038": {
|
| 308 |
+
"content": "<extra_id_35>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"32039": {
|
| 316 |
+
"content": "<extra_id_36>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"32040": {
|
| 324 |
+
"content": "<extra_id_37>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"32041": {
|
| 332 |
+
"content": "<extra_id_38>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"32042": {
|
| 340 |
+
"content": "<extra_id_39>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"32043": {
|
| 348 |
+
"content": "<extra_id_40>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"32044": {
|
| 356 |
+
"content": "<extra_id_41>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"32045": {
|
| 364 |
+
"content": "<extra_id_42>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"32046": {
|
| 372 |
+
"content": "<extra_id_43>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"32047": {
|
| 380 |
+
"content": "<extra_id_44>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"32048": {
|
| 388 |
+
"content": "<extra_id_45>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"32049": {
|
| 396 |
+
"content": "<extra_id_46>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"32050": {
|
| 404 |
+
"content": "<extra_id_47>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"32051": {
|
| 412 |
+
"content": "<extra_id_48>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"32052": {
|
| 420 |
+
"content": "<extra_id_49>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"32053": {
|
| 428 |
+
"content": "<extra_id_50>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"32054": {
|
| 436 |
+
"content": "<extra_id_51>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"32055": {
|
| 444 |
+
"content": "<extra_id_52>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"32056": {
|
| 452 |
+
"content": "<extra_id_53>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"32057": {
|
| 460 |
+
"content": "<extra_id_54>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"32058": {
|
| 468 |
+
"content": "<extra_id_55>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"32059": {
|
| 476 |
+
"content": "<extra_id_56>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"32060": {
|
| 484 |
+
"content": "<extra_id_57>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"32061": {
|
| 492 |
+
"content": "<extra_id_58>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"32062": {
|
| 500 |
+
"content": "<extra_id_59>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"32063": {
|
| 508 |
+
"content": "<extra_id_60>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"32064": {
|
| 516 |
+
"content": "<extra_id_61>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"32065": {
|
| 524 |
+
"content": "<extra_id_62>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"32066": {
|
| 532 |
+
"content": "<extra_id_63>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"32067": {
|
| 540 |
+
"content": "<extra_id_64>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"32068": {
|
| 548 |
+
"content": "<extra_id_65>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"32069": {
|
| 556 |
+
"content": "<extra_id_66>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"32070": {
|
| 564 |
+
"content": "<extra_id_67>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"32071": {
|
| 572 |
+
"content": "<extra_id_68>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"32072": {
|
| 580 |
+
"content": "<extra_id_69>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"32073": {
|
| 588 |
+
"content": "<extra_id_70>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"32074": {
|
| 596 |
+
"content": "<extra_id_71>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"32075": {
|
| 604 |
+
"content": "<extra_id_72>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"32076": {
|
| 612 |
+
"content": "<extra_id_73>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"32077": {
|
| 620 |
+
"content": "<extra_id_74>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"32078": {
|
| 628 |
+
"content": "<extra_id_75>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"32079": {
|
| 636 |
+
"content": "<extra_id_76>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"32080": {
|
| 644 |
+
"content": "<extra_id_77>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"32081": {
|
| 652 |
+
"content": "<extra_id_78>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"32082": {
|
| 660 |
+
"content": "<extra_id_79>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"32083": {
|
| 668 |
+
"content": "<extra_id_80>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"32084": {
|
| 676 |
+
"content": "<extra_id_81>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"32085": {
|
| 684 |
+
"content": "<extra_id_82>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"32086": {
|
| 692 |
+
"content": "<extra_id_83>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"32087": {
|
| 700 |
+
"content": "<extra_id_84>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"32088": {
|
| 708 |
+
"content": "<extra_id_85>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"32089": {
|
| 716 |
+
"content": "<extra_id_86>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"32090": {
|
| 724 |
+
"content": "<extra_id_87>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"32091": {
|
| 732 |
+
"content": "<extra_id_88>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"32092": {
|
| 740 |
+
"content": "<extra_id_89>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"32093": {
|
| 748 |
+
"content": "<extra_id_90>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"32094": {
|
| 756 |
+
"content": "<extra_id_91>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"32095": {
|
| 764 |
+
"content": "<extra_id_92>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"32096": {
|
| 772 |
+
"content": "<extra_id_93>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"32097": {
|
| 780 |
+
"content": "<extra_id_94>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"32098": {
|
| 788 |
+
"content": "<extra_id_95>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"32099": {
|
| 796 |
+
"content": "<extra_id_96>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"32100": {
|
| 804 |
+
"content": "<extra_id_97>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"32101": {
|
| 812 |
+
"content": "<extra_id_98>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"32102": {
|
| 820 |
+
"content": "<extra_id_99>",
|
| 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 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 934 |
+
"pad_token": "<pad>",
|
| 935 |
+
"tokenizer_class": "T5Tokenizer",
|
| 936 |
+
"unk_token": "<unk>"
|
| 937 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,833 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 3.1981074810028076,
|
| 3 |
+
"best_model_checkpoint": "checkpoints/it5-base/checkpoint-27001",
|
| 4 |
+
"epoch": 9.751173708920188,
|
| 5 |
+
"eval_steps": 2077,
|
| 6 |
+
"global_step": 27001,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14987360057782592,
|
| 13 |
+
"eval_g2l_cer": 100.4364,
|
| 14 |
+
"eval_g2l_gen_len": 5.3498,
|
| 15 |
+
"eval_g2l_rouge1": 23.9754,
|
| 16 |
+
"eval_g2l_rouge2": 12.4646,
|
| 17 |
+
"eval_g2l_rougeL": 23.7793,
|
| 18 |
+
"eval_g2l_rougeLsum": 23.7651,
|
| 19 |
+
"eval_l2ex_cer": 108.3181,
|
| 20 |
+
"eval_l2ex_gen_len": 40.6639,
|
| 21 |
+
"eval_l2ex_rouge1": 25.3285,
|
| 22 |
+
"eval_l2ex_rouge2": 11.5065,
|
| 23 |
+
"eval_l2ex_rougeL": 22.7839,
|
| 24 |
+
"eval_l2ex_rougeLsum": 22.7439,
|
| 25 |
+
"eval_l2g_cer": 97.287,
|
| 26 |
+
"eval_l2g_gen_len": 23.9843,
|
| 27 |
+
"eval_l2g_rouge1": 25.9551,
|
| 28 |
+
"eval_l2g_rouge2": 11.8024,
|
| 29 |
+
"eval_l2g_rougeL": 24.1441,
|
| 30 |
+
"eval_l2g_rougeLsum": 24.1774,
|
| 31 |
+
"eval_loss": 3.9933629035949707,
|
| 32 |
+
"eval_runtime": 160.4997,
|
| 33 |
+
"eval_samples_per_second": 61.813,
|
| 34 |
+
"eval_steps_per_second": 0.972,
|
| 35 |
+
"step": 415
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.15023474178403756,
|
| 39 |
+
"grad_norm": 14.013622283935547,
|
| 40 |
+
"learning_rate": 0.00014026974951830443,
|
| 41 |
+
"loss": 5.5983,
|
| 42 |
+
"step": 416
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.3004694835680751,
|
| 46 |
+
"grad_norm": 47.43400192260742,
|
| 47 |
+
"learning_rate": 0.00028053949903660886,
|
| 48 |
+
"loss": 4.0514,
|
| 49 |
+
"step": 832
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"epoch": 0.4507042253521127,
|
| 53 |
+
"grad_norm": 87.22700500488281,
|
| 54 |
+
"learning_rate": 0.0004208092485549133,
|
| 55 |
+
"loss": 3.8797,
|
| 56 |
+
"step": 1248
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.6009389671361502,
|
| 60 |
+
"grad_norm": 117.74351501464844,
|
| 61 |
+
"learning_rate": 0.0005610789980732177,
|
| 62 |
+
"loss": 3.7982,
|
| 63 |
+
"step": 1664
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.7500902853015529,
|
| 67 |
+
"eval_g2l_cer": 52.9873,
|
| 68 |
+
"eval_g2l_gen_len": 3.4046,
|
| 69 |
+
"eval_g2l_rouge1": 36.7676,
|
| 70 |
+
"eval_g2l_rouge2": 27.4065,
|
| 71 |
+
"eval_g2l_rougeL": 36.653,
|
| 72 |
+
"eval_g2l_rougeLsum": 36.6757,
|
| 73 |
+
"eval_l2ex_cer": 82.3042,
|
| 74 |
+
"eval_l2ex_gen_len": 18.221,
|
| 75 |
+
"eval_l2ex_rouge1": 29.9987,
|
| 76 |
+
"eval_l2ex_rouge2": 15.0081,
|
| 77 |
+
"eval_l2ex_rougeL": 27.336,
|
| 78 |
+
"eval_l2ex_rougeLsum": 27.3153,
|
| 79 |
+
"eval_l2g_cer": 72.0808,
|
| 80 |
+
"eval_l2g_gen_len": 10.2902,
|
| 81 |
+
"eval_l2g_rouge1": 32.6068,
|
| 82 |
+
"eval_l2g_rouge2": 20.974,
|
| 83 |
+
"eval_l2g_rougeL": 31.1844,
|
| 84 |
+
"eval_l2g_rougeLsum": 31.2287,
|
| 85 |
+
"eval_loss": 3.5869500637054443,
|
| 86 |
+
"eval_runtime": 137.2692,
|
| 87 |
+
"eval_samples_per_second": 72.274,
|
| 88 |
+
"eval_steps_per_second": 1.136,
|
| 89 |
+
"step": 2077
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.7511737089201878,
|
| 93 |
+
"grad_norm": 132.14553833007812,
|
| 94 |
+
"learning_rate": 0.0006999999822586204,
|
| 95 |
+
"loss": 3.7522,
|
| 96 |
+
"step": 2080
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.9014084507042254,
|
| 100 |
+
"grad_norm": 163.82469177246094,
|
| 101 |
+
"learning_rate": 0.0006998044195197278,
|
| 102 |
+
"loss": 3.7004,
|
| 103 |
+
"step": 2496
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 1.051643192488263,
|
| 107 |
+
"grad_norm": 134.45631408691406,
|
| 108 |
+
"learning_rate": 0.0006992253249390411,
|
| 109 |
+
"loss": 3.6596,
|
| 110 |
+
"step": 2912
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.2018779342723005,
|
| 114 |
+
"grad_norm": 110.51844787597656,
|
| 115 |
+
"learning_rate": 0.0006982633339003477,
|
| 116 |
+
"loss": 3.5916,
|
| 117 |
+
"step": 3328
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 1.352112676056338,
|
| 121 |
+
"grad_norm": 119.85750579833984,
|
| 122 |
+
"learning_rate": 0.000696919501902232,
|
| 123 |
+
"loss": 3.5667,
|
| 124 |
+
"step": 3744
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 1.500180570603106,
|
| 128 |
+
"eval_g2l_cer": 53.0855,
|
| 129 |
+
"eval_g2l_gen_len": 4.9383,
|
| 130 |
+
"eval_g2l_rouge1": 41.8458,
|
| 131 |
+
"eval_g2l_rouge2": 30.8627,
|
| 132 |
+
"eval_g2l_rougeL": 41.5679,
|
| 133 |
+
"eval_g2l_rougeLsum": 41.5758,
|
| 134 |
+
"eval_l2ex_cer": 85.4973,
|
| 135 |
+
"eval_l2ex_gen_len": 30.0565,
|
| 136 |
+
"eval_l2ex_rouge1": 30.6637,
|
| 137 |
+
"eval_l2ex_rouge2": 14.7084,
|
| 138 |
+
"eval_l2ex_rougeL": 27.5063,
|
| 139 |
+
"eval_l2ex_rougeLsum": 27.5683,
|
| 140 |
+
"eval_l2g_cer": 79.9636,
|
| 141 |
+
"eval_l2g_gen_len": 23.344,
|
| 142 |
+
"eval_l2g_rouge1": 38.4413,
|
| 143 |
+
"eval_l2g_rouge2": 25.3548,
|
| 144 |
+
"eval_l2g_rougeL": 36.2653,
|
| 145 |
+
"eval_l2g_rougeLsum": 36.3346,
|
| 146 |
+
"eval_loss": 3.4180662631988525,
|
| 147 |
+
"eval_runtime": 157.8624,
|
| 148 |
+
"eval_samples_per_second": 62.846,
|
| 149 |
+
"eval_steps_per_second": 0.988,
|
| 150 |
+
"step": 4154
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.5023474178403755,
|
| 154 |
+
"grad_norm": 130.5960235595703,
|
| 155 |
+
"learning_rate": 0.000695195303399979,
|
| 156 |
+
"loss": 3.5481,
|
| 157 |
+
"step": 4160
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 1.652582159624413,
|
| 161 |
+
"grad_norm": 128.95892333984375,
|
| 162 |
+
"learning_rate": 0.0006930926301877994,
|
| 163 |
+
"loss": 3.5237,
|
| 164 |
+
"step": 4576
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.8028169014084507,
|
| 168 |
+
"grad_norm": 129.52719116210938,
|
| 169 |
+
"learning_rate": 0.000690613789323149,
|
| 170 |
+
"loss": 3.5171,
|
| 171 |
+
"step": 4992
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 1.9530516431924883,
|
| 175 |
+
"grad_norm": 122.73914337158203,
|
| 176 |
+
"learning_rate": 0.0006877615005954206,
|
| 177 |
+
"loss": 3.5051,
|
| 178 |
+
"step": 5408
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.103286384976526,
|
| 182 |
+
"grad_norm": 100.69551849365234,
|
| 183 |
+
"learning_rate": 0.0006845388935417848,
|
| 184 |
+
"loss": 3.4086,
|
| 185 |
+
"step": 5824
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.2502708559046587,
|
| 189 |
+
"eval_g2l_cer": 50.7779,
|
| 190 |
+
"eval_g2l_gen_len": 4.8103,
|
| 191 |
+
"eval_g2l_rouge1": 42.8195,
|
| 192 |
+
"eval_g2l_rouge2": 31.8093,
|
| 193 |
+
"eval_g2l_rougeL": 42.5575,
|
| 194 |
+
"eval_g2l_rougeLsum": 42.5624,
|
| 195 |
+
"eval_l2ex_cer": 83.3686,
|
| 196 |
+
"eval_l2ex_gen_len": 29.3011,
|
| 197 |
+
"eval_l2ex_rouge1": 31.5473,
|
| 198 |
+
"eval_l2ex_rouge2": 15.1028,
|
| 199 |
+
"eval_l2ex_rougeL": 28.0691,
|
| 200 |
+
"eval_l2ex_rougeLsum": 28.1825,
|
| 201 |
+
"eval_l2g_cer": 77.4412,
|
| 202 |
+
"eval_l2g_gen_len": 21.7602,
|
| 203 |
+
"eval_l2g_rouge1": 39.093,
|
| 204 |
+
"eval_l2g_rouge2": 25.9346,
|
| 205 |
+
"eval_l2g_rougeL": 37.0244,
|
| 206 |
+
"eval_l2g_rougeLsum": 37.0876,
|
| 207 |
+
"eval_loss": 3.3524162769317627,
|
| 208 |
+
"eval_runtime": 157.4639,
|
| 209 |
+
"eval_samples_per_second": 63.005,
|
| 210 |
+
"eval_steps_per_second": 0.991,
|
| 211 |
+
"step": 6231
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"epoch": 2.2535211267605635,
|
| 215 |
+
"grad_norm": 101.63910675048828,
|
| 216 |
+
"learning_rate": 0.0006809495040134555,
|
| 217 |
+
"loss": 3.3874,
|
| 218 |
+
"step": 6240
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 2.403755868544601,
|
| 222 |
+
"grad_norm": 99.6649398803711,
|
| 223 |
+
"learning_rate": 0.000676997270296147,
|
| 224 |
+
"loss": 3.3843,
|
| 225 |
+
"step": 6656
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 2.5539906103286385,
|
| 229 |
+
"grad_norm": 102.08024597167969,
|
| 230 |
+
"learning_rate": 0.0006726865287889783,
|
| 231 |
+
"loss": 3.379,
|
| 232 |
+
"step": 7072
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 2.704225352112676,
|
| 236 |
+
"grad_norm": 93.55581665039062,
|
| 237 |
+
"learning_rate": 0.0006680220092465666,
|
| 238 |
+
"loss": 3.3681,
|
| 239 |
+
"step": 7488
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.8544600938967135,
|
| 243 |
+
"grad_norm": 95.19955444335938,
|
| 244 |
+
"learning_rate": 0.0006630088295895313,
|
| 245 |
+
"loss": 3.3544,
|
| 246 |
+
"step": 7904
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 3.0003611412062114,
|
| 250 |
+
"eval_g2l_cer": 47.3806,
|
| 251 |
+
"eval_g2l_gen_len": 3.8524,
|
| 252 |
+
"eval_g2l_rouge1": 44.4831,
|
| 253 |
+
"eval_g2l_rouge2": 34.1168,
|
| 254 |
+
"eval_g2l_rougeL": 44.3015,
|
| 255 |
+
"eval_g2l_rougeLsum": 44.3284,
|
| 256 |
+
"eval_l2ex_cer": 85.008,
|
| 257 |
+
"eval_l2ex_gen_len": 20.6814,
|
| 258 |
+
"eval_l2ex_rouge1": 31.6888,
|
| 259 |
+
"eval_l2ex_rouge2": 16.0577,
|
| 260 |
+
"eval_l2ex_rougeL": 28.2507,
|
| 261 |
+
"eval_l2ex_rougeLsum": 28.3238,
|
| 262 |
+
"eval_l2g_cer": 75.025,
|
| 263 |
+
"eval_l2g_gen_len": 15.1432,
|
| 264 |
+
"eval_l2g_rouge1": 38.7981,
|
| 265 |
+
"eval_l2g_rouge2": 26.3158,
|
| 266 |
+
"eval_l2g_rougeL": 36.9181,
|
| 267 |
+
"eval_l2g_rougeLsum": 36.9696,
|
| 268 |
+
"eval_loss": 3.283109188079834,
|
| 269 |
+
"eval_runtime": 151.9761,
|
| 270 |
+
"eval_samples_per_second": 65.28,
|
| 271 |
+
"eval_steps_per_second": 1.026,
|
| 272 |
+
"step": 8308
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 3.004694835680751,
|
| 276 |
+
"grad_norm": 93.19324493408203,
|
| 277 |
+
"learning_rate": 0.0006576524902890998,
|
| 278 |
+
"loss": 3.3457,
|
| 279 |
+
"step": 8320
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 3.1549295774647885,
|
| 283 |
+
"grad_norm": 104.09616088867188,
|
| 284 |
+
"learning_rate": 0.0006519588683319802,
|
| 285 |
+
"loss": 3.2525,
|
| 286 |
+
"step": 8736
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 3.3051643192488265,
|
| 290 |
+
"grad_norm": 104.19088745117188,
|
| 291 |
+
"learning_rate": 0.0006459342107721181,
|
| 292 |
+
"loss": 3.2478,
|
| 293 |
+
"step": 9152
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 3.455399061032864,
|
| 297 |
+
"grad_norm": 83.33271789550781,
|
| 298 |
+
"learning_rate": 0.0006395851278764164,
|
| 299 |
+
"loss": 3.2538,
|
| 300 |
+
"step": 9568
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 3.6056338028169015,
|
| 304 |
+
"grad_norm": 97.30130767822266,
|
| 305 |
+
"learning_rate": 0.0006329185858719365,
|
| 306 |
+
"loss": 3.2493,
|
| 307 |
+
"step": 9984
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 3.7504514265077646,
|
| 311 |
+
"eval_g2l_cer": 48.347,
|
| 312 |
+
"eval_g2l_gen_len": 4.6986,
|
| 313 |
+
"eval_g2l_rouge1": 45.126,
|
| 314 |
+
"eval_g2l_rouge2": 34.0899,
|
| 315 |
+
"eval_g2l_rougeL": 44.8883,
|
| 316 |
+
"eval_g2l_rougeLsum": 44.8974,
|
| 317 |
+
"eval_l2ex_cer": 83.8663,
|
| 318 |
+
"eval_l2ex_gen_len": 27.5262,
|
| 319 |
+
"eval_l2ex_rouge1": 32.7987,
|
| 320 |
+
"eval_l2ex_rouge2": 15.8604,
|
| 321 |
+
"eval_l2ex_rougeL": 28.7942,
|
| 322 |
+
"eval_l2ex_rougeLsum": 28.8651,
|
| 323 |
+
"eval_l2g_cer": 76.6028,
|
| 324 |
+
"eval_l2g_gen_len": 21.6109,
|
| 325 |
+
"eval_l2g_rouge1": 39.8458,
|
| 326 |
+
"eval_l2g_rouge2": 26.7789,
|
| 327 |
+
"eval_l2g_rougeL": 37.6794,
|
| 328 |
+
"eval_l2g_rougeLsum": 37.7404,
|
| 329 |
+
"eval_loss": 3.271592855453491,
|
| 330 |
+
"eval_runtime": 157.264,
|
| 331 |
+
"eval_samples_per_second": 63.085,
|
| 332 |
+
"eval_steps_per_second": 0.992,
|
| 333 |
+
"step": 10385
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 3.755868544600939,
|
| 337 |
+
"grad_norm": 87.18195343017578,
|
| 338 |
+
"learning_rate": 0.0006259418993025392,
|
| 339 |
+
"loss": 3.2387,
|
| 340 |
+
"step": 10400
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 3.9061032863849765,
|
| 344 |
+
"grad_norm": 77.52426147460938,
|
| 345 |
+
"learning_rate": 0.0006186627230033526,
|
| 346 |
+
"loss": 3.2361,
|
| 347 |
+
"step": 10816
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 4.056338028169014,
|
| 351 |
+
"grad_norm": 101.6712646484375,
|
| 352 |
+
"learning_rate": 0.0006110890437018696,
|
| 353 |
+
"loss": 3.1968,
|
| 354 |
+
"step": 11232
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 4.206572769953052,
|
| 358 |
+
"grad_norm": 99.43510437011719,
|
| 359 |
+
"learning_rate": 0.0006032291712548952,
|
| 360 |
+
"loss": 3.1304,
|
| 361 |
+
"step": 11648
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 4.356807511737089,
|
| 365 |
+
"grad_norm": 57.04045867919922,
|
| 366 |
+
"learning_rate": 0.0005950917295309531,
|
| 367 |
+
"loss": 3.1457,
|
| 368 |
+
"step": 12064
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 4.500541711809317,
|
| 372 |
+
"eval_g2l_cer": 47.8444,
|
| 373 |
+
"eval_g2l_gen_len": 4.6609,
|
| 374 |
+
"eval_g2l_rouge1": 45.1043,
|
| 375 |
+
"eval_g2l_rouge2": 34.1441,
|
| 376 |
+
"eval_g2l_rougeL": 44.9302,
|
| 377 |
+
"eval_g2l_rougeLsum": 44.9463,
|
| 378 |
+
"eval_l2ex_cer": 82.1447,
|
| 379 |
+
"eval_l2ex_gen_len": 26.408,
|
| 380 |
+
"eval_l2ex_rouge1": 33.2278,
|
| 381 |
+
"eval_l2ex_rouge2": 16.1616,
|
| 382 |
+
"eval_l2ex_rougeL": 29.2879,
|
| 383 |
+
"eval_l2ex_rougeLsum": 29.3229,
|
| 384 |
+
"eval_l2g_cer": 76.1324,
|
| 385 |
+
"eval_l2g_gen_len": 20.8059,
|
| 386 |
+
"eval_l2g_rouge1": 40.2785,
|
| 387 |
+
"eval_l2g_rouge2": 27.06,
|
| 388 |
+
"eval_l2g_rougeL": 38.0678,
|
| 389 |
+
"eval_l2g_rougeLsum": 38.1592,
|
| 390 |
+
"eval_loss": 3.266465902328491,
|
| 391 |
+
"eval_runtime": 157.9782,
|
| 392 |
+
"eval_samples_per_second": 62.8,
|
| 393 |
+
"eval_steps_per_second": 0.987,
|
| 394 |
+
"step": 12462
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 4.507042253521127,
|
| 398 |
+
"grad_norm": 67.55484771728516,
|
| 399 |
+
"learning_rate": 0.0005866856469481595,
|
| 400 |
+
"loss": 3.145,
|
| 401 |
+
"step": 12480
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 4.657276995305164,
|
| 405 |
+
"grad_norm": 76.89288330078125,
|
| 406 |
+
"learning_rate": 0.0005780201466779439,
|
| 407 |
+
"loss": 3.1236,
|
| 408 |
+
"step": 12896
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 4.807511737089202,
|
| 412 |
+
"grad_norm": 87.32029724121094,
|
| 413 |
+
"learning_rate": 0.0005691047365253672,
|
| 414 |
+
"loss": 3.1392,
|
| 415 |
+
"step": 13312
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 4.957746478873239,
|
| 419 |
+
"grad_norm": 109.48633575439453,
|
| 420 |
+
"learning_rate": 0.0005599491984971357,
|
| 421 |
+
"loss": 3.1438,
|
| 422 |
+
"step": 13728
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 5.107981220657277,
|
| 426 |
+
"grad_norm": 66.15205383300781,
|
| 427 |
+
"learning_rate": 0.0005505635780687648,
|
| 428 |
+
"loss": 3.0644,
|
| 429 |
+
"step": 14144
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 5.250631997110871,
|
| 433 |
+
"eval_g2l_cer": 46.2679,
|
| 434 |
+
"eval_g2l_gen_len": 3.7853,
|
| 435 |
+
"eval_g2l_rouge1": 45.7284,
|
| 436 |
+
"eval_g2l_rouge2": 35.1094,
|
| 437 |
+
"eval_g2l_rougeL": 45.5565,
|
| 438 |
+
"eval_g2l_rougeLsum": 45.5772,
|
| 439 |
+
"eval_l2ex_cer": 81.8173,
|
| 440 |
+
"eval_l2ex_gen_len": 18.9137,
|
| 441 |
+
"eval_l2ex_rouge1": 33.0179,
|
| 442 |
+
"eval_l2ex_rouge2": 16.8664,
|
| 443 |
+
"eval_l2ex_rougeL": 29.3623,
|
| 444 |
+
"eval_l2ex_rougeLsum": 29.4514,
|
| 445 |
+
"eval_l2g_cer": 70.134,
|
| 446 |
+
"eval_l2g_gen_len": 14.2539,
|
| 447 |
+
"eval_l2g_rouge1": 40.477,
|
| 448 |
+
"eval_l2g_rouge2": 27.4563,
|
| 449 |
+
"eval_l2g_rougeL": 38.398,
|
| 450 |
+
"eval_l2g_rougeLsum": 38.4554,
|
| 451 |
+
"eval_loss": 3.223316192626953,
|
| 452 |
+
"eval_runtime": 147.2815,
|
| 453 |
+
"eval_samples_per_second": 67.361,
|
| 454 |
+
"eval_steps_per_second": 1.059,
|
| 455 |
+
"step": 14539
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 5.258215962441315,
|
| 459 |
+
"grad_norm": 120.2764663696289,
|
| 460 |
+
"learning_rate": 0.0005409581731626619,
|
| 461 |
+
"loss": 3.0359,
|
| 462 |
+
"step": 14560
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 5.408450704225352,
|
| 466 |
+
"grad_norm": 66.7710189819336,
|
| 467 |
+
"learning_rate": 0.0005311435228492235,
|
| 468 |
+
"loss": 3.0459,
|
| 469 |
+
"step": 14976
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 5.55868544600939,
|
| 473 |
+
"grad_norm": 103.15011596679688,
|
| 474 |
+
"learning_rate": 0.0005211303957833462,
|
| 475 |
+
"loss": 3.0499,
|
| 476 |
+
"step": 15392
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 5.708920187793427,
|
| 480 |
+
"grad_norm": 91.70545196533203,
|
| 481 |
+
"learning_rate": 0.0005109297783890348,
|
| 482 |
+
"loss": 3.0455,
|
| 483 |
+
"step": 15808
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 5.859154929577465,
|
| 487 |
+
"grad_norm": 62.21952819824219,
|
| 488 |
+
"learning_rate": 0.0005005528628050757,
|
| 489 |
+
"loss": 3.0468,
|
| 490 |
+
"step": 16224
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 6.000722282412423,
|
| 494 |
+
"eval_g2l_cer": 46.2085,
|
| 495 |
+
"eval_g2l_gen_len": 4.1369,
|
| 496 |
+
"eval_g2l_rouge1": 46.8001,
|
| 497 |
+
"eval_g2l_rouge2": 35.9998,
|
| 498 |
+
"eval_g2l_rougeL": 46.6066,
|
| 499 |
+
"eval_g2l_rougeLsum": 46.6501,
|
| 500 |
+
"eval_l2ex_cer": 79.8794,
|
| 501 |
+
"eval_l2ex_gen_len": 18.741,
|
| 502 |
+
"eval_l2ex_rouge1": 33.8832,
|
| 503 |
+
"eval_l2ex_rouge2": 17.2827,
|
| 504 |
+
"eval_l2ex_rougeL": 29.9003,
|
| 505 |
+
"eval_l2ex_rougeLsum": 29.9671,
|
| 506 |
+
"eval_l2g_cer": 70.1127,
|
| 507 |
+
"eval_l2g_gen_len": 14.8234,
|
| 508 |
+
"eval_l2g_rouge1": 40.9429,
|
| 509 |
+
"eval_l2g_rouge2": 27.7443,
|
| 510 |
+
"eval_l2g_rougeL": 38.7561,
|
| 511 |
+
"eval_l2g_rougeLsum": 38.812,
|
| 512 |
+
"eval_loss": 3.198634624481201,
|
| 513 |
+
"eval_runtime": 147.3585,
|
| 514 |
+
"eval_samples_per_second": 67.326,
|
| 515 |
+
"eval_steps_per_second": 1.059,
|
| 516 |
+
"step": 16616
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 6.009389671361502,
|
| 520 |
+
"grad_norm": 60.71475601196289,
|
| 521 |
+
"learning_rate": 0.0004900110346049988,
|
| 522 |
+
"loss": 3.0478,
|
| 523 |
+
"step": 16640
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 6.15962441314554,
|
| 527 |
+
"grad_norm": 74.91094207763672,
|
| 528 |
+
"learning_rate": 0.0004793158603048017,
|
| 529 |
+
"loss": 2.9501,
|
| 530 |
+
"step": 17056
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 6.309859154929577,
|
| 534 |
+
"grad_norm": 98.47882843017578,
|
| 535 |
+
"learning_rate": 0.00046847907467214455,
|
| 536 |
+
"loss": 2.9655,
|
| 537 |
+
"step": 17472
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 6.460093896713615,
|
| 541 |
+
"grad_norm": 56.426727294921875,
|
| 542 |
+
"learning_rate": 0.00045751256785093856,
|
| 543 |
+
"loss": 2.9753,
|
| 544 |
+
"step": 17888
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 6.610328638497653,
|
| 548 |
+
"grad_norm": 47.2915153503418,
|
| 549 |
+
"learning_rate": 0.00044642837231545463,
|
| 550 |
+
"loss": 2.9699,
|
| 551 |
+
"step": 18304
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 6.750812567713976,
|
| 555 |
+
"eval_g2l_cer": 46.2359,
|
| 556 |
+
"eval_g2l_gen_len": 4.4804,
|
| 557 |
+
"eval_g2l_rouge1": 47.0405,
|
| 558 |
+
"eval_g2l_rouge2": 35.9417,
|
| 559 |
+
"eval_g2l_rougeL": 46.8609,
|
| 560 |
+
"eval_g2l_rougeLsum": 46.8948,
|
| 561 |
+
"eval_l2ex_cer": 81.7484,
|
| 562 |
+
"eval_l2ex_gen_len": 23.0452,
|
| 563 |
+
"eval_l2ex_rouge1": 33.3772,
|
| 564 |
+
"eval_l2ex_rouge2": 16.3629,
|
| 565 |
+
"eval_l2ex_rougeL": 29.2446,
|
| 566 |
+
"eval_l2ex_rougeLsum": 29.3549,
|
| 567 |
+
"eval_l2g_cer": 74.5769,
|
| 568 |
+
"eval_l2g_gen_len": 19.6127,
|
| 569 |
+
"eval_l2g_rouge1": 41.2652,
|
| 570 |
+
"eval_l2g_rouge2": 27.8695,
|
| 571 |
+
"eval_l2g_rougeL": 38.8879,
|
| 572 |
+
"eval_l2g_rougeLsum": 38.9752,
|
| 573 |
+
"eval_loss": 3.2092766761779785,
|
| 574 |
+
"eval_runtime": 156.9963,
|
| 575 |
+
"eval_samples_per_second": 63.193,
|
| 576 |
+
"eval_steps_per_second": 0.994,
|
| 577 |
+
"step": 18693
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 6.76056338028169,
|
| 581 |
+
"grad_norm": 40.62468338012695,
|
| 582 |
+
"learning_rate": 0.0004352386496682677,
|
| 583 |
+
"loss": 2.9756,
|
| 584 |
+
"step": 18720
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 6.910798122065728,
|
| 588 |
+
"grad_norm": 44.248905181884766,
|
| 589 |
+
"learning_rate": 0.00042395567729652095,
|
| 590 |
+
"loss": 2.9631,
|
| 591 |
+
"step": 19136
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 7.061032863849765,
|
| 595 |
+
"grad_norm": 71.54096984863281,
|
| 596 |
+
"learning_rate": 0.00041259183490115084,
|
| 597 |
+
"loss": 2.9346,
|
| 598 |
+
"step": 19552
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 7.211267605633803,
|
| 602 |
+
"grad_norm": 63.520111083984375,
|
| 603 |
+
"learning_rate": 0.0004011595909138531,
|
| 604 |
+
"loss": 2.8878,
|
| 605 |
+
"step": 19968
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 7.36150234741784,
|
| 609 |
+
"grad_norm": 52.090240478515625,
|
| 610 |
+
"learning_rate": 0.0003896714888166938,
|
| 611 |
+
"loss": 2.8877,
|
| 612 |
+
"step": 20384
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 7.500902853015529,
|
| 616 |
+
"eval_g2l_cer": 45.7698,
|
| 617 |
+
"eval_g2l_gen_len": 4.4545,
|
| 618 |
+
"eval_g2l_rouge1": 47.583,
|
| 619 |
+
"eval_g2l_rouge2": 36.2797,
|
| 620 |
+
"eval_g2l_rougeL": 47.433,
|
| 621 |
+
"eval_g2l_rougeLsum": 47.4196,
|
| 622 |
+
"eval_l2ex_cer": 81.5805,
|
| 623 |
+
"eval_l2ex_gen_len": 23.9979,
|
| 624 |
+
"eval_l2ex_rouge1": 33.9624,
|
| 625 |
+
"eval_l2ex_rouge2": 16.6357,
|
| 626 |
+
"eval_l2ex_rougeL": 29.8228,
|
| 627 |
+
"eval_l2ex_rougeLsum": 29.9123,
|
| 628 |
+
"eval_l2g_cer": 73.7736,
|
| 629 |
+
"eval_l2g_gen_len": 19.3481,
|
| 630 |
+
"eval_l2g_rouge1": 41.2698,
|
| 631 |
+
"eval_l2g_rouge2": 27.863,
|
| 632 |
+
"eval_l2g_rougeL": 38.869,
|
| 633 |
+
"eval_l2g_rougeLsum": 38.9562,
|
| 634 |
+
"eval_loss": 3.214210033416748,
|
| 635 |
+
"eval_runtime": 157.1314,
|
| 636 |
+
"eval_samples_per_second": 63.138,
|
| 637 |
+
"eval_steps_per_second": 0.993,
|
| 638 |
+
"step": 20770
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 7.511737089201878,
|
| 642 |
+
"grad_norm": 44.08253479003906,
|
| 643 |
+
"learning_rate": 0.0003781401333793737,
|
| 644 |
+
"loss": 2.888,
|
| 645 |
+
"step": 20800
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 7.661971830985916,
|
| 649 |
+
"grad_norm": 50.90373611450195,
|
| 650 |
+
"learning_rate": 0.00036657817682924954,
|
| 651 |
+
"loss": 2.9017,
|
| 652 |
+
"step": 21216
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 7.812206572769953,
|
| 656 |
+
"grad_norm": 70.20822143554688,
|
| 657 |
+
"learning_rate": 0.0003549983049692832,
|
| 658 |
+
"loss": 2.8951,
|
| 659 |
+
"step": 21632
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 7.962441314553991,
|
| 663 |
+
"grad_norm": 24.146835327148438,
|
| 664 |
+
"learning_rate": 0.00034341322325915155,
|
| 665 |
+
"loss": 2.9011,
|
| 666 |
+
"step": 22048
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 8.112676056338028,
|
| 670 |
+
"grad_norm": 43.61560821533203,
|
| 671 |
+
"learning_rate": 0.0003318356428747905,
|
| 672 |
+
"loss": 2.8542,
|
| 673 |
+
"step": 22464
|
| 674 |
+
},
|
| 675 |
+
{
|
| 676 |
+
"epoch": 8.250993138317082,
|
| 677 |
+
"eval_g2l_cer": 45.6053,
|
| 678 |
+
"eval_g2l_gen_len": 3.9989,
|
| 679 |
+
"eval_g2l_rouge1": 47.3053,
|
| 680 |
+
"eval_g2l_rouge2": 36.3191,
|
| 681 |
+
"eval_g2l_rougeL": 47.2008,
|
| 682 |
+
"eval_g2l_rougeLsum": 47.2596,
|
| 683 |
+
"eval_l2ex_cer": 81.0598,
|
| 684 |
+
"eval_l2ex_gen_len": 20.2055,
|
| 685 |
+
"eval_l2ex_rouge1": 33.9028,
|
| 686 |
+
"eval_l2ex_rouge2": 16.9085,
|
| 687 |
+
"eval_l2ex_rougeL": 29.7011,
|
| 688 |
+
"eval_l2ex_rougeLsum": 29.7791,
|
| 689 |
+
"eval_l2g_cer": 71.3827,
|
| 690 |
+
"eval_l2g_gen_len": 15.4007,
|
| 691 |
+
"eval_l2g_rouge1": 41.2614,
|
| 692 |
+
"eval_l2g_rouge2": 28.0203,
|
| 693 |
+
"eval_l2g_rougeL": 39.0253,
|
| 694 |
+
"eval_l2g_rougeLsum": 39.0954,
|
| 695 |
+
"eval_loss": 3.200995922088623,
|
| 696 |
+
"eval_runtime": 148.5568,
|
| 697 |
+
"eval_samples_per_second": 66.783,
|
| 698 |
+
"eval_steps_per_second": 1.05,
|
| 699 |
+
"step": 22847
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 8.262910798122066,
|
| 703 |
+
"grad_norm": 34.18248748779297,
|
| 704 |
+
"learning_rate": 0.0003202782667616653,
|
| 705 |
+
"loss": 2.8359,
|
| 706 |
+
"step": 22880
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 8.413145539906104,
|
| 710 |
+
"grad_norm": 46.180694580078125,
|
| 711 |
+
"learning_rate": 0.00030875377569707275,
|
| 712 |
+
"loss": 2.8378,
|
| 713 |
+
"step": 23296
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 8.56338028169014,
|
| 717 |
+
"grad_norm": 42.6771354675293,
|
| 718 |
+
"learning_rate": 0.000297274814376765,
|
| 719 |
+
"loss": 2.8327,
|
| 720 |
+
"step": 23712
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 8.713615023474178,
|
| 724 |
+
"grad_norm": 19.82225227355957,
|
| 725 |
+
"learning_rate": 0.0002858539775411638,
|
| 726 |
+
"loss": 2.843,
|
| 727 |
+
"step": 24128
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"epoch": 8.863849765258216,
|
| 731 |
+
"grad_norm": 19.00598907470703,
|
| 732 |
+
"learning_rate": 0.00027450379615638425,
|
| 733 |
+
"loss": 2.8231,
|
| 734 |
+
"step": 24544
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 9.001083423618635,
|
| 738 |
+
"eval_g2l_cer": 45.4637,
|
| 739 |
+
"eval_g2l_gen_len": 4.0383,
|
| 740 |
+
"eval_g2l_rouge1": 47.3272,
|
| 741 |
+
"eval_g2l_rouge2": 36.2943,
|
| 742 |
+
"eval_g2l_rougeL": 47.1452,
|
| 743 |
+
"eval_g2l_rougeLsum": 47.2213,
|
| 744 |
+
"eval_l2ex_cer": 80.295,
|
| 745 |
+
"eval_l2ex_gen_len": 19.4255,
|
| 746 |
+
"eval_l2ex_rouge1": 34.2944,
|
| 747 |
+
"eval_l2ex_rouge2": 17.3206,
|
| 748 |
+
"eval_l2ex_rougeL": 30.0912,
|
| 749 |
+
"eval_l2ex_rougeLsum": 30.1909,
|
| 750 |
+
"eval_l2g_cer": 69.8778,
|
| 751 |
+
"eval_l2g_gen_len": 14.8225,
|
| 752 |
+
"eval_l2g_rouge1": 41.2308,
|
| 753 |
+
"eval_l2g_rouge2": 27.9775,
|
| 754 |
+
"eval_l2g_rougeL": 39.0866,
|
| 755 |
+
"eval_l2g_rougeLsum": 39.1425,
|
| 756 |
+
"eval_loss": 3.2024292945861816,
|
| 757 |
+
"eval_runtime": 146.3445,
|
| 758 |
+
"eval_samples_per_second": 67.792,
|
| 759 |
+
"eval_steps_per_second": 1.066,
|
| 760 |
+
"step": 24924
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 9.014084507042254,
|
| 764 |
+
"grad_norm": 22.52915382385254,
|
| 765 |
+
"learning_rate": 0.00026323672366523274,
|
| 766 |
+
"loss": 2.8413,
|
| 767 |
+
"step": 24960
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 9.164319248826292,
|
| 771 |
+
"grad_norm": 30.310894012451172,
|
| 772 |
+
"learning_rate": 0.0002520651223232633,
|
| 773 |
+
"loss": 2.7777,
|
| 774 |
+
"step": 25376
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 9.314553990610328,
|
| 778 |
+
"grad_norm": 31.759746551513672,
|
| 779 |
+
"learning_rate": 0.000241001249634885,
|
| 780 |
+
"loss": 2.7963,
|
| 781 |
+
"step": 25792
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 9.464788732394366,
|
| 785 |
+
"grad_norm": 13.962241172790527,
|
| 786 |
+
"learning_rate": 0.00023005724490440243,
|
| 787 |
+
"loss": 2.7968,
|
| 788 |
+
"step": 26208
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 9.615023474178404,
|
| 792 |
+
"grad_norm": 20.10390853881836,
|
| 793 |
+
"learning_rate": 0.0002192451159167455,
|
| 794 |
+
"loss": 2.7902,
|
| 795 |
+
"step": 26624
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 9.751173708920188,
|
| 799 |
+
"eval_g2l_cer": 45.3083,
|
| 800 |
+
"eval_g2l_gen_len": 4.3145,
|
| 801 |
+
"eval_g2l_rouge1": 47.8559,
|
| 802 |
+
"eval_g2l_rouge2": 36.8346,
|
| 803 |
+
"eval_g2l_rougeL": 47.6856,
|
| 804 |
+
"eval_g2l_rougeLsum": 47.712,
|
| 805 |
+
"eval_l2ex_cer": 80.353,
|
| 806 |
+
"eval_l2ex_gen_len": 21.4861,
|
| 807 |
+
"eval_l2ex_rouge1": 34.306,
|
| 808 |
+
"eval_l2ex_rouge2": 16.8625,
|
| 809 |
+
"eval_l2ex_rougeL": 29.7995,
|
| 810 |
+
"eval_l2ex_rougeLsum": 29.9518,
|
| 811 |
+
"eval_l2g_cer": 71.8262,
|
| 812 |
+
"eval_l2g_gen_len": 17.528,
|
| 813 |
+
"eval_l2g_rouge1": 41.8619,
|
| 814 |
+
"eval_l2g_rouge2": 28.3549,
|
| 815 |
+
"eval_l2g_rougeL": 39.5168,
|
| 816 |
+
"eval_l2g_rougeLsum": 39.5953,
|
| 817 |
+
"eval_loss": 3.1981074810028076,
|
| 818 |
+
"eval_runtime": 153.7484,
|
| 819 |
+
"eval_samples_per_second": 64.527,
|
| 820 |
+
"eval_steps_per_second": 1.015,
|
| 821 |
+
"step": 27001
|
| 822 |
+
}
|
| 823 |
+
],
|
| 824 |
+
"logging_steps": 416,
|
| 825 |
+
"max_steps": 41535,
|
| 826 |
+
"num_input_tokens_seen": 0,
|
| 827 |
+
"num_train_epochs": 15,
|
| 828 |
+
"save_steps": 2077,
|
| 829 |
+
"total_flos": 2.9580064377012224e+17,
|
| 830 |
+
"train_batch_size": 32,
|
| 831 |
+
"trial_name": null,
|
| 832 |
+
"trial_params": null
|
| 833 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71dd917e81d4d7c2f48d871b5eea7f5c1514c4a40d5a6f405da5e97d831efe7d
|
| 3 |
+
size 5176
|