ilyes25 commited on
Commit
89f06d6
·
verified ·
1 Parent(s): 08b97ef

End of training

Browse files
Files changed (5) hide show
  1. README.md +45 -321
  2. adapter.ar.safetensors +3 -0
  3. config.json +2 -2
  4. model.safetensors +2 -2
  5. training_args.bin +1 -1
README.md CHANGED
@@ -9,21 +9,21 @@ metrics:
9
  - bleu
10
  - rouge
11
  model-index:
12
- - name: wav2vec2-large-mms-1b-DZkabyle
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
- # wav2vec2-large-mms-1b-DZkabyle
20
 
21
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
- - Loss: 19.6100
24
- - Wer: 1.0
25
- - Bleu: 0.0
26
- - Rouge: {'rouge1': 0.002775591766145671, 'rouge2': 0.0, 'rougeL': 0.0027371732534244783, 'rougeLsum': 0.002771582675127327}
27
 
28
  ## Model description
29
 
@@ -42,329 +42,53 @@ More information needed
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
- - learning_rate: 0.001
46
- - train_batch_size: 16
47
- - eval_batch_size: 8
48
  - seed: 42
49
- - gradient_accumulation_steps: 2
50
  - total_train_batch_size: 32
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
- - lr_scheduler_warmup_steps: 100
54
- - num_epochs: 30
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
- | Training Loss | Epoch | Step | Validation Loss | Wer | Bleu | Rouge |
60
- |:-------------:|:-------:|:-----:|:---------------:|:------:|:------:|:----------------------------------------------------------------------------------------------------------------------------------------:|
61
- | 4.5531 | 0.0975 | 100 | 0.5465 | 0.5803 | 0.2106 | {'rouge1': 0.536518997418804, 'rouge2': 0.3127097002460023, 'rougeL': 0.5352369729717742, 'rougeLsum': 0.535229140628796} |
62
- | 0.7985 | 0.1950 | 200 | 0.4527 | 0.5152 | 0.2716 | {'rouge1': 0.6010166464425964, 'rouge2': 0.3858129157875104, 'rougeL': 0.6001845344012944, 'rougeLsum': 0.6004675427115855} |
63
- | 0.7777 | 0.2925 | 300 | 0.4327 | 0.5040 | 0.2736 | {'rouge1': 0.5859896437664205, 'rouge2': 0.37416789936715045, 'rougeL': 0.585542062353025, 'rougeLsum': 0.5856970545681937} |
64
- | 0.7271 | 0.3901 | 400 | 0.4175 | 0.4872 | 0.2912 | {'rouge1': 0.5987171556870683, 'rouge2': 0.38754736060927064, 'rougeL': 0.5983431131413024, 'rougeLsum': 0.5983761703053142} |
65
- | 0.7297 | 0.4876 | 500 | 0.4237 | 0.5112 | 0.2667 | {'rouge1': 0.5759677426356395, 'rouge2': 0.36303843763298327, 'rougeL': 0.5753603539490343, 'rougeLsum': 0.5754771224775201} |
66
- | 0.7205 | 0.5851 | 600 | 0.4132 | 0.4774 | 0.3004 | {'rouge1': 0.617082391374579, 'rouge2': 0.40899858278773094, 'rougeL': 0.6163126312060403, 'rougeLsum': 0.616183727045307} |
67
- | 0.7116 | 0.6826 | 700 | 0.4076 | 0.5072 | 0.2769 | {'rouge1': 0.5834958094408133, 'rouge2': 0.37474268247882186, 'rougeL': 0.5830572506137937, 'rougeLsum': 0.5832971602297543} |
68
- | 0.702 | 0.7801 | 800 | 0.3956 | 0.4816 | 0.2994 | {'rouge1': 0.6045835381172854, 'rouge2': 0.3962230830027783, 'rougeL': 0.6038092557617667, 'rougeLsum': 0.6039743740874188} |
69
- | 0.6859 | 0.8776 | 900 | 0.4022 | 0.4825 | 0.2917 | {'rouge1': 0.6065743564853018, 'rouge2': 0.3969976079806643, 'rougeL': 0.6059955005468876, 'rougeLsum': 0.6058774170994092} |
70
- | 0.6786 | 0.9751 | 1000 | 0.3866 | 0.4607 | 0.3226 | {'rouge1': 0.6266688397267048, 'rouge2': 0.41997884742669955, 'rougeL': 0.626122365856318, 'rougeLsum': 0.6262375079592603} |
71
- | 0.652 | 1.0722 | 1100 | 0.3829 | 0.4633 | 0.3230 | {'rouge1': 0.6185241193869715, 'rouge2': 0.4143388907334785, 'rougeL': 0.6181805595908618, 'rougeLsum': 0.6182637801091142} |
72
- | 0.6957 | 1.1697 | 1200 | 0.3760 | 0.4574 | 0.3272 | {'rouge1': 0.6263581417328732, 'rouge2': 0.4213965989007058, 'rougeL': 0.625620675674093, 'rougeLsum': 0.625616103574512} |
73
- | 0.6712 | 1.2672 | 1300 | 0.3798 | 0.4537 | 0.3367 | {'rouge1': 0.6398411925961597, 'rouge2': 0.4349862799833104, 'rougeL': 0.6390953953870393, 'rougeLsum': 0.6392059174607969} |
74
- | 0.6733 | 1.3647 | 1400 | 0.3687 | 0.4511 | 0.3378 | {'rouge1': 0.6319343780028592, 'rouge2': 0.43047973067708173, 'rougeL': 0.6315021409872462, 'rougeLsum': 0.6316655600793417} |
75
- | 0.6727 | 1.4622 | 1500 | 0.3640 | 0.4438 | 0.3408 | {'rouge1': 0.6367610708793503, 'rouge2': 0.4323981324222224, 'rougeL': 0.6364113255054273, 'rougeLsum': 0.6364326590706857} |
76
- | 0.6581 | 1.5597 | 1600 | 0.3629 | 0.4415 | 0.3450 | {'rouge1': 0.6448963690970337, 'rouge2': 0.44217727338174456, 'rougeL': 0.6443607483752156, 'rougeLsum': 0.6443727810620359} |
77
- | 0.658 | 1.6572 | 1700 | 0.3624 | 0.4397 | 0.3449 | {'rouge1': 0.6450826481721259, 'rouge2': 0.44236962953480485, 'rougeL': 0.6442666919379593, 'rougeLsum': 0.6444579778624028} |
78
- | 0.6476 | 1.7548 | 1800 | 0.3580 | 0.4375 | 0.3511 | {'rouge1': 0.6473738433678231, 'rouge2': 0.44629141279321494, 'rougeL': 0.6467183712328526, 'rougeLsum': 0.6466437357905275} |
79
- | 0.645 | 1.8523 | 1900 | 0.3509 | 0.4319 | 0.3592 | {'rouge1': 0.6527881380751062, 'rouge2': 0.453138634786846, 'rougeL': 0.6522692668658607, 'rougeLsum': 0.6523629608574564} |
80
- | 0.6332 | 1.9498 | 2000 | 0.3567 | 0.4333 | 0.3541 | {'rouge1': 0.6513044725427062, 'rouge2': 0.44976193304000195, 'rougeL': 0.650811811265888, 'rougeLsum': 0.6505763592498004} |
81
- | 0.6513 | 2.0468 | 2100 | 0.3537 | 0.4289 | 0.3589 | {'rouge1': 0.6591461403184298, 'rouge2': 0.4577745107329835, 'rougeL': 0.6586729623513823, 'rougeLsum': 0.6586006816957712} |
82
- | 0.6329 | 2.1443 | 2200 | 0.3543 | 0.4353 | 0.3494 | {'rouge1': 0.6485366981976509, 'rouge2': 0.44525741217727355, 'rougeL': 0.648023055192262, 'rougeLsum': 0.6479256477918653} |
83
- | 0.6407 | 2.2418 | 2300 | 0.3472 | 0.4404 | 0.3487 | {'rouge1': 0.6436205096020204, 'rouge2': 0.4430631090623349, 'rougeL': 0.6431903785066468, 'rougeLsum': 0.6432469670258589} |
84
- | 0.6256 | 2.3393 | 2400 | 0.3437 | 0.4308 | 0.3542 | {'rouge1': 0.6517643090501104, 'rouge2': 0.4508993439073712, 'rougeL': 0.6514728411280324, 'rougeLsum': 0.6512327928966744} |
85
- | 0.6385 | 2.4369 | 2500 | 0.3510 | 0.4292 | 0.3531 | {'rouge1': 0.6559382509772739, 'rouge2': 0.45627349458405675, 'rougeL': 0.6554585427817229, 'rougeLsum': 0.6553879098632551} |
86
- | 0.634 | 2.5344 | 2600 | 0.3402 | 0.4188 | 0.3670 | {'rouge1': 0.6628433629542625, 'rouge2': 0.46472766118236153, 'rougeL': 0.6622492674426095, 'rougeLsum': 0.6621580764209117} |
87
- | 0.6179 | 2.6319 | 2700 | 0.3412 | 0.4232 | 0.3636 | {'rouge1': 0.6648499942272579, 'rouge2': 0.46475412482980955, 'rougeL': 0.6641503008411329, 'rougeLsum': 0.6642962683467788} |
88
- | 0.6313 | 2.7294 | 2800 | 0.3404 | 0.4214 | 0.3688 | {'rouge1': 0.6598162076736485, 'rouge2': 0.4624726656180853, 'rougeL': 0.6593257440436414, 'rougeLsum': 0.6593980216018982} |
89
- | 0.5976 | 2.8269 | 2900 | 0.3399 | 0.4235 | 0.3633 | {'rouge1': 0.6586765570012069, 'rouge2': 0.4596602941758655, 'rougeL': 0.6581011399137124, 'rougeLsum': 0.6580084675373729} |
90
- | 0.6134 | 2.9244 | 3000 | 0.3401 | 0.4206 | 0.3675 | {'rouge1': 0.6572800592834711, 'rouge2': 0.4592572176115573, 'rougeL': 0.6567528784040555, 'rougeLsum': 0.6572282178669175} |
91
- | 0.623 | 3.0215 | 3100 | 0.3390 | 0.4147 | 0.3768 | {'rouge1': 0.6663621762952652, 'rouge2': 0.46881483460932416, 'rougeL': 0.6657940027775697, 'rougeLsum': 0.6656472552118804} |
92
- | 0.5909 | 3.1190 | 3200 | 0.3312 | 0.4236 | 0.3610 | {'rouge1': 0.659210621753211, 'rouge2': 0.4621132426549109, 'rougeL': 0.6584314185912574, 'rougeLsum': 0.6586317092788629} |
93
- | 0.6039 | 3.2165 | 3300 | 0.3303 | 0.4124 | 0.3761 | {'rouge1': 0.6679178114282787, 'rouge2': 0.4717010228679888, 'rougeL': 0.6675603976069141, 'rougeLsum': 0.6676167607315281} |
94
- | 0.6088 | 3.3140 | 3400 | 0.3290 | 0.4103 | 0.3791 | {'rouge1': 0.6689365784470347, 'rouge2': 0.47331816582705555, 'rougeL': 0.6686522493424056, 'rougeLsum': 0.6687169242683799} |
95
- | 0.6094 | 3.4115 | 3500 | 0.3320 | 0.4099 | 0.3795 | {'rouge1': 0.6728793940662305, 'rouge2': 0.47944322587632726, 'rougeL': 0.6726859428351994, 'rougeLsum': 0.6726007276071504} |
96
- | 0.6108 | 3.5090 | 3600 | 0.3270 | 0.4027 | 0.3879 | {'rouge1': 0.678580626851935, 'rouge2': 0.48532892883861145, 'rougeL': 0.6778762651917698, 'rougeLsum': 0.6779349542290465} |
97
- | 0.6024 | 3.6065 | 3700 | 0.3242 | 0.4017 | 0.3901 | {'rouge1': 0.6796415287538013, 'rouge2': 0.48641219335762925, 'rougeL': 0.6791261702734515, 'rougeLsum': 0.6793170564298094} |
98
- | 0.5994 | 3.7040 | 3800 | 0.3278 | 0.4070 | 0.3828 | {'rouge1': 0.6775549693625558, 'rouge2': 0.4796751012899273, 'rougeL': 0.6768439375855321, 'rougeLsum': 0.6770999375862581} |
99
- | 0.6023 | 3.8016 | 3900 | 0.3227 | 0.3990 | 0.3863 | {'rouge1': 0.6817230615413241, 'rouge2': 0.4873625876176289, 'rougeL': 0.6813090396393942, 'rougeLsum': 0.6812627551794358} |
100
- | 0.5968 | 3.8991 | 4000 | 0.3199 | 0.4102 | 0.3779 | {'rouge1': 0.6678699856122026, 'rouge2': 0.47202611426272345, 'rougeL': 0.6675001295405356, 'rougeLsum': 0.6673654430783217} |
101
- | 0.5976 | 3.9966 | 4100 | 0.3174 | 0.3939 | 0.3993 | {'rouge1': 0.6813304046156214, 'rouge2': 0.4899203199859544, 'rougeL': 0.6810814409288062, 'rougeLsum': 0.6810248344733105} |
102
- | 0.577 | 4.0936 | 4200 | 0.3222 | 0.4059 | 0.3858 | {'rouge1': 0.6709587617584478, 'rouge2': 0.47494466804770424, 'rougeL': 0.6705533251824378, 'rougeLsum': 0.6704063722682035} |
103
- | 0.5847 | 4.1911 | 4300 | 0.3142 | 0.3960 | 0.3945 | {'rouge1': 0.6829485953027736, 'rouge2': 0.48961870199249397, 'rougeL': 0.6826726843365918, 'rougeLsum': 0.6825411425079256} |
104
- | 0.6017 | 4.2886 | 4400 | 0.3141 | 0.3952 | 0.3962 | {'rouge1': 0.682993948649464, 'rouge2': 0.4895944967617313, 'rougeL': 0.6824867925582025, 'rougeLsum': 0.6825265080391647} |
105
- | 0.5905 | 4.3862 | 4500 | 0.3165 | 0.4002 | 0.3898 | {'rouge1': 0.6767328165584545, 'rouge2': 0.4840084568291414, 'rougeL': 0.6763927290791076, 'rougeLsum': 0.6765965951119575} |
106
- | 0.572 | 4.4837 | 4600 | 0.3177 | 0.3967 | 0.3929 | {'rouge1': 0.6815558913405124, 'rouge2': 0.4889915755737708, 'rougeL': 0.681125773131119, 'rougeLsum': 0.6811195081952375} |
107
- | 0.5868 | 4.5812 | 4700 | 0.3218 | 0.4064 | 0.3833 | {'rouge1': 0.6726984154581488, 'rouge2': 0.4781016963339153, 'rougeL': 0.6719374626971724, 'rougeLsum': 0.6721149169391094} |
108
- | 0.5887 | 4.6787 | 4800 | 0.3190 | 0.4046 | 0.3807 | {'rouge1': 0.6744548579231036, 'rouge2': 0.4783458685264245, 'rougeL': 0.6742468180216349, 'rougeLsum': 0.6741252656943661} |
109
- | 0.586 | 4.7762 | 4900 | 0.3160 | 0.4081 | 0.3801 | {'rouge1': 0.6733257163760573, 'rouge2': 0.4793473218440264, 'rougeL': 0.6728643006740043, 'rougeLsum': 0.6727451539570265} |
110
- | 0.591 | 4.8737 | 5000 | 0.3107 | 0.4014 | 0.3872 | {'rouge1': 0.678928361304362, 'rouge2': 0.4876989096048495, 'rougeL': 0.6785719160017751, 'rougeLsum': 0.6787141164380055} |
111
- | 0.5732 | 4.9712 | 5100 | 0.3110 | 0.3893 | 0.3993 | {'rouge1': 0.6901640396889351, 'rouge2': 0.4996323700720813, 'rougeL': 0.6895620244488079, 'rougeLsum': 0.6897412567319816} |
112
- | 0.5747 | 5.0683 | 5200 | 0.3077 | 0.3886 | 0.4036 | {'rouge1': 0.6880390685664151, 'rouge2': 0.49693223704757494, 'rougeL': 0.687598300988361, 'rougeLsum': 0.6876228192118992} |
113
- | 0.5555 | 5.1658 | 5300 | 0.3101 | 0.3946 | 0.3964 | {'rouge1': 0.6845068251291462, 'rouge2': 0.49299241240144065, 'rougeL': 0.6841437543878461, 'rougeLsum': 0.6839228011464193} |
114
- | 0.5595 | 5.2633 | 5400 | 0.3112 | 0.3908 | 0.3991 | {'rouge1': 0.6904634217509346, 'rouge2': 0.4999892411077448, 'rougeL': 0.6900542465285848, 'rougeLsum': 0.6900496568202651} |
115
- | 0.5779 | 5.3608 | 5500 | 0.3157 | 0.3946 | 0.3966 | {'rouge1': 0.6832707588403484, 'rouge2': 0.49024378176082223, 'rougeL': 0.682699115894634, 'rougeLsum': 0.6826196074370546} |
116
- | 0.5823 | 5.4583 | 5600 | 0.3090 | 0.3914 | 0.3998 | {'rouge1': 0.6911763282954584, 'rouge2': 0.49901636263323446, 'rougeL': 0.6906184568530264, 'rougeLsum': 0.6906075570584593} |
117
- | 0.5813 | 5.5558 | 5700 | 0.3211 | 0.4005 | 0.3907 | {'rouge1': 0.6775725650329922, 'rouge2': 0.4838034419435823, 'rougeL': 0.6768274806498837, 'rougeLsum': 0.6768098671321758} |
118
- | 0.5731 | 5.6533 | 5800 | 0.3097 | 0.3931 | 0.4003 | {'rouge1': 0.6849011908160658, 'rouge2': 0.4944104349134254, 'rougeL': 0.6843787295487781, 'rougeLsum': 0.6843737633149923} |
119
- | 0.5708 | 5.7509 | 5900 | 0.3131 | 0.3954 | 0.3955 | {'rouge1': 0.684116809501709, 'rouge2': 0.4908722555316565, 'rougeL': 0.6836468866684247, 'rougeLsum': 0.6836050297051488} |
120
- | 0.5922 | 5.8484 | 6000 | 0.3117 | 0.3920 | 0.3999 | {'rouge1': 0.6844728330527279, 'rouge2': 0.4917876413947735, 'rougeL': 0.6842034576793503, 'rougeLsum': 0.6840648552744337} |
121
- | 0.5763 | 5.9459 | 6100 | 0.3245 | 0.4029 | 0.3891 | {'rouge1': 0.6819309361812524, 'rouge2': 0.4885063736099003, 'rougeL': 0.6816419277062403, 'rougeLsum': 0.6815143093663887} |
122
- | 0.5729 | 6.0429 | 6200 | 0.3123 | 0.4035 | 0.3913 | {'rouge1': 0.6745895992650799, 'rouge2': 0.48170408132323117, 'rougeL': 0.6740329578045565, 'rougeLsum': 0.6739165768665288} |
123
- | 0.5961 | 6.1404 | 6300 | 0.3206 | 0.4015 | 0.3858 | {'rouge1': 0.6752406041517205, 'rouge2': 0.48141098508071556, 'rougeL': 0.6746997051467627, 'rougeLsum': 0.6747290048606716} |
124
- | 0.5714 | 6.2379 | 6400 | 0.3136 | 0.3931 | 0.3992 | {'rouge1': 0.6850538441670542, 'rouge2': 0.49156572080349176, 'rougeL': 0.6844247357816631, 'rougeLsum': 0.6845027656732805} |
125
- | 0.5795 | 6.3354 | 6500 | 0.3313 | 0.4107 | 0.3662 | {'rouge1': 0.6622780496314785, 'rouge2': 0.46300737370669764, 'rougeL': 0.661737770702837, 'rougeLsum': 0.6615520243200708} |
126
- | 0.5836 | 6.4330 | 6600 | 0.3155 | 0.3908 | 0.4037 | {'rouge1': 0.6886632348837828, 'rouge2': 0.49720647214377145, 'rougeL': 0.6882784500133678, 'rougeLsum': 0.6881147742923043} |
127
- | 0.5647 | 6.5305 | 6700 | 0.3149 | 0.3980 | 0.3927 | {'rouge1': 0.6751904201997564, 'rouge2': 0.48251997594257967, 'rougeL': 0.6749789024201811, 'rougeLsum': 0.6751376960753348} |
128
- | 0.5794 | 6.6280 | 6800 | 0.3180 | 0.3946 | 0.3965 | {'rouge1': 0.6838250907050285, 'rouge2': 0.48887110898775976, 'rougeL': 0.6834169576087581, 'rougeLsum': 0.6835027885005307} |
129
- | 0.5807 | 6.7255 | 6900 | 0.3179 | 0.3951 | 0.3916 | {'rouge1': 0.6830137169182183, 'rouge2': 0.4895800675769315, 'rougeL': 0.6823403245800324, 'rougeLsum': 0.6825828640235584} |
130
- | 0.5859 | 6.8230 | 7000 | 0.3171 | 0.3928 | 0.3920 | {'rouge1': 0.6846008985916635, 'rouge2': 0.4920503701971746, 'rougeL': 0.6841182817079334, 'rougeLsum': 0.6841209924524078} |
131
- | 0.5942 | 6.9205 | 7100 | 0.3331 | 0.4165 | 0.3729 | {'rouge1': 0.6646450645785351, 'rouge2': 0.4684057598411131, 'rougeL': 0.664320719530437, 'rougeLsum': 0.6642585215688178} |
132
- | 0.6035 | 7.0176 | 7200 | 0.3516 | 0.4126 | 0.3747 | {'rouge1': 0.6665567366558782, 'rouge2': 0.4725017338239089, 'rougeL': 0.6663718168115231, 'rougeLsum': 0.6660044050733005} |
133
- | 0.6135 | 7.1151 | 7300 | 0.3523 | 0.4038 | 0.3807 | {'rouge1': 0.6769900164239071, 'rouge2': 0.47931015138946576, 'rougeL': 0.6766367984147572, 'rougeLsum': 0.676619111670449} |
134
- | 0.602 | 7.2126 | 7400 | 0.3247 | 0.3910 | 0.3990 | {'rouge1': 0.6858289772667316, 'rouge2': 0.4928069696243058, 'rougeL': 0.6850066670009453, 'rougeLsum': 0.6850498879898881} |
135
- | 0.598 | 7.3101 | 7500 | 0.3356 | 0.3961 | 0.3980 | {'rouge1': 0.6879891984060114, 'rouge2': 0.49561562991297137, 'rougeL': 0.6872849457327842, 'rougeLsum': 0.6874518743578207} |
136
- | 0.5882 | 7.4076 | 7600 | 0.3254 | 0.3934 | 0.3970 | {'rouge1': 0.6847469682194325, 'rouge2': 0.4917885159063927, 'rougeL': 0.6842181138929582, 'rougeLsum': 0.6841693591743288} |
137
- | 0.5936 | 7.5051 | 7700 | 0.3275 | 0.4005 | 0.3884 | {'rouge1': 0.6793444581533614, 'rouge2': 0.48597512806961024, 'rougeL': 0.6788657072459033, 'rougeLsum': 0.6789107168527937} |
138
- | 0.611 | 7.6026 | 7800 | 0.3704 | 0.4080 | 0.3806 | {'rouge1': 0.6746418344219114, 'rouge2': 0.4779130300562587, 'rougeL': 0.67420930399153, 'rougeLsum': 0.674269421429911} |
139
- | 0.6675 | 7.7001 | 7900 | 0.3603 | 0.4123 | 0.3798 | {'rouge1': 0.6661683374850148, 'rouge2': 0.4692712919814873, 'rougeL': 0.6656247581499741, 'rougeLsum': 0.6654874422068364} |
140
- | 0.65 | 7.7977 | 8000 | 0.3654 | 0.4072 | 0.3827 | {'rouge1': 0.6729269807796813, 'rouge2': 0.4773954788935819, 'rougeL': 0.6725765928482013, 'rougeLsum': 0.6724696394682321} |
141
- | 0.6648 | 7.8952 | 8100 | 0.3594 | 0.4132 | 0.3787 | {'rouge1': 0.6701517243313366, 'rouge2': 0.47307576182578814, 'rougeL': 0.6694746539591978, 'rougeLsum': 0.6695780931932368} |
142
- | 0.6374 | 7.9927 | 8200 | 0.3525 | 0.3998 | 0.3899 | {'rouge1': 0.6781850631435138, 'rouge2': 0.48312106280780354, 'rougeL': 0.6776148867760519, 'rougeLsum': 0.6775882488560225} |
143
- | 0.6833 | 8.0897 | 8300 | 0.3634 | 0.4535 | 0.3390 | {'rouge1': 0.6318018334689897, 'rouge2': 0.43010232075950816, 'rougeL': 0.6314028516063805, 'rougeLsum': 0.6314716039504424} |
144
- | 0.6387 | 8.1872 | 8400 | 0.3657 | 0.4114 | 0.3791 | {'rouge1': 0.6679524804649608, 'rouge2': 0.470341326277287, 'rougeL': 0.667449054495525, 'rougeLsum': 0.6672778220608753} |
145
- | 0.7075 | 8.2847 | 8500 | 0.4545 | 0.4417 | 0.3392 | {'rouge1': 0.6419227978209493, 'rouge2': 0.43720943207189084, 'rougeL': 0.6413975845286295, 'rougeLsum': 0.6417602166145829} |
146
- | 0.7846 | 8.3823 | 8600 | 0.3970 | 0.4406 | 0.3490 | {'rouge1': 0.6554058155481779, 'rouge2': 0.45341625559136634, 'rougeL': 0.6550837023083775, 'rougeLsum': 0.6549068116998291} |
147
- | 0.8308 | 8.4798 | 8700 | 0.4838 | 0.4565 | 0.3202 | {'rouge1': 0.6315759900134224, 'rouge2': 0.4242875384159027, 'rougeL': 0.6309658765389045, 'rougeLsum': 0.6311312934361659} |
148
- | 0.812 | 8.5773 | 8800 | 0.6257 | 0.7485 | 0.0980 | {'rouge1': 0.4244912447175161, 'rouge2': 0.21733718738872, 'rougeL': 0.42418094770042186, 'rougeLsum': 0.42403937871141895} |
149
- | 1.2754 | 8.6748 | 8900 | 1.2843 | 0.9971 | 0.0 | {'rouge1': 0.027358308375203713, 'rouge2': 0.00019977583170842556, 'rougeL': 0.02724639045615477, 'rougeLsum': 0.02724039522338019} |
150
- | 1.3974 | 8.7723 | 9000 | 0.8433 | 0.8171 | 0.0261 | {'rouge1': 0.27502688103655937, 'rouge2': 0.08394874989474396, 'rougeL': 0.2735541483110615, 'rougeLsum': 0.2733409462204587} |
151
- | 1.3188 | 8.8698 | 9100 | 1.3216 | 1.0 | 0.0 | {'rouge1': 0.014960419774965102, 'rouge2': 0.0, 'rougeL': 0.014943228548803146, 'rougeLsum': 0.014955025248598108} |
152
- | 2.8857 | 8.9673 | 9200 | 2.9996 | 0.9993 | 0.0 | {'rouge1': 0.0032135042830713535, 'rouge2': 0.0, 'rougeL': 0.003204702010162759, 'rougeLsum': 0.0032142824835082575} |
153
- | 3.4841 | 9.0644 | 9300 | 3.0931 | 1.0144 | 0.0 | {'rouge1': 0.020982583806433273, 'rouge2': 0.0002753030056784323, 'rougeL': 0.02073184056016708, 'rougeLsum': 0.02075185172477681} |
154
- | 3.189 | 9.1619 | 9400 | 3.0130 | 0.9995 | 0.0 | {'rouge1': 0.01166622891918148, 'rouge2': 6.052264478032397e-05, 'rougeL': 0.011700763559402513, 'rougeLsum': 0.011668933922451136} |
155
- | 3.1102 | 9.2594 | 9500 | 2.9422 | 1.0 | 0.0 | {'rouge1': 0.0007939893818733408, 'rouge2': 0.0, 'rougeL': 0.0007939893818733408, 'rougeLsum': 0.0007987296169890026} |
156
- | 3.0952 | 9.3569 | 9600 | 2.9332 | 1.0 | 0.0 | {'rouge1': 0.0006399317406143345, 'rouge2': 0.0, 'rougeL': 0.0006162305650360257, 'rougeLsum': 0.0006399317406143345} |
157
- | 3.0404 | 9.4544 | 9700 | 2.9274 | 1.0 | 0.0 | {'rouge1': 0.0010191505498672732, 'rouge2': 0.0, 'rougeL': 0.0010072999620781187, 'rougeLsum': 0.0010310011376564274} |
158
- | 3.0296 | 9.5519 | 9800 | 2.9126 | 1.0 | 0.0 | {'rouge1': 0.0005925293894577171, 'rouge2': 0.0, 'rougeL': 0.0006162305650360257, 'rougeLsum': 0.0006162305650360257} |
159
- | 3.0252 | 9.6494 | 9900 | 2.8578 | 1.0323 | 0.0 | {'rouge1': 0.014096634253447104, 'rouge2': 0.0001244311717861206, 'rougeL': 0.01395006512632463, 'rougeLsum': 0.013980355711991261} |
160
- | 2.9966 | 9.7470 | 10000 | 2.8867 | 1.0181 | 0.0 | {'rouge1': 0.011020493616829594, 'rouge2': 0.00013035646568069774, 'rougeL': 0.010911319452070422, 'rougeLsum': 0.010928326974934077} |
161
- | 2.9658 | 9.8445 | 10100 | 2.8191 | 1.0406 | 0.0 | {'rouge1': 0.015070554678309252, 'rouge2': 0.00012358470122975242, 'rougeL': 0.015002700700413034, 'rougeLsum': 0.014969551141969375} |
162
- | 2.9505 | 9.9420 | 10200 | 2.8052 | 1.0112 | 0.0 | {'rouge1': 0.008995157661292903, 'rouge2': 1.1850587789154341e-05, 'rougeL': 0.00894026538247861, 'rougeLsum': 0.008948343118886322} |
163
- | 2.9112 | 10.0390 | 10300 | 2.7613 | 1.0030 | 0.0 | {'rouge1': 0.002500145820889646, 'rouge2': 0.0, 'rougeL': 0.0024658867212445806, 'rougeLsum': 0.0024358306913150178} |
164
- | 2.9139 | 10.1365 | 10400 | 2.7502 | 0.9999 | 0.0 | {'rouge1': 0.00022050557993390758, 'rouge2': 0.0, 'rougeL': 0.00021906657998808167, 'rougeLsum': 0.0002170350506527981} |
165
- | 2.8978 | 10.2340 | 10500 | 2.7627 | 1.0 | 0.0 | {'rouge1': 0.00025281253950195927, 'rouge2': 0.0, 'rougeL': 0.00025834281380356463, 'rougeLsum': 0.00025281253950195927} |
166
- | 2.8844 | 10.3315 | 10600 | 2.7010 | 1.0000 | 0.0 | {'rouge1': 0.00024570731695305073, 'rouge2': 0.0, 'rougeL': 0.0002536641401829115, 'rougeLsum': 0.00024181355239375716} |
167
- | 2.867 | 10.4291 | 10700 | 2.6902 | 0.9999 | 0.0 | {'rouge1': 0.0005295046250677651, 'rouge2': 0.0, 'rougeL': 0.0005202123909461793, 'rougeLsum': 0.000524625876588334} |
168
- | 2.8576 | 10.5266 | 10800 | 2.6757 | 1.0000 | 0.0 | {'rouge1': 0.000637182585774736, 'rouge2': 0.0, 'rougeL': 0.0006400931422262481, 'rougeLsum': 0.0006272585570793762} |
169
- | 2.8379 | 10.6241 | 10900 | 2.6566 | 1.0002 | 0.0 | {'rouge1': 0.0006100554735367022, 'rouge2': 2.3701175578308683e-05, 'rougeL': 0.0006149223832670931, 'rougeLsum': 0.0006143875677792061} |
170
- | 2.8623 | 10.7216 | 11000 | 2.6695 | 1.0021 | 0.0 | {'rouge1': 0.002871344175957956, 'rouge2': 0.0, 'rougeL': 0.0028804247924404513, 'rougeLsum': 0.0028521028544555432} |
171
- | 2.8268 | 10.8191 | 11100 | 2.6751 | 1.0003 | 0.0 | {'rouge1': 0.0008514278352162311, 'rouge2': 0.0, 'rougeL': 0.0008438703724539902, 'rougeLsum': 0.0008457890390484249} |
172
- | 2.8214 | 10.9166 | 11200 | 2.6502 | 1.0013 | 0.0 | {'rouge1': 0.003592238503965565, 'rouge2': 7.110352673492605e-05, 'rougeL': 0.0036022191787537594, 'rougeLsum': 0.003609454244523757} |
173
- | 2.8145 | 11.0137 | 11300 | 2.6350 | 1.0213 | 0.0 | {'rouge1': 0.019332589820923014, 'rouge2': 0.00032409049047274306, 'rougeL': 0.01919495149585998, 'rougeLsum': 0.01915923054008686} |
174
- | 2.8163 | 11.1112 | 11400 | 2.6679 | 1.0087 | 0.0 | {'rouge1': 0.012136715703889116, 'rouge2': 0.00019231811040684762, 'rougeL': 0.012002154543706005, 'rougeLsum': 0.012029198708888581} |
175
- | 2.8478 | 11.2087 | 11500 | 2.6573 | 1.0104 | 0.0 | {'rouge1': 0.010538763369029947, 'rouge2': 2.031529335283602e-05, 'rougeL': 0.010509069596879646, 'rougeLsum': 0.010475433911953269} |
176
- | 2.8715 | 11.3062 | 11600 | 2.6556 | 1.0098 | 0.0 | {'rouge1': 0.010101999962987685, 'rouge2': 6.771764450945338e-05, 'rougeL': 0.009988550818818807, 'rougeLsum': 0.010035580090089365} |
177
- | 2.8867 | 11.4037 | 11700 | 2.6883 | 1.0260 | 0.0 | {'rouge1': 0.018079892425605208, 'rouge2': 0.0001366511285453265, 'rougeL': 0.017964736789800026, 'rougeLsum': 0.01795970302976206} |
178
- | 2.8899 | 11.5012 | 11800 | 2.7162 | 1.0153 | 0.0 | {'rouge1': 0.014783063789221694, 'rouge2': 8.236158513462267e-05, 'rougeL': 0.014610583224091972, 'rougeLsum': 0.0146150141497027} |
179
- | 2.9314 | 11.5987 | 11900 | 2.7474 | 1.0413 | 0.0 | {'rouge1': 0.0215670883375619, 'rouge2': 0.00021350325584540604, 'rougeL': 0.021384255292522955, 'rougeLsum': 0.021392649596292307} |
180
- | 3.0427 | 11.6962 | 12000 | 2.7859 | 1.0443 | 0.0 | {'rouge1': 0.023102746553997716, 'rouge2': 0.00019401401120684397, 'rougeL': 0.022809013983807656, 'rougeLsum': 0.022823107708851383} |
181
- | 3.1315 | 11.7938 | 12100 | 2.8847 | 1.0524 | 0.0 | {'rouge1': 0.02628866520387593, 'rouge2': 0.00023684120815720898, 'rougeL': 0.025847556437179255, 'rougeLsum': 0.025871705295219823} |
182
- | 3.3428 | 11.8913 | 12200 | 3.0294 | 1.0384 | 0.0 | {'rouge1': 0.022960052957817056, 'rouge2': 0.0002184687231615559, 'rougeL': 0.0226496599617046, 'rougeLsum': 0.022662001081545848} |
183
- | 3.53 | 11.9888 | 12300 | 3.1814 | 1.0258 | 0.0 | {'rouge1': 0.01666275976257626, 'rouge2': 0.0001215390640518627, 'rougeL': 0.016469990362328612, 'rougeLsum': 0.01647823562188238} |
184
- | 3.6624 | 12.0858 | 12400 | 3.3469 | 1.0018 | 0.0 | {'rouge1': 0.00636852642200336, 'rouge2': 3.453599869982123e-05, 'rougeL': 0.006328315375077831, 'rougeLsum': 0.00630680160569717} |
185
- | 3.961 | 12.1833 | 12500 | 3.4799 | 1.0069 | 0.0 | {'rouge1': 0.011706774927691625, 'rouge2': 5.349693916246817e-05, 'rougeL': 0.011565847514164153, 'rougeLsum': 0.011593790270177862} |
186
- | 4.0476 | 12.2808 | 12600 | 3.6956 | 1.0084 | 0.0 | {'rouge1': 0.013286089562097994, 'rouge2': 6.857950543957372e-05, 'rougeL': 0.013205572457525436, 'rougeLsum': 0.013176314118169} |
187
- | 4.3193 | 12.3784 | 12700 | 3.8364 | 1.0022 | 0.0 | {'rouge1': 0.008547526301154584, 'rouge2': 1.5800783718872454e-05, 'rougeL': 0.008403461265219469, 'rougeLsum': 0.008430793144770719} |
188
- | 4.7524 | 12.4759 | 12800 | 4.1571 | 1.0285 | 0.0 | {'rouge1': 0.019103974466880367, 'rouge2': 5.812431153728083e-05, 'rougeL': 0.018835383523354603, 'rougeLsum': 0.01884599703577602} |
189
- | 5.3779 | 12.5734 | 12900 | 4.6164 | 1.0082 | 0.0 | {'rouge1': 0.012938232858370233, 'rouge2': 1.4220705346985212e-05, 'rougeL': 0.012833677067274108, 'rougeLsum': 0.012826485123343173} |
190
- | 5.8864 | 12.6709 | 13000 | 5.3343 | 1.0324 | 0.0 | {'rouge1': 0.023679029596002987, 'rouge2': 0.00014497219062065478, 'rougeL': 0.02327772111349068, 'rougeLsum': 0.023277187762739106} |
191
- | 6.7304 | 12.7684 | 13100 | 6.3096 | 1.0202 | 0.0 | {'rouge1': 0.02080970634169841, 'rouge2': 0.0001231152948303119, 'rougeL': 0.02043054872899522, 'rougeLsum': 0.020429733181612605} |
192
- | 7.9349 | 12.8659 | 13200 | 7.1396 | 1.0348 | 0.0 | {'rouge1': 0.025865742991784707, 'rouge2': 0.0001663258409205508, 'rougeL': 0.02527140412309991, 'rougeLsum': 0.025286933050397635} |
193
- | 8.7209 | 12.9634 | 13300 | 7.6525 | 1.0228 | 0.0 | {'rouge1': 0.019628880355841035, 'rouge2': 8.751795227904442e-05, 'rougeL': 0.01929777606614972, 'rougeLsum': 0.019313906630460453} |
194
- | 9.3744 | 13.0605 | 13400 | 8.2577 | 1.0674 | 0.0 | {'rouge1': 0.03470567512378926, 'rouge2': 0.0003210067807099026, 'rougeL': 0.03379445868621681, 'rougeLsum': 0.033809224695505784} |
195
- | 10.1825 | 13.1580 | 13500 | 8.7805 | 1.0380 | 0.0 | {'rouge1': 0.026801734974880732, 'rouge2': 0.00029926946789148154, 'rougeL': 0.026272896362930842, 'rougeLsum': 0.026283817768791184} |
196
- | 11.0248 | 13.2555 | 13600 | 9.4702 | 1.0054 | 0.0 | {'rouge1': 0.013487409036653505, 'rouge2': 4.610955976143689e-05, 'rougeL': 0.013324204059586155, 'rougeLsum': 0.013319008043225368} |
197
- | 11.269 | 13.3530 | 13700 | 10.0853 | 1.0736 | 0.0 | {'rouge1': 0.03872910467532724, 'rouge2': 0.0003091531926103297, 'rougeL': 0.03762440962724672, 'rougeLsum': 0.0376588233448507} |
198
- | 12.3504 | 13.4505 | 13800 | 10.6979 | 1.0730 | 0.0 | {'rouge1': 0.03647314517393899, 'rouge2': 0.00017940581315782078, 'rougeL': 0.035554122692125045, 'rougeLsum': 0.03558204084414185} |
199
- | 13.2413 | 13.5480 | 13900 | 11.1209 | 1.0344 | 0.0 | {'rouge1': 0.026291943020701758, 'rouge2': 0.00015396529901649358, 'rougeL': 0.025796622173061626, 'rougeLsum': 0.02583491188645628} |
200
- | 13.3602 | 13.6455 | 14000 | 11.4005 | 1.0440 | 0.0 | {'rouge1': 0.024293059919310068, 'rouge2': 0.00011917022902517784, 'rougeL': 0.023698008947812328, 'rougeLsum': 0.023764461167099096} |
201
- | 14.5506 | 13.7431 | 14100 | 12.2570 | 1.0045 | 0.0 | {'rouge1': 0.008256882850614634, 'rouge2': 5.332764505119454e-05, 'rougeL': 0.008138403378605365, 'rougeLsum': 0.008161275150617405} |
202
- | 15.9935 | 13.8406 | 14200 | 14.6313 | 1.0269 | 0.0 | {'rouge1': 0.01685972088359004, 'rouge2': 0.00012446708265820893, 'rougeL': 0.016359178546338497, 'rougeLsum': 0.01636184594934208} |
203
- | 18.2697 | 13.9381 | 14300 | 16.3970 | 1.1112 | 0.0 | {'rouge1': 0.031464691521717866, 'rouge2': 0.00028121526534244867, 'rougeL': 0.03043895297936753, 'rougeLsum': 0.030500608576272275} |
204
- | 19.2067 | 14.0351 | 14400 | 17.8166 | 1.1318 | 0.0 | {'rouge1': 0.029538189881777463, 'rouge2': 0.0003701897899850119, 'rougeL': 0.028704061990264877, 'rougeLsum': 0.02869118585637762} |
205
- | 20.8718 | 14.1326 | 14500 | 18.3629 | 1.0485 | 0.0 | {'rouge1': 0.017939885402532205, 'rouge2': 0.00019274134568503172, 'rougeL': 0.01755712357774227, 'rougeLsum': 0.017609867469086625} |
206
- | 21.2056 | 14.2301 | 14600 | 18.6522 | 1.0068 | 0.0 | {'rouge1': 0.007419484200520266, 'rouge2': 4.7402351156617366e-05, 'rougeL': 0.007379329486918879, 'rougeLsum': 0.007359051671543866} |
207
- | 20.7942 | 14.3276 | 14700 | 18.6866 | 1.0496 | 0.0 | {'rouge1': 0.014757324524025362, 'rouge2': 0.00018338037717931314, 'rougeL': 0.014571761346301627, 'rougeLsum': 0.014578032361161983} |
208
- | 20.1671 | 14.4252 | 14800 | 18.0504 | 1.0782 | 0.0 | {'rouge1': 0.01788156092772678, 'rouge2': 0.00021769985444448404, 'rougeL': 0.017635007760316995, 'rougeLsum': 0.017687364589833585} |
209
- | 20.4919 | 14.5227 | 14900 | 18.3407 | 1.0306 | 0.0 | {'rouge1': 0.009702255014664271, 'rouge2': 6.489607598822615e-05, 'rougeL': 0.009727955623006535, 'rougeLsum': 0.00972689566858929} |
210
- | 20.2598 | 14.6202 | 15000 | 18.2410 | 1.0068 | 0.0 | {'rouge1': 0.002800847965442171, 'rouge2': 0.0, 'rougeL': 0.0028063509003581257, 'rougeLsum': 0.002811421616474566} |
211
- | 19.9369 | 14.7177 | 15100 | 17.9134 | 1.0165 | 0.0 | {'rouge1': 0.006948234451398746, 'rouge2': 3.002148906585767e-05, 'rougeL': 0.006879241151641123, 'rougeLsum': 0.006891196176649186} |
212
- | 19.5273 | 14.8152 | 15200 | 17.9612 | 1.0095 | 0.0 | {'rouge1': 0.00505022656714712, 'rouge2': 1.5800783718872457e-05, 'rougeL': 0.0050159227878310494, 'rougeLsum': 0.004993811968283713} |
213
- | 19.9424 | 14.9127 | 15300 | 17.8269 | 1.0072 | 0.0 | {'rouge1': 0.0038401298083567664, 'rouge2': 2.3701175578308686e-05, 'rougeL': 0.0037941540368443506, 'rougeLsum': 0.0038037264171244317} |
214
- | 20.1695 | 15.0098 | 15400 | 18.0152 | 1.0110 | 0.0 | {'rouge1': 0.005224299194092749, 'rouge2': 0.0, 'rougeL': 0.005160055994163106, 'rougeLsum': 0.005170117008017705} |
215
- | 19.8059 | 15.1073 | 15500 | 17.9431 | 1.0014 | 0.0 | {'rouge1': 0.0011396995869240394, 'rouge2': 0.0, 'rougeL': 0.0011403700547446781, 'rougeLsum': 0.0011451703424951768} |
216
- | 20.0626 | 15.2048 | 15600 | 18.3745 | 1.0002 | 0.0 | {'rouge1': 0.011103358317079596, 'rouge2': 1.4220705346985212e-05, 'rougeL': 0.0110287558528366, 'rougeLsum': 0.011047944560669888} |
217
- | 20.5184 | 15.3023 | 15700 | 18.1219 | 1.0000 | 0.0 | {'rouge1': 0.022160540268697723, 'rouge2': 0.00013508338220368936, 'rougeL': 0.021501575889712167, 'rougeLsum': 0.021494617583193747} |
218
- | 20.2695 | 15.3998 | 15800 | 18.2295 | 1.0000 | 0.0 | {'rouge1': 0.0001610874904390263, 'rouge2': 0.0, 'rougeL': 0.00015901570935700628, 'rougeLsum': 0.0001620622141099957} |
219
- | 20.0099 | 15.4973 | 15900 | 18.4134 | 1.0 | 0.0 | {'rouge1': 0.005314797484131354, 'rouge2': 0.0, 'rougeL': 0.005313087769199894, 'rougeLsum': 0.00531360514921223} |
220
- | 20.7051 | 15.5948 | 16000 | 19.1934 | 1.0 | 0.0 | {'rouge1': 0.00015341953268574427, 'rouge2': 0.0, 'rougeL': 0.00014617244246083836, 'rougeLsum': 0.00015683797147107725} |
221
- | 20.3615 | 15.6923 | 16100 | 19.2314 | 1.0 | 0.0 | {'rouge1': 0.00021433285618439201, 'rouge2': 0.0, 'rougeL': 0.0002136773841125377, 'rougeLsum': 0.00021143098148217602} |
222
- | 21.0817 | 15.7899 | 16200 | 19.2674 | 1.0 | 0.0 | {'rouge1': 0.0011377792025503324, 'rouge2': 0.0, 'rougeL': 0.0011235298578766255, 'rougeLsum': 0.0011340728152111406} |
223
- | 20.8609 | 15.8874 | 16300 | 19.1886 | 1.0 | 0.0 | {'rouge1': 0.0027978018332615786, 'rouge2': 3.5551763367463024e-05, 'rougeL': 0.00278317556022836, 'rougeLsum': 0.002789991717666881} |
224
- | 21.4362 | 15.9849 | 16400 | 19.6110 | 1.0 | 0.0 | {'rouge1': 0.002786240971854524, 'rouge2': 0.0, 'rougeL': 0.00276879019028298, 'rougeLsum': 0.0027711645651478174} |
225
- | 20.2069 | 16.0819 | 16500 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.0028514030823712185, 'rouge2': 0.0, 'rougeL': 0.0028477119370562197, 'rougeLsum': 0.002849979853068561} |
226
- | 20.9135 | 16.1794 | 16600 | 19.6095 | 1.0 | 0.0 | {'rouge1': 0.0027724705340236447, 'rouge2': 0.0, 'rougeL': 0.002757412781165869, 'rougeLsum': 0.002749409112836846} |
227
- | 21.7066 | 16.2769 | 16700 | 19.6097 | 1.0 | 0.0 | {'rouge1': 0.002734660553223062, 'rouge2': 0.0, 'rougeL': 0.002716864466740969, 'rougeLsum': 0.0027349566829145125} |
228
- | 21.1412 | 16.3745 | 16800 | 19.6098 | 1.0 | 0.0 | {'rouge1': 0.0027972396641546622, 'rouge2': 0.0, 'rougeL': 0.0027895287754198953, 'rougeLsum': 0.002806562288735993} |
229
- | 21.4289 | 16.4720 | 16900 | 19.6089 | 1.0 | 0.0 | {'rouge1': 0.002787720825991582, 'rouge2': 0.0, 'rougeL': 0.0027889926139920843, 'rougeLsum': 0.0027884321749430197} |
230
- | 21.0381 | 16.5695 | 17000 | 19.6097 | 1.0 | 0.0 | {'rouge1': 0.002754755567712896, 'rouge2': 0.0, 'rougeL': 0.002754095779506813, 'rougeLsum': 0.002760744052243856} |
231
- | 21.6149 | 16.6670 | 17100 | 19.6097 | 1.0 | 0.0 | {'rouge1': 0.002698994956740505, 'rouge2': 0.0, 'rougeL': 0.0026689255010097874, 'rougeLsum': 0.002676326681105694} |
232
- | 21.1703 | 16.7645 | 17200 | 19.6093 | 1.0 | 0.0 | {'rouge1': 0.002747120184234836, 'rouge2': 0.0, 'rougeL': 0.0027237428607519805, 'rougeLsum': 0.002739833825832328} |
233
- | 21.4163 | 16.8620 | 17300 | 19.6094 | 1.0 | 0.0 | {'rouge1': 0.0027257046358347675, 'rouge2': 0.0, 'rougeL': 0.0027167645610480075, 'rougeLsum': 0.0027014063294092} |
234
- | 21.1361 | 16.9595 | 17400 | 19.6084 | 1.0 | 0.0 | {'rouge1': 0.0027298601220551526, 'rouge2': 0.0, 'rougeL': 0.002727137334195138, 'rougeLsum': 0.0027331713375873673} |
235
- | 21.5562 | 17.0566 | 17500 | 19.6088 | 1.0 | 0.0 | {'rouge1': 0.002755317016232175, 'rouge2': 0.0, 'rougeL': 0.0027235014602289844, 'rougeLsum': 0.0027460631149170602} |
236
- | 20.6944 | 17.1541 | 17600 | 19.6107 | 1.0 | 0.0 | {'rouge1': 0.0028263147324225, 'rouge2': 0.0, 'rougeL': 0.0028280556537615114, 'rougeLsum': 0.0028291208815534336} |
237
- | 20.9795 | 17.2516 | 17700 | 19.6106 | 1.0 | 0.0 | {'rouge1': 0.00270073724094067, 'rouge2': 0.0, 'rougeL': 0.0026784640883809807, 'rougeLsum': 0.0026768265796754944} |
238
- | 21.3599 | 17.3491 | 17800 | 19.6083 | 1.0 | 0.0 | {'rouge1': 0.0027659635916373335, 'rouge2': 0.0, 'rougeL': 0.0027450888251502933, 'rougeLsum': 0.0027354603508858077} |
239
- | 21.3827 | 17.4466 | 17900 | 19.6096 | 1.0 | 0.0 | {'rouge1': 0.0027849632961228056, 'rouge2': 0.0, 'rougeL': 0.002760022037544714, 'rougeLsum': 0.002760083905393316} |
240
- | 21.2534 | 17.5441 | 18000 | 19.6088 | 1.0 | 0.0 | {'rouge1': 0.002748694968462319, 'rouge2': 0.0, 'rougeL': 0.002726468869737631, 'rougeLsum': 0.0027296657308795514} |
241
- | 20.3353 | 17.6416 | 18100 | 19.6100 | 1.0 | 0.0 | {'rouge1': 0.002693290950661233, 'rouge2': 0.0, 'rougeL': 0.002693634940542107, 'rougeLsum': 0.002688546105902051} |
242
- | 21.6997 | 17.7392 | 18200 | 19.6085 | 1.0 | 0.0 | {'rouge1': 0.0027836428953354163, 'rouge2': 0.0, 'rougeL': 0.002773438912296174, 'rougeLsum': 0.0027843598000688347} |
243
- | 21.7704 | 17.8367 | 18300 | 19.6099 | 1.0 | 0.0 | {'rouge1': 0.002714594542080103, 'rouge2': 0.0, 'rougeL': 0.0027104475653105154, 'rougeLsum': 0.002683018337909884} |
244
- | 21.3923 | 17.9342 | 18400 | 19.6102 | 1.0 | 0.0 | {'rouge1': 0.0027939737749679257, 'rouge2': 0.0, 'rougeL': 0.002787096573046755, 'rougeLsum': 0.002781018323600873} |
245
- | 20.3648 | 18.0312 | 18500 | 19.6096 | 1.0 | 0.0 | {'rouge1': 0.002755493671198677, 'rouge2': 0.0, 'rougeL': 0.0027443103040042443, 'rougeLsum': 0.0027266131853101797} |
246
- | 20.8171 | 18.1287 | 18600 | 19.6096 | 1.0 | 0.0 | {'rouge1': 0.002762253102397623, 'rouge2': 0.0, 'rougeL': 0.002759783832323296, 'rougeLsum': 0.002738455251093735} |
247
- | 20.7686 | 18.2262 | 18700 | 19.6083 | 1.0 | 0.0 | {'rouge1': 0.002787108950998835, 'rouge2': 0.0, 'rougeL': 0.0027831656807373057, 'rougeLsum': 0.002779212804473266} |
248
- | 21.0913 | 18.3237 | 18800 | 19.6103 | 1.0 | 0.0 | {'rouge1': 0.002736269461697797, 'rouge2': 0.0, 'rougeL': 0.0027413805653583884, 'rougeLsum': 0.0027326983208262965} |
249
- | 21.8394 | 18.4213 | 18900 | 19.6094 | 1.0 | 0.0 | {'rouge1': 0.0026882743207969828, 'rouge2': 0.0, 'rougeL': 0.0026944461160171634, 'rougeLsum': 0.002690466547527985} |
250
- | 21.3003 | 18.5188 | 19000 | 19.6100 | 1.0 | 0.0 | {'rouge1': 0.0026972822219798608, 'rouge2': 0.0, 'rougeL': 0.0027035506707190006, 'rougeLsum': 0.0026859918420529634} |
251
- | 21.3927 | 18.6163 | 19100 | 19.6100 | 1.0 | 0.0 | {'rouge1': 0.0027229895342109896, 'rouge2': 0.0, 'rougeL': 0.0027161998080930784, 'rougeLsum': 0.002716258975876111} |
252
- | 21.8066 | 18.7138 | 19200 | 19.6084 | 1.0 | 0.0 | {'rouge1': 0.0027547915138935327, 'rouge2': 0.0, 'rougeL': 0.0027402903942141186, 'rougeLsum': 0.0027386062148752454} |
253
- | 21.2417 | 18.8113 | 19300 | 19.6099 | 1.0 | 0.0 | {'rouge1': 0.00275590222215193, 'rouge2': 0.0, 'rougeL': 0.002750915364146628, 'rougeLsum': 0.002737685090499137} |
254
- | 21.0267 | 18.9088 | 19400 | 19.6093 | 1.0 | 0.0 | {'rouge1': 0.00281114166222364, 'rouge2': 0.0, 'rougeL': 0.002809994596482763, 'rougeLsum': 0.0028052979071486813} |
255
- | 21.5009 | 19.0059 | 19500 | 19.6098 | 1.0 | 0.0 | {'rouge1': 0.002771629735559773, 'rouge2': 0.0, 'rougeL': 0.0027792879375851875, 'rougeLsum': 0.002771271567341368} |
256
- | 20.8413 | 19.1034 | 19600 | 19.6095 | 1.0 | 0.0 | {'rouge1': 0.0027888813329887407, 'rouge2': 0.0, 'rougeL': 0.0027714813149101575, 'rougeLsum': 0.0027788299173989116} |
257
- | 21.2181 | 19.2009 | 19700 | 19.6088 | 1.0 | 0.0 | {'rouge1': 0.0027602074424341125, 'rouge2': 0.0, 'rougeL': 0.002753108308716328, 'rougeLsum': 0.002763534285709999} |
258
- | 20.9146 | 19.2984 | 19800 | 19.6096 | 1.0 | 0.0 | {'rouge1': 0.0027468964981578682, 'rouge2': 0.0, 'rougeL': 0.0027567987883931875, 'rougeLsum': 0.0027488001806101354} |
259
- | 21.1476 | 19.3959 | 19900 | 19.6086 | 1.0 | 0.0 | {'rouge1': 0.002737477181968217, 'rouge2': 0.0, 'rougeL': 0.0027265576259631937, 'rougeLsum': 0.0027365011293396376} |
260
- | 20.7956 | 19.4934 | 20000 | 19.6099 | 1.0 | 0.0 | {'rouge1': 0.00279006471977476, 'rouge2': 0.0, 'rougeL': 0.0027898196339676976, 'rougeLsum': 0.002790392449640854} |
261
- | 20.9314 | 19.5909 | 20100 | 19.6108 | 1.0 | 0.0 | {'rouge1': 0.0027869397814448867, 'rouge2': 0.0, 'rougeL': 0.0027623712906207423, 'rougeLsum': 0.002773878027014285} |
262
- | 21.6489 | 19.6884 | 20200 | 19.6099 | 1.0 | 0.0 | {'rouge1': 0.0027319378928685055, 'rouge2': 0.0, 'rougeL': 0.002717556639667897, 'rougeLsum': 0.0027426517250744033} |
263
- | 20.8808 | 19.7860 | 20300 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.0027519063139155595, 'rouge2': 0.0, 'rougeL': 0.002751781901002815, 'rougeLsum': 0.0027610020863314275} |
264
- | 21.6816 | 19.8835 | 20400 | 19.6098 | 1.0 | 0.0 | {'rouge1': 0.0027733318181049136, 'rouge2': 0.0, 'rougeL': 0.0027781018114251483, 'rougeLsum': 0.002773847592205045} |
265
- | 20.7439 | 19.9810 | 20500 | 19.6096 | 1.0 | 0.0 | {'rouge1': 0.002720074689908742, 'rouge2': 0.0, 'rougeL': 0.002719810041943358, 'rougeLsum': 0.002726557075748475} |
266
- | 20.7333 | 20.0780 | 20600 | 19.6100 | 1.0 | 0.0 | {'rouge1': 0.0026956789451869417, 'rouge2': 0.0, 'rougeL': 0.0026693102782522162, 'rougeLsum': 0.0026853496533263167} |
267
- | 21.4015 | 20.1755 | 20700 | 19.6101 | 1.0 | 0.0 | {'rouge1': 0.002696941880271095, 'rouge2': 0.0, 'rougeL': 0.0026770144409526014, 'rougeLsum': 0.002686601875319988} |
268
- | 21.9557 | 20.2730 | 20800 | 19.6086 | 1.0 | 0.0 | {'rouge1': 0.0027662192670771294, 'rouge2': 0.0, 'rougeL': 0.002759828569172164, 'rougeLsum': 0.0027472037136954596} |
269
- | 20.949 | 20.3706 | 20900 | 19.6094 | 1.0 | 0.0 | {'rouge1': 0.00280754065444111, 'rouge2': 0.0, 'rougeL': 0.0027843531715911213, 'rougeLsum': 0.0027886723677059168} |
270
- | 21.1133 | 20.4681 | 21000 | 19.6099 | 1.0 | 0.0 | {'rouge1': 0.002787006941238744, 'rouge2': 0.0, 'rougeL': 0.0027741869727929904, 'rougeLsum': 0.002764723923867584} |
271
- | 21.0117 | 20.5656 | 21100 | 19.6087 | 1.0 | 0.0 | {'rouge1': 0.0027988694355229275, 'rouge2': 0.0, 'rougeL': 0.002795160710550043, 'rougeLsum': 0.002785965192838283} |
272
- | 20.7446 | 20.6631 | 21200 | 19.6090 | 1.0 | 0.0 | {'rouge1': 0.002751446834668667, 'rouge2': 0.0, 'rougeL': 0.0027482116214166425, 'rougeLsum': 0.0027494203547003514} |
273
- | 21.1632 | 20.7606 | 21300 | 19.6112 | 1.0 | 0.0 | {'rouge1': 0.002735489478423482, 'rouge2': 0.0, 'rougeL': 0.002727980597110261, 'rougeLsum': 0.0027172506986589953} |
274
- | 21.2376 | 20.8581 | 21400 | 19.6089 | 1.0 | 0.0 | {'rouge1': 0.002713097967573196, 'rouge2': 0.0, 'rougeL': 0.002726878317882355, 'rougeLsum': 0.002718022583874662} |
275
- | 21.0155 | 20.9556 | 21500 | 19.6089 | 1.0 | 0.0 | {'rouge1': 0.0027394440482761614, 'rouge2': 0.0, 'rougeL': 0.002739816393427085, 'rougeLsum': 0.0027445977306268764} |
276
- | 22.3475 | 21.0527 | 21600 | 19.6105 | 1.0 | 0.0 | {'rouge1': 0.0027461303744056487, 'rouge2': 0.0, 'rougeL': 0.0027504361742856157, 'rougeLsum': 0.0027675317700505495} |
277
- | 21.1452 | 21.1502 | 21700 | 19.6094 | 1.0 | 0.0 | {'rouge1': 0.0027356143645196635, 'rouge2': 0.0, 'rougeL': 0.002726354177366377, 'rougeLsum': 0.0027246817211990767} |
278
- | 21.002 | 21.2477 | 21800 | 19.6099 | 1.0 | 0.0 | {'rouge1': 0.0027615984776698747, 'rouge2': 0.0, 'rougeL': 0.0027468815491409893, 'rougeLsum': 0.002750078948157963} |
279
- | 20.9211 | 21.3452 | 21900 | 19.6088 | 1.0 | 0.0 | {'rouge1': 0.002790151247559133, 'rouge2': 0.0, 'rougeL': 0.0027660782498606998, 'rougeLsum': 0.0027891331075057496} |
280
- | 21.6084 | 21.4427 | 22000 | 19.6094 | 1.0 | 0.0 | {'rouge1': 0.0027627236533316456, 'rouge2': 0.0, 'rougeL': 0.0027427685082249383, 'rougeLsum': 0.002742001190090771} |
281
- | 21.0958 | 21.5402 | 22100 | 19.6098 | 1.0 | 0.0 | {'rouge1': 0.002705879420767704, 'rouge2': 0.0, 'rougeL': 0.0026879789032630986, 'rougeLsum': 0.00268611373932317} |
282
- | 20.8982 | 21.6377 | 22200 | 19.6093 | 1.0 | 0.0 | {'rouge1': 0.0028397284133225426, 'rouge2': 0.0, 'rougeL': 0.002828348972619898, 'rougeLsum': 0.0028458282966945477} |
283
- | 21.1356 | 21.7353 | 22300 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.002722363224802095, 'rouge2': 0.0, 'rougeL': 0.0027283513607680287, 'rougeLsum': 0.002719823666889622} |
284
- | 21.0076 | 21.8328 | 22400 | 19.6106 | 1.0 | 0.0 | {'rouge1': 0.0027446767787117016, 'rouge2': 0.0, 'rougeL': 0.00274319478633041, 'rougeLsum': 0.0027414645705070343} |
285
- | 21.2843 | 21.9303 | 22500 | 19.6091 | 1.0 | 0.0 | {'rouge1': 0.002729247588096078, 'rouge2': 0.0, 'rougeL': 0.0027183399524529353, 'rougeLsum': 0.002734086860578381} |
286
- | 20.9945 | 22.0273 | 22600 | 19.6097 | 1.0 | 0.0 | {'rouge1': 0.0027219984875440717, 'rouge2': 0.0, 'rougeL': 0.002730870479061959, 'rougeLsum': 0.002704791368564033} |
287
- | 21.368 | 22.1248 | 22700 | 19.6102 | 1.0 | 0.0 | {'rouge1': 0.0026679797243019704, 'rouge2': 0.0, 'rougeL': 0.002670045108977524, 'rougeLsum': 0.0026720611872181233} |
288
- | 21.2502 | 22.2223 | 22800 | 19.6095 | 1.0 | 0.0 | {'rouge1': 0.0027991285605713824, 'rouge2': 0.0, 'rougeL': 0.002774390309416498, 'rougeLsum': 0.0027959852064211766} |
289
- | 21.0903 | 22.3198 | 22900 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.002765829138711636, 'rouge2': 0.0, 'rougeL': 0.0027676675771178276, 'rougeLsum': 0.0027719212344873797} |
290
- | 21.071 | 22.4174 | 23000 | 19.6087 | 1.0 | 0.0 | {'rouge1': 0.0026789308837803626, 'rouge2': 0.0, 'rougeL': 0.002681451503054184, 'rougeLsum': 0.002668732722925495} |
291
- | 21.1465 | 22.5149 | 23100 | 19.6102 | 1.0 | 0.0 | {'rouge1': 0.0028044582272094163, 'rouge2': 0.0, 'rougeL': 0.0027863951750427577, 'rougeLsum': 0.002784023350090521} |
292
- | 21.1717 | 22.6124 | 23200 | 19.6088 | 1.0 | 0.0 | {'rouge1': 0.002780345892809192, 'rouge2': 0.0, 'rougeL': 0.002756451642689166, 'rougeLsum': 0.002774335561510132} |
293
- | 21.6599 | 22.7099 | 23300 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.002839182953345387, 'rouge2': 0.0, 'rougeL': 0.0028091504550981465, 'rougeLsum': 0.002831068079761468} |
294
- | 21.2603 | 22.8074 | 23400 | 19.6081 | 1.0 | 0.0 | {'rouge1': 0.0027324605290447853, 'rouge2': 0.0, 'rougeL': 0.002726308985232696, 'rougeLsum': 0.0027371315377168522} |
295
- | 21.3685 | 22.9049 | 23500 | 19.6102 | 1.0 | 0.0 | {'rouge1': 0.002736892665114974, 'rouge2': 0.0, 'rougeL': 0.0027282636905552647, 'rougeLsum': 0.0027259660927268863} |
296
- | 21.6444 | 23.0020 | 23600 | 19.6098 | 1.0 | 0.0 | {'rouge1': 0.002784768978573526, 'rouge2': 0.0, 'rougeL': 0.002776283962224746, 'rougeLsum': 0.0027764071370780137} |
297
- | 21.7306 | 23.0995 | 23700 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.002722886097875529, 'rouge2': 0.0, 'rougeL': 0.0027158792979091015, 'rougeLsum': 0.002692359847128559} |
298
- | 21.0974 | 23.1970 | 23800 | 19.6098 | 1.0 | 0.0 | {'rouge1': 0.0027454097374119096, 'rouge2': 0.0, 'rougeL': 0.0027259725893778695, 'rougeLsum': 0.0027217332474579726} |
299
- | 20.9606 | 23.2945 | 23900 | 19.6097 | 1.0 | 0.0 | {'rouge1': 0.002760732324979422, 'rouge2': 0.0, 'rougeL': 0.0027481988657448806, 'rougeLsum': 0.0027586144694165026} |
300
- | 20.7565 | 23.3920 | 24000 | 19.6096 | 1.0 | 0.0 | {'rouge1': 0.0027365753958038157, 'rouge2': 0.0, 'rougeL': 0.0027309728014676526, 'rougeLsum': 0.0027534819600392433} |
301
- | 21.534 | 23.4895 | 24100 | 19.6094 | 1.0 | 0.0 | {'rouge1': 0.002779101134953702, 'rouge2': 0.0, 'rougeL': 0.00277314383049895, 'rougeLsum': 0.002766263505757792} |
302
- | 21.1627 | 23.5870 | 24200 | 19.6100 | 1.0 | 0.0 | {'rouge1': 0.0027624372614694368, 'rouge2': 0.0, 'rougeL': 0.002747376866884613, 'rougeLsum': 0.002769698148907234} |
303
- | 21.4407 | 23.6845 | 24300 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.0028061165636831444, 'rouge2': 0.0, 'rougeL': 0.0027919915912379347, 'rougeLsum': 0.002788596041922496} |
304
- | 21.3477 | 23.7821 | 24400 | 19.6097 | 1.0 | 0.0 | {'rouge1': 0.0027892369219911567, 'rouge2': 0.0, 'rougeL': 0.002806289525989932, 'rougeLsum': 0.002771552276529669} |
305
- | 21.1658 | 23.8796 | 24500 | 19.6089 | 1.0 | 0.0 | {'rouge1': 0.002778325438002934, 'rouge2': 0.0, 'rougeL': 0.002778645874637615, 'rougeLsum': 0.0027470988578707756} |
306
- | 20.8856 | 23.9771 | 24600 | 19.6095 | 1.0 | 0.0 | {'rouge1': 0.0027282643730243273, 'rouge2': 0.0, 'rougeL': 0.002718257900697881, 'rougeLsum': 0.0027184034986794} |
307
- | 20.2432 | 24.0741 | 24700 | 19.6108 | 1.0 | 0.0 | {'rouge1': 0.0027621818965239005, 'rouge2': 0.0, 'rougeL': 0.0027291337801835444, 'rougeLsum': 0.002727514909319422} |
308
- | 21.2013 | 24.1716 | 24800 | 19.6088 | 1.0 | 0.0 | {'rouge1': 0.0027708177876019603, 'rouge2': 0.0, 'rougeL': 0.0027586575230615995, 'rougeLsum': 0.0027511540512259007} |
309
- | 21.1907 | 24.2691 | 24900 | 19.6086 | 1.0 | 0.0 | {'rouge1': 0.002678475647715996, 'rouge2': 0.0, 'rougeL': 0.002668532292843159, 'rougeLsum': 0.002700247537073196} |
310
- | 21.3128 | 24.3667 | 25000 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.002752323478518874, 'rouge2': 0.0, 'rougeL': 0.0027409883881647605, 'rougeLsum': 0.0027384957635006486} |
311
- | 20.9111 | 24.4642 | 25100 | 19.6103 | 1.0 | 0.0 | {'rouge1': 0.0027686917855991233, 'rouge2': 0.0, 'rougeL': 0.0027543215742616865, 'rougeLsum': 0.0027525639337745702} |
312
- | 21.3538 | 24.5617 | 25200 | 19.6096 | 1.0 | 0.0 | {'rouge1': 0.002726750237339818, 'rouge2': 0.0, 'rougeL': 0.00272533735105983, 'rougeLsum': 0.0027144728128004033} |
313
- | 20.8228 | 24.6592 | 25300 | 19.6095 | 1.0 | 0.0 | {'rouge1': 0.002713663937480557, 'rouge2': 0.0, 'rougeL': 0.002692447691440572, 'rougeLsum': 0.0026975760579887147} |
314
- | 21.3194 | 24.7567 | 25400 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.002731194988580616, 'rouge2': 0.0, 'rougeL': 0.0027219996766114085, 'rougeLsum': 0.00271985033199193} |
315
- | 21.0206 | 24.8542 | 25500 | 19.6095 | 1.0 | 0.0 | {'rouge1': 0.0027240234631116, 'rouge2': 0.0, 'rougeL': 0.002711051458066428, 'rougeLsum': 0.0027161790453829764} |
316
- | 20.8306 | 24.9517 | 25600 | 19.6100 | 1.0 | 0.0 | {'rouge1': 0.0027606740427201576, 'rouge2': 0.0, 'rougeL': 0.0027303265728442563, 'rougeLsum': 0.0027488735475615206} |
317
- | 21.9604 | 25.0488 | 25700 | 19.6090 | 1.0 | 0.0 | {'rouge1': 0.002773348686306411, 'rouge2': 0.0, 'rougeL': 0.0027573265388723973, 'rougeLsum': 0.002755108940810327} |
318
- | 20.7326 | 25.1463 | 25800 | 19.6095 | 1.0 | 0.0 | {'rouge1': 0.0027568178487791433, 'rouge2': 0.0, 'rougeL': 0.0027579795693397093, 'rougeLsum': 0.0027484507339089605} |
319
- | 21.5932 | 25.2438 | 25900 | 19.6086 | 1.0 | 0.0 | {'rouge1': 0.002754771731453845, 'rouge2': 0.0, 'rougeL': 0.00276465556338118, 'rougeLsum': 0.0027489703138797966} |
320
- | 21.4978 | 25.3413 | 26000 | 19.6087 | 1.0 | 0.0 | {'rouge1': 0.0027042332793661503, 'rouge2': 0.0, 'rougeL': 0.0026850925884523286, 'rougeLsum': 0.0026929937924694957} |
321
- | 21.1363 | 25.4388 | 26100 | 19.6093 | 1.0 | 0.0 | {'rouge1': 0.0027385768349852896, 'rouge2': 0.0, 'rougeL': 0.0027217517650207903, 'rougeLsum': 0.002732035390342547} |
322
- | 21.17 | 25.5363 | 26200 | 19.6090 | 1.0 | 0.0 | {'rouge1': 0.002786092074111876, 'rouge2': 0.0, 'rougeL': 0.0027877477958592094, 'rougeLsum': 0.0027734949615645585} |
323
- | 21.1345 | 25.6338 | 26300 | 19.6088 | 1.0 | 0.0 | {'rouge1': 0.0028041777215512377, 'rouge2': 0.0, 'rougeL': 0.002806153019944042, 'rougeLsum': 0.002787532324029233} |
324
- | 21.4113 | 25.7314 | 26400 | 19.6098 | 1.0 | 0.0 | {'rouge1': 0.0027548755867270814, 'rouge2': 0.0, 'rougeL': 0.002742431657390738, 'rougeLsum': 0.002738679175595046} |
325
- | 20.841 | 25.8289 | 26500 | 19.6087 | 1.0 | 0.0 | {'rouge1': 0.0027655288801190113, 'rouge2': 0.0, 'rougeL': 0.0027596895393776945, 'rougeLsum': 0.002762966573591037} |
326
- | 21.4331 | 25.9264 | 26600 | 19.6094 | 1.0 | 0.0 | {'rouge1': 0.00282585225387446, 'rouge2': 0.0, 'rougeL': 0.002816292659076816, 'rougeLsum': 0.0028237053985688244} |
327
- | 20.3417 | 26.0234 | 26700 | 19.6106 | 1.0 | 0.0 | {'rouge1': 0.002805049803268029, 'rouge2': 0.0, 'rougeL': 0.002782995068480899, 'rougeLsum': 0.002792416317905279} |
328
- | 21.8391 | 26.1209 | 26800 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.002722652182703996, 'rouge2': 0.0, 'rougeL': 0.002724820716665052, 'rougeLsum': 0.002706308997412558} |
329
- | 21.4816 | 26.2184 | 26900 | 19.6078 | 1.0 | 0.0 | {'rouge1': 0.002738664293362692, 'rouge2': 0.0, 'rougeL': 0.0027288443520888384, 'rougeLsum': 0.0027316554372243543} |
330
- | 21.5785 | 26.3159 | 27000 | 19.6093 | 1.0 | 0.0 | {'rouge1': 0.0027791164773738, 'rouge2': 0.0, 'rougeL': 0.0027629520319637484, 'rougeLsum': 0.0027846341212940185} |
331
- | 20.7239 | 26.4135 | 27100 | 19.6108 | 1.0 | 0.0 | {'rouge1': 0.0028155830269883395, 'rouge2': 0.0, 'rougeL': 0.0028184057658230547, 'rougeLsum': 0.0028203792551108374} |
332
- | 20.8174 | 26.5110 | 27200 | 19.6089 | 1.0 | 0.0 | {'rouge1': 0.0027090665493339056, 'rouge2': 0.0, 'rougeL': 0.002704104627411546, 'rougeLsum': 0.0027066156977996287} |
333
- | 20.9267 | 26.6085 | 27300 | 19.6094 | 1.0 | 0.0 | {'rouge1': 0.0027840109287504107, 'rouge2': 0.0, 'rougeL': 0.0027913484712941044, 'rougeLsum': 0.002779264780430062} |
334
- | 21.1721 | 26.7060 | 27400 | 19.6086 | 1.0 | 0.0 | {'rouge1': 0.0028259216706665673, 'rouge2': 0.0, 'rougeL': 0.002826062007490909, 'rougeLsum': 0.002807178093606982} |
335
- | 21.4231 | 26.8035 | 27500 | 19.6096 | 1.0 | 0.0 | {'rouge1': 0.002754809033287315, 'rouge2': 0.0, 'rougeL': 0.0027677066534808163, 'rougeLsum': 0.002730772272790164} |
336
- | 20.9837 | 26.9010 | 27600 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.002679411814267354, 'rouge2': 0.0, 'rougeL': 0.002672702122369078, 'rougeLsum': 0.0026896329010613275} |
337
- | 21.7904 | 26.9985 | 27700 | 19.6090 | 1.0 | 0.0 | {'rouge1': 0.0027194416440195104, 'rouge2': 0.0, 'rougeL': 0.002698875836506065, 'rougeLsum': 0.0027119097529551975} |
338
- | 21.4393 | 27.0956 | 27800 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.002804782680710877, 'rouge2': 0.0, 'rougeL': 0.0028060797432799167, 'rougeLsum': 0.002811271467966249} |
339
- | 21.1316 | 27.1931 | 27900 | 19.6101 | 1.0 | 0.0 | {'rouge1': 0.00266017698782765, 'rouge2': 0.0, 'rougeL': 0.0026668012092724664, 'rougeLsum': 0.002667873851859838} |
340
- | 20.7437 | 27.2906 | 28000 | 19.6089 | 1.0 | 0.0 | {'rouge1': 0.0027635229432354533, 'rouge2': 0.0, 'rougeL': 0.0027611682245425304, 'rougeLsum': 0.002759335565299212} |
341
- | 21.822 | 27.3881 | 28100 | 19.6098 | 1.0 | 0.0 | {'rouge1': 0.002768042949824177, 'rouge2': 0.0, 'rougeL': 0.0027685843086949517, 'rougeLsum': 0.002759250001381941} |
342
- | 21.0373 | 27.4856 | 28200 | 19.6098 | 1.0 | 0.0 | {'rouge1': 0.0027321435756168643, 'rouge2': 0.0, 'rougeL': 0.0027288422959142727, 'rougeLsum': 0.002718000774614259} |
343
- | 21.264 | 27.5831 | 28300 | 19.6090 | 1.0 | 0.0 | {'rouge1': 0.0027436899749351527, 'rouge2': 0.0, 'rougeL': 0.002729064325238338, 'rougeLsum': 0.002736632601885361} |
344
- | 20.7029 | 27.6806 | 28400 | 19.6103 | 1.0 | 0.0 | {'rouge1': 0.002771395516355969, 'rouge2': 0.0, 'rougeL': 0.002779032030685019, 'rougeLsum': 0.0027803508468027035} |
345
- | 21.3658 | 27.7782 | 28500 | 19.6094 | 1.0 | 0.0 | {'rouge1': 0.00275988039002791, 'rouge2': 0.0, 'rougeL': 0.0027451007772776523, 'rougeLsum': 0.0027578104354608335} |
346
- | 21.7377 | 27.8757 | 28600 | 19.6091 | 1.0 | 0.0 | {'rouge1': 0.002729049347571442, 'rouge2': 0.0, 'rougeL': 0.002724451499375154, 'rougeLsum': 0.0027251072092604753} |
347
- | 20.9503 | 27.9732 | 28700 | 19.6089 | 1.0 | 0.0 | {'rouge1': 0.0027505515521059377, 'rouge2': 0.0, 'rougeL': 0.002737815782150629, 'rougeLsum': 0.002741249290034845} |
348
- | 21.3929 | 28.0702 | 28800 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.0027598944314073635, 'rouge2': 0.0, 'rougeL': 0.0027696588446880317, 'rougeLsum': 0.0027754888501531653} |
349
- | 21.3695 | 28.1677 | 28900 | 19.6086 | 1.0 | 0.0 | {'rouge1': 0.002742390120913706, 'rouge2': 0.0, 'rougeL': 0.002743540516104216, 'rougeLsum': 0.0027213975682811842} |
350
- | 20.8198 | 28.2652 | 29000 | 19.6095 | 1.0 | 0.0 | {'rouge1': 0.0027628680559538196, 'rouge2': 0.0, 'rougeL': 0.0027630991233503124, 'rougeLsum': 0.0027501538656922514} |
351
- | 21.2988 | 28.3627 | 29100 | 19.6099 | 1.0 | 0.0 | {'rouge1': 0.0027904236417805057, 'rouge2': 0.0, 'rougeL': 0.0027744804668661358, 'rougeLsum': 0.002779038112185649} |
352
- | 21.0188 | 28.4603 | 29200 | 19.6085 | 1.0 | 0.0 | {'rouge1': 0.002726579816164975, 'rouge2': 0.0, 'rougeL': 0.0027028543057875543, 'rougeLsum': 0.0027124727163823064} |
353
- | 21.0148 | 28.5578 | 29300 | 19.6098 | 1.0 | 0.0 | {'rouge1': 0.0027906423781852365, 'rouge2': 0.0, 'rougeL': 0.0027989759560418832, 'rougeLsum': 0.0027792669427427544} |
354
- | 21.0896 | 28.6553 | 29400 | 19.6091 | 1.0 | 0.0 | {'rouge1': 0.0027768255609248726, 'rouge2': 0.0, 'rougeL': 0.0027691620218105693, 'rougeLsum': 0.002770060518293274} |
355
- | 21.4141 | 28.7528 | 29500 | 19.6093 | 1.0 | 0.0 | {'rouge1': 0.0027493853514046016, 'rouge2': 0.0, 'rougeL': 0.0027501963347914796, 'rougeLsum': 0.0027570000302056426} |
356
- | 21.8846 | 28.8503 | 29600 | 19.6100 | 1.0 | 0.0 | {'rouge1': 0.0027581972375691774, 'rouge2': 0.0, 'rougeL': 0.0027439178568040585, 'rougeLsum': 0.002748603162078973} |
357
- | 21.0726 | 28.9478 | 29700 | 19.6095 | 1.0 | 0.0 | {'rouge1': 0.002741068009249928, 'rouge2': 0.0, 'rougeL': 0.002748308891400995, 'rougeLsum': 0.0027409254520187228} |
358
- | 21.4292 | 29.0449 | 29800 | 19.6088 | 1.0 | 0.0 | {'rouge1': 0.0027797382058343434, 'rouge2': 0.0, 'rougeL': 0.0027786886485021605, 'rougeLsum': 0.0027845311420149066} |
359
- | 21.0927 | 29.1424 | 29900 | 19.6096 | 1.0 | 0.0 | {'rouge1': 0.0027565718500200424, 'rouge2': 0.0, 'rougeL': 0.002754433924356602, 'rougeLsum': 0.0027489949717093756} |
360
- | 21.4523 | 29.2399 | 30000 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.0027045838155010235, 'rouge2': 0.0, 'rougeL': 0.002709761826664278, 'rougeLsum': 0.002720648586707702} |
361
- | 21.0274 | 29.3374 | 30100 | 19.6108 | 1.0 | 0.0 | {'rouge1': 0.0027522704886324785, 'rouge2': 0.0, 'rougeL': 0.0027336979669577077, 'rougeLsum': 0.002744414094402602} |
362
- | 20.8623 | 29.4349 | 30200 | 19.6091 | 1.0 | 0.0 | {'rouge1': 0.002759214902362148, 'rouge2': 0.0, 'rougeL': 0.0027449793496478123, 'rougeLsum': 0.002746657611933488} |
363
- | 21.1368 | 29.5324 | 30300 | 19.6092 | 1.0 | 0.0 | {'rouge1': 0.0027532425984933663, 'rouge2': 0.0, 'rougeL': 0.002760696348743756, 'rougeLsum': 0.002746639477083584} |
364
- | 21.161 | 29.6299 | 30400 | 19.6091 | 1.0 | 0.0 | {'rouge1': 0.002772743011754227, 'rouge2': 0.0, 'rougeL': 0.0027858855459742086, 'rougeLsum': 0.002777107442320375} |
365
- | 21.5073 | 29.7275 | 30500 | 19.6098 | 1.0 | 0.0 | {'rouge1': 0.0027408825621490964, 'rouge2': 0.0, 'rougeL': 0.0027116258867538705, 'rougeLsum': 0.0027303974881727564} |
366
- | 21.2063 | 29.8250 | 30600 | 19.6100 | 1.0 | 0.0 | {'rouge1': 0.0027690102473374285, 'rouge2': 0.0, 'rougeL': 0.002774398680841517, 'rougeLsum': 0.0027809552916059598} |
367
- | 21.531 | 29.9225 | 30700 | 19.6100 | 1.0 | 0.0 | {'rouge1': 0.002775591766145671, 'rouge2': 0.0, 'rougeL': 0.0027371732534244783, 'rougeLsum': 0.002771582675127327} |
368
 
369
 
370
  ### Framework versions
 
9
  - bleu
10
  - rouge
11
  model-index:
12
+ - name: wav2vec2-large-mms-1b-DZ
13
  results: []
14
  ---
15
 
16
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
17
  should probably proofread and complete it, then remove this comment. -->
18
 
19
+ # wav2vec2-large-mms-1b-DZ
20
 
21
  This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
22
  It achieves the following results on the evaluation set:
23
+ - Loss: 0.3318
24
+ - Wer: 0.5332
25
+ - Bleu: {'bleu': 0.20626502760570276, 'precisions': [0.4828561729093584, 0.26526984126984127, 0.15708092485549133, 0.09694133377904061], 'brevity_penalty': 0.9815017376632986, 'length_ratio': 0.981670739835592, 'translation_length': 8837, 'reference_length': 9002}
26
+ - Rouge: {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0}
27
 
28
  ## Model description
29
 
 
42
  ### Training hyperparameters
43
 
44
  The following hyperparameters were used during training:
45
+ - learning_rate: 0.0001
46
+ - train_batch_size: 8
47
+ - eval_batch_size: 16
48
  - seed: 42
49
+ - gradient_accumulation_steps: 4
50
  - total_train_batch_size: 32
51
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
52
  - lr_scheduler_type: linear
53
+ - lr_scheduler_warmup_steps: 500
54
+ - num_epochs: 100
55
  - mixed_precision_training: Native AMP
56
 
57
  ### Training results
58
 
59
+ | Training Loss | Epoch | Step | Validation Loss | Wer | Bleu | Rouge |
60
+ |:-------------:|:-----:|:----:|:---------------:|:------:|:---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------:|
61
+ | 8.9409 | 1.0 | 121 | 7.3836 | 1.0009 | {'bleu': 0.0, 'precisions': [0.0, 0.0, 0.0, 0.0], 'brevity_penalty': 0.15361828967433966, 'length_ratio': 0.3480337702732726, 'translation_length': 3133, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
62
+ | 5.8951 | 2.0 | 242 | 3.9240 | 1.0 | {'bleu': 0.0, 'precisions': [0.0, 0.0, 0.0, 0.0], 'brevity_penalty': 0.00023460944616129434, 'length_ratio': 0.10686514107976006, 'translation_length': 962, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
63
+ | 3.448 | 3.0 | 363 | 3.3244 | 1.0072 | {'bleu': 0.0, 'precisions': [0.00021687269572760788, 0.0, 0.0, 0.0], 'brevity_penalty': 0.38585716882722343, 'length_ratio': 0.5122195067762719, 'translation_length': 4611, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
64
+ | 3.3048 | 4.0 | 484 | 3.2099 | 1.0540 | {'bleu': 0.0, 'precisions': [0.0012913223140495868, 0.0, 0.0, 0.0], 'brevity_penalty': 0.8500599971491325, 'length_ratio': 0.8602532770495446, 'translation_length': 7744, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
65
+ | 1.3604 | 5.0 | 605 | 0.6633 | 0.7965 | {'bleu': 0.034929556738440316, 'precisions': [0.21936736325225534, 0.05991019884541373, 0.017828437819669734, 0.007105396717983421], 'brevity_penalty': 0.9724101311329575, 'length_ratio': 0.9727838258164853, 'translation_length': 8757, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
66
+ | 0.6764 | 6.0 | 726 | 0.4717 | 0.6724 | {'bleu': 0.09414039105458619, 'precisions': [0.34541504687857305, 0.1395169578622816, 0.06105417276720351, 0.030010172939979655], 'brevity_penalty': 0.9711537088639254, 'length_ratio': 0.971561875138858, 'translation_length': 8746, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
67
+ | 0.6118 | 7.0 | 847 | 0.4297 | 0.6431 | {'bleu': 0.10327123610576155, 'precisions': [0.3748719699556162, 0.1584664536741214, 0.06853899883585565, 0.03080808080808081], 'brevity_penalty': 0.9758289500370382, 'length_ratio': 0.9761164185736503, 'translation_length': 8787, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
68
+ | 0.5499 | 8.0 | 968 | 0.4136 | 0.6383 | {'bleu': 0.09547633908306723, 'precisions': [0.37913718329148594, 0.15538461538461537, 0.06206191588785047, 0.0253592561284869], 'brevity_penalty': 0.9729807252327849, 'length_ratio': 0.9733392579426794, 'translation_length': 8762, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
69
+ | 0.5426 | 9.0 | 1089 | 0.3948 | 0.6236 | {'bleu': 0.1146211663681401, 'precisions': [0.3941814033086138, 0.1719851339228502, 0.07882061012990804, 0.03599188915174045], 'brevity_penalty': 0.973322929713784, 'length_ratio': 0.9736725172183959, 'translation_length': 8765, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
70
+ | 0.5224 | 10.0 | 1210 | 0.3845 | 0.6133 | {'bleu': 0.14615786010373802, 'precisions': [0.4039206747207659, 0.19687660010240654, 0.10451895043731778, 0.060917988525143435], 'brevity_penalty': 0.9743488596571711, 'length_ratio': 0.9746722950455454, 'translation_length': 8774, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
71
+ | 0.5106 | 11.0 | 1331 | 0.3768 | 0.6081 | {'bleu': 0.14761534429663833, 'precisions': [0.4103973434100538, 0.2001029468536868, 0.10602727672679278, 0.0616822429906542], 'brevity_penalty': 0.969666867156736, 'length_ratio': 0.9701177516107532, 'translation_length': 8733, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
72
+ | 0.4808 | 12.0 | 1452 | 0.3689 | 0.6038 | {'bleu': 0.14419001572294796, 'precisions': [0.4128158433872069, 0.20002556237218813, 0.10203784570596798, 0.05660377358490566], 'brevity_penalty': 0.9757151727531809, 'length_ratio': 0.9760053321484115, 'translation_length': 8786, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
73
+ | 0.4887 | 13.0 | 1573 | 0.3645 | 0.5959 | {'bleu': 0.14552105797325302, 'precisions': [0.4212262541235354, 0.20283561118916849, 0.10340314136125654, 0.0558734432850892], 'brevity_penalty': 0.9762839328773337, 'length_ratio': 0.9765607642746057, 'translation_length': 8791, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
74
+ | 0.4868 | 14.0 | 1694 | 0.3618 | 0.5964 | {'bleu': 0.14398457640279802, 'precisions': [0.4209029910155806, 0.20061294853786235, 0.10206455364931666, 0.05484522207267833], 'brevity_penalty': 0.9765113485390307, 'length_ratio': 0.9767829371250834, 'translation_length': 8793, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
75
+ | 0.4694 | 15.0 | 1815 | 0.3552 | 0.5896 | {'bleu': 0.1407651620422715, 'precisions': [0.42652899126290705, 0.20315883326964718, 0.1007830626450116, 0.04898506961919141], 'brevity_penalty': 0.978782729886213, 'length_ratio': 0.97900466562986, 'translation_length': 8813, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
76
+ | 0.4717 | 16.0 | 1936 | 0.3515 | 0.5820 | {'bleu': 0.14704090054592955, 'precisions': [0.4347430650295589, 0.21087567015573142, 0.10566860465116279, 0.05299461641991925], 'brevity_penalty': 0.9768523773634661, 'length_ratio': 0.9771161964007998, 'translation_length': 8796, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
77
+ | 0.4697 | 17.0 | 2057 | 0.3472 | 0.5820 | {'bleu': 0.16519675176223306, 'precisions': [0.4347628256171084, 0.221356495082386, 0.12045388420133837, 0.0707189762586294], 'brevity_penalty': 0.9762839328773337, 'length_ratio': 0.9765607642746057, 'translation_length': 8791, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
78
+ | 0.4495 | 18.0 | 2178 | 0.3440 | 0.5790 | {'bleu': 0.16684635490186076, 'precisions': [0.4380551127305853, 0.22327365728900256, 0.12163146394756008, 0.07200674536256324], 'brevity_penalty': 0.9752599372827168, 'length_ratio': 0.9755609864474561, 'translation_length': 8782, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
79
+ | 0.4415 | 19.0 | 2299 | 0.3415 | 0.5724 | {'bleu': 0.162083792001847, 'precisions': [0.4451789377706861, 0.22375832053251407, 0.11798162461717952, 0.06515867656988521], 'brevity_penalty': 0.9743488596571711, 'length_ratio': 0.9746722950455454, 'translation_length': 8774, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
80
+ | 0.4418 | 20.0 | 2420 | 0.3407 | 0.5635 | {'bleu': 0.1651392945199903, 'precisions': [0.45348043676069155, 0.22924648786717752, 0.12087272727272727, 0.06511862695608278], 'brevity_penalty': 0.9763976470202772, 'length_ratio': 0.9766718506998445, 'translation_length': 8792, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
81
+ | 0.4411 | 21.0 | 2541 | 0.3380 | 0.5612 | {'bleu': 0.17032448446358872, 'precisions': [0.4554837246228876, 0.2328453214513049, 0.12492753623188406, 0.06908115358819585], 'brevity_penalty': 0.9792364011971344, 'length_ratio': 0.9794490113308154, 'translation_length': 8817, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
82
+ | 0.4368 | 22.0 | 2662 | 0.3403 | 0.5563 | {'bleu': 0.17429463351579735, 'precisions': [0.46019505556815604, 0.2389256619144603, 0.12896681640341978, 0.07074601844090528], 'brevity_penalty': 0.9793497875444289, 'length_ratio': 0.9795600977560542, 'translation_length': 8818, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
83
+ | 0.4322 | 23.0 | 2783 | 0.3307 | 0.5598 | {'bleu': 0.18466486831726667, 'precisions': [0.4570876435148346, 0.24365028717294193, 0.1379360465116279, 0.08309503784693019], 'brevity_penalty': 0.9769660283987757, 'length_ratio': 0.9772272828260387, 'translation_length': 8797, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
84
+ | 0.4263 | 24.0 | 2904 | 0.3398 | 0.5549 | {'bleu': 0.1797281293297898, 'precisions': [0.46188799272975123, 0.2423160311184798, 0.13404008132442638, 0.07613445378151261], 'brevity_penalty': 0.9776476696891355, 'length_ratio': 0.9778938013774717, 'translation_length': 8803, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
85
+ | 0.4102 | 25.0 | 3025 | 0.3253 | 0.5472 | {'bleu': 0.19095303691786358, 'precisions': [0.469932931681255, 0.25488194001276326, 0.14375, 0.08476286579212916], 'brevity_penalty': 0.9769660283987757, 'length_ratio': 0.9772272828260387, 'translation_length': 8797, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
86
+ | 0.4236 | 26.0 | 3146 | 0.3274 | 0.5474 | {'bleu': 0.18409612160683292, 'precisions': [0.4694085656016315, 0.2483468972533062, 0.13677811550151975, 0.07801774652603381], 'brevity_penalty': 0.9802564252131077, 'length_ratio': 0.9804487891579649, 'translation_length': 8826, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
87
+ | 0.4177 | 27.0 | 3267 | 0.3255 | 0.5419 | {'bleu': 0.19152955171945296, 'precisions': [0.47450135992747056, 0.25489697278046297, 0.14405675401766324, 0.08372404554588078], 'brevity_penalty': 0.980029841295489, 'length_ratio': 0.9802266163074872, 'translation_length': 8824, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
88
+ | 0.4051 | 28.0 | 3388 | 0.3218 | 0.5380 | {'bleu': 0.20391771010111173, 'precisions': [0.47922814982973894, 0.2658002038735984, 0.1550848687073843, 0.09550184625713326], 'brevity_penalty': 0.9784423441477751, 'length_ratio': 0.9786714063541435, 'translation_length': 8810, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
89
+ | 0.3993 | 29.0 | 3509 | 0.3225 | 0.5364 | {'bleu': 0.1991760083321937, 'precisions': [0.4802765812740875, 0.26145038167938933, 0.15090514120202753, 0.09011725293132328], 'brevity_penalty': 0.9798032070519724, 'length_ratio': 0.9800044434570095, 'translation_length': 8822, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
90
+ | 0.3942 | 30.0 | 3630 | 0.3230 | 0.5335 | {'bleu': 0.20119532062721326, 'precisions': [0.48279375141498754, 0.2630843495934959, 0.15223362729507012, 0.09144098963557339], 'brevity_penalty': 0.981162257838828, 'length_ratio': 0.9813374805598756, 'translation_length': 8834, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
91
+ | 0.3846 | 31.0 | 3751 | 0.3318 | 0.5332 | {'bleu': 0.20626502760570276, 'precisions': [0.4828561729093584, 0.26526984126984127, 0.15708092485549133, 0.09694133377904061], 'brevity_penalty': 0.9815017376632986, 'length_ratio': 0.981670739835592, 'translation_length': 8837, 'reference_length': 9002} | {'rouge1': 0.0, 'rouge2': 0.0, 'rougeL': 0.0, 'rougeLsum': 0.0} |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
92
 
93
 
94
  ### Framework versions
adapter.ar.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:751decbe8dd659e232349972cfcc03b15cc3cb30b52076b4176f93b8de84a212
3
+ size 8936896
config.json CHANGED
@@ -77,7 +77,7 @@
77
  "num_hidden_layers": 48,
78
  "num_negatives": 100,
79
  "output_hidden_size": 1280,
80
- "pad_token_id": 58,
81
  "proj_codevector_dim": 1024,
82
  "tdnn_dilation": [
83
  1,
@@ -103,6 +103,6 @@
103
  "torch_dtype": "float32",
104
  "transformers_version": "4.49.0",
105
  "use_weighted_layer_sum": false,
106
- "vocab_size": 61,
107
  "xvector_output_dim": 512
108
  }
 
77
  "num_hidden_layers": 48,
78
  "num_negatives": 100,
79
  "output_hidden_size": 1280,
80
+ "pad_token_id": 55,
81
  "proj_codevector_dim": 1024,
82
  "tdnn_dilation": [
83
  1,
 
103
  "torch_dtype": "float32",
104
  "transformers_version": "4.49.0",
105
  "use_weighted_layer_sum": false,
106
+ "vocab_size": 58,
107
  "xvector_output_dim": 512
108
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d9490b270d3f4e574b72922327fdeb644b3bbfeba48bb0bf1354a38fc66ab9f
3
- size 3859044644
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f480f95da2d14aacc99955561a1be43fa28819b1b11fff4e4779875d42a11cf3
3
+ size 3859029272
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b82ccef5fbe4c65e94fecef2515bbd6a601eff23e8c7d3f12403e1828ea7577
3
  size 5368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c4357cc770c91cd000a5f54167afc9f8befa84bb10ca226680d0b0ce2e4830
3
  size 5368