Upload T5 spelling corrector checkpoint from local
Browse files- added_tokens.json +102 -0
- config.json +60 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +125 -0
- spiece.model +3 -0
- tokenizer_config.json +941 -0
- trainer_state.json +3729 -0
- training_args.bin +3 -0
- upload.py +25 -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": 3072,
|
| 7 |
+
"d_kv": 64,
|
| 8 |
+
"d_model": 768,
|
| 9 |
+
"decoder_start_token_id": 0,
|
| 10 |
+
"dense_act_fn": "relu",
|
| 11 |
+
"dropout_rate": 0.1,
|
| 12 |
+
"dtype": "float32",
|
| 13 |
+
"eos_token_id": 1,
|
| 14 |
+
"feed_forward_proj": "relu",
|
| 15 |
+
"initializer_factor": 1.0,
|
| 16 |
+
"is_encoder_decoder": true,
|
| 17 |
+
"is_gated_act": false,
|
| 18 |
+
"layer_norm_epsilon": 1e-06,
|
| 19 |
+
"model_type": "t5",
|
| 20 |
+
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
+
"output_past": true,
|
| 25 |
+
"pad_token_id": 0,
|
| 26 |
+
"relative_attention_max_distance": 128,
|
| 27 |
+
"relative_attention_num_buckets": 32,
|
| 28 |
+
"task_specific_params": {
|
| 29 |
+
"summarization": {
|
| 30 |
+
"early_stopping": true,
|
| 31 |
+
"length_penalty": 2.0,
|
| 32 |
+
"max_length": 200,
|
| 33 |
+
"min_length": 30,
|
| 34 |
+
"no_repeat_ngram_size": 3,
|
| 35 |
+
"num_beams": 4,
|
| 36 |
+
"prefix": "summarize: "
|
| 37 |
+
},
|
| 38 |
+
"translation_en_to_de": {
|
| 39 |
+
"early_stopping": true,
|
| 40 |
+
"max_length": 300,
|
| 41 |
+
"num_beams": 4,
|
| 42 |
+
"prefix": "translate English to German: "
|
| 43 |
+
},
|
| 44 |
+
"translation_en_to_fr": {
|
| 45 |
+
"early_stopping": true,
|
| 46 |
+
"max_length": 300,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"prefix": "translate English to French: "
|
| 49 |
+
},
|
| 50 |
+
"translation_en_to_ro": {
|
| 51 |
+
"early_stopping": true,
|
| 52 |
+
"max_length": 300,
|
| 53 |
+
"num_beams": 4,
|
| 54 |
+
"prefix": "translate English to Romanian: "
|
| 55 |
+
}
|
| 56 |
+
},
|
| 57 |
+
"transformers_version": "4.56.2",
|
| 58 |
+
"use_cache": true,
|
| 59 |
+
"vocab_size": 32128
|
| 60 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"decoder_start_token_id": 0,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
1
|
| 5 |
+
],
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.56.2"
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c8aa3ef4c7676976682613f4ba8e3ea5d6eab4422dc760c6b1816196100fb56
|
| 3 |
+
size 891644712
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74810134dfa66422735b506f52eb0ac6755641d6512c0c9c5e2cecc52d6dd755
|
| 3 |
+
size 1783448843
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27b327dabfb282f32c20a8cc969f7757e3fd968319bbdd4a51288cc959104b94
|
| 3 |
+
size 14645
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cf62c8f7c628278af51e74bf864787afce6064255c8ca15d4994d558e95a752
|
| 3 |
+
size 1383
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8128bd31b2985a3c95d0dc3e72c07aac0ce98ee14f3794ea2b5cfcb6a19689f5
|
| 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": false,
|
| 932 |
+
"eos_token": "</s>",
|
| 933 |
+
"extra_ids": 100,
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
+
"legacy": true,
|
| 936 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 937 |
+
"pad_token": "<pad>",
|
| 938 |
+
"sp_model_kwargs": {},
|
| 939 |
+
"tokenizer_class": "T5Tokenizer",
|
| 940 |
+
"unk_token": "<unk>"
|
| 941 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,3729 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 5000,
|
| 3 |
+
"best_metric": 0.992226148409894,
|
| 4 |
+
"best_model_checkpoint": "./models/t5_spelling_corrector_finetuned_v3/checkpoint-5000",
|
| 5 |
+
"epoch": 50.0,
|
| 6 |
+
"eval_steps": 1000,
|
| 7 |
+
"global_step": 5200,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.09615384615384616,
|
| 14 |
+
"grad_norm": 3.347588539123535,
|
| 15 |
+
"learning_rate": 5.4e-07,
|
| 16 |
+
"loss": 0.6699,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.19230769230769232,
|
| 21 |
+
"grad_norm": 2.8302624225616455,
|
| 22 |
+
"learning_rate": 1.14e-06,
|
| 23 |
+
"loss": 0.5993,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.28846153846153844,
|
| 28 |
+
"grad_norm": 3.3392577171325684,
|
| 29 |
+
"learning_rate": 1.74e-06,
|
| 30 |
+
"loss": 0.564,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.38461538461538464,
|
| 35 |
+
"grad_norm": 3.260563611984253,
|
| 36 |
+
"learning_rate": 2.34e-06,
|
| 37 |
+
"loss": 0.5126,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.4807692307692308,
|
| 42 |
+
"grad_norm": 2.92582631111145,
|
| 43 |
+
"learning_rate": 2.9400000000000002e-06,
|
| 44 |
+
"loss": 0.4923,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.5769230769230769,
|
| 49 |
+
"grad_norm": 2.35099720954895,
|
| 50 |
+
"learning_rate": 3.54e-06,
|
| 51 |
+
"loss": 0.4266,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.6730769230769231,
|
| 56 |
+
"grad_norm": 2.393505334854126,
|
| 57 |
+
"learning_rate": 4.14e-06,
|
| 58 |
+
"loss": 0.3655,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.7692307692307693,
|
| 63 |
+
"grad_norm": 1.5848568677902222,
|
| 64 |
+
"learning_rate": 4.74e-06,
|
| 65 |
+
"loss": 0.3313,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.8653846153846154,
|
| 70 |
+
"grad_norm": 1.625791072845459,
|
| 71 |
+
"learning_rate": 5.34e-06,
|
| 72 |
+
"loss": 0.2682,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.9615384615384616,
|
| 77 |
+
"grad_norm": 1.9399585723876953,
|
| 78 |
+
"learning_rate": 5.940000000000001e-06,
|
| 79 |
+
"loss": 0.2452,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0576923076923077,
|
| 84 |
+
"grad_norm": 1.909173607826233,
|
| 85 |
+
"learning_rate": 6.54e-06,
|
| 86 |
+
"loss": 0.2577,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.1538461538461537,
|
| 91 |
+
"grad_norm": 1.0260469913482666,
|
| 92 |
+
"learning_rate": 7.14e-06,
|
| 93 |
+
"loss": 0.1986,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.25,
|
| 98 |
+
"grad_norm": 1.2334129810333252,
|
| 99 |
+
"learning_rate": 7.74e-06,
|
| 100 |
+
"loss": 0.1966,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.3461538461538463,
|
| 105 |
+
"grad_norm": 1.1841124296188354,
|
| 106 |
+
"learning_rate": 8.340000000000001e-06,
|
| 107 |
+
"loss": 0.1764,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.4423076923076923,
|
| 112 |
+
"grad_norm": 1.069820523262024,
|
| 113 |
+
"learning_rate": 8.939999999999999e-06,
|
| 114 |
+
"loss": 0.172,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.5384615384615383,
|
| 119 |
+
"grad_norm": 0.9867880344390869,
|
| 120 |
+
"learning_rate": 9.54e-06,
|
| 121 |
+
"loss": 0.1585,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.6346153846153846,
|
| 126 |
+
"grad_norm": 1.1286975145339966,
|
| 127 |
+
"learning_rate": 1.0140000000000001e-05,
|
| 128 |
+
"loss": 0.1385,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 1.7307692307692308,
|
| 133 |
+
"grad_norm": 1.0937390327453613,
|
| 134 |
+
"learning_rate": 1.074e-05,
|
| 135 |
+
"loss": 0.1412,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.8269230769230769,
|
| 140 |
+
"grad_norm": 1.139171838760376,
|
| 141 |
+
"learning_rate": 1.134e-05,
|
| 142 |
+
"loss": 0.1217,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.9230769230769231,
|
| 147 |
+
"grad_norm": 0.9474167227745056,
|
| 148 |
+
"learning_rate": 1.1940000000000001e-05,
|
| 149 |
+
"loss": 0.13,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 2.019230769230769,
|
| 154 |
+
"grad_norm": 0.8131914138793945,
|
| 155 |
+
"learning_rate": 1.254e-05,
|
| 156 |
+
"loss": 0.1128,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 2.1153846153846154,
|
| 161 |
+
"grad_norm": 1.041396975517273,
|
| 162 |
+
"learning_rate": 1.314e-05,
|
| 163 |
+
"loss": 0.1158,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 2.2115384615384617,
|
| 168 |
+
"grad_norm": 0.9056050777435303,
|
| 169 |
+
"learning_rate": 1.374e-05,
|
| 170 |
+
"loss": 0.1131,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 2.3076923076923075,
|
| 175 |
+
"grad_norm": 0.8580456972122192,
|
| 176 |
+
"learning_rate": 1.434e-05,
|
| 177 |
+
"loss": 0.1107,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 2.4038461538461537,
|
| 182 |
+
"grad_norm": 1.473669409751892,
|
| 183 |
+
"learning_rate": 1.4940000000000001e-05,
|
| 184 |
+
"loss": 0.1127,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 2.5,
|
| 189 |
+
"grad_norm": 0.9101526141166687,
|
| 190 |
+
"learning_rate": 1.554e-05,
|
| 191 |
+
"loss": 0.1022,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 2.5961538461538463,
|
| 196 |
+
"grad_norm": 0.8412496447563171,
|
| 197 |
+
"learning_rate": 1.614e-05,
|
| 198 |
+
"loss": 0.1023,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 2.6923076923076925,
|
| 203 |
+
"grad_norm": 1.4617328643798828,
|
| 204 |
+
"learning_rate": 1.6740000000000002e-05,
|
| 205 |
+
"loss": 0.0978,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.7884615384615383,
|
| 210 |
+
"grad_norm": 1.095248818397522,
|
| 211 |
+
"learning_rate": 1.734e-05,
|
| 212 |
+
"loss": 0.0946,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 2.8846153846153846,
|
| 217 |
+
"grad_norm": 0.5798925757408142,
|
| 218 |
+
"learning_rate": 1.794e-05,
|
| 219 |
+
"loss": 0.0916,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 2.980769230769231,
|
| 224 |
+
"grad_norm": 0.708819568157196,
|
| 225 |
+
"learning_rate": 1.854e-05,
|
| 226 |
+
"loss": 0.0866,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.076923076923077,
|
| 231 |
+
"grad_norm": 0.47592493891716003,
|
| 232 |
+
"learning_rate": 1.914e-05,
|
| 233 |
+
"loss": 0.0742,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 3.173076923076923,
|
| 238 |
+
"grad_norm": 1.1844018697738647,
|
| 239 |
+
"learning_rate": 1.974e-05,
|
| 240 |
+
"loss": 0.0974,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 3.269230769230769,
|
| 245 |
+
"grad_norm": 0.6659021973609924,
|
| 246 |
+
"learning_rate": 2.0340000000000002e-05,
|
| 247 |
+
"loss": 0.071,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 3.3653846153846154,
|
| 252 |
+
"grad_norm": 0.8126431107521057,
|
| 253 |
+
"learning_rate": 2.094e-05,
|
| 254 |
+
"loss": 0.0718,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 3.4615384615384617,
|
| 259 |
+
"grad_norm": 0.6788111925125122,
|
| 260 |
+
"learning_rate": 2.154e-05,
|
| 261 |
+
"loss": 0.0801,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 3.5576923076923075,
|
| 266 |
+
"grad_norm": 0.8465282917022705,
|
| 267 |
+
"learning_rate": 2.214e-05,
|
| 268 |
+
"loss": 0.0696,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 3.6538461538461537,
|
| 273 |
+
"grad_norm": 0.6793688535690308,
|
| 274 |
+
"learning_rate": 2.274e-05,
|
| 275 |
+
"loss": 0.0806,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 3.75,
|
| 280 |
+
"grad_norm": 0.7204192876815796,
|
| 281 |
+
"learning_rate": 2.334e-05,
|
| 282 |
+
"loss": 0.0604,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 3.8461538461538463,
|
| 287 |
+
"grad_norm": 0.5197739601135254,
|
| 288 |
+
"learning_rate": 2.394e-05,
|
| 289 |
+
"loss": 0.0696,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 3.9423076923076925,
|
| 294 |
+
"grad_norm": 0.5837198495864868,
|
| 295 |
+
"learning_rate": 2.454e-05,
|
| 296 |
+
"loss": 0.0675,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 4.038461538461538,
|
| 301 |
+
"grad_norm": 0.6246194243431091,
|
| 302 |
+
"learning_rate": 2.514e-05,
|
| 303 |
+
"loss": 0.0585,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 4.134615384615385,
|
| 308 |
+
"grad_norm": 0.8931935429573059,
|
| 309 |
+
"learning_rate": 2.574e-05,
|
| 310 |
+
"loss": 0.0626,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 4.230769230769231,
|
| 315 |
+
"grad_norm": 0.8182059526443481,
|
| 316 |
+
"learning_rate": 2.6340000000000002e-05,
|
| 317 |
+
"loss": 0.0574,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 4.326923076923077,
|
| 322 |
+
"grad_norm": 0.6059229373931885,
|
| 323 |
+
"learning_rate": 2.6940000000000003e-05,
|
| 324 |
+
"loss": 0.0571,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 4.423076923076923,
|
| 329 |
+
"grad_norm": 0.7983167171478271,
|
| 330 |
+
"learning_rate": 2.754e-05,
|
| 331 |
+
"loss": 0.051,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 4.519230769230769,
|
| 336 |
+
"grad_norm": 1.0164097547531128,
|
| 337 |
+
"learning_rate": 2.8139999999999998e-05,
|
| 338 |
+
"loss": 0.0487,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 4.615384615384615,
|
| 343 |
+
"grad_norm": 0.7057549357414246,
|
| 344 |
+
"learning_rate": 2.874e-05,
|
| 345 |
+
"loss": 0.0587,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 4.711538461538462,
|
| 350 |
+
"grad_norm": 1.007047176361084,
|
| 351 |
+
"learning_rate": 2.934e-05,
|
| 352 |
+
"loss": 0.0545,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 4.8076923076923075,
|
| 357 |
+
"grad_norm": 0.9160193204879761,
|
| 358 |
+
"learning_rate": 2.994e-05,
|
| 359 |
+
"loss": 0.05,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 4.903846153846154,
|
| 364 |
+
"grad_norm": 0.9796598553657532,
|
| 365 |
+
"learning_rate": 2.9942553191489364e-05,
|
| 366 |
+
"loss": 0.0556,
|
| 367 |
+
"step": 510
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 5.0,
|
| 371 |
+
"grad_norm": 1.1414951086044312,
|
| 372 |
+
"learning_rate": 2.987872340425532e-05,
|
| 373 |
+
"loss": 0.05,
|
| 374 |
+
"step": 520
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 5.096153846153846,
|
| 378 |
+
"grad_norm": 0.4623892605304718,
|
| 379 |
+
"learning_rate": 2.9814893617021278e-05,
|
| 380 |
+
"loss": 0.0502,
|
| 381 |
+
"step": 530
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 5.1923076923076925,
|
| 385 |
+
"grad_norm": 0.6435359120368958,
|
| 386 |
+
"learning_rate": 2.9751063829787234e-05,
|
| 387 |
+
"loss": 0.045,
|
| 388 |
+
"step": 540
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 5.288461538461538,
|
| 392 |
+
"grad_norm": 1.070151925086975,
|
| 393 |
+
"learning_rate": 2.9687234042553193e-05,
|
| 394 |
+
"loss": 0.0499,
|
| 395 |
+
"step": 550
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 5.384615384615385,
|
| 399 |
+
"grad_norm": 0.5936897993087769,
|
| 400 |
+
"learning_rate": 2.962340425531915e-05,
|
| 401 |
+
"loss": 0.0519,
|
| 402 |
+
"step": 560
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 5.480769230769231,
|
| 406 |
+
"grad_norm": 0.47224923968315125,
|
| 407 |
+
"learning_rate": 2.9559574468085107e-05,
|
| 408 |
+
"loss": 0.0485,
|
| 409 |
+
"step": 570
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 5.576923076923077,
|
| 413 |
+
"grad_norm": 0.8727656602859497,
|
| 414 |
+
"learning_rate": 2.9495744680851063e-05,
|
| 415 |
+
"loss": 0.043,
|
| 416 |
+
"step": 580
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 5.673076923076923,
|
| 420 |
+
"grad_norm": 1.1207246780395508,
|
| 421 |
+
"learning_rate": 2.9431914893617022e-05,
|
| 422 |
+
"loss": 0.0408,
|
| 423 |
+
"step": 590
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 5.769230769230769,
|
| 427 |
+
"grad_norm": 0.4979076683521271,
|
| 428 |
+
"learning_rate": 2.9368085106382978e-05,
|
| 429 |
+
"loss": 0.0419,
|
| 430 |
+
"step": 600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 5.865384615384615,
|
| 434 |
+
"grad_norm": 0.6043898463249207,
|
| 435 |
+
"learning_rate": 2.9304255319148937e-05,
|
| 436 |
+
"loss": 0.0445,
|
| 437 |
+
"step": 610
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 5.961538461538462,
|
| 441 |
+
"grad_norm": 0.8977653384208679,
|
| 442 |
+
"learning_rate": 2.9240425531914892e-05,
|
| 443 |
+
"loss": 0.0456,
|
| 444 |
+
"step": 620
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 6.0576923076923075,
|
| 448 |
+
"grad_norm": 0.44534873962402344,
|
| 449 |
+
"learning_rate": 2.917659574468085e-05,
|
| 450 |
+
"loss": 0.0368,
|
| 451 |
+
"step": 630
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 6.153846153846154,
|
| 455 |
+
"grad_norm": 1.2936347723007202,
|
| 456 |
+
"learning_rate": 2.911276595744681e-05,
|
| 457 |
+
"loss": 0.0373,
|
| 458 |
+
"step": 640
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 6.25,
|
| 462 |
+
"grad_norm": 0.6867542862892151,
|
| 463 |
+
"learning_rate": 2.9048936170212766e-05,
|
| 464 |
+
"loss": 0.0355,
|
| 465 |
+
"step": 650
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 6.346153846153846,
|
| 469 |
+
"grad_norm": 0.8258110880851746,
|
| 470 |
+
"learning_rate": 2.8985106382978725e-05,
|
| 471 |
+
"loss": 0.0389,
|
| 472 |
+
"step": 660
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 6.4423076923076925,
|
| 476 |
+
"grad_norm": 0.42925509810447693,
|
| 477 |
+
"learning_rate": 2.892127659574468e-05,
|
| 478 |
+
"loss": 0.0353,
|
| 479 |
+
"step": 670
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 6.538461538461538,
|
| 483 |
+
"grad_norm": 0.9368314146995544,
|
| 484 |
+
"learning_rate": 2.885744680851064e-05,
|
| 485 |
+
"loss": 0.0378,
|
| 486 |
+
"step": 680
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 6.634615384615385,
|
| 490 |
+
"grad_norm": 0.5876572132110596,
|
| 491 |
+
"learning_rate": 2.8793617021276595e-05,
|
| 492 |
+
"loss": 0.0329,
|
| 493 |
+
"step": 690
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 6.730769230769231,
|
| 497 |
+
"grad_norm": 0.6402647495269775,
|
| 498 |
+
"learning_rate": 2.8729787234042554e-05,
|
| 499 |
+
"loss": 0.027,
|
| 500 |
+
"step": 700
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 6.826923076923077,
|
| 504 |
+
"grad_norm": 0.5723885297775269,
|
| 505 |
+
"learning_rate": 2.866595744680851e-05,
|
| 506 |
+
"loss": 0.0327,
|
| 507 |
+
"step": 710
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 6.923076923076923,
|
| 511 |
+
"grad_norm": 0.4314801096916199,
|
| 512 |
+
"learning_rate": 2.860212765957447e-05,
|
| 513 |
+
"loss": 0.0331,
|
| 514 |
+
"step": 720
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 7.019230769230769,
|
| 518 |
+
"grad_norm": 0.5018507838249207,
|
| 519 |
+
"learning_rate": 2.8538297872340424e-05,
|
| 520 |
+
"loss": 0.0351,
|
| 521 |
+
"step": 730
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 7.115384615384615,
|
| 525 |
+
"grad_norm": 0.49081480503082275,
|
| 526 |
+
"learning_rate": 2.8474468085106383e-05,
|
| 527 |
+
"loss": 0.0308,
|
| 528 |
+
"step": 740
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 7.211538461538462,
|
| 532 |
+
"grad_norm": 0.7369358539581299,
|
| 533 |
+
"learning_rate": 2.841063829787234e-05,
|
| 534 |
+
"loss": 0.0276,
|
| 535 |
+
"step": 750
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 7.3076923076923075,
|
| 539 |
+
"grad_norm": 0.49376147985458374,
|
| 540 |
+
"learning_rate": 2.8346808510638298e-05,
|
| 541 |
+
"loss": 0.0323,
|
| 542 |
+
"step": 760
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 7.403846153846154,
|
| 546 |
+
"grad_norm": 0.7800844311714172,
|
| 547 |
+
"learning_rate": 2.8282978723404253e-05,
|
| 548 |
+
"loss": 0.0287,
|
| 549 |
+
"step": 770
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 7.5,
|
| 553 |
+
"grad_norm": 0.9613171815872192,
|
| 554 |
+
"learning_rate": 2.8219148936170212e-05,
|
| 555 |
+
"loss": 0.0279,
|
| 556 |
+
"step": 780
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 7.596153846153846,
|
| 560 |
+
"grad_norm": 1.0874011516571045,
|
| 561 |
+
"learning_rate": 2.8155319148936168e-05,
|
| 562 |
+
"loss": 0.0371,
|
| 563 |
+
"step": 790
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 7.6923076923076925,
|
| 567 |
+
"grad_norm": 0.3330044746398926,
|
| 568 |
+
"learning_rate": 2.8091489361702127e-05,
|
| 569 |
+
"loss": 0.0283,
|
| 570 |
+
"step": 800
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 7.788461538461538,
|
| 574 |
+
"grad_norm": 1.4728511571884155,
|
| 575 |
+
"learning_rate": 2.8027659574468086e-05,
|
| 576 |
+
"loss": 0.0325,
|
| 577 |
+
"step": 810
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 7.884615384615385,
|
| 581 |
+
"grad_norm": 1.2733508348464966,
|
| 582 |
+
"learning_rate": 2.796382978723404e-05,
|
| 583 |
+
"loss": 0.0257,
|
| 584 |
+
"step": 820
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 7.980769230769231,
|
| 588 |
+
"grad_norm": 0.6438696980476379,
|
| 589 |
+
"learning_rate": 2.79e-05,
|
| 590 |
+
"loss": 0.0312,
|
| 591 |
+
"step": 830
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 8.076923076923077,
|
| 595 |
+
"grad_norm": 0.6629941463470459,
|
| 596 |
+
"learning_rate": 2.783617021276596e-05,
|
| 597 |
+
"loss": 0.0298,
|
| 598 |
+
"step": 840
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 8.173076923076923,
|
| 602 |
+
"grad_norm": 0.3993019461631775,
|
| 603 |
+
"learning_rate": 2.777234042553192e-05,
|
| 604 |
+
"loss": 0.0325,
|
| 605 |
+
"step": 850
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 8.26923076923077,
|
| 609 |
+
"grad_norm": 0.6544252634048462,
|
| 610 |
+
"learning_rate": 2.7708510638297874e-05,
|
| 611 |
+
"loss": 0.0271,
|
| 612 |
+
"step": 860
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 8.365384615384615,
|
| 616 |
+
"grad_norm": 0.581778883934021,
|
| 617 |
+
"learning_rate": 2.7644680851063833e-05,
|
| 618 |
+
"loss": 0.0287,
|
| 619 |
+
"step": 870
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 8.461538461538462,
|
| 623 |
+
"grad_norm": 0.7206617593765259,
|
| 624 |
+
"learning_rate": 2.758085106382979e-05,
|
| 625 |
+
"loss": 0.0243,
|
| 626 |
+
"step": 880
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 8.557692307692308,
|
| 630 |
+
"grad_norm": 0.7053912878036499,
|
| 631 |
+
"learning_rate": 2.7517021276595748e-05,
|
| 632 |
+
"loss": 0.0257,
|
| 633 |
+
"step": 890
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 8.653846153846153,
|
| 637 |
+
"grad_norm": 0.9742723107337952,
|
| 638 |
+
"learning_rate": 2.7453191489361703e-05,
|
| 639 |
+
"loss": 0.0256,
|
| 640 |
+
"step": 900
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 8.75,
|
| 644 |
+
"grad_norm": 1.0441752672195435,
|
| 645 |
+
"learning_rate": 2.7389361702127662e-05,
|
| 646 |
+
"loss": 0.0273,
|
| 647 |
+
"step": 910
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 8.846153846153847,
|
| 651 |
+
"grad_norm": 0.571890115737915,
|
| 652 |
+
"learning_rate": 2.7325531914893618e-05,
|
| 653 |
+
"loss": 0.0218,
|
| 654 |
+
"step": 920
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 8.942307692307692,
|
| 658 |
+
"grad_norm": 0.6239679455757141,
|
| 659 |
+
"learning_rate": 2.7261702127659577e-05,
|
| 660 |
+
"loss": 0.0266,
|
| 661 |
+
"step": 930
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 9.038461538461538,
|
| 665 |
+
"grad_norm": 0.6254406571388245,
|
| 666 |
+
"learning_rate": 2.7197872340425533e-05,
|
| 667 |
+
"loss": 0.0207,
|
| 668 |
+
"step": 940
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 9.134615384615385,
|
| 672 |
+
"grad_norm": 0.4847211241722107,
|
| 673 |
+
"learning_rate": 2.713404255319149e-05,
|
| 674 |
+
"loss": 0.0285,
|
| 675 |
+
"step": 950
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 9.23076923076923,
|
| 679 |
+
"grad_norm": 0.7274488806724548,
|
| 680 |
+
"learning_rate": 2.7070212765957447e-05,
|
| 681 |
+
"loss": 0.0233,
|
| 682 |
+
"step": 960
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 9.326923076923077,
|
| 686 |
+
"grad_norm": 0.5963655710220337,
|
| 687 |
+
"learning_rate": 2.7006382978723406e-05,
|
| 688 |
+
"loss": 0.023,
|
| 689 |
+
"step": 970
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 9.423076923076923,
|
| 693 |
+
"grad_norm": 0.4576031267642975,
|
| 694 |
+
"learning_rate": 2.6942553191489362e-05,
|
| 695 |
+
"loss": 0.0241,
|
| 696 |
+
"step": 980
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 9.51923076923077,
|
| 700 |
+
"grad_norm": 0.38139963150024414,
|
| 701 |
+
"learning_rate": 2.687872340425532e-05,
|
| 702 |
+
"loss": 0.0251,
|
| 703 |
+
"step": 990
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 9.615384615384615,
|
| 707 |
+
"grad_norm": 0.4351661801338196,
|
| 708 |
+
"learning_rate": 2.681489361702128e-05,
|
| 709 |
+
"loss": 0.0288,
|
| 710 |
+
"step": 1000
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 9.615384615384615,
|
| 714 |
+
"eval_correct_predictions": 1324,
|
| 715 |
+
"eval_exact_match_accuracy": 0.9356890459363958,
|
| 716 |
+
"eval_loss": 0.018085243180394173,
|
| 717 |
+
"eval_runtime": 67.218,
|
| 718 |
+
"eval_samples_per_second": 21.051,
|
| 719 |
+
"eval_steps_per_second": 0.342,
|
| 720 |
+
"eval_total_predictions": 1415,
|
| 721 |
+
"step": 1000
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"epoch": 9.711538461538462,
|
| 725 |
+
"grad_norm": 1.3073899745941162,
|
| 726 |
+
"learning_rate": 2.6751063829787235e-05,
|
| 727 |
+
"loss": 0.0228,
|
| 728 |
+
"step": 1010
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 9.807692307692308,
|
| 732 |
+
"grad_norm": 0.844657838344574,
|
| 733 |
+
"learning_rate": 2.6687234042553194e-05,
|
| 734 |
+
"loss": 0.0224,
|
| 735 |
+
"step": 1020
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 9.903846153846153,
|
| 739 |
+
"grad_norm": 0.7185432314872742,
|
| 740 |
+
"learning_rate": 2.662340425531915e-05,
|
| 741 |
+
"loss": 0.0196,
|
| 742 |
+
"step": 1030
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 10.0,
|
| 746 |
+
"grad_norm": 1.6467353105545044,
|
| 747 |
+
"learning_rate": 2.655957446808511e-05,
|
| 748 |
+
"loss": 0.0223,
|
| 749 |
+
"step": 1040
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 10.096153846153847,
|
| 753 |
+
"grad_norm": 0.581244945526123,
|
| 754 |
+
"learning_rate": 2.6495744680851065e-05,
|
| 755 |
+
"loss": 0.0212,
|
| 756 |
+
"step": 1050
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 10.192307692307692,
|
| 760 |
+
"grad_norm": 0.8405095338821411,
|
| 761 |
+
"learning_rate": 2.6431914893617024e-05,
|
| 762 |
+
"loss": 0.0247,
|
| 763 |
+
"step": 1060
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 10.288461538461538,
|
| 767 |
+
"grad_norm": 0.7707756757736206,
|
| 768 |
+
"learning_rate": 2.636808510638298e-05,
|
| 769 |
+
"loss": 0.0183,
|
| 770 |
+
"step": 1070
|
| 771 |
+
},
|
| 772 |
+
{
|
| 773 |
+
"epoch": 10.384615384615385,
|
| 774 |
+
"grad_norm": 0.5692296624183655,
|
| 775 |
+
"learning_rate": 2.6304255319148938e-05,
|
| 776 |
+
"loss": 0.0221,
|
| 777 |
+
"step": 1080
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 10.48076923076923,
|
| 781 |
+
"grad_norm": 0.2527153789997101,
|
| 782 |
+
"learning_rate": 2.6240425531914894e-05,
|
| 783 |
+
"loss": 0.0228,
|
| 784 |
+
"step": 1090
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 10.576923076923077,
|
| 788 |
+
"grad_norm": 0.6079349517822266,
|
| 789 |
+
"learning_rate": 2.6176595744680853e-05,
|
| 790 |
+
"loss": 0.0223,
|
| 791 |
+
"step": 1100
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 10.673076923076923,
|
| 795 |
+
"grad_norm": 0.43173831701278687,
|
| 796 |
+
"learning_rate": 2.611276595744681e-05,
|
| 797 |
+
"loss": 0.017,
|
| 798 |
+
"step": 1110
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 10.76923076923077,
|
| 802 |
+
"grad_norm": 0.5763304829597473,
|
| 803 |
+
"learning_rate": 2.6048936170212767e-05,
|
| 804 |
+
"loss": 0.0183,
|
| 805 |
+
"step": 1120
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 10.865384615384615,
|
| 809 |
+
"grad_norm": 0.5463092923164368,
|
| 810 |
+
"learning_rate": 2.5985106382978723e-05,
|
| 811 |
+
"loss": 0.0197,
|
| 812 |
+
"step": 1130
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 10.961538461538462,
|
| 816 |
+
"grad_norm": 1.0987874269485474,
|
| 817 |
+
"learning_rate": 2.5921276595744682e-05,
|
| 818 |
+
"loss": 0.0201,
|
| 819 |
+
"step": 1140
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 11.057692307692308,
|
| 823 |
+
"grad_norm": 0.25165650248527527,
|
| 824 |
+
"learning_rate": 2.5857446808510638e-05,
|
| 825 |
+
"loss": 0.0154,
|
| 826 |
+
"step": 1150
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 11.153846153846153,
|
| 830 |
+
"grad_norm": 0.8446175456047058,
|
| 831 |
+
"learning_rate": 2.5793617021276597e-05,
|
| 832 |
+
"loss": 0.0189,
|
| 833 |
+
"step": 1160
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 11.25,
|
| 837 |
+
"grad_norm": 0.597083568572998,
|
| 838 |
+
"learning_rate": 2.5729787234042556e-05,
|
| 839 |
+
"loss": 0.0169,
|
| 840 |
+
"step": 1170
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 11.346153846153847,
|
| 844 |
+
"grad_norm": 0.5754260420799255,
|
| 845 |
+
"learning_rate": 2.566595744680851e-05,
|
| 846 |
+
"loss": 0.0179,
|
| 847 |
+
"step": 1180
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 11.442307692307692,
|
| 851 |
+
"grad_norm": 0.3986382782459259,
|
| 852 |
+
"learning_rate": 2.560212765957447e-05,
|
| 853 |
+
"loss": 0.0187,
|
| 854 |
+
"step": 1190
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 11.538461538461538,
|
| 858 |
+
"grad_norm": 0.649178147315979,
|
| 859 |
+
"learning_rate": 2.5538297872340426e-05,
|
| 860 |
+
"loss": 0.019,
|
| 861 |
+
"step": 1200
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 11.634615384615385,
|
| 865 |
+
"grad_norm": 0.5855590105056763,
|
| 866 |
+
"learning_rate": 2.5474468085106385e-05,
|
| 867 |
+
"loss": 0.0179,
|
| 868 |
+
"step": 1210
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 11.73076923076923,
|
| 872 |
+
"grad_norm": 0.7554678916931152,
|
| 873 |
+
"learning_rate": 2.541063829787234e-05,
|
| 874 |
+
"loss": 0.018,
|
| 875 |
+
"step": 1220
|
| 876 |
+
},
|
| 877 |
+
{
|
| 878 |
+
"epoch": 11.826923076923077,
|
| 879 |
+
"grad_norm": 0.417162150144577,
|
| 880 |
+
"learning_rate": 2.53468085106383e-05,
|
| 881 |
+
"loss": 0.0244,
|
| 882 |
+
"step": 1230
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 11.923076923076923,
|
| 886 |
+
"grad_norm": 1.6350237131118774,
|
| 887 |
+
"learning_rate": 2.5282978723404255e-05,
|
| 888 |
+
"loss": 0.0207,
|
| 889 |
+
"step": 1240
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"epoch": 12.01923076923077,
|
| 893 |
+
"grad_norm": 0.41877123713493347,
|
| 894 |
+
"learning_rate": 2.5219148936170214e-05,
|
| 895 |
+
"loss": 0.019,
|
| 896 |
+
"step": 1250
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 12.115384615384615,
|
| 900 |
+
"grad_norm": 0.48958903551101685,
|
| 901 |
+
"learning_rate": 2.515531914893617e-05,
|
| 902 |
+
"loss": 0.0172,
|
| 903 |
+
"step": 1260
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 12.211538461538462,
|
| 907 |
+
"grad_norm": 0.8494559526443481,
|
| 908 |
+
"learning_rate": 2.509148936170213e-05,
|
| 909 |
+
"loss": 0.0177,
|
| 910 |
+
"step": 1270
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 12.307692307692308,
|
| 914 |
+
"grad_norm": 0.31908470392227173,
|
| 915 |
+
"learning_rate": 2.5027659574468084e-05,
|
| 916 |
+
"loss": 0.0145,
|
| 917 |
+
"step": 1280
|
| 918 |
+
},
|
| 919 |
+
{
|
| 920 |
+
"epoch": 12.403846153846153,
|
| 921 |
+
"grad_norm": 1.0067028999328613,
|
| 922 |
+
"learning_rate": 2.4963829787234043e-05,
|
| 923 |
+
"loss": 0.0245,
|
| 924 |
+
"step": 1290
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 12.5,
|
| 928 |
+
"grad_norm": 0.999679684638977,
|
| 929 |
+
"learning_rate": 2.49e-05,
|
| 930 |
+
"loss": 0.0151,
|
| 931 |
+
"step": 1300
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"epoch": 12.596153846153847,
|
| 935 |
+
"grad_norm": 1.5106195211410522,
|
| 936 |
+
"learning_rate": 2.4836170212765958e-05,
|
| 937 |
+
"loss": 0.014,
|
| 938 |
+
"step": 1310
|
| 939 |
+
},
|
| 940 |
+
{
|
| 941 |
+
"epoch": 12.692307692307692,
|
| 942 |
+
"grad_norm": 0.810861349105835,
|
| 943 |
+
"learning_rate": 2.4772340425531913e-05,
|
| 944 |
+
"loss": 0.0179,
|
| 945 |
+
"step": 1320
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 12.788461538461538,
|
| 949 |
+
"grad_norm": 0.45111358165740967,
|
| 950 |
+
"learning_rate": 2.4708510638297872e-05,
|
| 951 |
+
"loss": 0.0128,
|
| 952 |
+
"step": 1330
|
| 953 |
+
},
|
| 954 |
+
{
|
| 955 |
+
"epoch": 12.884615384615385,
|
| 956 |
+
"grad_norm": 0.6044699549674988,
|
| 957 |
+
"learning_rate": 2.4644680851063828e-05,
|
| 958 |
+
"loss": 0.0195,
|
| 959 |
+
"step": 1340
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 12.98076923076923,
|
| 963 |
+
"grad_norm": 0.5198887586593628,
|
| 964 |
+
"learning_rate": 2.4580851063829787e-05,
|
| 965 |
+
"loss": 0.0154,
|
| 966 |
+
"step": 1350
|
| 967 |
+
},
|
| 968 |
+
{
|
| 969 |
+
"epoch": 13.076923076923077,
|
| 970 |
+
"grad_norm": 0.7923489809036255,
|
| 971 |
+
"learning_rate": 2.4517021276595746e-05,
|
| 972 |
+
"loss": 0.0155,
|
| 973 |
+
"step": 1360
|
| 974 |
+
},
|
| 975 |
+
{
|
| 976 |
+
"epoch": 13.173076923076923,
|
| 977 |
+
"grad_norm": 0.6800804734230042,
|
| 978 |
+
"learning_rate": 2.44531914893617e-05,
|
| 979 |
+
"loss": 0.0144,
|
| 980 |
+
"step": 1370
|
| 981 |
+
},
|
| 982 |
+
{
|
| 983 |
+
"epoch": 13.26923076923077,
|
| 984 |
+
"grad_norm": 0.8769320845603943,
|
| 985 |
+
"learning_rate": 2.438936170212766e-05,
|
| 986 |
+
"loss": 0.0142,
|
| 987 |
+
"step": 1380
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 13.365384615384615,
|
| 991 |
+
"grad_norm": 0.14133420586585999,
|
| 992 |
+
"learning_rate": 2.4325531914893616e-05,
|
| 993 |
+
"loss": 0.0137,
|
| 994 |
+
"step": 1390
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 13.461538461538462,
|
| 998 |
+
"grad_norm": 0.7058908343315125,
|
| 999 |
+
"learning_rate": 2.4261702127659575e-05,
|
| 1000 |
+
"loss": 0.0206,
|
| 1001 |
+
"step": 1400
|
| 1002 |
+
},
|
| 1003 |
+
{
|
| 1004 |
+
"epoch": 13.557692307692308,
|
| 1005 |
+
"grad_norm": 0.4690243899822235,
|
| 1006 |
+
"learning_rate": 2.419787234042553e-05,
|
| 1007 |
+
"loss": 0.0196,
|
| 1008 |
+
"step": 1410
|
| 1009 |
+
},
|
| 1010 |
+
{
|
| 1011 |
+
"epoch": 13.653846153846153,
|
| 1012 |
+
"grad_norm": 0.4434458017349243,
|
| 1013 |
+
"learning_rate": 2.413404255319149e-05,
|
| 1014 |
+
"loss": 0.0156,
|
| 1015 |
+
"step": 1420
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 13.75,
|
| 1019 |
+
"grad_norm": 1.199776530265808,
|
| 1020 |
+
"learning_rate": 2.4070212765957445e-05,
|
| 1021 |
+
"loss": 0.0129,
|
| 1022 |
+
"step": 1430
|
| 1023 |
+
},
|
| 1024 |
+
{
|
| 1025 |
+
"epoch": 13.846153846153847,
|
| 1026 |
+
"grad_norm": 0.999998927116394,
|
| 1027 |
+
"learning_rate": 2.4006382978723404e-05,
|
| 1028 |
+
"loss": 0.0153,
|
| 1029 |
+
"step": 1440
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 13.942307692307692,
|
| 1033 |
+
"grad_norm": 0.4517202079296112,
|
| 1034 |
+
"learning_rate": 2.394255319148936e-05,
|
| 1035 |
+
"loss": 0.0135,
|
| 1036 |
+
"step": 1450
|
| 1037 |
+
},
|
| 1038 |
+
{
|
| 1039 |
+
"epoch": 14.038461538461538,
|
| 1040 |
+
"grad_norm": 3.2634222507476807,
|
| 1041 |
+
"learning_rate": 2.387872340425532e-05,
|
| 1042 |
+
"loss": 0.0134,
|
| 1043 |
+
"step": 1460
|
| 1044 |
+
},
|
| 1045 |
+
{
|
| 1046 |
+
"epoch": 14.134615384615385,
|
| 1047 |
+
"grad_norm": 0.2920875549316406,
|
| 1048 |
+
"learning_rate": 2.3814893617021275e-05,
|
| 1049 |
+
"loss": 0.0137,
|
| 1050 |
+
"step": 1470
|
| 1051 |
+
},
|
| 1052 |
+
{
|
| 1053 |
+
"epoch": 14.23076923076923,
|
| 1054 |
+
"grad_norm": 0.38768115639686584,
|
| 1055 |
+
"learning_rate": 2.3751063829787234e-05,
|
| 1056 |
+
"loss": 0.0122,
|
| 1057 |
+
"step": 1480
|
| 1058 |
+
},
|
| 1059 |
+
{
|
| 1060 |
+
"epoch": 14.326923076923077,
|
| 1061 |
+
"grad_norm": 0.26864001154899597,
|
| 1062 |
+
"learning_rate": 2.368723404255319e-05,
|
| 1063 |
+
"loss": 0.0117,
|
| 1064 |
+
"step": 1490
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 14.423076923076923,
|
| 1068 |
+
"grad_norm": 0.6234428286552429,
|
| 1069 |
+
"learning_rate": 2.3623404255319148e-05,
|
| 1070 |
+
"loss": 0.0182,
|
| 1071 |
+
"step": 1500
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 14.51923076923077,
|
| 1075 |
+
"grad_norm": 0.464770644903183,
|
| 1076 |
+
"learning_rate": 2.3559574468085107e-05,
|
| 1077 |
+
"loss": 0.017,
|
| 1078 |
+
"step": 1510
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 14.615384615384615,
|
| 1082 |
+
"grad_norm": 0.4075222313404083,
|
| 1083 |
+
"learning_rate": 2.3495744680851066e-05,
|
| 1084 |
+
"loss": 0.0131,
|
| 1085 |
+
"step": 1520
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 14.711538461538462,
|
| 1089 |
+
"grad_norm": 0.5356881022453308,
|
| 1090 |
+
"learning_rate": 2.3431914893617022e-05,
|
| 1091 |
+
"loss": 0.0123,
|
| 1092 |
+
"step": 1530
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 14.807692307692308,
|
| 1096 |
+
"grad_norm": 0.4046107828617096,
|
| 1097 |
+
"learning_rate": 2.336808510638298e-05,
|
| 1098 |
+
"loss": 0.013,
|
| 1099 |
+
"step": 1540
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 14.903846153846153,
|
| 1103 |
+
"grad_norm": 0.5966467261314392,
|
| 1104 |
+
"learning_rate": 2.330425531914894e-05,
|
| 1105 |
+
"loss": 0.0153,
|
| 1106 |
+
"step": 1550
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 15.0,
|
| 1110 |
+
"grad_norm": 2.5298049449920654,
|
| 1111 |
+
"learning_rate": 2.3240425531914895e-05,
|
| 1112 |
+
"loss": 0.0213,
|
| 1113 |
+
"step": 1560
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 15.096153846153847,
|
| 1117 |
+
"grad_norm": 0.5523245930671692,
|
| 1118 |
+
"learning_rate": 2.3176595744680854e-05,
|
| 1119 |
+
"loss": 0.0185,
|
| 1120 |
+
"step": 1570
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 15.192307692307692,
|
| 1124 |
+
"grad_norm": 1.1738141775131226,
|
| 1125 |
+
"learning_rate": 2.311276595744681e-05,
|
| 1126 |
+
"loss": 0.0152,
|
| 1127 |
+
"step": 1580
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 15.288461538461538,
|
| 1131 |
+
"grad_norm": 0.4074403941631317,
|
| 1132 |
+
"learning_rate": 2.304893617021277e-05,
|
| 1133 |
+
"loss": 0.0153,
|
| 1134 |
+
"step": 1590
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 15.384615384615385,
|
| 1138 |
+
"grad_norm": 0.5409718751907349,
|
| 1139 |
+
"learning_rate": 2.2985106382978725e-05,
|
| 1140 |
+
"loss": 0.0115,
|
| 1141 |
+
"step": 1600
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 15.48076923076923,
|
| 1145 |
+
"grad_norm": 0.39902809262275696,
|
| 1146 |
+
"learning_rate": 2.2921276595744684e-05,
|
| 1147 |
+
"loss": 0.0126,
|
| 1148 |
+
"step": 1610
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 15.576923076923077,
|
| 1152 |
+
"grad_norm": 0.2555994391441345,
|
| 1153 |
+
"learning_rate": 2.285744680851064e-05,
|
| 1154 |
+
"loss": 0.015,
|
| 1155 |
+
"step": 1620
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 15.673076923076923,
|
| 1159 |
+
"grad_norm": 0.5419341325759888,
|
| 1160 |
+
"learning_rate": 2.2793617021276598e-05,
|
| 1161 |
+
"loss": 0.0146,
|
| 1162 |
+
"step": 1630
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 15.76923076923077,
|
| 1166 |
+
"grad_norm": 0.31709060072898865,
|
| 1167 |
+
"learning_rate": 2.2729787234042554e-05,
|
| 1168 |
+
"loss": 0.0103,
|
| 1169 |
+
"step": 1640
|
| 1170 |
+
},
|
| 1171 |
+
{
|
| 1172 |
+
"epoch": 15.865384615384615,
|
| 1173 |
+
"grad_norm": 0.514011800289154,
|
| 1174 |
+
"learning_rate": 2.2665957446808513e-05,
|
| 1175 |
+
"loss": 0.0186,
|
| 1176 |
+
"step": 1650
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 15.961538461538462,
|
| 1180 |
+
"grad_norm": 1.1153632402420044,
|
| 1181 |
+
"learning_rate": 2.260212765957447e-05,
|
| 1182 |
+
"loss": 0.0107,
|
| 1183 |
+
"step": 1660
|
| 1184 |
+
},
|
| 1185 |
+
{
|
| 1186 |
+
"epoch": 16.057692307692307,
|
| 1187 |
+
"grad_norm": 0.3839642405509949,
|
| 1188 |
+
"learning_rate": 2.2538297872340427e-05,
|
| 1189 |
+
"loss": 0.0137,
|
| 1190 |
+
"step": 1670
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"epoch": 16.153846153846153,
|
| 1194 |
+
"grad_norm": 0.42906543612480164,
|
| 1195 |
+
"learning_rate": 2.2474468085106383e-05,
|
| 1196 |
+
"loss": 0.0115,
|
| 1197 |
+
"step": 1680
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 16.25,
|
| 1201 |
+
"grad_norm": 0.35228168964385986,
|
| 1202 |
+
"learning_rate": 2.2410638297872342e-05,
|
| 1203 |
+
"loss": 0.0119,
|
| 1204 |
+
"step": 1690
|
| 1205 |
+
},
|
| 1206 |
+
{
|
| 1207 |
+
"epoch": 16.346153846153847,
|
| 1208 |
+
"grad_norm": 0.9752399325370789,
|
| 1209 |
+
"learning_rate": 2.2346808510638298e-05,
|
| 1210 |
+
"loss": 0.0122,
|
| 1211 |
+
"step": 1700
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 16.442307692307693,
|
| 1215 |
+
"grad_norm": 0.5118827223777771,
|
| 1216 |
+
"learning_rate": 2.2282978723404257e-05,
|
| 1217 |
+
"loss": 0.0105,
|
| 1218 |
+
"step": 1710
|
| 1219 |
+
},
|
| 1220 |
+
{
|
| 1221 |
+
"epoch": 16.53846153846154,
|
| 1222 |
+
"grad_norm": 0.6164939999580383,
|
| 1223 |
+
"learning_rate": 2.2219148936170216e-05,
|
| 1224 |
+
"loss": 0.0125,
|
| 1225 |
+
"step": 1720
|
| 1226 |
+
},
|
| 1227 |
+
{
|
| 1228 |
+
"epoch": 16.634615384615383,
|
| 1229 |
+
"grad_norm": 0.5313933491706848,
|
| 1230 |
+
"learning_rate": 2.215531914893617e-05,
|
| 1231 |
+
"loss": 0.011,
|
| 1232 |
+
"step": 1730
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 16.73076923076923,
|
| 1236 |
+
"grad_norm": 0.5187636017799377,
|
| 1237 |
+
"learning_rate": 2.209148936170213e-05,
|
| 1238 |
+
"loss": 0.0144,
|
| 1239 |
+
"step": 1740
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 16.826923076923077,
|
| 1243 |
+
"grad_norm": 1.1867964267730713,
|
| 1244 |
+
"learning_rate": 2.2027659574468086e-05,
|
| 1245 |
+
"loss": 0.0093,
|
| 1246 |
+
"step": 1750
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 16.923076923076923,
|
| 1250 |
+
"grad_norm": 0.7687259316444397,
|
| 1251 |
+
"learning_rate": 2.1963829787234045e-05,
|
| 1252 |
+
"loss": 0.0115,
|
| 1253 |
+
"step": 1760
|
| 1254 |
+
},
|
| 1255 |
+
{
|
| 1256 |
+
"epoch": 17.01923076923077,
|
| 1257 |
+
"grad_norm": 0.28656214475631714,
|
| 1258 |
+
"learning_rate": 2.19e-05,
|
| 1259 |
+
"loss": 0.0098,
|
| 1260 |
+
"step": 1770
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 17.115384615384617,
|
| 1264 |
+
"grad_norm": 0.9335207939147949,
|
| 1265 |
+
"learning_rate": 2.183617021276596e-05,
|
| 1266 |
+
"loss": 0.0122,
|
| 1267 |
+
"step": 1780
|
| 1268 |
+
},
|
| 1269 |
+
{
|
| 1270 |
+
"epoch": 17.21153846153846,
|
| 1271 |
+
"grad_norm": 0.21729937195777893,
|
| 1272 |
+
"learning_rate": 2.1772340425531915e-05,
|
| 1273 |
+
"loss": 0.0083,
|
| 1274 |
+
"step": 1790
|
| 1275 |
+
},
|
| 1276 |
+
{
|
| 1277 |
+
"epoch": 17.307692307692307,
|
| 1278 |
+
"grad_norm": 0.4466613233089447,
|
| 1279 |
+
"learning_rate": 2.1708510638297874e-05,
|
| 1280 |
+
"loss": 0.0122,
|
| 1281 |
+
"step": 1800
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 17.403846153846153,
|
| 1285 |
+
"grad_norm": 1.2216111421585083,
|
| 1286 |
+
"learning_rate": 2.164468085106383e-05,
|
| 1287 |
+
"loss": 0.0169,
|
| 1288 |
+
"step": 1810
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 17.5,
|
| 1292 |
+
"grad_norm": 0.4963133633136749,
|
| 1293 |
+
"learning_rate": 2.158085106382979e-05,
|
| 1294 |
+
"loss": 0.0105,
|
| 1295 |
+
"step": 1820
|
| 1296 |
+
},
|
| 1297 |
+
{
|
| 1298 |
+
"epoch": 17.596153846153847,
|
| 1299 |
+
"grad_norm": 0.701065719127655,
|
| 1300 |
+
"learning_rate": 2.1517021276595744e-05,
|
| 1301 |
+
"loss": 0.0168,
|
| 1302 |
+
"step": 1830
|
| 1303 |
+
},
|
| 1304 |
+
{
|
| 1305 |
+
"epoch": 17.692307692307693,
|
| 1306 |
+
"grad_norm": 0.8817301392555237,
|
| 1307 |
+
"learning_rate": 2.1453191489361703e-05,
|
| 1308 |
+
"loss": 0.008,
|
| 1309 |
+
"step": 1840
|
| 1310 |
+
},
|
| 1311 |
+
{
|
| 1312 |
+
"epoch": 17.78846153846154,
|
| 1313 |
+
"grad_norm": 0.5563378930091858,
|
| 1314 |
+
"learning_rate": 2.138936170212766e-05,
|
| 1315 |
+
"loss": 0.011,
|
| 1316 |
+
"step": 1850
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 17.884615384615383,
|
| 1320 |
+
"grad_norm": 0.16618973016738892,
|
| 1321 |
+
"learning_rate": 2.1325531914893618e-05,
|
| 1322 |
+
"loss": 0.0103,
|
| 1323 |
+
"step": 1860
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 17.98076923076923,
|
| 1327 |
+
"grad_norm": 0.2868179678916931,
|
| 1328 |
+
"learning_rate": 2.1261702127659573e-05,
|
| 1329 |
+
"loss": 0.012,
|
| 1330 |
+
"step": 1870
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 18.076923076923077,
|
| 1334 |
+
"grad_norm": 0.6677718758583069,
|
| 1335 |
+
"learning_rate": 2.1197872340425532e-05,
|
| 1336 |
+
"loss": 0.0082,
|
| 1337 |
+
"step": 1880
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 18.173076923076923,
|
| 1341 |
+
"grad_norm": 0.3902364671230316,
|
| 1342 |
+
"learning_rate": 2.1134042553191488e-05,
|
| 1343 |
+
"loss": 0.0116,
|
| 1344 |
+
"step": 1890
|
| 1345 |
+
},
|
| 1346 |
+
{
|
| 1347 |
+
"epoch": 18.26923076923077,
|
| 1348 |
+
"grad_norm": 0.563302218914032,
|
| 1349 |
+
"learning_rate": 2.1070212765957447e-05,
|
| 1350 |
+
"loss": 0.0093,
|
| 1351 |
+
"step": 1900
|
| 1352 |
+
},
|
| 1353 |
+
{
|
| 1354 |
+
"epoch": 18.365384615384617,
|
| 1355 |
+
"grad_norm": 0.8351249098777771,
|
| 1356 |
+
"learning_rate": 2.1006382978723406e-05,
|
| 1357 |
+
"loss": 0.0072,
|
| 1358 |
+
"step": 1910
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"epoch": 18.46153846153846,
|
| 1362 |
+
"grad_norm": 0.35901957750320435,
|
| 1363 |
+
"learning_rate": 2.094255319148936e-05,
|
| 1364 |
+
"loss": 0.0145,
|
| 1365 |
+
"step": 1920
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 18.557692307692307,
|
| 1369 |
+
"grad_norm": 1.6402753591537476,
|
| 1370 |
+
"learning_rate": 2.087872340425532e-05,
|
| 1371 |
+
"loss": 0.0148,
|
| 1372 |
+
"step": 1930
|
| 1373 |
+
},
|
| 1374 |
+
{
|
| 1375 |
+
"epoch": 18.653846153846153,
|
| 1376 |
+
"grad_norm": 0.6766220331192017,
|
| 1377 |
+
"learning_rate": 2.0814893617021276e-05,
|
| 1378 |
+
"loss": 0.0093,
|
| 1379 |
+
"step": 1940
|
| 1380 |
+
},
|
| 1381 |
+
{
|
| 1382 |
+
"epoch": 18.75,
|
| 1383 |
+
"grad_norm": 0.3588562607765198,
|
| 1384 |
+
"learning_rate": 2.0751063829787235e-05,
|
| 1385 |
+
"loss": 0.0111,
|
| 1386 |
+
"step": 1950
|
| 1387 |
+
},
|
| 1388 |
+
{
|
| 1389 |
+
"epoch": 18.846153846153847,
|
| 1390 |
+
"grad_norm": 0.3064340651035309,
|
| 1391 |
+
"learning_rate": 2.068723404255319e-05,
|
| 1392 |
+
"loss": 0.0084,
|
| 1393 |
+
"step": 1960
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 18.942307692307693,
|
| 1397 |
+
"grad_norm": 0.9118555188179016,
|
| 1398 |
+
"learning_rate": 2.062340425531915e-05,
|
| 1399 |
+
"loss": 0.0142,
|
| 1400 |
+
"step": 1970
|
| 1401 |
+
},
|
| 1402 |
+
{
|
| 1403 |
+
"epoch": 19.03846153846154,
|
| 1404 |
+
"grad_norm": 0.47235992550849915,
|
| 1405 |
+
"learning_rate": 2.0559574468085105e-05,
|
| 1406 |
+
"loss": 0.0146,
|
| 1407 |
+
"step": 1980
|
| 1408 |
+
},
|
| 1409 |
+
{
|
| 1410 |
+
"epoch": 19.134615384615383,
|
| 1411 |
+
"grad_norm": 0.7751461863517761,
|
| 1412 |
+
"learning_rate": 2.0495744680851064e-05,
|
| 1413 |
+
"loss": 0.0077,
|
| 1414 |
+
"step": 1990
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 19.23076923076923,
|
| 1418 |
+
"grad_norm": 0.4031819701194763,
|
| 1419 |
+
"learning_rate": 2.043191489361702e-05,
|
| 1420 |
+
"loss": 0.0107,
|
| 1421 |
+
"step": 2000
|
| 1422 |
+
},
|
| 1423 |
+
{
|
| 1424 |
+
"epoch": 19.23076923076923,
|
| 1425 |
+
"eval_correct_predictions": 1382,
|
| 1426 |
+
"eval_exact_match_accuracy": 0.976678445229682,
|
| 1427 |
+
"eval_loss": 0.007804804015904665,
|
| 1428 |
+
"eval_runtime": 58.2622,
|
| 1429 |
+
"eval_samples_per_second": 24.287,
|
| 1430 |
+
"eval_steps_per_second": 0.395,
|
| 1431 |
+
"eval_total_predictions": 1415,
|
| 1432 |
+
"step": 2000
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 19.326923076923077,
|
| 1436 |
+
"grad_norm": 0.42076176404953003,
|
| 1437 |
+
"learning_rate": 2.036808510638298e-05,
|
| 1438 |
+
"loss": 0.0108,
|
| 1439 |
+
"step": 2010
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 19.423076923076923,
|
| 1443 |
+
"grad_norm": 0.8498334884643555,
|
| 1444 |
+
"learning_rate": 2.0304255319148935e-05,
|
| 1445 |
+
"loss": 0.01,
|
| 1446 |
+
"step": 2020
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 19.51923076923077,
|
| 1450 |
+
"grad_norm": 0.5926603674888611,
|
| 1451 |
+
"learning_rate": 2.0240425531914894e-05,
|
| 1452 |
+
"loss": 0.009,
|
| 1453 |
+
"step": 2030
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 19.615384615384617,
|
| 1457 |
+
"grad_norm": 0.6045398712158203,
|
| 1458 |
+
"learning_rate": 2.017659574468085e-05,
|
| 1459 |
+
"loss": 0.0094,
|
| 1460 |
+
"step": 2040
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 19.71153846153846,
|
| 1464 |
+
"grad_norm": 0.4028799831867218,
|
| 1465 |
+
"learning_rate": 2.0112765957446808e-05,
|
| 1466 |
+
"loss": 0.012,
|
| 1467 |
+
"step": 2050
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 19.807692307692307,
|
| 1471 |
+
"grad_norm": 0.4177253544330597,
|
| 1472 |
+
"learning_rate": 2.0048936170212764e-05,
|
| 1473 |
+
"loss": 0.012,
|
| 1474 |
+
"step": 2060
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 19.903846153846153,
|
| 1478 |
+
"grad_norm": 0.30318310856819153,
|
| 1479 |
+
"learning_rate": 1.9985106382978723e-05,
|
| 1480 |
+
"loss": 0.0119,
|
| 1481 |
+
"step": 2070
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 20.0,
|
| 1485 |
+
"grad_norm": 1.5503188371658325,
|
| 1486 |
+
"learning_rate": 1.9921276595744682e-05,
|
| 1487 |
+
"loss": 0.0096,
|
| 1488 |
+
"step": 2080
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 20.096153846153847,
|
| 1492 |
+
"grad_norm": 0.6722589731216431,
|
| 1493 |
+
"learning_rate": 1.9857446808510637e-05,
|
| 1494 |
+
"loss": 0.0069,
|
| 1495 |
+
"step": 2090
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 20.192307692307693,
|
| 1499 |
+
"grad_norm": 0.2268471121788025,
|
| 1500 |
+
"learning_rate": 1.9793617021276596e-05,
|
| 1501 |
+
"loss": 0.0081,
|
| 1502 |
+
"step": 2100
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 20.28846153846154,
|
| 1506 |
+
"grad_norm": 0.4761890769004822,
|
| 1507 |
+
"learning_rate": 1.9729787234042552e-05,
|
| 1508 |
+
"loss": 0.0109,
|
| 1509 |
+
"step": 2110
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 20.384615384615383,
|
| 1513 |
+
"grad_norm": 0.37841594219207764,
|
| 1514 |
+
"learning_rate": 1.966595744680851e-05,
|
| 1515 |
+
"loss": 0.0107,
|
| 1516 |
+
"step": 2120
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 20.48076923076923,
|
| 1520 |
+
"grad_norm": 0.4525921046733856,
|
| 1521 |
+
"learning_rate": 1.9602127659574467e-05,
|
| 1522 |
+
"loss": 0.0107,
|
| 1523 |
+
"step": 2130
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 20.576923076923077,
|
| 1527 |
+
"grad_norm": 0.1672481745481491,
|
| 1528 |
+
"learning_rate": 1.9538297872340426e-05,
|
| 1529 |
+
"loss": 0.0093,
|
| 1530 |
+
"step": 2140
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 20.673076923076923,
|
| 1534 |
+
"grad_norm": 0.8809177279472351,
|
| 1535 |
+
"learning_rate": 1.947446808510638e-05,
|
| 1536 |
+
"loss": 0.0118,
|
| 1537 |
+
"step": 2150
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 20.76923076923077,
|
| 1541 |
+
"grad_norm": 1.2535909414291382,
|
| 1542 |
+
"learning_rate": 1.941063829787234e-05,
|
| 1543 |
+
"loss": 0.0095,
|
| 1544 |
+
"step": 2160
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 20.865384615384617,
|
| 1548 |
+
"grad_norm": 0.2467496544122696,
|
| 1549 |
+
"learning_rate": 1.9346808510638296e-05,
|
| 1550 |
+
"loss": 0.0083,
|
| 1551 |
+
"step": 2170
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 20.96153846153846,
|
| 1555 |
+
"grad_norm": 0.3241216838359833,
|
| 1556 |
+
"learning_rate": 1.9282978723404255e-05,
|
| 1557 |
+
"loss": 0.0102,
|
| 1558 |
+
"step": 2180
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 21.057692307692307,
|
| 1562 |
+
"grad_norm": 1.0612328052520752,
|
| 1563 |
+
"learning_rate": 1.9219148936170214e-05,
|
| 1564 |
+
"loss": 0.0079,
|
| 1565 |
+
"step": 2190
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 21.153846153846153,
|
| 1569 |
+
"grad_norm": 0.6267879605293274,
|
| 1570 |
+
"learning_rate": 1.9155319148936173e-05,
|
| 1571 |
+
"loss": 0.0111,
|
| 1572 |
+
"step": 2200
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 21.25,
|
| 1576 |
+
"grad_norm": 0.34094300866127014,
|
| 1577 |
+
"learning_rate": 1.909148936170213e-05,
|
| 1578 |
+
"loss": 0.0082,
|
| 1579 |
+
"step": 2210
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 21.346153846153847,
|
| 1583 |
+
"grad_norm": 0.3252468705177307,
|
| 1584 |
+
"learning_rate": 1.9027659574468087e-05,
|
| 1585 |
+
"loss": 0.0076,
|
| 1586 |
+
"step": 2220
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 21.442307692307693,
|
| 1590 |
+
"grad_norm": 0.18613576889038086,
|
| 1591 |
+
"learning_rate": 1.8963829787234043e-05,
|
| 1592 |
+
"loss": 0.0111,
|
| 1593 |
+
"step": 2230
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 21.53846153846154,
|
| 1597 |
+
"grad_norm": 0.5395278334617615,
|
| 1598 |
+
"learning_rate": 1.8900000000000002e-05,
|
| 1599 |
+
"loss": 0.008,
|
| 1600 |
+
"step": 2240
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 21.634615384615383,
|
| 1604 |
+
"grad_norm": 1.6617084741592407,
|
| 1605 |
+
"learning_rate": 1.8836170212765958e-05,
|
| 1606 |
+
"loss": 0.0092,
|
| 1607 |
+
"step": 2250
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 21.73076923076923,
|
| 1611 |
+
"grad_norm": 0.4416300654411316,
|
| 1612 |
+
"learning_rate": 1.8772340425531917e-05,
|
| 1613 |
+
"loss": 0.0075,
|
| 1614 |
+
"step": 2260
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 21.826923076923077,
|
| 1618 |
+
"grad_norm": 0.25209808349609375,
|
| 1619 |
+
"learning_rate": 1.8708510638297876e-05,
|
| 1620 |
+
"loss": 0.0084,
|
| 1621 |
+
"step": 2270
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 21.923076923076923,
|
| 1625 |
+
"grad_norm": 0.47792643308639526,
|
| 1626 |
+
"learning_rate": 1.864468085106383e-05,
|
| 1627 |
+
"loss": 0.0124,
|
| 1628 |
+
"step": 2280
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 22.01923076923077,
|
| 1632 |
+
"grad_norm": 0.49080875515937805,
|
| 1633 |
+
"learning_rate": 1.858085106382979e-05,
|
| 1634 |
+
"loss": 0.0096,
|
| 1635 |
+
"step": 2290
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 22.115384615384617,
|
| 1639 |
+
"grad_norm": 0.6654906868934631,
|
| 1640 |
+
"learning_rate": 1.8517021276595746e-05,
|
| 1641 |
+
"loss": 0.0066,
|
| 1642 |
+
"step": 2300
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 22.21153846153846,
|
| 1646 |
+
"grad_norm": 0.9110317230224609,
|
| 1647 |
+
"learning_rate": 1.8453191489361705e-05,
|
| 1648 |
+
"loss": 0.011,
|
| 1649 |
+
"step": 2310
|
| 1650 |
+
},
|
| 1651 |
+
{
|
| 1652 |
+
"epoch": 22.307692307692307,
|
| 1653 |
+
"grad_norm": 0.9715136885643005,
|
| 1654 |
+
"learning_rate": 1.838936170212766e-05,
|
| 1655 |
+
"loss": 0.0094,
|
| 1656 |
+
"step": 2320
|
| 1657 |
+
},
|
| 1658 |
+
{
|
| 1659 |
+
"epoch": 22.403846153846153,
|
| 1660 |
+
"grad_norm": 1.4085966348648071,
|
| 1661 |
+
"learning_rate": 1.832553191489362e-05,
|
| 1662 |
+
"loss": 0.0086,
|
| 1663 |
+
"step": 2330
|
| 1664 |
+
},
|
| 1665 |
+
{
|
| 1666 |
+
"epoch": 22.5,
|
| 1667 |
+
"grad_norm": 0.3735029995441437,
|
| 1668 |
+
"learning_rate": 1.8261702127659575e-05,
|
| 1669 |
+
"loss": 0.009,
|
| 1670 |
+
"step": 2340
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"epoch": 22.596153846153847,
|
| 1674 |
+
"grad_norm": 0.6319369077682495,
|
| 1675 |
+
"learning_rate": 1.8197872340425534e-05,
|
| 1676 |
+
"loss": 0.0075,
|
| 1677 |
+
"step": 2350
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 22.692307692307693,
|
| 1681 |
+
"grad_norm": 1.088571548461914,
|
| 1682 |
+
"learning_rate": 1.813404255319149e-05,
|
| 1683 |
+
"loss": 0.0075,
|
| 1684 |
+
"step": 2360
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 22.78846153846154,
|
| 1688 |
+
"grad_norm": 0.1355327069759369,
|
| 1689 |
+
"learning_rate": 1.807021276595745e-05,
|
| 1690 |
+
"loss": 0.0084,
|
| 1691 |
+
"step": 2370
|
| 1692 |
+
},
|
| 1693 |
+
{
|
| 1694 |
+
"epoch": 22.884615384615383,
|
| 1695 |
+
"grad_norm": 0.1889447569847107,
|
| 1696 |
+
"learning_rate": 1.8006382978723404e-05,
|
| 1697 |
+
"loss": 0.0092,
|
| 1698 |
+
"step": 2380
|
| 1699 |
+
},
|
| 1700 |
+
{
|
| 1701 |
+
"epoch": 22.98076923076923,
|
| 1702 |
+
"grad_norm": 0.1720777302980423,
|
| 1703 |
+
"learning_rate": 1.7942553191489363e-05,
|
| 1704 |
+
"loss": 0.0092,
|
| 1705 |
+
"step": 2390
|
| 1706 |
+
},
|
| 1707 |
+
{
|
| 1708 |
+
"epoch": 23.076923076923077,
|
| 1709 |
+
"grad_norm": 0.7916960716247559,
|
| 1710 |
+
"learning_rate": 1.787872340425532e-05,
|
| 1711 |
+
"loss": 0.0068,
|
| 1712 |
+
"step": 2400
|
| 1713 |
+
},
|
| 1714 |
+
{
|
| 1715 |
+
"epoch": 23.173076923076923,
|
| 1716 |
+
"grad_norm": 0.3657436668872833,
|
| 1717 |
+
"learning_rate": 1.7814893617021278e-05,
|
| 1718 |
+
"loss": 0.0082,
|
| 1719 |
+
"step": 2410
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 23.26923076923077,
|
| 1723 |
+
"grad_norm": 1.1953802108764648,
|
| 1724 |
+
"learning_rate": 1.7751063829787233e-05,
|
| 1725 |
+
"loss": 0.0108,
|
| 1726 |
+
"step": 2420
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 23.365384615384617,
|
| 1730 |
+
"grad_norm": 1.18259859085083,
|
| 1731 |
+
"learning_rate": 1.7687234042553192e-05,
|
| 1732 |
+
"loss": 0.007,
|
| 1733 |
+
"step": 2430
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 23.46153846153846,
|
| 1737 |
+
"grad_norm": 0.5571394562721252,
|
| 1738 |
+
"learning_rate": 1.762340425531915e-05,
|
| 1739 |
+
"loss": 0.0091,
|
| 1740 |
+
"step": 2440
|
| 1741 |
+
},
|
| 1742 |
+
{
|
| 1743 |
+
"epoch": 23.557692307692307,
|
| 1744 |
+
"grad_norm": 0.6768787503242493,
|
| 1745 |
+
"learning_rate": 1.7559574468085107e-05,
|
| 1746 |
+
"loss": 0.0098,
|
| 1747 |
+
"step": 2450
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"epoch": 23.653846153846153,
|
| 1751 |
+
"grad_norm": 1.5829925537109375,
|
| 1752 |
+
"learning_rate": 1.7495744680851066e-05,
|
| 1753 |
+
"loss": 0.0104,
|
| 1754 |
+
"step": 2460
|
| 1755 |
+
},
|
| 1756 |
+
{
|
| 1757 |
+
"epoch": 23.75,
|
| 1758 |
+
"grad_norm": 0.7399948239326477,
|
| 1759 |
+
"learning_rate": 1.743191489361702e-05,
|
| 1760 |
+
"loss": 0.0093,
|
| 1761 |
+
"step": 2470
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 23.846153846153847,
|
| 1765 |
+
"grad_norm": 0.14280381798744202,
|
| 1766 |
+
"learning_rate": 1.736808510638298e-05,
|
| 1767 |
+
"loss": 0.0079,
|
| 1768 |
+
"step": 2480
|
| 1769 |
+
},
|
| 1770 |
+
{
|
| 1771 |
+
"epoch": 23.942307692307693,
|
| 1772 |
+
"grad_norm": 0.14676937460899353,
|
| 1773 |
+
"learning_rate": 1.7304255319148936e-05,
|
| 1774 |
+
"loss": 0.0067,
|
| 1775 |
+
"step": 2490
|
| 1776 |
+
},
|
| 1777 |
+
{
|
| 1778 |
+
"epoch": 24.03846153846154,
|
| 1779 |
+
"grad_norm": 0.29147419333457947,
|
| 1780 |
+
"learning_rate": 1.7240425531914895e-05,
|
| 1781 |
+
"loss": 0.007,
|
| 1782 |
+
"step": 2500
|
| 1783 |
+
},
|
| 1784 |
+
{
|
| 1785 |
+
"epoch": 24.134615384615383,
|
| 1786 |
+
"grad_norm": 0.773118793964386,
|
| 1787 |
+
"learning_rate": 1.717659574468085e-05,
|
| 1788 |
+
"loss": 0.006,
|
| 1789 |
+
"step": 2510
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 24.23076923076923,
|
| 1793 |
+
"grad_norm": 1.2377712726593018,
|
| 1794 |
+
"learning_rate": 1.711276595744681e-05,
|
| 1795 |
+
"loss": 0.005,
|
| 1796 |
+
"step": 2520
|
| 1797 |
+
},
|
| 1798 |
+
{
|
| 1799 |
+
"epoch": 24.326923076923077,
|
| 1800 |
+
"grad_norm": 0.9301372170448303,
|
| 1801 |
+
"learning_rate": 1.7048936170212765e-05,
|
| 1802 |
+
"loss": 0.0082,
|
| 1803 |
+
"step": 2530
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 24.423076923076923,
|
| 1807 |
+
"grad_norm": 0.3903908133506775,
|
| 1808 |
+
"learning_rate": 1.6985106382978724e-05,
|
| 1809 |
+
"loss": 0.007,
|
| 1810 |
+
"step": 2540
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 24.51923076923077,
|
| 1814 |
+
"grad_norm": 0.8196276426315308,
|
| 1815 |
+
"learning_rate": 1.692127659574468e-05,
|
| 1816 |
+
"loss": 0.0064,
|
| 1817 |
+
"step": 2550
|
| 1818 |
+
},
|
| 1819 |
+
{
|
| 1820 |
+
"epoch": 24.615384615384617,
|
| 1821 |
+
"grad_norm": 0.3960936963558197,
|
| 1822 |
+
"learning_rate": 1.685744680851064e-05,
|
| 1823 |
+
"loss": 0.0066,
|
| 1824 |
+
"step": 2560
|
| 1825 |
+
},
|
| 1826 |
+
{
|
| 1827 |
+
"epoch": 24.71153846153846,
|
| 1828 |
+
"grad_norm": 0.43898555636405945,
|
| 1829 |
+
"learning_rate": 1.6793617021276595e-05,
|
| 1830 |
+
"loss": 0.0101,
|
| 1831 |
+
"step": 2570
|
| 1832 |
+
},
|
| 1833 |
+
{
|
| 1834 |
+
"epoch": 24.807692307692307,
|
| 1835 |
+
"grad_norm": 0.3561786115169525,
|
| 1836 |
+
"learning_rate": 1.6729787234042554e-05,
|
| 1837 |
+
"loss": 0.0122,
|
| 1838 |
+
"step": 2580
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 24.903846153846153,
|
| 1842 |
+
"grad_norm": 0.5492029786109924,
|
| 1843 |
+
"learning_rate": 1.666595744680851e-05,
|
| 1844 |
+
"loss": 0.0093,
|
| 1845 |
+
"step": 2590
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 25.0,
|
| 1849 |
+
"grad_norm": 1.1004884243011475,
|
| 1850 |
+
"learning_rate": 1.6602127659574468e-05,
|
| 1851 |
+
"loss": 0.0083,
|
| 1852 |
+
"step": 2600
|
| 1853 |
+
},
|
| 1854 |
+
{
|
| 1855 |
+
"epoch": 25.096153846153847,
|
| 1856 |
+
"grad_norm": 0.4236828088760376,
|
| 1857 |
+
"learning_rate": 1.6538297872340424e-05,
|
| 1858 |
+
"loss": 0.0092,
|
| 1859 |
+
"step": 2610
|
| 1860 |
+
},
|
| 1861 |
+
{
|
| 1862 |
+
"epoch": 25.192307692307693,
|
| 1863 |
+
"grad_norm": 0.642759382724762,
|
| 1864 |
+
"learning_rate": 1.6474468085106383e-05,
|
| 1865 |
+
"loss": 0.0066,
|
| 1866 |
+
"step": 2620
|
| 1867 |
+
},
|
| 1868 |
+
{
|
| 1869 |
+
"epoch": 25.28846153846154,
|
| 1870 |
+
"grad_norm": 1.0845800638198853,
|
| 1871 |
+
"learning_rate": 1.6410638297872342e-05,
|
| 1872 |
+
"loss": 0.0067,
|
| 1873 |
+
"step": 2630
|
| 1874 |
+
},
|
| 1875 |
+
{
|
| 1876 |
+
"epoch": 25.384615384615383,
|
| 1877 |
+
"grad_norm": 0.4961228370666504,
|
| 1878 |
+
"learning_rate": 1.6346808510638297e-05,
|
| 1879 |
+
"loss": 0.0051,
|
| 1880 |
+
"step": 2640
|
| 1881 |
+
},
|
| 1882 |
+
{
|
| 1883 |
+
"epoch": 25.48076923076923,
|
| 1884 |
+
"grad_norm": 0.7525473237037659,
|
| 1885 |
+
"learning_rate": 1.6282978723404256e-05,
|
| 1886 |
+
"loss": 0.008,
|
| 1887 |
+
"step": 2650
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 25.576923076923077,
|
| 1891 |
+
"grad_norm": 0.5340065956115723,
|
| 1892 |
+
"learning_rate": 1.6219148936170212e-05,
|
| 1893 |
+
"loss": 0.0086,
|
| 1894 |
+
"step": 2660
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 25.673076923076923,
|
| 1898 |
+
"grad_norm": 0.9437041282653809,
|
| 1899 |
+
"learning_rate": 1.615531914893617e-05,
|
| 1900 |
+
"loss": 0.0073,
|
| 1901 |
+
"step": 2670
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 25.76923076923077,
|
| 1905 |
+
"grad_norm": 0.1908496618270874,
|
| 1906 |
+
"learning_rate": 1.6091489361702127e-05,
|
| 1907 |
+
"loss": 0.0054,
|
| 1908 |
+
"step": 2680
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 25.865384615384617,
|
| 1912 |
+
"grad_norm": 0.7633543014526367,
|
| 1913 |
+
"learning_rate": 1.6027659574468086e-05,
|
| 1914 |
+
"loss": 0.0062,
|
| 1915 |
+
"step": 2690
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 25.96153846153846,
|
| 1919 |
+
"grad_norm": 0.36000245809555054,
|
| 1920 |
+
"learning_rate": 1.596382978723404e-05,
|
| 1921 |
+
"loss": 0.0087,
|
| 1922 |
+
"step": 2700
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 26.057692307692307,
|
| 1926 |
+
"grad_norm": 0.24572286009788513,
|
| 1927 |
+
"learning_rate": 1.59e-05,
|
| 1928 |
+
"loss": 0.0137,
|
| 1929 |
+
"step": 2710
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 26.153846153846153,
|
| 1933 |
+
"grad_norm": 0.7748898863792419,
|
| 1934 |
+
"learning_rate": 1.5836170212765956e-05,
|
| 1935 |
+
"loss": 0.007,
|
| 1936 |
+
"step": 2720
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 26.25,
|
| 1940 |
+
"grad_norm": 0.18942640721797943,
|
| 1941 |
+
"learning_rate": 1.5772340425531915e-05,
|
| 1942 |
+
"loss": 0.005,
|
| 1943 |
+
"step": 2730
|
| 1944 |
+
},
|
| 1945 |
+
{
|
| 1946 |
+
"epoch": 26.346153846153847,
|
| 1947 |
+
"grad_norm": 0.5449305772781372,
|
| 1948 |
+
"learning_rate": 1.570851063829787e-05,
|
| 1949 |
+
"loss": 0.0093,
|
| 1950 |
+
"step": 2740
|
| 1951 |
+
},
|
| 1952 |
+
{
|
| 1953 |
+
"epoch": 26.442307692307693,
|
| 1954 |
+
"grad_norm": 0.7563040256500244,
|
| 1955 |
+
"learning_rate": 1.564468085106383e-05,
|
| 1956 |
+
"loss": 0.0055,
|
| 1957 |
+
"step": 2750
|
| 1958 |
+
},
|
| 1959 |
+
{
|
| 1960 |
+
"epoch": 26.53846153846154,
|
| 1961 |
+
"grad_norm": 0.024510016664862633,
|
| 1962 |
+
"learning_rate": 1.5580851063829785e-05,
|
| 1963 |
+
"loss": 0.0091,
|
| 1964 |
+
"step": 2760
|
| 1965 |
+
},
|
| 1966 |
+
{
|
| 1967 |
+
"epoch": 26.634615384615383,
|
| 1968 |
+
"grad_norm": 0.9824059009552002,
|
| 1969 |
+
"learning_rate": 1.5517021276595744e-05,
|
| 1970 |
+
"loss": 0.007,
|
| 1971 |
+
"step": 2770
|
| 1972 |
+
},
|
| 1973 |
+
{
|
| 1974 |
+
"epoch": 26.73076923076923,
|
| 1975 |
+
"grad_norm": 1.0016579627990723,
|
| 1976 |
+
"learning_rate": 1.54531914893617e-05,
|
| 1977 |
+
"loss": 0.0082,
|
| 1978 |
+
"step": 2780
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 26.826923076923077,
|
| 1982 |
+
"grad_norm": 0.3715296685695648,
|
| 1983 |
+
"learning_rate": 1.538936170212766e-05,
|
| 1984 |
+
"loss": 0.0051,
|
| 1985 |
+
"step": 2790
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 26.923076923076923,
|
| 1989 |
+
"grad_norm": 0.609065592288971,
|
| 1990 |
+
"learning_rate": 1.5325531914893618e-05,
|
| 1991 |
+
"loss": 0.0081,
|
| 1992 |
+
"step": 2800
|
| 1993 |
+
},
|
| 1994 |
+
{
|
| 1995 |
+
"epoch": 27.01923076923077,
|
| 1996 |
+
"grad_norm": 0.8376663327217102,
|
| 1997 |
+
"learning_rate": 1.5261702127659573e-05,
|
| 1998 |
+
"loss": 0.0082,
|
| 1999 |
+
"step": 2810
|
| 2000 |
+
},
|
| 2001 |
+
{
|
| 2002 |
+
"epoch": 27.115384615384617,
|
| 2003 |
+
"grad_norm": 0.08116922527551651,
|
| 2004 |
+
"learning_rate": 1.5197872340425534e-05,
|
| 2005 |
+
"loss": 0.0063,
|
| 2006 |
+
"step": 2820
|
| 2007 |
+
},
|
| 2008 |
+
{
|
| 2009 |
+
"epoch": 27.21153846153846,
|
| 2010 |
+
"grad_norm": 0.4511634409427643,
|
| 2011 |
+
"learning_rate": 1.513404255319149e-05,
|
| 2012 |
+
"loss": 0.0061,
|
| 2013 |
+
"step": 2830
|
| 2014 |
+
},
|
| 2015 |
+
{
|
| 2016 |
+
"epoch": 27.307692307692307,
|
| 2017 |
+
"grad_norm": 0.8804696202278137,
|
| 2018 |
+
"learning_rate": 1.5070212765957449e-05,
|
| 2019 |
+
"loss": 0.0063,
|
| 2020 |
+
"step": 2840
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 27.403846153846153,
|
| 2024 |
+
"grad_norm": 0.2572877109050751,
|
| 2025 |
+
"learning_rate": 1.5006382978723404e-05,
|
| 2026 |
+
"loss": 0.0058,
|
| 2027 |
+
"step": 2850
|
| 2028 |
+
},
|
| 2029 |
+
{
|
| 2030 |
+
"epoch": 27.5,
|
| 2031 |
+
"grad_norm": 1.1330682039260864,
|
| 2032 |
+
"learning_rate": 1.4942553191489361e-05,
|
| 2033 |
+
"loss": 0.0077,
|
| 2034 |
+
"step": 2860
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 27.596153846153847,
|
| 2038 |
+
"grad_norm": 0.5823140740394592,
|
| 2039 |
+
"learning_rate": 1.4878723404255319e-05,
|
| 2040 |
+
"loss": 0.0068,
|
| 2041 |
+
"step": 2870
|
| 2042 |
+
},
|
| 2043 |
+
{
|
| 2044 |
+
"epoch": 27.692307692307693,
|
| 2045 |
+
"grad_norm": 0.20316189527511597,
|
| 2046 |
+
"learning_rate": 1.4814893617021276e-05,
|
| 2047 |
+
"loss": 0.007,
|
| 2048 |
+
"step": 2880
|
| 2049 |
+
},
|
| 2050 |
+
{
|
| 2051 |
+
"epoch": 27.78846153846154,
|
| 2052 |
+
"grad_norm": 0.86988365650177,
|
| 2053 |
+
"learning_rate": 1.4751063829787235e-05,
|
| 2054 |
+
"loss": 0.0053,
|
| 2055 |
+
"step": 2890
|
| 2056 |
+
},
|
| 2057 |
+
{
|
| 2058 |
+
"epoch": 27.884615384615383,
|
| 2059 |
+
"grad_norm": 0.4562746584415436,
|
| 2060 |
+
"learning_rate": 1.4687234042553192e-05,
|
| 2061 |
+
"loss": 0.0058,
|
| 2062 |
+
"step": 2900
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 27.98076923076923,
|
| 2066 |
+
"grad_norm": 0.7957671284675598,
|
| 2067 |
+
"learning_rate": 1.462340425531915e-05,
|
| 2068 |
+
"loss": 0.0061,
|
| 2069 |
+
"step": 2910
|
| 2070 |
+
},
|
| 2071 |
+
{
|
| 2072 |
+
"epoch": 28.076923076923077,
|
| 2073 |
+
"grad_norm": 0.2981686592102051,
|
| 2074 |
+
"learning_rate": 1.4559574468085107e-05,
|
| 2075 |
+
"loss": 0.0091,
|
| 2076 |
+
"step": 2920
|
| 2077 |
+
},
|
| 2078 |
+
{
|
| 2079 |
+
"epoch": 28.173076923076923,
|
| 2080 |
+
"grad_norm": 0.34361180663108826,
|
| 2081 |
+
"learning_rate": 1.4495744680851064e-05,
|
| 2082 |
+
"loss": 0.0045,
|
| 2083 |
+
"step": 2930
|
| 2084 |
+
},
|
| 2085 |
+
{
|
| 2086 |
+
"epoch": 28.26923076923077,
|
| 2087 |
+
"grad_norm": 0.3850739598274231,
|
| 2088 |
+
"learning_rate": 1.4431914893617022e-05,
|
| 2089 |
+
"loss": 0.0093,
|
| 2090 |
+
"step": 2940
|
| 2091 |
+
},
|
| 2092 |
+
{
|
| 2093 |
+
"epoch": 28.365384615384617,
|
| 2094 |
+
"grad_norm": 0.2868598699569702,
|
| 2095 |
+
"learning_rate": 1.4368085106382979e-05,
|
| 2096 |
+
"loss": 0.0048,
|
| 2097 |
+
"step": 2950
|
| 2098 |
+
},
|
| 2099 |
+
{
|
| 2100 |
+
"epoch": 28.46153846153846,
|
| 2101 |
+
"grad_norm": 0.20695632696151733,
|
| 2102 |
+
"learning_rate": 1.4304255319148936e-05,
|
| 2103 |
+
"loss": 0.0054,
|
| 2104 |
+
"step": 2960
|
| 2105 |
+
},
|
| 2106 |
+
{
|
| 2107 |
+
"epoch": 28.557692307692307,
|
| 2108 |
+
"grad_norm": 0.13250812888145447,
|
| 2109 |
+
"learning_rate": 1.4240425531914893e-05,
|
| 2110 |
+
"loss": 0.0038,
|
| 2111 |
+
"step": 2970
|
| 2112 |
+
},
|
| 2113 |
+
{
|
| 2114 |
+
"epoch": 28.653846153846153,
|
| 2115 |
+
"grad_norm": 0.9032599329948425,
|
| 2116 |
+
"learning_rate": 1.417659574468085e-05,
|
| 2117 |
+
"loss": 0.007,
|
| 2118 |
+
"step": 2980
|
| 2119 |
+
},
|
| 2120 |
+
{
|
| 2121 |
+
"epoch": 28.75,
|
| 2122 |
+
"grad_norm": 0.2160140872001648,
|
| 2123 |
+
"learning_rate": 1.4112765957446808e-05,
|
| 2124 |
+
"loss": 0.0051,
|
| 2125 |
+
"step": 2990
|
| 2126 |
+
},
|
| 2127 |
+
{
|
| 2128 |
+
"epoch": 28.846153846153847,
|
| 2129 |
+
"grad_norm": 0.8250911831855774,
|
| 2130 |
+
"learning_rate": 1.4048936170212765e-05,
|
| 2131 |
+
"loss": 0.0079,
|
| 2132 |
+
"step": 3000
|
| 2133 |
+
},
|
| 2134 |
+
{
|
| 2135 |
+
"epoch": 28.846153846153847,
|
| 2136 |
+
"eval_correct_predictions": 1391,
|
| 2137 |
+
"eval_exact_match_accuracy": 0.9830388692579505,
|
| 2138 |
+
"eval_loss": 0.006084157153964043,
|
| 2139 |
+
"eval_runtime": 58.5417,
|
| 2140 |
+
"eval_samples_per_second": 24.171,
|
| 2141 |
+
"eval_steps_per_second": 0.393,
|
| 2142 |
+
"eval_total_predictions": 1415,
|
| 2143 |
+
"step": 3000
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 28.942307692307693,
|
| 2147 |
+
"grad_norm": 2.7227625846862793,
|
| 2148 |
+
"learning_rate": 1.3985106382978723e-05,
|
| 2149 |
+
"loss": 0.0085,
|
| 2150 |
+
"step": 3010
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 29.03846153846154,
|
| 2154 |
+
"grad_norm": 0.41631412506103516,
|
| 2155 |
+
"learning_rate": 1.3921276595744682e-05,
|
| 2156 |
+
"loss": 0.0065,
|
| 2157 |
+
"step": 3020
|
| 2158 |
+
},
|
| 2159 |
+
{
|
| 2160 |
+
"epoch": 29.134615384615383,
|
| 2161 |
+
"grad_norm": 0.566443681716919,
|
| 2162 |
+
"learning_rate": 1.3857446808510639e-05,
|
| 2163 |
+
"loss": 0.0044,
|
| 2164 |
+
"step": 3030
|
| 2165 |
+
},
|
| 2166 |
+
{
|
| 2167 |
+
"epoch": 29.23076923076923,
|
| 2168 |
+
"grad_norm": 0.34673500061035156,
|
| 2169 |
+
"learning_rate": 1.3793617021276596e-05,
|
| 2170 |
+
"loss": 0.0081,
|
| 2171 |
+
"step": 3040
|
| 2172 |
+
},
|
| 2173 |
+
{
|
| 2174 |
+
"epoch": 29.326923076923077,
|
| 2175 |
+
"grad_norm": 0.10608164221048355,
|
| 2176 |
+
"learning_rate": 1.3729787234042554e-05,
|
| 2177 |
+
"loss": 0.0059,
|
| 2178 |
+
"step": 3050
|
| 2179 |
+
},
|
| 2180 |
+
{
|
| 2181 |
+
"epoch": 29.423076923076923,
|
| 2182 |
+
"grad_norm": 0.258186012506485,
|
| 2183 |
+
"learning_rate": 1.3665957446808511e-05,
|
| 2184 |
+
"loss": 0.0042,
|
| 2185 |
+
"step": 3060
|
| 2186 |
+
},
|
| 2187 |
+
{
|
| 2188 |
+
"epoch": 29.51923076923077,
|
| 2189 |
+
"grad_norm": 0.8078503608703613,
|
| 2190 |
+
"learning_rate": 1.360212765957447e-05,
|
| 2191 |
+
"loss": 0.0056,
|
| 2192 |
+
"step": 3070
|
| 2193 |
+
},
|
| 2194 |
+
{
|
| 2195 |
+
"epoch": 29.615384615384617,
|
| 2196 |
+
"grad_norm": 0.3078606128692627,
|
| 2197 |
+
"learning_rate": 1.3538297872340427e-05,
|
| 2198 |
+
"loss": 0.0065,
|
| 2199 |
+
"step": 3080
|
| 2200 |
+
},
|
| 2201 |
+
{
|
| 2202 |
+
"epoch": 29.71153846153846,
|
| 2203 |
+
"grad_norm": 0.5479371547698975,
|
| 2204 |
+
"learning_rate": 1.3474468085106384e-05,
|
| 2205 |
+
"loss": 0.005,
|
| 2206 |
+
"step": 3090
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 29.807692307692307,
|
| 2210 |
+
"grad_norm": 0.43646132946014404,
|
| 2211 |
+
"learning_rate": 1.3410638297872342e-05,
|
| 2212 |
+
"loss": 0.0075,
|
| 2213 |
+
"step": 3100
|
| 2214 |
+
},
|
| 2215 |
+
{
|
| 2216 |
+
"epoch": 29.903846153846153,
|
| 2217 |
+
"grad_norm": 0.15388578176498413,
|
| 2218 |
+
"learning_rate": 1.3346808510638299e-05,
|
| 2219 |
+
"loss": 0.0066,
|
| 2220 |
+
"step": 3110
|
| 2221 |
+
},
|
| 2222 |
+
{
|
| 2223 |
+
"epoch": 30.0,
|
| 2224 |
+
"grad_norm": 1.9249227046966553,
|
| 2225 |
+
"learning_rate": 1.3282978723404256e-05,
|
| 2226 |
+
"loss": 0.0073,
|
| 2227 |
+
"step": 3120
|
| 2228 |
+
},
|
| 2229 |
+
{
|
| 2230 |
+
"epoch": 30.096153846153847,
|
| 2231 |
+
"grad_norm": 0.027103092521429062,
|
| 2232 |
+
"learning_rate": 1.3219148936170214e-05,
|
| 2233 |
+
"loss": 0.0057,
|
| 2234 |
+
"step": 3130
|
| 2235 |
+
},
|
| 2236 |
+
{
|
| 2237 |
+
"epoch": 30.192307692307693,
|
| 2238 |
+
"grad_norm": 0.8037792444229126,
|
| 2239 |
+
"learning_rate": 1.3155319148936171e-05,
|
| 2240 |
+
"loss": 0.0092,
|
| 2241 |
+
"step": 3140
|
| 2242 |
+
},
|
| 2243 |
+
{
|
| 2244 |
+
"epoch": 30.28846153846154,
|
| 2245 |
+
"grad_norm": 1.0261093378067017,
|
| 2246 |
+
"learning_rate": 1.3091489361702128e-05,
|
| 2247 |
+
"loss": 0.0069,
|
| 2248 |
+
"step": 3150
|
| 2249 |
+
},
|
| 2250 |
+
{
|
| 2251 |
+
"epoch": 30.384615384615383,
|
| 2252 |
+
"grad_norm": 0.049915142357349396,
|
| 2253 |
+
"learning_rate": 1.3027659574468086e-05,
|
| 2254 |
+
"loss": 0.0074,
|
| 2255 |
+
"step": 3160
|
| 2256 |
+
},
|
| 2257 |
+
{
|
| 2258 |
+
"epoch": 30.48076923076923,
|
| 2259 |
+
"grad_norm": 0.51163250207901,
|
| 2260 |
+
"learning_rate": 1.2963829787234043e-05,
|
| 2261 |
+
"loss": 0.0044,
|
| 2262 |
+
"step": 3170
|
| 2263 |
+
},
|
| 2264 |
+
{
|
| 2265 |
+
"epoch": 30.576923076923077,
|
| 2266 |
+
"grad_norm": 1.2742948532104492,
|
| 2267 |
+
"learning_rate": 1.29e-05,
|
| 2268 |
+
"loss": 0.0072,
|
| 2269 |
+
"step": 3180
|
| 2270 |
+
},
|
| 2271 |
+
{
|
| 2272 |
+
"epoch": 30.673076923076923,
|
| 2273 |
+
"grad_norm": 2.13923978805542,
|
| 2274 |
+
"learning_rate": 1.2836170212765957e-05,
|
| 2275 |
+
"loss": 0.005,
|
| 2276 |
+
"step": 3190
|
| 2277 |
+
},
|
| 2278 |
+
{
|
| 2279 |
+
"epoch": 30.76923076923077,
|
| 2280 |
+
"grad_norm": 0.12393970787525177,
|
| 2281 |
+
"learning_rate": 1.2772340425531915e-05,
|
| 2282 |
+
"loss": 0.004,
|
| 2283 |
+
"step": 3200
|
| 2284 |
+
},
|
| 2285 |
+
{
|
| 2286 |
+
"epoch": 30.865384615384617,
|
| 2287 |
+
"grad_norm": 0.8308172821998596,
|
| 2288 |
+
"learning_rate": 1.2708510638297872e-05,
|
| 2289 |
+
"loss": 0.0057,
|
| 2290 |
+
"step": 3210
|
| 2291 |
+
},
|
| 2292 |
+
{
|
| 2293 |
+
"epoch": 30.96153846153846,
|
| 2294 |
+
"grad_norm": 0.19924144446849823,
|
| 2295 |
+
"learning_rate": 1.264468085106383e-05,
|
| 2296 |
+
"loss": 0.0046,
|
| 2297 |
+
"step": 3220
|
| 2298 |
+
},
|
| 2299 |
+
{
|
| 2300 |
+
"epoch": 31.057692307692307,
|
| 2301 |
+
"grad_norm": 0.7076709270477295,
|
| 2302 |
+
"learning_rate": 1.2580851063829787e-05,
|
| 2303 |
+
"loss": 0.0047,
|
| 2304 |
+
"step": 3230
|
| 2305 |
+
},
|
| 2306 |
+
{
|
| 2307 |
+
"epoch": 31.153846153846153,
|
| 2308 |
+
"grad_norm": 0.5298773050308228,
|
| 2309 |
+
"learning_rate": 1.2517021276595744e-05,
|
| 2310 |
+
"loss": 0.0076,
|
| 2311 |
+
"step": 3240
|
| 2312 |
+
},
|
| 2313 |
+
{
|
| 2314 |
+
"epoch": 31.25,
|
| 2315 |
+
"grad_norm": 0.11929306387901306,
|
| 2316 |
+
"learning_rate": 1.2453191489361703e-05,
|
| 2317 |
+
"loss": 0.0043,
|
| 2318 |
+
"step": 3250
|
| 2319 |
+
},
|
| 2320 |
+
{
|
| 2321 |
+
"epoch": 31.346153846153847,
|
| 2322 |
+
"grad_norm": 0.3417571485042572,
|
| 2323 |
+
"learning_rate": 1.238936170212766e-05,
|
| 2324 |
+
"loss": 0.0073,
|
| 2325 |
+
"step": 3260
|
| 2326 |
+
},
|
| 2327 |
+
{
|
| 2328 |
+
"epoch": 31.442307692307693,
|
| 2329 |
+
"grad_norm": 0.5745849609375,
|
| 2330 |
+
"learning_rate": 1.2325531914893618e-05,
|
| 2331 |
+
"loss": 0.0048,
|
| 2332 |
+
"step": 3270
|
| 2333 |
+
},
|
| 2334 |
+
{
|
| 2335 |
+
"epoch": 31.53846153846154,
|
| 2336 |
+
"grad_norm": 0.7137449979782104,
|
| 2337 |
+
"learning_rate": 1.2261702127659575e-05,
|
| 2338 |
+
"loss": 0.0041,
|
| 2339 |
+
"step": 3280
|
| 2340 |
+
},
|
| 2341 |
+
{
|
| 2342 |
+
"epoch": 31.634615384615383,
|
| 2343 |
+
"grad_norm": 1.3129104375839233,
|
| 2344 |
+
"learning_rate": 1.2197872340425532e-05,
|
| 2345 |
+
"loss": 0.0033,
|
| 2346 |
+
"step": 3290
|
| 2347 |
+
},
|
| 2348 |
+
{
|
| 2349 |
+
"epoch": 31.73076923076923,
|
| 2350 |
+
"grad_norm": 1.0879548788070679,
|
| 2351 |
+
"learning_rate": 1.213404255319149e-05,
|
| 2352 |
+
"loss": 0.0052,
|
| 2353 |
+
"step": 3300
|
| 2354 |
+
},
|
| 2355 |
+
{
|
| 2356 |
+
"epoch": 31.826923076923077,
|
| 2357 |
+
"grad_norm": 0.42951247096061707,
|
| 2358 |
+
"learning_rate": 1.2070212765957447e-05,
|
| 2359 |
+
"loss": 0.0072,
|
| 2360 |
+
"step": 3310
|
| 2361 |
+
},
|
| 2362 |
+
{
|
| 2363 |
+
"epoch": 31.923076923076923,
|
| 2364 |
+
"grad_norm": 0.2130812406539917,
|
| 2365 |
+
"learning_rate": 1.2006382978723404e-05,
|
| 2366 |
+
"loss": 0.0062,
|
| 2367 |
+
"step": 3320
|
| 2368 |
+
},
|
| 2369 |
+
{
|
| 2370 |
+
"epoch": 32.01923076923077,
|
| 2371 |
+
"grad_norm": 0.13096341490745544,
|
| 2372 |
+
"learning_rate": 1.1942553191489361e-05,
|
| 2373 |
+
"loss": 0.0047,
|
| 2374 |
+
"step": 3330
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 32.11538461538461,
|
| 2378 |
+
"grad_norm": 0.42370834946632385,
|
| 2379 |
+
"learning_rate": 1.1878723404255319e-05,
|
| 2380 |
+
"loss": 0.0053,
|
| 2381 |
+
"step": 3340
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 32.21153846153846,
|
| 2385 |
+
"grad_norm": 0.6214959621429443,
|
| 2386 |
+
"learning_rate": 1.1814893617021276e-05,
|
| 2387 |
+
"loss": 0.0057,
|
| 2388 |
+
"step": 3350
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 32.30769230769231,
|
| 2392 |
+
"grad_norm": 0.24280411005020142,
|
| 2393 |
+
"learning_rate": 1.1751063829787235e-05,
|
| 2394 |
+
"loss": 0.0055,
|
| 2395 |
+
"step": 3360
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 32.40384615384615,
|
| 2399 |
+
"grad_norm": 0.22130908071994781,
|
| 2400 |
+
"learning_rate": 1.1687234042553192e-05,
|
| 2401 |
+
"loss": 0.0074,
|
| 2402 |
+
"step": 3370
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 32.5,
|
| 2406 |
+
"grad_norm": 0.5882713794708252,
|
| 2407 |
+
"learning_rate": 1.162340425531915e-05,
|
| 2408 |
+
"loss": 0.0065,
|
| 2409 |
+
"step": 3380
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 32.59615384615385,
|
| 2413 |
+
"grad_norm": 0.09809905290603638,
|
| 2414 |
+
"learning_rate": 1.1559574468085107e-05,
|
| 2415 |
+
"loss": 0.0061,
|
| 2416 |
+
"step": 3390
|
| 2417 |
+
},
|
| 2418 |
+
{
|
| 2419 |
+
"epoch": 32.69230769230769,
|
| 2420 |
+
"grad_norm": 0.6485664248466492,
|
| 2421 |
+
"learning_rate": 1.1495744680851064e-05,
|
| 2422 |
+
"loss": 0.0058,
|
| 2423 |
+
"step": 3400
|
| 2424 |
+
},
|
| 2425 |
+
{
|
| 2426 |
+
"epoch": 32.78846153846154,
|
| 2427 |
+
"grad_norm": 0.07379120588302612,
|
| 2428 |
+
"learning_rate": 1.1431914893617021e-05,
|
| 2429 |
+
"loss": 0.005,
|
| 2430 |
+
"step": 3410
|
| 2431 |
+
},
|
| 2432 |
+
{
|
| 2433 |
+
"epoch": 32.88461538461539,
|
| 2434 |
+
"grad_norm": 0.2927326261997223,
|
| 2435 |
+
"learning_rate": 1.1368085106382979e-05,
|
| 2436 |
+
"loss": 0.0041,
|
| 2437 |
+
"step": 3420
|
| 2438 |
+
},
|
| 2439 |
+
{
|
| 2440 |
+
"epoch": 32.98076923076923,
|
| 2441 |
+
"grad_norm": 0.3531413674354553,
|
| 2442 |
+
"learning_rate": 1.1304255319148938e-05,
|
| 2443 |
+
"loss": 0.0035,
|
| 2444 |
+
"step": 3430
|
| 2445 |
+
},
|
| 2446 |
+
{
|
| 2447 |
+
"epoch": 33.07692307692308,
|
| 2448 |
+
"grad_norm": 0.10925979912281036,
|
| 2449 |
+
"learning_rate": 1.1240425531914895e-05,
|
| 2450 |
+
"loss": 0.0057,
|
| 2451 |
+
"step": 3440
|
| 2452 |
+
},
|
| 2453 |
+
{
|
| 2454 |
+
"epoch": 33.17307692307692,
|
| 2455 |
+
"grad_norm": 0.2170642763376236,
|
| 2456 |
+
"learning_rate": 1.1176595744680852e-05,
|
| 2457 |
+
"loss": 0.0048,
|
| 2458 |
+
"step": 3450
|
| 2459 |
+
},
|
| 2460 |
+
{
|
| 2461 |
+
"epoch": 33.26923076923077,
|
| 2462 |
+
"grad_norm": 0.774167001247406,
|
| 2463 |
+
"learning_rate": 1.111276595744681e-05,
|
| 2464 |
+
"loss": 0.0041,
|
| 2465 |
+
"step": 3460
|
| 2466 |
+
},
|
| 2467 |
+
{
|
| 2468 |
+
"epoch": 33.36538461538461,
|
| 2469 |
+
"grad_norm": 0.22706744074821472,
|
| 2470 |
+
"learning_rate": 1.1048936170212767e-05,
|
| 2471 |
+
"loss": 0.0042,
|
| 2472 |
+
"step": 3470
|
| 2473 |
+
},
|
| 2474 |
+
{
|
| 2475 |
+
"epoch": 33.46153846153846,
|
| 2476 |
+
"grad_norm": 0.2846420407295227,
|
| 2477 |
+
"learning_rate": 1.0985106382978724e-05,
|
| 2478 |
+
"loss": 0.0056,
|
| 2479 |
+
"step": 3480
|
| 2480 |
+
},
|
| 2481 |
+
{
|
| 2482 |
+
"epoch": 33.55769230769231,
|
| 2483 |
+
"grad_norm": 1.1403943300247192,
|
| 2484 |
+
"learning_rate": 1.0921276595744682e-05,
|
| 2485 |
+
"loss": 0.0093,
|
| 2486 |
+
"step": 3490
|
| 2487 |
+
},
|
| 2488 |
+
{
|
| 2489 |
+
"epoch": 33.65384615384615,
|
| 2490 |
+
"grad_norm": 1.2854979038238525,
|
| 2491 |
+
"learning_rate": 1.0857446808510639e-05,
|
| 2492 |
+
"loss": 0.0056,
|
| 2493 |
+
"step": 3500
|
| 2494 |
+
},
|
| 2495 |
+
{
|
| 2496 |
+
"epoch": 33.75,
|
| 2497 |
+
"grad_norm": 0.6309840679168701,
|
| 2498 |
+
"learning_rate": 1.0793617021276596e-05,
|
| 2499 |
+
"loss": 0.0051,
|
| 2500 |
+
"step": 3510
|
| 2501 |
+
},
|
| 2502 |
+
{
|
| 2503 |
+
"epoch": 33.84615384615385,
|
| 2504 |
+
"grad_norm": 0.35604169964790344,
|
| 2505 |
+
"learning_rate": 1.0729787234042553e-05,
|
| 2506 |
+
"loss": 0.0048,
|
| 2507 |
+
"step": 3520
|
| 2508 |
+
},
|
| 2509 |
+
{
|
| 2510 |
+
"epoch": 33.94230769230769,
|
| 2511 |
+
"grad_norm": 0.038923054933547974,
|
| 2512 |
+
"learning_rate": 1.066595744680851e-05,
|
| 2513 |
+
"loss": 0.0039,
|
| 2514 |
+
"step": 3530
|
| 2515 |
+
},
|
| 2516 |
+
{
|
| 2517 |
+
"epoch": 34.03846153846154,
|
| 2518 |
+
"grad_norm": 0.10073179751634598,
|
| 2519 |
+
"learning_rate": 1.0602127659574468e-05,
|
| 2520 |
+
"loss": 0.0036,
|
| 2521 |
+
"step": 3540
|
| 2522 |
+
},
|
| 2523 |
+
{
|
| 2524 |
+
"epoch": 34.13461538461539,
|
| 2525 |
+
"grad_norm": 0.10360430926084518,
|
| 2526 |
+
"learning_rate": 1.0538297872340425e-05,
|
| 2527 |
+
"loss": 0.0041,
|
| 2528 |
+
"step": 3550
|
| 2529 |
+
},
|
| 2530 |
+
{
|
| 2531 |
+
"epoch": 34.23076923076923,
|
| 2532 |
+
"grad_norm": 0.1899426281452179,
|
| 2533 |
+
"learning_rate": 1.0474468085106383e-05,
|
| 2534 |
+
"loss": 0.0049,
|
| 2535 |
+
"step": 3560
|
| 2536 |
+
},
|
| 2537 |
+
{
|
| 2538 |
+
"epoch": 34.32692307692308,
|
| 2539 |
+
"grad_norm": 0.7377802133560181,
|
| 2540 |
+
"learning_rate": 1.041063829787234e-05,
|
| 2541 |
+
"loss": 0.0077,
|
| 2542 |
+
"step": 3570
|
| 2543 |
+
},
|
| 2544 |
+
{
|
| 2545 |
+
"epoch": 34.42307692307692,
|
| 2546 |
+
"grad_norm": 0.056161731481552124,
|
| 2547 |
+
"learning_rate": 1.0346808510638297e-05,
|
| 2548 |
+
"loss": 0.0049,
|
| 2549 |
+
"step": 3580
|
| 2550 |
+
},
|
| 2551 |
+
{
|
| 2552 |
+
"epoch": 34.51923076923077,
|
| 2553 |
+
"grad_norm": 0.7138869762420654,
|
| 2554 |
+
"learning_rate": 1.0282978723404255e-05,
|
| 2555 |
+
"loss": 0.0037,
|
| 2556 |
+
"step": 3590
|
| 2557 |
+
},
|
| 2558 |
+
{
|
| 2559 |
+
"epoch": 34.61538461538461,
|
| 2560 |
+
"grad_norm": 0.47865352034568787,
|
| 2561 |
+
"learning_rate": 1.0219148936170212e-05,
|
| 2562 |
+
"loss": 0.0049,
|
| 2563 |
+
"step": 3600
|
| 2564 |
+
},
|
| 2565 |
+
{
|
| 2566 |
+
"epoch": 34.71153846153846,
|
| 2567 |
+
"grad_norm": 0.032178666442632675,
|
| 2568 |
+
"learning_rate": 1.015531914893617e-05,
|
| 2569 |
+
"loss": 0.0045,
|
| 2570 |
+
"step": 3610
|
| 2571 |
+
},
|
| 2572 |
+
{
|
| 2573 |
+
"epoch": 34.80769230769231,
|
| 2574 |
+
"grad_norm": 0.7013983130455017,
|
| 2575 |
+
"learning_rate": 1.0091489361702128e-05,
|
| 2576 |
+
"loss": 0.0043,
|
| 2577 |
+
"step": 3620
|
| 2578 |
+
},
|
| 2579 |
+
{
|
| 2580 |
+
"epoch": 34.90384615384615,
|
| 2581 |
+
"grad_norm": 0.3409075438976288,
|
| 2582 |
+
"learning_rate": 1.0027659574468085e-05,
|
| 2583 |
+
"loss": 0.0046,
|
| 2584 |
+
"step": 3630
|
| 2585 |
+
},
|
| 2586 |
+
{
|
| 2587 |
+
"epoch": 35.0,
|
| 2588 |
+
"grad_norm": 0.06704340875148773,
|
| 2589 |
+
"learning_rate": 9.963829787234043e-06,
|
| 2590 |
+
"loss": 0.0069,
|
| 2591 |
+
"step": 3640
|
| 2592 |
+
},
|
| 2593 |
+
{
|
| 2594 |
+
"epoch": 35.09615384615385,
|
| 2595 |
+
"grad_norm": 1.4539157152175903,
|
| 2596 |
+
"learning_rate": 9.9e-06,
|
| 2597 |
+
"loss": 0.0047,
|
| 2598 |
+
"step": 3650
|
| 2599 |
+
},
|
| 2600 |
+
{
|
| 2601 |
+
"epoch": 35.19230769230769,
|
| 2602 |
+
"grad_norm": 0.1617375612258911,
|
| 2603 |
+
"learning_rate": 9.836170212765957e-06,
|
| 2604 |
+
"loss": 0.0036,
|
| 2605 |
+
"step": 3660
|
| 2606 |
+
},
|
| 2607 |
+
{
|
| 2608 |
+
"epoch": 35.28846153846154,
|
| 2609 |
+
"grad_norm": 0.190397247672081,
|
| 2610 |
+
"learning_rate": 9.772340425531915e-06,
|
| 2611 |
+
"loss": 0.0049,
|
| 2612 |
+
"step": 3670
|
| 2613 |
+
},
|
| 2614 |
+
{
|
| 2615 |
+
"epoch": 35.38461538461539,
|
| 2616 |
+
"grad_norm": 0.31659790873527527,
|
| 2617 |
+
"learning_rate": 9.708510638297872e-06,
|
| 2618 |
+
"loss": 0.0064,
|
| 2619 |
+
"step": 3680
|
| 2620 |
+
},
|
| 2621 |
+
{
|
| 2622 |
+
"epoch": 35.48076923076923,
|
| 2623 |
+
"grad_norm": 0.3006196618080139,
|
| 2624 |
+
"learning_rate": 9.64468085106383e-06,
|
| 2625 |
+
"loss": 0.0053,
|
| 2626 |
+
"step": 3690
|
| 2627 |
+
},
|
| 2628 |
+
{
|
| 2629 |
+
"epoch": 35.57692307692308,
|
| 2630 |
+
"grad_norm": 0.07199200987815857,
|
| 2631 |
+
"learning_rate": 9.580851063829788e-06,
|
| 2632 |
+
"loss": 0.0045,
|
| 2633 |
+
"step": 3700
|
| 2634 |
+
},
|
| 2635 |
+
{
|
| 2636 |
+
"epoch": 35.67307692307692,
|
| 2637 |
+
"grad_norm": 0.5229556560516357,
|
| 2638 |
+
"learning_rate": 9.517021276595746e-06,
|
| 2639 |
+
"loss": 0.0038,
|
| 2640 |
+
"step": 3710
|
| 2641 |
+
},
|
| 2642 |
+
{
|
| 2643 |
+
"epoch": 35.76923076923077,
|
| 2644 |
+
"grad_norm": 0.6748898029327393,
|
| 2645 |
+
"learning_rate": 9.453191489361703e-06,
|
| 2646 |
+
"loss": 0.0086,
|
| 2647 |
+
"step": 3720
|
| 2648 |
+
},
|
| 2649 |
+
{
|
| 2650 |
+
"epoch": 35.86538461538461,
|
| 2651 |
+
"grad_norm": 0.24701105058193207,
|
| 2652 |
+
"learning_rate": 9.38936170212766e-06,
|
| 2653 |
+
"loss": 0.0047,
|
| 2654 |
+
"step": 3730
|
| 2655 |
+
},
|
| 2656 |
+
{
|
| 2657 |
+
"epoch": 35.96153846153846,
|
| 2658 |
+
"grad_norm": 0.4330107271671295,
|
| 2659 |
+
"learning_rate": 9.325531914893617e-06,
|
| 2660 |
+
"loss": 0.0039,
|
| 2661 |
+
"step": 3740
|
| 2662 |
+
},
|
| 2663 |
+
{
|
| 2664 |
+
"epoch": 36.05769230769231,
|
| 2665 |
+
"grad_norm": 0.24795526266098022,
|
| 2666 |
+
"learning_rate": 9.261702127659575e-06,
|
| 2667 |
+
"loss": 0.0037,
|
| 2668 |
+
"step": 3750
|
| 2669 |
+
},
|
| 2670 |
+
{
|
| 2671 |
+
"epoch": 36.15384615384615,
|
| 2672 |
+
"grad_norm": 0.5435231328010559,
|
| 2673 |
+
"learning_rate": 9.197872340425532e-06,
|
| 2674 |
+
"loss": 0.0047,
|
| 2675 |
+
"step": 3760
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 36.25,
|
| 2679 |
+
"grad_norm": 0.5274829864501953,
|
| 2680 |
+
"learning_rate": 9.13404255319149e-06,
|
| 2681 |
+
"loss": 0.0048,
|
| 2682 |
+
"step": 3770
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 36.34615384615385,
|
| 2686 |
+
"grad_norm": 0.40137821435928345,
|
| 2687 |
+
"learning_rate": 9.070212765957447e-06,
|
| 2688 |
+
"loss": 0.0054,
|
| 2689 |
+
"step": 3780
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 36.44230769230769,
|
| 2693 |
+
"grad_norm": 0.2212786227464676,
|
| 2694 |
+
"learning_rate": 9.006382978723404e-06,
|
| 2695 |
+
"loss": 0.0052,
|
| 2696 |
+
"step": 3790
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 36.53846153846154,
|
| 2700 |
+
"grad_norm": 0.43687814474105835,
|
| 2701 |
+
"learning_rate": 8.942553191489363e-06,
|
| 2702 |
+
"loss": 0.0035,
|
| 2703 |
+
"step": 3800
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 36.63461538461539,
|
| 2707 |
+
"grad_norm": 0.21894030272960663,
|
| 2708 |
+
"learning_rate": 8.87872340425532e-06,
|
| 2709 |
+
"loss": 0.0048,
|
| 2710 |
+
"step": 3810
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 36.73076923076923,
|
| 2714 |
+
"grad_norm": 1.4914783239364624,
|
| 2715 |
+
"learning_rate": 8.814893617021278e-06,
|
| 2716 |
+
"loss": 0.0037,
|
| 2717 |
+
"step": 3820
|
| 2718 |
+
},
|
| 2719 |
+
{
|
| 2720 |
+
"epoch": 36.82692307692308,
|
| 2721 |
+
"grad_norm": 0.32890626788139343,
|
| 2722 |
+
"learning_rate": 8.751063829787235e-06,
|
| 2723 |
+
"loss": 0.0043,
|
| 2724 |
+
"step": 3830
|
| 2725 |
+
},
|
| 2726 |
+
{
|
| 2727 |
+
"epoch": 36.92307692307692,
|
| 2728 |
+
"grad_norm": 0.3183184266090393,
|
| 2729 |
+
"learning_rate": 8.687234042553192e-06,
|
| 2730 |
+
"loss": 0.0026,
|
| 2731 |
+
"step": 3840
|
| 2732 |
+
},
|
| 2733 |
+
{
|
| 2734 |
+
"epoch": 37.01923076923077,
|
| 2735 |
+
"grad_norm": 0.4841859042644501,
|
| 2736 |
+
"learning_rate": 8.62340425531915e-06,
|
| 2737 |
+
"loss": 0.003,
|
| 2738 |
+
"step": 3850
|
| 2739 |
+
},
|
| 2740 |
+
{
|
| 2741 |
+
"epoch": 37.11538461538461,
|
| 2742 |
+
"grad_norm": 0.4076668620109558,
|
| 2743 |
+
"learning_rate": 8.559574468085107e-06,
|
| 2744 |
+
"loss": 0.0032,
|
| 2745 |
+
"step": 3860
|
| 2746 |
+
},
|
| 2747 |
+
{
|
| 2748 |
+
"epoch": 37.21153846153846,
|
| 2749 |
+
"grad_norm": 0.05997830256819725,
|
| 2750 |
+
"learning_rate": 8.495744680851064e-06,
|
| 2751 |
+
"loss": 0.0043,
|
| 2752 |
+
"step": 3870
|
| 2753 |
+
},
|
| 2754 |
+
{
|
| 2755 |
+
"epoch": 37.30769230769231,
|
| 2756 |
+
"grad_norm": 0.20216123759746552,
|
| 2757 |
+
"learning_rate": 8.431914893617021e-06,
|
| 2758 |
+
"loss": 0.003,
|
| 2759 |
+
"step": 3880
|
| 2760 |
+
},
|
| 2761 |
+
{
|
| 2762 |
+
"epoch": 37.40384615384615,
|
| 2763 |
+
"grad_norm": 0.19002175331115723,
|
| 2764 |
+
"learning_rate": 8.368085106382979e-06,
|
| 2765 |
+
"loss": 0.0061,
|
| 2766 |
+
"step": 3890
|
| 2767 |
+
},
|
| 2768 |
+
{
|
| 2769 |
+
"epoch": 37.5,
|
| 2770 |
+
"grad_norm": 0.051696181297302246,
|
| 2771 |
+
"learning_rate": 8.304255319148936e-06,
|
| 2772 |
+
"loss": 0.0026,
|
| 2773 |
+
"step": 3900
|
| 2774 |
+
},
|
| 2775 |
+
{
|
| 2776 |
+
"epoch": 37.59615384615385,
|
| 2777 |
+
"grad_norm": 0.1388806402683258,
|
| 2778 |
+
"learning_rate": 8.240425531914893e-06,
|
| 2779 |
+
"loss": 0.0043,
|
| 2780 |
+
"step": 3910
|
| 2781 |
+
},
|
| 2782 |
+
{
|
| 2783 |
+
"epoch": 37.69230769230769,
|
| 2784 |
+
"grad_norm": 0.24038566648960114,
|
| 2785 |
+
"learning_rate": 8.17659574468085e-06,
|
| 2786 |
+
"loss": 0.0059,
|
| 2787 |
+
"step": 3920
|
| 2788 |
+
},
|
| 2789 |
+
{
|
| 2790 |
+
"epoch": 37.78846153846154,
|
| 2791 |
+
"grad_norm": 0.04175787419080734,
|
| 2792 |
+
"learning_rate": 8.112765957446808e-06,
|
| 2793 |
+
"loss": 0.0037,
|
| 2794 |
+
"step": 3930
|
| 2795 |
+
},
|
| 2796 |
+
{
|
| 2797 |
+
"epoch": 37.88461538461539,
|
| 2798 |
+
"grad_norm": 0.15831300616264343,
|
| 2799 |
+
"learning_rate": 8.048936170212765e-06,
|
| 2800 |
+
"loss": 0.0048,
|
| 2801 |
+
"step": 3940
|
| 2802 |
+
},
|
| 2803 |
+
{
|
| 2804 |
+
"epoch": 37.98076923076923,
|
| 2805 |
+
"grad_norm": 0.40547874569892883,
|
| 2806 |
+
"learning_rate": 7.985106382978723e-06,
|
| 2807 |
+
"loss": 0.0054,
|
| 2808 |
+
"step": 3950
|
| 2809 |
+
},
|
| 2810 |
+
{
|
| 2811 |
+
"epoch": 38.07692307692308,
|
| 2812 |
+
"grad_norm": 0.4601777493953705,
|
| 2813 |
+
"learning_rate": 7.92127659574468e-06,
|
| 2814 |
+
"loss": 0.0046,
|
| 2815 |
+
"step": 3960
|
| 2816 |
+
},
|
| 2817 |
+
{
|
| 2818 |
+
"epoch": 38.17307692307692,
|
| 2819 |
+
"grad_norm": 1.0779550075531006,
|
| 2820 |
+
"learning_rate": 7.857446808510637e-06,
|
| 2821 |
+
"loss": 0.0048,
|
| 2822 |
+
"step": 3970
|
| 2823 |
+
},
|
| 2824 |
+
{
|
| 2825 |
+
"epoch": 38.26923076923077,
|
| 2826 |
+
"grad_norm": 1.490932822227478,
|
| 2827 |
+
"learning_rate": 7.793617021276596e-06,
|
| 2828 |
+
"loss": 0.0068,
|
| 2829 |
+
"step": 3980
|
| 2830 |
+
},
|
| 2831 |
+
{
|
| 2832 |
+
"epoch": 38.36538461538461,
|
| 2833 |
+
"grad_norm": 0.7527866363525391,
|
| 2834 |
+
"learning_rate": 7.729787234042553e-06,
|
| 2835 |
+
"loss": 0.0044,
|
| 2836 |
+
"step": 3990
|
| 2837 |
+
},
|
| 2838 |
+
{
|
| 2839 |
+
"epoch": 38.46153846153846,
|
| 2840 |
+
"grad_norm": 0.030520111322402954,
|
| 2841 |
+
"learning_rate": 7.66595744680851e-06,
|
| 2842 |
+
"loss": 0.0041,
|
| 2843 |
+
"step": 4000
|
| 2844 |
+
},
|
| 2845 |
+
{
|
| 2846 |
+
"epoch": 38.46153846153846,
|
| 2847 |
+
"eval_correct_predictions": 1400,
|
| 2848 |
+
"eval_exact_match_accuracy": 0.9893992932862191,
|
| 2849 |
+
"eval_loss": 0.004963812418282032,
|
| 2850 |
+
"eval_runtime": 75.6553,
|
| 2851 |
+
"eval_samples_per_second": 18.703,
|
| 2852 |
+
"eval_steps_per_second": 0.304,
|
| 2853 |
+
"eval_total_predictions": 1415,
|
| 2854 |
+
"step": 4000
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 38.55769230769231,
|
| 2858 |
+
"grad_norm": 0.2399033159017563,
|
| 2859 |
+
"learning_rate": 7.602127659574469e-06,
|
| 2860 |
+
"loss": 0.0049,
|
| 2861 |
+
"step": 4010
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 38.65384615384615,
|
| 2865 |
+
"grad_norm": 0.300660103559494,
|
| 2866 |
+
"learning_rate": 7.538297872340426e-06,
|
| 2867 |
+
"loss": 0.0039,
|
| 2868 |
+
"step": 4020
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 38.75,
|
| 2872 |
+
"grad_norm": 0.08755325525999069,
|
| 2873 |
+
"learning_rate": 7.4744680851063834e-06,
|
| 2874 |
+
"loss": 0.0069,
|
| 2875 |
+
"step": 4030
|
| 2876 |
+
},
|
| 2877 |
+
{
|
| 2878 |
+
"epoch": 38.84615384615385,
|
| 2879 |
+
"grad_norm": 0.5832145810127258,
|
| 2880 |
+
"learning_rate": 7.410638297872341e-06,
|
| 2881 |
+
"loss": 0.0051,
|
| 2882 |
+
"step": 4040
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 38.94230769230769,
|
| 2886 |
+
"grad_norm": 0.31291982531547546,
|
| 2887 |
+
"learning_rate": 7.346808510638298e-06,
|
| 2888 |
+
"loss": 0.003,
|
| 2889 |
+
"step": 4050
|
| 2890 |
+
},
|
| 2891 |
+
{
|
| 2892 |
+
"epoch": 39.03846153846154,
|
| 2893 |
+
"grad_norm": 0.39460045099258423,
|
| 2894 |
+
"learning_rate": 7.282978723404255e-06,
|
| 2895 |
+
"loss": 0.0029,
|
| 2896 |
+
"step": 4060
|
| 2897 |
+
},
|
| 2898 |
+
{
|
| 2899 |
+
"epoch": 39.13461538461539,
|
| 2900 |
+
"grad_norm": 0.4764561951160431,
|
| 2901 |
+
"learning_rate": 7.219148936170213e-06,
|
| 2902 |
+
"loss": 0.0031,
|
| 2903 |
+
"step": 4070
|
| 2904 |
+
},
|
| 2905 |
+
{
|
| 2906 |
+
"epoch": 39.23076923076923,
|
| 2907 |
+
"grad_norm": 0.05070360749959946,
|
| 2908 |
+
"learning_rate": 7.15531914893617e-06,
|
| 2909 |
+
"loss": 0.0057,
|
| 2910 |
+
"step": 4080
|
| 2911 |
+
},
|
| 2912 |
+
{
|
| 2913 |
+
"epoch": 39.32692307692308,
|
| 2914 |
+
"grad_norm": 0.23319944739341736,
|
| 2915 |
+
"learning_rate": 7.091489361702127e-06,
|
| 2916 |
+
"loss": 0.0046,
|
| 2917 |
+
"step": 4090
|
| 2918 |
+
},
|
| 2919 |
+
{
|
| 2920 |
+
"epoch": 39.42307692307692,
|
| 2921 |
+
"grad_norm": 0.10411890596151352,
|
| 2922 |
+
"learning_rate": 7.0276595744680846e-06,
|
| 2923 |
+
"loss": 0.0038,
|
| 2924 |
+
"step": 4100
|
| 2925 |
+
},
|
| 2926 |
+
{
|
| 2927 |
+
"epoch": 39.51923076923077,
|
| 2928 |
+
"grad_norm": 0.3427359163761139,
|
| 2929 |
+
"learning_rate": 6.963829787234043e-06,
|
| 2930 |
+
"loss": 0.0058,
|
| 2931 |
+
"step": 4110
|
| 2932 |
+
},
|
| 2933 |
+
{
|
| 2934 |
+
"epoch": 39.61538461538461,
|
| 2935 |
+
"grad_norm": 0.7232850790023804,
|
| 2936 |
+
"learning_rate": 6.900000000000001e-06,
|
| 2937 |
+
"loss": 0.0035,
|
| 2938 |
+
"step": 4120
|
| 2939 |
+
},
|
| 2940 |
+
{
|
| 2941 |
+
"epoch": 39.71153846153846,
|
| 2942 |
+
"grad_norm": 0.012613312341272831,
|
| 2943 |
+
"learning_rate": 6.836170212765958e-06,
|
| 2944 |
+
"loss": 0.0022,
|
| 2945 |
+
"step": 4130
|
| 2946 |
+
},
|
| 2947 |
+
{
|
| 2948 |
+
"epoch": 39.80769230769231,
|
| 2949 |
+
"grad_norm": 0.922091543674469,
|
| 2950 |
+
"learning_rate": 6.7723404255319155e-06,
|
| 2951 |
+
"loss": 0.0048,
|
| 2952 |
+
"step": 4140
|
| 2953 |
+
},
|
| 2954 |
+
{
|
| 2955 |
+
"epoch": 39.90384615384615,
|
| 2956 |
+
"grad_norm": 0.4784044325351715,
|
| 2957 |
+
"learning_rate": 6.708510638297873e-06,
|
| 2958 |
+
"loss": 0.0044,
|
| 2959 |
+
"step": 4150
|
| 2960 |
+
},
|
| 2961 |
+
{
|
| 2962 |
+
"epoch": 40.0,
|
| 2963 |
+
"grad_norm": 4.750979900360107,
|
| 2964 |
+
"learning_rate": 6.64468085106383e-06,
|
| 2965 |
+
"loss": 0.0045,
|
| 2966 |
+
"step": 4160
|
| 2967 |
+
},
|
| 2968 |
+
{
|
| 2969 |
+
"epoch": 40.09615384615385,
|
| 2970 |
+
"grad_norm": 0.5721331834793091,
|
| 2971 |
+
"learning_rate": 6.580851063829787e-06,
|
| 2972 |
+
"loss": 0.0061,
|
| 2973 |
+
"step": 4170
|
| 2974 |
+
},
|
| 2975 |
+
{
|
| 2976 |
+
"epoch": 40.19230769230769,
|
| 2977 |
+
"grad_norm": 0.9367163777351379,
|
| 2978 |
+
"learning_rate": 6.517021276595745e-06,
|
| 2979 |
+
"loss": 0.0052,
|
| 2980 |
+
"step": 4180
|
| 2981 |
+
},
|
| 2982 |
+
{
|
| 2983 |
+
"epoch": 40.28846153846154,
|
| 2984 |
+
"grad_norm": 0.008925567381083965,
|
| 2985 |
+
"learning_rate": 6.453191489361702e-06,
|
| 2986 |
+
"loss": 0.0043,
|
| 2987 |
+
"step": 4190
|
| 2988 |
+
},
|
| 2989 |
+
{
|
| 2990 |
+
"epoch": 40.38461538461539,
|
| 2991 |
+
"grad_norm": 0.5253669023513794,
|
| 2992 |
+
"learning_rate": 6.38936170212766e-06,
|
| 2993 |
+
"loss": 0.0049,
|
| 2994 |
+
"step": 4200
|
| 2995 |
+
},
|
| 2996 |
+
{
|
| 2997 |
+
"epoch": 40.48076923076923,
|
| 2998 |
+
"grad_norm": 0.048985060304403305,
|
| 2999 |
+
"learning_rate": 6.325531914893617e-06,
|
| 3000 |
+
"loss": 0.0064,
|
| 3001 |
+
"step": 4210
|
| 3002 |
+
},
|
| 3003 |
+
{
|
| 3004 |
+
"epoch": 40.57692307692308,
|
| 3005 |
+
"grad_norm": 0.1342606544494629,
|
| 3006 |
+
"learning_rate": 6.261702127659575e-06,
|
| 3007 |
+
"loss": 0.0034,
|
| 3008 |
+
"step": 4220
|
| 3009 |
+
},
|
| 3010 |
+
{
|
| 3011 |
+
"epoch": 40.67307692307692,
|
| 3012 |
+
"grad_norm": 0.06901761889457703,
|
| 3013 |
+
"learning_rate": 6.197872340425532e-06,
|
| 3014 |
+
"loss": 0.0035,
|
| 3015 |
+
"step": 4230
|
| 3016 |
+
},
|
| 3017 |
+
{
|
| 3018 |
+
"epoch": 40.76923076923077,
|
| 3019 |
+
"grad_norm": 0.13464286923408508,
|
| 3020 |
+
"learning_rate": 6.134042553191489e-06,
|
| 3021 |
+
"loss": 0.005,
|
| 3022 |
+
"step": 4240
|
| 3023 |
+
},
|
| 3024 |
+
{
|
| 3025 |
+
"epoch": 40.86538461538461,
|
| 3026 |
+
"grad_norm": 0.43832606077194214,
|
| 3027 |
+
"learning_rate": 6.070212765957447e-06,
|
| 3028 |
+
"loss": 0.0031,
|
| 3029 |
+
"step": 4250
|
| 3030 |
+
},
|
| 3031 |
+
{
|
| 3032 |
+
"epoch": 40.96153846153846,
|
| 3033 |
+
"grad_norm": 0.44453272223472595,
|
| 3034 |
+
"learning_rate": 6.006382978723404e-06,
|
| 3035 |
+
"loss": 0.0048,
|
| 3036 |
+
"step": 4260
|
| 3037 |
+
},
|
| 3038 |
+
{
|
| 3039 |
+
"epoch": 41.05769230769231,
|
| 3040 |
+
"grad_norm": 0.47965118288993835,
|
| 3041 |
+
"learning_rate": 5.942553191489361e-06,
|
| 3042 |
+
"loss": 0.0042,
|
| 3043 |
+
"step": 4270
|
| 3044 |
+
},
|
| 3045 |
+
{
|
| 3046 |
+
"epoch": 41.15384615384615,
|
| 3047 |
+
"grad_norm": 0.10220217704772949,
|
| 3048 |
+
"learning_rate": 5.878723404255319e-06,
|
| 3049 |
+
"loss": 0.0049,
|
| 3050 |
+
"step": 4280
|
| 3051 |
+
},
|
| 3052 |
+
{
|
| 3053 |
+
"epoch": 41.25,
|
| 3054 |
+
"grad_norm": 0.4104725420475006,
|
| 3055 |
+
"learning_rate": 5.8148936170212775e-06,
|
| 3056 |
+
"loss": 0.0036,
|
| 3057 |
+
"step": 4290
|
| 3058 |
+
},
|
| 3059 |
+
{
|
| 3060 |
+
"epoch": 41.34615384615385,
|
| 3061 |
+
"grad_norm": 0.1370197832584381,
|
| 3062 |
+
"learning_rate": 5.751063829787235e-06,
|
| 3063 |
+
"loss": 0.0022,
|
| 3064 |
+
"step": 4300
|
| 3065 |
+
},
|
| 3066 |
+
{
|
| 3067 |
+
"epoch": 41.44230769230769,
|
| 3068 |
+
"grad_norm": 0.6965671181678772,
|
| 3069 |
+
"learning_rate": 5.687234042553192e-06,
|
| 3070 |
+
"loss": 0.0047,
|
| 3071 |
+
"step": 4310
|
| 3072 |
+
},
|
| 3073 |
+
{
|
| 3074 |
+
"epoch": 41.53846153846154,
|
| 3075 |
+
"grad_norm": 0.17734394967556,
|
| 3076 |
+
"learning_rate": 5.623404255319149e-06,
|
| 3077 |
+
"loss": 0.003,
|
| 3078 |
+
"step": 4320
|
| 3079 |
+
},
|
| 3080 |
+
{
|
| 3081 |
+
"epoch": 41.63461538461539,
|
| 3082 |
+
"grad_norm": 0.01661546155810356,
|
| 3083 |
+
"learning_rate": 5.559574468085107e-06,
|
| 3084 |
+
"loss": 0.0038,
|
| 3085 |
+
"step": 4330
|
| 3086 |
+
},
|
| 3087 |
+
{
|
| 3088 |
+
"epoch": 41.73076923076923,
|
| 3089 |
+
"grad_norm": 0.17337529361248016,
|
| 3090 |
+
"learning_rate": 5.495744680851064e-06,
|
| 3091 |
+
"loss": 0.0045,
|
| 3092 |
+
"step": 4340
|
| 3093 |
+
},
|
| 3094 |
+
{
|
| 3095 |
+
"epoch": 41.82692307692308,
|
| 3096 |
+
"grad_norm": 0.40350341796875,
|
| 3097 |
+
"learning_rate": 5.431914893617021e-06,
|
| 3098 |
+
"loss": 0.0061,
|
| 3099 |
+
"step": 4350
|
| 3100 |
+
},
|
| 3101 |
+
{
|
| 3102 |
+
"epoch": 41.92307692307692,
|
| 3103 |
+
"grad_norm": 0.17201651632785797,
|
| 3104 |
+
"learning_rate": 5.368085106382979e-06,
|
| 3105 |
+
"loss": 0.004,
|
| 3106 |
+
"step": 4360
|
| 3107 |
+
},
|
| 3108 |
+
{
|
| 3109 |
+
"epoch": 42.01923076923077,
|
| 3110 |
+
"grad_norm": 0.5255150198936462,
|
| 3111 |
+
"learning_rate": 5.304255319148936e-06,
|
| 3112 |
+
"loss": 0.0033,
|
| 3113 |
+
"step": 4370
|
| 3114 |
+
},
|
| 3115 |
+
{
|
| 3116 |
+
"epoch": 42.11538461538461,
|
| 3117 |
+
"grad_norm": 0.758439302444458,
|
| 3118 |
+
"learning_rate": 5.240425531914894e-06,
|
| 3119 |
+
"loss": 0.005,
|
| 3120 |
+
"step": 4380
|
| 3121 |
+
},
|
| 3122 |
+
{
|
| 3123 |
+
"epoch": 42.21153846153846,
|
| 3124 |
+
"grad_norm": 0.7857176661491394,
|
| 3125 |
+
"learning_rate": 5.176595744680851e-06,
|
| 3126 |
+
"loss": 0.004,
|
| 3127 |
+
"step": 4390
|
| 3128 |
+
},
|
| 3129 |
+
{
|
| 3130 |
+
"epoch": 42.30769230769231,
|
| 3131 |
+
"grad_norm": 0.38413724303245544,
|
| 3132 |
+
"learning_rate": 5.112765957446809e-06,
|
| 3133 |
+
"loss": 0.0022,
|
| 3134 |
+
"step": 4400
|
| 3135 |
+
},
|
| 3136 |
+
{
|
| 3137 |
+
"epoch": 42.40384615384615,
|
| 3138 |
+
"grad_norm": 0.457057923078537,
|
| 3139 |
+
"learning_rate": 5.048936170212766e-06,
|
| 3140 |
+
"loss": 0.0041,
|
| 3141 |
+
"step": 4410
|
| 3142 |
+
},
|
| 3143 |
+
{
|
| 3144 |
+
"epoch": 42.5,
|
| 3145 |
+
"grad_norm": 0.028009217232465744,
|
| 3146 |
+
"learning_rate": 4.985106382978723e-06,
|
| 3147 |
+
"loss": 0.0025,
|
| 3148 |
+
"step": 4420
|
| 3149 |
+
},
|
| 3150 |
+
{
|
| 3151 |
+
"epoch": 42.59615384615385,
|
| 3152 |
+
"grad_norm": 0.7792872190475464,
|
| 3153 |
+
"learning_rate": 4.9212765957446806e-06,
|
| 3154 |
+
"loss": 0.0052,
|
| 3155 |
+
"step": 4430
|
| 3156 |
+
},
|
| 3157 |
+
{
|
| 3158 |
+
"epoch": 42.69230769230769,
|
| 3159 |
+
"grad_norm": 0.46134594082832336,
|
| 3160 |
+
"learning_rate": 4.857446808510638e-06,
|
| 3161 |
+
"loss": 0.0017,
|
| 3162 |
+
"step": 4440
|
| 3163 |
+
},
|
| 3164 |
+
{
|
| 3165 |
+
"epoch": 42.78846153846154,
|
| 3166 |
+
"grad_norm": 0.43057435750961304,
|
| 3167 |
+
"learning_rate": 4.793617021276596e-06,
|
| 3168 |
+
"loss": 0.0038,
|
| 3169 |
+
"step": 4450
|
| 3170 |
+
},
|
| 3171 |
+
{
|
| 3172 |
+
"epoch": 42.88461538461539,
|
| 3173 |
+
"grad_norm": 0.2747887372970581,
|
| 3174 |
+
"learning_rate": 4.729787234042553e-06,
|
| 3175 |
+
"loss": 0.0052,
|
| 3176 |
+
"step": 4460
|
| 3177 |
+
},
|
| 3178 |
+
{
|
| 3179 |
+
"epoch": 42.98076923076923,
|
| 3180 |
+
"grad_norm": 0.053347088396549225,
|
| 3181 |
+
"learning_rate": 4.6659574468085115e-06,
|
| 3182 |
+
"loss": 0.0046,
|
| 3183 |
+
"step": 4470
|
| 3184 |
+
},
|
| 3185 |
+
{
|
| 3186 |
+
"epoch": 43.07692307692308,
|
| 3187 |
+
"grad_norm": 0.5245047807693481,
|
| 3188 |
+
"learning_rate": 4.602127659574469e-06,
|
| 3189 |
+
"loss": 0.004,
|
| 3190 |
+
"step": 4480
|
| 3191 |
+
},
|
| 3192 |
+
{
|
| 3193 |
+
"epoch": 43.17307692307692,
|
| 3194 |
+
"grad_norm": 0.14071467518806458,
|
| 3195 |
+
"learning_rate": 4.538297872340426e-06,
|
| 3196 |
+
"loss": 0.0036,
|
| 3197 |
+
"step": 4490
|
| 3198 |
+
},
|
| 3199 |
+
{
|
| 3200 |
+
"epoch": 43.26923076923077,
|
| 3201 |
+
"grad_norm": 0.5309870839118958,
|
| 3202 |
+
"learning_rate": 4.474468085106383e-06,
|
| 3203 |
+
"loss": 0.0056,
|
| 3204 |
+
"step": 4500
|
| 3205 |
+
},
|
| 3206 |
+
{
|
| 3207 |
+
"epoch": 43.36538461538461,
|
| 3208 |
+
"grad_norm": 0.6158878803253174,
|
| 3209 |
+
"learning_rate": 4.410638297872341e-06,
|
| 3210 |
+
"loss": 0.0032,
|
| 3211 |
+
"step": 4510
|
| 3212 |
+
},
|
| 3213 |
+
{
|
| 3214 |
+
"epoch": 43.46153846153846,
|
| 3215 |
+
"grad_norm": 0.3933374881744385,
|
| 3216 |
+
"learning_rate": 4.346808510638298e-06,
|
| 3217 |
+
"loss": 0.0027,
|
| 3218 |
+
"step": 4520
|
| 3219 |
+
},
|
| 3220 |
+
{
|
| 3221 |
+
"epoch": 43.55769230769231,
|
| 3222 |
+
"grad_norm": 0.32318615913391113,
|
| 3223 |
+
"learning_rate": 4.282978723404255e-06,
|
| 3224 |
+
"loss": 0.0031,
|
| 3225 |
+
"step": 4530
|
| 3226 |
+
},
|
| 3227 |
+
{
|
| 3228 |
+
"epoch": 43.65384615384615,
|
| 3229 |
+
"grad_norm": 0.4188336730003357,
|
| 3230 |
+
"learning_rate": 4.219148936170213e-06,
|
| 3231 |
+
"loss": 0.0038,
|
| 3232 |
+
"step": 4540
|
| 3233 |
+
},
|
| 3234 |
+
{
|
| 3235 |
+
"epoch": 43.75,
|
| 3236 |
+
"grad_norm": 0.13132989406585693,
|
| 3237 |
+
"learning_rate": 4.15531914893617e-06,
|
| 3238 |
+
"loss": 0.0046,
|
| 3239 |
+
"step": 4550
|
| 3240 |
+
},
|
| 3241 |
+
{
|
| 3242 |
+
"epoch": 43.84615384615385,
|
| 3243 |
+
"grad_norm": 0.5103133916854858,
|
| 3244 |
+
"learning_rate": 4.091489361702128e-06,
|
| 3245 |
+
"loss": 0.004,
|
| 3246 |
+
"step": 4560
|
| 3247 |
+
},
|
| 3248 |
+
{
|
| 3249 |
+
"epoch": 43.94230769230769,
|
| 3250 |
+
"grad_norm": 0.11087504774332047,
|
| 3251 |
+
"learning_rate": 4.027659574468085e-06,
|
| 3252 |
+
"loss": 0.003,
|
| 3253 |
+
"step": 4570
|
| 3254 |
+
},
|
| 3255 |
+
{
|
| 3256 |
+
"epoch": 44.03846153846154,
|
| 3257 |
+
"grad_norm": 0.9140055179595947,
|
| 3258 |
+
"learning_rate": 3.963829787234043e-06,
|
| 3259 |
+
"loss": 0.0038,
|
| 3260 |
+
"step": 4580
|
| 3261 |
+
},
|
| 3262 |
+
{
|
| 3263 |
+
"epoch": 44.13461538461539,
|
| 3264 |
+
"grad_norm": 0.41617265343666077,
|
| 3265 |
+
"learning_rate": 3.9e-06,
|
| 3266 |
+
"loss": 0.0036,
|
| 3267 |
+
"step": 4590
|
| 3268 |
+
},
|
| 3269 |
+
{
|
| 3270 |
+
"epoch": 44.23076923076923,
|
| 3271 |
+
"grad_norm": 0.14915060997009277,
|
| 3272 |
+
"learning_rate": 3.836170212765957e-06,
|
| 3273 |
+
"loss": 0.0026,
|
| 3274 |
+
"step": 4600
|
| 3275 |
+
},
|
| 3276 |
+
{
|
| 3277 |
+
"epoch": 44.32692307692308,
|
| 3278 |
+
"grad_norm": 0.045890841633081436,
|
| 3279 |
+
"learning_rate": 3.772340425531915e-06,
|
| 3280 |
+
"loss": 0.0063,
|
| 3281 |
+
"step": 4610
|
| 3282 |
+
},
|
| 3283 |
+
{
|
| 3284 |
+
"epoch": 44.42307692307692,
|
| 3285 |
+
"grad_norm": 0.35580122470855713,
|
| 3286 |
+
"learning_rate": 3.7085106382978723e-06,
|
| 3287 |
+
"loss": 0.0049,
|
| 3288 |
+
"step": 4620
|
| 3289 |
+
},
|
| 3290 |
+
{
|
| 3291 |
+
"epoch": 44.51923076923077,
|
| 3292 |
+
"grad_norm": 0.26410701870918274,
|
| 3293 |
+
"learning_rate": 3.64468085106383e-06,
|
| 3294 |
+
"loss": 0.0029,
|
| 3295 |
+
"step": 4630
|
| 3296 |
+
},
|
| 3297 |
+
{
|
| 3298 |
+
"epoch": 44.61538461538461,
|
| 3299 |
+
"grad_norm": 0.5982622504234314,
|
| 3300 |
+
"learning_rate": 3.5808510638297873e-06,
|
| 3301 |
+
"loss": 0.0023,
|
| 3302 |
+
"step": 4640
|
| 3303 |
+
},
|
| 3304 |
+
{
|
| 3305 |
+
"epoch": 44.71153846153846,
|
| 3306 |
+
"grad_norm": 0.44741129875183105,
|
| 3307 |
+
"learning_rate": 3.5170212765957446e-06,
|
| 3308 |
+
"loss": 0.0039,
|
| 3309 |
+
"step": 4650
|
| 3310 |
+
},
|
| 3311 |
+
{
|
| 3312 |
+
"epoch": 44.80769230769231,
|
| 3313 |
+
"grad_norm": 0.20336119830608368,
|
| 3314 |
+
"learning_rate": 3.4531914893617023e-06,
|
| 3315 |
+
"loss": 0.0025,
|
| 3316 |
+
"step": 4660
|
| 3317 |
+
},
|
| 3318 |
+
{
|
| 3319 |
+
"epoch": 44.90384615384615,
|
| 3320 |
+
"grad_norm": 0.0518646277487278,
|
| 3321 |
+
"learning_rate": 3.3893617021276596e-06,
|
| 3322 |
+
"loss": 0.0031,
|
| 3323 |
+
"step": 4670
|
| 3324 |
+
},
|
| 3325 |
+
{
|
| 3326 |
+
"epoch": 45.0,
|
| 3327 |
+
"grad_norm": 0.021453868597745895,
|
| 3328 |
+
"learning_rate": 3.3255319148936173e-06,
|
| 3329 |
+
"loss": 0.0038,
|
| 3330 |
+
"step": 4680
|
| 3331 |
+
},
|
| 3332 |
+
{
|
| 3333 |
+
"epoch": 45.09615384615385,
|
| 3334 |
+
"grad_norm": 0.059526897966861725,
|
| 3335 |
+
"learning_rate": 3.2617021276595746e-06,
|
| 3336 |
+
"loss": 0.0044,
|
| 3337 |
+
"step": 4690
|
| 3338 |
+
},
|
| 3339 |
+
{
|
| 3340 |
+
"epoch": 45.19230769230769,
|
| 3341 |
+
"grad_norm": 0.03833373263478279,
|
| 3342 |
+
"learning_rate": 3.197872340425532e-06,
|
| 3343 |
+
"loss": 0.0039,
|
| 3344 |
+
"step": 4700
|
| 3345 |
+
},
|
| 3346 |
+
{
|
| 3347 |
+
"epoch": 45.28846153846154,
|
| 3348 |
+
"grad_norm": 0.054637033492326736,
|
| 3349 |
+
"learning_rate": 3.1340425531914892e-06,
|
| 3350 |
+
"loss": 0.0069,
|
| 3351 |
+
"step": 4710
|
| 3352 |
+
},
|
| 3353 |
+
{
|
| 3354 |
+
"epoch": 45.38461538461539,
|
| 3355 |
+
"grad_norm": 0.32997268438339233,
|
| 3356 |
+
"learning_rate": 3.070212765957447e-06,
|
| 3357 |
+
"loss": 0.0033,
|
| 3358 |
+
"step": 4720
|
| 3359 |
+
},
|
| 3360 |
+
{
|
| 3361 |
+
"epoch": 45.48076923076923,
|
| 3362 |
+
"grad_norm": 0.01344509981572628,
|
| 3363 |
+
"learning_rate": 3.0063829787234043e-06,
|
| 3364 |
+
"loss": 0.0047,
|
| 3365 |
+
"step": 4730
|
| 3366 |
+
},
|
| 3367 |
+
{
|
| 3368 |
+
"epoch": 45.57692307692308,
|
| 3369 |
+
"grad_norm": 0.1493314951658249,
|
| 3370 |
+
"learning_rate": 2.942553191489362e-06,
|
| 3371 |
+
"loss": 0.0042,
|
| 3372 |
+
"step": 4740
|
| 3373 |
+
},
|
| 3374 |
+
{
|
| 3375 |
+
"epoch": 45.67307692307692,
|
| 3376 |
+
"grad_norm": 0.5637978911399841,
|
| 3377 |
+
"learning_rate": 2.8787234042553193e-06,
|
| 3378 |
+
"loss": 0.0038,
|
| 3379 |
+
"step": 4750
|
| 3380 |
+
},
|
| 3381 |
+
{
|
| 3382 |
+
"epoch": 45.76923076923077,
|
| 3383 |
+
"grad_norm": 0.8575944304466248,
|
| 3384 |
+
"learning_rate": 2.8148936170212766e-06,
|
| 3385 |
+
"loss": 0.0046,
|
| 3386 |
+
"step": 4760
|
| 3387 |
+
},
|
| 3388 |
+
{
|
| 3389 |
+
"epoch": 45.86538461538461,
|
| 3390 |
+
"grad_norm": 0.810599148273468,
|
| 3391 |
+
"learning_rate": 2.7510638297872343e-06,
|
| 3392 |
+
"loss": 0.0035,
|
| 3393 |
+
"step": 4770
|
| 3394 |
+
},
|
| 3395 |
+
{
|
| 3396 |
+
"epoch": 45.96153846153846,
|
| 3397 |
+
"grad_norm": 0.031988173723220825,
|
| 3398 |
+
"learning_rate": 2.6872340425531916e-06,
|
| 3399 |
+
"loss": 0.0022,
|
| 3400 |
+
"step": 4780
|
| 3401 |
+
},
|
| 3402 |
+
{
|
| 3403 |
+
"epoch": 46.05769230769231,
|
| 3404 |
+
"grad_norm": 0.06916001439094543,
|
| 3405 |
+
"learning_rate": 2.623404255319149e-06,
|
| 3406 |
+
"loss": 0.004,
|
| 3407 |
+
"step": 4790
|
| 3408 |
+
},
|
| 3409 |
+
{
|
| 3410 |
+
"epoch": 46.15384615384615,
|
| 3411 |
+
"grad_norm": 0.04660704359412193,
|
| 3412 |
+
"learning_rate": 2.5595744680851062e-06,
|
| 3413 |
+
"loss": 0.0027,
|
| 3414 |
+
"step": 4800
|
| 3415 |
+
},
|
| 3416 |
+
{
|
| 3417 |
+
"epoch": 46.25,
|
| 3418 |
+
"grad_norm": 1.0712189674377441,
|
| 3419 |
+
"learning_rate": 2.495744680851064e-06,
|
| 3420 |
+
"loss": 0.0032,
|
| 3421 |
+
"step": 4810
|
| 3422 |
+
},
|
| 3423 |
+
{
|
| 3424 |
+
"epoch": 46.34615384615385,
|
| 3425 |
+
"grad_norm": 0.17620952427387238,
|
| 3426 |
+
"learning_rate": 2.4319148936170212e-06,
|
| 3427 |
+
"loss": 0.002,
|
| 3428 |
+
"step": 4820
|
| 3429 |
+
},
|
| 3430 |
+
{
|
| 3431 |
+
"epoch": 46.44230769230769,
|
| 3432 |
+
"grad_norm": 0.29380717873573303,
|
| 3433 |
+
"learning_rate": 2.368085106382979e-06,
|
| 3434 |
+
"loss": 0.0029,
|
| 3435 |
+
"step": 4830
|
| 3436 |
+
},
|
| 3437 |
+
{
|
| 3438 |
+
"epoch": 46.53846153846154,
|
| 3439 |
+
"grad_norm": 0.015064992010593414,
|
| 3440 |
+
"learning_rate": 2.3042553191489363e-06,
|
| 3441 |
+
"loss": 0.0034,
|
| 3442 |
+
"step": 4840
|
| 3443 |
+
},
|
| 3444 |
+
{
|
| 3445 |
+
"epoch": 46.63461538461539,
|
| 3446 |
+
"grad_norm": 0.9566193222999573,
|
| 3447 |
+
"learning_rate": 2.2404255319148936e-06,
|
| 3448 |
+
"loss": 0.0039,
|
| 3449 |
+
"step": 4850
|
| 3450 |
+
},
|
| 3451 |
+
{
|
| 3452 |
+
"epoch": 46.73076923076923,
|
| 3453 |
+
"grad_norm": 0.4771270751953125,
|
| 3454 |
+
"learning_rate": 2.1765957446808513e-06,
|
| 3455 |
+
"loss": 0.0041,
|
| 3456 |
+
"step": 4860
|
| 3457 |
+
},
|
| 3458 |
+
{
|
| 3459 |
+
"epoch": 46.82692307692308,
|
| 3460 |
+
"grad_norm": 0.10530088096857071,
|
| 3461 |
+
"learning_rate": 2.1127659574468086e-06,
|
| 3462 |
+
"loss": 0.0056,
|
| 3463 |
+
"step": 4870
|
| 3464 |
+
},
|
| 3465 |
+
{
|
| 3466 |
+
"epoch": 46.92307692307692,
|
| 3467 |
+
"grad_norm": 0.38113558292388916,
|
| 3468 |
+
"learning_rate": 2.048936170212766e-06,
|
| 3469 |
+
"loss": 0.0044,
|
| 3470 |
+
"step": 4880
|
| 3471 |
+
},
|
| 3472 |
+
{
|
| 3473 |
+
"epoch": 47.01923076923077,
|
| 3474 |
+
"grad_norm": 0.34304213523864746,
|
| 3475 |
+
"learning_rate": 1.985106382978723e-06,
|
| 3476 |
+
"loss": 0.0036,
|
| 3477 |
+
"step": 4890
|
| 3478 |
+
},
|
| 3479 |
+
{
|
| 3480 |
+
"epoch": 47.11538461538461,
|
| 3481 |
+
"grad_norm": 0.3129338026046753,
|
| 3482 |
+
"learning_rate": 1.921276595744681e-06,
|
| 3483 |
+
"loss": 0.0045,
|
| 3484 |
+
"step": 4900
|
| 3485 |
+
},
|
| 3486 |
+
{
|
| 3487 |
+
"epoch": 47.21153846153846,
|
| 3488 |
+
"grad_norm": 0.04093209281563759,
|
| 3489 |
+
"learning_rate": 1.8574468085106384e-06,
|
| 3490 |
+
"loss": 0.0044,
|
| 3491 |
+
"step": 4910
|
| 3492 |
+
},
|
| 3493 |
+
{
|
| 3494 |
+
"epoch": 47.30769230769231,
|
| 3495 |
+
"grad_norm": 0.19558611512184143,
|
| 3496 |
+
"learning_rate": 1.7936170212765957e-06,
|
| 3497 |
+
"loss": 0.0038,
|
| 3498 |
+
"step": 4920
|
| 3499 |
+
},
|
| 3500 |
+
{
|
| 3501 |
+
"epoch": 47.40384615384615,
|
| 3502 |
+
"grad_norm": 0.07514757663011551,
|
| 3503 |
+
"learning_rate": 1.7297872340425532e-06,
|
| 3504 |
+
"loss": 0.0024,
|
| 3505 |
+
"step": 4930
|
| 3506 |
+
},
|
| 3507 |
+
{
|
| 3508 |
+
"epoch": 47.5,
|
| 3509 |
+
"grad_norm": 0.6852735877037048,
|
| 3510 |
+
"learning_rate": 1.6659574468085108e-06,
|
| 3511 |
+
"loss": 0.0031,
|
| 3512 |
+
"step": 4940
|
| 3513 |
+
},
|
| 3514 |
+
{
|
| 3515 |
+
"epoch": 47.59615384615385,
|
| 3516 |
+
"grad_norm": 0.6539517641067505,
|
| 3517 |
+
"learning_rate": 1.602127659574468e-06,
|
| 3518 |
+
"loss": 0.0039,
|
| 3519 |
+
"step": 4950
|
| 3520 |
+
},
|
| 3521 |
+
{
|
| 3522 |
+
"epoch": 47.69230769230769,
|
| 3523 |
+
"grad_norm": 0.06155241280794144,
|
| 3524 |
+
"learning_rate": 1.5382978723404256e-06,
|
| 3525 |
+
"loss": 0.0031,
|
| 3526 |
+
"step": 4960
|
| 3527 |
+
},
|
| 3528 |
+
{
|
| 3529 |
+
"epoch": 47.78846153846154,
|
| 3530 |
+
"grad_norm": 0.3951682150363922,
|
| 3531 |
+
"learning_rate": 1.4744680851063829e-06,
|
| 3532 |
+
"loss": 0.0032,
|
| 3533 |
+
"step": 4970
|
| 3534 |
+
},
|
| 3535 |
+
{
|
| 3536 |
+
"epoch": 47.88461538461539,
|
| 3537 |
+
"grad_norm": 0.0964864119887352,
|
| 3538 |
+
"learning_rate": 1.4106382978723406e-06,
|
| 3539 |
+
"loss": 0.002,
|
| 3540 |
+
"step": 4980
|
| 3541 |
+
},
|
| 3542 |
+
{
|
| 3543 |
+
"epoch": 47.98076923076923,
|
| 3544 |
+
"grad_norm": 0.17981211841106415,
|
| 3545 |
+
"learning_rate": 1.346808510638298e-06,
|
| 3546 |
+
"loss": 0.003,
|
| 3547 |
+
"step": 4990
|
| 3548 |
+
},
|
| 3549 |
+
{
|
| 3550 |
+
"epoch": 48.07692307692308,
|
| 3551 |
+
"grad_norm": 0.7259301543235779,
|
| 3552 |
+
"learning_rate": 1.2829787234042554e-06,
|
| 3553 |
+
"loss": 0.0028,
|
| 3554 |
+
"step": 5000
|
| 3555 |
+
},
|
| 3556 |
+
{
|
| 3557 |
+
"epoch": 48.07692307692308,
|
| 3558 |
+
"eval_correct_predictions": 1404,
|
| 3559 |
+
"eval_exact_match_accuracy": 0.992226148409894,
|
| 3560 |
+
"eval_loss": 0.004099734127521515,
|
| 3561 |
+
"eval_runtime": 71.3472,
|
| 3562 |
+
"eval_samples_per_second": 19.833,
|
| 3563 |
+
"eval_steps_per_second": 0.322,
|
| 3564 |
+
"eval_total_predictions": 1415,
|
| 3565 |
+
"step": 5000
|
| 3566 |
+
},
|
| 3567 |
+
{
|
| 3568 |
+
"epoch": 48.17307692307692,
|
| 3569 |
+
"grad_norm": 0.2118825614452362,
|
| 3570 |
+
"learning_rate": 1.2191489361702127e-06,
|
| 3571 |
+
"loss": 0.0032,
|
| 3572 |
+
"step": 5010
|
| 3573 |
+
},
|
| 3574 |
+
{
|
| 3575 |
+
"epoch": 48.26923076923077,
|
| 3576 |
+
"grad_norm": 1.0008749961853027,
|
| 3577 |
+
"learning_rate": 1.1553191489361702e-06,
|
| 3578 |
+
"loss": 0.0028,
|
| 3579 |
+
"step": 5020
|
| 3580 |
+
},
|
| 3581 |
+
{
|
| 3582 |
+
"epoch": 48.36538461538461,
|
| 3583 |
+
"grad_norm": 0.6345369815826416,
|
| 3584 |
+
"learning_rate": 1.0914893617021277e-06,
|
| 3585 |
+
"loss": 0.0032,
|
| 3586 |
+
"step": 5030
|
| 3587 |
+
},
|
| 3588 |
+
{
|
| 3589 |
+
"epoch": 48.46153846153846,
|
| 3590 |
+
"grad_norm": 0.7323829531669617,
|
| 3591 |
+
"learning_rate": 1.027659574468085e-06,
|
| 3592 |
+
"loss": 0.006,
|
| 3593 |
+
"step": 5040
|
| 3594 |
+
},
|
| 3595 |
+
{
|
| 3596 |
+
"epoch": 48.55769230769231,
|
| 3597 |
+
"grad_norm": 0.22454875707626343,
|
| 3598 |
+
"learning_rate": 9.638297872340426e-07,
|
| 3599 |
+
"loss": 0.0043,
|
| 3600 |
+
"step": 5050
|
| 3601 |
+
},
|
| 3602 |
+
{
|
| 3603 |
+
"epoch": 48.65384615384615,
|
| 3604 |
+
"grad_norm": 0.4376821219921112,
|
| 3605 |
+
"learning_rate": 9e-07,
|
| 3606 |
+
"loss": 0.0028,
|
| 3607 |
+
"step": 5060
|
| 3608 |
+
},
|
| 3609 |
+
{
|
| 3610 |
+
"epoch": 48.75,
|
| 3611 |
+
"grad_norm": 0.21368823945522308,
|
| 3612 |
+
"learning_rate": 8.361702127659575e-07,
|
| 3613 |
+
"loss": 0.0027,
|
| 3614 |
+
"step": 5070
|
| 3615 |
+
},
|
| 3616 |
+
{
|
| 3617 |
+
"epoch": 48.84615384615385,
|
| 3618 |
+
"grad_norm": 0.6260131001472473,
|
| 3619 |
+
"learning_rate": 7.723404255319149e-07,
|
| 3620 |
+
"loss": 0.0032,
|
| 3621 |
+
"step": 5080
|
| 3622 |
+
},
|
| 3623 |
+
{
|
| 3624 |
+
"epoch": 48.94230769230769,
|
| 3625 |
+
"grad_norm": 0.27165454626083374,
|
| 3626 |
+
"learning_rate": 7.085106382978724e-07,
|
| 3627 |
+
"loss": 0.0057,
|
| 3628 |
+
"step": 5090
|
| 3629 |
+
},
|
| 3630 |
+
{
|
| 3631 |
+
"epoch": 49.03846153846154,
|
| 3632 |
+
"grad_norm": 0.3616870641708374,
|
| 3633 |
+
"learning_rate": 6.446808510638298e-07,
|
| 3634 |
+
"loss": 0.0076,
|
| 3635 |
+
"step": 5100
|
| 3636 |
+
},
|
| 3637 |
+
{
|
| 3638 |
+
"epoch": 49.13461538461539,
|
| 3639 |
+
"grad_norm": 0.1850527971982956,
|
| 3640 |
+
"learning_rate": 5.808510638297873e-07,
|
| 3641 |
+
"loss": 0.0029,
|
| 3642 |
+
"step": 5110
|
| 3643 |
+
},
|
| 3644 |
+
{
|
| 3645 |
+
"epoch": 49.23076923076923,
|
| 3646 |
+
"grad_norm": 0.09594523161649704,
|
| 3647 |
+
"learning_rate": 5.170212765957447e-07,
|
| 3648 |
+
"loss": 0.0053,
|
| 3649 |
+
"step": 5120
|
| 3650 |
+
},
|
| 3651 |
+
{
|
| 3652 |
+
"epoch": 49.32692307692308,
|
| 3653 |
+
"grad_norm": 0.2822889983654022,
|
| 3654 |
+
"learning_rate": 4.531914893617021e-07,
|
| 3655 |
+
"loss": 0.0034,
|
| 3656 |
+
"step": 5130
|
| 3657 |
+
},
|
| 3658 |
+
{
|
| 3659 |
+
"epoch": 49.42307692307692,
|
| 3660 |
+
"grad_norm": 0.37851470708847046,
|
| 3661 |
+
"learning_rate": 3.893617021276596e-07,
|
| 3662 |
+
"loss": 0.005,
|
| 3663 |
+
"step": 5140
|
| 3664 |
+
},
|
| 3665 |
+
{
|
| 3666 |
+
"epoch": 49.51923076923077,
|
| 3667 |
+
"grad_norm": 0.257566899061203,
|
| 3668 |
+
"learning_rate": 3.2553191489361704e-07,
|
| 3669 |
+
"loss": 0.0028,
|
| 3670 |
+
"step": 5150
|
| 3671 |
+
},
|
| 3672 |
+
{
|
| 3673 |
+
"epoch": 49.61538461538461,
|
| 3674 |
+
"grad_norm": 0.022371169179677963,
|
| 3675 |
+
"learning_rate": 2.6170212765957445e-07,
|
| 3676 |
+
"loss": 0.0028,
|
| 3677 |
+
"step": 5160
|
| 3678 |
+
},
|
| 3679 |
+
{
|
| 3680 |
+
"epoch": 49.71153846153846,
|
| 3681 |
+
"grad_norm": 0.9283726215362549,
|
| 3682 |
+
"learning_rate": 1.978723404255319e-07,
|
| 3683 |
+
"loss": 0.0038,
|
| 3684 |
+
"step": 5170
|
| 3685 |
+
},
|
| 3686 |
+
{
|
| 3687 |
+
"epoch": 49.80769230769231,
|
| 3688 |
+
"grad_norm": 0.5324678421020508,
|
| 3689 |
+
"learning_rate": 1.3404255319148937e-07,
|
| 3690 |
+
"loss": 0.0022,
|
| 3691 |
+
"step": 5180
|
| 3692 |
+
},
|
| 3693 |
+
{
|
| 3694 |
+
"epoch": 49.90384615384615,
|
| 3695 |
+
"grad_norm": 0.11308519542217255,
|
| 3696 |
+
"learning_rate": 7.021276595744682e-08,
|
| 3697 |
+
"loss": 0.0023,
|
| 3698 |
+
"step": 5190
|
| 3699 |
+
},
|
| 3700 |
+
{
|
| 3701 |
+
"epoch": 50.0,
|
| 3702 |
+
"grad_norm": 0.00943013746291399,
|
| 3703 |
+
"learning_rate": 6.3829787234042555e-09,
|
| 3704 |
+
"loss": 0.0022,
|
| 3705 |
+
"step": 5200
|
| 3706 |
+
}
|
| 3707 |
+
],
|
| 3708 |
+
"logging_steps": 10,
|
| 3709 |
+
"max_steps": 5200,
|
| 3710 |
+
"num_input_tokens_seen": 0,
|
| 3711 |
+
"num_train_epochs": 50,
|
| 3712 |
+
"save_steps": 1000,
|
| 3713 |
+
"stateful_callbacks": {
|
| 3714 |
+
"TrainerControl": {
|
| 3715 |
+
"args": {
|
| 3716 |
+
"should_epoch_stop": false,
|
| 3717 |
+
"should_evaluate": false,
|
| 3718 |
+
"should_log": false,
|
| 3719 |
+
"should_save": true,
|
| 3720 |
+
"should_training_stop": true
|
| 3721 |
+
},
|
| 3722 |
+
"attributes": {}
|
| 3723 |
+
}
|
| 3724 |
+
},
|
| 3725 |
+
"total_flos": 2.51195129856e+16,
|
| 3726 |
+
"train_batch_size": 64,
|
| 3727 |
+
"trial_name": null,
|
| 3728 |
+
"trial_params": null
|
| 3729 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d201b06bf05e44f993a60966d6b1a6c489fc427e0e35dcbbd0054439b445df8
|
| 3 |
+
size 5969
|
upload.py
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import os
|
| 2 |
+
from huggingface_hub import HfApi, upload_folder
|
| 3 |
+
|
| 4 |
+
token = os.environ.get("HF_TOKEN")
|
| 5 |
+
if not token:
|
| 6 |
+
raise SystemExit("No HF token provided. Set HF_TOKEN env var.")
|
| 7 |
+
|
| 8 |
+
api = HfApi(token=token)
|
| 9 |
+
user = api.whoami()['name']
|
| 10 |
+
repo_name = "t5-spelling-corrector-finetuned-v3"
|
| 11 |
+
repo_id = f"{user}/{repo_name}"
|
| 12 |
+
|
| 13 |
+
print(f"Creating repo: {repo_id}")
|
| 14 |
+
api.create_repo(repo_id=repo_id, repo_type="model", exist_ok=True, private=False)
|
| 15 |
+
|
| 16 |
+
folder_path = "." # current directory
|
| 17 |
+
print(f"Uploading folder {folder_path} to {repo_id} ...")
|
| 18 |
+
upload_folder(
|
| 19 |
+
folder_path=folder_path,
|
| 20 |
+
repo_id=repo_id,
|
| 21 |
+
repo_type="model",
|
| 22 |
+
token=token,
|
| 23 |
+
commit_message="Upload T5 spelling corrector checkpoint from local"
|
| 24 |
+
)
|
| 25 |
+
print(f"Upload complete. Model available at: https://huggingface.co/{repo_id}")
|