Upload folder using huggingface_hub
Browse files- added_tokens.json +102 -0
- config.json +60 -0
- generation_config.json +7 -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 +941 -0
- trainer_state.json +1474 -0
- training_args.bin +3 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<extra_id_0>": 32099,
|
| 3 |
+
"<extra_id_10>": 32089,
|
| 4 |
+
"<extra_id_11>": 32088,
|
| 5 |
+
"<extra_id_12>": 32087,
|
| 6 |
+
"<extra_id_13>": 32086,
|
| 7 |
+
"<extra_id_14>": 32085,
|
| 8 |
+
"<extra_id_15>": 32084,
|
| 9 |
+
"<extra_id_16>": 32083,
|
| 10 |
+
"<extra_id_17>": 32082,
|
| 11 |
+
"<extra_id_18>": 32081,
|
| 12 |
+
"<extra_id_19>": 32080,
|
| 13 |
+
"<extra_id_1>": 32098,
|
| 14 |
+
"<extra_id_20>": 32079,
|
| 15 |
+
"<extra_id_21>": 32078,
|
| 16 |
+
"<extra_id_22>": 32077,
|
| 17 |
+
"<extra_id_23>": 32076,
|
| 18 |
+
"<extra_id_24>": 32075,
|
| 19 |
+
"<extra_id_25>": 32074,
|
| 20 |
+
"<extra_id_26>": 32073,
|
| 21 |
+
"<extra_id_27>": 32072,
|
| 22 |
+
"<extra_id_28>": 32071,
|
| 23 |
+
"<extra_id_29>": 32070,
|
| 24 |
+
"<extra_id_2>": 32097,
|
| 25 |
+
"<extra_id_30>": 32069,
|
| 26 |
+
"<extra_id_31>": 32068,
|
| 27 |
+
"<extra_id_32>": 32067,
|
| 28 |
+
"<extra_id_33>": 32066,
|
| 29 |
+
"<extra_id_34>": 32065,
|
| 30 |
+
"<extra_id_35>": 32064,
|
| 31 |
+
"<extra_id_36>": 32063,
|
| 32 |
+
"<extra_id_37>": 32062,
|
| 33 |
+
"<extra_id_38>": 32061,
|
| 34 |
+
"<extra_id_39>": 32060,
|
| 35 |
+
"<extra_id_3>": 32096,
|
| 36 |
+
"<extra_id_40>": 32059,
|
| 37 |
+
"<extra_id_41>": 32058,
|
| 38 |
+
"<extra_id_42>": 32057,
|
| 39 |
+
"<extra_id_43>": 32056,
|
| 40 |
+
"<extra_id_44>": 32055,
|
| 41 |
+
"<extra_id_45>": 32054,
|
| 42 |
+
"<extra_id_46>": 32053,
|
| 43 |
+
"<extra_id_47>": 32052,
|
| 44 |
+
"<extra_id_48>": 32051,
|
| 45 |
+
"<extra_id_49>": 32050,
|
| 46 |
+
"<extra_id_4>": 32095,
|
| 47 |
+
"<extra_id_50>": 32049,
|
| 48 |
+
"<extra_id_51>": 32048,
|
| 49 |
+
"<extra_id_52>": 32047,
|
| 50 |
+
"<extra_id_53>": 32046,
|
| 51 |
+
"<extra_id_54>": 32045,
|
| 52 |
+
"<extra_id_55>": 32044,
|
| 53 |
+
"<extra_id_56>": 32043,
|
| 54 |
+
"<extra_id_57>": 32042,
|
| 55 |
+
"<extra_id_58>": 32041,
|
| 56 |
+
"<extra_id_59>": 32040,
|
| 57 |
+
"<extra_id_5>": 32094,
|
| 58 |
+
"<extra_id_60>": 32039,
|
| 59 |
+
"<extra_id_61>": 32038,
|
| 60 |
+
"<extra_id_62>": 32037,
|
| 61 |
+
"<extra_id_63>": 32036,
|
| 62 |
+
"<extra_id_64>": 32035,
|
| 63 |
+
"<extra_id_65>": 32034,
|
| 64 |
+
"<extra_id_66>": 32033,
|
| 65 |
+
"<extra_id_67>": 32032,
|
| 66 |
+
"<extra_id_68>": 32031,
|
| 67 |
+
"<extra_id_69>": 32030,
|
| 68 |
+
"<extra_id_6>": 32093,
|
| 69 |
+
"<extra_id_70>": 32029,
|
| 70 |
+
"<extra_id_71>": 32028,
|
| 71 |
+
"<extra_id_72>": 32027,
|
| 72 |
+
"<extra_id_73>": 32026,
|
| 73 |
+
"<extra_id_74>": 32025,
|
| 74 |
+
"<extra_id_75>": 32024,
|
| 75 |
+
"<extra_id_76>": 32023,
|
| 76 |
+
"<extra_id_77>": 32022,
|
| 77 |
+
"<extra_id_78>": 32021,
|
| 78 |
+
"<extra_id_79>": 32020,
|
| 79 |
+
"<extra_id_7>": 32092,
|
| 80 |
+
"<extra_id_80>": 32019,
|
| 81 |
+
"<extra_id_81>": 32018,
|
| 82 |
+
"<extra_id_82>": 32017,
|
| 83 |
+
"<extra_id_83>": 32016,
|
| 84 |
+
"<extra_id_84>": 32015,
|
| 85 |
+
"<extra_id_85>": 32014,
|
| 86 |
+
"<extra_id_86>": 32013,
|
| 87 |
+
"<extra_id_87>": 32012,
|
| 88 |
+
"<extra_id_88>": 32011,
|
| 89 |
+
"<extra_id_89>": 32010,
|
| 90 |
+
"<extra_id_8>": 32091,
|
| 91 |
+
"<extra_id_90>": 32009,
|
| 92 |
+
"<extra_id_91>": 32008,
|
| 93 |
+
"<extra_id_92>": 32007,
|
| 94 |
+
"<extra_id_93>": 32006,
|
| 95 |
+
"<extra_id_94>": 32005,
|
| 96 |
+
"<extra_id_95>": 32004,
|
| 97 |
+
"<extra_id_96>": 32003,
|
| 98 |
+
"<extra_id_97>": 32002,
|
| 99 |
+
"<extra_id_98>": 32001,
|
| 100 |
+
"<extra_id_99>": 32000,
|
| 101 |
+
"<extra_id_9>": 32090
|
| 102 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"T5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"classifier_dropout": 0.0,
|
| 6 |
+
"d_ff": 2048,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 512,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "relu",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"eos_token_id": 1,
|
| 13 |
+
"feed_forward_proj": "relu",
|
| 14 |
+
"initializer_factor": 1.0,
|
| 15 |
+
"is_encoder_decoder": true,
|
| 16 |
+
"is_gated_act": false,
|
| 17 |
+
"layer_norm_epsilon": 1e-06,
|
| 18 |
+
"model_type": "t5",
|
| 19 |
+
"n_positions": 512,
|
| 20 |
+
"num_decoder_layers": 6,
|
| 21 |
+
"num_heads": 8,
|
| 22 |
+
"num_layers": 6,
|
| 23 |
+
"output_past": true,
|
| 24 |
+
"pad_token_id": 0,
|
| 25 |
+
"relative_attention_max_distance": 128,
|
| 26 |
+
"relative_attention_num_buckets": 32,
|
| 27 |
+
"task_specific_params": {
|
| 28 |
+
"summarization": {
|
| 29 |
+
"early_stopping": true,
|
| 30 |
+
"length_penalty": 2.0,
|
| 31 |
+
"max_length": 200,
|
| 32 |
+
"min_length": 30,
|
| 33 |
+
"no_repeat_ngram_size": 3,
|
| 34 |
+
"num_beams": 4,
|
| 35 |
+
"prefix": "summarize: "
|
| 36 |
+
},
|
| 37 |
+
"translation_en_to_de": {
|
| 38 |
+
"early_stopping": true,
|
| 39 |
+
"max_length": 300,
|
| 40 |
+
"num_beams": 4,
|
| 41 |
+
"prefix": "translate English to German: "
|
| 42 |
+
},
|
| 43 |
+
"translation_en_to_fr": {
|
| 44 |
+
"early_stopping": true,
|
| 45 |
+
"max_length": 300,
|
| 46 |
+
"num_beams": 4,
|
| 47 |
+
"prefix": "translate English to French: "
|
| 48 |
+
},
|
| 49 |
+
"translation_en_to_ro": {
|
| 50 |
+
"early_stopping": true,
|
| 51 |
+
"max_length": 300,
|
| 52 |
+
"num_beams": 4,
|
| 53 |
+
"prefix": "translate English to Romanian: "
|
| 54 |
+
}
|
| 55 |
+
},
|
| 56 |
+
"torch_dtype": "float32",
|
| 57 |
+
"transformers_version": "4.55.3",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 32128
|
| 60 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"decoder_start_token_id": 0,
|
| 4 |
+
"eos_token_id": 1,
|
| 5 |
+
"pad_token_id": 0,
|
| 6 |
+
"transformers_version": "4.55.3"
|
| 7 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7cc6994e838d102566718aefac51c5f283388df6efa5539eb8a53fc3a4dedb7
|
| 3 |
+
size 242041896
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e662d6190c69d910a5c8ca6241fcb0988c12a7811354792d056bab9eaee36f7d
|
| 3 |
+
size 484160331
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8bc0a06476aa10c49515a450d15dfde5a85365f12ce731a7b2aaa5e3f5a94dd
|
| 3 |
+
size 14455
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:672ca08ae7e12889d647f5617032834a28e7a4366e5dbbdbd888ea2b8386e9e7
|
| 3 |
+
size 1465
|
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:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
|
| 3 |
+
size 791656
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,941 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 31 |
+
"normalized": false,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"32001": {
|
| 37 |
+
"content": "<extra_id_98>",
|
| 38 |
+
"lstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"32002": {
|
| 45 |
+
"content": "<extra_id_97>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"32003": {
|
| 53 |
+
"content": "<extra_id_96>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"32004": {
|
| 61 |
+
"content": "<extra_id_95>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"32005": {
|
| 69 |
+
"content": "<extra_id_94>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"32006": {
|
| 77 |
+
"content": "<extra_id_93>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"32007": {
|
| 85 |
+
"content": "<extra_id_92>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
},
|
| 92 |
+
"32008": {
|
| 93 |
+
"content": "<extra_id_91>",
|
| 94 |
+
"lstrip": false,
|
| 95 |
+
"normalized": false,
|
| 96 |
+
"rstrip": false,
|
| 97 |
+
"single_word": false,
|
| 98 |
+
"special": true
|
| 99 |
+
},
|
| 100 |
+
"32009": {
|
| 101 |
+
"content": "<extra_id_90>",
|
| 102 |
+
"lstrip": false,
|
| 103 |
+
"normalized": false,
|
| 104 |
+
"rstrip": false,
|
| 105 |
+
"single_word": false,
|
| 106 |
+
"special": true
|
| 107 |
+
},
|
| 108 |
+
"32010": {
|
| 109 |
+
"content": "<extra_id_89>",
|
| 110 |
+
"lstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"rstrip": false,
|
| 113 |
+
"single_word": false,
|
| 114 |
+
"special": true
|
| 115 |
+
},
|
| 116 |
+
"32011": {
|
| 117 |
+
"content": "<extra_id_88>",
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"normalized": false,
|
| 120 |
+
"rstrip": false,
|
| 121 |
+
"single_word": false,
|
| 122 |
+
"special": true
|
| 123 |
+
},
|
| 124 |
+
"32012": {
|
| 125 |
+
"content": "<extra_id_87>",
|
| 126 |
+
"lstrip": false,
|
| 127 |
+
"normalized": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"single_word": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
"32013": {
|
| 133 |
+
"content": "<extra_id_86>",
|
| 134 |
+
"lstrip": false,
|
| 135 |
+
"normalized": false,
|
| 136 |
+
"rstrip": false,
|
| 137 |
+
"single_word": false,
|
| 138 |
+
"special": true
|
| 139 |
+
},
|
| 140 |
+
"32014": {
|
| 141 |
+
"content": "<extra_id_85>",
|
| 142 |
+
"lstrip": false,
|
| 143 |
+
"normalized": false,
|
| 144 |
+
"rstrip": false,
|
| 145 |
+
"single_word": false,
|
| 146 |
+
"special": true
|
| 147 |
+
},
|
| 148 |
+
"32015": {
|
| 149 |
+
"content": "<extra_id_84>",
|
| 150 |
+
"lstrip": false,
|
| 151 |
+
"normalized": false,
|
| 152 |
+
"rstrip": false,
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"special": true
|
| 155 |
+
},
|
| 156 |
+
"32016": {
|
| 157 |
+
"content": "<extra_id_83>",
|
| 158 |
+
"lstrip": false,
|
| 159 |
+
"normalized": false,
|
| 160 |
+
"rstrip": false,
|
| 161 |
+
"single_word": false,
|
| 162 |
+
"special": true
|
| 163 |
+
},
|
| 164 |
+
"32017": {
|
| 165 |
+
"content": "<extra_id_82>",
|
| 166 |
+
"lstrip": false,
|
| 167 |
+
"normalized": false,
|
| 168 |
+
"rstrip": false,
|
| 169 |
+
"single_word": false,
|
| 170 |
+
"special": true
|
| 171 |
+
},
|
| 172 |
+
"32018": {
|
| 173 |
+
"content": "<extra_id_81>",
|
| 174 |
+
"lstrip": false,
|
| 175 |
+
"normalized": false,
|
| 176 |
+
"rstrip": false,
|
| 177 |
+
"single_word": false,
|
| 178 |
+
"special": true
|
| 179 |
+
},
|
| 180 |
+
"32019": {
|
| 181 |
+
"content": "<extra_id_80>",
|
| 182 |
+
"lstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"rstrip": false,
|
| 185 |
+
"single_word": false,
|
| 186 |
+
"special": true
|
| 187 |
+
},
|
| 188 |
+
"32020": {
|
| 189 |
+
"content": "<extra_id_79>",
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"normalized": false,
|
| 192 |
+
"rstrip": false,
|
| 193 |
+
"single_word": false,
|
| 194 |
+
"special": true
|
| 195 |
+
},
|
| 196 |
+
"32021": {
|
| 197 |
+
"content": "<extra_id_78>",
|
| 198 |
+
"lstrip": false,
|
| 199 |
+
"normalized": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"single_word": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
"32022": {
|
| 205 |
+
"content": "<extra_id_77>",
|
| 206 |
+
"lstrip": false,
|
| 207 |
+
"normalized": false,
|
| 208 |
+
"rstrip": false,
|
| 209 |
+
"single_word": false,
|
| 210 |
+
"special": true
|
| 211 |
+
},
|
| 212 |
+
"32023": {
|
| 213 |
+
"content": "<extra_id_76>",
|
| 214 |
+
"lstrip": false,
|
| 215 |
+
"normalized": false,
|
| 216 |
+
"rstrip": false,
|
| 217 |
+
"single_word": false,
|
| 218 |
+
"special": true
|
| 219 |
+
},
|
| 220 |
+
"32024": {
|
| 221 |
+
"content": "<extra_id_75>",
|
| 222 |
+
"lstrip": false,
|
| 223 |
+
"normalized": false,
|
| 224 |
+
"rstrip": false,
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"special": true
|
| 227 |
+
},
|
| 228 |
+
"32025": {
|
| 229 |
+
"content": "<extra_id_74>",
|
| 230 |
+
"lstrip": false,
|
| 231 |
+
"normalized": false,
|
| 232 |
+
"rstrip": false,
|
| 233 |
+
"single_word": false,
|
| 234 |
+
"special": true
|
| 235 |
+
},
|
| 236 |
+
"32026": {
|
| 237 |
+
"content": "<extra_id_73>",
|
| 238 |
+
"lstrip": false,
|
| 239 |
+
"normalized": false,
|
| 240 |
+
"rstrip": false,
|
| 241 |
+
"single_word": false,
|
| 242 |
+
"special": true
|
| 243 |
+
},
|
| 244 |
+
"32027": {
|
| 245 |
+
"content": "<extra_id_72>",
|
| 246 |
+
"lstrip": false,
|
| 247 |
+
"normalized": false,
|
| 248 |
+
"rstrip": false,
|
| 249 |
+
"single_word": false,
|
| 250 |
+
"special": true
|
| 251 |
+
},
|
| 252 |
+
"32028": {
|
| 253 |
+
"content": "<extra_id_71>",
|
| 254 |
+
"lstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"rstrip": false,
|
| 257 |
+
"single_word": false,
|
| 258 |
+
"special": true
|
| 259 |
+
},
|
| 260 |
+
"32029": {
|
| 261 |
+
"content": "<extra_id_70>",
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"normalized": false,
|
| 264 |
+
"rstrip": false,
|
| 265 |
+
"single_word": false,
|
| 266 |
+
"special": true
|
| 267 |
+
},
|
| 268 |
+
"32030": {
|
| 269 |
+
"content": "<extra_id_69>",
|
| 270 |
+
"lstrip": false,
|
| 271 |
+
"normalized": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"single_word": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
"32031": {
|
| 277 |
+
"content": "<extra_id_68>",
|
| 278 |
+
"lstrip": false,
|
| 279 |
+
"normalized": false,
|
| 280 |
+
"rstrip": false,
|
| 281 |
+
"single_word": false,
|
| 282 |
+
"special": true
|
| 283 |
+
},
|
| 284 |
+
"32032": {
|
| 285 |
+
"content": "<extra_id_67>",
|
| 286 |
+
"lstrip": false,
|
| 287 |
+
"normalized": false,
|
| 288 |
+
"rstrip": false,
|
| 289 |
+
"single_word": false,
|
| 290 |
+
"special": true
|
| 291 |
+
},
|
| 292 |
+
"32033": {
|
| 293 |
+
"content": "<extra_id_66>",
|
| 294 |
+
"lstrip": false,
|
| 295 |
+
"normalized": false,
|
| 296 |
+
"rstrip": false,
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"special": true
|
| 299 |
+
},
|
| 300 |
+
"32034": {
|
| 301 |
+
"content": "<extra_id_65>",
|
| 302 |
+
"lstrip": false,
|
| 303 |
+
"normalized": false,
|
| 304 |
+
"rstrip": false,
|
| 305 |
+
"single_word": false,
|
| 306 |
+
"special": true
|
| 307 |
+
},
|
| 308 |
+
"32035": {
|
| 309 |
+
"content": "<extra_id_64>",
|
| 310 |
+
"lstrip": false,
|
| 311 |
+
"normalized": false,
|
| 312 |
+
"rstrip": false,
|
| 313 |
+
"single_word": false,
|
| 314 |
+
"special": true
|
| 315 |
+
},
|
| 316 |
+
"32036": {
|
| 317 |
+
"content": "<extra_id_63>",
|
| 318 |
+
"lstrip": false,
|
| 319 |
+
"normalized": false,
|
| 320 |
+
"rstrip": false,
|
| 321 |
+
"single_word": false,
|
| 322 |
+
"special": true
|
| 323 |
+
},
|
| 324 |
+
"32037": {
|
| 325 |
+
"content": "<extra_id_62>",
|
| 326 |
+
"lstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"rstrip": false,
|
| 329 |
+
"single_word": false,
|
| 330 |
+
"special": true
|
| 331 |
+
},
|
| 332 |
+
"32038": {
|
| 333 |
+
"content": "<extra_id_61>",
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"normalized": false,
|
| 336 |
+
"rstrip": false,
|
| 337 |
+
"single_word": false,
|
| 338 |
+
"special": true
|
| 339 |
+
},
|
| 340 |
+
"32039": {
|
| 341 |
+
"content": "<extra_id_60>",
|
| 342 |
+
"lstrip": false,
|
| 343 |
+
"normalized": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"single_word": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
"32040": {
|
| 349 |
+
"content": "<extra_id_59>",
|
| 350 |
+
"lstrip": false,
|
| 351 |
+
"normalized": false,
|
| 352 |
+
"rstrip": false,
|
| 353 |
+
"single_word": false,
|
| 354 |
+
"special": true
|
| 355 |
+
},
|
| 356 |
+
"32041": {
|
| 357 |
+
"content": "<extra_id_58>",
|
| 358 |
+
"lstrip": false,
|
| 359 |
+
"normalized": false,
|
| 360 |
+
"rstrip": false,
|
| 361 |
+
"single_word": false,
|
| 362 |
+
"special": true
|
| 363 |
+
},
|
| 364 |
+
"32042": {
|
| 365 |
+
"content": "<extra_id_57>",
|
| 366 |
+
"lstrip": false,
|
| 367 |
+
"normalized": false,
|
| 368 |
+
"rstrip": false,
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"special": true
|
| 371 |
+
},
|
| 372 |
+
"32043": {
|
| 373 |
+
"content": "<extra_id_56>",
|
| 374 |
+
"lstrip": false,
|
| 375 |
+
"normalized": false,
|
| 376 |
+
"rstrip": false,
|
| 377 |
+
"single_word": false,
|
| 378 |
+
"special": true
|
| 379 |
+
},
|
| 380 |
+
"32044": {
|
| 381 |
+
"content": "<extra_id_55>",
|
| 382 |
+
"lstrip": false,
|
| 383 |
+
"normalized": false,
|
| 384 |
+
"rstrip": false,
|
| 385 |
+
"single_word": false,
|
| 386 |
+
"special": true
|
| 387 |
+
},
|
| 388 |
+
"32045": {
|
| 389 |
+
"content": "<extra_id_54>",
|
| 390 |
+
"lstrip": false,
|
| 391 |
+
"normalized": false,
|
| 392 |
+
"rstrip": false,
|
| 393 |
+
"single_word": false,
|
| 394 |
+
"special": true
|
| 395 |
+
},
|
| 396 |
+
"32046": {
|
| 397 |
+
"content": "<extra_id_53>",
|
| 398 |
+
"lstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"rstrip": false,
|
| 401 |
+
"single_word": false,
|
| 402 |
+
"special": true
|
| 403 |
+
},
|
| 404 |
+
"32047": {
|
| 405 |
+
"content": "<extra_id_52>",
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"normalized": false,
|
| 408 |
+
"rstrip": false,
|
| 409 |
+
"single_word": false,
|
| 410 |
+
"special": true
|
| 411 |
+
},
|
| 412 |
+
"32048": {
|
| 413 |
+
"content": "<extra_id_51>",
|
| 414 |
+
"lstrip": false,
|
| 415 |
+
"normalized": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"single_word": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
"32049": {
|
| 421 |
+
"content": "<extra_id_50>",
|
| 422 |
+
"lstrip": false,
|
| 423 |
+
"normalized": false,
|
| 424 |
+
"rstrip": false,
|
| 425 |
+
"single_word": false,
|
| 426 |
+
"special": true
|
| 427 |
+
},
|
| 428 |
+
"32050": {
|
| 429 |
+
"content": "<extra_id_49>",
|
| 430 |
+
"lstrip": false,
|
| 431 |
+
"normalized": false,
|
| 432 |
+
"rstrip": false,
|
| 433 |
+
"single_word": false,
|
| 434 |
+
"special": true
|
| 435 |
+
},
|
| 436 |
+
"32051": {
|
| 437 |
+
"content": "<extra_id_48>",
|
| 438 |
+
"lstrip": false,
|
| 439 |
+
"normalized": false,
|
| 440 |
+
"rstrip": false,
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"special": true
|
| 443 |
+
},
|
| 444 |
+
"32052": {
|
| 445 |
+
"content": "<extra_id_47>",
|
| 446 |
+
"lstrip": false,
|
| 447 |
+
"normalized": false,
|
| 448 |
+
"rstrip": false,
|
| 449 |
+
"single_word": false,
|
| 450 |
+
"special": true
|
| 451 |
+
},
|
| 452 |
+
"32053": {
|
| 453 |
+
"content": "<extra_id_46>",
|
| 454 |
+
"lstrip": false,
|
| 455 |
+
"normalized": false,
|
| 456 |
+
"rstrip": false,
|
| 457 |
+
"single_word": false,
|
| 458 |
+
"special": true
|
| 459 |
+
},
|
| 460 |
+
"32054": {
|
| 461 |
+
"content": "<extra_id_45>",
|
| 462 |
+
"lstrip": false,
|
| 463 |
+
"normalized": false,
|
| 464 |
+
"rstrip": false,
|
| 465 |
+
"single_word": false,
|
| 466 |
+
"special": true
|
| 467 |
+
},
|
| 468 |
+
"32055": {
|
| 469 |
+
"content": "<extra_id_44>",
|
| 470 |
+
"lstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"rstrip": false,
|
| 473 |
+
"single_word": false,
|
| 474 |
+
"special": true
|
| 475 |
+
},
|
| 476 |
+
"32056": {
|
| 477 |
+
"content": "<extra_id_43>",
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"normalized": false,
|
| 480 |
+
"rstrip": false,
|
| 481 |
+
"single_word": false,
|
| 482 |
+
"special": true
|
| 483 |
+
},
|
| 484 |
+
"32057": {
|
| 485 |
+
"content": "<extra_id_42>",
|
| 486 |
+
"lstrip": false,
|
| 487 |
+
"normalized": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"single_word": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
"32058": {
|
| 493 |
+
"content": "<extra_id_41>",
|
| 494 |
+
"lstrip": false,
|
| 495 |
+
"normalized": false,
|
| 496 |
+
"rstrip": false,
|
| 497 |
+
"single_word": false,
|
| 498 |
+
"special": true
|
| 499 |
+
},
|
| 500 |
+
"32059": {
|
| 501 |
+
"content": "<extra_id_40>",
|
| 502 |
+
"lstrip": false,
|
| 503 |
+
"normalized": false,
|
| 504 |
+
"rstrip": false,
|
| 505 |
+
"single_word": false,
|
| 506 |
+
"special": true
|
| 507 |
+
},
|
| 508 |
+
"32060": {
|
| 509 |
+
"content": "<extra_id_39>",
|
| 510 |
+
"lstrip": false,
|
| 511 |
+
"normalized": false,
|
| 512 |
+
"rstrip": false,
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"special": true
|
| 515 |
+
},
|
| 516 |
+
"32061": {
|
| 517 |
+
"content": "<extra_id_38>",
|
| 518 |
+
"lstrip": false,
|
| 519 |
+
"normalized": false,
|
| 520 |
+
"rstrip": false,
|
| 521 |
+
"single_word": false,
|
| 522 |
+
"special": true
|
| 523 |
+
},
|
| 524 |
+
"32062": {
|
| 525 |
+
"content": "<extra_id_37>",
|
| 526 |
+
"lstrip": false,
|
| 527 |
+
"normalized": false,
|
| 528 |
+
"rstrip": false,
|
| 529 |
+
"single_word": false,
|
| 530 |
+
"special": true
|
| 531 |
+
},
|
| 532 |
+
"32063": {
|
| 533 |
+
"content": "<extra_id_36>",
|
| 534 |
+
"lstrip": false,
|
| 535 |
+
"normalized": false,
|
| 536 |
+
"rstrip": false,
|
| 537 |
+
"single_word": false,
|
| 538 |
+
"special": true
|
| 539 |
+
},
|
| 540 |
+
"32064": {
|
| 541 |
+
"content": "<extra_id_35>",
|
| 542 |
+
"lstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"rstrip": false,
|
| 545 |
+
"single_word": false,
|
| 546 |
+
"special": true
|
| 547 |
+
},
|
| 548 |
+
"32065": {
|
| 549 |
+
"content": "<extra_id_34>",
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"normalized": false,
|
| 552 |
+
"rstrip": false,
|
| 553 |
+
"single_word": false,
|
| 554 |
+
"special": true
|
| 555 |
+
},
|
| 556 |
+
"32066": {
|
| 557 |
+
"content": "<extra_id_33>",
|
| 558 |
+
"lstrip": false,
|
| 559 |
+
"normalized": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"single_word": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
"32067": {
|
| 565 |
+
"content": "<extra_id_32>",
|
| 566 |
+
"lstrip": false,
|
| 567 |
+
"normalized": false,
|
| 568 |
+
"rstrip": false,
|
| 569 |
+
"single_word": false,
|
| 570 |
+
"special": true
|
| 571 |
+
},
|
| 572 |
+
"32068": {
|
| 573 |
+
"content": "<extra_id_31>",
|
| 574 |
+
"lstrip": false,
|
| 575 |
+
"normalized": false,
|
| 576 |
+
"rstrip": false,
|
| 577 |
+
"single_word": false,
|
| 578 |
+
"special": true
|
| 579 |
+
},
|
| 580 |
+
"32069": {
|
| 581 |
+
"content": "<extra_id_30>",
|
| 582 |
+
"lstrip": false,
|
| 583 |
+
"normalized": false,
|
| 584 |
+
"rstrip": false,
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"special": true
|
| 587 |
+
},
|
| 588 |
+
"32070": {
|
| 589 |
+
"content": "<extra_id_29>",
|
| 590 |
+
"lstrip": false,
|
| 591 |
+
"normalized": false,
|
| 592 |
+
"rstrip": false,
|
| 593 |
+
"single_word": false,
|
| 594 |
+
"special": true
|
| 595 |
+
},
|
| 596 |
+
"32071": {
|
| 597 |
+
"content": "<extra_id_28>",
|
| 598 |
+
"lstrip": false,
|
| 599 |
+
"normalized": false,
|
| 600 |
+
"rstrip": false,
|
| 601 |
+
"single_word": false,
|
| 602 |
+
"special": true
|
| 603 |
+
},
|
| 604 |
+
"32072": {
|
| 605 |
+
"content": "<extra_id_27>",
|
| 606 |
+
"lstrip": false,
|
| 607 |
+
"normalized": false,
|
| 608 |
+
"rstrip": false,
|
| 609 |
+
"single_word": false,
|
| 610 |
+
"special": true
|
| 611 |
+
},
|
| 612 |
+
"32073": {
|
| 613 |
+
"content": "<extra_id_26>",
|
| 614 |
+
"lstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"rstrip": false,
|
| 617 |
+
"single_word": false,
|
| 618 |
+
"special": true
|
| 619 |
+
},
|
| 620 |
+
"32074": {
|
| 621 |
+
"content": "<extra_id_25>",
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"normalized": false,
|
| 624 |
+
"rstrip": false,
|
| 625 |
+
"single_word": false,
|
| 626 |
+
"special": true
|
| 627 |
+
},
|
| 628 |
+
"32075": {
|
| 629 |
+
"content": "<extra_id_24>",
|
| 630 |
+
"lstrip": false,
|
| 631 |
+
"normalized": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"single_word": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
"32076": {
|
| 637 |
+
"content": "<extra_id_23>",
|
| 638 |
+
"lstrip": false,
|
| 639 |
+
"normalized": false,
|
| 640 |
+
"rstrip": false,
|
| 641 |
+
"single_word": false,
|
| 642 |
+
"special": true
|
| 643 |
+
},
|
| 644 |
+
"32077": {
|
| 645 |
+
"content": "<extra_id_22>",
|
| 646 |
+
"lstrip": false,
|
| 647 |
+
"normalized": false,
|
| 648 |
+
"rstrip": false,
|
| 649 |
+
"single_word": false,
|
| 650 |
+
"special": true
|
| 651 |
+
},
|
| 652 |
+
"32078": {
|
| 653 |
+
"content": "<extra_id_21>",
|
| 654 |
+
"lstrip": false,
|
| 655 |
+
"normalized": false,
|
| 656 |
+
"rstrip": false,
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"special": true
|
| 659 |
+
},
|
| 660 |
+
"32079": {
|
| 661 |
+
"content": "<extra_id_20>",
|
| 662 |
+
"lstrip": false,
|
| 663 |
+
"normalized": false,
|
| 664 |
+
"rstrip": false,
|
| 665 |
+
"single_word": false,
|
| 666 |
+
"special": true
|
| 667 |
+
},
|
| 668 |
+
"32080": {
|
| 669 |
+
"content": "<extra_id_19>",
|
| 670 |
+
"lstrip": false,
|
| 671 |
+
"normalized": false,
|
| 672 |
+
"rstrip": false,
|
| 673 |
+
"single_word": false,
|
| 674 |
+
"special": true
|
| 675 |
+
},
|
| 676 |
+
"32081": {
|
| 677 |
+
"content": "<extra_id_18>",
|
| 678 |
+
"lstrip": false,
|
| 679 |
+
"normalized": false,
|
| 680 |
+
"rstrip": false,
|
| 681 |
+
"single_word": false,
|
| 682 |
+
"special": true
|
| 683 |
+
},
|
| 684 |
+
"32082": {
|
| 685 |
+
"content": "<extra_id_17>",
|
| 686 |
+
"lstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"rstrip": false,
|
| 689 |
+
"single_word": false,
|
| 690 |
+
"special": true
|
| 691 |
+
},
|
| 692 |
+
"32083": {
|
| 693 |
+
"content": "<extra_id_16>",
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"normalized": false,
|
| 696 |
+
"rstrip": false,
|
| 697 |
+
"single_word": false,
|
| 698 |
+
"special": true
|
| 699 |
+
},
|
| 700 |
+
"32084": {
|
| 701 |
+
"content": "<extra_id_15>",
|
| 702 |
+
"lstrip": false,
|
| 703 |
+
"normalized": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"single_word": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
"32085": {
|
| 709 |
+
"content": "<extra_id_14>",
|
| 710 |
+
"lstrip": false,
|
| 711 |
+
"normalized": false,
|
| 712 |
+
"rstrip": false,
|
| 713 |
+
"single_word": false,
|
| 714 |
+
"special": true
|
| 715 |
+
},
|
| 716 |
+
"32086": {
|
| 717 |
+
"content": "<extra_id_13>",
|
| 718 |
+
"lstrip": false,
|
| 719 |
+
"normalized": false,
|
| 720 |
+
"rstrip": false,
|
| 721 |
+
"single_word": false,
|
| 722 |
+
"special": true
|
| 723 |
+
},
|
| 724 |
+
"32087": {
|
| 725 |
+
"content": "<extra_id_12>",
|
| 726 |
+
"lstrip": false,
|
| 727 |
+
"normalized": false,
|
| 728 |
+
"rstrip": false,
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"special": true
|
| 731 |
+
},
|
| 732 |
+
"32088": {
|
| 733 |
+
"content": "<extra_id_11>",
|
| 734 |
+
"lstrip": false,
|
| 735 |
+
"normalized": false,
|
| 736 |
+
"rstrip": false,
|
| 737 |
+
"single_word": false,
|
| 738 |
+
"special": true
|
| 739 |
+
},
|
| 740 |
+
"32089": {
|
| 741 |
+
"content": "<extra_id_10>",
|
| 742 |
+
"lstrip": false,
|
| 743 |
+
"normalized": false,
|
| 744 |
+
"rstrip": false,
|
| 745 |
+
"single_word": false,
|
| 746 |
+
"special": true
|
| 747 |
+
},
|
| 748 |
+
"32090": {
|
| 749 |
+
"content": "<extra_id_9>",
|
| 750 |
+
"lstrip": false,
|
| 751 |
+
"normalized": false,
|
| 752 |
+
"rstrip": false,
|
| 753 |
+
"single_word": false,
|
| 754 |
+
"special": true
|
| 755 |
+
},
|
| 756 |
+
"32091": {
|
| 757 |
+
"content": "<extra_id_8>",
|
| 758 |
+
"lstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"rstrip": false,
|
| 761 |
+
"single_word": false,
|
| 762 |
+
"special": true
|
| 763 |
+
},
|
| 764 |
+
"32092": {
|
| 765 |
+
"content": "<extra_id_7>",
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"normalized": false,
|
| 768 |
+
"rstrip": false,
|
| 769 |
+
"single_word": false,
|
| 770 |
+
"special": true
|
| 771 |
+
},
|
| 772 |
+
"32093": {
|
| 773 |
+
"content": "<extra_id_6>",
|
| 774 |
+
"lstrip": false,
|
| 775 |
+
"normalized": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"single_word": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
"32094": {
|
| 781 |
+
"content": "<extra_id_5>",
|
| 782 |
+
"lstrip": false,
|
| 783 |
+
"normalized": false,
|
| 784 |
+
"rstrip": false,
|
| 785 |
+
"single_word": false,
|
| 786 |
+
"special": true
|
| 787 |
+
},
|
| 788 |
+
"32095": {
|
| 789 |
+
"content": "<extra_id_4>",
|
| 790 |
+
"lstrip": false,
|
| 791 |
+
"normalized": false,
|
| 792 |
+
"rstrip": false,
|
| 793 |
+
"single_word": false,
|
| 794 |
+
"special": true
|
| 795 |
+
},
|
| 796 |
+
"32096": {
|
| 797 |
+
"content": "<extra_id_3>",
|
| 798 |
+
"lstrip": false,
|
| 799 |
+
"normalized": false,
|
| 800 |
+
"rstrip": false,
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"special": true
|
| 803 |
+
},
|
| 804 |
+
"32097": {
|
| 805 |
+
"content": "<extra_id_2>",
|
| 806 |
+
"lstrip": false,
|
| 807 |
+
"normalized": false,
|
| 808 |
+
"rstrip": false,
|
| 809 |
+
"single_word": false,
|
| 810 |
+
"special": true
|
| 811 |
+
},
|
| 812 |
+
"32098": {
|
| 813 |
+
"content": "<extra_id_1>",
|
| 814 |
+
"lstrip": false,
|
| 815 |
+
"normalized": false,
|
| 816 |
+
"rstrip": false,
|
| 817 |
+
"single_word": false,
|
| 818 |
+
"special": true
|
| 819 |
+
},
|
| 820 |
+
"32099": {
|
| 821 |
+
"content": "<extra_id_0>",
|
| 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 |
+
"extra_special_tokens": {},
|
| 935 |
+
"legacy": true,
|
| 936 |
+
"model_max_length": 512,
|
| 937 |
+
"pad_token": "<pad>",
|
| 938 |
+
"sp_model_kwargs": {},
|
| 939 |
+
"tokenizer_class": "T5Tokenizer",
|
| 940 |
+
"unk_token": "<unk>"
|
| 941 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1474 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 5.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 10000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.025,
|
| 14 |
+
"grad_norm": 8.230839729309082,
|
| 15 |
+
"learning_rate": 4.9755e-05,
|
| 16 |
+
"loss": 4.8912,
|
| 17 |
+
"step": 50
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.05,
|
| 21 |
+
"grad_norm": 4.688719749450684,
|
| 22 |
+
"learning_rate": 4.9505e-05,
|
| 23 |
+
"loss": 1.6864,
|
| 24 |
+
"step": 100
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.075,
|
| 28 |
+
"grad_norm": 5.002687454223633,
|
| 29 |
+
"learning_rate": 4.9255e-05,
|
| 30 |
+
"loss": 1.0988,
|
| 31 |
+
"step": 150
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.1,
|
| 35 |
+
"grad_norm": 4.780168533325195,
|
| 36 |
+
"learning_rate": 4.9005e-05,
|
| 37 |
+
"loss": 0.8088,
|
| 38 |
+
"step": 200
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.125,
|
| 42 |
+
"grad_norm": 4.83399772644043,
|
| 43 |
+
"learning_rate": 4.8755e-05,
|
| 44 |
+
"loss": 0.6977,
|
| 45 |
+
"step": 250
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.15,
|
| 49 |
+
"grad_norm": 3.855978488922119,
|
| 50 |
+
"learning_rate": 4.8505e-05,
|
| 51 |
+
"loss": 0.5413,
|
| 52 |
+
"step": 300
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.175,
|
| 56 |
+
"grad_norm": 2.9968976974487305,
|
| 57 |
+
"learning_rate": 4.8255e-05,
|
| 58 |
+
"loss": 0.4831,
|
| 59 |
+
"step": 350
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.2,
|
| 63 |
+
"grad_norm": 3.2543575763702393,
|
| 64 |
+
"learning_rate": 4.8005e-05,
|
| 65 |
+
"loss": 0.464,
|
| 66 |
+
"step": 400
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.225,
|
| 70 |
+
"grad_norm": 2.6646761894226074,
|
| 71 |
+
"learning_rate": 4.7755e-05,
|
| 72 |
+
"loss": 0.4362,
|
| 73 |
+
"step": 450
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.25,
|
| 77 |
+
"grad_norm": 3.7676384449005127,
|
| 78 |
+
"learning_rate": 4.7505e-05,
|
| 79 |
+
"loss": 0.4083,
|
| 80 |
+
"step": 500
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.275,
|
| 84 |
+
"grad_norm": 3.2820680141448975,
|
| 85 |
+
"learning_rate": 4.725500000000001e-05,
|
| 86 |
+
"loss": 0.3694,
|
| 87 |
+
"step": 550
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.3,
|
| 91 |
+
"grad_norm": 3.288299322128296,
|
| 92 |
+
"learning_rate": 4.7005e-05,
|
| 93 |
+
"loss": 0.3735,
|
| 94 |
+
"step": 600
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.325,
|
| 98 |
+
"grad_norm": 3.515395402908325,
|
| 99 |
+
"learning_rate": 4.6755e-05,
|
| 100 |
+
"loss": 0.3563,
|
| 101 |
+
"step": 650
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.35,
|
| 105 |
+
"grad_norm": 4.2986159324646,
|
| 106 |
+
"learning_rate": 4.6505e-05,
|
| 107 |
+
"loss": 0.3822,
|
| 108 |
+
"step": 700
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.375,
|
| 112 |
+
"grad_norm": 2.9694278240203857,
|
| 113 |
+
"learning_rate": 4.6255000000000004e-05,
|
| 114 |
+
"loss": 0.3447,
|
| 115 |
+
"step": 750
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.4,
|
| 119 |
+
"grad_norm": 2.727344512939453,
|
| 120 |
+
"learning_rate": 4.6005000000000004e-05,
|
| 121 |
+
"loss": 0.3232,
|
| 122 |
+
"step": 800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.425,
|
| 126 |
+
"grad_norm": 2.925055503845215,
|
| 127 |
+
"learning_rate": 4.5755000000000005e-05,
|
| 128 |
+
"loss": 0.3168,
|
| 129 |
+
"step": 850
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.45,
|
| 133 |
+
"grad_norm": 1.7304507493972778,
|
| 134 |
+
"learning_rate": 4.5505000000000006e-05,
|
| 135 |
+
"loss": 0.3269,
|
| 136 |
+
"step": 900
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.475,
|
| 140 |
+
"grad_norm": 2.8221561908721924,
|
| 141 |
+
"learning_rate": 4.5255000000000006e-05,
|
| 142 |
+
"loss": 0.3053,
|
| 143 |
+
"step": 950
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.5,
|
| 147 |
+
"grad_norm": 3.467146396636963,
|
| 148 |
+
"learning_rate": 4.5005e-05,
|
| 149 |
+
"loss": 0.3055,
|
| 150 |
+
"step": 1000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.525,
|
| 154 |
+
"grad_norm": 2.420332908630371,
|
| 155 |
+
"learning_rate": 4.4755e-05,
|
| 156 |
+
"loss": 0.3226,
|
| 157 |
+
"step": 1050
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.55,
|
| 161 |
+
"grad_norm": 2.0012848377227783,
|
| 162 |
+
"learning_rate": 4.4505e-05,
|
| 163 |
+
"loss": 0.318,
|
| 164 |
+
"step": 1100
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.575,
|
| 168 |
+
"grad_norm": 3.340888500213623,
|
| 169 |
+
"learning_rate": 4.4255e-05,
|
| 170 |
+
"loss": 0.3017,
|
| 171 |
+
"step": 1150
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.6,
|
| 175 |
+
"grad_norm": 2.88847279548645,
|
| 176 |
+
"learning_rate": 4.4005e-05,
|
| 177 |
+
"loss": 0.3067,
|
| 178 |
+
"step": 1200
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.625,
|
| 182 |
+
"grad_norm": 3.5503618717193604,
|
| 183 |
+
"learning_rate": 4.3755000000000004e-05,
|
| 184 |
+
"loss": 0.2866,
|
| 185 |
+
"step": 1250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.65,
|
| 189 |
+
"grad_norm": 1.97746741771698,
|
| 190 |
+
"learning_rate": 4.3505000000000004e-05,
|
| 191 |
+
"loss": 0.2764,
|
| 192 |
+
"step": 1300
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.675,
|
| 196 |
+
"grad_norm": 2.513754367828369,
|
| 197 |
+
"learning_rate": 4.3255e-05,
|
| 198 |
+
"loss": 0.2738,
|
| 199 |
+
"step": 1350
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.7,
|
| 203 |
+
"grad_norm": 1.928359866142273,
|
| 204 |
+
"learning_rate": 4.3005e-05,
|
| 205 |
+
"loss": 0.272,
|
| 206 |
+
"step": 1400
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.725,
|
| 210 |
+
"grad_norm": 3.0566446781158447,
|
| 211 |
+
"learning_rate": 4.2755e-05,
|
| 212 |
+
"loss": 0.2858,
|
| 213 |
+
"step": 1450
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.75,
|
| 217 |
+
"grad_norm": 3.126354932785034,
|
| 218 |
+
"learning_rate": 4.2505e-05,
|
| 219 |
+
"loss": 0.2687,
|
| 220 |
+
"step": 1500
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.775,
|
| 224 |
+
"grad_norm": 2.6933629512786865,
|
| 225 |
+
"learning_rate": 4.2255e-05,
|
| 226 |
+
"loss": 0.2625,
|
| 227 |
+
"step": 1550
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.8,
|
| 231 |
+
"grad_norm": 1.8243509531021118,
|
| 232 |
+
"learning_rate": 4.2005e-05,
|
| 233 |
+
"loss": 0.26,
|
| 234 |
+
"step": 1600
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.825,
|
| 238 |
+
"grad_norm": 1.5713759660720825,
|
| 239 |
+
"learning_rate": 4.1755e-05,
|
| 240 |
+
"loss": 0.2658,
|
| 241 |
+
"step": 1650
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.85,
|
| 245 |
+
"grad_norm": 3.0764338970184326,
|
| 246 |
+
"learning_rate": 4.1504999999999996e-05,
|
| 247 |
+
"loss": 0.2391,
|
| 248 |
+
"step": 1700
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.875,
|
| 252 |
+
"grad_norm": 1.8904582262039185,
|
| 253 |
+
"learning_rate": 4.1255e-05,
|
| 254 |
+
"loss": 0.2362,
|
| 255 |
+
"step": 1750
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.9,
|
| 259 |
+
"grad_norm": 2.638389825820923,
|
| 260 |
+
"learning_rate": 4.1005000000000005e-05,
|
| 261 |
+
"loss": 0.2635,
|
| 262 |
+
"step": 1800
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.925,
|
| 266 |
+
"grad_norm": 3.567256450653076,
|
| 267 |
+
"learning_rate": 4.0755000000000005e-05,
|
| 268 |
+
"loss": 0.2487,
|
| 269 |
+
"step": 1850
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.95,
|
| 273 |
+
"grad_norm": 1.0650864839553833,
|
| 274 |
+
"learning_rate": 4.0505000000000006e-05,
|
| 275 |
+
"loss": 0.2561,
|
| 276 |
+
"step": 1900
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.975,
|
| 280 |
+
"grad_norm": 1.547837257385254,
|
| 281 |
+
"learning_rate": 4.025500000000001e-05,
|
| 282 |
+
"loss": 0.2529,
|
| 283 |
+
"step": 1950
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 1.0,
|
| 287 |
+
"grad_norm": 1.24297297000885,
|
| 288 |
+
"learning_rate": 4.0005e-05,
|
| 289 |
+
"loss": 0.2592,
|
| 290 |
+
"step": 2000
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.0,
|
| 294 |
+
"eval_loss": 0.17051538825035095,
|
| 295 |
+
"eval_runtime": 64.5766,
|
| 296 |
+
"eval_samples_per_second": 15.485,
|
| 297 |
+
"eval_steps_per_second": 3.871,
|
| 298 |
+
"step": 2000
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 1.025,
|
| 302 |
+
"grad_norm": 2.5889508724212646,
|
| 303 |
+
"learning_rate": 3.9755e-05,
|
| 304 |
+
"loss": 0.2366,
|
| 305 |
+
"step": 2050
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 1.05,
|
| 309 |
+
"grad_norm": 2.5479001998901367,
|
| 310 |
+
"learning_rate": 3.9505e-05,
|
| 311 |
+
"loss": 0.2362,
|
| 312 |
+
"step": 2100
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.075,
|
| 316 |
+
"grad_norm": 1.6057442426681519,
|
| 317 |
+
"learning_rate": 3.9255e-05,
|
| 318 |
+
"loss": 0.2418,
|
| 319 |
+
"step": 2150
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"epoch": 1.1,
|
| 323 |
+
"grad_norm": 6.403870582580566,
|
| 324 |
+
"learning_rate": 3.9005000000000003e-05,
|
| 325 |
+
"loss": 0.239,
|
| 326 |
+
"step": 2200
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 1.125,
|
| 330 |
+
"grad_norm": 1.7852602005004883,
|
| 331 |
+
"learning_rate": 3.8755000000000004e-05,
|
| 332 |
+
"loss": 0.2317,
|
| 333 |
+
"step": 2250
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.15,
|
| 337 |
+
"grad_norm": 1.732895851135254,
|
| 338 |
+
"learning_rate": 3.8505000000000005e-05,
|
| 339 |
+
"loss": 0.2362,
|
| 340 |
+
"step": 2300
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 1.175,
|
| 344 |
+
"grad_norm": 1.529485821723938,
|
| 345 |
+
"learning_rate": 3.8255e-05,
|
| 346 |
+
"loss": 0.2168,
|
| 347 |
+
"step": 2350
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"epoch": 1.2,
|
| 351 |
+
"grad_norm": 1.7006224393844604,
|
| 352 |
+
"learning_rate": 3.8005e-05,
|
| 353 |
+
"loss": 0.2307,
|
| 354 |
+
"step": 2400
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.225,
|
| 358 |
+
"grad_norm": 1.7951953411102295,
|
| 359 |
+
"learning_rate": 3.7755e-05,
|
| 360 |
+
"loss": 0.2161,
|
| 361 |
+
"step": 2450
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 1.25,
|
| 365 |
+
"grad_norm": 2.2083799839019775,
|
| 366 |
+
"learning_rate": 3.7505e-05,
|
| 367 |
+
"loss": 0.2013,
|
| 368 |
+
"step": 2500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.275,
|
| 372 |
+
"grad_norm": 3.326378107070923,
|
| 373 |
+
"learning_rate": 3.7255e-05,
|
| 374 |
+
"loss": 0.2323,
|
| 375 |
+
"step": 2550
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.3,
|
| 379 |
+
"grad_norm": 2.719395160675049,
|
| 380 |
+
"learning_rate": 3.7005e-05,
|
| 381 |
+
"loss": 0.2244,
|
| 382 |
+
"step": 2600
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.325,
|
| 386 |
+
"grad_norm": 1.8044047355651855,
|
| 387 |
+
"learning_rate": 3.6755e-05,
|
| 388 |
+
"loss": 0.2256,
|
| 389 |
+
"step": 2650
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.35,
|
| 393 |
+
"grad_norm": 2.9023215770721436,
|
| 394 |
+
"learning_rate": 3.6505e-05,
|
| 395 |
+
"loss": 0.2171,
|
| 396 |
+
"step": 2700
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.375,
|
| 400 |
+
"grad_norm": 3.302866220474243,
|
| 401 |
+
"learning_rate": 3.6255e-05,
|
| 402 |
+
"loss": 0.2366,
|
| 403 |
+
"step": 2750
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 1.4,
|
| 407 |
+
"grad_norm": 1.5518901348114014,
|
| 408 |
+
"learning_rate": 3.6005e-05,
|
| 409 |
+
"loss": 0.2179,
|
| 410 |
+
"step": 2800
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.425,
|
| 414 |
+
"grad_norm": 2.0442991256713867,
|
| 415 |
+
"learning_rate": 3.5755e-05,
|
| 416 |
+
"loss": 0.2054,
|
| 417 |
+
"step": 2850
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.45,
|
| 421 |
+
"grad_norm": 2.274137020111084,
|
| 422 |
+
"learning_rate": 3.5505e-05,
|
| 423 |
+
"loss": 0.2158,
|
| 424 |
+
"step": 2900
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 1.475,
|
| 428 |
+
"grad_norm": 2.449765205383301,
|
| 429 |
+
"learning_rate": 3.5255e-05,
|
| 430 |
+
"loss": 0.2241,
|
| 431 |
+
"step": 2950
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 1.5,
|
| 435 |
+
"grad_norm": 1.705886960029602,
|
| 436 |
+
"learning_rate": 3.5005e-05,
|
| 437 |
+
"loss": 0.2107,
|
| 438 |
+
"step": 3000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.525,
|
| 442 |
+
"grad_norm": 1.9636527299880981,
|
| 443 |
+
"learning_rate": 3.4755e-05,
|
| 444 |
+
"loss": 0.2127,
|
| 445 |
+
"step": 3050
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 1.55,
|
| 449 |
+
"grad_norm": 2.048348903656006,
|
| 450 |
+
"learning_rate": 3.4505e-05,
|
| 451 |
+
"loss": 0.2244,
|
| 452 |
+
"step": 3100
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 1.575,
|
| 456 |
+
"grad_norm": 2.6252517700195312,
|
| 457 |
+
"learning_rate": 3.4255e-05,
|
| 458 |
+
"loss": 0.2038,
|
| 459 |
+
"step": 3150
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.6,
|
| 463 |
+
"grad_norm": 5.407904624938965,
|
| 464 |
+
"learning_rate": 3.4005000000000004e-05,
|
| 465 |
+
"loss": 0.2146,
|
| 466 |
+
"step": 3200
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 1.625,
|
| 470 |
+
"grad_norm": 2.5721547603607178,
|
| 471 |
+
"learning_rate": 3.3755000000000005e-05,
|
| 472 |
+
"loss": 0.2236,
|
| 473 |
+
"step": 3250
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.65,
|
| 477 |
+
"grad_norm": 2.8725879192352295,
|
| 478 |
+
"learning_rate": 3.3505000000000005e-05,
|
| 479 |
+
"loss": 0.2178,
|
| 480 |
+
"step": 3300
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 1.675,
|
| 484 |
+
"grad_norm": 3.0591113567352295,
|
| 485 |
+
"learning_rate": 3.3255000000000006e-05,
|
| 486 |
+
"loss": 0.208,
|
| 487 |
+
"step": 3350
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 1.7,
|
| 491 |
+
"grad_norm": 2.7534451484680176,
|
| 492 |
+
"learning_rate": 3.3005e-05,
|
| 493 |
+
"loss": 0.2073,
|
| 494 |
+
"step": 3400
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.725,
|
| 498 |
+
"grad_norm": 2.5346784591674805,
|
| 499 |
+
"learning_rate": 3.2755e-05,
|
| 500 |
+
"loss": 0.1929,
|
| 501 |
+
"step": 3450
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.75,
|
| 505 |
+
"grad_norm": 4.595905780792236,
|
| 506 |
+
"learning_rate": 3.2505e-05,
|
| 507 |
+
"loss": 0.2034,
|
| 508 |
+
"step": 3500
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 1.775,
|
| 512 |
+
"grad_norm": 2.5899410247802734,
|
| 513 |
+
"learning_rate": 3.2255e-05,
|
| 514 |
+
"loss": 0.2061,
|
| 515 |
+
"step": 3550
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 1.8,
|
| 519 |
+
"grad_norm": 2.3893258571624756,
|
| 520 |
+
"learning_rate": 3.2005e-05,
|
| 521 |
+
"loss": 0.1996,
|
| 522 |
+
"step": 3600
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 1.825,
|
| 526 |
+
"grad_norm": 1.27448570728302,
|
| 527 |
+
"learning_rate": 3.1755000000000003e-05,
|
| 528 |
+
"loss": 0.2008,
|
| 529 |
+
"step": 3650
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 1.85,
|
| 533 |
+
"grad_norm": 2.1095352172851562,
|
| 534 |
+
"learning_rate": 3.1505000000000004e-05,
|
| 535 |
+
"loss": 0.194,
|
| 536 |
+
"step": 3700
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 1.875,
|
| 540 |
+
"grad_norm": 3.202643632888794,
|
| 541 |
+
"learning_rate": 3.1255e-05,
|
| 542 |
+
"loss": 0.1924,
|
| 543 |
+
"step": 3750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.9,
|
| 547 |
+
"grad_norm": 2.5014896392822266,
|
| 548 |
+
"learning_rate": 3.1005e-05,
|
| 549 |
+
"loss": 0.1814,
|
| 550 |
+
"step": 3800
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 1.925,
|
| 554 |
+
"grad_norm": 1.8779760599136353,
|
| 555 |
+
"learning_rate": 3.0755e-05,
|
| 556 |
+
"loss": 0.1876,
|
| 557 |
+
"step": 3850
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 1.95,
|
| 561 |
+
"grad_norm": 1.9704879522323608,
|
| 562 |
+
"learning_rate": 3.0505e-05,
|
| 563 |
+
"loss": 0.2035,
|
| 564 |
+
"step": 3900
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 1.975,
|
| 568 |
+
"grad_norm": 1.5915486812591553,
|
| 569 |
+
"learning_rate": 3.0255e-05,
|
| 570 |
+
"loss": 0.1871,
|
| 571 |
+
"step": 3950
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 2.0,
|
| 575 |
+
"grad_norm": 1.360573172569275,
|
| 576 |
+
"learning_rate": 3.0004999999999998e-05,
|
| 577 |
+
"loss": 0.1721,
|
| 578 |
+
"step": 4000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 2.0,
|
| 582 |
+
"eval_loss": 0.14247964322566986,
|
| 583 |
+
"eval_runtime": 57.8322,
|
| 584 |
+
"eval_samples_per_second": 17.291,
|
| 585 |
+
"eval_steps_per_second": 4.323,
|
| 586 |
+
"step": 4000
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 2.025,
|
| 590 |
+
"grad_norm": 1.7904751300811768,
|
| 591 |
+
"learning_rate": 2.9755e-05,
|
| 592 |
+
"loss": 0.1838,
|
| 593 |
+
"step": 4050
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 2.05,
|
| 597 |
+
"grad_norm": 2.8318934440612793,
|
| 598 |
+
"learning_rate": 2.9505e-05,
|
| 599 |
+
"loss": 0.1726,
|
| 600 |
+
"step": 4100
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 2.075,
|
| 604 |
+
"grad_norm": 2.9856910705566406,
|
| 605 |
+
"learning_rate": 2.9255e-05,
|
| 606 |
+
"loss": 0.1935,
|
| 607 |
+
"step": 4150
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 2.1,
|
| 611 |
+
"grad_norm": 1.2206937074661255,
|
| 612 |
+
"learning_rate": 2.9004999999999998e-05,
|
| 613 |
+
"loss": 0.173,
|
| 614 |
+
"step": 4200
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 2.125,
|
| 618 |
+
"grad_norm": 1.7264775037765503,
|
| 619 |
+
"learning_rate": 2.8754999999999998e-05,
|
| 620 |
+
"loss": 0.2022,
|
| 621 |
+
"step": 4250
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.15,
|
| 625 |
+
"grad_norm": 1.7826628684997559,
|
| 626 |
+
"learning_rate": 2.8505000000000002e-05,
|
| 627 |
+
"loss": 0.1703,
|
| 628 |
+
"step": 4300
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 2.175,
|
| 632 |
+
"grad_norm": 1.6034504175186157,
|
| 633 |
+
"learning_rate": 2.8255000000000003e-05,
|
| 634 |
+
"loss": 0.1809,
|
| 635 |
+
"step": 4350
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 2.2,
|
| 639 |
+
"grad_norm": 2.0662107467651367,
|
| 640 |
+
"learning_rate": 2.8005000000000004e-05,
|
| 641 |
+
"loss": 0.1707,
|
| 642 |
+
"step": 4400
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"epoch": 2.225,
|
| 646 |
+
"grad_norm": 2.3653218746185303,
|
| 647 |
+
"learning_rate": 2.7755000000000004e-05,
|
| 648 |
+
"loss": 0.176,
|
| 649 |
+
"step": 4450
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 2.25,
|
| 653 |
+
"grad_norm": 1.6109884977340698,
|
| 654 |
+
"learning_rate": 2.7505000000000002e-05,
|
| 655 |
+
"loss": 0.1823,
|
| 656 |
+
"step": 4500
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"epoch": 2.275,
|
| 660 |
+
"grad_norm": 1.0589327812194824,
|
| 661 |
+
"learning_rate": 2.7255000000000002e-05,
|
| 662 |
+
"loss": 0.172,
|
| 663 |
+
"step": 4550
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 2.3,
|
| 667 |
+
"grad_norm": 1.8202016353607178,
|
| 668 |
+
"learning_rate": 2.7005000000000003e-05,
|
| 669 |
+
"loss": 0.1794,
|
| 670 |
+
"step": 4600
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 2.325,
|
| 674 |
+
"grad_norm": 1.9865130186080933,
|
| 675 |
+
"learning_rate": 2.6755000000000004e-05,
|
| 676 |
+
"loss": 0.1734,
|
| 677 |
+
"step": 4650
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 2.35,
|
| 681 |
+
"grad_norm": 1.5040825605392456,
|
| 682 |
+
"learning_rate": 2.6505e-05,
|
| 683 |
+
"loss": 0.1757,
|
| 684 |
+
"step": 4700
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 2.375,
|
| 688 |
+
"grad_norm": 1.8152176141738892,
|
| 689 |
+
"learning_rate": 2.6255000000000002e-05,
|
| 690 |
+
"loss": 0.2076,
|
| 691 |
+
"step": 4750
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"epoch": 2.4,
|
| 695 |
+
"grad_norm": 1.0795916318893433,
|
| 696 |
+
"learning_rate": 2.6005000000000003e-05,
|
| 697 |
+
"loss": 0.1967,
|
| 698 |
+
"step": 4800
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 2.425,
|
| 702 |
+
"grad_norm": 2.887174129486084,
|
| 703 |
+
"learning_rate": 2.5755e-05,
|
| 704 |
+
"loss": 0.189,
|
| 705 |
+
"step": 4850
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.45,
|
| 709 |
+
"grad_norm": 1.6766159534454346,
|
| 710 |
+
"learning_rate": 2.5505e-05,
|
| 711 |
+
"loss": 0.1768,
|
| 712 |
+
"step": 4900
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 2.475,
|
| 716 |
+
"grad_norm": 1.336639404296875,
|
| 717 |
+
"learning_rate": 2.5255e-05,
|
| 718 |
+
"loss": 0.1686,
|
| 719 |
+
"step": 4950
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 2.5,
|
| 723 |
+
"grad_norm": 1.3105192184448242,
|
| 724 |
+
"learning_rate": 2.5005000000000002e-05,
|
| 725 |
+
"loss": 0.1906,
|
| 726 |
+
"step": 5000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 2.525,
|
| 730 |
+
"grad_norm": 3.529892683029175,
|
| 731 |
+
"learning_rate": 2.4755e-05,
|
| 732 |
+
"loss": 0.1802,
|
| 733 |
+
"step": 5050
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 2.55,
|
| 737 |
+
"grad_norm": 2.232103109359741,
|
| 738 |
+
"learning_rate": 2.4505e-05,
|
| 739 |
+
"loss": 0.1843,
|
| 740 |
+
"step": 5100
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 2.575,
|
| 744 |
+
"grad_norm": 3.0913138389587402,
|
| 745 |
+
"learning_rate": 2.4255e-05,
|
| 746 |
+
"loss": 0.1825,
|
| 747 |
+
"step": 5150
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.6,
|
| 751 |
+
"grad_norm": 2.240821361541748,
|
| 752 |
+
"learning_rate": 2.4005e-05,
|
| 753 |
+
"loss": 0.1681,
|
| 754 |
+
"step": 5200
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 2.625,
|
| 758 |
+
"grad_norm": 1.1728991270065308,
|
| 759 |
+
"learning_rate": 2.3755000000000002e-05,
|
| 760 |
+
"loss": 0.1711,
|
| 761 |
+
"step": 5250
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 2.65,
|
| 765 |
+
"grad_norm": 2.0626940727233887,
|
| 766 |
+
"learning_rate": 2.3505000000000003e-05,
|
| 767 |
+
"loss": 0.1685,
|
| 768 |
+
"step": 5300
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 2.675,
|
| 772 |
+
"grad_norm": 3.6568186283111572,
|
| 773 |
+
"learning_rate": 2.3255e-05,
|
| 774 |
+
"loss": 0.1835,
|
| 775 |
+
"step": 5350
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 2.7,
|
| 779 |
+
"grad_norm": 2.1457467079162598,
|
| 780 |
+
"learning_rate": 2.3005e-05,
|
| 781 |
+
"loss": 0.1844,
|
| 782 |
+
"step": 5400
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 2.725,
|
| 786 |
+
"grad_norm": 2.00649094581604,
|
| 787 |
+
"learning_rate": 2.2755e-05,
|
| 788 |
+
"loss": 0.1853,
|
| 789 |
+
"step": 5450
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.75,
|
| 793 |
+
"grad_norm": 1.8169037103652954,
|
| 794 |
+
"learning_rate": 2.2505000000000002e-05,
|
| 795 |
+
"loss": 0.1808,
|
| 796 |
+
"step": 5500
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 2.775,
|
| 800 |
+
"grad_norm": 1.9334608316421509,
|
| 801 |
+
"learning_rate": 2.2255e-05,
|
| 802 |
+
"loss": 0.1579,
|
| 803 |
+
"step": 5550
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 2.8,
|
| 807 |
+
"grad_norm": 1.9589757919311523,
|
| 808 |
+
"learning_rate": 2.2005e-05,
|
| 809 |
+
"loss": 0.149,
|
| 810 |
+
"step": 5600
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 2.825,
|
| 814 |
+
"grad_norm": 1.5965051651000977,
|
| 815 |
+
"learning_rate": 2.1755e-05,
|
| 816 |
+
"loss": 0.1826,
|
| 817 |
+
"step": 5650
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 2.85,
|
| 821 |
+
"grad_norm": 1.2711127996444702,
|
| 822 |
+
"learning_rate": 2.1505e-05,
|
| 823 |
+
"loss": 0.1633,
|
| 824 |
+
"step": 5700
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 2.875,
|
| 828 |
+
"grad_norm": 1.6561341285705566,
|
| 829 |
+
"learning_rate": 2.1255e-05,
|
| 830 |
+
"loss": 0.174,
|
| 831 |
+
"step": 5750
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.9,
|
| 835 |
+
"grad_norm": 1.9388906955718994,
|
| 836 |
+
"learning_rate": 2.1005e-05,
|
| 837 |
+
"loss": 0.1692,
|
| 838 |
+
"step": 5800
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 2.925,
|
| 842 |
+
"grad_norm": 2.6603758335113525,
|
| 843 |
+
"learning_rate": 2.0755000000000004e-05,
|
| 844 |
+
"loss": 0.1672,
|
| 845 |
+
"step": 5850
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 2.95,
|
| 849 |
+
"grad_norm": 3.2559964656829834,
|
| 850 |
+
"learning_rate": 2.0505e-05,
|
| 851 |
+
"loss": 0.1757,
|
| 852 |
+
"step": 5900
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 2.975,
|
| 856 |
+
"grad_norm": 1.919048547744751,
|
| 857 |
+
"learning_rate": 2.0255000000000002e-05,
|
| 858 |
+
"loss": 0.1735,
|
| 859 |
+
"step": 5950
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 3.0,
|
| 863 |
+
"grad_norm": 3.5572509765625,
|
| 864 |
+
"learning_rate": 2.0005000000000002e-05,
|
| 865 |
+
"loss": 0.1922,
|
| 866 |
+
"step": 6000
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 3.0,
|
| 870 |
+
"eval_loss": 0.12903086841106415,
|
| 871 |
+
"eval_runtime": 57.4845,
|
| 872 |
+
"eval_samples_per_second": 17.396,
|
| 873 |
+
"eval_steps_per_second": 4.349,
|
| 874 |
+
"step": 6000
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 3.025,
|
| 878 |
+
"grad_norm": 1.5934720039367676,
|
| 879 |
+
"learning_rate": 1.9755e-05,
|
| 880 |
+
"loss": 0.1699,
|
| 881 |
+
"step": 6050
|
| 882 |
+
},
|
| 883 |
+
{
|
| 884 |
+
"epoch": 3.05,
|
| 885 |
+
"grad_norm": 2.1117281913757324,
|
| 886 |
+
"learning_rate": 1.9505e-05,
|
| 887 |
+
"loss": 0.1738,
|
| 888 |
+
"step": 6100
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 3.075,
|
| 892 |
+
"grad_norm": 3.2797703742980957,
|
| 893 |
+
"learning_rate": 1.9255e-05,
|
| 894 |
+
"loss": 0.1694,
|
| 895 |
+
"step": 6150
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"epoch": 3.1,
|
| 899 |
+
"grad_norm": 1.5360231399536133,
|
| 900 |
+
"learning_rate": 1.9005000000000002e-05,
|
| 901 |
+
"loss": 0.1512,
|
| 902 |
+
"step": 6200
|
| 903 |
+
},
|
| 904 |
+
{
|
| 905 |
+
"epoch": 3.125,
|
| 906 |
+
"grad_norm": 1.4587829113006592,
|
| 907 |
+
"learning_rate": 1.8755e-05,
|
| 908 |
+
"loss": 0.1697,
|
| 909 |
+
"step": 6250
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 3.15,
|
| 913 |
+
"grad_norm": 3.891972064971924,
|
| 914 |
+
"learning_rate": 1.8505e-05,
|
| 915 |
+
"loss": 0.1733,
|
| 916 |
+
"step": 6300
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 3.175,
|
| 920 |
+
"grad_norm": 3.0549535751342773,
|
| 921 |
+
"learning_rate": 1.8255e-05,
|
| 922 |
+
"loss": 0.1514,
|
| 923 |
+
"step": 6350
|
| 924 |
+
},
|
| 925 |
+
{
|
| 926 |
+
"epoch": 3.2,
|
| 927 |
+
"grad_norm": 1.4268131256103516,
|
| 928 |
+
"learning_rate": 1.8005e-05,
|
| 929 |
+
"loss": 0.1844,
|
| 930 |
+
"step": 6400
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 3.225,
|
| 934 |
+
"grad_norm": 1.3441020250320435,
|
| 935 |
+
"learning_rate": 1.7755000000000002e-05,
|
| 936 |
+
"loss": 0.1581,
|
| 937 |
+
"step": 6450
|
| 938 |
+
},
|
| 939 |
+
{
|
| 940 |
+
"epoch": 3.25,
|
| 941 |
+
"grad_norm": 1.2834066152572632,
|
| 942 |
+
"learning_rate": 1.7505000000000003e-05,
|
| 943 |
+
"loss": 0.1426,
|
| 944 |
+
"step": 6500
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"epoch": 3.275,
|
| 948 |
+
"grad_norm": 2.298339366912842,
|
| 949 |
+
"learning_rate": 1.7255000000000003e-05,
|
| 950 |
+
"loss": 0.1597,
|
| 951 |
+
"step": 6550
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 3.3,
|
| 955 |
+
"grad_norm": 2.287705659866333,
|
| 956 |
+
"learning_rate": 1.7005e-05,
|
| 957 |
+
"loss": 0.1716,
|
| 958 |
+
"step": 6600
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 3.325,
|
| 962 |
+
"grad_norm": 1.9559084177017212,
|
| 963 |
+
"learning_rate": 1.6755e-05,
|
| 964 |
+
"loss": 0.142,
|
| 965 |
+
"step": 6650
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 3.35,
|
| 969 |
+
"grad_norm": 1.5680958032608032,
|
| 970 |
+
"learning_rate": 1.6505000000000002e-05,
|
| 971 |
+
"loss": 0.1573,
|
| 972 |
+
"step": 6700
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 3.375,
|
| 976 |
+
"grad_norm": 0.831417441368103,
|
| 977 |
+
"learning_rate": 1.6255e-05,
|
| 978 |
+
"loss": 0.1687,
|
| 979 |
+
"step": 6750
|
| 980 |
+
},
|
| 981 |
+
{
|
| 982 |
+
"epoch": 3.4,
|
| 983 |
+
"grad_norm": 2.815106153488159,
|
| 984 |
+
"learning_rate": 1.6005e-05,
|
| 985 |
+
"loss": 0.1577,
|
| 986 |
+
"step": 6800
|
| 987 |
+
},
|
| 988 |
+
{
|
| 989 |
+
"epoch": 3.425,
|
| 990 |
+
"grad_norm": 3.7050323486328125,
|
| 991 |
+
"learning_rate": 1.5755e-05,
|
| 992 |
+
"loss": 0.1719,
|
| 993 |
+
"step": 6850
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 3.45,
|
| 997 |
+
"grad_norm": 2.6608221530914307,
|
| 998 |
+
"learning_rate": 1.5505e-05,
|
| 999 |
+
"loss": 0.1644,
|
| 1000 |
+
"step": 6900
|
| 1001 |
+
},
|
| 1002 |
+
{
|
| 1003 |
+
"epoch": 3.475,
|
| 1004 |
+
"grad_norm": 2.1603200435638428,
|
| 1005 |
+
"learning_rate": 1.5255e-05,
|
| 1006 |
+
"loss": 0.1501,
|
| 1007 |
+
"step": 6950
|
| 1008 |
+
},
|
| 1009 |
+
{
|
| 1010 |
+
"epoch": 3.5,
|
| 1011 |
+
"grad_norm": 5.807039260864258,
|
| 1012 |
+
"learning_rate": 1.5005e-05,
|
| 1013 |
+
"loss": 0.1557,
|
| 1014 |
+
"step": 7000
|
| 1015 |
+
},
|
| 1016 |
+
{
|
| 1017 |
+
"epoch": 3.525,
|
| 1018 |
+
"grad_norm": 2.840177297592163,
|
| 1019 |
+
"learning_rate": 1.4755e-05,
|
| 1020 |
+
"loss": 0.1632,
|
| 1021 |
+
"step": 7050
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 3.55,
|
| 1025 |
+
"grad_norm": 1.3503317832946777,
|
| 1026 |
+
"learning_rate": 1.4505000000000003e-05,
|
| 1027 |
+
"loss": 0.1546,
|
| 1028 |
+
"step": 7100
|
| 1029 |
+
},
|
| 1030 |
+
{
|
| 1031 |
+
"epoch": 3.575,
|
| 1032 |
+
"grad_norm": 2.2482845783233643,
|
| 1033 |
+
"learning_rate": 1.4255000000000002e-05,
|
| 1034 |
+
"loss": 0.1729,
|
| 1035 |
+
"step": 7150
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 3.6,
|
| 1039 |
+
"grad_norm": 2.3148233890533447,
|
| 1040 |
+
"learning_rate": 1.4005000000000002e-05,
|
| 1041 |
+
"loss": 0.1611,
|
| 1042 |
+
"step": 7200
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 3.625,
|
| 1046 |
+
"grad_norm": 1.579547643661499,
|
| 1047 |
+
"learning_rate": 1.3755000000000001e-05,
|
| 1048 |
+
"loss": 0.1448,
|
| 1049 |
+
"step": 7250
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 3.65,
|
| 1053 |
+
"grad_norm": 2.187784433364868,
|
| 1054 |
+
"learning_rate": 1.3505e-05,
|
| 1055 |
+
"loss": 0.1517,
|
| 1056 |
+
"step": 7300
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 3.675,
|
| 1060 |
+
"grad_norm": 2.1139655113220215,
|
| 1061 |
+
"learning_rate": 1.3255000000000001e-05,
|
| 1062 |
+
"loss": 0.1499,
|
| 1063 |
+
"step": 7350
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 3.7,
|
| 1067 |
+
"grad_norm": 2.0396082401275635,
|
| 1068 |
+
"learning_rate": 1.3005e-05,
|
| 1069 |
+
"loss": 0.1669,
|
| 1070 |
+
"step": 7400
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 3.725,
|
| 1074 |
+
"grad_norm": 3.240251064300537,
|
| 1075 |
+
"learning_rate": 1.2755e-05,
|
| 1076 |
+
"loss": 0.154,
|
| 1077 |
+
"step": 7450
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 3.75,
|
| 1081 |
+
"grad_norm": 1.9571031332015991,
|
| 1082 |
+
"learning_rate": 1.2505e-05,
|
| 1083 |
+
"loss": 0.1563,
|
| 1084 |
+
"step": 7500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 3.775,
|
| 1088 |
+
"grad_norm": 3.260962963104248,
|
| 1089 |
+
"learning_rate": 1.2255e-05,
|
| 1090 |
+
"loss": 0.169,
|
| 1091 |
+
"step": 7550
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 3.8,
|
| 1095 |
+
"grad_norm": 1.8954269886016846,
|
| 1096 |
+
"learning_rate": 1.2005000000000001e-05,
|
| 1097 |
+
"loss": 0.157,
|
| 1098 |
+
"step": 7600
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 3.825,
|
| 1102 |
+
"grad_norm": 2.130872964859009,
|
| 1103 |
+
"learning_rate": 1.1755e-05,
|
| 1104 |
+
"loss": 0.1573,
|
| 1105 |
+
"step": 7650
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 3.85,
|
| 1109 |
+
"grad_norm": 2.272871494293213,
|
| 1110 |
+
"learning_rate": 1.1505e-05,
|
| 1111 |
+
"loss": 0.1459,
|
| 1112 |
+
"step": 7700
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 3.875,
|
| 1116 |
+
"grad_norm": 2.3315696716308594,
|
| 1117 |
+
"learning_rate": 1.1255e-05,
|
| 1118 |
+
"loss": 0.1647,
|
| 1119 |
+
"step": 7750
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 3.9,
|
| 1123 |
+
"grad_norm": 1.6526434421539307,
|
| 1124 |
+
"learning_rate": 1.1005e-05,
|
| 1125 |
+
"loss": 0.1436,
|
| 1126 |
+
"step": 7800
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 3.925,
|
| 1130 |
+
"grad_norm": 0.8647462129592896,
|
| 1131 |
+
"learning_rate": 1.0755000000000001e-05,
|
| 1132 |
+
"loss": 0.1579,
|
| 1133 |
+
"step": 7850
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 3.95,
|
| 1137 |
+
"grad_norm": 2.794496774673462,
|
| 1138 |
+
"learning_rate": 1.0505e-05,
|
| 1139 |
+
"loss": 0.17,
|
| 1140 |
+
"step": 7900
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 3.975,
|
| 1144 |
+
"grad_norm": 1.3235639333724976,
|
| 1145 |
+
"learning_rate": 1.0255000000000001e-05,
|
| 1146 |
+
"loss": 0.1565,
|
| 1147 |
+
"step": 7950
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 4.0,
|
| 1151 |
+
"grad_norm": 2.952364206314087,
|
| 1152 |
+
"learning_rate": 1.0005e-05,
|
| 1153 |
+
"loss": 0.1558,
|
| 1154 |
+
"step": 8000
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 4.0,
|
| 1158 |
+
"eval_loss": 0.12239066511392593,
|
| 1159 |
+
"eval_runtime": 65.1197,
|
| 1160 |
+
"eval_samples_per_second": 15.356,
|
| 1161 |
+
"eval_steps_per_second": 3.839,
|
| 1162 |
+
"step": 8000
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 4.025,
|
| 1166 |
+
"grad_norm": 2.830843210220337,
|
| 1167 |
+
"learning_rate": 9.755e-06,
|
| 1168 |
+
"loss": 0.1528,
|
| 1169 |
+
"step": 8050
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 4.05,
|
| 1173 |
+
"grad_norm": 3.2282028198242188,
|
| 1174 |
+
"learning_rate": 9.505e-06,
|
| 1175 |
+
"loss": 0.1545,
|
| 1176 |
+
"step": 8100
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 4.075,
|
| 1180 |
+
"grad_norm": 2.520493268966675,
|
| 1181 |
+
"learning_rate": 9.255e-06,
|
| 1182 |
+
"loss": 0.1643,
|
| 1183 |
+
"step": 8150
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 4.1,
|
| 1187 |
+
"grad_norm": 1.4111956357955933,
|
| 1188 |
+
"learning_rate": 9.005000000000001e-06,
|
| 1189 |
+
"loss": 0.164,
|
| 1190 |
+
"step": 8200
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 4.125,
|
| 1194 |
+
"grad_norm": 2.735272169113159,
|
| 1195 |
+
"learning_rate": 8.755e-06,
|
| 1196 |
+
"loss": 0.1411,
|
| 1197 |
+
"step": 8250
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 4.15,
|
| 1201 |
+
"grad_norm": 1.5018057823181152,
|
| 1202 |
+
"learning_rate": 8.505e-06,
|
| 1203 |
+
"loss": 0.1607,
|
| 1204 |
+
"step": 8300
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 4.175,
|
| 1208 |
+
"grad_norm": 2.3549647331237793,
|
| 1209 |
+
"learning_rate": 8.255e-06,
|
| 1210 |
+
"loss": 0.1589,
|
| 1211 |
+
"step": 8350
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 4.2,
|
| 1215 |
+
"grad_norm": 1.8919823169708252,
|
| 1216 |
+
"learning_rate": 8.005e-06,
|
| 1217 |
+
"loss": 0.1354,
|
| 1218 |
+
"step": 8400
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 4.225,
|
| 1222 |
+
"grad_norm": 1.9286110401153564,
|
| 1223 |
+
"learning_rate": 7.755e-06,
|
| 1224 |
+
"loss": 0.1523,
|
| 1225 |
+
"step": 8450
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 4.25,
|
| 1229 |
+
"grad_norm": 1.6039056777954102,
|
| 1230 |
+
"learning_rate": 7.505000000000001e-06,
|
| 1231 |
+
"loss": 0.141,
|
| 1232 |
+
"step": 8500
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 4.275,
|
| 1236 |
+
"grad_norm": 1.682285189628601,
|
| 1237 |
+
"learning_rate": 7.255000000000001e-06,
|
| 1238 |
+
"loss": 0.1542,
|
| 1239 |
+
"step": 8550
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 4.3,
|
| 1243 |
+
"grad_norm": 2.6263935565948486,
|
| 1244 |
+
"learning_rate": 7.005000000000001e-06,
|
| 1245 |
+
"loss": 0.1622,
|
| 1246 |
+
"step": 8600
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 4.325,
|
| 1250 |
+
"grad_norm": 1.4278345108032227,
|
| 1251 |
+
"learning_rate": 6.7550000000000005e-06,
|
| 1252 |
+
"loss": 0.1381,
|
| 1253 |
+
"step": 8650
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 4.35,
|
| 1257 |
+
"grad_norm": 2.0380184650421143,
|
| 1258 |
+
"learning_rate": 6.505e-06,
|
| 1259 |
+
"loss": 0.1579,
|
| 1260 |
+
"step": 8700
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 4.375,
|
| 1264 |
+
"grad_norm": 2.6025896072387695,
|
| 1265 |
+
"learning_rate": 6.254999999999999e-06,
|
| 1266 |
+
"loss": 0.1742,
|
| 1267 |
+
"step": 8750
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 4.4,
|
| 1271 |
+
"grad_norm": 2.4303677082061768,
|
| 1272 |
+
"learning_rate": 6.005e-06,
|
| 1273 |
+
"loss": 0.139,
|
| 1274 |
+
"step": 8800
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 4.425,
|
| 1278 |
+
"grad_norm": 1.5707917213439941,
|
| 1279 |
+
"learning_rate": 5.755e-06,
|
| 1280 |
+
"loss": 0.1442,
|
| 1281 |
+
"step": 8850
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 4.45,
|
| 1285 |
+
"grad_norm": 3.853732109069824,
|
| 1286 |
+
"learning_rate": 5.505000000000001e-06,
|
| 1287 |
+
"loss": 0.1486,
|
| 1288 |
+
"step": 8900
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 4.475,
|
| 1292 |
+
"grad_norm": 2.794379234313965,
|
| 1293 |
+
"learning_rate": 5.2550000000000005e-06,
|
| 1294 |
+
"loss": 0.1599,
|
| 1295 |
+
"step": 8950
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 4.5,
|
| 1299 |
+
"grad_norm": 1.6828454732894897,
|
| 1300 |
+
"learning_rate": 5.005e-06,
|
| 1301 |
+
"loss": 0.1338,
|
| 1302 |
+
"step": 9000
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 4.525,
|
| 1306 |
+
"grad_norm": 1.348374843597412,
|
| 1307 |
+
"learning_rate": 4.755e-06,
|
| 1308 |
+
"loss": 0.1308,
|
| 1309 |
+
"step": 9050
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 4.55,
|
| 1313 |
+
"grad_norm": 3.534005880355835,
|
| 1314 |
+
"learning_rate": 4.505e-06,
|
| 1315 |
+
"loss": 0.1622,
|
| 1316 |
+
"step": 9100
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 4.575,
|
| 1320 |
+
"grad_norm": 3.5305874347686768,
|
| 1321 |
+
"learning_rate": 4.255e-06,
|
| 1322 |
+
"loss": 0.1527,
|
| 1323 |
+
"step": 9150
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 4.6,
|
| 1327 |
+
"grad_norm": 3.4382681846618652,
|
| 1328 |
+
"learning_rate": 4.005000000000001e-06,
|
| 1329 |
+
"loss": 0.1546,
|
| 1330 |
+
"step": 9200
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 4.625,
|
| 1334 |
+
"grad_norm": 3.7415757179260254,
|
| 1335 |
+
"learning_rate": 3.755e-06,
|
| 1336 |
+
"loss": 0.1595,
|
| 1337 |
+
"step": 9250
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 4.65,
|
| 1341 |
+
"grad_norm": 1.252262830734253,
|
| 1342 |
+
"learning_rate": 3.505e-06,
|
| 1343 |
+
"loss": 0.1273,
|
| 1344 |
+
"step": 9300
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 4.675,
|
| 1348 |
+
"grad_norm": 1.3889789581298828,
|
| 1349 |
+
"learning_rate": 3.2550000000000006e-06,
|
| 1350 |
+
"loss": 0.1519,
|
| 1351 |
+
"step": 9350
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 4.7,
|
| 1355 |
+
"grad_norm": 1.1047695875167847,
|
| 1356 |
+
"learning_rate": 3.005e-06,
|
| 1357 |
+
"loss": 0.1472,
|
| 1358 |
+
"step": 9400
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 4.725,
|
| 1362 |
+
"grad_norm": 1.56324303150177,
|
| 1363 |
+
"learning_rate": 2.7550000000000003e-06,
|
| 1364 |
+
"loss": 0.1217,
|
| 1365 |
+
"step": 9450
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 4.75,
|
| 1369 |
+
"grad_norm": 2.3788673877716064,
|
| 1370 |
+
"learning_rate": 2.505e-06,
|
| 1371 |
+
"loss": 0.1534,
|
| 1372 |
+
"step": 9500
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 4.775,
|
| 1376 |
+
"grad_norm": 1.8210504055023193,
|
| 1377 |
+
"learning_rate": 2.255e-06,
|
| 1378 |
+
"loss": 0.1424,
|
| 1379 |
+
"step": 9550
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 4.8,
|
| 1383 |
+
"grad_norm": 1.365644097328186,
|
| 1384 |
+
"learning_rate": 2.005e-06,
|
| 1385 |
+
"loss": 0.1686,
|
| 1386 |
+
"step": 9600
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 4.825,
|
| 1390 |
+
"grad_norm": 1.9589169025421143,
|
| 1391 |
+
"learning_rate": 1.7550000000000001e-06,
|
| 1392 |
+
"loss": 0.1543,
|
| 1393 |
+
"step": 9650
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 4.85,
|
| 1397 |
+
"grad_norm": 2.8975677490234375,
|
| 1398 |
+
"learning_rate": 1.505e-06,
|
| 1399 |
+
"loss": 0.1449,
|
| 1400 |
+
"step": 9700
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 4.875,
|
| 1404 |
+
"grad_norm": 0.7453130483627319,
|
| 1405 |
+
"learning_rate": 1.255e-06,
|
| 1406 |
+
"loss": 0.1548,
|
| 1407 |
+
"step": 9750
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 4.9,
|
| 1411 |
+
"grad_norm": 1.493669867515564,
|
| 1412 |
+
"learning_rate": 1.0050000000000001e-06,
|
| 1413 |
+
"loss": 0.1537,
|
| 1414 |
+
"step": 9800
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 4.925,
|
| 1418 |
+
"grad_norm": 2.2871060371398926,
|
| 1419 |
+
"learning_rate": 7.550000000000001e-07,
|
| 1420 |
+
"loss": 0.1611,
|
| 1421 |
+
"step": 9850
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 4.95,
|
| 1425 |
+
"grad_norm": 1.1288138628005981,
|
| 1426 |
+
"learning_rate": 5.05e-07,
|
| 1427 |
+
"loss": 0.1619,
|
| 1428 |
+
"step": 9900
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 4.975,
|
| 1432 |
+
"grad_norm": 1.5970274209976196,
|
| 1433 |
+
"learning_rate": 2.5500000000000005e-07,
|
| 1434 |
+
"loss": 0.1349,
|
| 1435 |
+
"step": 9950
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 5.0,
|
| 1439 |
+
"grad_norm": 2.328122615814209,
|
| 1440 |
+
"learning_rate": 5e-09,
|
| 1441 |
+
"loss": 0.1619,
|
| 1442 |
+
"step": 10000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 5.0,
|
| 1446 |
+
"eval_loss": 0.12139008939266205,
|
| 1447 |
+
"eval_runtime": 58.7123,
|
| 1448 |
+
"eval_samples_per_second": 17.032,
|
| 1449 |
+
"eval_steps_per_second": 4.258,
|
| 1450 |
+
"step": 10000
|
| 1451 |
+
}
|
| 1452 |
+
],
|
| 1453 |
+
"logging_steps": 50,
|
| 1454 |
+
"max_steps": 10000,
|
| 1455 |
+
"num_input_tokens_seen": 0,
|
| 1456 |
+
"num_train_epochs": 5,
|
| 1457 |
+
"save_steps": 500,
|
| 1458 |
+
"stateful_callbacks": {
|
| 1459 |
+
"TrainerControl": {
|
| 1460 |
+
"args": {
|
| 1461 |
+
"should_epoch_stop": false,
|
| 1462 |
+
"should_evaluate": false,
|
| 1463 |
+
"should_log": false,
|
| 1464 |
+
"should_save": true,
|
| 1465 |
+
"should_training_stop": true
|
| 1466 |
+
},
|
| 1467 |
+
"attributes": {}
|
| 1468 |
+
}
|
| 1469 |
+
},
|
| 1470 |
+
"total_flos": 338354503680000.0,
|
| 1471 |
+
"train_batch_size": 4,
|
| 1472 |
+
"trial_name": null,
|
| 1473 |
+
"trial_params": null
|
| 1474 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b54d60119a806cb2f8c5ae743c008cbf1bc6e58d913fe99790fdbd9312c6ddb
|
| 3 |
+
size 5713
|