Upload checkpoint folder via API
Browse files- checkpoint-13050/added_tokens.json +104 -0
- checkpoint-13050/config.json +32 -0
- checkpoint-13050/generation_config.json +9 -0
- checkpoint-13050/model.safetensors +3 -0
- checkpoint-13050/optimizer.pt +3 -0
- checkpoint-13050/rng_state.pth +3 -0
- checkpoint-13050/scheduler.pt +3 -0
- checkpoint-13050/special_tokens_map.json +127 -0
- checkpoint-13050/spiece.model +3 -0
- checkpoint-13050/tokenizer_config.json +959 -0
- checkpoint-13050/trainer_state.json +1024 -0
- checkpoint-13050/training_args.bin +3 -0
checkpoint-13050/added_tokens.json
ADDED
|
@@ -0,0 +1,104 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<BH>": 32101,
|
| 3 |
+
"<BN>": 32100,
|
| 4 |
+
"<extra_id_0>": 32099,
|
| 5 |
+
"<extra_id_10>": 32089,
|
| 6 |
+
"<extra_id_11>": 32088,
|
| 7 |
+
"<extra_id_12>": 32087,
|
| 8 |
+
"<extra_id_13>": 32086,
|
| 9 |
+
"<extra_id_14>": 32085,
|
| 10 |
+
"<extra_id_15>": 32084,
|
| 11 |
+
"<extra_id_16>": 32083,
|
| 12 |
+
"<extra_id_17>": 32082,
|
| 13 |
+
"<extra_id_18>": 32081,
|
| 14 |
+
"<extra_id_19>": 32080,
|
| 15 |
+
"<extra_id_1>": 32098,
|
| 16 |
+
"<extra_id_20>": 32079,
|
| 17 |
+
"<extra_id_21>": 32078,
|
| 18 |
+
"<extra_id_22>": 32077,
|
| 19 |
+
"<extra_id_23>": 32076,
|
| 20 |
+
"<extra_id_24>": 32075,
|
| 21 |
+
"<extra_id_25>": 32074,
|
| 22 |
+
"<extra_id_26>": 32073,
|
| 23 |
+
"<extra_id_27>": 32072,
|
| 24 |
+
"<extra_id_28>": 32071,
|
| 25 |
+
"<extra_id_29>": 32070,
|
| 26 |
+
"<extra_id_2>": 32097,
|
| 27 |
+
"<extra_id_30>": 32069,
|
| 28 |
+
"<extra_id_31>": 32068,
|
| 29 |
+
"<extra_id_32>": 32067,
|
| 30 |
+
"<extra_id_33>": 32066,
|
| 31 |
+
"<extra_id_34>": 32065,
|
| 32 |
+
"<extra_id_35>": 32064,
|
| 33 |
+
"<extra_id_36>": 32063,
|
| 34 |
+
"<extra_id_37>": 32062,
|
| 35 |
+
"<extra_id_38>": 32061,
|
| 36 |
+
"<extra_id_39>": 32060,
|
| 37 |
+
"<extra_id_3>": 32096,
|
| 38 |
+
"<extra_id_40>": 32059,
|
| 39 |
+
"<extra_id_41>": 32058,
|
| 40 |
+
"<extra_id_42>": 32057,
|
| 41 |
+
"<extra_id_43>": 32056,
|
| 42 |
+
"<extra_id_44>": 32055,
|
| 43 |
+
"<extra_id_45>": 32054,
|
| 44 |
+
"<extra_id_46>": 32053,
|
| 45 |
+
"<extra_id_47>": 32052,
|
| 46 |
+
"<extra_id_48>": 32051,
|
| 47 |
+
"<extra_id_49>": 32050,
|
| 48 |
+
"<extra_id_4>": 32095,
|
| 49 |
+
"<extra_id_50>": 32049,
|
| 50 |
+
"<extra_id_51>": 32048,
|
| 51 |
+
"<extra_id_52>": 32047,
|
| 52 |
+
"<extra_id_53>": 32046,
|
| 53 |
+
"<extra_id_54>": 32045,
|
| 54 |
+
"<extra_id_55>": 32044,
|
| 55 |
+
"<extra_id_56>": 32043,
|
| 56 |
+
"<extra_id_57>": 32042,
|
| 57 |
+
"<extra_id_58>": 32041,
|
| 58 |
+
"<extra_id_59>": 32040,
|
| 59 |
+
"<extra_id_5>": 32094,
|
| 60 |
+
"<extra_id_60>": 32039,
|
| 61 |
+
"<extra_id_61>": 32038,
|
| 62 |
+
"<extra_id_62>": 32037,
|
| 63 |
+
"<extra_id_63>": 32036,
|
| 64 |
+
"<extra_id_64>": 32035,
|
| 65 |
+
"<extra_id_65>": 32034,
|
| 66 |
+
"<extra_id_66>": 32033,
|
| 67 |
+
"<extra_id_67>": 32032,
|
| 68 |
+
"<extra_id_68>": 32031,
|
| 69 |
+
"<extra_id_69>": 32030,
|
| 70 |
+
"<extra_id_6>": 32093,
|
| 71 |
+
"<extra_id_70>": 32029,
|
| 72 |
+
"<extra_id_71>": 32028,
|
| 73 |
+
"<extra_id_72>": 32027,
|
| 74 |
+
"<extra_id_73>": 32026,
|
| 75 |
+
"<extra_id_74>": 32025,
|
| 76 |
+
"<extra_id_75>": 32024,
|
| 77 |
+
"<extra_id_76>": 32023,
|
| 78 |
+
"<extra_id_77>": 32022,
|
| 79 |
+
"<extra_id_78>": 32021,
|
| 80 |
+
"<extra_id_79>": 32020,
|
| 81 |
+
"<extra_id_7>": 32092,
|
| 82 |
+
"<extra_id_80>": 32019,
|
| 83 |
+
"<extra_id_81>": 32018,
|
| 84 |
+
"<extra_id_82>": 32017,
|
| 85 |
+
"<extra_id_83>": 32016,
|
| 86 |
+
"<extra_id_84>": 32015,
|
| 87 |
+
"<extra_id_85>": 32014,
|
| 88 |
+
"<extra_id_86>": 32013,
|
| 89 |
+
"<extra_id_87>": 32012,
|
| 90 |
+
"<extra_id_88>": 32011,
|
| 91 |
+
"<extra_id_89>": 32010,
|
| 92 |
+
"<extra_id_8>": 32091,
|
| 93 |
+
"<extra_id_90>": 32009,
|
| 94 |
+
"<extra_id_91>": 32008,
|
| 95 |
+
"<extra_id_92>": 32007,
|
| 96 |
+
"<extra_id_93>": 32006,
|
| 97 |
+
"<extra_id_94>": 32005,
|
| 98 |
+
"<extra_id_95>": 32004,
|
| 99 |
+
"<extra_id_96>": 32003,
|
| 100 |
+
"<extra_id_97>": 32002,
|
| 101 |
+
"<extra_id_98>": 32001,
|
| 102 |
+
"<extra_id_99>": 32000,
|
| 103 |
+
"<extra_id_9>": 32090
|
| 104 |
+
}
|
checkpoint-13050/config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"T5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"classifier_dropout": 0.0,
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "gelu_new",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"dtype": "float32",
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "gated-gelu",
|
| 15 |
+
"gradient_checkpointing": false,
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": true,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"model_type": "t5",
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"tie_word_embeddings": false,
|
| 29 |
+
"transformers_version": "4.57.1",
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 32102
|
| 32 |
+
}
|
checkpoint-13050/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
1
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 0,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
+
}
|
checkpoint-13050/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:291fc2f3e16d13535aef0e5857f8b8ec1a8d614e56a8f5d606113b4a4a374730
|
| 3 |
+
size 990185320
|
checkpoint-13050/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d1e5028d0fbb6284b8ffabcbca2defbea234f1fbf114f91360a7357eabe56b40
|
| 3 |
+
size 1980545291
|
checkpoint-13050/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b093150b09d392f3fd23e6def05a2ad4ce45b25f2b1fb6925cf93a70dbcfee67
|
| 3 |
+
size 14645
|
checkpoint-13050/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0fe1e1e872dbf47922e600b1580d90407a1b849b891ace6ebcf1d27bc1d9b435
|
| 3 |
+
size 1465
|
checkpoint-13050/special_tokens_map.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<BN>",
|
| 4 |
+
"<BH>",
|
| 5 |
+
"<extra_id_0>",
|
| 6 |
+
"<extra_id_1>",
|
| 7 |
+
"<extra_id_2>",
|
| 8 |
+
"<extra_id_3>",
|
| 9 |
+
"<extra_id_4>",
|
| 10 |
+
"<extra_id_5>",
|
| 11 |
+
"<extra_id_6>",
|
| 12 |
+
"<extra_id_7>",
|
| 13 |
+
"<extra_id_8>",
|
| 14 |
+
"<extra_id_9>",
|
| 15 |
+
"<extra_id_10>",
|
| 16 |
+
"<extra_id_11>",
|
| 17 |
+
"<extra_id_12>",
|
| 18 |
+
"<extra_id_13>",
|
| 19 |
+
"<extra_id_14>",
|
| 20 |
+
"<extra_id_15>",
|
| 21 |
+
"<extra_id_16>",
|
| 22 |
+
"<extra_id_17>",
|
| 23 |
+
"<extra_id_18>",
|
| 24 |
+
"<extra_id_19>",
|
| 25 |
+
"<extra_id_20>",
|
| 26 |
+
"<extra_id_21>",
|
| 27 |
+
"<extra_id_22>",
|
| 28 |
+
"<extra_id_23>",
|
| 29 |
+
"<extra_id_24>",
|
| 30 |
+
"<extra_id_25>",
|
| 31 |
+
"<extra_id_26>",
|
| 32 |
+
"<extra_id_27>",
|
| 33 |
+
"<extra_id_28>",
|
| 34 |
+
"<extra_id_29>",
|
| 35 |
+
"<extra_id_30>",
|
| 36 |
+
"<extra_id_31>",
|
| 37 |
+
"<extra_id_32>",
|
| 38 |
+
"<extra_id_33>",
|
| 39 |
+
"<extra_id_34>",
|
| 40 |
+
"<extra_id_35>",
|
| 41 |
+
"<extra_id_36>",
|
| 42 |
+
"<extra_id_37>",
|
| 43 |
+
"<extra_id_38>",
|
| 44 |
+
"<extra_id_39>",
|
| 45 |
+
"<extra_id_40>",
|
| 46 |
+
"<extra_id_41>",
|
| 47 |
+
"<extra_id_42>",
|
| 48 |
+
"<extra_id_43>",
|
| 49 |
+
"<extra_id_44>",
|
| 50 |
+
"<extra_id_45>",
|
| 51 |
+
"<extra_id_46>",
|
| 52 |
+
"<extra_id_47>",
|
| 53 |
+
"<extra_id_48>",
|
| 54 |
+
"<extra_id_49>",
|
| 55 |
+
"<extra_id_50>",
|
| 56 |
+
"<extra_id_51>",
|
| 57 |
+
"<extra_id_52>",
|
| 58 |
+
"<extra_id_53>",
|
| 59 |
+
"<extra_id_54>",
|
| 60 |
+
"<extra_id_55>",
|
| 61 |
+
"<extra_id_56>",
|
| 62 |
+
"<extra_id_57>",
|
| 63 |
+
"<extra_id_58>",
|
| 64 |
+
"<extra_id_59>",
|
| 65 |
+
"<extra_id_60>",
|
| 66 |
+
"<extra_id_61>",
|
| 67 |
+
"<extra_id_62>",
|
| 68 |
+
"<extra_id_63>",
|
| 69 |
+
"<extra_id_64>",
|
| 70 |
+
"<extra_id_65>",
|
| 71 |
+
"<extra_id_66>",
|
| 72 |
+
"<extra_id_67>",
|
| 73 |
+
"<extra_id_68>",
|
| 74 |
+
"<extra_id_69>",
|
| 75 |
+
"<extra_id_70>",
|
| 76 |
+
"<extra_id_71>",
|
| 77 |
+
"<extra_id_72>",
|
| 78 |
+
"<extra_id_73>",
|
| 79 |
+
"<extra_id_74>",
|
| 80 |
+
"<extra_id_75>",
|
| 81 |
+
"<extra_id_76>",
|
| 82 |
+
"<extra_id_77>",
|
| 83 |
+
"<extra_id_78>",
|
| 84 |
+
"<extra_id_79>",
|
| 85 |
+
"<extra_id_80>",
|
| 86 |
+
"<extra_id_81>",
|
| 87 |
+
"<extra_id_82>",
|
| 88 |
+
"<extra_id_83>",
|
| 89 |
+
"<extra_id_84>",
|
| 90 |
+
"<extra_id_85>",
|
| 91 |
+
"<extra_id_86>",
|
| 92 |
+
"<extra_id_87>",
|
| 93 |
+
"<extra_id_88>",
|
| 94 |
+
"<extra_id_89>",
|
| 95 |
+
"<extra_id_90>",
|
| 96 |
+
"<extra_id_91>",
|
| 97 |
+
"<extra_id_92>",
|
| 98 |
+
"<extra_id_93>",
|
| 99 |
+
"<extra_id_94>",
|
| 100 |
+
"<extra_id_95>",
|
| 101 |
+
"<extra_id_96>",
|
| 102 |
+
"<extra_id_97>",
|
| 103 |
+
"<extra_id_98>",
|
| 104 |
+
"<extra_id_99>"
|
| 105 |
+
],
|
| 106 |
+
"eos_token": {
|
| 107 |
+
"content": "</s>",
|
| 108 |
+
"lstrip": false,
|
| 109 |
+
"normalized": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"single_word": false
|
| 112 |
+
},
|
| 113 |
+
"pad_token": {
|
| 114 |
+
"content": "<pad>",
|
| 115 |
+
"lstrip": false,
|
| 116 |
+
"normalized": false,
|
| 117 |
+
"rstrip": false,
|
| 118 |
+
"single_word": false
|
| 119 |
+
},
|
| 120 |
+
"unk_token": {
|
| 121 |
+
"content": "<unk>",
|
| 122 |
+
"lstrip": false,
|
| 123 |
+
"normalized": false,
|
| 124 |
+
"rstrip": false,
|
| 125 |
+
"single_word": false
|
| 126 |
+
}
|
| 127 |
+
}
|
checkpoint-13050/spiece.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dcab96935a2a51b1461c84e44c952ea8a3640c8bc3e2c6ae7a21d855454ae27
|
| 3 |
+
size 1111492
|
checkpoint-13050/tokenizer_config.json
ADDED
|
@@ -0,0 +1,959 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": false,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "<unk>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": false,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"32000": {
|
| 29 |
+
"content": "<extra_id_99>",
|
| 30 |
+
"lstrip": true,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": true,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"32001": {
|
| 37 |
+
"content": "<extra_id_98>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": true,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"32002": {
|
| 45 |
+
"content": "<extra_id_97>",
|
| 46 |
+
"lstrip": true,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": true,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"32003": {
|
| 53 |
+
"content": "<extra_id_96>",
|
| 54 |
+
"lstrip": true,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": true,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"32004": {
|
| 61 |
+
"content": "<extra_id_95>",
|
| 62 |
+
"lstrip": true,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": true,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"32005": {
|
| 69 |
+
"content": "<extra_id_94>",
|
| 70 |
+
"lstrip": true,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": true,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"32006": {
|
| 77 |
+
"content": "<extra_id_93>",
|
| 78 |
+
"lstrip": true,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": true,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"32007": {
|
| 85 |
+
"content": "<extra_id_92>",
|
| 86 |
+
"lstrip": true,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": true,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"32008": {
|
| 93 |
+
"content": "<extra_id_91>",
|
| 94 |
+
"lstrip": true,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": true,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"32009": {
|
| 101 |
+
"content": "<extra_id_90>",
|
| 102 |
+
"lstrip": true,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": true,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"32010": {
|
| 109 |
+
"content": "<extra_id_89>",
|
| 110 |
+
"lstrip": true,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": true,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"32011": {
|
| 117 |
+
"content": "<extra_id_88>",
|
| 118 |
+
"lstrip": true,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": true,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"32012": {
|
| 125 |
+
"content": "<extra_id_87>",
|
| 126 |
+
"lstrip": true,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": true,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"32013": {
|
| 133 |
+
"content": "<extra_id_86>",
|
| 134 |
+
"lstrip": true,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": true,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"32014": {
|
| 141 |
+
"content": "<extra_id_85>",
|
| 142 |
+
"lstrip": true,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": true,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"32015": {
|
| 149 |
+
"content": "<extra_id_84>",
|
| 150 |
+
"lstrip": true,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": true,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"32016": {
|
| 157 |
+
"content": "<extra_id_83>",
|
| 158 |
+
"lstrip": true,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": true,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"32017": {
|
| 165 |
+
"content": "<extra_id_82>",
|
| 166 |
+
"lstrip": true,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": true,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"32018": {
|
| 173 |
+
"content": "<extra_id_81>",
|
| 174 |
+
"lstrip": true,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": true,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"32019": {
|
| 181 |
+
"content": "<extra_id_80>",
|
| 182 |
+
"lstrip": true,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": true,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"32020": {
|
| 189 |
+
"content": "<extra_id_79>",
|
| 190 |
+
"lstrip": true,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": true,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"32021": {
|
| 197 |
+
"content": "<extra_id_78>",
|
| 198 |
+
"lstrip": true,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": true,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"32022": {
|
| 205 |
+
"content": "<extra_id_77>",
|
| 206 |
+
"lstrip": true,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": true,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"32023": {
|
| 213 |
+
"content": "<extra_id_76>",
|
| 214 |
+
"lstrip": true,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": true,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"32024": {
|
| 221 |
+
"content": "<extra_id_75>",
|
| 222 |
+
"lstrip": true,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": true,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"32025": {
|
| 229 |
+
"content": "<extra_id_74>",
|
| 230 |
+
"lstrip": true,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": true,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"32026": {
|
| 237 |
+
"content": "<extra_id_73>",
|
| 238 |
+
"lstrip": true,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": true,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"32027": {
|
| 245 |
+
"content": "<extra_id_72>",
|
| 246 |
+
"lstrip": true,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": true,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"32028": {
|
| 253 |
+
"content": "<extra_id_71>",
|
| 254 |
+
"lstrip": true,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": true,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32029": {
|
| 261 |
+
"content": "<extra_id_70>",
|
| 262 |
+
"lstrip": true,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": true,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"32030": {
|
| 269 |
+
"content": "<extra_id_69>",
|
| 270 |
+
"lstrip": true,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": true,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"32031": {
|
| 277 |
+
"content": "<extra_id_68>",
|
| 278 |
+
"lstrip": true,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": true,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"32032": {
|
| 285 |
+
"content": "<extra_id_67>",
|
| 286 |
+
"lstrip": true,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": true,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"32033": {
|
| 293 |
+
"content": "<extra_id_66>",
|
| 294 |
+
"lstrip": true,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": true,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"32034": {
|
| 301 |
+
"content": "<extra_id_65>",
|
| 302 |
+
"lstrip": true,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": true,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"32035": {
|
| 309 |
+
"content": "<extra_id_64>",
|
| 310 |
+
"lstrip": true,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": true,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"32036": {
|
| 317 |
+
"content": "<extra_id_63>",
|
| 318 |
+
"lstrip": true,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": true,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"32037": {
|
| 325 |
+
"content": "<extra_id_62>",
|
| 326 |
+
"lstrip": true,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": true,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"32038": {
|
| 333 |
+
"content": "<extra_id_61>",
|
| 334 |
+
"lstrip": true,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": true,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"32039": {
|
| 341 |
+
"content": "<extra_id_60>",
|
| 342 |
+
"lstrip": true,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": true,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"32040": {
|
| 349 |
+
"content": "<extra_id_59>",
|
| 350 |
+
"lstrip": true,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": true,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"32041": {
|
| 357 |
+
"content": "<extra_id_58>",
|
| 358 |
+
"lstrip": true,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": true,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"32042": {
|
| 365 |
+
"content": "<extra_id_57>",
|
| 366 |
+
"lstrip": true,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": true,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"32043": {
|
| 373 |
+
"content": "<extra_id_56>",
|
| 374 |
+
"lstrip": true,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": true,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"32044": {
|
| 381 |
+
"content": "<extra_id_55>",
|
| 382 |
+
"lstrip": true,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": true,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"32045": {
|
| 389 |
+
"content": "<extra_id_54>",
|
| 390 |
+
"lstrip": true,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": true,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"32046": {
|
| 397 |
+
"content": "<extra_id_53>",
|
| 398 |
+
"lstrip": true,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": true,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"32047": {
|
| 405 |
+
"content": "<extra_id_52>",
|
| 406 |
+
"lstrip": true,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": true,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"32048": {
|
| 413 |
+
"content": "<extra_id_51>",
|
| 414 |
+
"lstrip": true,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": true,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"32049": {
|
| 421 |
+
"content": "<extra_id_50>",
|
| 422 |
+
"lstrip": true,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": true,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"32050": {
|
| 429 |
+
"content": "<extra_id_49>",
|
| 430 |
+
"lstrip": true,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": true,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"32051": {
|
| 437 |
+
"content": "<extra_id_48>",
|
| 438 |
+
"lstrip": true,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": true,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"32052": {
|
| 445 |
+
"content": "<extra_id_47>",
|
| 446 |
+
"lstrip": true,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": true,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"32053": {
|
| 453 |
+
"content": "<extra_id_46>",
|
| 454 |
+
"lstrip": true,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": true,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"32054": {
|
| 461 |
+
"content": "<extra_id_45>",
|
| 462 |
+
"lstrip": true,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": true,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"32055": {
|
| 469 |
+
"content": "<extra_id_44>",
|
| 470 |
+
"lstrip": true,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": true,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"32056": {
|
| 477 |
+
"content": "<extra_id_43>",
|
| 478 |
+
"lstrip": true,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": true,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"32057": {
|
| 485 |
+
"content": "<extra_id_42>",
|
| 486 |
+
"lstrip": true,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": true,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"32058": {
|
| 493 |
+
"content": "<extra_id_41>",
|
| 494 |
+
"lstrip": true,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": true,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"32059": {
|
| 501 |
+
"content": "<extra_id_40>",
|
| 502 |
+
"lstrip": true,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": true,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"32060": {
|
| 509 |
+
"content": "<extra_id_39>",
|
| 510 |
+
"lstrip": true,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": true,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"32061": {
|
| 517 |
+
"content": "<extra_id_38>",
|
| 518 |
+
"lstrip": true,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": true,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"32062": {
|
| 525 |
+
"content": "<extra_id_37>",
|
| 526 |
+
"lstrip": true,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": true,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"32063": {
|
| 533 |
+
"content": "<extra_id_36>",
|
| 534 |
+
"lstrip": true,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": true,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"32064": {
|
| 541 |
+
"content": "<extra_id_35>",
|
| 542 |
+
"lstrip": true,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": true,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"32065": {
|
| 549 |
+
"content": "<extra_id_34>",
|
| 550 |
+
"lstrip": true,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": true,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"32066": {
|
| 557 |
+
"content": "<extra_id_33>",
|
| 558 |
+
"lstrip": true,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": true,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"32067": {
|
| 565 |
+
"content": "<extra_id_32>",
|
| 566 |
+
"lstrip": true,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": true,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"32068": {
|
| 573 |
+
"content": "<extra_id_31>",
|
| 574 |
+
"lstrip": true,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": true,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"32069": {
|
| 581 |
+
"content": "<extra_id_30>",
|
| 582 |
+
"lstrip": true,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": true,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"32070": {
|
| 589 |
+
"content": "<extra_id_29>",
|
| 590 |
+
"lstrip": true,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": true,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"32071": {
|
| 597 |
+
"content": "<extra_id_28>",
|
| 598 |
+
"lstrip": true,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": true,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"32072": {
|
| 605 |
+
"content": "<extra_id_27>",
|
| 606 |
+
"lstrip": true,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": true,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"32073": {
|
| 613 |
+
"content": "<extra_id_26>",
|
| 614 |
+
"lstrip": true,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": true,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"32074": {
|
| 621 |
+
"content": "<extra_id_25>",
|
| 622 |
+
"lstrip": true,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": true,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"32075": {
|
| 629 |
+
"content": "<extra_id_24>",
|
| 630 |
+
"lstrip": true,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": true,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"32076": {
|
| 637 |
+
"content": "<extra_id_23>",
|
| 638 |
+
"lstrip": true,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": true,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"32077": {
|
| 645 |
+
"content": "<extra_id_22>",
|
| 646 |
+
"lstrip": true,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": true,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"32078": {
|
| 653 |
+
"content": "<extra_id_21>",
|
| 654 |
+
"lstrip": true,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": true,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"32079": {
|
| 661 |
+
"content": "<extra_id_20>",
|
| 662 |
+
"lstrip": true,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": true,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"32080": {
|
| 669 |
+
"content": "<extra_id_19>",
|
| 670 |
+
"lstrip": true,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": true,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"32081": {
|
| 677 |
+
"content": "<extra_id_18>",
|
| 678 |
+
"lstrip": true,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": true,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"32082": {
|
| 685 |
+
"content": "<extra_id_17>",
|
| 686 |
+
"lstrip": true,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": true,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"32083": {
|
| 693 |
+
"content": "<extra_id_16>",
|
| 694 |
+
"lstrip": true,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": true,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"32084": {
|
| 701 |
+
"content": "<extra_id_15>",
|
| 702 |
+
"lstrip": true,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": true,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"32085": {
|
| 709 |
+
"content": "<extra_id_14>",
|
| 710 |
+
"lstrip": true,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": true,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"32086": {
|
| 717 |
+
"content": "<extra_id_13>",
|
| 718 |
+
"lstrip": true,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": true,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"32087": {
|
| 725 |
+
"content": "<extra_id_12>",
|
| 726 |
+
"lstrip": true,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": true,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"32088": {
|
| 733 |
+
"content": "<extra_id_11>",
|
| 734 |
+
"lstrip": true,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": true,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"32089": {
|
| 741 |
+
"content": "<extra_id_10>",
|
| 742 |
+
"lstrip": true,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": true,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"32090": {
|
| 749 |
+
"content": "<extra_id_9>",
|
| 750 |
+
"lstrip": true,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": true,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"32091": {
|
| 757 |
+
"content": "<extra_id_8>",
|
| 758 |
+
"lstrip": true,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": true,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"32092": {
|
| 765 |
+
"content": "<extra_id_7>",
|
| 766 |
+
"lstrip": true,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": true,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"32093": {
|
| 773 |
+
"content": "<extra_id_6>",
|
| 774 |
+
"lstrip": true,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": true,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"32094": {
|
| 781 |
+
"content": "<extra_id_5>",
|
| 782 |
+
"lstrip": true,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": true,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"32095": {
|
| 789 |
+
"content": "<extra_id_4>",
|
| 790 |
+
"lstrip": true,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": true,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"32096": {
|
| 797 |
+
"content": "<extra_id_3>",
|
| 798 |
+
"lstrip": true,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": true,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"32097": {
|
| 805 |
+
"content": "<extra_id_2>",
|
| 806 |
+
"lstrip": true,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": true,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"32098": {
|
| 813 |
+
"content": "<extra_id_1>",
|
| 814 |
+
"lstrip": true,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": true,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"32099": {
|
| 821 |
+
"content": "<extra_id_0>",
|
| 822 |
+
"lstrip": true,
|
| 823 |
+
"normalized": false,
|
| 824 |
+
"rstrip": true,
|
| 825 |
+
"single_word": false,
|
| 826 |
+
"special": true
|
| 827 |
+
},
|
| 828 |
+
"32100": {
|
| 829 |
+
"content": "<BN>",
|
| 830 |
+
"lstrip": false,
|
| 831 |
+
"normalized": false,
|
| 832 |
+
"rstrip": false,
|
| 833 |
+
"single_word": false,
|
| 834 |
+
"special": true
|
| 835 |
+
},
|
| 836 |
+
"32101": {
|
| 837 |
+
"content": "<BH>",
|
| 838 |
+
"lstrip": false,
|
| 839 |
+
"normalized": false,
|
| 840 |
+
"rstrip": false,
|
| 841 |
+
"single_word": false,
|
| 842 |
+
"special": true
|
| 843 |
+
}
|
| 844 |
+
},
|
| 845 |
+
"additional_special_tokens": [
|
| 846 |
+
"<BN>",
|
| 847 |
+
"<BH>",
|
| 848 |
+
"<extra_id_0>",
|
| 849 |
+
"<extra_id_1>",
|
| 850 |
+
"<extra_id_2>",
|
| 851 |
+
"<extra_id_3>",
|
| 852 |
+
"<extra_id_4>",
|
| 853 |
+
"<extra_id_5>",
|
| 854 |
+
"<extra_id_6>",
|
| 855 |
+
"<extra_id_7>",
|
| 856 |
+
"<extra_id_8>",
|
| 857 |
+
"<extra_id_9>",
|
| 858 |
+
"<extra_id_10>",
|
| 859 |
+
"<extra_id_11>",
|
| 860 |
+
"<extra_id_12>",
|
| 861 |
+
"<extra_id_13>",
|
| 862 |
+
"<extra_id_14>",
|
| 863 |
+
"<extra_id_15>",
|
| 864 |
+
"<extra_id_16>",
|
| 865 |
+
"<extra_id_17>",
|
| 866 |
+
"<extra_id_18>",
|
| 867 |
+
"<extra_id_19>",
|
| 868 |
+
"<extra_id_20>",
|
| 869 |
+
"<extra_id_21>",
|
| 870 |
+
"<extra_id_22>",
|
| 871 |
+
"<extra_id_23>",
|
| 872 |
+
"<extra_id_24>",
|
| 873 |
+
"<extra_id_25>",
|
| 874 |
+
"<extra_id_26>",
|
| 875 |
+
"<extra_id_27>",
|
| 876 |
+
"<extra_id_28>",
|
| 877 |
+
"<extra_id_29>",
|
| 878 |
+
"<extra_id_30>",
|
| 879 |
+
"<extra_id_31>",
|
| 880 |
+
"<extra_id_32>",
|
| 881 |
+
"<extra_id_33>",
|
| 882 |
+
"<extra_id_34>",
|
| 883 |
+
"<extra_id_35>",
|
| 884 |
+
"<extra_id_36>",
|
| 885 |
+
"<extra_id_37>",
|
| 886 |
+
"<extra_id_38>",
|
| 887 |
+
"<extra_id_39>",
|
| 888 |
+
"<extra_id_40>",
|
| 889 |
+
"<extra_id_41>",
|
| 890 |
+
"<extra_id_42>",
|
| 891 |
+
"<extra_id_43>",
|
| 892 |
+
"<extra_id_44>",
|
| 893 |
+
"<extra_id_45>",
|
| 894 |
+
"<extra_id_46>",
|
| 895 |
+
"<extra_id_47>",
|
| 896 |
+
"<extra_id_48>",
|
| 897 |
+
"<extra_id_49>",
|
| 898 |
+
"<extra_id_50>",
|
| 899 |
+
"<extra_id_51>",
|
| 900 |
+
"<extra_id_52>",
|
| 901 |
+
"<extra_id_53>",
|
| 902 |
+
"<extra_id_54>",
|
| 903 |
+
"<extra_id_55>",
|
| 904 |
+
"<extra_id_56>",
|
| 905 |
+
"<extra_id_57>",
|
| 906 |
+
"<extra_id_58>",
|
| 907 |
+
"<extra_id_59>",
|
| 908 |
+
"<extra_id_60>",
|
| 909 |
+
"<extra_id_61>",
|
| 910 |
+
"<extra_id_62>",
|
| 911 |
+
"<extra_id_63>",
|
| 912 |
+
"<extra_id_64>",
|
| 913 |
+
"<extra_id_65>",
|
| 914 |
+
"<extra_id_66>",
|
| 915 |
+
"<extra_id_67>",
|
| 916 |
+
"<extra_id_68>",
|
| 917 |
+
"<extra_id_69>",
|
| 918 |
+
"<extra_id_70>",
|
| 919 |
+
"<extra_id_71>",
|
| 920 |
+
"<extra_id_72>",
|
| 921 |
+
"<extra_id_73>",
|
| 922 |
+
"<extra_id_74>",
|
| 923 |
+
"<extra_id_75>",
|
| 924 |
+
"<extra_id_76>",
|
| 925 |
+
"<extra_id_77>",
|
| 926 |
+
"<extra_id_78>",
|
| 927 |
+
"<extra_id_79>",
|
| 928 |
+
"<extra_id_80>",
|
| 929 |
+
"<extra_id_81>",
|
| 930 |
+
"<extra_id_82>",
|
| 931 |
+
"<extra_id_83>",
|
| 932 |
+
"<extra_id_84>",
|
| 933 |
+
"<extra_id_85>",
|
| 934 |
+
"<extra_id_86>",
|
| 935 |
+
"<extra_id_87>",
|
| 936 |
+
"<extra_id_88>",
|
| 937 |
+
"<extra_id_89>",
|
| 938 |
+
"<extra_id_90>",
|
| 939 |
+
"<extra_id_91>",
|
| 940 |
+
"<extra_id_92>",
|
| 941 |
+
"<extra_id_93>",
|
| 942 |
+
"<extra_id_94>",
|
| 943 |
+
"<extra_id_95>",
|
| 944 |
+
"<extra_id_96>",
|
| 945 |
+
"<extra_id_97>",
|
| 946 |
+
"<extra_id_98>",
|
| 947 |
+
"<extra_id_99>"
|
| 948 |
+
],
|
| 949 |
+
"clean_up_tokenization_spaces": false,
|
| 950 |
+
"eos_token": "</s>",
|
| 951 |
+
"extra_ids": 100,
|
| 952 |
+
"extra_special_tokens": {},
|
| 953 |
+
"legacy": true,
|
| 954 |
+
"model_max_length": 512,
|
| 955 |
+
"pad_token": "<pad>",
|
| 956 |
+
"sp_model_kwargs": {},
|
| 957 |
+
"tokenizer_class": "T5Tokenizer",
|
| 958 |
+
"unk_token": "<unk>"
|
| 959 |
+
}
|
checkpoint-13050/trainer_state.json
ADDED
|
@@ -0,0 +1,1024 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 13050,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.07662835249042145,
|
| 14 |
+
"grad_norm": 5.7344746589660645,
|
| 15 |
+
"learning_rate": 4.981034482758621e-05,
|
| 16 |
+
"loss": 1.1305,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.1532567049808429,
|
| 21 |
+
"grad_norm": 3.8406965732574463,
|
| 22 |
+
"learning_rate": 4.961877394636015e-05,
|
| 23 |
+
"loss": 1.0906,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.22988505747126436,
|
| 28 |
+
"grad_norm": 3.591132164001465,
|
| 29 |
+
"learning_rate": 4.9427203065134104e-05,
|
| 30 |
+
"loss": 1.0333,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.3065134099616858,
|
| 35 |
+
"grad_norm": 3.5736236572265625,
|
| 36 |
+
"learning_rate": 4.9235632183908045e-05,
|
| 37 |
+
"loss": 0.9976,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.3831417624521073,
|
| 42 |
+
"grad_norm": 4.690476417541504,
|
| 43 |
+
"learning_rate": 4.904406130268199e-05,
|
| 44 |
+
"loss": 1.0542,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.45977011494252873,
|
| 49 |
+
"grad_norm": 6.11126184463501,
|
| 50 |
+
"learning_rate": 4.885249042145594e-05,
|
| 51 |
+
"loss": 1.0791,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.5363984674329502,
|
| 56 |
+
"grad_norm": 4.683467864990234,
|
| 57 |
+
"learning_rate": 4.866091954022989e-05,
|
| 58 |
+
"loss": 1.02,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.6130268199233716,
|
| 63 |
+
"grad_norm": 5.850108623504639,
|
| 64 |
+
"learning_rate": 4.8469348659003835e-05,
|
| 65 |
+
"loss": 1.0065,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.6896551724137931,
|
| 70 |
+
"grad_norm": 4.229581832885742,
|
| 71 |
+
"learning_rate": 4.8277777777777776e-05,
|
| 72 |
+
"loss": 0.9875,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.7662835249042146,
|
| 77 |
+
"grad_norm": 3.624990463256836,
|
| 78 |
+
"learning_rate": 4.808620689655173e-05,
|
| 79 |
+
"loss": 0.9984,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.842911877394636,
|
| 84 |
+
"grad_norm": 4.911725044250488,
|
| 85 |
+
"learning_rate": 4.789463601532567e-05,
|
| 86 |
+
"loss": 1.0487,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.9195402298850575,
|
| 91 |
+
"grad_norm": 3.8310468196868896,
|
| 92 |
+
"learning_rate": 4.770306513409962e-05,
|
| 93 |
+
"loss": 1.0149,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.9961685823754789,
|
| 98 |
+
"grad_norm": 3.5830583572387695,
|
| 99 |
+
"learning_rate": 4.7511494252873566e-05,
|
| 100 |
+
"loss": 1.06,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.0,
|
| 105 |
+
"eval_loss": 1.0906214714050293,
|
| 106 |
+
"eval_runtime": 35.7309,
|
| 107 |
+
"eval_samples_per_second": 21.998,
|
| 108 |
+
"eval_steps_per_second": 2.771,
|
| 109 |
+
"step": 1305
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 1.0727969348659003,
|
| 113 |
+
"grad_norm": 3.774888277053833,
|
| 114 |
+
"learning_rate": 4.7319923371647514e-05,
|
| 115 |
+
"loss": 0.956,
|
| 116 |
+
"step": 1400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.1494252873563218,
|
| 120 |
+
"grad_norm": 4.611693382263184,
|
| 121 |
+
"learning_rate": 4.7128352490421454e-05,
|
| 122 |
+
"loss": 0.9284,
|
| 123 |
+
"step": 1500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 1.2260536398467432,
|
| 127 |
+
"grad_norm": 4.032992362976074,
|
| 128 |
+
"learning_rate": 4.693678160919541e-05,
|
| 129 |
+
"loss": 0.9204,
|
| 130 |
+
"step": 1600
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 1.3026819923371646,
|
| 134 |
+
"grad_norm": 5.431839466094971,
|
| 135 |
+
"learning_rate": 4.674521072796935e-05,
|
| 136 |
+
"loss": 0.9229,
|
| 137 |
+
"step": 1700
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.3793103448275863,
|
| 141 |
+
"grad_norm": 3.730992317199707,
|
| 142 |
+
"learning_rate": 4.65536398467433e-05,
|
| 143 |
+
"loss": 1.0133,
|
| 144 |
+
"step": 1800
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.4559386973180077,
|
| 148 |
+
"grad_norm": 4211.0546875,
|
| 149 |
+
"learning_rate": 4.6362068965517244e-05,
|
| 150 |
+
"loss": 0.9689,
|
| 151 |
+
"step": 1900
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 1.5325670498084292,
|
| 155 |
+
"grad_norm": 4.043152332305908,
|
| 156 |
+
"learning_rate": 4.617049808429119e-05,
|
| 157 |
+
"loss": 0.9687,
|
| 158 |
+
"step": 2000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.6091954022988506,
|
| 162 |
+
"grad_norm": 3.3573741912841797,
|
| 163 |
+
"learning_rate": 4.597892720306514e-05,
|
| 164 |
+
"loss": 0.9888,
|
| 165 |
+
"step": 2100
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.685823754789272,
|
| 169 |
+
"grad_norm": 4.522321701049805,
|
| 170 |
+
"learning_rate": 4.578735632183908e-05,
|
| 171 |
+
"loss": 0.9124,
|
| 172 |
+
"step": 2200
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.7624521072796935,
|
| 176 |
+
"grad_norm": 3.765150547027588,
|
| 177 |
+
"learning_rate": 4.5595785440613034e-05,
|
| 178 |
+
"loss": 0.9307,
|
| 179 |
+
"step": 2300
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.839080459770115,
|
| 183 |
+
"grad_norm": 3.1807477474212646,
|
| 184 |
+
"learning_rate": 4.5404214559386975e-05,
|
| 185 |
+
"loss": 0.8748,
|
| 186 |
+
"step": 2400
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.9157088122605364,
|
| 190 |
+
"grad_norm": 2.6313624382019043,
|
| 191 |
+
"learning_rate": 4.521264367816092e-05,
|
| 192 |
+
"loss": 0.9171,
|
| 193 |
+
"step": 2500
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.9923371647509578,
|
| 197 |
+
"grad_norm": 3.634876012802124,
|
| 198 |
+
"learning_rate": 4.5021072796934863e-05,
|
| 199 |
+
"loss": 0.8612,
|
| 200 |
+
"step": 2600
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.0,
|
| 204 |
+
"eval_loss": 1.101178765296936,
|
| 205 |
+
"eval_runtime": 35.7767,
|
| 206 |
+
"eval_samples_per_second": 21.97,
|
| 207 |
+
"eval_steps_per_second": 2.767,
|
| 208 |
+
"step": 2610
|
| 209 |
+
},
|
| 210 |
+
{
|
| 211 |
+
"epoch": 2.0689655172413794,
|
| 212 |
+
"grad_norm": 3.910709857940674,
|
| 213 |
+
"learning_rate": 4.482950191570882e-05,
|
| 214 |
+
"loss": 0.8766,
|
| 215 |
+
"step": 2700
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 2.1455938697318007,
|
| 219 |
+
"grad_norm": 4.120099067687988,
|
| 220 |
+
"learning_rate": 4.463793103448276e-05,
|
| 221 |
+
"loss": 0.8384,
|
| 222 |
+
"step": 2800
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 2.2222222222222223,
|
| 226 |
+
"grad_norm": 3.503195285797119,
|
| 227 |
+
"learning_rate": 4.4446360153256706e-05,
|
| 228 |
+
"loss": 0.8002,
|
| 229 |
+
"step": 2900
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 2.2988505747126435,
|
| 233 |
+
"grad_norm": 2.656142473220825,
|
| 234 |
+
"learning_rate": 4.4254789272030654e-05,
|
| 235 |
+
"loss": 0.847,
|
| 236 |
+
"step": 3000
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 2.375478927203065,
|
| 240 |
+
"grad_norm": 5.821937561035156,
|
| 241 |
+
"learning_rate": 4.40632183908046e-05,
|
| 242 |
+
"loss": 0.8926,
|
| 243 |
+
"step": 3100
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.4521072796934864,
|
| 247 |
+
"grad_norm": 3.25353741645813,
|
| 248 |
+
"learning_rate": 4.387164750957854e-05,
|
| 249 |
+
"loss": 0.861,
|
| 250 |
+
"step": 3200
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 2.528735632183908,
|
| 254 |
+
"grad_norm": 4.392641544342041,
|
| 255 |
+
"learning_rate": 4.368007662835249e-05,
|
| 256 |
+
"loss": 0.8816,
|
| 257 |
+
"step": 3300
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 2.6053639846743293,
|
| 261 |
+
"grad_norm": 4.363289833068848,
|
| 262 |
+
"learning_rate": 4.348850574712644e-05,
|
| 263 |
+
"loss": 0.8456,
|
| 264 |
+
"step": 3400
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 2.681992337164751,
|
| 268 |
+
"grad_norm": 6.091750621795654,
|
| 269 |
+
"learning_rate": 4.3296934865900384e-05,
|
| 270 |
+
"loss": 0.8657,
|
| 271 |
+
"step": 3500
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 2.7586206896551726,
|
| 275 |
+
"grad_norm": 2.8924543857574463,
|
| 276 |
+
"learning_rate": 4.310536398467433e-05,
|
| 277 |
+
"loss": 0.8545,
|
| 278 |
+
"step": 3600
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.835249042145594,
|
| 282 |
+
"grad_norm": 4.278523921966553,
|
| 283 |
+
"learning_rate": 4.291379310344828e-05,
|
| 284 |
+
"loss": 0.8116,
|
| 285 |
+
"step": 3700
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.9118773946360155,
|
| 289 |
+
"grad_norm": 4.9069695472717285,
|
| 290 |
+
"learning_rate": 4.272222222222223e-05,
|
| 291 |
+
"loss": 0.7743,
|
| 292 |
+
"step": 3800
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 2.9885057471264367,
|
| 296 |
+
"grad_norm": 3.1737210750579834,
|
| 297 |
+
"learning_rate": 4.253065134099617e-05,
|
| 298 |
+
"loss": 0.8303,
|
| 299 |
+
"step": 3900
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 3.0,
|
| 303 |
+
"eval_loss": 1.0942989587783813,
|
| 304 |
+
"eval_runtime": 35.7171,
|
| 305 |
+
"eval_samples_per_second": 22.006,
|
| 306 |
+
"eval_steps_per_second": 2.772,
|
| 307 |
+
"step": 3915
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 3.0651340996168583,
|
| 311 |
+
"grad_norm": 3.6027774810791016,
|
| 312 |
+
"learning_rate": 4.233908045977012e-05,
|
| 313 |
+
"loss": 0.8078,
|
| 314 |
+
"step": 4000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 3.1417624521072796,
|
| 318 |
+
"grad_norm": 3.8461861610412598,
|
| 319 |
+
"learning_rate": 4.214750957854406e-05,
|
| 320 |
+
"loss": 0.7684,
|
| 321 |
+
"step": 4100
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 3.218390804597701,
|
| 325 |
+
"grad_norm": 3.361426591873169,
|
| 326 |
+
"learning_rate": 4.195593869731801e-05,
|
| 327 |
+
"loss": 0.7332,
|
| 328 |
+
"step": 4200
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 3.2950191570881224,
|
| 332 |
+
"grad_norm": 5.258439064025879,
|
| 333 |
+
"learning_rate": 4.176436781609195e-05,
|
| 334 |
+
"loss": 0.7648,
|
| 335 |
+
"step": 4300
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.371647509578544,
|
| 339 |
+
"grad_norm": 4.770920753479004,
|
| 340 |
+
"learning_rate": 4.1572796934865905e-05,
|
| 341 |
+
"loss": 0.8065,
|
| 342 |
+
"step": 4400
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 3.4482758620689653,
|
| 346 |
+
"grad_norm": 3.109750270843506,
|
| 347 |
+
"learning_rate": 4.1381226053639846e-05,
|
| 348 |
+
"loss": 0.8222,
|
| 349 |
+
"step": 4500
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 3.524904214559387,
|
| 353 |
+
"grad_norm": 4.756752014160156,
|
| 354 |
+
"learning_rate": 4.1189655172413794e-05,
|
| 355 |
+
"loss": 0.7097,
|
| 356 |
+
"step": 4600
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.6015325670498086,
|
| 360 |
+
"grad_norm": 5.091802597045898,
|
| 361 |
+
"learning_rate": 4.099808429118774e-05,
|
| 362 |
+
"loss": 0.7392,
|
| 363 |
+
"step": 4700
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 3.67816091954023,
|
| 367 |
+
"grad_norm": 3.8680636882781982,
|
| 368 |
+
"learning_rate": 4.080651340996169e-05,
|
| 369 |
+
"loss": 0.8201,
|
| 370 |
+
"step": 4800
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 3.7547892720306515,
|
| 374 |
+
"grad_norm": 3.1535446643829346,
|
| 375 |
+
"learning_rate": 4.0614942528735636e-05,
|
| 376 |
+
"loss": 0.743,
|
| 377 |
+
"step": 4900
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.8314176245210727,
|
| 381 |
+
"grad_norm": 6.09443998336792,
|
| 382 |
+
"learning_rate": 4.042337164750958e-05,
|
| 383 |
+
"loss": 0.7441,
|
| 384 |
+
"step": 5000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.9080459770114944,
|
| 388 |
+
"grad_norm": 6.005178451538086,
|
| 389 |
+
"learning_rate": 4.023180076628353e-05,
|
| 390 |
+
"loss": 0.7593,
|
| 391 |
+
"step": 5100
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"epoch": 3.9846743295019156,
|
| 395 |
+
"grad_norm": 3.668241262435913,
|
| 396 |
+
"learning_rate": 4.004022988505747e-05,
|
| 397 |
+
"loss": 0.8069,
|
| 398 |
+
"step": 5200
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 4.0,
|
| 402 |
+
"eval_loss": 1.110893964767456,
|
| 403 |
+
"eval_runtime": 35.7068,
|
| 404 |
+
"eval_samples_per_second": 22.013,
|
| 405 |
+
"eval_steps_per_second": 2.773,
|
| 406 |
+
"step": 5220
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 4.061302681992337,
|
| 410 |
+
"grad_norm": 2.764216899871826,
|
| 411 |
+
"learning_rate": 3.984865900383142e-05,
|
| 412 |
+
"loss": 0.7624,
|
| 413 |
+
"step": 5300
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.137931034482759,
|
| 417 |
+
"grad_norm": 4.847288131713867,
|
| 418 |
+
"learning_rate": 3.965708812260537e-05,
|
| 419 |
+
"loss": 0.7193,
|
| 420 |
+
"step": 5400
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 4.21455938697318,
|
| 424 |
+
"grad_norm": 3.8520867824554443,
|
| 425 |
+
"learning_rate": 3.9465517241379314e-05,
|
| 426 |
+
"loss": 0.7152,
|
| 427 |
+
"step": 5500
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"epoch": 4.291187739463601,
|
| 431 |
+
"grad_norm": 2.7300610542297363,
|
| 432 |
+
"learning_rate": 3.9273946360153255e-05,
|
| 433 |
+
"loss": 0.6824,
|
| 434 |
+
"step": 5600
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 4.3678160919540225,
|
| 438 |
+
"grad_norm": 5.303357124328613,
|
| 439 |
+
"learning_rate": 3.90823754789272e-05,
|
| 440 |
+
"loss": 0.782,
|
| 441 |
+
"step": 5700
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 4.444444444444445,
|
| 445 |
+
"grad_norm": 3.1370625495910645,
|
| 446 |
+
"learning_rate": 3.889080459770115e-05,
|
| 447 |
+
"loss": 0.7441,
|
| 448 |
+
"step": 5800
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 4.521072796934866,
|
| 452 |
+
"grad_norm": 3.079803943634033,
|
| 453 |
+
"learning_rate": 3.86992337164751e-05,
|
| 454 |
+
"loss": 0.7316,
|
| 455 |
+
"step": 5900
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 4.597701149425287,
|
| 459 |
+
"grad_norm": 4.676971435546875,
|
| 460 |
+
"learning_rate": 3.8507662835249045e-05,
|
| 461 |
+
"loss": 0.7132,
|
| 462 |
+
"step": 6000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 4.674329501915709,
|
| 466 |
+
"grad_norm": 4.069165229797363,
|
| 467 |
+
"learning_rate": 3.831609195402299e-05,
|
| 468 |
+
"loss": 0.7221,
|
| 469 |
+
"step": 6100
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 4.75095785440613,
|
| 473 |
+
"grad_norm": 4.058932304382324,
|
| 474 |
+
"learning_rate": 3.812452107279694e-05,
|
| 475 |
+
"loss": 0.711,
|
| 476 |
+
"step": 6200
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 4.827586206896552,
|
| 480 |
+
"grad_norm": 2.9622995853424072,
|
| 481 |
+
"learning_rate": 3.793295019157088e-05,
|
| 482 |
+
"loss": 0.7267,
|
| 483 |
+
"step": 6300
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 4.904214559386973,
|
| 487 |
+
"grad_norm": 3.9263229370117188,
|
| 488 |
+
"learning_rate": 3.7741379310344835e-05,
|
| 489 |
+
"loss": 0.6668,
|
| 490 |
+
"step": 6400
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 4.980842911877395,
|
| 494 |
+
"grad_norm": 4.2369489669799805,
|
| 495 |
+
"learning_rate": 3.7549808429118776e-05,
|
| 496 |
+
"loss": 0.7119,
|
| 497 |
+
"step": 6500
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 5.0,
|
| 501 |
+
"eval_loss": 1.1032949686050415,
|
| 502 |
+
"eval_runtime": 35.7481,
|
| 503 |
+
"eval_samples_per_second": 21.987,
|
| 504 |
+
"eval_steps_per_second": 2.769,
|
| 505 |
+
"step": 6525
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 5.057471264367816,
|
| 509 |
+
"grad_norm": 4.44255256652832,
|
| 510 |
+
"learning_rate": 3.7358237547892724e-05,
|
| 511 |
+
"loss": 0.6828,
|
| 512 |
+
"step": 6600
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 5.134099616858237,
|
| 516 |
+
"grad_norm": 4.4376349449157715,
|
| 517 |
+
"learning_rate": 3.7166666666666664e-05,
|
| 518 |
+
"loss": 0.6346,
|
| 519 |
+
"step": 6700
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 5.210727969348659,
|
| 523 |
+
"grad_norm": 5.4497785568237305,
|
| 524 |
+
"learning_rate": 3.697509578544062e-05,
|
| 525 |
+
"loss": 0.6359,
|
| 526 |
+
"step": 6800
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 5.287356321839081,
|
| 530 |
+
"grad_norm": 9.438552856445312,
|
| 531 |
+
"learning_rate": 3.678352490421456e-05,
|
| 532 |
+
"loss": 0.7428,
|
| 533 |
+
"step": 6900
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 5.363984674329502,
|
| 537 |
+
"grad_norm": 3.200032949447632,
|
| 538 |
+
"learning_rate": 3.659195402298851e-05,
|
| 539 |
+
"loss": 0.6552,
|
| 540 |
+
"step": 7000
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 5.440613026819923,
|
| 544 |
+
"grad_norm": 5.670555591583252,
|
| 545 |
+
"learning_rate": 3.6400383141762454e-05,
|
| 546 |
+
"loss": 0.7455,
|
| 547 |
+
"step": 7100
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 5.517241379310345,
|
| 551 |
+
"grad_norm": 4.551922798156738,
|
| 552 |
+
"learning_rate": 3.62088122605364e-05,
|
| 553 |
+
"loss": 0.6697,
|
| 554 |
+
"step": 7200
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 5.593869731800766,
|
| 558 |
+
"grad_norm": 6.317702770233154,
|
| 559 |
+
"learning_rate": 3.601724137931034e-05,
|
| 560 |
+
"loss": 0.6993,
|
| 561 |
+
"step": 7300
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 5.670498084291188,
|
| 565 |
+
"grad_norm": 5.221860408782959,
|
| 566 |
+
"learning_rate": 3.582567049808429e-05,
|
| 567 |
+
"loss": 0.7392,
|
| 568 |
+
"step": 7400
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 5.747126436781609,
|
| 572 |
+
"grad_norm": 3.0438530445098877,
|
| 573 |
+
"learning_rate": 3.563409961685824e-05,
|
| 574 |
+
"loss": 0.6925,
|
| 575 |
+
"step": 7500
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.823754789272031,
|
| 579 |
+
"grad_norm": 4.787004470825195,
|
| 580 |
+
"learning_rate": 3.5442528735632185e-05,
|
| 581 |
+
"loss": 0.6557,
|
| 582 |
+
"step": 7600
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 5.900383141762452,
|
| 586 |
+
"grad_norm": 4.179075241088867,
|
| 587 |
+
"learning_rate": 3.525095785440613e-05,
|
| 588 |
+
"loss": 0.721,
|
| 589 |
+
"step": 7700
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 5.977011494252873,
|
| 593 |
+
"grad_norm": 5.991757869720459,
|
| 594 |
+
"learning_rate": 3.505938697318008e-05,
|
| 595 |
+
"loss": 0.6911,
|
| 596 |
+
"step": 7800
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 6.0,
|
| 600 |
+
"eval_loss": 1.1111713647842407,
|
| 601 |
+
"eval_runtime": 35.7998,
|
| 602 |
+
"eval_samples_per_second": 21.955,
|
| 603 |
+
"eval_steps_per_second": 2.765,
|
| 604 |
+
"step": 7830
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 6.053639846743295,
|
| 608 |
+
"grad_norm": 6.965334415435791,
|
| 609 |
+
"learning_rate": 3.486781609195403e-05,
|
| 610 |
+
"loss": 0.6634,
|
| 611 |
+
"step": 7900
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 6.130268199233717,
|
| 615 |
+
"grad_norm": 2.8945555686950684,
|
| 616 |
+
"learning_rate": 3.467624521072797e-05,
|
| 617 |
+
"loss": 0.6409,
|
| 618 |
+
"step": 8000
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 6.206896551724138,
|
| 622 |
+
"grad_norm": 7.04621696472168,
|
| 623 |
+
"learning_rate": 3.4484674329501916e-05,
|
| 624 |
+
"loss": 0.6478,
|
| 625 |
+
"step": 8100
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 6.283524904214559,
|
| 629 |
+
"grad_norm": 5.964188098907471,
|
| 630 |
+
"learning_rate": 3.4293103448275864e-05,
|
| 631 |
+
"loss": 0.6609,
|
| 632 |
+
"step": 8200
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 6.360153256704981,
|
| 636 |
+
"grad_norm": 3.6937413215637207,
|
| 637 |
+
"learning_rate": 3.410153256704981e-05,
|
| 638 |
+
"loss": 0.6455,
|
| 639 |
+
"step": 8300
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 6.436781609195402,
|
| 643 |
+
"grad_norm": 3.6063153743743896,
|
| 644 |
+
"learning_rate": 3.390996168582375e-05,
|
| 645 |
+
"loss": 0.6708,
|
| 646 |
+
"step": 8400
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 6.513409961685824,
|
| 650 |
+
"grad_norm": 5.0566840171813965,
|
| 651 |
+
"learning_rate": 3.3718390804597706e-05,
|
| 652 |
+
"loss": 0.6484,
|
| 653 |
+
"step": 8500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 6.590038314176245,
|
| 657 |
+
"grad_norm": 4.076525688171387,
|
| 658 |
+
"learning_rate": 3.352681992337165e-05,
|
| 659 |
+
"loss": 0.6417,
|
| 660 |
+
"step": 8600
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 6.666666666666667,
|
| 664 |
+
"grad_norm": 4.602978229522705,
|
| 665 |
+
"learning_rate": 3.3335249042145594e-05,
|
| 666 |
+
"loss": 0.6754,
|
| 667 |
+
"step": 8700
|
| 668 |
+
},
|
| 669 |
+
{
|
| 670 |
+
"epoch": 6.743295019157088,
|
| 671 |
+
"grad_norm": 3.83683443069458,
|
| 672 |
+
"learning_rate": 3.314367816091954e-05,
|
| 673 |
+
"loss": 0.6572,
|
| 674 |
+
"step": 8800
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 6.819923371647509,
|
| 678 |
+
"grad_norm": 5.415637016296387,
|
| 679 |
+
"learning_rate": 3.295210727969349e-05,
|
| 680 |
+
"loss": 0.6382,
|
| 681 |
+
"step": 8900
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 6.896551724137931,
|
| 685 |
+
"grad_norm": 2.880042314529419,
|
| 686 |
+
"learning_rate": 3.276053639846744e-05,
|
| 687 |
+
"loss": 0.5834,
|
| 688 |
+
"step": 9000
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"epoch": 6.973180076628353,
|
| 692 |
+
"grad_norm": 4.762007236480713,
|
| 693 |
+
"learning_rate": 3.256896551724138e-05,
|
| 694 |
+
"loss": 0.6903,
|
| 695 |
+
"step": 9100
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 7.0,
|
| 699 |
+
"eval_loss": 1.1124777793884277,
|
| 700 |
+
"eval_runtime": 35.689,
|
| 701 |
+
"eval_samples_per_second": 22.024,
|
| 702 |
+
"eval_steps_per_second": 2.774,
|
| 703 |
+
"step": 9135
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 7.049808429118774,
|
| 707 |
+
"grad_norm": 3.987518548965454,
|
| 708 |
+
"learning_rate": 3.237739463601533e-05,
|
| 709 |
+
"loss": 0.6701,
|
| 710 |
+
"step": 9200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 7.126436781609195,
|
| 714 |
+
"grad_norm": 3.5589754581451416,
|
| 715 |
+
"learning_rate": 3.218582375478927e-05,
|
| 716 |
+
"loss": 0.661,
|
| 717 |
+
"step": 9300
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 7.203065134099617,
|
| 721 |
+
"grad_norm": 5.494041442871094,
|
| 722 |
+
"learning_rate": 3.199425287356322e-05,
|
| 723 |
+
"loss": 0.5611,
|
| 724 |
+
"step": 9400
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 7.2796934865900385,
|
| 728 |
+
"grad_norm": 4.825826644897461,
|
| 729 |
+
"learning_rate": 3.180268199233717e-05,
|
| 730 |
+
"loss": 0.6459,
|
| 731 |
+
"step": 9500
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 7.35632183908046,
|
| 735 |
+
"grad_norm": 4.284668922424316,
|
| 736 |
+
"learning_rate": 3.1611111111111115e-05,
|
| 737 |
+
"loss": 0.6769,
|
| 738 |
+
"step": 9600
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 7.432950191570881,
|
| 742 |
+
"grad_norm": 4.435478210449219,
|
| 743 |
+
"learning_rate": 3.1419540229885056e-05,
|
| 744 |
+
"loss": 0.6881,
|
| 745 |
+
"step": 9700
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 7.509578544061303,
|
| 749 |
+
"grad_norm": 4.267325401306152,
|
| 750 |
+
"learning_rate": 3.1227969348659004e-05,
|
| 751 |
+
"loss": 0.5564,
|
| 752 |
+
"step": 9800
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 7.586206896551724,
|
| 756 |
+
"grad_norm": 3.8725171089172363,
|
| 757 |
+
"learning_rate": 3.103639846743295e-05,
|
| 758 |
+
"loss": 0.6377,
|
| 759 |
+
"step": 9900
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 7.662835249042145,
|
| 763 |
+
"grad_norm": 3.9399173259735107,
|
| 764 |
+
"learning_rate": 3.08448275862069e-05,
|
| 765 |
+
"loss": 0.6397,
|
| 766 |
+
"step": 10000
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 7.739463601532567,
|
| 770 |
+
"grad_norm": 5.38878870010376,
|
| 771 |
+
"learning_rate": 3.0653256704980846e-05,
|
| 772 |
+
"loss": 0.6351,
|
| 773 |
+
"step": 10100
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 7.816091954022989,
|
| 777 |
+
"grad_norm": 2.5697309970855713,
|
| 778 |
+
"learning_rate": 3.0461685823754794e-05,
|
| 779 |
+
"loss": 0.5687,
|
| 780 |
+
"step": 10200
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 7.89272030651341,
|
| 784 |
+
"grad_norm": 5.963043689727783,
|
| 785 |
+
"learning_rate": 3.0270114942528738e-05,
|
| 786 |
+
"loss": 0.6146,
|
| 787 |
+
"step": 10300
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 7.969348659003831,
|
| 791 |
+
"grad_norm": 3.923363208770752,
|
| 792 |
+
"learning_rate": 3.0078544061302682e-05,
|
| 793 |
+
"loss": 0.7019,
|
| 794 |
+
"step": 10400
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 8.0,
|
| 798 |
+
"eval_loss": 1.117806077003479,
|
| 799 |
+
"eval_runtime": 35.7772,
|
| 800 |
+
"eval_samples_per_second": 21.969,
|
| 801 |
+
"eval_steps_per_second": 2.767,
|
| 802 |
+
"step": 10440
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 8.045977011494253,
|
| 806 |
+
"grad_norm": 4.843721389770508,
|
| 807 |
+
"learning_rate": 2.9886973180076626e-05,
|
| 808 |
+
"loss": 0.6183,
|
| 809 |
+
"step": 10500
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 8.122605363984674,
|
| 813 |
+
"grad_norm": 3.855008840560913,
|
| 814 |
+
"learning_rate": 2.9695402298850577e-05,
|
| 815 |
+
"loss": 0.5585,
|
| 816 |
+
"step": 10600
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 8.199233716475096,
|
| 820 |
+
"grad_norm": 2.75059175491333,
|
| 821 |
+
"learning_rate": 2.950383141762452e-05,
|
| 822 |
+
"loss": 0.6155,
|
| 823 |
+
"step": 10700
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 8.275862068965518,
|
| 827 |
+
"grad_norm": 3.5318546295166016,
|
| 828 |
+
"learning_rate": 2.931226053639847e-05,
|
| 829 |
+
"loss": 0.567,
|
| 830 |
+
"step": 10800
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 8.352490421455938,
|
| 834 |
+
"grad_norm": 5.06632661819458,
|
| 835 |
+
"learning_rate": 2.9120689655172416e-05,
|
| 836 |
+
"loss": 0.6041,
|
| 837 |
+
"step": 10900
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 8.42911877394636,
|
| 841 |
+
"grad_norm": 2.8366219997406006,
|
| 842 |
+
"learning_rate": 2.8929118773946364e-05,
|
| 843 |
+
"loss": 0.6351,
|
| 844 |
+
"step": 11000
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 8.505747126436782,
|
| 848 |
+
"grad_norm": 6.297276020050049,
|
| 849 |
+
"learning_rate": 2.8737547892720308e-05,
|
| 850 |
+
"loss": 0.5999,
|
| 851 |
+
"step": 11100
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 8.582375478927203,
|
| 855 |
+
"grad_norm": 4.257690906524658,
|
| 856 |
+
"learning_rate": 2.8545977011494252e-05,
|
| 857 |
+
"loss": 0.6634,
|
| 858 |
+
"step": 11200
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 8.659003831417625,
|
| 862 |
+
"grad_norm": 2.6695499420166016,
|
| 863 |
+
"learning_rate": 2.8354406130268203e-05,
|
| 864 |
+
"loss": 0.6064,
|
| 865 |
+
"step": 11300
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 8.735632183908045,
|
| 869 |
+
"grad_norm": 4.196438789367676,
|
| 870 |
+
"learning_rate": 2.8162835249042147e-05,
|
| 871 |
+
"loss": 0.6061,
|
| 872 |
+
"step": 11400
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 8.812260536398467,
|
| 876 |
+
"grad_norm": 7.031342029571533,
|
| 877 |
+
"learning_rate": 2.797126436781609e-05,
|
| 878 |
+
"loss": 0.6253,
|
| 879 |
+
"step": 11500
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 8.88888888888889,
|
| 883 |
+
"grad_norm": 2.9885549545288086,
|
| 884 |
+
"learning_rate": 2.7779693486590042e-05,
|
| 885 |
+
"loss": 0.5806,
|
| 886 |
+
"step": 11600
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 8.96551724137931,
|
| 890 |
+
"grad_norm": 4.496192455291748,
|
| 891 |
+
"learning_rate": 2.7588122605363986e-05,
|
| 892 |
+
"loss": 0.6611,
|
| 893 |
+
"step": 11700
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 9.0,
|
| 897 |
+
"eval_loss": 1.1148502826690674,
|
| 898 |
+
"eval_runtime": 35.7907,
|
| 899 |
+
"eval_samples_per_second": 21.961,
|
| 900 |
+
"eval_steps_per_second": 2.766,
|
| 901 |
+
"step": 11745
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 9.042145593869732,
|
| 905 |
+
"grad_norm": 2.8324880599975586,
|
| 906 |
+
"learning_rate": 2.739655172413793e-05,
|
| 907 |
+
"loss": 0.6048,
|
| 908 |
+
"step": 11800
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 9.118773946360154,
|
| 912 |
+
"grad_norm": 6.008921146392822,
|
| 913 |
+
"learning_rate": 2.720498084291188e-05,
|
| 914 |
+
"loss": 0.5953,
|
| 915 |
+
"step": 11900
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 9.195402298850574,
|
| 919 |
+
"grad_norm": 4.370833396911621,
|
| 920 |
+
"learning_rate": 2.7013409961685825e-05,
|
| 921 |
+
"loss": 0.5641,
|
| 922 |
+
"step": 12000
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 9.272030651340996,
|
| 926 |
+
"grad_norm": 3.73600172996521,
|
| 927 |
+
"learning_rate": 2.682183908045977e-05,
|
| 928 |
+
"loss": 0.564,
|
| 929 |
+
"step": 12100
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 9.348659003831418,
|
| 933 |
+
"grad_norm": 4.205686092376709,
|
| 934 |
+
"learning_rate": 2.6630268199233717e-05,
|
| 935 |
+
"loss": 0.5849,
|
| 936 |
+
"step": 12200
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 9.425287356321839,
|
| 940 |
+
"grad_norm": 4.107269287109375,
|
| 941 |
+
"learning_rate": 2.6438697318007664e-05,
|
| 942 |
+
"loss": 0.6371,
|
| 943 |
+
"step": 12300
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 9.50191570881226,
|
| 947 |
+
"grad_norm": 3.6027779579162598,
|
| 948 |
+
"learning_rate": 2.6247126436781612e-05,
|
| 949 |
+
"loss": 0.5692,
|
| 950 |
+
"step": 12400
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 9.578544061302683,
|
| 954 |
+
"grad_norm": 3.764218807220459,
|
| 955 |
+
"learning_rate": 2.6055555555555556e-05,
|
| 956 |
+
"loss": 0.6007,
|
| 957 |
+
"step": 12500
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 9.655172413793103,
|
| 961 |
+
"grad_norm": 3.6567819118499756,
|
| 962 |
+
"learning_rate": 2.5863984674329507e-05,
|
| 963 |
+
"loss": 0.569,
|
| 964 |
+
"step": 12600
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 9.731800766283525,
|
| 968 |
+
"grad_norm": 4.256430625915527,
|
| 969 |
+
"learning_rate": 2.567241379310345e-05,
|
| 970 |
+
"loss": 0.5743,
|
| 971 |
+
"step": 12700
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 9.808429118773946,
|
| 975 |
+
"grad_norm": 3.4850544929504395,
|
| 976 |
+
"learning_rate": 2.5480842911877395e-05,
|
| 977 |
+
"loss": 0.5589,
|
| 978 |
+
"step": 12800
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 9.885057471264368,
|
| 982 |
+
"grad_norm": 3.632444381713867,
|
| 983 |
+
"learning_rate": 2.528927203065134e-05,
|
| 984 |
+
"loss": 0.582,
|
| 985 |
+
"step": 12900
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 9.96168582375479,
|
| 989 |
+
"grad_norm": 3.1498610973358154,
|
| 990 |
+
"learning_rate": 2.509770114942529e-05,
|
| 991 |
+
"loss": 0.6006,
|
| 992 |
+
"step": 13000
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 10.0,
|
| 996 |
+
"eval_loss": 1.1268223524093628,
|
| 997 |
+
"eval_runtime": 35.8204,
|
| 998 |
+
"eval_samples_per_second": 21.943,
|
| 999 |
+
"eval_steps_per_second": 2.764,
|
| 1000 |
+
"step": 13050
|
| 1001 |
+
}
|
| 1002 |
+
],
|
| 1003 |
+
"logging_steps": 100,
|
| 1004 |
+
"max_steps": 26100,
|
| 1005 |
+
"num_input_tokens_seen": 0,
|
| 1006 |
+
"num_train_epochs": 20,
|
| 1007 |
+
"save_steps": 500,
|
| 1008 |
+
"stateful_callbacks": {
|
| 1009 |
+
"TrainerControl": {
|
| 1010 |
+
"args": {
|
| 1011 |
+
"should_epoch_stop": false,
|
| 1012 |
+
"should_evaluate": false,
|
| 1013 |
+
"should_log": false,
|
| 1014 |
+
"should_save": true,
|
| 1015 |
+
"should_training_stop": false
|
| 1016 |
+
},
|
| 1017 |
+
"attributes": {}
|
| 1018 |
+
}
|
| 1019 |
+
},
|
| 1020 |
+
"total_flos": 3.572059088093184e+16,
|
| 1021 |
+
"train_batch_size": 8,
|
| 1022 |
+
"trial_name": null,
|
| 1023 |
+
"trial_params": null
|
| 1024 |
+
}
|
checkpoint-13050/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b17a1ef2cbbdad10f6a0f2ae93b7122cbb4eeade1854656a3fb26539771a4dc3
|
| 3 |
+
size 5905
|