Upload 12 files
Browse files- added_tokens.json +103 -0
- config.json +33 -0
- generation_config.json +9 -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_config.json +940 -0
- trainer_state.json +1811 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,103 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<extra_id_0>": 64099,
|
| 3 |
+
"<extra_id_10>": 64089,
|
| 4 |
+
"<extra_id_11>": 64088,
|
| 5 |
+
"<extra_id_12>": 64087,
|
| 6 |
+
"<extra_id_13>": 64086,
|
| 7 |
+
"<extra_id_14>": 64085,
|
| 8 |
+
"<extra_id_15>": 64084,
|
| 9 |
+
"<extra_id_16>": 64083,
|
| 10 |
+
"<extra_id_17>": 64082,
|
| 11 |
+
"<extra_id_18>": 64081,
|
| 12 |
+
"<extra_id_19>": 64080,
|
| 13 |
+
"<extra_id_1>": 64098,
|
| 14 |
+
"<extra_id_20>": 64079,
|
| 15 |
+
"<extra_id_21>": 64078,
|
| 16 |
+
"<extra_id_22>": 64077,
|
| 17 |
+
"<extra_id_23>": 64076,
|
| 18 |
+
"<extra_id_24>": 64075,
|
| 19 |
+
"<extra_id_25>": 64074,
|
| 20 |
+
"<extra_id_26>": 64073,
|
| 21 |
+
"<extra_id_27>": 64072,
|
| 22 |
+
"<extra_id_28>": 64071,
|
| 23 |
+
"<extra_id_29>": 64070,
|
| 24 |
+
"<extra_id_2>": 64097,
|
| 25 |
+
"<extra_id_30>": 64069,
|
| 26 |
+
"<extra_id_31>": 64068,
|
| 27 |
+
"<extra_id_32>": 64067,
|
| 28 |
+
"<extra_id_33>": 64066,
|
| 29 |
+
"<extra_id_34>": 64065,
|
| 30 |
+
"<extra_id_35>": 64064,
|
| 31 |
+
"<extra_id_36>": 64063,
|
| 32 |
+
"<extra_id_37>": 64062,
|
| 33 |
+
"<extra_id_38>": 64061,
|
| 34 |
+
"<extra_id_39>": 64060,
|
| 35 |
+
"<extra_id_3>": 64096,
|
| 36 |
+
"<extra_id_40>": 64059,
|
| 37 |
+
"<extra_id_41>": 64058,
|
| 38 |
+
"<extra_id_42>": 64057,
|
| 39 |
+
"<extra_id_43>": 64056,
|
| 40 |
+
"<extra_id_44>": 64055,
|
| 41 |
+
"<extra_id_45>": 64054,
|
| 42 |
+
"<extra_id_46>": 64053,
|
| 43 |
+
"<extra_id_47>": 64052,
|
| 44 |
+
"<extra_id_48>": 64051,
|
| 45 |
+
"<extra_id_49>": 64050,
|
| 46 |
+
"<extra_id_4>": 64095,
|
| 47 |
+
"<extra_id_50>": 64049,
|
| 48 |
+
"<extra_id_51>": 64048,
|
| 49 |
+
"<extra_id_52>": 64047,
|
| 50 |
+
"<extra_id_53>": 64046,
|
| 51 |
+
"<extra_id_54>": 64045,
|
| 52 |
+
"<extra_id_55>": 64044,
|
| 53 |
+
"<extra_id_56>": 64043,
|
| 54 |
+
"<extra_id_57>": 64042,
|
| 55 |
+
"<extra_id_58>": 64041,
|
| 56 |
+
"<extra_id_59>": 64040,
|
| 57 |
+
"<extra_id_5>": 64094,
|
| 58 |
+
"<extra_id_60>": 64039,
|
| 59 |
+
"<extra_id_61>": 64038,
|
| 60 |
+
"<extra_id_62>": 64037,
|
| 61 |
+
"<extra_id_63>": 64036,
|
| 62 |
+
"<extra_id_64>": 64035,
|
| 63 |
+
"<extra_id_65>": 64034,
|
| 64 |
+
"<extra_id_66>": 64033,
|
| 65 |
+
"<extra_id_67>": 64032,
|
| 66 |
+
"<extra_id_68>": 64031,
|
| 67 |
+
"<extra_id_69>": 64030,
|
| 68 |
+
"<extra_id_6>": 64093,
|
| 69 |
+
"<extra_id_70>": 64029,
|
| 70 |
+
"<extra_id_71>": 64028,
|
| 71 |
+
"<extra_id_72>": 64027,
|
| 72 |
+
"<extra_id_73>": 64026,
|
| 73 |
+
"<extra_id_74>": 64025,
|
| 74 |
+
"<extra_id_75>": 64024,
|
| 75 |
+
"<extra_id_76>": 64023,
|
| 76 |
+
"<extra_id_77>": 64022,
|
| 77 |
+
"<extra_id_78>": 64021,
|
| 78 |
+
"<extra_id_79>": 64020,
|
| 79 |
+
"<extra_id_7>": 64092,
|
| 80 |
+
"<extra_id_80>": 64019,
|
| 81 |
+
"<extra_id_81>": 64018,
|
| 82 |
+
"<extra_id_82>": 64017,
|
| 83 |
+
"<extra_id_83>": 64016,
|
| 84 |
+
"<extra_id_84>": 64015,
|
| 85 |
+
"<extra_id_85>": 64014,
|
| 86 |
+
"<extra_id_86>": 64013,
|
| 87 |
+
"<extra_id_87>": 64012,
|
| 88 |
+
"<extra_id_88>": 64011,
|
| 89 |
+
"<extra_id_89>": 64010,
|
| 90 |
+
"<extra_id_8>": 64091,
|
| 91 |
+
"<extra_id_90>": 64009,
|
| 92 |
+
"<extra_id_91>": 64008,
|
| 93 |
+
"<extra_id_92>": 64007,
|
| 94 |
+
"<extra_id_93>": 64006,
|
| 95 |
+
"<extra_id_94>": 64005,
|
| 96 |
+
"<extra_id_95>": 64004,
|
| 97 |
+
"<extra_id_96>": 64003,
|
| 98 |
+
"<extra_id_97>": 64002,
|
| 99 |
+
"<extra_id_98>": 64001,
|
| 100 |
+
"<extra_id_99>": 64000,
|
| 101 |
+
"<extra_id_9>": 64090,
|
| 102 |
+
"<pad>": 64100
|
| 103 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/kaggle/input/meid-3-512-first500/kaggle/working/results/checkpoint-125000",
|
| 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": "4.39.3",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 64101
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"max_new_tokens": 256,
|
| 6 |
+
"min_new_tokens": 0,
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "4.39.3"
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:340fbb3dd34555ce98df006431dd372fec735d1dc7df61f46c72af89c7fd2e27
|
| 3 |
+
size 1186787176
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd9b7ffc7637109f488eca1ec125fb1647e9b6439ed34cf4bd1ed2fa5645bce7
|
| 3 |
+
size 2373744634
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ebd6b177f9cee8c31c28a5368980edb415e88a38dad1fd47f27fde864bf31fc0
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f40f860c1576b83d4016acd48c4406073222dbeae15d9abdbddd1030e118f36
|
| 3 |
+
size 1064
|
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:e8b0c94f9d6e9e75161a1365e73132f35666ab675de0d5ae10ec9f6f5eacda09
|
| 3 |
+
size 1457188
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,940 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<unk>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"2": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"64000": {
|
| 21 |
+
"content": "<extra_id_99>",
|
| 22 |
+
"lstrip": true,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": true,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"64001": {
|
| 29 |
+
"content": "<extra_id_98>",
|
| 30 |
+
"lstrip": true,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": true,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"64002": {
|
| 37 |
+
"content": "<extra_id_97>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": true,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"64003": {
|
| 45 |
+
"content": "<extra_id_96>",
|
| 46 |
+
"lstrip": true,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": true,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"64004": {
|
| 53 |
+
"content": "<extra_id_95>",
|
| 54 |
+
"lstrip": true,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": true,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"64005": {
|
| 61 |
+
"content": "<extra_id_94>",
|
| 62 |
+
"lstrip": true,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": true,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"64006": {
|
| 69 |
+
"content": "<extra_id_93>",
|
| 70 |
+
"lstrip": true,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": true,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"64007": {
|
| 77 |
+
"content": "<extra_id_92>",
|
| 78 |
+
"lstrip": true,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": true,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"64008": {
|
| 85 |
+
"content": "<extra_id_91>",
|
| 86 |
+
"lstrip": true,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": true,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"64009": {
|
| 93 |
+
"content": "<extra_id_90>",
|
| 94 |
+
"lstrip": true,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": true,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"64010": {
|
| 101 |
+
"content": "<extra_id_89>",
|
| 102 |
+
"lstrip": true,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": true,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"64011": {
|
| 109 |
+
"content": "<extra_id_88>",
|
| 110 |
+
"lstrip": true,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": true,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"64012": {
|
| 117 |
+
"content": "<extra_id_87>",
|
| 118 |
+
"lstrip": true,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": true,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"64013": {
|
| 125 |
+
"content": "<extra_id_86>",
|
| 126 |
+
"lstrip": true,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": true,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"64014": {
|
| 133 |
+
"content": "<extra_id_85>",
|
| 134 |
+
"lstrip": true,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": true,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"64015": {
|
| 141 |
+
"content": "<extra_id_84>",
|
| 142 |
+
"lstrip": true,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": true,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"64016": {
|
| 149 |
+
"content": "<extra_id_83>",
|
| 150 |
+
"lstrip": true,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": true,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"64017": {
|
| 157 |
+
"content": "<extra_id_82>",
|
| 158 |
+
"lstrip": true,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": true,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"64018": {
|
| 165 |
+
"content": "<extra_id_81>",
|
| 166 |
+
"lstrip": true,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": true,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"64019": {
|
| 173 |
+
"content": "<extra_id_80>",
|
| 174 |
+
"lstrip": true,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": true,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"64020": {
|
| 181 |
+
"content": "<extra_id_79>",
|
| 182 |
+
"lstrip": true,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": true,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"64021": {
|
| 189 |
+
"content": "<extra_id_78>",
|
| 190 |
+
"lstrip": true,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": true,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"64022": {
|
| 197 |
+
"content": "<extra_id_77>",
|
| 198 |
+
"lstrip": true,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": true,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"64023": {
|
| 205 |
+
"content": "<extra_id_76>",
|
| 206 |
+
"lstrip": true,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": true,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"64024": {
|
| 213 |
+
"content": "<extra_id_75>",
|
| 214 |
+
"lstrip": true,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": true,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"64025": {
|
| 221 |
+
"content": "<extra_id_74>",
|
| 222 |
+
"lstrip": true,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": true,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"64026": {
|
| 229 |
+
"content": "<extra_id_73>",
|
| 230 |
+
"lstrip": true,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": true,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"64027": {
|
| 237 |
+
"content": "<extra_id_72>",
|
| 238 |
+
"lstrip": true,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": true,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"64028": {
|
| 245 |
+
"content": "<extra_id_71>",
|
| 246 |
+
"lstrip": true,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": true,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"64029": {
|
| 253 |
+
"content": "<extra_id_70>",
|
| 254 |
+
"lstrip": true,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": true,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"64030": {
|
| 261 |
+
"content": "<extra_id_69>",
|
| 262 |
+
"lstrip": true,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": true,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"64031": {
|
| 269 |
+
"content": "<extra_id_68>",
|
| 270 |
+
"lstrip": true,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": true,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"64032": {
|
| 277 |
+
"content": "<extra_id_67>",
|
| 278 |
+
"lstrip": true,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": true,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"64033": {
|
| 285 |
+
"content": "<extra_id_66>",
|
| 286 |
+
"lstrip": true,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": true,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"64034": {
|
| 293 |
+
"content": "<extra_id_65>",
|
| 294 |
+
"lstrip": true,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": true,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"64035": {
|
| 301 |
+
"content": "<extra_id_64>",
|
| 302 |
+
"lstrip": true,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": true,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"64036": {
|
| 309 |
+
"content": "<extra_id_63>",
|
| 310 |
+
"lstrip": true,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": true,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"64037": {
|
| 317 |
+
"content": "<extra_id_62>",
|
| 318 |
+
"lstrip": true,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": true,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"64038": {
|
| 325 |
+
"content": "<extra_id_61>",
|
| 326 |
+
"lstrip": true,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": true,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"64039": {
|
| 333 |
+
"content": "<extra_id_60>",
|
| 334 |
+
"lstrip": true,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": true,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"64040": {
|
| 341 |
+
"content": "<extra_id_59>",
|
| 342 |
+
"lstrip": true,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": true,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"64041": {
|
| 349 |
+
"content": "<extra_id_58>",
|
| 350 |
+
"lstrip": true,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": true,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"64042": {
|
| 357 |
+
"content": "<extra_id_57>",
|
| 358 |
+
"lstrip": true,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": true,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"64043": {
|
| 365 |
+
"content": "<extra_id_56>",
|
| 366 |
+
"lstrip": true,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": true,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"64044": {
|
| 373 |
+
"content": "<extra_id_55>",
|
| 374 |
+
"lstrip": true,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": true,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"64045": {
|
| 381 |
+
"content": "<extra_id_54>",
|
| 382 |
+
"lstrip": true,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": true,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"64046": {
|
| 389 |
+
"content": "<extra_id_53>",
|
| 390 |
+
"lstrip": true,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": true,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"64047": {
|
| 397 |
+
"content": "<extra_id_52>",
|
| 398 |
+
"lstrip": true,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": true,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"64048": {
|
| 405 |
+
"content": "<extra_id_51>",
|
| 406 |
+
"lstrip": true,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": true,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"64049": {
|
| 413 |
+
"content": "<extra_id_50>",
|
| 414 |
+
"lstrip": true,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": true,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"64050": {
|
| 421 |
+
"content": "<extra_id_49>",
|
| 422 |
+
"lstrip": true,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": true,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"64051": {
|
| 429 |
+
"content": "<extra_id_48>",
|
| 430 |
+
"lstrip": true,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": true,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"64052": {
|
| 437 |
+
"content": "<extra_id_47>",
|
| 438 |
+
"lstrip": true,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": true,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"64053": {
|
| 445 |
+
"content": "<extra_id_46>",
|
| 446 |
+
"lstrip": true,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": true,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"64054": {
|
| 453 |
+
"content": "<extra_id_45>",
|
| 454 |
+
"lstrip": true,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": true,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"64055": {
|
| 461 |
+
"content": "<extra_id_44>",
|
| 462 |
+
"lstrip": true,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": true,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"64056": {
|
| 469 |
+
"content": "<extra_id_43>",
|
| 470 |
+
"lstrip": true,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": true,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"64057": {
|
| 477 |
+
"content": "<extra_id_42>",
|
| 478 |
+
"lstrip": true,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": true,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"64058": {
|
| 485 |
+
"content": "<extra_id_41>",
|
| 486 |
+
"lstrip": true,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": true,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"64059": {
|
| 493 |
+
"content": "<extra_id_40>",
|
| 494 |
+
"lstrip": true,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": true,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"64060": {
|
| 501 |
+
"content": "<extra_id_39>",
|
| 502 |
+
"lstrip": true,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": true,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"64061": {
|
| 509 |
+
"content": "<extra_id_38>",
|
| 510 |
+
"lstrip": true,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": true,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"64062": {
|
| 517 |
+
"content": "<extra_id_37>",
|
| 518 |
+
"lstrip": true,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": true,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"64063": {
|
| 525 |
+
"content": "<extra_id_36>",
|
| 526 |
+
"lstrip": true,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": true,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"64064": {
|
| 533 |
+
"content": "<extra_id_35>",
|
| 534 |
+
"lstrip": true,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": true,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"64065": {
|
| 541 |
+
"content": "<extra_id_34>",
|
| 542 |
+
"lstrip": true,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": true,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"64066": {
|
| 549 |
+
"content": "<extra_id_33>",
|
| 550 |
+
"lstrip": true,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": true,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"64067": {
|
| 557 |
+
"content": "<extra_id_32>",
|
| 558 |
+
"lstrip": true,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": true,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"64068": {
|
| 565 |
+
"content": "<extra_id_31>",
|
| 566 |
+
"lstrip": true,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": true,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"64069": {
|
| 573 |
+
"content": "<extra_id_30>",
|
| 574 |
+
"lstrip": true,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": true,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"64070": {
|
| 581 |
+
"content": "<extra_id_29>",
|
| 582 |
+
"lstrip": true,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": true,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"64071": {
|
| 589 |
+
"content": "<extra_id_28>",
|
| 590 |
+
"lstrip": true,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": true,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"64072": {
|
| 597 |
+
"content": "<extra_id_27>",
|
| 598 |
+
"lstrip": true,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": true,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"64073": {
|
| 605 |
+
"content": "<extra_id_26>",
|
| 606 |
+
"lstrip": true,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": true,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"64074": {
|
| 613 |
+
"content": "<extra_id_25>",
|
| 614 |
+
"lstrip": true,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": true,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"64075": {
|
| 621 |
+
"content": "<extra_id_24>",
|
| 622 |
+
"lstrip": true,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": true,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"64076": {
|
| 629 |
+
"content": "<extra_id_23>",
|
| 630 |
+
"lstrip": true,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": true,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"64077": {
|
| 637 |
+
"content": "<extra_id_22>",
|
| 638 |
+
"lstrip": true,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": true,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"64078": {
|
| 645 |
+
"content": "<extra_id_21>",
|
| 646 |
+
"lstrip": true,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": true,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"64079": {
|
| 653 |
+
"content": "<extra_id_20>",
|
| 654 |
+
"lstrip": true,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": true,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"64080": {
|
| 661 |
+
"content": "<extra_id_19>",
|
| 662 |
+
"lstrip": true,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": true,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"64081": {
|
| 669 |
+
"content": "<extra_id_18>",
|
| 670 |
+
"lstrip": true,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": true,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"64082": {
|
| 677 |
+
"content": "<extra_id_17>",
|
| 678 |
+
"lstrip": true,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": true,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"64083": {
|
| 685 |
+
"content": "<extra_id_16>",
|
| 686 |
+
"lstrip": true,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": true,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"64084": {
|
| 693 |
+
"content": "<extra_id_15>",
|
| 694 |
+
"lstrip": true,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": true,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"64085": {
|
| 701 |
+
"content": "<extra_id_14>",
|
| 702 |
+
"lstrip": true,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": true,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"64086": {
|
| 709 |
+
"content": "<extra_id_13>",
|
| 710 |
+
"lstrip": true,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": true,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"64087": {
|
| 717 |
+
"content": "<extra_id_12>",
|
| 718 |
+
"lstrip": true,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": true,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"64088": {
|
| 725 |
+
"content": "<extra_id_11>",
|
| 726 |
+
"lstrip": true,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": true,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"64089": {
|
| 733 |
+
"content": "<extra_id_10>",
|
| 734 |
+
"lstrip": true,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": true,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"64090": {
|
| 741 |
+
"content": "<extra_id_9>",
|
| 742 |
+
"lstrip": true,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": true,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"64091": {
|
| 749 |
+
"content": "<extra_id_8>",
|
| 750 |
+
"lstrip": true,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": true,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"64092": {
|
| 757 |
+
"content": "<extra_id_7>",
|
| 758 |
+
"lstrip": true,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": true,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"64093": {
|
| 765 |
+
"content": "<extra_id_6>",
|
| 766 |
+
"lstrip": true,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": true,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"64094": {
|
| 773 |
+
"content": "<extra_id_5>",
|
| 774 |
+
"lstrip": true,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": true,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"64095": {
|
| 781 |
+
"content": "<extra_id_4>",
|
| 782 |
+
"lstrip": true,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": true,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"64096": {
|
| 789 |
+
"content": "<extra_id_3>",
|
| 790 |
+
"lstrip": true,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": true,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"64097": {
|
| 797 |
+
"content": "<extra_id_2>",
|
| 798 |
+
"lstrip": true,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": true,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"64098": {
|
| 805 |
+
"content": "<extra_id_1>",
|
| 806 |
+
"lstrip": true,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": true,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"64099": {
|
| 813 |
+
"content": "<extra_id_0>",
|
| 814 |
+
"lstrip": true,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": true,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"64100": {
|
| 821 |
+
"content": "<pad>",
|
| 822 |
+
"lstrip": false,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": false,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
}
|
| 828 |
+
},
|
| 829 |
+
"additional_special_tokens": [
|
| 830 |
+
"<extra_id_0>",
|
| 831 |
+
"<extra_id_1>",
|
| 832 |
+
"<extra_id_2>",
|
| 833 |
+
"<extra_id_3>",
|
| 834 |
+
"<extra_id_4>",
|
| 835 |
+
"<extra_id_5>",
|
| 836 |
+
"<extra_id_6>",
|
| 837 |
+
"<extra_id_7>",
|
| 838 |
+
"<extra_id_8>",
|
| 839 |
+
"<extra_id_9>",
|
| 840 |
+
"<extra_id_10>",
|
| 841 |
+
"<extra_id_11>",
|
| 842 |
+
"<extra_id_12>",
|
| 843 |
+
"<extra_id_13>",
|
| 844 |
+
"<extra_id_14>",
|
| 845 |
+
"<extra_id_15>",
|
| 846 |
+
"<extra_id_16>",
|
| 847 |
+
"<extra_id_17>",
|
| 848 |
+
"<extra_id_18>",
|
| 849 |
+
"<extra_id_19>",
|
| 850 |
+
"<extra_id_20>",
|
| 851 |
+
"<extra_id_21>",
|
| 852 |
+
"<extra_id_22>",
|
| 853 |
+
"<extra_id_23>",
|
| 854 |
+
"<extra_id_24>",
|
| 855 |
+
"<extra_id_25>",
|
| 856 |
+
"<extra_id_26>",
|
| 857 |
+
"<extra_id_27>",
|
| 858 |
+
"<extra_id_28>",
|
| 859 |
+
"<extra_id_29>",
|
| 860 |
+
"<extra_id_30>",
|
| 861 |
+
"<extra_id_31>",
|
| 862 |
+
"<extra_id_32>",
|
| 863 |
+
"<extra_id_33>",
|
| 864 |
+
"<extra_id_34>",
|
| 865 |
+
"<extra_id_35>",
|
| 866 |
+
"<extra_id_36>",
|
| 867 |
+
"<extra_id_37>",
|
| 868 |
+
"<extra_id_38>",
|
| 869 |
+
"<extra_id_39>",
|
| 870 |
+
"<extra_id_40>",
|
| 871 |
+
"<extra_id_41>",
|
| 872 |
+
"<extra_id_42>",
|
| 873 |
+
"<extra_id_43>",
|
| 874 |
+
"<extra_id_44>",
|
| 875 |
+
"<extra_id_45>",
|
| 876 |
+
"<extra_id_46>",
|
| 877 |
+
"<extra_id_47>",
|
| 878 |
+
"<extra_id_48>",
|
| 879 |
+
"<extra_id_49>",
|
| 880 |
+
"<extra_id_50>",
|
| 881 |
+
"<extra_id_51>",
|
| 882 |
+
"<extra_id_52>",
|
| 883 |
+
"<extra_id_53>",
|
| 884 |
+
"<extra_id_54>",
|
| 885 |
+
"<extra_id_55>",
|
| 886 |
+
"<extra_id_56>",
|
| 887 |
+
"<extra_id_57>",
|
| 888 |
+
"<extra_id_58>",
|
| 889 |
+
"<extra_id_59>",
|
| 890 |
+
"<extra_id_60>",
|
| 891 |
+
"<extra_id_61>",
|
| 892 |
+
"<extra_id_62>",
|
| 893 |
+
"<extra_id_63>",
|
| 894 |
+
"<extra_id_64>",
|
| 895 |
+
"<extra_id_65>",
|
| 896 |
+
"<extra_id_66>",
|
| 897 |
+
"<extra_id_67>",
|
| 898 |
+
"<extra_id_68>",
|
| 899 |
+
"<extra_id_69>",
|
| 900 |
+
"<extra_id_70>",
|
| 901 |
+
"<extra_id_71>",
|
| 902 |
+
"<extra_id_72>",
|
| 903 |
+
"<extra_id_73>",
|
| 904 |
+
"<extra_id_74>",
|
| 905 |
+
"<extra_id_75>",
|
| 906 |
+
"<extra_id_76>",
|
| 907 |
+
"<extra_id_77>",
|
| 908 |
+
"<extra_id_78>",
|
| 909 |
+
"<extra_id_79>",
|
| 910 |
+
"<extra_id_80>",
|
| 911 |
+
"<extra_id_81>",
|
| 912 |
+
"<extra_id_82>",
|
| 913 |
+
"<extra_id_83>",
|
| 914 |
+
"<extra_id_84>",
|
| 915 |
+
"<extra_id_85>",
|
| 916 |
+
"<extra_id_86>",
|
| 917 |
+
"<extra_id_87>",
|
| 918 |
+
"<extra_id_88>",
|
| 919 |
+
"<extra_id_89>",
|
| 920 |
+
"<extra_id_90>",
|
| 921 |
+
"<extra_id_91>",
|
| 922 |
+
"<extra_id_92>",
|
| 923 |
+
"<extra_id_93>",
|
| 924 |
+
"<extra_id_94>",
|
| 925 |
+
"<extra_id_95>",
|
| 926 |
+
"<extra_id_96>",
|
| 927 |
+
"<extra_id_97>",
|
| 928 |
+
"<extra_id_98>",
|
| 929 |
+
"<extra_id_99>"
|
| 930 |
+
],
|
| 931 |
+
"clean_up_tokenization_spaces": true,
|
| 932 |
+
"eos_token": "</s>",
|
| 933 |
+
"extra_ids": 100,
|
| 934 |
+
"legacy": true,
|
| 935 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 936 |
+
"pad_token": "<pad>",
|
| 937 |
+
"sp_model_kwargs": {},
|
| 938 |
+
"tokenizer_class": "T5Tokenizer",
|
| 939 |
+
"unk_token": "<unk>"
|
| 940 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1811 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 25000,
|
| 6 |
+
"global_step": 125000,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"grad_norm": 0.6675467491149902,
|
| 14 |
+
"learning_rate": 0.0002988,
|
| 15 |
+
"loss": 0.2058,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.01,
|
| 20 |
+
"grad_norm": 0.40607237815856934,
|
| 21 |
+
"learning_rate": 0.00029759999999999997,
|
| 22 |
+
"loss": 0.2096,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.01,
|
| 27 |
+
"grad_norm": 0.9344772100448608,
|
| 28 |
+
"learning_rate": 0.0002964,
|
| 29 |
+
"loss": 0.237,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.02,
|
| 34 |
+
"grad_norm": 2.254749059677124,
|
| 35 |
+
"learning_rate": 0.00029519999999999997,
|
| 36 |
+
"loss": 0.2275,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.02,
|
| 41 |
+
"grad_norm": 0.8561826348304749,
|
| 42 |
+
"learning_rate": 0.000294,
|
| 43 |
+
"loss": 0.2355,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.02,
|
| 48 |
+
"grad_norm": 1.0209927558898926,
|
| 49 |
+
"learning_rate": 0.00029279999999999996,
|
| 50 |
+
"loss": 0.2275,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"grad_norm": 0.9906947612762451,
|
| 56 |
+
"learning_rate": 0.0002916,
|
| 57 |
+
"loss": 0.2188,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.03,
|
| 62 |
+
"grad_norm": 0.9113153219223022,
|
| 63 |
+
"learning_rate": 0.00029039999999999996,
|
| 64 |
+
"loss": 0.2272,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.04,
|
| 69 |
+
"grad_norm": 1.4784849882125854,
|
| 70 |
+
"learning_rate": 0.0002892,
|
| 71 |
+
"loss": 0.2437,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.04,
|
| 76 |
+
"grad_norm": 0.9436748623847961,
|
| 77 |
+
"learning_rate": 0.00028799999999999995,
|
| 78 |
+
"loss": 0.2378,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.04,
|
| 83 |
+
"grad_norm": 0.9457006454467773,
|
| 84 |
+
"learning_rate": 0.0002868,
|
| 85 |
+
"loss": 0.2244,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.05,
|
| 90 |
+
"grad_norm": 0.6395999193191528,
|
| 91 |
+
"learning_rate": 0.00028559999999999995,
|
| 92 |
+
"loss": 0.2251,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"grad_norm": 0.4920419156551361,
|
| 98 |
+
"learning_rate": 0.0002844,
|
| 99 |
+
"loss": 0.2249,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.06,
|
| 104 |
+
"grad_norm": 0.67146235704422,
|
| 105 |
+
"learning_rate": 0.00028319999999999994,
|
| 106 |
+
"loss": 0.2223,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.06,
|
| 111 |
+
"grad_norm": 1.5474592447280884,
|
| 112 |
+
"learning_rate": 0.00028199999999999997,
|
| 113 |
+
"loss": 0.2231,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.06,
|
| 118 |
+
"grad_norm": 1.2913522720336914,
|
| 119 |
+
"learning_rate": 0.0002808,
|
| 120 |
+
"loss": 0.2344,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.07,
|
| 125 |
+
"grad_norm": 1.6871858835220337,
|
| 126 |
+
"learning_rate": 0.00027959999999999997,
|
| 127 |
+
"loss": 0.2325,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.07,
|
| 132 |
+
"grad_norm": 0.6918925046920776,
|
| 133 |
+
"learning_rate": 0.0002784,
|
| 134 |
+
"loss": 0.2329,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.08,
|
| 139 |
+
"grad_norm": 0.9310051798820496,
|
| 140 |
+
"learning_rate": 0.0002772,
|
| 141 |
+
"loss": 0.2309,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.08,
|
| 146 |
+
"grad_norm": 1.6937859058380127,
|
| 147 |
+
"learning_rate": 0.000276,
|
| 148 |
+
"loss": 0.2362,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.08,
|
| 153 |
+
"grad_norm": 3.504669666290283,
|
| 154 |
+
"learning_rate": 0.0002748,
|
| 155 |
+
"loss": 0.2295,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.09,
|
| 160 |
+
"grad_norm": 0.7235252261161804,
|
| 161 |
+
"learning_rate": 0.0002736,
|
| 162 |
+
"loss": 0.2286,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.09,
|
| 167 |
+
"grad_norm": 1.0144588947296143,
|
| 168 |
+
"learning_rate": 0.0002724,
|
| 169 |
+
"loss": 0.2302,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.1,
|
| 174 |
+
"grad_norm": 0.7903403043746948,
|
| 175 |
+
"learning_rate": 0.0002712,
|
| 176 |
+
"loss": 0.2266,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"grad_norm": 1.6691497564315796,
|
| 182 |
+
"learning_rate": 0.00027,
|
| 183 |
+
"loss": 0.2356,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.1,
|
| 188 |
+
"grad_norm": 0.6409358978271484,
|
| 189 |
+
"learning_rate": 0.0002688,
|
| 190 |
+
"loss": 0.2292,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.11,
|
| 195 |
+
"grad_norm": 0.7465757131576538,
|
| 196 |
+
"learning_rate": 0.0002676,
|
| 197 |
+
"loss": 0.2347,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.11,
|
| 202 |
+
"grad_norm": 1.411289930343628,
|
| 203 |
+
"learning_rate": 0.00026639999999999997,
|
| 204 |
+
"loss": 0.2275,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.12,
|
| 209 |
+
"grad_norm": 1.5167527198791504,
|
| 210 |
+
"learning_rate": 0.0002652,
|
| 211 |
+
"loss": 0.2364,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.12,
|
| 216 |
+
"grad_norm": 1.128173589706421,
|
| 217 |
+
"learning_rate": 0.00026399999999999997,
|
| 218 |
+
"loss": 0.2197,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12,
|
| 223 |
+
"grad_norm": 0.8312121033668518,
|
| 224 |
+
"learning_rate": 0.0002628,
|
| 225 |
+
"loss": 0.236,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.13,
|
| 230 |
+
"grad_norm": 0.7007321715354919,
|
| 231 |
+
"learning_rate": 0.00026159999999999996,
|
| 232 |
+
"loss": 0.2229,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.13,
|
| 237 |
+
"grad_norm": 1.0870940685272217,
|
| 238 |
+
"learning_rate": 0.0002604,
|
| 239 |
+
"loss": 0.2201,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.14,
|
| 244 |
+
"grad_norm": 0.8884884715080261,
|
| 245 |
+
"learning_rate": 0.00025919999999999996,
|
| 246 |
+
"loss": 0.2178,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.14,
|
| 251 |
+
"grad_norm": 0.5293123126029968,
|
| 252 |
+
"learning_rate": 0.000258,
|
| 253 |
+
"loss": 0.2248,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.14,
|
| 258 |
+
"grad_norm": 0.8335347771644592,
|
| 259 |
+
"learning_rate": 0.00025679999999999995,
|
| 260 |
+
"loss": 0.2236,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.15,
|
| 265 |
+
"grad_norm": 0.7105595469474792,
|
| 266 |
+
"learning_rate": 0.0002556,
|
| 267 |
+
"loss": 0.2294,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.15,
|
| 272 |
+
"grad_norm": 1.0978660583496094,
|
| 273 |
+
"learning_rate": 0.00025439999999999995,
|
| 274 |
+
"loss": 0.2236,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.16,
|
| 279 |
+
"grad_norm": 0.7025924921035767,
|
| 280 |
+
"learning_rate": 0.0002532,
|
| 281 |
+
"loss": 0.219,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.16,
|
| 286 |
+
"grad_norm": 0.9559372067451477,
|
| 287 |
+
"learning_rate": 0.00025199999999999995,
|
| 288 |
+
"loss": 0.2147,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.16,
|
| 293 |
+
"grad_norm": 0.550178587436676,
|
| 294 |
+
"learning_rate": 0.00025079999999999997,
|
| 295 |
+
"loss": 0.2141,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.17,
|
| 300 |
+
"grad_norm": 1.0202014446258545,
|
| 301 |
+
"learning_rate": 0.00024959999999999994,
|
| 302 |
+
"loss": 0.2166,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.17,
|
| 307 |
+
"grad_norm": 0.5799145102500916,
|
| 308 |
+
"learning_rate": 0.00024839999999999997,
|
| 309 |
+
"loss": 0.2219,
|
| 310 |
+
"step": 21500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.18,
|
| 314 |
+
"grad_norm": 1.9509211778640747,
|
| 315 |
+
"learning_rate": 0.0002472,
|
| 316 |
+
"loss": 0.2144,
|
| 317 |
+
"step": 22000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.18,
|
| 321 |
+
"grad_norm": 0.6535309553146362,
|
| 322 |
+
"learning_rate": 0.00024599999999999996,
|
| 323 |
+
"loss": 0.2189,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.18,
|
| 328 |
+
"grad_norm": 1.4835234880447388,
|
| 329 |
+
"learning_rate": 0.0002448,
|
| 330 |
+
"loss": 0.2105,
|
| 331 |
+
"step": 23000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.19,
|
| 335 |
+
"grad_norm": 1.50291907787323,
|
| 336 |
+
"learning_rate": 0.00024359999999999999,
|
| 337 |
+
"loss": 0.2076,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.19,
|
| 342 |
+
"grad_norm": 0.6879478693008423,
|
| 343 |
+
"learning_rate": 0.00024239999999999998,
|
| 344 |
+
"loss": 0.2231,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.2,
|
| 349 |
+
"grad_norm": 1.3261083364486694,
|
| 350 |
+
"learning_rate": 0.00024119999999999998,
|
| 351 |
+
"loss": 0.2255,
|
| 352 |
+
"step": 24500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.2,
|
| 356 |
+
"grad_norm": 1.1070926189422607,
|
| 357 |
+
"learning_rate": 0.00023999999999999998,
|
| 358 |
+
"loss": 0.229,
|
| 359 |
+
"step": 25000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.2,
|
| 363 |
+
"eval_loss": 0.14503039419651031,
|
| 364 |
+
"eval_runtime": 197.5245,
|
| 365 |
+
"eval_samples_per_second": 101.253,
|
| 366 |
+
"eval_steps_per_second": 25.313,
|
| 367 |
+
"step": 25000
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.2,
|
| 371 |
+
"grad_norm": 0.4342971742153168,
|
| 372 |
+
"learning_rate": 0.0002388,
|
| 373 |
+
"loss": 0.2178,
|
| 374 |
+
"step": 25500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.21,
|
| 378 |
+
"grad_norm": 4.339428901672363,
|
| 379 |
+
"learning_rate": 0.0002376,
|
| 380 |
+
"loss": 0.2107,
|
| 381 |
+
"step": 26000
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.21,
|
| 385 |
+
"grad_norm": 3.38554310798645,
|
| 386 |
+
"learning_rate": 0.0002364,
|
| 387 |
+
"loss": 0.2227,
|
| 388 |
+
"step": 26500
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.22,
|
| 392 |
+
"grad_norm": 1.249841332435608,
|
| 393 |
+
"learning_rate": 0.0002352,
|
| 394 |
+
"loss": 0.2119,
|
| 395 |
+
"step": 27000
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.22,
|
| 399 |
+
"grad_norm": 1.1185526847839355,
|
| 400 |
+
"learning_rate": 0.000234,
|
| 401 |
+
"loss": 0.2085,
|
| 402 |
+
"step": 27500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.22,
|
| 406 |
+
"grad_norm": 1.008499264717102,
|
| 407 |
+
"learning_rate": 0.0002328,
|
| 408 |
+
"loss": 0.214,
|
| 409 |
+
"step": 28000
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.23,
|
| 413 |
+
"grad_norm": 1.0491580963134766,
|
| 414 |
+
"learning_rate": 0.0002316,
|
| 415 |
+
"loss": 0.2086,
|
| 416 |
+
"step": 28500
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.23,
|
| 420 |
+
"grad_norm": 1.0968835353851318,
|
| 421 |
+
"learning_rate": 0.0002304,
|
| 422 |
+
"loss": 0.2094,
|
| 423 |
+
"step": 29000
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.24,
|
| 427 |
+
"grad_norm": 0.4313267767429352,
|
| 428 |
+
"learning_rate": 0.0002292,
|
| 429 |
+
"loss": 0.2048,
|
| 430 |
+
"step": 29500
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.24,
|
| 434 |
+
"grad_norm": 0.5634821653366089,
|
| 435 |
+
"learning_rate": 0.00022799999999999999,
|
| 436 |
+
"loss": 0.211,
|
| 437 |
+
"step": 30000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.24,
|
| 441 |
+
"grad_norm": 0.8901171684265137,
|
| 442 |
+
"learning_rate": 0.00022679999999999998,
|
| 443 |
+
"loss": 0.2123,
|
| 444 |
+
"step": 30500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.25,
|
| 448 |
+
"grad_norm": 0.5377653241157532,
|
| 449 |
+
"learning_rate": 0.00022559999999999998,
|
| 450 |
+
"loss": 0.2097,
|
| 451 |
+
"step": 31000
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.25,
|
| 455 |
+
"grad_norm": 0.8237270712852478,
|
| 456 |
+
"learning_rate": 0.00022439999999999998,
|
| 457 |
+
"loss": 0.2066,
|
| 458 |
+
"step": 31500
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.26,
|
| 462 |
+
"grad_norm": 0.5759382247924805,
|
| 463 |
+
"learning_rate": 0.00022319999999999998,
|
| 464 |
+
"loss": 0.2098,
|
| 465 |
+
"step": 32000
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.26,
|
| 469 |
+
"grad_norm": 0.7323036193847656,
|
| 470 |
+
"learning_rate": 0.00022199999999999998,
|
| 471 |
+
"loss": 0.2087,
|
| 472 |
+
"step": 32500
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.26,
|
| 476 |
+
"grad_norm": 0.8658179640769958,
|
| 477 |
+
"learning_rate": 0.00022079999999999997,
|
| 478 |
+
"loss": 0.2038,
|
| 479 |
+
"step": 33000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.27,
|
| 483 |
+
"grad_norm": 0.8712558150291443,
|
| 484 |
+
"learning_rate": 0.00021959999999999997,
|
| 485 |
+
"loss": 0.2202,
|
| 486 |
+
"step": 33500
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.27,
|
| 490 |
+
"grad_norm": 1.005462884902954,
|
| 491 |
+
"learning_rate": 0.00021839999999999997,
|
| 492 |
+
"loss": 0.2052,
|
| 493 |
+
"step": 34000
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.28,
|
| 497 |
+
"grad_norm": 0.4281785786151886,
|
| 498 |
+
"learning_rate": 0.00021719999999999997,
|
| 499 |
+
"loss": 0.2049,
|
| 500 |
+
"step": 34500
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.28,
|
| 504 |
+
"grad_norm": 0.5366469621658325,
|
| 505 |
+
"learning_rate": 0.00021599999999999996,
|
| 506 |
+
"loss": 0.2067,
|
| 507 |
+
"step": 35000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.28,
|
| 511 |
+
"grad_norm": 0.9057306051254272,
|
| 512 |
+
"learning_rate": 0.00021479999999999996,
|
| 513 |
+
"loss": 0.2036,
|
| 514 |
+
"step": 35500
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.29,
|
| 518 |
+
"grad_norm": 0.9041026830673218,
|
| 519 |
+
"learning_rate": 0.00021359999999999996,
|
| 520 |
+
"loss": 0.2092,
|
| 521 |
+
"step": 36000
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.29,
|
| 525 |
+
"grad_norm": 0.8272420167922974,
|
| 526 |
+
"learning_rate": 0.00021239999999999996,
|
| 527 |
+
"loss": 0.2043,
|
| 528 |
+
"step": 36500
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.3,
|
| 532 |
+
"grad_norm": 1.302566409111023,
|
| 533 |
+
"learning_rate": 0.00021119999999999996,
|
| 534 |
+
"loss": 0.2247,
|
| 535 |
+
"step": 37000
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.3,
|
| 539 |
+
"grad_norm": 0.45851215720176697,
|
| 540 |
+
"learning_rate": 0.00020999999999999998,
|
| 541 |
+
"loss": 0.2119,
|
| 542 |
+
"step": 37500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.3,
|
| 546 |
+
"grad_norm": 0.9625339508056641,
|
| 547 |
+
"learning_rate": 0.00020879999999999998,
|
| 548 |
+
"loss": 0.2036,
|
| 549 |
+
"step": 38000
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.31,
|
| 553 |
+
"grad_norm": 2.465646505355835,
|
| 554 |
+
"learning_rate": 0.00020759999999999998,
|
| 555 |
+
"loss": 0.1981,
|
| 556 |
+
"step": 38500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.31,
|
| 560 |
+
"grad_norm": 3.8826301097869873,
|
| 561 |
+
"learning_rate": 0.00020639999999999998,
|
| 562 |
+
"loss": 0.2008,
|
| 563 |
+
"step": 39000
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.32,
|
| 567 |
+
"grad_norm": 0.9201263785362244,
|
| 568 |
+
"learning_rate": 0.0002052,
|
| 569 |
+
"loss": 0.1959,
|
| 570 |
+
"step": 39500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.32,
|
| 574 |
+
"grad_norm": 0.8154922723770142,
|
| 575 |
+
"learning_rate": 0.000204,
|
| 576 |
+
"loss": 0.2032,
|
| 577 |
+
"step": 40000
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.32,
|
| 581 |
+
"grad_norm": 1.0132577419281006,
|
| 582 |
+
"learning_rate": 0.0002028,
|
| 583 |
+
"loss": 0.2012,
|
| 584 |
+
"step": 40500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.33,
|
| 588 |
+
"grad_norm": 0.34237733483314514,
|
| 589 |
+
"learning_rate": 0.0002016,
|
| 590 |
+
"loss": 0.2068,
|
| 591 |
+
"step": 41000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.33,
|
| 595 |
+
"grad_norm": 0.5986165404319763,
|
| 596 |
+
"learning_rate": 0.0002004,
|
| 597 |
+
"loss": 0.204,
|
| 598 |
+
"step": 41500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.34,
|
| 602 |
+
"grad_norm": 1.2128850221633911,
|
| 603 |
+
"learning_rate": 0.0001992,
|
| 604 |
+
"loss": 0.1969,
|
| 605 |
+
"step": 42000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.34,
|
| 609 |
+
"grad_norm": 1.2548407316207886,
|
| 610 |
+
"learning_rate": 0.000198,
|
| 611 |
+
"loss": 0.2055,
|
| 612 |
+
"step": 42500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.34,
|
| 616 |
+
"grad_norm": 0.9521819949150085,
|
| 617 |
+
"learning_rate": 0.00019679999999999999,
|
| 618 |
+
"loss": 0.2018,
|
| 619 |
+
"step": 43000
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.35,
|
| 623 |
+
"grad_norm": 0.6435508728027344,
|
| 624 |
+
"learning_rate": 0.00019559999999999998,
|
| 625 |
+
"loss": 0.2013,
|
| 626 |
+
"step": 43500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.35,
|
| 630 |
+
"grad_norm": 2.0959296226501465,
|
| 631 |
+
"learning_rate": 0.00019439999999999998,
|
| 632 |
+
"loss": 0.2032,
|
| 633 |
+
"step": 44000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.36,
|
| 637 |
+
"grad_norm": 0.5862271189689636,
|
| 638 |
+
"learning_rate": 0.00019319999999999998,
|
| 639 |
+
"loss": 0.1961,
|
| 640 |
+
"step": 44500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.36,
|
| 644 |
+
"grad_norm": 0.31843170523643494,
|
| 645 |
+
"learning_rate": 0.00019199999999999998,
|
| 646 |
+
"loss": 0.196,
|
| 647 |
+
"step": 45000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.36,
|
| 651 |
+
"grad_norm": 1.3819515705108643,
|
| 652 |
+
"learning_rate": 0.00019079999999999998,
|
| 653 |
+
"loss": 0.1966,
|
| 654 |
+
"step": 45500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.37,
|
| 658 |
+
"grad_norm": 1.03080415725708,
|
| 659 |
+
"learning_rate": 0.00018959999999999997,
|
| 660 |
+
"loss": 0.1985,
|
| 661 |
+
"step": 46000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.37,
|
| 665 |
+
"grad_norm": 0.47353965044021606,
|
| 666 |
+
"learning_rate": 0.00018839999999999997,
|
| 667 |
+
"loss": 0.1928,
|
| 668 |
+
"step": 46500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.38,
|
| 672 |
+
"grad_norm": 0.774486780166626,
|
| 673 |
+
"learning_rate": 0.0001872,
|
| 674 |
+
"loss": 0.1985,
|
| 675 |
+
"step": 47000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.38,
|
| 679 |
+
"grad_norm": 1.371840000152588,
|
| 680 |
+
"learning_rate": 0.000186,
|
| 681 |
+
"loss": 0.2053,
|
| 682 |
+
"step": 47500
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.38,
|
| 686 |
+
"grad_norm": 0.9633282423019409,
|
| 687 |
+
"learning_rate": 0.0001848,
|
| 688 |
+
"loss": 0.1967,
|
| 689 |
+
"step": 48000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.39,
|
| 693 |
+
"grad_norm": 0.7216082215309143,
|
| 694 |
+
"learning_rate": 0.0001836,
|
| 695 |
+
"loss": 0.1935,
|
| 696 |
+
"step": 48500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.39,
|
| 700 |
+
"grad_norm": 0.8321841955184937,
|
| 701 |
+
"learning_rate": 0.0001824,
|
| 702 |
+
"loss": 0.1909,
|
| 703 |
+
"step": 49000
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.4,
|
| 707 |
+
"grad_norm": 0.924881637096405,
|
| 708 |
+
"learning_rate": 0.00018119999999999999,
|
| 709 |
+
"loss": 0.1914,
|
| 710 |
+
"step": 49500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.4,
|
| 714 |
+
"grad_norm": 1.1322112083435059,
|
| 715 |
+
"learning_rate": 0.00017999999999999998,
|
| 716 |
+
"loss": 0.1823,
|
| 717 |
+
"step": 50000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.4,
|
| 721 |
+
"eval_loss": 0.1376880556344986,
|
| 722 |
+
"eval_runtime": 197.1453,
|
| 723 |
+
"eval_samples_per_second": 101.448,
|
| 724 |
+
"eval_steps_per_second": 25.362,
|
| 725 |
+
"step": 50000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.4,
|
| 729 |
+
"grad_norm": 0.5036086440086365,
|
| 730 |
+
"learning_rate": 0.00017879999999999998,
|
| 731 |
+
"loss": 0.19,
|
| 732 |
+
"step": 50500
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.41,
|
| 736 |
+
"grad_norm": 0.8745198249816895,
|
| 737 |
+
"learning_rate": 0.00017759999999999998,
|
| 738 |
+
"loss": 0.1952,
|
| 739 |
+
"step": 51000
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 0.41,
|
| 743 |
+
"grad_norm": 0.9014063477516174,
|
| 744 |
+
"learning_rate": 0.00017639999999999998,
|
| 745 |
+
"loss": 0.1825,
|
| 746 |
+
"step": 51500
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 0.42,
|
| 750 |
+
"grad_norm": 0.5580583214759827,
|
| 751 |
+
"learning_rate": 0.00017519999999999998,
|
| 752 |
+
"loss": 0.1958,
|
| 753 |
+
"step": 52000
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.42,
|
| 757 |
+
"grad_norm": 0.6560271382331848,
|
| 758 |
+
"learning_rate": 0.00017399999999999997,
|
| 759 |
+
"loss": 0.1986,
|
| 760 |
+
"step": 52500
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 0.42,
|
| 764 |
+
"grad_norm": 0.9042519330978394,
|
| 765 |
+
"learning_rate": 0.00017279999999999997,
|
| 766 |
+
"loss": 0.2037,
|
| 767 |
+
"step": 53000
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.43,
|
| 771 |
+
"grad_norm": 0.7758679986000061,
|
| 772 |
+
"learning_rate": 0.00017159999999999997,
|
| 773 |
+
"loss": 0.1891,
|
| 774 |
+
"step": 53500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.43,
|
| 778 |
+
"grad_norm": 0.9086706042289734,
|
| 779 |
+
"learning_rate": 0.00017039999999999997,
|
| 780 |
+
"loss": 0.1864,
|
| 781 |
+
"step": 54000
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 0.44,
|
| 785 |
+
"grad_norm": 1.0545058250427246,
|
| 786 |
+
"learning_rate": 0.00016919999999999997,
|
| 787 |
+
"loss": 0.199,
|
| 788 |
+
"step": 54500
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.44,
|
| 792 |
+
"grad_norm": 0.20504042506217957,
|
| 793 |
+
"learning_rate": 0.000168,
|
| 794 |
+
"loss": 0.1902,
|
| 795 |
+
"step": 55000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.44,
|
| 799 |
+
"grad_norm": 0.7427380084991455,
|
| 800 |
+
"learning_rate": 0.0001668,
|
| 801 |
+
"loss": 0.192,
|
| 802 |
+
"step": 55500
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 0.45,
|
| 806 |
+
"grad_norm": 0.42541056871414185,
|
| 807 |
+
"learning_rate": 0.0001656,
|
| 808 |
+
"loss": 0.1939,
|
| 809 |
+
"step": 56000
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 0.45,
|
| 813 |
+
"grad_norm": 1.1101672649383545,
|
| 814 |
+
"learning_rate": 0.0001644,
|
| 815 |
+
"loss": 0.195,
|
| 816 |
+
"step": 56500
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 0.46,
|
| 820 |
+
"grad_norm": 0.7569801807403564,
|
| 821 |
+
"learning_rate": 0.0001632,
|
| 822 |
+
"loss": 0.1838,
|
| 823 |
+
"step": 57000
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 0.46,
|
| 827 |
+
"grad_norm": 0.2808530032634735,
|
| 828 |
+
"learning_rate": 0.000162,
|
| 829 |
+
"loss": 0.1948,
|
| 830 |
+
"step": 57500
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 0.46,
|
| 834 |
+
"grad_norm": 1.3836987018585205,
|
| 835 |
+
"learning_rate": 0.0001608,
|
| 836 |
+
"loss": 0.1908,
|
| 837 |
+
"step": 58000
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.47,
|
| 841 |
+
"grad_norm": 0.8910863995552063,
|
| 842 |
+
"learning_rate": 0.0001596,
|
| 843 |
+
"loss": 0.1916,
|
| 844 |
+
"step": 58500
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 0.47,
|
| 848 |
+
"grad_norm": 0.40731602907180786,
|
| 849 |
+
"learning_rate": 0.0001584,
|
| 850 |
+
"loss": 0.178,
|
| 851 |
+
"step": 59000
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 0.48,
|
| 855 |
+
"grad_norm": 1.8736116886138916,
|
| 856 |
+
"learning_rate": 0.0001572,
|
| 857 |
+
"loss": 0.1932,
|
| 858 |
+
"step": 59500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.48,
|
| 862 |
+
"grad_norm": 1.457201600074768,
|
| 863 |
+
"learning_rate": 0.000156,
|
| 864 |
+
"loss": 0.1815,
|
| 865 |
+
"step": 60000
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 0.48,
|
| 869 |
+
"grad_norm": 0.6906099319458008,
|
| 870 |
+
"learning_rate": 0.0001548,
|
| 871 |
+
"loss": 0.1923,
|
| 872 |
+
"step": 60500
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.49,
|
| 876 |
+
"grad_norm": 1.0163846015930176,
|
| 877 |
+
"learning_rate": 0.0001536,
|
| 878 |
+
"loss": 0.1843,
|
| 879 |
+
"step": 61000
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.49,
|
| 883 |
+
"grad_norm": 0.36051931977272034,
|
| 884 |
+
"learning_rate": 0.0001524,
|
| 885 |
+
"loss": 0.1722,
|
| 886 |
+
"step": 61500
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 0.5,
|
| 890 |
+
"grad_norm": 1.3554840087890625,
|
| 891 |
+
"learning_rate": 0.0001512,
|
| 892 |
+
"loss": 0.1868,
|
| 893 |
+
"step": 62000
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 0.5,
|
| 897 |
+
"grad_norm": 0.4623011350631714,
|
| 898 |
+
"learning_rate": 0.00015,
|
| 899 |
+
"loss": 0.1833,
|
| 900 |
+
"step": 62500
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 0.5,
|
| 904 |
+
"grad_norm": 0.31331172585487366,
|
| 905 |
+
"learning_rate": 0.00014879999999999998,
|
| 906 |
+
"loss": 0.1826,
|
| 907 |
+
"step": 63000
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 0.51,
|
| 911 |
+
"grad_norm": 1.1543946266174316,
|
| 912 |
+
"learning_rate": 0.00014759999999999998,
|
| 913 |
+
"loss": 0.181,
|
| 914 |
+
"step": 63500
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 0.51,
|
| 918 |
+
"grad_norm": 1.758339524269104,
|
| 919 |
+
"learning_rate": 0.00014639999999999998,
|
| 920 |
+
"loss": 0.1813,
|
| 921 |
+
"step": 64000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.52,
|
| 925 |
+
"grad_norm": 0.7100640535354614,
|
| 926 |
+
"learning_rate": 0.00014519999999999998,
|
| 927 |
+
"loss": 0.1822,
|
| 928 |
+
"step": 64500
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.52,
|
| 932 |
+
"grad_norm": 0.7758503556251526,
|
| 933 |
+
"learning_rate": 0.00014399999999999998,
|
| 934 |
+
"loss": 0.1809,
|
| 935 |
+
"step": 65000
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 0.52,
|
| 939 |
+
"grad_norm": 1.6668974161148071,
|
| 940 |
+
"learning_rate": 0.00014279999999999997,
|
| 941 |
+
"loss": 0.1888,
|
| 942 |
+
"step": 65500
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.53,
|
| 946 |
+
"grad_norm": 0.6467080116271973,
|
| 947 |
+
"learning_rate": 0.00014159999999999997,
|
| 948 |
+
"loss": 0.1809,
|
| 949 |
+
"step": 66000
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"epoch": 0.53,
|
| 953 |
+
"grad_norm": 0.47351643443107605,
|
| 954 |
+
"learning_rate": 0.0001404,
|
| 955 |
+
"loss": 0.1822,
|
| 956 |
+
"step": 66500
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 0.54,
|
| 960 |
+
"grad_norm": 0.6044811606407166,
|
| 961 |
+
"learning_rate": 0.0001392,
|
| 962 |
+
"loss": 0.1822,
|
| 963 |
+
"step": 67000
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.54,
|
| 967 |
+
"grad_norm": 1.485547423362732,
|
| 968 |
+
"learning_rate": 0.000138,
|
| 969 |
+
"loss": 0.1789,
|
| 970 |
+
"step": 67500
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 0.54,
|
| 974 |
+
"grad_norm": 0.9173816442489624,
|
| 975 |
+
"learning_rate": 0.0001368,
|
| 976 |
+
"loss": 0.184,
|
| 977 |
+
"step": 68000
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 0.55,
|
| 981 |
+
"grad_norm": 0.2925781011581421,
|
| 982 |
+
"learning_rate": 0.0001356,
|
| 983 |
+
"loss": 0.183,
|
| 984 |
+
"step": 68500
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 0.55,
|
| 988 |
+
"grad_norm": 0.29401320219039917,
|
| 989 |
+
"learning_rate": 0.0001344,
|
| 990 |
+
"loss": 0.1799,
|
| 991 |
+
"step": 69000
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 0.56,
|
| 995 |
+
"grad_norm": 0.5869783163070679,
|
| 996 |
+
"learning_rate": 0.00013319999999999999,
|
| 997 |
+
"loss": 0.1768,
|
| 998 |
+
"step": 69500
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.56,
|
| 1002 |
+
"grad_norm": 1.3995858430862427,
|
| 1003 |
+
"learning_rate": 0.00013199999999999998,
|
| 1004 |
+
"loss": 0.1848,
|
| 1005 |
+
"step": 70000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.56,
|
| 1009 |
+
"grad_norm": 0.703525185585022,
|
| 1010 |
+
"learning_rate": 0.00013079999999999998,
|
| 1011 |
+
"loss": 0.1734,
|
| 1012 |
+
"step": 70500
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.57,
|
| 1016 |
+
"grad_norm": 0.8634682893753052,
|
| 1017 |
+
"learning_rate": 0.00012959999999999998,
|
| 1018 |
+
"loss": 0.1789,
|
| 1019 |
+
"step": 71000
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.57,
|
| 1023 |
+
"grad_norm": 0.5816720724105835,
|
| 1024 |
+
"learning_rate": 0.00012839999999999998,
|
| 1025 |
+
"loss": 0.1772,
|
| 1026 |
+
"step": 71500
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.58,
|
| 1030 |
+
"grad_norm": 1.1784312725067139,
|
| 1031 |
+
"learning_rate": 0.00012719999999999997,
|
| 1032 |
+
"loss": 0.1759,
|
| 1033 |
+
"step": 72000
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.58,
|
| 1037 |
+
"grad_norm": 0.4554961025714874,
|
| 1038 |
+
"learning_rate": 0.00012599999999999997,
|
| 1039 |
+
"loss": 0.184,
|
| 1040 |
+
"step": 72500
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 0.58,
|
| 1044 |
+
"grad_norm": 0.8070880174636841,
|
| 1045 |
+
"learning_rate": 0.00012479999999999997,
|
| 1046 |
+
"loss": 0.1813,
|
| 1047 |
+
"step": 73000
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.59,
|
| 1051 |
+
"grad_norm": 0.8661233186721802,
|
| 1052 |
+
"learning_rate": 0.0001236,
|
| 1053 |
+
"loss": 0.1733,
|
| 1054 |
+
"step": 73500
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 0.59,
|
| 1058 |
+
"grad_norm": 0.788370668888092,
|
| 1059 |
+
"learning_rate": 0.0001224,
|
| 1060 |
+
"loss": 0.1788,
|
| 1061 |
+
"step": 74000
|
| 1062 |
+
},
|
| 1063 |
+
{
|
| 1064 |
+
"epoch": 0.6,
|
| 1065 |
+
"grad_norm": 1.25436270236969,
|
| 1066 |
+
"learning_rate": 0.00012119999999999999,
|
| 1067 |
+
"loss": 0.1808,
|
| 1068 |
+
"step": 74500
|
| 1069 |
+
},
|
| 1070 |
+
{
|
| 1071 |
+
"epoch": 0.6,
|
| 1072 |
+
"grad_norm": 0.562129020690918,
|
| 1073 |
+
"learning_rate": 0.00011999999999999999,
|
| 1074 |
+
"loss": 0.1757,
|
| 1075 |
+
"step": 75000
|
| 1076 |
+
},
|
| 1077 |
+
{
|
| 1078 |
+
"epoch": 0.6,
|
| 1079 |
+
"eval_loss": 0.1267654001712799,
|
| 1080 |
+
"eval_runtime": 198.6188,
|
| 1081 |
+
"eval_samples_per_second": 100.695,
|
| 1082 |
+
"eval_steps_per_second": 25.174,
|
| 1083 |
+
"step": 75000
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.6,
|
| 1087 |
+
"grad_norm": 0.4803348481655121,
|
| 1088 |
+
"learning_rate": 0.0001188,
|
| 1089 |
+
"loss": 0.1827,
|
| 1090 |
+
"step": 75500
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 0.61,
|
| 1094 |
+
"grad_norm": 0.7015312910079956,
|
| 1095 |
+
"learning_rate": 0.0001176,
|
| 1096 |
+
"loss": 0.1731,
|
| 1097 |
+
"step": 76000
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 0.61,
|
| 1101 |
+
"grad_norm": 0.7549095153808594,
|
| 1102 |
+
"learning_rate": 0.0001164,
|
| 1103 |
+
"loss": 0.1815,
|
| 1104 |
+
"step": 76500
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 0.62,
|
| 1108 |
+
"grad_norm": 1.0105984210968018,
|
| 1109 |
+
"learning_rate": 0.0001152,
|
| 1110 |
+
"loss": 0.1695,
|
| 1111 |
+
"step": 77000
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 0.62,
|
| 1115 |
+
"grad_norm": 0.8554935455322266,
|
| 1116 |
+
"learning_rate": 0.00011399999999999999,
|
| 1117 |
+
"loss": 0.1767,
|
| 1118 |
+
"step": 77500
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 0.62,
|
| 1122 |
+
"grad_norm": 0.7114706039428711,
|
| 1123 |
+
"learning_rate": 0.00011279999999999999,
|
| 1124 |
+
"loss": 0.1667,
|
| 1125 |
+
"step": 78000
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.63,
|
| 1129 |
+
"grad_norm": 0.6958938241004944,
|
| 1130 |
+
"learning_rate": 0.00011159999999999999,
|
| 1131 |
+
"loss": 0.1765,
|
| 1132 |
+
"step": 78500
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 0.63,
|
| 1136 |
+
"grad_norm": 0.3407191336154938,
|
| 1137 |
+
"learning_rate": 0.00011039999999999999,
|
| 1138 |
+
"loss": 0.1834,
|
| 1139 |
+
"step": 79000
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 0.64,
|
| 1143 |
+
"grad_norm": 1.1113251447677612,
|
| 1144 |
+
"learning_rate": 0.00010919999999999998,
|
| 1145 |
+
"loss": 0.173,
|
| 1146 |
+
"step": 79500
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 0.64,
|
| 1150 |
+
"grad_norm": 0.9301660060882568,
|
| 1151 |
+
"learning_rate": 0.00010799999999999998,
|
| 1152 |
+
"loss": 0.1731,
|
| 1153 |
+
"step": 80000
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 0.64,
|
| 1157 |
+
"grad_norm": 0.45441198348999023,
|
| 1158 |
+
"learning_rate": 0.00010679999999999998,
|
| 1159 |
+
"loss": 0.1747,
|
| 1160 |
+
"step": 80500
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 0.65,
|
| 1164 |
+
"grad_norm": 0.413922518491745,
|
| 1165 |
+
"learning_rate": 0.00010559999999999998,
|
| 1166 |
+
"loss": 0.1783,
|
| 1167 |
+
"step": 81000
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.65,
|
| 1171 |
+
"grad_norm": 0.6205990314483643,
|
| 1172 |
+
"learning_rate": 0.00010439999999999999,
|
| 1173 |
+
"loss": 0.174,
|
| 1174 |
+
"step": 81500
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 0.66,
|
| 1178 |
+
"grad_norm": 0.4416259527206421,
|
| 1179 |
+
"learning_rate": 0.00010319999999999999,
|
| 1180 |
+
"loss": 0.1773,
|
| 1181 |
+
"step": 82000
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 0.66,
|
| 1185 |
+
"grad_norm": 0.6363853216171265,
|
| 1186 |
+
"learning_rate": 0.000102,
|
| 1187 |
+
"loss": 0.1781,
|
| 1188 |
+
"step": 82500
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 0.66,
|
| 1192 |
+
"grad_norm": 0.5858229398727417,
|
| 1193 |
+
"learning_rate": 0.0001008,
|
| 1194 |
+
"loss": 0.1675,
|
| 1195 |
+
"step": 83000
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 0.67,
|
| 1199 |
+
"grad_norm": 0.49044686555862427,
|
| 1200 |
+
"learning_rate": 9.96e-05,
|
| 1201 |
+
"loss": 0.1672,
|
| 1202 |
+
"step": 83500
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 0.67,
|
| 1206 |
+
"grad_norm": 0.8010206818580627,
|
| 1207 |
+
"learning_rate": 9.839999999999999e-05,
|
| 1208 |
+
"loss": 0.1658,
|
| 1209 |
+
"step": 84000
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.68,
|
| 1213 |
+
"grad_norm": 1.1232587099075317,
|
| 1214 |
+
"learning_rate": 9.719999999999999e-05,
|
| 1215 |
+
"loss": 0.171,
|
| 1216 |
+
"step": 84500
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 0.68,
|
| 1220 |
+
"grad_norm": 0.5122153759002686,
|
| 1221 |
+
"learning_rate": 9.599999999999999e-05,
|
| 1222 |
+
"loss": 0.1768,
|
| 1223 |
+
"step": 85000
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 0.68,
|
| 1227 |
+
"grad_norm": 1.524728775024414,
|
| 1228 |
+
"learning_rate": 9.479999999999999e-05,
|
| 1229 |
+
"loss": 0.1741,
|
| 1230 |
+
"step": 85500
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 0.69,
|
| 1234 |
+
"grad_norm": 0.6309654116630554,
|
| 1235 |
+
"learning_rate": 9.36e-05,
|
| 1236 |
+
"loss": 0.168,
|
| 1237 |
+
"step": 86000
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 0.69,
|
| 1241 |
+
"grad_norm": 0.7848625183105469,
|
| 1242 |
+
"learning_rate": 9.24e-05,
|
| 1243 |
+
"loss": 0.1727,
|
| 1244 |
+
"step": 86500
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 0.7,
|
| 1248 |
+
"grad_norm": 1.2840665578842163,
|
| 1249 |
+
"learning_rate": 9.12e-05,
|
| 1250 |
+
"loss": 0.1681,
|
| 1251 |
+
"step": 87000
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.7,
|
| 1255 |
+
"grad_norm": 0.561613917350769,
|
| 1256 |
+
"learning_rate": 8.999999999999999e-05,
|
| 1257 |
+
"loss": 0.174,
|
| 1258 |
+
"step": 87500
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 0.7,
|
| 1262 |
+
"grad_norm": 0.3210696578025818,
|
| 1263 |
+
"learning_rate": 8.879999999999999e-05,
|
| 1264 |
+
"loss": 0.1665,
|
| 1265 |
+
"step": 88000
|
| 1266 |
+
},
|
| 1267 |
+
{
|
| 1268 |
+
"epoch": 0.71,
|
| 1269 |
+
"grad_norm": 0.6899012327194214,
|
| 1270 |
+
"learning_rate": 8.759999999999999e-05,
|
| 1271 |
+
"loss": 0.1713,
|
| 1272 |
+
"step": 88500
|
| 1273 |
+
},
|
| 1274 |
+
{
|
| 1275 |
+
"epoch": 0.71,
|
| 1276 |
+
"grad_norm": 0.5571711659431458,
|
| 1277 |
+
"learning_rate": 8.639999999999999e-05,
|
| 1278 |
+
"loss": 0.1742,
|
| 1279 |
+
"step": 89000
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 0.72,
|
| 1283 |
+
"grad_norm": 0.3232167065143585,
|
| 1284 |
+
"learning_rate": 8.519999999999998e-05,
|
| 1285 |
+
"loss": 0.1642,
|
| 1286 |
+
"step": 89500
|
| 1287 |
+
},
|
| 1288 |
+
{
|
| 1289 |
+
"epoch": 0.72,
|
| 1290 |
+
"grad_norm": 0.5947475433349609,
|
| 1291 |
+
"learning_rate": 8.4e-05,
|
| 1292 |
+
"loss": 0.1607,
|
| 1293 |
+
"step": 90000
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.72,
|
| 1297 |
+
"grad_norm": 1.0395877361297607,
|
| 1298 |
+
"learning_rate": 8.28e-05,
|
| 1299 |
+
"loss": 0.1668,
|
| 1300 |
+
"step": 90500
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 0.73,
|
| 1304 |
+
"grad_norm": 0.8020333051681519,
|
| 1305 |
+
"learning_rate": 8.16e-05,
|
| 1306 |
+
"loss": 0.1705,
|
| 1307 |
+
"step": 91000
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"epoch": 0.73,
|
| 1311 |
+
"grad_norm": 0.420878142118454,
|
| 1312 |
+
"learning_rate": 8.04e-05,
|
| 1313 |
+
"loss": 0.1495,
|
| 1314 |
+
"step": 91500
|
| 1315 |
+
},
|
| 1316 |
+
{
|
| 1317 |
+
"epoch": 0.74,
|
| 1318 |
+
"grad_norm": 0.2120175063610077,
|
| 1319 |
+
"learning_rate": 7.92e-05,
|
| 1320 |
+
"loss": 0.1684,
|
| 1321 |
+
"step": 92000
|
| 1322 |
+
},
|
| 1323 |
+
{
|
| 1324 |
+
"epoch": 0.74,
|
| 1325 |
+
"grad_norm": 1.321204662322998,
|
| 1326 |
+
"learning_rate": 7.8e-05,
|
| 1327 |
+
"loss": 0.1677,
|
| 1328 |
+
"step": 92500
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 0.74,
|
| 1332 |
+
"grad_norm": 0.5741947889328003,
|
| 1333 |
+
"learning_rate": 7.68e-05,
|
| 1334 |
+
"loss": 0.1643,
|
| 1335 |
+
"step": 93000
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.75,
|
| 1339 |
+
"grad_norm": 0.2746628224849701,
|
| 1340 |
+
"learning_rate": 7.56e-05,
|
| 1341 |
+
"loss": 0.169,
|
| 1342 |
+
"step": 93500
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.75,
|
| 1346 |
+
"grad_norm": 1.5869113206863403,
|
| 1347 |
+
"learning_rate": 7.439999999999999e-05,
|
| 1348 |
+
"loss": 0.158,
|
| 1349 |
+
"step": 94000
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.76,
|
| 1353 |
+
"grad_norm": 0.5085694789886475,
|
| 1354 |
+
"learning_rate": 7.319999999999999e-05,
|
| 1355 |
+
"loss": 0.1766,
|
| 1356 |
+
"step": 94500
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.76,
|
| 1360 |
+
"grad_norm": 0.8071849942207336,
|
| 1361 |
+
"learning_rate": 7.199999999999999e-05,
|
| 1362 |
+
"loss": 0.1623,
|
| 1363 |
+
"step": 95000
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.76,
|
| 1367 |
+
"grad_norm": 0.6275350451469421,
|
| 1368 |
+
"learning_rate": 7.079999999999999e-05,
|
| 1369 |
+
"loss": 0.1624,
|
| 1370 |
+
"step": 95500
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.77,
|
| 1374 |
+
"grad_norm": 0.35898515582084656,
|
| 1375 |
+
"learning_rate": 6.96e-05,
|
| 1376 |
+
"loss": 0.1659,
|
| 1377 |
+
"step": 96000
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.77,
|
| 1381 |
+
"grad_norm": 0.5679383873939514,
|
| 1382 |
+
"learning_rate": 6.84e-05,
|
| 1383 |
+
"loss": 0.1621,
|
| 1384 |
+
"step": 96500
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"epoch": 0.78,
|
| 1388 |
+
"grad_norm": 1.2387058734893799,
|
| 1389 |
+
"learning_rate": 6.72e-05,
|
| 1390 |
+
"loss": 0.1603,
|
| 1391 |
+
"step": 97000
|
| 1392 |
+
},
|
| 1393 |
+
{
|
| 1394 |
+
"epoch": 0.78,
|
| 1395 |
+
"grad_norm": 0.4777892529964447,
|
| 1396 |
+
"learning_rate": 6.599999999999999e-05,
|
| 1397 |
+
"loss": 0.1584,
|
| 1398 |
+
"step": 97500
|
| 1399 |
+
},
|
| 1400 |
+
{
|
| 1401 |
+
"epoch": 0.78,
|
| 1402 |
+
"grad_norm": 0.789397120475769,
|
| 1403 |
+
"learning_rate": 6.479999999999999e-05,
|
| 1404 |
+
"loss": 0.1621,
|
| 1405 |
+
"step": 98000
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 0.79,
|
| 1409 |
+
"grad_norm": 0.8871356248855591,
|
| 1410 |
+
"learning_rate": 6.359999999999999e-05,
|
| 1411 |
+
"loss": 0.1559,
|
| 1412 |
+
"step": 98500
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 0.79,
|
| 1416 |
+
"grad_norm": 1.0920441150665283,
|
| 1417 |
+
"learning_rate": 6.239999999999999e-05,
|
| 1418 |
+
"loss": 0.169,
|
| 1419 |
+
"step": 99000
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.8,
|
| 1423 |
+
"grad_norm": 1.3875184059143066,
|
| 1424 |
+
"learning_rate": 6.12e-05,
|
| 1425 |
+
"loss": 0.1623,
|
| 1426 |
+
"step": 99500
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 0.8,
|
| 1430 |
+
"grad_norm": 1.1163883209228516,
|
| 1431 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 1432 |
+
"loss": 0.1663,
|
| 1433 |
+
"step": 100000
|
| 1434 |
+
},
|
| 1435 |
+
{
|
| 1436 |
+
"epoch": 0.8,
|
| 1437 |
+
"eval_loss": 0.1176806390285492,
|
| 1438 |
+
"eval_runtime": 202.7443,
|
| 1439 |
+
"eval_samples_per_second": 98.646,
|
| 1440 |
+
"eval_steps_per_second": 24.662,
|
| 1441 |
+
"step": 100000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 0.8,
|
| 1445 |
+
"grad_norm": 0.8637445569038391,
|
| 1446 |
+
"learning_rate": 5.88e-05,
|
| 1447 |
+
"loss": 0.1663,
|
| 1448 |
+
"step": 100500
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 0.81,
|
| 1452 |
+
"grad_norm": 3.794600486755371,
|
| 1453 |
+
"learning_rate": 5.76e-05,
|
| 1454 |
+
"loss": 0.1638,
|
| 1455 |
+
"step": 101000
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 0.81,
|
| 1459 |
+
"grad_norm": 0.7344540953636169,
|
| 1460 |
+
"learning_rate": 5.6399999999999995e-05,
|
| 1461 |
+
"loss": 0.1589,
|
| 1462 |
+
"step": 101500
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 0.82,
|
| 1466 |
+
"grad_norm": 0.591451108455658,
|
| 1467 |
+
"learning_rate": 5.519999999999999e-05,
|
| 1468 |
+
"loss": 0.1613,
|
| 1469 |
+
"step": 102000
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 0.82,
|
| 1473 |
+
"grad_norm": 0.9407438635826111,
|
| 1474 |
+
"learning_rate": 5.399999999999999e-05,
|
| 1475 |
+
"loss": 0.1588,
|
| 1476 |
+
"step": 102500
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 0.82,
|
| 1480 |
+
"grad_norm": 0.5834544897079468,
|
| 1481 |
+
"learning_rate": 5.279999999999999e-05,
|
| 1482 |
+
"loss": 0.1708,
|
| 1483 |
+
"step": 103000
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 0.83,
|
| 1487 |
+
"grad_norm": 0.6752551198005676,
|
| 1488 |
+
"learning_rate": 5.1599999999999994e-05,
|
| 1489 |
+
"loss": 0.1548,
|
| 1490 |
+
"step": 103500
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 0.83,
|
| 1494 |
+
"grad_norm": 0.6357858180999756,
|
| 1495 |
+
"learning_rate": 5.04e-05,
|
| 1496 |
+
"loss": 0.1641,
|
| 1497 |
+
"step": 104000
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.84,
|
| 1501 |
+
"grad_norm": 0.6341969966888428,
|
| 1502 |
+
"learning_rate": 4.9199999999999997e-05,
|
| 1503 |
+
"loss": 0.162,
|
| 1504 |
+
"step": 104500
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 0.84,
|
| 1508 |
+
"grad_norm": 0.3042418956756592,
|
| 1509 |
+
"learning_rate": 4.7999999999999994e-05,
|
| 1510 |
+
"loss": 0.1519,
|
| 1511 |
+
"step": 105000
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 0.84,
|
| 1515 |
+
"grad_norm": 1.0411969423294067,
|
| 1516 |
+
"learning_rate": 4.68e-05,
|
| 1517 |
+
"loss": 0.1552,
|
| 1518 |
+
"step": 105500
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 0.85,
|
| 1522 |
+
"grad_norm": 0.1914784461259842,
|
| 1523 |
+
"learning_rate": 4.56e-05,
|
| 1524 |
+
"loss": 0.1614,
|
| 1525 |
+
"step": 106000
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 0.85,
|
| 1529 |
+
"grad_norm": 0.5716798305511475,
|
| 1530 |
+
"learning_rate": 4.4399999999999995e-05,
|
| 1531 |
+
"loss": 0.1639,
|
| 1532 |
+
"step": 106500
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 0.86,
|
| 1536 |
+
"grad_norm": 1.2206032276153564,
|
| 1537 |
+
"learning_rate": 4.319999999999999e-05,
|
| 1538 |
+
"loss": 0.1504,
|
| 1539 |
+
"step": 107000
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.86,
|
| 1543 |
+
"grad_norm": 0.9124048352241516,
|
| 1544 |
+
"learning_rate": 4.2e-05,
|
| 1545 |
+
"loss": 0.1575,
|
| 1546 |
+
"step": 107500
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 0.86,
|
| 1550 |
+
"grad_norm": 0.4684576392173767,
|
| 1551 |
+
"learning_rate": 4.08e-05,
|
| 1552 |
+
"loss": 0.1678,
|
| 1553 |
+
"step": 108000
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 0.87,
|
| 1557 |
+
"grad_norm": 0.4757069945335388,
|
| 1558 |
+
"learning_rate": 3.96e-05,
|
| 1559 |
+
"loss": 0.1609,
|
| 1560 |
+
"step": 108500
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 0.87,
|
| 1564 |
+
"grad_norm": 0.4235193431377411,
|
| 1565 |
+
"learning_rate": 3.84e-05,
|
| 1566 |
+
"loss": 0.1633,
|
| 1567 |
+
"step": 109000
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 0.88,
|
| 1571 |
+
"grad_norm": 0.6009053587913513,
|
| 1572 |
+
"learning_rate": 3.7199999999999996e-05,
|
| 1573 |
+
"loss": 0.1528,
|
| 1574 |
+
"step": 109500
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 0.88,
|
| 1578 |
+
"grad_norm": 0.9195963144302368,
|
| 1579 |
+
"learning_rate": 3.5999999999999994e-05,
|
| 1580 |
+
"loss": 0.1616,
|
| 1581 |
+
"step": 110000
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 0.88,
|
| 1585 |
+
"grad_norm": 0.5454314947128296,
|
| 1586 |
+
"learning_rate": 3.48e-05,
|
| 1587 |
+
"loss": 0.1611,
|
| 1588 |
+
"step": 110500
|
| 1589 |
+
},
|
| 1590 |
+
{
|
| 1591 |
+
"epoch": 0.89,
|
| 1592 |
+
"grad_norm": 0.5214249491691589,
|
| 1593 |
+
"learning_rate": 3.36e-05,
|
| 1594 |
+
"loss": 0.1586,
|
| 1595 |
+
"step": 111000
|
| 1596 |
+
},
|
| 1597 |
+
{
|
| 1598 |
+
"epoch": 0.89,
|
| 1599 |
+
"grad_norm": 1.0026371479034424,
|
| 1600 |
+
"learning_rate": 3.2399999999999995e-05,
|
| 1601 |
+
"loss": 0.1641,
|
| 1602 |
+
"step": 111500
|
| 1603 |
+
},
|
| 1604 |
+
{
|
| 1605 |
+
"epoch": 0.9,
|
| 1606 |
+
"grad_norm": 1.3591657876968384,
|
| 1607 |
+
"learning_rate": 3.119999999999999e-05,
|
| 1608 |
+
"loss": 0.1599,
|
| 1609 |
+
"step": 112000
|
| 1610 |
+
},
|
| 1611 |
+
{
|
| 1612 |
+
"epoch": 0.9,
|
| 1613 |
+
"grad_norm": 0.6785110831260681,
|
| 1614 |
+
"learning_rate": 2.9999999999999997e-05,
|
| 1615 |
+
"loss": 0.1585,
|
| 1616 |
+
"step": 112500
|
| 1617 |
+
},
|
| 1618 |
+
{
|
| 1619 |
+
"epoch": 0.9,
|
| 1620 |
+
"grad_norm": 1.6680885553359985,
|
| 1621 |
+
"learning_rate": 2.88e-05,
|
| 1622 |
+
"loss": 0.1534,
|
| 1623 |
+
"step": 113000
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.91,
|
| 1627 |
+
"grad_norm": 1.4302424192428589,
|
| 1628 |
+
"learning_rate": 2.7599999999999997e-05,
|
| 1629 |
+
"loss": 0.1603,
|
| 1630 |
+
"step": 113500
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 0.91,
|
| 1634 |
+
"grad_norm": 0.9608228206634521,
|
| 1635 |
+
"learning_rate": 2.6399999999999995e-05,
|
| 1636 |
+
"loss": 0.1509,
|
| 1637 |
+
"step": 114000
|
| 1638 |
+
},
|
| 1639 |
+
{
|
| 1640 |
+
"epoch": 0.92,
|
| 1641 |
+
"grad_norm": 0.16929888725280762,
|
| 1642 |
+
"learning_rate": 2.52e-05,
|
| 1643 |
+
"loss": 0.1576,
|
| 1644 |
+
"step": 114500
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"epoch": 0.92,
|
| 1648 |
+
"grad_norm": 0.19129659235477448,
|
| 1649 |
+
"learning_rate": 2.3999999999999997e-05,
|
| 1650 |
+
"loss": 0.1556,
|
| 1651 |
+
"step": 115000
|
| 1652 |
+
},
|
| 1653 |
+
{
|
| 1654 |
+
"epoch": 0.92,
|
| 1655 |
+
"grad_norm": 0.7054457068443298,
|
| 1656 |
+
"learning_rate": 2.28e-05,
|
| 1657 |
+
"loss": 0.1615,
|
| 1658 |
+
"step": 115500
|
| 1659 |
+
},
|
| 1660 |
+
{
|
| 1661 |
+
"epoch": 0.93,
|
| 1662 |
+
"grad_norm": 1.2099674940109253,
|
| 1663 |
+
"learning_rate": 2.1599999999999996e-05,
|
| 1664 |
+
"loss": 0.152,
|
| 1665 |
+
"step": 116000
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.93,
|
| 1669 |
+
"grad_norm": 0.6213043332099915,
|
| 1670 |
+
"learning_rate": 2.04e-05,
|
| 1671 |
+
"loss": 0.159,
|
| 1672 |
+
"step": 116500
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 0.94,
|
| 1676 |
+
"grad_norm": 0.5257019996643066,
|
| 1677 |
+
"learning_rate": 1.92e-05,
|
| 1678 |
+
"loss": 0.1643,
|
| 1679 |
+
"step": 117000
|
| 1680 |
+
},
|
| 1681 |
+
{
|
| 1682 |
+
"epoch": 0.94,
|
| 1683 |
+
"grad_norm": 0.7175723314285278,
|
| 1684 |
+
"learning_rate": 1.7999999999999997e-05,
|
| 1685 |
+
"loss": 0.1561,
|
| 1686 |
+
"step": 117500
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 0.94,
|
| 1690 |
+
"grad_norm": 0.37755417823791504,
|
| 1691 |
+
"learning_rate": 1.68e-05,
|
| 1692 |
+
"loss": 0.1594,
|
| 1693 |
+
"step": 118000
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.95,
|
| 1697 |
+
"grad_norm": 0.6101952195167542,
|
| 1698 |
+
"learning_rate": 1.5599999999999996e-05,
|
| 1699 |
+
"loss": 0.1574,
|
| 1700 |
+
"step": 118500
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.95,
|
| 1704 |
+
"grad_norm": 1.0712097883224487,
|
| 1705 |
+
"learning_rate": 1.44e-05,
|
| 1706 |
+
"loss": 0.1468,
|
| 1707 |
+
"step": 119000
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.96,
|
| 1711 |
+
"grad_norm": 0.5005315542221069,
|
| 1712 |
+
"learning_rate": 1.3199999999999997e-05,
|
| 1713 |
+
"loss": 0.1586,
|
| 1714 |
+
"step": 119500
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.96,
|
| 1718 |
+
"grad_norm": 0.7147447466850281,
|
| 1719 |
+
"learning_rate": 1.1999999999999999e-05,
|
| 1720 |
+
"loss": 0.1553,
|
| 1721 |
+
"step": 120000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.96,
|
| 1725 |
+
"grad_norm": 1.2048006057739258,
|
| 1726 |
+
"learning_rate": 1.0799999999999998e-05,
|
| 1727 |
+
"loss": 0.1603,
|
| 1728 |
+
"step": 120500
|
| 1729 |
+
},
|
| 1730 |
+
{
|
| 1731 |
+
"epoch": 0.97,
|
| 1732 |
+
"grad_norm": 0.6054685711860657,
|
| 1733 |
+
"learning_rate": 9.6e-06,
|
| 1734 |
+
"loss": 0.161,
|
| 1735 |
+
"step": 121000
|
| 1736 |
+
},
|
| 1737 |
+
{
|
| 1738 |
+
"epoch": 0.97,
|
| 1739 |
+
"grad_norm": 0.4145253300666809,
|
| 1740 |
+
"learning_rate": 8.4e-06,
|
| 1741 |
+
"loss": 0.1549,
|
| 1742 |
+
"step": 121500
|
| 1743 |
+
},
|
| 1744 |
+
{
|
| 1745 |
+
"epoch": 0.98,
|
| 1746 |
+
"grad_norm": 0.2331937849521637,
|
| 1747 |
+
"learning_rate": 7.2e-06,
|
| 1748 |
+
"loss": 0.1584,
|
| 1749 |
+
"step": 122000
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.98,
|
| 1753 |
+
"grad_norm": 0.44909703731536865,
|
| 1754 |
+
"learning_rate": 5.999999999999999e-06,
|
| 1755 |
+
"loss": 0.161,
|
| 1756 |
+
"step": 122500
|
| 1757 |
+
},
|
| 1758 |
+
{
|
| 1759 |
+
"epoch": 0.98,
|
| 1760 |
+
"grad_norm": 6.39445686340332,
|
| 1761 |
+
"learning_rate": 4.8e-06,
|
| 1762 |
+
"loss": 0.159,
|
| 1763 |
+
"step": 123000
|
| 1764 |
+
},
|
| 1765 |
+
{
|
| 1766 |
+
"epoch": 0.99,
|
| 1767 |
+
"grad_norm": 0.5847737193107605,
|
| 1768 |
+
"learning_rate": 3.6e-06,
|
| 1769 |
+
"loss": 0.1469,
|
| 1770 |
+
"step": 123500
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 0.99,
|
| 1774 |
+
"grad_norm": 0.45996806025505066,
|
| 1775 |
+
"learning_rate": 2.4e-06,
|
| 1776 |
+
"loss": 0.1606,
|
| 1777 |
+
"step": 124000
|
| 1778 |
+
},
|
| 1779 |
+
{
|
| 1780 |
+
"epoch": 1.0,
|
| 1781 |
+
"grad_norm": 0.5662907361984253,
|
| 1782 |
+
"learning_rate": 1.2e-06,
|
| 1783 |
+
"loss": 0.1511,
|
| 1784 |
+
"step": 124500
|
| 1785 |
+
},
|
| 1786 |
+
{
|
| 1787 |
+
"epoch": 1.0,
|
| 1788 |
+
"grad_norm": 0.9263651967048645,
|
| 1789 |
+
"learning_rate": 0.0,
|
| 1790 |
+
"loss": 0.1543,
|
| 1791 |
+
"step": 125000
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 1.0,
|
| 1795 |
+
"eval_loss": 0.11344572901725769,
|
| 1796 |
+
"eval_runtime": 200.0914,
|
| 1797 |
+
"eval_samples_per_second": 99.954,
|
| 1798 |
+
"eval_steps_per_second": 24.989,
|
| 1799 |
+
"step": 125000
|
| 1800 |
+
}
|
| 1801 |
+
],
|
| 1802 |
+
"logging_steps": 500,
|
| 1803 |
+
"max_steps": 125000,
|
| 1804 |
+
"num_input_tokens_seen": 0,
|
| 1805 |
+
"num_train_epochs": 1,
|
| 1806 |
+
"save_steps": 62500,
|
| 1807 |
+
"total_flos": 6.527143521828864e+16,
|
| 1808 |
+
"train_batch_size": 4,
|
| 1809 |
+
"trial_name": null,
|
| 1810 |
+
"trial_params": null
|
| 1811 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3df1b02ac02f1247cd1228422049ef534a76ce62617761edf5a179754c03590
|
| 3 |
+
size 5048
|