diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/args.json b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/args.json new file mode 100644 index 0000000000000000000000000000000000000000..2790b05e421ddd03751604425f5af45cae9b2e64 --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/args.json @@ -0,0 +1 @@ +{"hellaswag": true, "attention_kind": "selective", "log_dir": "proxy_model_sweep_2/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338", "resume_checkpoint": null, "resume_optimizer": false, "add_a_head": false, "add_head_to_start": true, "new_head_init": "normal", "n_heads": 2, "protect_bos_token": true, "prevent_from_masking_myself": true, "max_steps": 5000, "warmup_steps": 200, "group": "proxy_model_sweep_2", "use_wandb": true, "kill_self_after_run": false, "random_seed": 1338, "memory_penalty_epsilon": 0.1, "selection_head_linear_combo": "none", "selection_head_linear_combo_scale": 1.0, "protection_kind": "none", "leaky_relu_alpha": null, "leaky_relu_bias": null, "use_compile": true, "use_mini_model": false, "upload_to_hf": true, "seq_len": 256, "batch_size": 20, "total_batch_size": 5120, "protection_head_scaling_factor": 1.0, "protection_head_bias": 0.0, "n_sliced_masks": null, "n_latent_masks": null, "mask_layernorm": false, "residual_attention_masks": false, "compute_base_shapes": false, "base_shapes_savefile": null, "mup": true, "disable_selection": false, "mup_enable_coord_check_logging": false, "max_lr": 0.0002, "decay_lr": true, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "n_embd": 128} \ No newline at end of file diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/dataloader_02500.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/dataloader_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bc253f8fc6225637fb651d7b45bcde02b1c9ff0 --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/dataloader_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5f86eba64e08aa3145708d463ef689ecaee47ebe0a97035e6e0aeb59f377344 +size 964 diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/dataloader_04999.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/dataloader_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..0618c479f1dc6588bdd52311cf3417cbd843ddd9 --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/dataloader_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431842dc67f0d83e5eb85cf9c36fd024e295001fe78f3ba5deeae77865394feb +size 964 diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/log2.txt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/log2.txt new file mode 100644 index 0000000000000000000000000000000000000000..fde20f03d09d59f13c79d1d9e0189ab0a3af6cdb --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/log2.txt @@ -0,0 +1,5203 @@ +max_steps: 5000 +0 val loss 11.7668 +0 val perplexity 128904.1953 +0 train 11.771575 (lr=1.0000e-06) (hash(x)=22886834) +1 train 11.749569 (lr=2.0000e-06) (hash(x)=26375038) +2 train 11.783487 (lr=3.0000e-06) (hash(x)=30598777) +3 train 11.770488 (lr=4.0000e-06) (hash(x)=27234506) +4 train 11.762046 (lr=5.0000e-06) (hash(x)=27767880) +5 train 11.655691 (lr=6.0000e-06) (hash(x)=23702020) +6 train 11.748717 (lr=7.0000e-06) (hash(x)=31986844) +7 train 11.675021 (lr=8.0000e-06) (hash(x)=20782690) +8 train 11.705728 (lr=9.0000e-06) (hash(x)=25201599) +9 train 11.663925 (lr=1.0000e-05) (hash(x)=23094976) +10 train 11.650023 (lr=1.1000e-05) (hash(x)=23841096) +11 train 11.645606 (lr=1.2000e-05) (hash(x)=26532095) +12 train 11.632196 (lr=1.3000e-05) (hash(x)=24432298) +13 train 11.585650 (lr=1.4000e-05) (hash(x)=27151649) +14 train 11.536504 (lr=1.5000e-05) (hash(x)=24596846) +15 train 11.498213 (lr=1.6000e-05) (hash(x)=23890908) +16 train 11.443544 (lr=1.7000e-05) (hash(x)=28913955) +17 train 11.436437 (lr=1.8000e-05) (hash(x)=25588236) +18 train 11.394956 (lr=1.9000e-05) (hash(x)=23770034) +19 train 11.327438 (lr=2.0000e-05) (hash(x)=24011372) +20 train 11.234990 (lr=2.1000e-05) (hash(x)=25441898) +21 train 11.290613 (lr=2.2000e-05) (hash(x)=28375581) +22 train 11.239290 (lr=2.3000e-05) (hash(x)=24046679) +23 train 11.230716 (lr=2.4000e-05) (hash(x)=24611628) +24 train 11.126025 (lr=2.5000e-05) (hash(x)=26169030) +25 train 11.136379 (lr=2.6000e-05) (hash(x)=30298407) +26 train 11.022460 (lr=2.7000e-05) (hash(x)=23711112) +27 train 10.912953 (lr=2.8000e-05) (hash(x)=19245352) +28 train 10.856606 (lr=2.9000e-05) (hash(x)=21529136) +29 train 10.956057 (lr=3.0000e-05) (hash(x)=28936608) +30 train 10.675776 (lr=3.1000e-05) (hash(x)=24339013) +31 train 10.528908 (lr=3.2000e-05) (hash(x)=25767553) +32 train 10.587272 (lr=3.3000e-05) (hash(x)=26439905) +33 train 10.734705 (lr=3.4000e-05) (hash(x)=31093473) +34 train 10.481090 (lr=3.5000e-05) (hash(x)=25450374) +35 train 10.451982 (lr=3.6000e-05) (hash(x)=24809873) +36 train 10.602655 (lr=3.7000e-05) (hash(x)=23253252) +37 train 10.563127 (lr=3.8000e-05) (hash(x)=27852919) +38 train 10.509063 (lr=3.9000e-05) (hash(x)=23327497) +39 train 10.399692 (lr=4.0000e-05) (hash(x)=22512166) +40 train 10.556300 (lr=4.1000e-05) (hash(x)=22859419) +41 train 10.421841 (lr=4.2000e-05) (hash(x)=27620338) +42 train 10.428044 (lr=4.3000e-05) (hash(x)=26397837) +43 train 10.424989 (lr=4.4000e-05) (hash(x)=28092148) +44 train 10.275783 (lr=4.5000e-05) (hash(x)=24662703) +45 train 10.418662 (lr=4.6000e-05) (hash(x)=27938767) +46 train 10.458705 (lr=4.7000e-05) (hash(x)=26037988) +47 train 10.343122 (lr=4.8000e-05) (hash(x)=24732833) +48 train 10.341268 (lr=4.9000e-05) (hash(x)=25259526) +49 train 10.315691 (lr=5.0000e-05) (hash(x)=23200230) +50 val loss 10.2616 +50 val perplexity 28613.0898 +50 train 10.220908 (lr=5.1000e-05) (hash(x)=26721357) +51 train 10.216792 (lr=5.2000e-05) (hash(x)=22694718) +52 train 10.197001 (lr=5.3000e-05) (hash(x)=28066766) +53 train 10.188023 (lr=5.4000e-05) (hash(x)=23125151) +54 train 10.277395 (lr=5.5000e-05) (hash(x)=27193725) +55 train 10.093409 (lr=5.6000e-05) (hash(x)=25129410) +56 train 10.140718 (lr=5.7000e-05) (hash(x)=24263988) +57 train 10.060890 (lr=5.8000e-05) (hash(x)=23059154) +58 train 10.169934 (lr=5.9000e-05) (hash(x)=26063864) +59 train 10.298917 (lr=6.0000e-05) (hash(x)=27858570) +60 train 10.145186 (lr=6.1000e-05) (hash(x)=23874620) +61 train 10.048021 (lr=6.2000e-05) (hash(x)=22402617) +62 train 10.078882 (lr=6.3000e-05) (hash(x)=23600822) +63 train 9.851382 (lr=6.4000e-05) (hash(x)=26582391) +64 train 9.890672 (lr=6.5000e-05) (hash(x)=23225283) +65 train 10.101229 (lr=6.6000e-05) (hash(x)=26075451) +66 train 9.948666 (lr=6.7000e-05) (hash(x)=24723419) +67 train 9.935628 (lr=6.8000e-05) (hash(x)=27279806) +68 train 9.797580 (lr=6.9000e-05) (hash(x)=25870391) +69 train 9.953123 (lr=7.0000e-05) (hash(x)=26188136) +70 train 9.925657 (lr=7.1000e-05) (hash(x)=30373443) +71 train 9.916730 (lr=7.2000e-05) (hash(x)=26472336) +72 train 9.753589 (lr=7.3000e-05) (hash(x)=26651572) +73 train 9.774107 (lr=7.4000e-05) (hash(x)=26376212) +74 train 9.765795 (lr=7.5000e-05) (hash(x)=26733350) +75 train 9.870773 (lr=7.6000e-05) (hash(x)=28301589) +76 train 9.781246 (lr=7.7000e-05) (hash(x)=27599559) +77 train 9.675636 (lr=7.8000e-05) (hash(x)=28035221) +78 train 9.713618 (lr=7.9000e-05) (hash(x)=25016783) +79 train 9.768145 (lr=8.0000e-05) (hash(x)=27654289) +80 train 9.738141 (lr=8.1000e-05) (hash(x)=24597558) +81 train 9.620611 (lr=8.2000e-05) (hash(x)=21560904) +82 train 9.513152 (lr=8.3000e-05) (hash(x)=21983837) +83 train 9.596865 (lr=8.4000e-05) (hash(x)=24995715) +84 train 9.711629 (lr=8.5000e-05) (hash(x)=29876413) +85 train 9.497687 (lr=8.6000e-05) (hash(x)=23792508) +86 train 9.402532 (lr=8.7000e-05) (hash(x)=25509120) +87 train 9.504023 (lr=8.8000e-05) (hash(x)=26559876) +88 train 9.518368 (lr=8.9000e-05) (hash(x)=23569647) +89 train 9.495510 (lr=9.0000e-05) (hash(x)=25758852) +90 train 9.354423 (lr=9.1000e-05) (hash(x)=25706298) +91 train 9.323924 (lr=9.2000e-05) (hash(x)=28364895) +92 train 9.297713 (lr=9.3000e-05) (hash(x)=25304663) +93 train 9.280094 (lr=9.4000e-05) (hash(x)=25269299) +94 train 9.470055 (lr=9.5000e-05) (hash(x)=25870566) +95 train 9.110240 (lr=9.6000e-05) (hash(x)=21770329) +96 train 9.417693 (lr=9.7000e-05) (hash(x)=27595900) +97 train 9.343434 (lr=9.8000e-05) (hash(x)=24785397) +98 train 9.078946 (lr=9.9000e-05) (hash(x)=21521480) +99 train 9.117221 (lr=1.0000e-04) (hash(x)=24628606) +100 val loss 9.1783 +100 val perplexity 9684.2402 +100 train 9.187901 (lr=1.0100e-04) (hash(x)=24670150) +101 train 9.165133 (lr=1.0200e-04) (hash(x)=23181910) +102 train 9.024367 (lr=1.0300e-04) (hash(x)=22714991) +103 train 9.095443 (lr=1.0400e-04) (hash(x)=22723459) +104 train 9.060447 (lr=1.0500e-04) (hash(x)=21524316) +105 train 9.021395 (lr=1.0600e-04) (hash(x)=25506632) +106 train 8.797079 (lr=1.0700e-04) (hash(x)=21675672) +107 train 8.850362 (lr=1.0800e-04) (hash(x)=22897919) +108 train 8.842906 (lr=1.0900e-04) (hash(x)=23321631) +109 train 8.894814 (lr=1.1000e-04) (hash(x)=26546719) +110 train 9.685050 (lr=1.1100e-04) (hash(x)=31962348) +111 train 8.939997 (lr=1.1200e-04) (hash(x)=30338342) +112 train 8.739920 (lr=1.1300e-04) (hash(x)=23724471) +113 train 8.854120 (lr=1.1400e-04) (hash(x)=29175888) +114 train 8.896634 (lr=1.1500e-04) (hash(x)=23256716) +115 train 8.826398 (lr=1.1600e-04) (hash(x)=27063280) +116 train 8.837104 (lr=1.1700e-04) (hash(x)=31057659) +117 train 8.963999 (lr=1.1800e-04) (hash(x)=32915097) +118 train 8.798224 (lr=1.1900e-04) (hash(x)=28842717) +119 train 8.588093 (lr=1.2000e-04) (hash(x)=25678059) +120 train 8.533955 (lr=1.2100e-04) (hash(x)=21593510) +121 train 8.366417 (lr=1.2200e-04) (hash(x)=20083773) +122 train 8.604654 (lr=1.2300e-04) (hash(x)=23002820) +123 train 8.415335 (lr=1.2400e-04) (hash(x)=21853028) +124 train 8.481009 (lr=1.2500e-04) (hash(x)=26985625) +125 train 8.413676 (lr=1.2600e-04) (hash(x)=21808483) +126 train 8.618134 (lr=1.2700e-04) (hash(x)=28873251) +127 train 8.447415 (lr=1.2800e-04) (hash(x)=26109335) +128 train 8.546885 (lr=1.2900e-04) (hash(x)=26334674) +129 train 8.492493 (lr=1.3000e-04) (hash(x)=24916754) +130 train 8.371627 (lr=1.3100e-04) (hash(x)=25449624) +131 train 8.424730 (lr=1.3200e-04) (hash(x)=25334848) +132 train 8.687352 (lr=1.3300e-04) (hash(x)=27484863) +133 train 8.231074 (lr=1.3400e-04) (hash(x)=24917705) +134 train 8.184694 (lr=1.3500e-04) (hash(x)=25143449) +135 train 8.186393 (lr=1.3600e-04) (hash(x)=25044885) +136 train 8.395933 (lr=1.3700e-04) (hash(x)=27821028) +137 train 8.386345 (lr=1.3800e-04) (hash(x)=28747022) +138 train 8.307564 (lr=1.3900e-04) (hash(x)=27182888) +139 train 8.093913 (lr=1.4000e-04) (hash(x)=23678349) +140 train 8.251424 (lr=1.4100e-04) (hash(x)=23593235) +141 train 8.433281 (lr=1.4200e-04) (hash(x)=28529813) +142 train 8.790956 (lr=1.4300e-04) (hash(x)=32074661) +143 train 8.289670 (lr=1.4400e-04) (hash(x)=28870690) +144 train 8.270183 (lr=1.4500e-04) (hash(x)=27307705) +145 train 8.142523 (lr=1.4600e-04) (hash(x)=25044834) +146 train 8.205136 (lr=1.4700e-04) (hash(x)=23712023) +147 train 8.582007 (lr=1.4800e-04) (hash(x)=32982615) +148 train 8.361385 (lr=1.4900e-04) (hash(x)=30113660) +149 train 7.903682 (lr=1.5000e-04) (hash(x)=20970960) +150 val loss 8.0567 +150 val perplexity 3154.9875 +150 train 8.028915 (lr=1.5100e-04) (hash(x)=23132684) +151 train 9.578074 (lr=1.5200e-04) (hash(x)=35279941) +152 train 8.821334 (lr=1.5300e-04) (hash(x)=31227444) +153 train 7.977191 (lr=1.5400e-04) (hash(x)=25529472) +154 train 8.055231 (lr=1.5500e-04) (hash(x)=24350409) +155 train 8.359627 (lr=1.5600e-04) (hash(x)=26400041) +156 train 8.070658 (lr=1.5700e-04) (hash(x)=25262621) +157 train 8.098633 (lr=1.5800e-04) (hash(x)=24656138) +158 train 8.282262 (lr=1.5900e-04) (hash(x)=26803414) +159 train 8.185042 (lr=1.6000e-04) (hash(x)=25015923) +160 train 7.928418 (lr=1.6100e-04) (hash(x)=23581172) +161 train 7.997267 (lr=1.6200e-04) (hash(x)=22924885) +162 train 7.975391 (lr=1.6300e-04) (hash(x)=23414296) +163 train 8.097053 (lr=1.6400e-04) (hash(x)=24853586) +164 train 8.143879 (lr=1.6500e-04) (hash(x)=25000130) +165 train 8.015790 (lr=1.6600e-04) (hash(x)=27004780) +166 train 7.975032 (lr=1.6700e-04) (hash(x)=26148573) +167 train 7.927322 (lr=1.6800e-04) (hash(x)=26740855) +168 train 7.604534 (lr=1.6900e-04) (hash(x)=20965419) +169 train 7.864275 (lr=1.7000e-04) (hash(x)=23950114) +170 train 7.801551 (lr=1.7100e-04) (hash(x)=24951982) +171 train 7.922438 (lr=1.7200e-04) (hash(x)=24584116) +172 train 7.911367 (lr=1.7300e-04) (hash(x)=24378759) +173 train 7.876874 (lr=1.7400e-04) (hash(x)=25718516) +174 train 8.030281 (lr=1.7500e-04) (hash(x)=28424396) +175 train 7.802613 (lr=1.7600e-04) (hash(x)=22262151) +176 train 8.008176 (lr=1.7700e-04) (hash(x)=26438412) +177 train 7.825824 (lr=1.7800e-04) (hash(x)=23025303) +178 train 7.811582 (lr=1.7900e-04) (hash(x)=24190770) +179 train 7.992679 (lr=1.8000e-04) (hash(x)=26627860) +180 train 7.792380 (lr=1.8100e-04) (hash(x)=23663439) +181 train 7.696089 (lr=1.8200e-04) (hash(x)=23700532) +182 train 7.767004 (lr=1.8300e-04) (hash(x)=23075676) +183 train 7.988178 (lr=1.8400e-04) (hash(x)=26621834) +184 train 8.029065 (lr=1.8500e-04) (hash(x)=29426269) +185 train 7.667892 (lr=1.8600e-04) (hash(x)=21821465) +186 train 7.916147 (lr=1.8700e-04) (hash(x)=26506130) +187 train 8.137744 (lr=1.8800e-04) (hash(x)=26930630) +188 train 7.652866 (lr=1.8900e-04) (hash(x)=22993793) +189 train 7.539168 (lr=1.9000e-04) (hash(x)=19557946) +190 train 7.881896 (lr=1.9100e-04) (hash(x)=23572891) +191 train 7.699520 (lr=1.9200e-04) (hash(x)=23234741) +192 train 7.768867 (lr=1.9300e-04) (hash(x)=25547951) +193 train 7.859448 (lr=1.9400e-04) (hash(x)=26713563) +194 train 7.894437 (lr=1.9500e-04) (hash(x)=25913622) +195 train 8.131106 (lr=1.9600e-04) (hash(x)=28102443) +196 train 7.788873 (lr=1.9700e-04) (hash(x)=23093351) +197 train 8.518240 (lr=1.9800e-04) (hash(x)=31689122) +198 train 8.386565 (lr=1.9900e-04) (hash(x)=32252517) +199 train 7.885911 (lr=2.0000e-04) (hash(x)=25470563) +200 val loss 7.8155 +200 val perplexity 2478.7041 +200 train 7.937332 (lr=2.0000e-04) (hash(x)=25597614) +201 train 7.936986 (lr=2.0000e-04) (hash(x)=23757479) +202 train 7.752808 (lr=2.0000e-04) (hash(x)=25140048) +203 train 7.988181 (lr=2.0000e-04) (hash(x)=28282861) +204 train 7.773126 (lr=2.0000e-04) (hash(x)=24754885) +205 train 7.984372 (lr=2.0000e-04) (hash(x)=26731964) +206 train 8.107638 (lr=2.0000e-04) (hash(x)=26660561) +207 train 7.655229 (lr=2.0000e-04) (hash(x)=21799102) +208 train 7.873468 (lr=2.0000e-04) (hash(x)=27025986) +209 train 7.704780 (lr=2.0000e-04) (hash(x)=24672077) +210 train 7.786009 (lr=2.0000e-04) (hash(x)=25322984) +211 train 7.664168 (lr=2.0000e-04) (hash(x)=23471769) +212 train 7.489067 (lr=2.0000e-04) (hash(x)=20766491) +213 train 7.981935 (lr=2.0000e-04) (hash(x)=24058931) +214 train 7.675731 (lr=2.0000e-04) (hash(x)=23872843) +215 train 7.703256 (lr=2.0000e-04) (hash(x)=23275479) +216 train 7.841854 (lr=2.0000e-04) (hash(x)=24914695) +217 train 7.693302 (lr=1.9999e-04) (hash(x)=24364396) +218 train 7.951123 (lr=1.9999e-04) (hash(x)=27986474) +219 train 7.979080 (lr=1.9999e-04) (hash(x)=24473581) +220 train 7.776287 (lr=1.9999e-04) (hash(x)=22974689) +221 train 7.850399 (lr=1.9999e-04) (hash(x)=23774644) +222 train 7.790394 (lr=1.9999e-04) (hash(x)=23245327) +223 train 7.606348 (lr=1.9999e-04) (hash(x)=22091862) +224 train 7.688361 (lr=1.9999e-04) (hash(x)=24362839) +225 train 7.837192 (lr=1.9999e-04) (hash(x)=25482303) +226 train 7.906391 (lr=1.9999e-04) (hash(x)=24911853) +227 train 7.895607 (lr=1.9999e-04) (hash(x)=26018202) +228 train 7.734973 (lr=1.9998e-04) (hash(x)=26124495) +229 train 7.849262 (lr=1.9998e-04) (hash(x)=24560096) +230 train 7.807765 (lr=1.9998e-04) (hash(x)=24695331) +231 train 7.547498 (lr=1.9998e-04) (hash(x)=17430373) +232 train 7.573497 (lr=1.9998e-04) (hash(x)=21813345) +233 train 7.221056 (lr=1.9998e-04) (hash(x)=20098681) +234 train 7.561543 (lr=1.9998e-04) (hash(x)=25095928) +235 train 7.674619 (lr=1.9998e-04) (hash(x)=24078083) +236 train 7.685706 (lr=1.9998e-04) (hash(x)=22901505) +237 train 7.906703 (lr=1.9997e-04) (hash(x)=26595592) +238 train 7.778410 (lr=1.9997e-04) (hash(x)=27663196) +239 train 7.549297 (lr=1.9997e-04) (hash(x)=22954861) +240 train 8.008821 (lr=1.9997e-04) (hash(x)=30159234) +241 train 7.910115 (lr=1.9997e-04) (hash(x)=29294271) +242 train 7.868607 (lr=1.9997e-04) (hash(x)=23728322) +243 train 7.920455 (lr=1.9996e-04) (hash(x)=28695016) +244 train 8.065787 (lr=1.9996e-04) (hash(x)=26702728) +245 train 7.875377 (lr=1.9996e-04) (hash(x)=27100115) +246 train 7.772190 (lr=1.9996e-04) (hash(x)=25082752) +247 train 8.117278 (lr=1.9996e-04) (hash(x)=26671799) +248 train 7.803123 (lr=1.9996e-04) (hash(x)=23718946) +249 train 8.025902 (lr=1.9995e-04) (hash(x)=28137394) +250 val loss 7.7873 +250 val perplexity 2409.7048 +250 train 8.043147 (lr=1.9995e-04) (hash(x)=23893495) +251 train 7.784383 (lr=1.9995e-04) (hash(x)=23166092) +252 train 7.837033 (lr=1.9995e-04) (hash(x)=25907665) +253 train 7.794666 (lr=1.9995e-04) (hash(x)=25885986) +254 train 7.804096 (lr=1.9994e-04) (hash(x)=25262712) +255 train 7.794916 (lr=1.9994e-04) (hash(x)=26924723) +256 train 7.948215 (lr=1.9994e-04) (hash(x)=28744736) +257 train 7.714418 (lr=1.9994e-04) (hash(x)=26140590) +258 train 7.924117 (lr=1.9994e-04) (hash(x)=25780449) +259 train 7.749880 (lr=1.9993e-04) (hash(x)=25138659) +260 train 8.086245 (lr=1.9993e-04) (hash(x)=27244046) +261 train 7.931664 (lr=1.9993e-04) (hash(x)=27224685) +262 train 8.238861 (lr=1.9993e-04) (hash(x)=28274477) +263 train 7.703838 (lr=1.9992e-04) (hash(x)=23557495) +264 train 7.814442 (lr=1.9992e-04) (hash(x)=24680596) +265 train 7.792367 (lr=1.9992e-04) (hash(x)=23928957) +266 train 7.763197 (lr=1.9992e-04) (hash(x)=23761390) +267 train 7.700505 (lr=1.9991e-04) (hash(x)=25288123) +268 train 7.977100 (lr=1.9991e-04) (hash(x)=28705502) +269 train 7.563018 (lr=1.9991e-04) (hash(x)=23246294) +270 train 7.663179 (lr=1.9991e-04) (hash(x)=28639079) +271 train 7.589955 (lr=1.9990e-04) (hash(x)=27804380) +272 train 7.753479 (lr=1.9990e-04) (hash(x)=24172235) +273 train 7.811822 (lr=1.9990e-04) (hash(x)=23089140) +274 train 8.013392 (lr=1.9989e-04) (hash(x)=27163701) +275 train 8.114638 (lr=1.9989e-04) (hash(x)=26993263) +276 train 7.853265 (lr=1.9989e-04) (hash(x)=28224233) +277 train 8.136869 (lr=1.9989e-04) (hash(x)=27397203) +278 train 8.072218 (lr=1.9988e-04) (hash(x)=27923882) +279 train 7.872284 (lr=1.9988e-04) (hash(x)=26654908) +280 train 7.851320 (lr=1.9988e-04) (hash(x)=24213147) +281 train 7.583749 (lr=1.9987e-04) (hash(x)=21965022) +282 train 7.753253 (lr=1.9987e-04) (hash(x)=25465685) +283 train 7.949507 (lr=1.9987e-04) (hash(x)=27347722) +284 train 7.980058 (lr=1.9986e-04) (hash(x)=26732050) +285 train 8.126079 (lr=1.9986e-04) (hash(x)=28314127) +286 train 7.619839 (lr=1.9986e-04) (hash(x)=21471186) +287 train 7.586215 (lr=1.9985e-04) (hash(x)=23627518) +288 train 7.570610 (lr=1.9985e-04) (hash(x)=20870353) +289 train 7.672429 (lr=1.9985e-04) (hash(x)=25024764) +290 train 7.500483 (lr=1.9984e-04) (hash(x)=20683822) +291 train 7.792840 (lr=1.9984e-04) (hash(x)=21768671) +292 train 7.807906 (lr=1.9984e-04) (hash(x)=25557309) +293 train 7.954138 (lr=1.9983e-04) (hash(x)=25076667) +294 train 7.607332 (lr=1.9983e-04) (hash(x)=23765822) +295 train 7.593652 (lr=1.9983e-04) (hash(x)=21889990) +296 train 7.814748 (lr=1.9982e-04) (hash(x)=26339893) +297 train 7.506679 (lr=1.9982e-04) (hash(x)=20932794) +298 train 7.653348 (lr=1.9981e-04) (hash(x)=21750070) +299 train 7.881866 (lr=1.9981e-04) (hash(x)=23665838) +300 val loss 7.7451 +300 val perplexity 2310.2820 +300 train 8.549685 (lr=1.9981e-04) (hash(x)=32888061) +301 train 8.339683 (lr=1.9980e-04) (hash(x)=30223582) +302 train 8.037990 (lr=1.9980e-04) (hash(x)=26908418) +303 train 7.420986 (lr=1.9980e-04) (hash(x)=22528001) +304 train 7.991797 (lr=1.9979e-04) (hash(x)=27452187) +305 train 7.810339 (lr=1.9979e-04) (hash(x)=25181641) +306 train 7.887389 (lr=1.9978e-04) (hash(x)=25546593) +307 train 7.843050 (lr=1.9978e-04) (hash(x)=22487328) +308 train 7.999632 (lr=1.9978e-04) (hash(x)=27804274) +309 train 8.058911 (lr=1.9977e-04) (hash(x)=26544630) +310 train 8.219489 (lr=1.9977e-04) (hash(x)=27738934) +311 train 8.015042 (lr=1.9976e-04) (hash(x)=29248942) +312 train 7.719405 (lr=1.9976e-04) (hash(x)=25103452) +313 train 7.972228 (lr=1.9975e-04) (hash(x)=25052066) +314 train 7.761133 (lr=1.9975e-04) (hash(x)=24481302) +315 train 7.690351 (lr=1.9975e-04) (hash(x)=23543273) +316 train 7.715511 (lr=1.9974e-04) (hash(x)=25608244) +317 train 7.922704 (lr=1.9974e-04) (hash(x)=27451288) +318 train 7.582157 (lr=1.9973e-04) (hash(x)=22806491) +319 train 7.787945 (lr=1.9973e-04) (hash(x)=25533417) +320 train 7.803335 (lr=1.9972e-04) (hash(x)=24557997) +321 train 7.836481 (lr=1.9972e-04) (hash(x)=24432899) +322 train 8.080955 (lr=1.9971e-04) (hash(x)=27583287) +323 train 8.023428 (lr=1.9971e-04) (hash(x)=25552036) +324 train 7.701482 (lr=1.9970e-04) (hash(x)=24201868) +325 train 7.992358 (lr=1.9970e-04) (hash(x)=28149782) +326 train 7.790254 (lr=1.9969e-04) (hash(x)=25529698) +327 train 7.450864 (lr=1.9969e-04) (hash(x)=20612533) +328 train 7.496365 (lr=1.9968e-04) (hash(x)=20699000) +329 train 7.431180 (lr=1.9968e-04) (hash(x)=19774173) +330 train 7.472606 (lr=1.9967e-04) (hash(x)=21681646) +331 train 7.333058 (lr=1.9967e-04) (hash(x)=20216795) +332 train 8.078488 (lr=1.9966e-04) (hash(x)=27697998) +333 train 7.808600 (lr=1.9966e-04) (hash(x)=25896435) +334 train 7.711981 (lr=1.9965e-04) (hash(x)=21585310) +335 train 7.760551 (lr=1.9965e-04) (hash(x)=24677740) +336 train 7.609490 (lr=1.9964e-04) (hash(x)=22027900) +337 train 7.623082 (lr=1.9964e-04) (hash(x)=21835643) +338 train 7.520436 (lr=1.9963e-04) (hash(x)=20558462) +339 train 7.418970 (lr=1.9963e-04) (hash(x)=16722715) +340 train 7.603919 (lr=1.9962e-04) (hash(x)=20972655) +341 train 8.063443 (lr=1.9962e-04) (hash(x)=26303975) +342 train 7.810741 (lr=1.9961e-04) (hash(x)=22938170) +343 train 7.881382 (lr=1.9961e-04) (hash(x)=25347203) +344 train 7.803060 (lr=1.9960e-04) (hash(x)=27398686) +345 train 7.789327 (lr=1.9960e-04) (hash(x)=25973417) +346 train 7.800903 (lr=1.9959e-04) (hash(x)=26918389) +347 train 7.759146 (lr=1.9958e-04) (hash(x)=24272489) +348 train 7.820366 (lr=1.9958e-04) (hash(x)=25593714) +349 train 7.868445 (lr=1.9957e-04) (hash(x)=29260846) +350 val loss 7.7859 +350 val perplexity 2406.5173 +350 train 7.939607 (lr=1.9957e-04) (hash(x)=27951602) +351 train 8.038503 (lr=1.9956e-04) (hash(x)=28922363) +352 train 7.911312 (lr=1.9956e-04) (hash(x)=27210734) +353 train 7.942363 (lr=1.9955e-04) (hash(x)=26322572) +354 train 7.819276 (lr=1.9954e-04) (hash(x)=27084665) +355 train 7.725905 (lr=1.9954e-04) (hash(x)=25510798) +356 train 7.843944 (lr=1.9953e-04) (hash(x)=24970921) +357 train 7.856723 (lr=1.9953e-04) (hash(x)=24138948) +358 train 7.744389 (lr=1.9952e-04) (hash(x)=24790211) +359 train 7.842651 (lr=1.9951e-04) (hash(x)=25631397) +360 train 7.718969 (lr=1.9951e-04) (hash(x)=23226625) +361 train 7.801975 (lr=1.9950e-04) (hash(x)=24001903) +362 train 7.726758 (lr=1.9949e-04) (hash(x)=24587948) +363 train 7.459872 (lr=1.9949e-04) (hash(x)=21333676) +364 train 7.386127 (lr=1.9948e-04) (hash(x)=23673779) +365 train 8.765097 (lr=1.9948e-04) (hash(x)=30770484) +366 train 8.011015 (lr=1.9947e-04) (hash(x)=26564899) +367 train 8.024920 (lr=1.9946e-04) (hash(x)=26237983) +368 train 7.802367 (lr=1.9946e-04) (hash(x)=23764356) +369 train 8.068944 (lr=1.9945e-04) (hash(x)=26205744) +370 train 7.716957 (lr=1.9944e-04) (hash(x)=19208770) +371 train 7.943411 (lr=1.9944e-04) (hash(x)=25976502) +372 train 7.765667 (lr=1.9943e-04) (hash(x)=23983933) +373 train 7.722264 (lr=1.9942e-04) (hash(x)=24080636) +374 train 7.824669 (lr=1.9942e-04) (hash(x)=24404047) +375 train 7.767568 (lr=1.9941e-04) (hash(x)=24742645) +376 train 7.847772 (lr=1.9940e-04) (hash(x)=24159600) +377 train 8.053142 (lr=1.9940e-04) (hash(x)=28677257) +378 train 7.798433 (lr=1.9939e-04) (hash(x)=25604111) +379 train 7.735391 (lr=1.9938e-04) (hash(x)=27086333) +380 train 7.727715 (lr=1.9938e-04) (hash(x)=25188207) +381 train 7.934860 (lr=1.9937e-04) (hash(x)=27855233) +382 train 7.508335 (lr=1.9936e-04) (hash(x)=19470039) +383 train 7.829261 (lr=1.9936e-04) (hash(x)=26157660) +384 train 7.758698 (lr=1.9935e-04) (hash(x)=25291570) +385 train 7.746210 (lr=1.9934e-04) (hash(x)=25046062) +386 train 8.022800 (lr=1.9933e-04) (hash(x)=27020337) +387 train 7.649140 (lr=1.9933e-04) (hash(x)=23616370) +388 train 7.309493 (lr=1.9932e-04) (hash(x)=19113218) +389 train 7.721472 (lr=1.9931e-04) (hash(x)=24302232) +390 train 7.731041 (lr=1.9931e-04) (hash(x)=22188949) +391 train 7.547197 (lr=1.9930e-04) (hash(x)=22582169) +392 train 7.732793 (lr=1.9929e-04) (hash(x)=24700570) +393 train 7.612782 (lr=1.9928e-04) (hash(x)=22773833) +394 train 7.476511 (lr=1.9928e-04) (hash(x)=21875928) +395 train 7.756046 (lr=1.9927e-04) (hash(x)=26233189) +396 train 7.613618 (lr=1.9926e-04) (hash(x)=24321467) +397 train 7.892681 (lr=1.9925e-04) (hash(x)=26431507) +398 train 7.981488 (lr=1.9925e-04) (hash(x)=28690877) +399 train 7.893730 (lr=1.9924e-04) (hash(x)=26431960) +400 val loss 7.7763 +400 val perplexity 2383.5430 +400 train 7.743123 (lr=1.9923e-04) (hash(x)=24580300) +401 train 7.746867 (lr=1.9922e-04) (hash(x)=25112360) +402 train 7.835190 (lr=1.9921e-04) (hash(x)=27597243) +403 train 8.325218 (lr=1.9921e-04) (hash(x)=30707498) +404 train 7.994939 (lr=1.9920e-04) (hash(x)=28485465) +405 train 7.630550 (lr=1.9919e-04) (hash(x)=22586447) +406 train 7.779144 (lr=1.9918e-04) (hash(x)=23175270) +407 train 7.870225 (lr=1.9918e-04) (hash(x)=25716176) +408 train 7.955653 (lr=1.9917e-04) (hash(x)=26861373) +409 train 8.034328 (lr=1.9916e-04) (hash(x)=25118971) +410 train 7.530042 (lr=1.9915e-04) (hash(x)=19829066) +411 train 7.702719 (lr=1.9914e-04) (hash(x)=26256420) +412 train 7.960090 (lr=1.9914e-04) (hash(x)=27796153) +413 train 7.688210 (lr=1.9913e-04) (hash(x)=22633318) +414 train 7.719736 (lr=1.9912e-04) (hash(x)=22589383) +415 train 8.093697 (lr=1.9911e-04) (hash(x)=28019788) +416 train 8.025054 (lr=1.9910e-04) (hash(x)=28970440) +417 train 7.699556 (lr=1.9909e-04) (hash(x)=27396089) +418 train 7.686037 (lr=1.9909e-04) (hash(x)=21183513) +419 train 7.719329 (lr=1.9908e-04) (hash(x)=23510110) +420 train 7.923060 (lr=1.9907e-04) (hash(x)=28833467) +421 train 7.801155 (lr=1.9906e-04) (hash(x)=23646926) +422 train 7.751253 (lr=1.9905e-04) (hash(x)=24697272) +423 train 7.543594 (lr=1.9904e-04) (hash(x)=20382963) +424 train 7.534091 (lr=1.9903e-04) (hash(x)=23467595) +425 train 7.677396 (lr=1.9903e-04) (hash(x)=24304768) +426 train 7.641410 (lr=1.9902e-04) (hash(x)=21392328) +427 train 7.656342 (lr=1.9901e-04) (hash(x)=25339466) +428 train 7.591760 (lr=1.9900e-04) (hash(x)=22092542) +429 train 7.690637 (lr=1.9899e-04) (hash(x)=22088696) +430 train 7.600308 (lr=1.9898e-04) (hash(x)=22184471) +431 train 7.721800 (lr=1.9897e-04) (hash(x)=24489647) +432 train 7.756096 (lr=1.9896e-04) (hash(x)=26794132) +433 train 7.553221 (lr=1.9896e-04) (hash(x)=22940357) +434 train 7.721350 (lr=1.9895e-04) (hash(x)=23719522) +435 train 7.561054 (lr=1.9894e-04) (hash(x)=22927699) +436 train 7.759799 (lr=1.9893e-04) (hash(x)=26068576) +437 train 7.872817 (lr=1.9892e-04) (hash(x)=27631132) +438 train 7.735948 (lr=1.9891e-04) (hash(x)=26739991) +439 train 7.843007 (lr=1.9890e-04) (hash(x)=25128502) +440 train 7.858248 (lr=1.9889e-04) (hash(x)=25657260) +441 train 7.607169 (lr=1.9888e-04) (hash(x)=23576982) +442 train 7.908042 (lr=1.9887e-04) (hash(x)=27117886) +443 train 7.842915 (lr=1.9886e-04) (hash(x)=25808969) +444 train 7.736764 (lr=1.9885e-04) (hash(x)=24738238) +445 train 7.706159 (lr=1.9885e-04) (hash(x)=23429962) +446 train 7.891702 (lr=1.9884e-04) (hash(x)=25075165) +447 train 7.738043 (lr=1.9883e-04) (hash(x)=25231390) +448 train 7.568040 (lr=1.9882e-04) (hash(x)=22055054) +449 train 7.804100 (lr=1.9881e-04) (hash(x)=25395441) +450 val loss 7.7889 +450 val perplexity 2413.5676 +450 train 7.815767 (lr=1.9880e-04) (hash(x)=25863209) +451 train 7.515046 (lr=1.9879e-04) (hash(x)=21154388) +452 train 7.504448 (lr=1.9878e-04) (hash(x)=21600876) +453 train 7.647257 (lr=1.9877e-04) (hash(x)=24278611) +454 train 7.508924 (lr=1.9876e-04) (hash(x)=23221720) +455 train 7.679599 (lr=1.9875e-04) (hash(x)=22708977) +456 train 8.241851 (lr=1.9874e-04) (hash(x)=23637758) +457 train 7.963562 (lr=1.9873e-04) (hash(x)=28228490) +458 train 7.984622 (lr=1.9872e-04) (hash(x)=28638071) +459 train 7.863575 (lr=1.9871e-04) (hash(x)=27258353) +460 train 7.885516 (lr=1.9870e-04) (hash(x)=26604728) +461 train 7.732118 (lr=1.9869e-04) (hash(x)=23252199) +462 train 7.817242 (lr=1.9868e-04) (hash(x)=26441427) +463 train 7.564949 (lr=1.9867e-04) (hash(x)=24364920) +464 train 7.722456 (lr=1.9866e-04) (hash(x)=25623792) +465 train 7.615758 (lr=1.9865e-04) (hash(x)=23283905) +466 train 8.029738 (lr=1.9864e-04) (hash(x)=26025267) +467 train 7.808649 (lr=1.9863e-04) (hash(x)=27243972) +468 train 8.175218 (lr=1.9862e-04) (hash(x)=30449945) +469 train 7.881450 (lr=1.9861e-04) (hash(x)=28113043) +470 train 7.726092 (lr=1.9860e-04) (hash(x)=25182521) +471 train 7.742975 (lr=1.9859e-04) (hash(x)=24932925) +472 train 7.525945 (lr=1.9858e-04) (hash(x)=20353098) +473 train 7.433614 (lr=1.9857e-04) (hash(x)=19001259) +474 train 8.037007 (lr=1.9856e-04) (hash(x)=27585685) +475 train 7.768137 (lr=1.9855e-04) (hash(x)=26371091) +476 train 7.640594 (lr=1.9854e-04) (hash(x)=24891798) +477 train 7.719480 (lr=1.9852e-04) (hash(x)=24258817) +478 train 7.799266 (lr=1.9851e-04) (hash(x)=24330263) +479 train 7.907599 (lr=1.9850e-04) (hash(x)=26913684) +480 train 7.904230 (lr=1.9849e-04) (hash(x)=26338455) +481 train 8.123240 (lr=1.9848e-04) (hash(x)=27753043) +482 train 7.899156 (lr=1.9847e-04) (hash(x)=26123289) +483 train 7.961040 (lr=1.9846e-04) (hash(x)=29239611) +484 train 7.876962 (lr=1.9845e-04) (hash(x)=26553003) +485 train 7.798313 (lr=1.9844e-04) (hash(x)=22984557) +486 train 7.318967 (lr=1.9843e-04) (hash(x)=16947491) +487 train 7.367414 (lr=1.9842e-04) (hash(x)=18017792) +488 train 7.488843 (lr=1.9841e-04) (hash(x)=19918608) +489 train 7.966363 (lr=1.9839e-04) (hash(x)=23374526) +490 train 7.795452 (lr=1.9838e-04) (hash(x)=25009505) +491 train 7.791440 (lr=1.9837e-04) (hash(x)=27574089) +492 train 7.918322 (lr=1.9836e-04) (hash(x)=24122664) +493 train 7.764580 (lr=1.9835e-04) (hash(x)=26154906) +494 train 7.691667 (lr=1.9834e-04) (hash(x)=25192767) +495 train 7.815776 (lr=1.9833e-04) (hash(x)=28613882) +496 train 7.788770 (lr=1.9832e-04) (hash(x)=23547219) +497 train 7.769513 (lr=1.9830e-04) (hash(x)=25272182) +498 train 7.631283 (lr=1.9829e-04) (hash(x)=24992761) +499 train 7.884870 (lr=1.9828e-04) (hash(x)=26981914) +500 val loss 7.7525 +500 val perplexity 2327.3794 +500 train 7.678533 (lr=1.9827e-04) (hash(x)=22051933) +501 train 7.846703 (lr=1.9826e-04) (hash(x)=24232348) +502 train 7.808000 (lr=1.9825e-04) (hash(x)=23158331) +503 train 7.627761 (lr=1.9824e-04) (hash(x)=22652243) +504 train 7.682685 (lr=1.9822e-04) (hash(x)=23805602) +505 train 8.012827 (lr=1.9821e-04) (hash(x)=25411991) +506 train 7.341363 (lr=1.9820e-04) (hash(x)=18827215) +507 train 7.079272 (lr=1.9819e-04) (hash(x)=15446025) +508 train 7.399449 (lr=1.9818e-04) (hash(x)=20516263) +509 train 7.823252 (lr=1.9817e-04) (hash(x)=27846176) +510 train 7.517776 (lr=1.9815e-04) (hash(x)=23342449) +511 train 7.800474 (lr=1.9814e-04) (hash(x)=27194521) +512 train 7.609797 (lr=1.9813e-04) (hash(x)=23008284) +513 train 8.055231 (lr=1.9812e-04) (hash(x)=29430001) +514 train 7.413117 (lr=1.9811e-04) (hash(x)=22579319) +515 train 7.442401 (lr=1.9809e-04) (hash(x)=25264518) +516 train 7.789366 (lr=1.9808e-04) (hash(x)=25359075) +517 train 7.768211 (lr=1.9807e-04) (hash(x)=25568956) +518 train 8.056121 (lr=1.9806e-04) (hash(x)=32004108) +519 train 7.719841 (lr=1.9805e-04) (hash(x)=24936836) +520 train 7.861398 (lr=1.9803e-04) (hash(x)=27263338) +521 train 7.898507 (lr=1.9802e-04) (hash(x)=27452099) +522 train 7.776648 (lr=1.9801e-04) (hash(x)=25965406) +523 train 7.996295 (lr=1.9800e-04) (hash(x)=28197282) +524 train 7.663554 (lr=1.9798e-04) (hash(x)=22466209) +525 train 7.708882 (lr=1.9797e-04) (hash(x)=22931889) +526 train 7.834468 (lr=1.9796e-04) (hash(x)=26903920) +527 train 7.749457 (lr=1.9795e-04) (hash(x)=24765578) +528 train 7.837804 (lr=1.9793e-04) (hash(x)=27811359) +529 train 7.633492 (lr=1.9792e-04) (hash(x)=25078649) +530 train 7.821426 (lr=1.9791e-04) (hash(x)=25572416) +531 train 7.898537 (lr=1.9790e-04) (hash(x)=27448185) +532 train 7.967413 (lr=1.9788e-04) (hash(x)=25923719) +533 train 7.778568 (lr=1.9787e-04) (hash(x)=24804856) +534 train 7.928314 (lr=1.9786e-04) (hash(x)=23207829) +535 train 7.811592 (lr=1.9785e-04) (hash(x)=23107416) +536 train 7.624629 (lr=1.9783e-04) (hash(x)=26739531) +537 train 7.603721 (lr=1.9782e-04) (hash(x)=24960796) +538 train 7.761052 (lr=1.9781e-04) (hash(x)=24667802) +539 train 7.843249 (lr=1.9779e-04) (hash(x)=26755138) +540 train 7.744049 (lr=1.9778e-04) (hash(x)=25537132) +541 train 7.610271 (lr=1.9777e-04) (hash(x)=24542526) +542 train 7.422276 (lr=1.9775e-04) (hash(x)=21296355) +543 train 7.994564 (lr=1.9774e-04) (hash(x)=29314255) +544 train 7.719131 (lr=1.9773e-04) (hash(x)=26001799) +545 train 7.778956 (lr=1.9772e-04) (hash(x)=27347755) +546 train 7.768811 (lr=1.9770e-04) (hash(x)=25107798) +547 train 7.585405 (lr=1.9769e-04) (hash(x)=22112669) +548 train 7.605032 (lr=1.9768e-04) (hash(x)=21897967) +549 train 7.732882 (lr=1.9766e-04) (hash(x)=25161929) +550 val loss 7.7866 +550 val perplexity 2408.1208 +550 train 7.657370 (lr=1.9765e-04) (hash(x)=27465106) +551 train 7.779373 (lr=1.9764e-04) (hash(x)=24013079) +552 train 7.727408 (lr=1.9762e-04) (hash(x)=23142015) +553 train 7.840704 (lr=1.9761e-04) (hash(x)=26768629) +554 train 7.821641 (lr=1.9760e-04) (hash(x)=26393383) +555 train 7.609509 (lr=1.9758e-04) (hash(x)=22537194) +556 train 7.873086 (lr=1.9757e-04) (hash(x)=24046036) +557 train 7.788322 (lr=1.9755e-04) (hash(x)=24974360) +558 train 8.030382 (lr=1.9754e-04) (hash(x)=28379928) +559 train 7.760377 (lr=1.9753e-04) (hash(x)=25322001) +560 train 7.848627 (lr=1.9751e-04) (hash(x)=26622031) +561 train 7.483489 (lr=1.9750e-04) (hash(x)=20562247) +562 train 7.881948 (lr=1.9749e-04) (hash(x)=27381885) +563 train 8.046615 (lr=1.9747e-04) (hash(x)=27028126) +564 train 7.868500 (lr=1.9746e-04) (hash(x)=28882928) +565 train 7.762764 (lr=1.9744e-04) (hash(x)=25666355) +566 train 7.892996 (lr=1.9743e-04) (hash(x)=24330810) +567 train 7.804665 (lr=1.9742e-04) (hash(x)=26690440) +568 train 7.653615 (lr=1.9740e-04) (hash(x)=22923592) +569 train 7.807591 (lr=1.9739e-04) (hash(x)=27348418) +570 train 7.867024 (lr=1.9737e-04) (hash(x)=28849848) +571 train 7.884728 (lr=1.9736e-04) (hash(x)=26967331) +572 train 7.698482 (lr=1.9735e-04) (hash(x)=22831467) +573 train 7.743096 (lr=1.9733e-04) (hash(x)=24765121) +574 train 7.715751 (lr=1.9732e-04) (hash(x)=24331857) +575 train 7.559145 (lr=1.9730e-04) (hash(x)=22598512) +576 train 7.722701 (lr=1.9729e-04) (hash(x)=25149353) +577 train 7.570291 (lr=1.9727e-04) (hash(x)=23725598) +578 train 7.807045 (lr=1.9726e-04) (hash(x)=26449557) +579 train 7.871687 (lr=1.9725e-04) (hash(x)=24697985) +580 train 7.842152 (lr=1.9723e-04) (hash(x)=26923059) +581 train 7.662653 (lr=1.9722e-04) (hash(x)=25201962) +582 train 7.293463 (lr=1.9720e-04) (hash(x)=20931520) +583 train 7.363842 (lr=1.9719e-04) (hash(x)=18473911) +584 train 7.487541 (lr=1.9717e-04) (hash(x)=21306267) +585 train 7.794487 (lr=1.9716e-04) (hash(x)=25982840) +586 train 7.679922 (lr=1.9714e-04) (hash(x)=25364874) +587 train 7.602844 (lr=1.9713e-04) (hash(x)=23172124) +588 train 7.865535 (lr=1.9711e-04) (hash(x)=27876897) +589 train 8.454387 (lr=1.9710e-04) (hash(x)=34646114) +590 train 8.779843 (lr=1.9708e-04) (hash(x)=35153576) +591 train 7.639150 (lr=1.9707e-04) (hash(x)=22322442) +592 train 7.922729 (lr=1.9705e-04) (hash(x)=27907331) +593 train 7.808531 (lr=1.9704e-04) (hash(x)=26211794) +594 train 8.019201 (lr=1.9702e-04) (hash(x)=29291512) +595 train 8.244912 (lr=1.9701e-04) (hash(x)=29659121) +596 train 8.084265 (lr=1.9699e-04) (hash(x)=29674399) +597 train 7.728960 (lr=1.9698e-04) (hash(x)=23538306) +598 train 7.811261 (lr=1.9696e-04) (hash(x)=21991524) +599 train 7.744179 (lr=1.9695e-04) (hash(x)=26324153) +600 val loss 7.7119 +600 val perplexity 2234.7634 +600 train 7.725095 (lr=1.9693e-04) (hash(x)=23712082) +601 train 7.754073 (lr=1.9692e-04) (hash(x)=24910403) +602 train 7.713945 (lr=1.9690e-04) (hash(x)=26737205) +603 train 7.867311 (lr=1.9689e-04) (hash(x)=26939970) +604 train 7.744615 (lr=1.9687e-04) (hash(x)=27651943) +605 train 8.063166 (lr=1.9686e-04) (hash(x)=27515446) +606 train 7.952283 (lr=1.9684e-04) (hash(x)=26753129) +607 train 7.611319 (lr=1.9683e-04) (hash(x)=23446058) +608 train 7.940535 (lr=1.9681e-04) (hash(x)=27587849) +609 train 7.805387 (lr=1.9679e-04) (hash(x)=25308253) +610 train 7.801201 (lr=1.9678e-04) (hash(x)=26615098) +611 train 7.837065 (lr=1.9676e-04) (hash(x)=29981801) +612 train 7.922391 (lr=1.9675e-04) (hash(x)=29592345) +613 train 7.979389 (lr=1.9673e-04) (hash(x)=23470413) +614 train 7.869417 (lr=1.9672e-04) (hash(x)=24742370) +615 train 7.848534 (lr=1.9670e-04) (hash(x)=24843741) +616 train 7.726870 (lr=1.9668e-04) (hash(x)=25192548) +617 train 7.827699 (lr=1.9667e-04) (hash(x)=27176996) +618 train 7.715825 (lr=1.9665e-04) (hash(x)=23964552) +619 train 7.664890 (lr=1.9664e-04) (hash(x)=22855363) +620 train 7.674344 (lr=1.9662e-04) (hash(x)=26332996) +621 train 7.506065 (lr=1.9660e-04) (hash(x)=22960957) +622 train 7.825584 (lr=1.9659e-04) (hash(x)=22752597) +623 train 7.707257 (lr=1.9657e-04) (hash(x)=23197102) +624 train 8.179389 (lr=1.9656e-04) (hash(x)=27383319) +625 train 7.706972 (lr=1.9654e-04) (hash(x)=26132276) +626 train 7.576851 (lr=1.9652e-04) (hash(x)=19810497) +627 train 7.684837 (lr=1.9651e-04) (hash(x)=25704919) +628 train 7.852735 (lr=1.9649e-04) (hash(x)=27174264) +629 train 7.980241 (lr=1.9648e-04) (hash(x)=22280814) +630 train 8.692590 (lr=1.9646e-04) (hash(x)=24279448) +631 train 8.166540 (lr=1.9644e-04) (hash(x)=23054940) +632 train 8.265895 (lr=1.9643e-04) (hash(x)=23942400) +633 train 8.503886 (lr=1.9641e-04) (hash(x)=24712416) +634 train 8.114071 (lr=1.9639e-04) (hash(x)=24564658) +635 train 7.794017 (lr=1.9638e-04) (hash(x)=24909904) +636 train 7.799278 (lr=1.9636e-04) (hash(x)=23049534) +637 train 7.890192 (lr=1.9634e-04) (hash(x)=24321591) +638 train 7.700247 (lr=1.9633e-04) (hash(x)=26153298) +639 train 7.731563 (lr=1.9631e-04) (hash(x)=27140757) +640 train 7.526123 (lr=1.9629e-04) (hash(x)=25115907) +641 train 7.569061 (lr=1.9628e-04) (hash(x)=26563770) +642 train 7.747261 (lr=1.9626e-04) (hash(x)=28089252) +643 train 7.683803 (lr=1.9624e-04) (hash(x)=25993110) +644 train 7.622728 (lr=1.9623e-04) (hash(x)=25150008) +645 train 7.873084 (lr=1.9621e-04) (hash(x)=28520222) +646 train 7.507164 (lr=1.9619e-04) (hash(x)=21349943) +647 train 7.604231 (lr=1.9618e-04) (hash(x)=25149419) +648 train 7.792694 (lr=1.9616e-04) (hash(x)=25730641) +649 train 7.918859 (lr=1.9614e-04) (hash(x)=26112813) +650 val loss 7.7302 +650 val perplexity 2276.0830 +650 train 7.768733 (lr=1.9612e-04) (hash(x)=25907805) +651 train 7.813058 (lr=1.9611e-04) (hash(x)=27623643) +652 train 7.772527 (lr=1.9609e-04) (hash(x)=26484959) +653 train 7.824371 (lr=1.9607e-04) (hash(x)=29199854) +654 train 7.772023 (lr=1.9606e-04) (hash(x)=28369628) +655 train 7.654570 (lr=1.9604e-04) (hash(x)=24727764) +656 train 7.418724 (lr=1.9602e-04) (hash(x)=22610673) +657 train 7.376244 (lr=1.9600e-04) (hash(x)=22667179) +658 train 7.203572 (lr=1.9599e-04) (hash(x)=18477300) +659 train 7.584197 (lr=1.9597e-04) (hash(x)=23155773) +660 train 7.342638 (lr=1.9595e-04) (hash(x)=19461032) +661 train 7.631986 (lr=1.9593e-04) (hash(x)=23453788) +662 train 7.750983 (lr=1.9592e-04) (hash(x)=24543466) +663 train 7.535265 (lr=1.9590e-04) (hash(x)=21935931) +664 train 7.363919 (lr=1.9588e-04) (hash(x)=19910292) +665 train 7.668031 (lr=1.9586e-04) (hash(x)=24481079) +666 train 7.339485 (lr=1.9585e-04) (hash(x)=18922411) +667 train 7.393097 (lr=1.9583e-04) (hash(x)=20054917) +668 train 7.631470 (lr=1.9581e-04) (hash(x)=24850470) +669 train 7.658822 (lr=1.9579e-04) (hash(x)=25907741) +670 train 7.806902 (lr=1.9578e-04) (hash(x)=26873522) +671 train 7.858834 (lr=1.9576e-04) (hash(x)=27606073) +672 train 7.951534 (lr=1.9574e-04) (hash(x)=26209645) +673 train 7.796901 (lr=1.9572e-04) (hash(x)=25202001) +674 train 7.844139 (lr=1.9570e-04) (hash(x)=25569462) +675 train 7.798089 (lr=1.9569e-04) (hash(x)=26534487) +676 train 7.786978 (lr=1.9567e-04) (hash(x)=26455057) +677 train 7.671373 (lr=1.9565e-04) (hash(x)=24095850) +678 train 7.889379 (lr=1.9563e-04) (hash(x)=25287752) +679 train 7.362187 (lr=1.9561e-04) (hash(x)=22450341) +680 train 8.091969 (lr=1.9560e-04) (hash(x)=29004853) +681 train 7.805799 (lr=1.9558e-04) (hash(x)=27993763) +682 train 7.652844 (lr=1.9556e-04) (hash(x)=26382658) +683 train 7.752538 (lr=1.9554e-04) (hash(x)=25013073) +684 train 7.805671 (lr=1.9552e-04) (hash(x)=30595809) +685 train 7.891605 (lr=1.9550e-04) (hash(x)=30934371) +686 train 8.472994 (lr=1.9549e-04) (hash(x)=33060834) +687 train 7.764513 (lr=1.9547e-04) (hash(x)=25945859) +688 train 7.579477 (lr=1.9545e-04) (hash(x)=23375678) +689 train 7.647514 (lr=1.9543e-04) (hash(x)=25218689) +690 train 7.791622 (lr=1.9541e-04) (hash(x)=28127397) +691 train 7.676419 (lr=1.9539e-04) (hash(x)=24418091) +692 train 7.603237 (lr=1.9537e-04) (hash(x)=22761099) +693 train 7.585611 (lr=1.9536e-04) (hash(x)=24615466) +694 train 7.717437 (lr=1.9534e-04) (hash(x)=24699240) +695 train 7.631001 (lr=1.9532e-04) (hash(x)=21613707) +696 train 7.719936 (lr=1.9530e-04) (hash(x)=24977554) +697 train 7.650555 (lr=1.9528e-04) (hash(x)=24348175) +698 train 7.842303 (lr=1.9526e-04) (hash(x)=25102767) +699 train 7.786335 (lr=1.9524e-04) (hash(x)=26386157) +700 val loss 7.7295 +700 val perplexity 2274.3655 +700 train 7.765370 (lr=1.9522e-04) (hash(x)=26423460) +701 train 7.670255 (lr=1.9520e-04) (hash(x)=25771047) +702 train 7.711510 (lr=1.9519e-04) (hash(x)=26999875) +703 train 7.662324 (lr=1.9517e-04) (hash(x)=24396519) +704 train 7.681601 (lr=1.9515e-04) (hash(x)=22588122) +705 train 8.008059 (lr=1.9513e-04) (hash(x)=25142399) +706 train 7.756539 (lr=1.9511e-04) (hash(x)=20440214) +707 train 7.594737 (lr=1.9509e-04) (hash(x)=23265507) +708 train 7.667482 (lr=1.9507e-04) (hash(x)=24563470) +709 train 7.571256 (lr=1.9505e-04) (hash(x)=22514858) +710 train 7.947202 (lr=1.9503e-04) (hash(x)=26691212) +711 train 8.009685 (lr=1.9501e-04) (hash(x)=29138828) +712 train 7.982678 (lr=1.9499e-04) (hash(x)=28028528) +713 train 7.810258 (lr=1.9497e-04) (hash(x)=20531210) +714 train 7.707214 (lr=1.9496e-04) (hash(x)=25075352) +715 train 7.744718 (lr=1.9494e-04) (hash(x)=24265353) +716 train 7.808933 (lr=1.9492e-04) (hash(x)=24635726) +717 train 7.705533 (lr=1.9490e-04) (hash(x)=24999726) +718 train 7.896923 (lr=1.9488e-04) (hash(x)=27412910) +719 train 7.697567 (lr=1.9486e-04) (hash(x)=24685515) +720 train 7.718792 (lr=1.9484e-04) (hash(x)=23780329) +721 train 7.559627 (lr=1.9482e-04) (hash(x)=25071701) +722 train 7.727734 (lr=1.9480e-04) (hash(x)=23767130) +723 train 7.726370 (lr=1.9478e-04) (hash(x)=24876269) +724 train 7.825487 (lr=1.9476e-04) (hash(x)=26405773) +725 train 8.221280 (lr=1.9474e-04) (hash(x)=31733180) +726 train 7.502093 (lr=1.9472e-04) (hash(x)=21337509) +727 train 7.568280 (lr=1.9470e-04) (hash(x)=22825749) +728 train 7.906999 (lr=1.9468e-04) (hash(x)=28638695) +729 train 7.793335 (lr=1.9466e-04) (hash(x)=26393943) +730 train 7.918453 (lr=1.9464e-04) (hash(x)=27563583) +731 train 7.481687 (lr=1.9462e-04) (hash(x)=21239652) +732 train 7.590038 (lr=1.9460e-04) (hash(x)=23986428) +733 train 7.483735 (lr=1.9458e-04) (hash(x)=24943881) +734 train 8.054044 (lr=1.9456e-04) (hash(x)=29691448) +735 train 7.976167 (lr=1.9454e-04) (hash(x)=28767869) +736 train 7.686824 (lr=1.9452e-04) (hash(x)=23628188) +737 train 7.986019 (lr=1.9450e-04) (hash(x)=29341482) +738 train 7.820424 (lr=1.9448e-04) (hash(x)=30336570) +739 train 7.728809 (lr=1.9446e-04) (hash(x)=25614301) +740 train 7.618103 (lr=1.9444e-04) (hash(x)=24160500) +741 train 7.794523 (lr=1.9442e-04) (hash(x)=26030058) +742 train 8.143236 (lr=1.9440e-04) (hash(x)=29243936) +743 train 7.448659 (lr=1.9438e-04) (hash(x)=21159060) +744 train 7.569942 (lr=1.9436e-04) (hash(x)=23701853) +745 train 7.765334 (lr=1.9433e-04) (hash(x)=24629937) +746 train 7.682066 (lr=1.9431e-04) (hash(x)=25110108) +747 train 7.731210 (lr=1.9429e-04) (hash(x)=26751788) +748 train 7.762425 (lr=1.9427e-04) (hash(x)=26430427) +749 train 7.616586 (lr=1.9425e-04) (hash(x)=26012353) +750 val loss 7.6741 +750 val perplexity 2151.8735 +750 train 7.763222 (lr=1.9423e-04) (hash(x)=22735910) +751 train 7.579507 (lr=1.9421e-04) (hash(x)=25045397) +752 train 7.286607 (lr=1.9419e-04) (hash(x)=21554427) +753 train 7.413031 (lr=1.9417e-04) (hash(x)=23751143) +754 train 8.162292 (lr=1.9415e-04) (hash(x)=28602273) +755 train 8.182625 (lr=1.9413e-04) (hash(x)=29989709) +756 train 7.616182 (lr=1.9411e-04) (hash(x)=22331648) +757 train 7.986131 (lr=1.9409e-04) (hash(x)=31017246) +758 train 7.952241 (lr=1.9406e-04) (hash(x)=29709045) +759 train 8.041177 (lr=1.9404e-04) (hash(x)=25560928) +760 train 7.747766 (lr=1.9402e-04) (hash(x)=25075464) +761 train 7.837605 (lr=1.9400e-04) (hash(x)=27352253) +762 train 8.003541 (lr=1.9398e-04) (hash(x)=28187891) +763 train 7.878601 (lr=1.9396e-04) (hash(x)=26062687) +764 train 7.868335 (lr=1.9394e-04) (hash(x)=27427811) +765 train 7.918667 (lr=1.9392e-04) (hash(x)=27614522) +766 train 7.707654 (lr=1.9389e-04) (hash(x)=26129544) +767 train 8.244135 (lr=1.9387e-04) (hash(x)=28959222) +768 train 7.803838 (lr=1.9385e-04) (hash(x)=26860067) +769 train 7.569221 (lr=1.9383e-04) (hash(x)=25122598) +770 train 7.634522 (lr=1.9381e-04) (hash(x)=25245030) +771 train 7.653938 (lr=1.9379e-04) (hash(x)=25434884) +772 train 7.738338 (lr=1.9377e-04) (hash(x)=27732790) +773 train 7.707780 (lr=1.9374e-04) (hash(x)=27824438) +774 train 7.880441 (lr=1.9372e-04) (hash(x)=27201953) +775 train 7.594666 (lr=1.9370e-04) (hash(x)=21248405) +776 train 7.407650 (lr=1.9368e-04) (hash(x)=22805934) +777 train 7.669936 (lr=1.9366e-04) (hash(x)=26482588) +778 train 7.728265 (lr=1.9364e-04) (hash(x)=24153691) +779 train 7.843231 (lr=1.9361e-04) (hash(x)=25044192) +780 train 7.777481 (lr=1.9359e-04) (hash(x)=25910078) +781 train 7.804030 (lr=1.9357e-04) (hash(x)=28645524) +782 train 7.600325 (lr=1.9355e-04) (hash(x)=24368498) +783 train 7.662036 (lr=1.9353e-04) (hash(x)=25830182) +784 train 7.755760 (lr=1.9351e-04) (hash(x)=29181807) +785 train 7.698790 (lr=1.9348e-04) (hash(x)=25585137) +786 train 7.623371 (lr=1.9346e-04) (hash(x)=24798246) +787 train 7.735772 (lr=1.9344e-04) (hash(x)=26621419) +788 train 7.292851 (lr=1.9342e-04) (hash(x)=21446891) +789 train 7.227391 (lr=1.9339e-04) (hash(x)=22165286) +790 train 7.486896 (lr=1.9337e-04) (hash(x)=23477219) +791 train 7.758893 (lr=1.9335e-04) (hash(x)=25173113) +792 train 7.631598 (lr=1.9333e-04) (hash(x)=25853788) +793 train 7.746405 (lr=1.9331e-04) (hash(x)=27267091) +794 train 7.583335 (lr=1.9328e-04) (hash(x)=23743694) +795 train 7.570453 (lr=1.9326e-04) (hash(x)=24400133) +796 train 7.668386 (lr=1.9324e-04) (hash(x)=23663639) +797 train 7.542465 (lr=1.9322e-04) (hash(x)=23103223) +798 train 8.050569 (lr=1.9319e-04) (hash(x)=28748411) +799 train 7.386157 (lr=1.9317e-04) (hash(x)=23486277) +800 val loss 7.6869 +800 val perplexity 2179.6960 +800 train 7.678397 (lr=1.9315e-04) (hash(x)=25678518) +801 train 7.590005 (lr=1.9313e-04) (hash(x)=23421286) +802 train 7.753471 (lr=1.9310e-04) (hash(x)=26054104) +803 train 7.757391 (lr=1.9308e-04) (hash(x)=25978130) +804 train 7.778117 (lr=1.9306e-04) (hash(x)=26006525) +805 train 7.754684 (lr=1.9304e-04) (hash(x)=25769432) +806 train 7.562862 (lr=1.9301e-04) (hash(x)=22430795) +807 train 7.941864 (lr=1.9299e-04) (hash(x)=28916006) +808 train 7.716609 (lr=1.9297e-04) (hash(x)=25166800) +809 train 7.821579 (lr=1.9294e-04) (hash(x)=24226056) +810 train 7.643736 (lr=1.9292e-04) (hash(x)=25057934) +811 train 8.424454 (lr=1.9290e-04) (hash(x)=33195100) +812 train 7.841278 (lr=1.9288e-04) (hash(x)=26312888) +813 train 8.008039 (lr=1.9285e-04) (hash(x)=27730410) +814 train 7.873559 (lr=1.9283e-04) (hash(x)=27372474) +815 train 7.710435 (lr=1.9281e-04) (hash(x)=25556929) +816 train 7.783272 (lr=1.9278e-04) (hash(x)=26909985) +817 train 7.578075 (lr=1.9276e-04) (hash(x)=25991247) +818 train 7.810253 (lr=1.9274e-04) (hash(x)=27438141) +819 train 7.971584 (lr=1.9271e-04) (hash(x)=29536986) +820 train 7.679801 (lr=1.9269e-04) (hash(x)=24478391) +821 train 7.674594 (lr=1.9267e-04) (hash(x)=26125216) +822 train 7.679646 (lr=1.9264e-04) (hash(x)=26422130) +823 train 7.886177 (lr=1.9262e-04) (hash(x)=29648798) +824 train 7.585496 (lr=1.9260e-04) (hash(x)=21247770) +825 train 7.720960 (lr=1.9257e-04) (hash(x)=23195388) +826 train 7.679245 (lr=1.9255e-04) (hash(x)=25796725) +827 train 7.736967 (lr=1.9253e-04) (hash(x)=23124767) +828 train 7.765054 (lr=1.9250e-04) (hash(x)=25233464) +829 train 7.749599 (lr=1.9248e-04) (hash(x)=25713275) +830 train 7.667947 (lr=1.9246e-04) (hash(x)=25550167) +831 train 7.589333 (lr=1.9243e-04) (hash(x)=24976217) +832 train 7.879935 (lr=1.9241e-04) (hash(x)=28536827) +833 train 7.774293 (lr=1.9239e-04) (hash(x)=27500801) +834 train 7.583018 (lr=1.9236e-04) (hash(x)=25545765) +835 train 7.636909 (lr=1.9234e-04) (hash(x)=23632825) +836 train 7.690586 (lr=1.9231e-04) (hash(x)=25708009) +837 train 7.753835 (lr=1.9229e-04) (hash(x)=24456276) +838 train 7.832035 (lr=1.9227e-04) (hash(x)=29189855) +839 train 8.045058 (lr=1.9224e-04) (hash(x)=31019606) +840 train 7.902132 (lr=1.9222e-04) (hash(x)=26328013) +841 train 7.847775 (lr=1.9220e-04) (hash(x)=25027904) +842 train 7.640970 (lr=1.9217e-04) (hash(x)=23734189) +843 train 7.904175 (lr=1.9215e-04) (hash(x)=28236580) +844 train 7.686363 (lr=1.9212e-04) (hash(x)=26509780) +845 train 7.746884 (lr=1.9210e-04) (hash(x)=25386473) +846 train 7.687967 (lr=1.9207e-04) (hash(x)=24052671) +847 train 7.869141 (lr=1.9205e-04) (hash(x)=28269421) +848 train 7.359294 (lr=1.9203e-04) (hash(x)=22251724) +849 train 7.573221 (lr=1.9200e-04) (hash(x)=24308447) +850 val loss 7.6823 +850 val perplexity 2169.6694 +850 train 7.544991 (lr=1.9198e-04) (hash(x)=24242830) +851 train 7.707771 (lr=1.9195e-04) (hash(x)=25563279) +852 train 7.743881 (lr=1.9193e-04) (hash(x)=26354481) +853 train 7.902176 (lr=1.9190e-04) (hash(x)=26152637) +854 train 7.927469 (lr=1.9188e-04) (hash(x)=28051025) +855 train 7.714743 (lr=1.9186e-04) (hash(x)=24865358) +856 train 7.613256 (lr=1.9183e-04) (hash(x)=24288911) +857 train 7.510205 (lr=1.9181e-04) (hash(x)=22230964) +858 train 7.406274 (lr=1.9178e-04) (hash(x)=21303832) +859 train 7.586470 (lr=1.9176e-04) (hash(x)=22155546) +860 train 7.676827 (lr=1.9173e-04) (hash(x)=25296428) +861 train 7.836428 (lr=1.9171e-04) (hash(x)=29142319) +862 train 7.639890 (lr=1.9168e-04) (hash(x)=25545430) +863 train 7.503406 (lr=1.9166e-04) (hash(x)=26984272) +864 train 7.675130 (lr=1.9163e-04) (hash(x)=25429005) +865 train 7.712409 (lr=1.9161e-04) (hash(x)=27077032) +866 train 7.701894 (lr=1.9158e-04) (hash(x)=26494424) +867 train 7.678000 (lr=1.9156e-04) (hash(x)=23193673) +868 train 7.701917 (lr=1.9153e-04) (hash(x)=25075134) +869 train 7.764646 (lr=1.9151e-04) (hash(x)=27112558) +870 train 7.949636 (lr=1.9148e-04) (hash(x)=27436608) +871 train 7.607687 (lr=1.9146e-04) (hash(x)=24544116) +872 train 7.983875 (lr=1.9143e-04) (hash(x)=31632686) +873 train 7.650281 (lr=1.9141e-04) (hash(x)=25890184) +874 train 7.759118 (lr=1.9138e-04) (hash(x)=22887555) +875 train 7.620056 (lr=1.9136e-04) (hash(x)=24547533) +876 train 7.721323 (lr=1.9133e-04) (hash(x)=26553496) +877 train 7.812256 (lr=1.9131e-04) (hash(x)=27467688) +878 train 7.597523 (lr=1.9128e-04) (hash(x)=24766934) +879 train 7.458284 (lr=1.9126e-04) (hash(x)=22059850) +880 train 7.862318 (lr=1.9123e-04) (hash(x)=22871702) +881 train 7.682838 (lr=1.9121e-04) (hash(x)=23893130) +882 train 7.737639 (lr=1.9118e-04) (hash(x)=25125691) +883 train 7.685982 (lr=1.9116e-04) (hash(x)=25994573) +884 train 7.746265 (lr=1.9113e-04) (hash(x)=26076345) +885 train 7.660385 (lr=1.9111e-04) (hash(x)=26577783) +886 train 7.780622 (lr=1.9108e-04) (hash(x)=27395225) +887 train 7.617593 (lr=1.9105e-04) (hash(x)=23926632) +888 train 7.467262 (lr=1.9103e-04) (hash(x)=21737239) +889 train 7.738924 (lr=1.9100e-04) (hash(x)=23574207) +890 train 7.396074 (lr=1.9098e-04) (hash(x)=24365231) +891 train 7.570849 (lr=1.9095e-04) (hash(x)=27111369) +892 train 7.834388 (lr=1.9093e-04) (hash(x)=27290015) +893 train 7.626697 (lr=1.9090e-04) (hash(x)=23979820) +894 train 7.712796 (lr=1.9087e-04) (hash(x)=26450121) +895 train 7.634922 (lr=1.9085e-04) (hash(x)=27025333) +896 train 7.626338 (lr=1.9082e-04) (hash(x)=23624605) +897 train 7.472151 (lr=1.9080e-04) (hash(x)=22846386) +898 train 7.519318 (lr=1.9077e-04) (hash(x)=22970561) +899 train 7.353206 (lr=1.9074e-04) (hash(x)=16908068) +900 val loss 7.6280 +900 val perplexity 2054.9924 +900 train 7.599403 (lr=1.9072e-04) (hash(x)=24661446) +901 train 7.690077 (lr=1.9069e-04) (hash(x)=25664727) +902 train 7.648757 (lr=1.9067e-04) (hash(x)=25667011) +903 train 7.723057 (lr=1.9064e-04) (hash(x)=29120407) +904 train 7.733173 (lr=1.9061e-04) (hash(x)=23385735) +905 train 7.756490 (lr=1.9059e-04) (hash(x)=25564213) +906 train 7.837747 (lr=1.9056e-04) (hash(x)=25413898) +907 train 7.766463 (lr=1.9054e-04) (hash(x)=27092710) +908 train 7.558139 (lr=1.9051e-04) (hash(x)=25789923) +909 train 7.661148 (lr=1.9048e-04) (hash(x)=28533197) +910 train 7.492767 (lr=1.9046e-04) (hash(x)=22982996) +911 train 7.585385 (lr=1.9043e-04) (hash(x)=23827393) +912 train 7.273323 (lr=1.9040e-04) (hash(x)=21242640) +913 train 7.644277 (lr=1.9038e-04) (hash(x)=24154233) +914 train 7.648184 (lr=1.9035e-04) (hash(x)=24331967) +915 train 7.874647 (lr=1.9032e-04) (hash(x)=32812727) +916 train 7.569633 (lr=1.9030e-04) (hash(x)=23572994) +917 train 7.596375 (lr=1.9027e-04) (hash(x)=26305435) +918 train 7.649402 (lr=1.9024e-04) (hash(x)=26268355) +919 train 7.799970 (lr=1.9022e-04) (hash(x)=27230027) +920 train 7.628154 (lr=1.9019e-04) (hash(x)=23885377) +921 train 7.563693 (lr=1.9016e-04) (hash(x)=23532437) +922 train 7.618789 (lr=1.9014e-04) (hash(x)=25577034) +923 train 7.748274 (lr=1.9011e-04) (hash(x)=25703381) +924 train 7.754161 (lr=1.9008e-04) (hash(x)=27113866) +925 train 7.575099 (lr=1.9006e-04) (hash(x)=26961429) +926 train 7.389259 (lr=1.9003e-04) (hash(x)=21355372) +927 train 7.563704 (lr=1.9000e-04) (hash(x)=24968260) +928 train 7.530243 (lr=1.8998e-04) (hash(x)=25357517) +929 train 7.621249 (lr=1.8995e-04) (hash(x)=24854265) +930 train 7.358922 (lr=1.8992e-04) (hash(x)=21102770) +931 train 7.662925 (lr=1.8989e-04) (hash(x)=25676468) +932 train 7.603921 (lr=1.8987e-04) (hash(x)=22809869) +933 train 7.739404 (lr=1.8984e-04) (hash(x)=25503865) +934 train 7.579716 (lr=1.8981e-04) (hash(x)=24853995) +935 train 7.737237 (lr=1.8979e-04) (hash(x)=27544803) +936 train 7.765428 (lr=1.8976e-04) (hash(x)=25981933) +937 train 7.508266 (lr=1.8973e-04) (hash(x)=24658683) +938 train 7.675022 (lr=1.8970e-04) (hash(x)=23855201) +939 train 7.611467 (lr=1.8968e-04) (hash(x)=24331407) +940 train 7.811347 (lr=1.8965e-04) (hash(x)=29265551) +941 train 7.493658 (lr=1.8962e-04) (hash(x)=21892556) +942 train 7.526296 (lr=1.8959e-04) (hash(x)=27183405) +943 train 7.492926 (lr=1.8957e-04) (hash(x)=26540663) +944 train 7.460661 (lr=1.8954e-04) (hash(x)=25718393) +945 train 7.648582 (lr=1.8951e-04) (hash(x)=26819462) +946 train 7.664230 (lr=1.8948e-04) (hash(x)=27427540) +947 train 7.633901 (lr=1.8946e-04) (hash(x)=25532657) +948 train 7.863449 (lr=1.8943e-04) (hash(x)=27641372) +949 train 7.625379 (lr=1.8940e-04) (hash(x)=26515570) +950 val loss 7.6265 +950 val perplexity 2051.8582 +950 train 7.830888 (lr=1.8937e-04) (hash(x)=26911957) +951 train 7.936368 (lr=1.8935e-04) (hash(x)=25856625) +952 train 7.499635 (lr=1.8932e-04) (hash(x)=25219129) +953 train 7.478160 (lr=1.8929e-04) (hash(x)=25260471) +954 train 7.812857 (lr=1.8926e-04) (hash(x)=29373370) +955 train 7.390720 (lr=1.8923e-04) (hash(x)=23437426) +956 train 7.686177 (lr=1.8921e-04) (hash(x)=23769521) +957 train 7.729100 (lr=1.8918e-04) (hash(x)=25961833) +958 train 7.466821 (lr=1.8915e-04) (hash(x)=23582666) +959 train 7.506217 (lr=1.8912e-04) (hash(x)=23164356) +960 train 7.526762 (lr=1.8909e-04) (hash(x)=24443114) +961 train 7.555103 (lr=1.8907e-04) (hash(x)=25052665) +962 train 7.671937 (lr=1.8904e-04) (hash(x)=27802272) +963 train 7.547755 (lr=1.8901e-04) (hash(x)=25957896) +964 train 7.595136 (lr=1.8898e-04) (hash(x)=26737251) +965 train 7.728930 (lr=1.8895e-04) (hash(x)=24723263) +966 train 7.659047 (lr=1.8892e-04) (hash(x)=24707011) +967 train 7.628091 (lr=1.8890e-04) (hash(x)=25646282) +968 train 7.671089 (lr=1.8887e-04) (hash(x)=27544665) +969 train 7.597840 (lr=1.8884e-04) (hash(x)=25851993) +970 train 7.864595 (lr=1.8881e-04) (hash(x)=29059700) +971 train 7.557237 (lr=1.8878e-04) (hash(x)=21513584) +972 train 7.351889 (lr=1.8875e-04) (hash(x)=23151267) +973 train 7.628883 (lr=1.8873e-04) (hash(x)=26017176) +974 train 7.730402 (lr=1.8870e-04) (hash(x)=26979518) +975 train 7.672785 (lr=1.8867e-04) (hash(x)=23843233) +976 train 7.841615 (lr=1.8864e-04) (hash(x)=24193010) +977 train 7.574764 (lr=1.8861e-04) (hash(x)=21476847) +978 train 7.427007 (lr=1.8858e-04) (hash(x)=21366504) +979 train 7.515633 (lr=1.8855e-04) (hash(x)=23226697) +980 train 7.334566 (lr=1.8852e-04) (hash(x)=19961773) +981 train 7.182587 (lr=1.8850e-04) (hash(x)=19772969) +982 train 7.453693 (lr=1.8847e-04) (hash(x)=23110142) +983 train 7.712500 (lr=1.8844e-04) (hash(x)=24506028) +984 train 7.657120 (lr=1.8841e-04) (hash(x)=25480731) +985 train 7.473416 (lr=1.8838e-04) (hash(x)=21077417) +986 train 7.502199 (lr=1.8835e-04) (hash(x)=23686713) +987 train 7.579089 (lr=1.8832e-04) (hash(x)=26024321) +988 train 7.685767 (lr=1.8829e-04) (hash(x)=27424109) +989 train 7.784911 (lr=1.8826e-04) (hash(x)=27786174) +990 train 7.597383 (lr=1.8824e-04) (hash(x)=25232502) +991 train 7.589963 (lr=1.8821e-04) (hash(x)=22781277) +992 train 7.654509 (lr=1.8818e-04) (hash(x)=26184527) +993 train 7.653077 (lr=1.8815e-04) (hash(x)=24459895) +994 train 7.599239 (lr=1.8812e-04) (hash(x)=25244624) +995 train 7.728543 (lr=1.8809e-04) (hash(x)=24451843) +996 train 7.723577 (lr=1.8806e-04) (hash(x)=22129897) +997 train 7.534253 (lr=1.8803e-04) (hash(x)=21116390) +998 train 7.360538 (lr=1.8800e-04) (hash(x)=20650070) +999 train 7.686526 (lr=1.8797e-04) (hash(x)=24948650) +1000 val loss 7.5921 +1000 val perplexity 1982.4272 +1000 train 7.555673 (lr=1.8794e-04) (hash(x)=25444553) +1001 train 7.565030 (lr=1.8791e-04) (hash(x)=25617781) +1002 train 7.468167 (lr=1.8788e-04) (hash(x)=23862434) +1003 train 7.472465 (lr=1.8785e-04) (hash(x)=25559534) +1004 train 7.685417 (lr=1.8782e-04) (hash(x)=26577585) +1005 train 7.546773 (lr=1.8779e-04) (hash(x)=25546274) +1006 train 7.633173 (lr=1.8776e-04) (hash(x)=26284202) +1007 train 7.640697 (lr=1.8774e-04) (hash(x)=26373991) +1008 train 7.552299 (lr=1.8771e-04) (hash(x)=24612851) +1009 train 7.630090 (lr=1.8768e-04) (hash(x)=26410662) +1010 train 7.673848 (lr=1.8765e-04) (hash(x)=23824841) +1011 train 7.961549 (lr=1.8762e-04) (hash(x)=27756673) +1012 train 7.718840 (lr=1.8759e-04) (hash(x)=25427447) +1013 train 7.716030 (lr=1.8756e-04) (hash(x)=23661686) +1014 train 7.625960 (lr=1.8753e-04) (hash(x)=25129504) +1015 train 7.564085 (lr=1.8750e-04) (hash(x)=23402396) +1016 train 7.768701 (lr=1.8747e-04) (hash(x)=26145557) +1017 train 7.572812 (lr=1.8744e-04) (hash(x)=26547918) +1018 train 7.636101 (lr=1.8741e-04) (hash(x)=26653070) +1019 train 7.629062 (lr=1.8738e-04) (hash(x)=28250354) +1020 train 7.648537 (lr=1.8735e-04) (hash(x)=25437401) +1021 train 7.671164 (lr=1.8732e-04) (hash(x)=25598861) +1022 train 7.508971 (lr=1.8729e-04) (hash(x)=24572587) +1023 train 7.566394 (lr=1.8726e-04) (hash(x)=21562133) +1024 train 7.942134 (lr=1.8723e-04) (hash(x)=27718876) +1025 train 7.520586 (lr=1.8720e-04) (hash(x)=25312391) +1026 train 7.633708 (lr=1.8717e-04) (hash(x)=26579535) +1027 train 7.828081 (lr=1.8713e-04) (hash(x)=27253861) +1028 train 7.715068 (lr=1.8710e-04) (hash(x)=28451867) +1029 train 7.468096 (lr=1.8707e-04) (hash(x)=26795921) +1030 train 7.611829 (lr=1.8704e-04) (hash(x)=26147208) +1031 train 7.656087 (lr=1.8701e-04) (hash(x)=25009210) +1032 train 7.597188 (lr=1.8698e-04) (hash(x)=25213771) +1033 train 7.495992 (lr=1.8695e-04) (hash(x)=26254538) +1034 train 7.533343 (lr=1.8692e-04) (hash(x)=25565614) +1035 train 7.374374 (lr=1.8689e-04) (hash(x)=23052577) +1036 train 8.101628 (lr=1.8686e-04) (hash(x)=29630613) +1037 train 7.421541 (lr=1.8683e-04) (hash(x)=23667224) +1038 train 7.546014 (lr=1.8680e-04) (hash(x)=25740670) +1039 train 7.609142 (lr=1.8677e-04) (hash(x)=27161811) +1040 train 7.729666 (lr=1.8674e-04) (hash(x)=26385663) +1041 train 7.424304 (lr=1.8671e-04) (hash(x)=26313522) +1042 train 7.551754 (lr=1.8668e-04) (hash(x)=26814686) +1043 train 7.704320 (lr=1.8665e-04) (hash(x)=27302459) +1044 train 7.973453 (lr=1.8661e-04) (hash(x)=26758132) +1045 train 7.598505 (lr=1.8658e-04) (hash(x)=26837963) +1046 train 7.385884 (lr=1.8655e-04) (hash(x)=22089547) +1047 train 7.854928 (lr=1.8652e-04) (hash(x)=29515100) +1048 train 7.572184 (lr=1.8649e-04) (hash(x)=25471442) +1049 train 7.581758 (lr=1.8646e-04) (hash(x)=26674478) +1050 val loss 7.5766 +1050 val perplexity 1951.9821 +1050 train 7.539838 (lr=1.8643e-04) (hash(x)=25373386) +1051 train 7.544708 (lr=1.8640e-04) (hash(x)=25318001) +1052 train 7.702713 (lr=1.8637e-04) (hash(x)=27255021) +1053 train 7.626054 (lr=1.8633e-04) (hash(x)=25174043) +1054 train 7.382549 (lr=1.8630e-04) (hash(x)=23857597) +1055 train 7.620056 (lr=1.8627e-04) (hash(x)=25305929) +1056 train 7.663875 (lr=1.8624e-04) (hash(x)=27009246) +1057 train 7.731271 (lr=1.8621e-04) (hash(x)=26175477) +1058 train 7.437087 (lr=1.8618e-04) (hash(x)=22700025) +1059 train 7.494198 (lr=1.8615e-04) (hash(x)=24339043) +1060 train 7.362265 (lr=1.8612e-04) (hash(x)=22139900) +1061 train 8.119118 (lr=1.8608e-04) (hash(x)=25412772) +1062 train 7.589244 (lr=1.8605e-04) (hash(x)=27020849) +1063 train 7.492914 (lr=1.8602e-04) (hash(x)=26808543) +1064 train 7.325162 (lr=1.8599e-04) (hash(x)=23061527) +1065 train 7.490963 (lr=1.8596e-04) (hash(x)=24738650) +1066 train 7.382779 (lr=1.8593e-04) (hash(x)=24036715) +1067 train 7.426881 (lr=1.8589e-04) (hash(x)=25763991) +1068 train 7.671356 (lr=1.8586e-04) (hash(x)=27393753) +1069 train 7.789060 (lr=1.8583e-04) (hash(x)=28182190) +1070 train 7.433305 (lr=1.8580e-04) (hash(x)=23358569) +1071 train 7.613277 (lr=1.8577e-04) (hash(x)=25669509) +1072 train 7.747363 (lr=1.8574e-04) (hash(x)=29139024) +1073 train 7.638700 (lr=1.8570e-04) (hash(x)=25616522) +1074 train 7.565798 (lr=1.8567e-04) (hash(x)=25695789) +1075 train 7.708545 (lr=1.8564e-04) (hash(x)=27676869) +1076 train 7.578668 (lr=1.8561e-04) (hash(x)=25952695) +1077 train 7.604021 (lr=1.8558e-04) (hash(x)=26316170) +1078 train 7.475339 (lr=1.8554e-04) (hash(x)=24081867) +1079 train 7.684617 (lr=1.8551e-04) (hash(x)=28435805) +1080 train 7.569556 (lr=1.8548e-04) (hash(x)=23375063) +1081 train 7.556133 (lr=1.8545e-04) (hash(x)=26869022) +1082 train 7.448319 (lr=1.8542e-04) (hash(x)=25793007) +1083 train 7.450591 (lr=1.8538e-04) (hash(x)=23455211) +1084 train 7.436150 (lr=1.8535e-04) (hash(x)=20441501) +1085 train 7.791787 (lr=1.8532e-04) (hash(x)=29321187) +1086 train 7.923284 (lr=1.8529e-04) (hash(x)=32627505) +1087 train 7.475442 (lr=1.8525e-04) (hash(x)=26482758) +1088 train 7.335450 (lr=1.8522e-04) (hash(x)=21431511) +1089 train 7.610668 (lr=1.8519e-04) (hash(x)=26046639) +1090 train 7.686721 (lr=1.8516e-04) (hash(x)=27464841) +1091 train 7.528619 (lr=1.8513e-04) (hash(x)=27068280) +1092 train 7.412956 (lr=1.8509e-04) (hash(x)=23119133) +1093 train 7.587083 (lr=1.8506e-04) (hash(x)=26782091) +1094 train 7.599720 (lr=1.8503e-04) (hash(x)=26265326) +1095 train 7.630132 (lr=1.8500e-04) (hash(x)=24929929) +1096 train 7.491672 (lr=1.8496e-04) (hash(x)=23158628) +1097 train 7.577437 (lr=1.8493e-04) (hash(x)=25950541) +1098 train 7.387074 (lr=1.8490e-04) (hash(x)=22093912) +1099 train 7.525951 (lr=1.8486e-04) (hash(x)=25373676) +1100 val loss 7.5285 +1100 val perplexity 1860.2252 +1100 train 7.238816 (lr=1.8483e-04) (hash(x)=18986670) +1101 train 7.731666 (lr=1.8480e-04) (hash(x)=27283187) +1102 train 7.492186 (lr=1.8477e-04) (hash(x)=25474743) +1103 train 7.452324 (lr=1.8473e-04) (hash(x)=25043037) +1104 train 7.361247 (lr=1.8470e-04) (hash(x)=23156261) +1105 train 7.809726 (lr=1.8467e-04) (hash(x)=27027534) +1106 train 7.427492 (lr=1.8464e-04) (hash(x)=22733630) +1107 train 7.655629 (lr=1.8460e-04) (hash(x)=27906976) +1108 train 7.582325 (lr=1.8457e-04) (hash(x)=27848655) +1109 train 7.524204 (lr=1.8454e-04) (hash(x)=23889709) +1110 train 8.516034 (lr=1.8450e-04) (hash(x)=33189918) +1111 train 8.102610 (lr=1.8447e-04) (hash(x)=29151257) +1112 train 7.804785 (lr=1.8444e-04) (hash(x)=23881512) +1113 train 7.512683 (lr=1.8440e-04) (hash(x)=21307974) +1114 train 7.527910 (lr=1.8437e-04) (hash(x)=25264524) +1115 train 7.676703 (lr=1.8434e-04) (hash(x)=26405613) +1116 train 7.419920 (lr=1.8430e-04) (hash(x)=21918678) +1117 train 7.381271 (lr=1.8427e-04) (hash(x)=24233887) +1118 train 7.027851 (lr=1.8424e-04) (hash(x)=19490509) +1119 train 7.596524 (lr=1.8420e-04) (hash(x)=26400365) +1120 train 7.897218 (lr=1.8417e-04) (hash(x)=28572086) +1121 train 7.302793 (lr=1.8414e-04) (hash(x)=22293114) +1122 train 7.472042 (lr=1.8410e-04) (hash(x)=26845479) +1123 train 7.369507 (lr=1.8407e-04) (hash(x)=23971905) +1124 train 7.564978 (lr=1.8404e-04) (hash(x)=25639959) +1125 train 7.192587 (lr=1.8400e-04) (hash(x)=20076502) +1126 train 7.592453 (lr=1.8397e-04) (hash(x)=25089255) +1127 train 7.486467 (lr=1.8394e-04) (hash(x)=24098812) +1128 train 7.493239 (lr=1.8390e-04) (hash(x)=23493707) +1129 train 7.706886 (lr=1.8387e-04) (hash(x)=27610410) +1130 train 7.477085 (lr=1.8384e-04) (hash(x)=24540186) +1131 train 7.763455 (lr=1.8380e-04) (hash(x)=29402976) +1132 train 7.350609 (lr=1.8377e-04) (hash(x)=23776025) +1133 train 7.169466 (lr=1.8373e-04) (hash(x)=19032564) +1134 train 7.678875 (lr=1.8370e-04) (hash(x)=26921117) +1135 train 7.316682 (lr=1.8367e-04) (hash(x)=20967666) +1136 train 7.356919 (lr=1.8363e-04) (hash(x)=23394540) +1137 train 7.400156 (lr=1.8360e-04) (hash(x)=22666342) +1138 train 7.573081 (lr=1.8357e-04) (hash(x)=23482498) +1139 train 7.593708 (lr=1.8353e-04) (hash(x)=24287610) +1140 train 7.665570 (lr=1.8350e-04) (hash(x)=24512831) +1141 train 7.895320 (lr=1.8346e-04) (hash(x)=28637634) +1142 train 8.148598 (lr=1.8343e-04) (hash(x)=24107127) +1143 train 7.789571 (lr=1.8340e-04) (hash(x)=28667963) +1144 train 7.678395 (lr=1.8336e-04) (hash(x)=26302492) +1145 train 7.696847 (lr=1.8333e-04) (hash(x)=23621685) +1146 train 7.423781 (lr=1.8329e-04) (hash(x)=23997414) +1147 train 7.522644 (lr=1.8326e-04) (hash(x)=25974316) +1148 train 7.488329 (lr=1.8322e-04) (hash(x)=23464988) +1149 train 7.573183 (lr=1.8319e-04) (hash(x)=24487710) +1150 val loss 7.5296 +1150 val perplexity 1862.4255 +1150 train 7.752884 (lr=1.8316e-04) (hash(x)=29610350) +1151 train 7.835132 (lr=1.8312e-04) (hash(x)=27083417) +1152 train 7.234849 (lr=1.8309e-04) (hash(x)=20666288) +1153 train 7.352441 (lr=1.8305e-04) (hash(x)=22850633) +1154 train 7.501044 (lr=1.8302e-04) (hash(x)=24741872) +1155 train 7.866710 (lr=1.8298e-04) (hash(x)=28605205) +1156 train 7.338481 (lr=1.8295e-04) (hash(x)=22624463) +1157 train 7.589583 (lr=1.8292e-04) (hash(x)=24786468) +1158 train 7.354545 (lr=1.8288e-04) (hash(x)=21365399) +1159 train 7.537956 (lr=1.8285e-04) (hash(x)=23649001) +1160 train 7.614875 (lr=1.8281e-04) (hash(x)=28203982) +1161 train 7.517470 (lr=1.8278e-04) (hash(x)=26473994) +1162 train 7.203378 (lr=1.8274e-04) (hash(x)=19476441) +1163 train 7.494380 (lr=1.8271e-04) (hash(x)=25921700) +1164 train 7.299153 (lr=1.8267e-04) (hash(x)=23064343) +1165 train 7.462579 (lr=1.8264e-04) (hash(x)=24117626) +1166 train 7.365293 (lr=1.8260e-04) (hash(x)=21764556) +1167 train 8.219919 (lr=1.8257e-04) (hash(x)=31338300) +1168 train 7.708766 (lr=1.8253e-04) (hash(x)=27443187) +1169 train 7.128510 (lr=1.8250e-04) (hash(x)=21337692) +1170 train 7.678122 (lr=1.8246e-04) (hash(x)=27845383) +1171 train 7.450066 (lr=1.8243e-04) (hash(x)=23862328) +1172 train 7.638710 (lr=1.8239e-04) (hash(x)=23811014) +1173 train 7.595592 (lr=1.8236e-04) (hash(x)=24380098) +1174 train 7.333128 (lr=1.8232e-04) (hash(x)=22351136) +1175 train 7.576141 (lr=1.8229e-04) (hash(x)=30603174) +1176 train 7.613353 (lr=1.8225e-04) (hash(x)=27924596) +1177 train 7.947983 (lr=1.8222e-04) (hash(x)=30882548) +1178 train 7.431008 (lr=1.8218e-04) (hash(x)=22339464) +1179 train 7.282309 (lr=1.8215e-04) (hash(x)=23603806) +1180 train 7.633237 (lr=1.8211e-04) (hash(x)=24809041) +1181 train 7.445183 (lr=1.8208e-04) (hash(x)=24382442) +1182 train 7.430264 (lr=1.8204e-04) (hash(x)=23134077) +1183 train 7.452533 (lr=1.8201e-04) (hash(x)=24830965) +1184 train 7.545783 (lr=1.8197e-04) (hash(x)=25527259) +1185 train 7.575629 (lr=1.8194e-04) (hash(x)=25547480) +1186 train 7.450849 (lr=1.8190e-04) (hash(x)=24424314) +1187 train 7.817470 (lr=1.8187e-04) (hash(x)=32488729) +1188 train 7.734064 (lr=1.8183e-04) (hash(x)=31168462) +1189 train 7.986362 (lr=1.8179e-04) (hash(x)=31331643) +1190 train 7.633668 (lr=1.8176e-04) (hash(x)=28746633) +1191 train 7.637533 (lr=1.8172e-04) (hash(x)=27269893) +1192 train 7.424439 (lr=1.8169e-04) (hash(x)=23484031) +1193 train 7.448750 (lr=1.8165e-04) (hash(x)=23278725) +1194 train 7.546944 (lr=1.8162e-04) (hash(x)=25440745) +1195 train 7.601706 (lr=1.8158e-04) (hash(x)=25215077) +1196 train 7.649152 (lr=1.8154e-04) (hash(x)=28309266) +1197 train 7.353832 (lr=1.8151e-04) (hash(x)=22442404) +1198 train 7.408181 (lr=1.8147e-04) (hash(x)=20775262) +1199 train 7.484366 (lr=1.8144e-04) (hash(x)=24825041) +1200 val loss 7.5140 +1200 val perplexity 1833.5321 +1200 train 7.634745 (lr=1.8140e-04) (hash(x)=29016896) +1201 train 7.571529 (lr=1.8137e-04) (hash(x)=25590276) +1202 train 7.462616 (lr=1.8133e-04) (hash(x)=22816384) +1203 train 7.565063 (lr=1.8129e-04) (hash(x)=25893804) +1204 train 7.449255 (lr=1.8126e-04) (hash(x)=23983816) +1205 train 7.360803 (lr=1.8122e-04) (hash(x)=22222468) +1206 train 7.380003 (lr=1.8119e-04) (hash(x)=23039141) +1207 train 7.381001 (lr=1.8115e-04) (hash(x)=22724871) +1208 train 7.431016 (lr=1.8111e-04) (hash(x)=25253062) +1209 train 7.428430 (lr=1.8108e-04) (hash(x)=25140744) +1210 train 7.479745 (lr=1.8104e-04) (hash(x)=24717218) +1211 train 7.575819 (lr=1.8101e-04) (hash(x)=27317554) +1212 train 7.222820 (lr=1.8097e-04) (hash(x)=22013236) +1213 train 7.795300 (lr=1.8093e-04) (hash(x)=26692343) +1214 train 7.297035 (lr=1.8090e-04) (hash(x)=19859225) +1215 train 7.281682 (lr=1.8086e-04) (hash(x)=24683717) +1216 train 7.335892 (lr=1.8082e-04) (hash(x)=21932013) +1217 train 7.533382 (lr=1.8079e-04) (hash(x)=26849303) +1218 train 7.628855 (lr=1.8075e-04) (hash(x)=26458000) +1219 train 7.433553 (lr=1.8071e-04) (hash(x)=21584083) +1220 train 7.757539 (lr=1.8068e-04) (hash(x)=23598625) +1221 train 7.483323 (lr=1.8064e-04) (hash(x)=26059939) +1222 train 7.726270 (lr=1.8061e-04) (hash(x)=25481982) +1223 train 7.605075 (lr=1.8057e-04) (hash(x)=26190337) +1224 train 7.767110 (lr=1.8053e-04) (hash(x)=28767755) +1225 train 7.429821 (lr=1.8050e-04) (hash(x)=23663918) +1226 train 7.508752 (lr=1.8046e-04) (hash(x)=21293227) +1227 train 7.509848 (lr=1.8042e-04) (hash(x)=22249019) +1228 train 7.628850 (lr=1.8039e-04) (hash(x)=26886529) +1229 train 7.446178 (lr=1.8035e-04) (hash(x)=25779849) +1230 train 7.573771 (lr=1.8031e-04) (hash(x)=26228964) +1231 train 7.502126 (lr=1.8028e-04) (hash(x)=23086289) +1232 train 7.611916 (lr=1.8024e-04) (hash(x)=23198922) +1233 train 7.655760 (lr=1.8020e-04) (hash(x)=27523941) +1234 train 7.427443 (lr=1.8017e-04) (hash(x)=24293992) +1235 train 8.165462 (lr=1.8013e-04) (hash(x)=28047044) +1236 train 7.632396 (lr=1.8009e-04) (hash(x)=23688671) +1237 train 7.491746 (lr=1.8005e-04) (hash(x)=25125498) +1238 train 7.381650 (lr=1.8002e-04) (hash(x)=21977292) +1239 train 7.452070 (lr=1.7998e-04) (hash(x)=23593875) +1240 train 7.382544 (lr=1.7994e-04) (hash(x)=22659030) +1241 train 7.478049 (lr=1.7991e-04) (hash(x)=25117733) +1242 train 7.445905 (lr=1.7987e-04) (hash(x)=22322808) +1243 train 7.500023 (lr=1.7983e-04) (hash(x)=26059735) +1244 train 7.499078 (lr=1.7979e-04) (hash(x)=22485526) +1245 train 7.404733 (lr=1.7976e-04) (hash(x)=23028679) +1246 train 7.395212 (lr=1.7972e-04) (hash(x)=22906035) +1247 train 7.309209 (lr=1.7968e-04) (hash(x)=22414190) +1248 train 7.598354 (lr=1.7965e-04) (hash(x)=26229624) +1249 train 7.384288 (lr=1.7961e-04) (hash(x)=22223137) +1250 val loss 7.5052 +1250 val perplexity 1817.4625 +1250 train 7.611647 (lr=1.7957e-04) (hash(x)=24911520) +1251 train 7.791100 (lr=1.7953e-04) (hash(x)=24204591) +1252 train 7.405615 (lr=1.7950e-04) (hash(x)=24379601) +1253 train 7.377211 (lr=1.7946e-04) (hash(x)=22922475) +1254 train 7.415395 (lr=1.7942e-04) (hash(x)=23426249) +1255 train 7.674257 (lr=1.7938e-04) (hash(x)=26758114) +1256 train 7.347127 (lr=1.7935e-04) (hash(x)=24027111) +1257 train 7.507306 (lr=1.7931e-04) (hash(x)=25358064) +1258 train 7.384502 (lr=1.7927e-04) (hash(x)=22571285) +1259 train 7.736182 (lr=1.7923e-04) (hash(x)=20084233) +1260 train 7.542972 (lr=1.7920e-04) (hash(x)=18786581) +1261 train 7.499954 (lr=1.7916e-04) (hash(x)=26395104) +1262 train 7.388165 (lr=1.7912e-04) (hash(x)=24212567) +1263 train 7.239652 (lr=1.7908e-04) (hash(x)=21563184) +1264 train 7.518897 (lr=1.7904e-04) (hash(x)=26490150) +1265 train 7.588436 (lr=1.7901e-04) (hash(x)=25207694) +1266 train 7.440845 (lr=1.7897e-04) (hash(x)=23914544) +1267 train 7.427248 (lr=1.7893e-04) (hash(x)=23861489) +1268 train 7.836102 (lr=1.7889e-04) (hash(x)=30714540) +1269 train 7.437215 (lr=1.7886e-04) (hash(x)=23471007) +1270 train 7.425882 (lr=1.7882e-04) (hash(x)=23244293) +1271 train 7.372518 (lr=1.7878e-04) (hash(x)=19218470) +1272 train 7.610861 (lr=1.7874e-04) (hash(x)=26965136) +1273 train 7.359265 (lr=1.7870e-04) (hash(x)=22944035) +1274 train 7.384590 (lr=1.7867e-04) (hash(x)=22002714) +1275 train 7.691148 (lr=1.7863e-04) (hash(x)=28469562) +1276 train 7.756165 (lr=1.7859e-04) (hash(x)=26889992) +1277 train 7.783827 (lr=1.7855e-04) (hash(x)=26452814) +1278 train 7.600021 (lr=1.7851e-04) (hash(x)=28397488) +1279 train 7.674484 (lr=1.7847e-04) (hash(x)=25588469) +1280 train 7.555857 (lr=1.7844e-04) (hash(x)=24833139) +1281 train 7.430098 (lr=1.7840e-04) (hash(x)=24788298) +1282 train 7.629064 (lr=1.7836e-04) (hash(x)=24979383) +1283 train 7.624069 (lr=1.7832e-04) (hash(x)=25236367) +1284 train 7.467426 (lr=1.7828e-04) (hash(x)=22638257) +1285 train 7.367494 (lr=1.7824e-04) (hash(x)=23069067) +1286 train 7.528029 (lr=1.7821e-04) (hash(x)=25133239) +1287 train 8.051213 (lr=1.7817e-04) (hash(x)=30433767) +1288 train 8.049170 (lr=1.7813e-04) (hash(x)=34319079) +1289 train 7.909279 (lr=1.7809e-04) (hash(x)=29268881) +1290 train 7.523921 (lr=1.7805e-04) (hash(x)=24528336) +1291 train 7.696045 (lr=1.7801e-04) (hash(x)=26302626) +1292 train 7.672953 (lr=1.7798e-04) (hash(x)=25479111) +1293 train 7.787210 (lr=1.7794e-04) (hash(x)=24749682) +1294 train 7.409897 (lr=1.7790e-04) (hash(x)=24111393) +1295 train 7.147518 (lr=1.7786e-04) (hash(x)=17851621) +1296 train 7.452519 (lr=1.7782e-04) (hash(x)=26463070) +1297 train 7.478751 (lr=1.7778e-04) (hash(x)=25620741) +1298 train 8.154523 (lr=1.7774e-04) (hash(x)=28225676) +1299 train 7.948047 (lr=1.7770e-04) (hash(x)=27028191) +1300 val loss 7.5038 +1300 val perplexity 1814.8826 +1300 train 7.643556 (lr=1.7767e-04) (hash(x)=29006516) +1301 train 7.660791 (lr=1.7763e-04) (hash(x)=27590299) +1302 train 7.796421 (lr=1.7759e-04) (hash(x)=28678983) +1303 train 7.664966 (lr=1.7755e-04) (hash(x)=25183690) +1304 train 7.269347 (lr=1.7751e-04) (hash(x)=19918097) +1305 train 7.994386 (lr=1.7747e-04) (hash(x)=31114252) +1306 train 7.954857 (lr=1.7743e-04) (hash(x)=30913255) +1307 train 7.589433 (lr=1.7739e-04) (hash(x)=26182243) +1308 train 7.816391 (lr=1.7735e-04) (hash(x)=27420668) +1309 train 8.074536 (lr=1.7731e-04) (hash(x)=30419908) +1310 train 7.933122 (lr=1.7728e-04) (hash(x)=29002281) +1311 train 7.613068 (lr=1.7724e-04) (hash(x)=27040642) +1312 train 7.491214 (lr=1.7720e-04) (hash(x)=26929300) +1313 train 7.570533 (lr=1.7716e-04) (hash(x)=26240761) +1314 train 7.636490 (lr=1.7712e-04) (hash(x)=27161876) +1315 train 7.486239 (lr=1.7708e-04) (hash(x)=24489607) +1316 train 7.832559 (lr=1.7704e-04) (hash(x)=27040115) +1317 train 7.546991 (lr=1.7700e-04) (hash(x)=25012872) +1318 train 7.193055 (lr=1.7696e-04) (hash(x)=20894720) +1319 train 7.336178 (lr=1.7692e-04) (hash(x)=22183303) +1320 train 7.546183 (lr=1.7688e-04) (hash(x)=26291778) +1321 train 7.646647 (lr=1.7684e-04) (hash(x)=27682633) +1322 train 7.440039 (lr=1.7680e-04) (hash(x)=26490892) +1323 train 7.846274 (lr=1.7676e-04) (hash(x)=28844646) +1324 train 8.148518 (lr=1.7673e-04) (hash(x)=29545304) +1325 train 8.279584 (lr=1.7669e-04) (hash(x)=31082070) +1326 train 7.911991 (lr=1.7665e-04) (hash(x)=27486316) +1327 train 7.872516 (lr=1.7661e-04) (hash(x)=27537063) +1328 train 7.574136 (lr=1.7657e-04) (hash(x)=26955557) +1329 train 7.597261 (lr=1.7653e-04) (hash(x)=26125988) +1330 train 7.589724 (lr=1.7649e-04) (hash(x)=22800125) +1331 train 7.738342 (lr=1.7645e-04) (hash(x)=25446686) +1332 train 7.797683 (lr=1.7641e-04) (hash(x)=28743746) +1333 train 7.540285 (lr=1.7637e-04) (hash(x)=19819857) +1334 train 7.329230 (lr=1.7633e-04) (hash(x)=23518628) +1335 train 7.233037 (lr=1.7629e-04) (hash(x)=19492832) +1336 train 7.549953 (lr=1.7625e-04) (hash(x)=24627720) +1337 train 7.424287 (lr=1.7621e-04) (hash(x)=23741214) +1338 train 7.502259 (lr=1.7617e-04) (hash(x)=25837914) +1339 train 7.442078 (lr=1.7613e-04) (hash(x)=25484958) +1340 train 7.392017 (lr=1.7609e-04) (hash(x)=23671284) +1341 train 7.527875 (lr=1.7605e-04) (hash(x)=25525370) +1342 train 7.550336 (lr=1.7601e-04) (hash(x)=26585300) +1343 train 7.618244 (lr=1.7597e-04) (hash(x)=25951629) +1344 train 7.784412 (lr=1.7593e-04) (hash(x)=28743135) +1345 train 7.966664 (lr=1.7589e-04) (hash(x)=28557663) +1346 train 7.376771 (lr=1.7585e-04) (hash(x)=22642751) +1347 train 7.274148 (lr=1.7581e-04) (hash(x)=23462798) +1348 train 7.145050 (lr=1.7577e-04) (hash(x)=24292328) +1349 train 7.490060 (lr=1.7573e-04) (hash(x)=27320280) +1350 val loss 7.4984 +1350 val perplexity 1805.1401 +1350 train 7.717232 (lr=1.7569e-04) (hash(x)=27352812) +1351 train 7.523219 (lr=1.7565e-04) (hash(x)=22408682) +1352 train 7.420094 (lr=1.7561e-04) (hash(x)=23144732) +1353 train 7.314205 (lr=1.7557e-04) (hash(x)=22230799) +1354 train 7.717955 (lr=1.7553e-04) (hash(x)=29747687) +1355 train 7.938026 (lr=1.7549e-04) (hash(x)=31317970) +1356 train 7.184528 (lr=1.7545e-04) (hash(x)=20131758) +1357 train 7.511316 (lr=1.7541e-04) (hash(x)=24020983) +1358 train 7.373727 (lr=1.7536e-04) (hash(x)=23998051) +1359 train 7.482879 (lr=1.7532e-04) (hash(x)=27633457) +1360 train 7.200626 (lr=1.7528e-04) (hash(x)=20155247) +1361 train 7.478195 (lr=1.7524e-04) (hash(x)=23766987) +1362 train 7.353387 (lr=1.7520e-04) (hash(x)=25960383) +1363 train 7.638423 (lr=1.7516e-04) (hash(x)=23729283) +1364 train 7.745946 (lr=1.7512e-04) (hash(x)=27775445) +1365 train 7.589127 (lr=1.7508e-04) (hash(x)=25975834) +1366 train 7.442932 (lr=1.7504e-04) (hash(x)=22765259) +1367 train 7.680820 (lr=1.7500e-04) (hash(x)=27635080) +1368 train 7.466535 (lr=1.7496e-04) (hash(x)=23848542) +1369 train 7.606029 (lr=1.7492e-04) (hash(x)=27181156) +1370 train 7.713274 (lr=1.7488e-04) (hash(x)=28321340) +1371 train 7.460516 (lr=1.7484e-04) (hash(x)=25918780) +1372 train 7.494777 (lr=1.7480e-04) (hash(x)=23338297) +1373 train 7.622930 (lr=1.7475e-04) (hash(x)=22370417) +1374 train 7.535329 (lr=1.7471e-04) (hash(x)=24272668) +1375 train 7.252018 (lr=1.7467e-04) (hash(x)=22287596) +1376 train 7.386700 (lr=1.7463e-04) (hash(x)=25257403) +1377 train 7.368343 (lr=1.7459e-04) (hash(x)=21584419) +1378 train 7.526613 (lr=1.7455e-04) (hash(x)=25318823) +1379 train 7.330308 (lr=1.7451e-04) (hash(x)=22694623) +1380 train 7.499468 (lr=1.7447e-04) (hash(x)=23743406) +1381 train 7.693374 (lr=1.7443e-04) (hash(x)=30820846) +1382 train 8.198759 (lr=1.7438e-04) (hash(x)=34639557) +1383 train 8.034083 (lr=1.7434e-04) (hash(x)=35895440) +1384 train 7.535305 (lr=1.7430e-04) (hash(x)=26304839) +1385 train 7.675674 (lr=1.7426e-04) (hash(x)=27058657) +1386 train 7.529552 (lr=1.7422e-04) (hash(x)=25209529) +1387 train 7.472003 (lr=1.7418e-04) (hash(x)=24298886) +1388 train 7.605849 (lr=1.7414e-04) (hash(x)=26200200) +1389 train 7.499010 (lr=1.7410e-04) (hash(x)=27303061) +1390 train 7.564508 (lr=1.7405e-04) (hash(x)=26531628) +1391 train 7.575092 (lr=1.7401e-04) (hash(x)=25888847) +1392 train 7.717247 (lr=1.7397e-04) (hash(x)=28924067) +1393 train 7.213638 (lr=1.7393e-04) (hash(x)=21267641) +1394 train 7.731733 (lr=1.7389e-04) (hash(x)=29419156) +1395 train 7.984273 (lr=1.7385e-04) (hash(x)=30860646) +1396 train 7.533061 (lr=1.7381e-04) (hash(x)=25744434) +1397 train 7.513622 (lr=1.7376e-04) (hash(x)=26881837) +1398 train 7.502990 (lr=1.7372e-04) (hash(x)=26676176) +1399 train 7.685921 (lr=1.7368e-04) (hash(x)=26518800) +1400 val loss 7.4904 +1400 val perplexity 1790.7295 +1400 train 7.445290 (lr=1.7364e-04) (hash(x)=25043238) +1401 train 7.702843 (lr=1.7360e-04) (hash(x)=25863277) +1402 train 7.384724 (lr=1.7356e-04) (hash(x)=24073623) +1403 train 7.407113 (lr=1.7351e-04) (hash(x)=25385523) +1404 train 7.471757 (lr=1.7347e-04) (hash(x)=24958112) +1405 train 7.392669 (lr=1.7343e-04) (hash(x)=23362519) +1406 train 7.679748 (lr=1.7339e-04) (hash(x)=29262616) +1407 train 8.098048 (lr=1.7335e-04) (hash(x)=37519283) +1408 train 8.329896 (lr=1.7331e-04) (hash(x)=33716930) +1409 train 7.514571 (lr=1.7326e-04) (hash(x)=23392584) +1410 train 7.888465 (lr=1.7322e-04) (hash(x)=22877779) +1411 train 8.214800 (lr=1.7318e-04) (hash(x)=20564397) +1412 train 7.678931 (lr=1.7314e-04) (hash(x)=24366235) +1413 train 7.583693 (lr=1.7310e-04) (hash(x)=27065499) +1414 train 7.469943 (lr=1.7305e-04) (hash(x)=26844114) +1415 train 7.582291 (lr=1.7301e-04) (hash(x)=25141945) +1416 train 7.775026 (lr=1.7297e-04) (hash(x)=28813116) +1417 train 7.557521 (lr=1.7293e-04) (hash(x)=25466598) +1418 train 7.439490 (lr=1.7289e-04) (hash(x)=22800032) +1419 train 7.488641 (lr=1.7284e-04) (hash(x)=22717866) +1420 train 8.015751 (lr=1.7280e-04) (hash(x)=28040763) +1421 train 8.102727 (lr=1.7276e-04) (hash(x)=29648992) +1422 train 8.062004 (lr=1.7272e-04) (hash(x)=31747228) +1423 train 7.546941 (lr=1.7267e-04) (hash(x)=28527939) +1424 train 7.469959 (lr=1.7263e-04) (hash(x)=21563992) +1425 train 7.420429 (lr=1.7259e-04) (hash(x)=25134784) +1426 train 7.641141 (lr=1.7255e-04) (hash(x)=28442823) +1427 train 8.129983 (lr=1.7251e-04) (hash(x)=32757059) +1428 train 7.347173 (lr=1.7246e-04) (hash(x)=24110500) +1429 train 7.499123 (lr=1.7242e-04) (hash(x)=24145729) +1430 train 7.453495 (lr=1.7238e-04) (hash(x)=23541086) +1431 train 7.320953 (lr=1.7234e-04) (hash(x)=21942471) +1432 train 7.471940 (lr=1.7229e-04) (hash(x)=24736836) +1433 train 7.582859 (lr=1.7225e-04) (hash(x)=25325444) +1434 train 7.595211 (lr=1.7221e-04) (hash(x)=25188954) +1435 train 8.189535 (lr=1.7217e-04) (hash(x)=24247339) +1436 train 7.654197 (lr=1.7212e-04) (hash(x)=23773363) +1437 train 7.344107 (lr=1.7208e-04) (hash(x)=24142989) +1438 train 7.370773 (lr=1.7204e-04) (hash(x)=24226952) +1439 train 7.550502 (lr=1.7199e-04) (hash(x)=24955630) +1440 train 7.524097 (lr=1.7195e-04) (hash(x)=24563233) +1441 train 7.642963 (lr=1.7191e-04) (hash(x)=25491335) +1442 train 7.989816 (lr=1.7187e-04) (hash(x)=33253763) +1443 train 7.417467 (lr=1.7182e-04) (hash(x)=21368780) +1444 train 7.463522 (lr=1.7178e-04) (hash(x)=26615500) +1445 train 7.665120 (lr=1.7174e-04) (hash(x)=27146278) +1446 train 7.514490 (lr=1.7170e-04) (hash(x)=25904861) +1447 train 7.385544 (lr=1.7165e-04) (hash(x)=25541230) +1448 train 7.519307 (lr=1.7161e-04) (hash(x)=25434227) +1449 train 7.505417 (lr=1.7157e-04) (hash(x)=25375355) +1450 val loss 7.4892 +1450 val perplexity 1788.5355 +1450 train 7.351310 (lr=1.7152e-04) (hash(x)=21921129) +1451 train 7.344995 (lr=1.7148e-04) (hash(x)=23098806) +1452 train 7.402469 (lr=1.7144e-04) (hash(x)=22000544) +1453 train 7.313705 (lr=1.7139e-04) (hash(x)=22061174) +1454 train 7.374973 (lr=1.7135e-04) (hash(x)=24326286) +1455 train 7.390938 (lr=1.7131e-04) (hash(x)=23501481) +1456 train 7.582948 (lr=1.7126e-04) (hash(x)=26397938) +1457 train 7.545494 (lr=1.7122e-04) (hash(x)=24656430) +1458 train 7.310643 (lr=1.7118e-04) (hash(x)=23494971) +1459 train 7.361117 (lr=1.7114e-04) (hash(x)=23802681) +1460 train 7.399655 (lr=1.7109e-04) (hash(x)=21990153) +1461 train 7.412168 (lr=1.7105e-04) (hash(x)=23496118) +1462 train 7.387212 (lr=1.7101e-04) (hash(x)=24233822) +1463 train 7.683971 (lr=1.7096e-04) (hash(x)=22754988) +1464 train 7.420976 (lr=1.7092e-04) (hash(x)=23116635) +1465 train 7.154424 (lr=1.7088e-04) (hash(x)=21461650) +1466 train 7.276817 (lr=1.7083e-04) (hash(x)=22274473) +1467 train 7.343991 (lr=1.7079e-04) (hash(x)=22183009) +1468 train 7.562062 (lr=1.7075e-04) (hash(x)=24972441) +1469 train 7.335395 (lr=1.7070e-04) (hash(x)=22300616) +1470 train 7.136159 (lr=1.7066e-04) (hash(x)=21443060) +1471 train 7.389680 (lr=1.7061e-04) (hash(x)=23475070) +1472 train 7.300659 (lr=1.7057e-04) (hash(x)=22316810) +1473 train 7.710475 (lr=1.7053e-04) (hash(x)=24508407) +1474 train 7.680329 (lr=1.7048e-04) (hash(x)=24603557) +1475 train 7.379530 (lr=1.7044e-04) (hash(x)=23359061) +1476 train 7.415578 (lr=1.7040e-04) (hash(x)=22950844) +1477 train 7.498379 (lr=1.7035e-04) (hash(x)=22588667) +1478 train 7.601573 (lr=1.7031e-04) (hash(x)=26083526) +1479 train 7.512424 (lr=1.7027e-04) (hash(x)=23609959) +1480 train 7.512996 (lr=1.7022e-04) (hash(x)=24088171) +1481 train 7.510700 (lr=1.7018e-04) (hash(x)=25394852) +1482 train 7.442501 (lr=1.7013e-04) (hash(x)=24503040) +1483 train 7.210845 (lr=1.7009e-04) (hash(x)=22408449) +1484 train 7.505135 (lr=1.7005e-04) (hash(x)=25069325) +1485 train 7.500066 (lr=1.7000e-04) (hash(x)=26947398) +1486 train 7.021222 (lr=1.6996e-04) (hash(x)=17527161) +1487 train 7.383518 (lr=1.6991e-04) (hash(x)=23441847) +1488 train 7.396881 (lr=1.6987e-04) (hash(x)=25592861) +1489 train 7.316556 (lr=1.6983e-04) (hash(x)=23101350) +1490 train 7.296989 (lr=1.6978e-04) (hash(x)=24201380) +1491 train 7.413137 (lr=1.6974e-04) (hash(x)=23676365) +1492 train 7.495236 (lr=1.6969e-04) (hash(x)=26668088) +1493 train 7.626526 (lr=1.6965e-04) (hash(x)=26488811) +1494 train 7.595590 (lr=1.6961e-04) (hash(x)=27248109) +1495 train 7.627043 (lr=1.6956e-04) (hash(x)=23096292) +1496 train 7.576032 (lr=1.6952e-04) (hash(x)=22101981) +1497 train 7.696577 (lr=1.6947e-04) (hash(x)=24512380) +1498 train 7.529018 (lr=1.6943e-04) (hash(x)=25367738) +1499 train 7.526918 (lr=1.6939e-04) (hash(x)=27706294) +1500 val loss 7.4812 +1500 val perplexity 1774.3285 +1500 train 7.601366 (lr=1.6934e-04) (hash(x)=24154026) +1501 train 7.328624 (lr=1.6930e-04) (hash(x)=21892472) +1502 train 7.388885 (lr=1.6925e-04) (hash(x)=23662543) +1503 train 7.464120 (lr=1.6921e-04) (hash(x)=26171093) +1504 train 7.518772 (lr=1.6916e-04) (hash(x)=25974292) +1505 train 7.364701 (lr=1.6912e-04) (hash(x)=23191101) +1506 train 7.604065 (lr=1.6907e-04) (hash(x)=26498861) +1507 train 8.079084 (lr=1.6903e-04) (hash(x)=34946941) +1508 train 7.736268 (lr=1.6899e-04) (hash(x)=25442719) +1509 train 7.540930 (lr=1.6894e-04) (hash(x)=25569942) +1510 train 7.217131 (lr=1.6890e-04) (hash(x)=21265828) +1511 train 7.131653 (lr=1.6885e-04) (hash(x)=20060838) +1512 train 7.328359 (lr=1.6881e-04) (hash(x)=22588251) +1513 train 7.329296 (lr=1.6876e-04) (hash(x)=24581020) +1514 train 7.334812 (lr=1.6872e-04) (hash(x)=21882493) +1515 train 7.315303 (lr=1.6867e-04) (hash(x)=21591702) +1516 train 7.280536 (lr=1.6863e-04) (hash(x)=19813285) +1517 train 7.382616 (lr=1.6858e-04) (hash(x)=21870012) +1518 train 7.402910 (lr=1.6854e-04) (hash(x)=26895498) +1519 train 7.462294 (lr=1.6850e-04) (hash(x)=25451055) +1520 train 7.485951 (lr=1.6845e-04) (hash(x)=25395865) +1521 train 6.953722 (lr=1.6841e-04) (hash(x)=18989695) +1522 train 6.837862 (lr=1.6836e-04) (hash(x)=17040678) +1523 train 6.969522 (lr=1.6832e-04) (hash(x)=18691455) +1524 train 7.157720 (lr=1.6827e-04) (hash(x)=19017167) +1525 train 7.423235 (lr=1.6823e-04) (hash(x)=22406503) +1526 train 7.542374 (lr=1.6818e-04) (hash(x)=23036138) +1527 train 7.460960 (lr=1.6814e-04) (hash(x)=24934792) +1528 train 7.432519 (lr=1.6809e-04) (hash(x)=22843127) +1529 train 7.412536 (lr=1.6805e-04) (hash(x)=24249677) +1530 train 7.317975 (lr=1.6800e-04) (hash(x)=23318555) +1531 train 7.355708 (lr=1.6796e-04) (hash(x)=23864361) +1532 train 7.244712 (lr=1.6791e-04) (hash(x)=20242060) +1533 train 7.369148 (lr=1.6787e-04) (hash(x)=21549554) +1534 train 7.254011 (lr=1.6782e-04) (hash(x)=21642024) +1535 train 7.701389 (lr=1.6778e-04) (hash(x)=25367597) +1536 train 7.848870 (lr=1.6773e-04) (hash(x)=27224144) +1537 train 7.399079 (lr=1.6769e-04) (hash(x)=24409290) +1538 train 7.456886 (lr=1.6764e-04) (hash(x)=24987180) +1539 train 7.385472 (lr=1.6759e-04) (hash(x)=27016702) +1540 train 7.577886 (lr=1.6755e-04) (hash(x)=25819636) +1541 train 7.537833 (lr=1.6750e-04) (hash(x)=25520453) +1542 train 7.287468 (lr=1.6746e-04) (hash(x)=23580496) +1543 train 7.534531 (lr=1.6741e-04) (hash(x)=25022148) +1544 train 7.597484 (lr=1.6737e-04) (hash(x)=25447327) +1545 train 7.551069 (lr=1.6732e-04) (hash(x)=25010319) +1546 train 7.467079 (lr=1.6728e-04) (hash(x)=25511777) +1547 train 7.411705 (lr=1.6723e-04) (hash(x)=24459012) +1548 train 7.474686 (lr=1.6719e-04) (hash(x)=25082785) +1549 train 7.553277 (lr=1.6714e-04) (hash(x)=26528670) +1550 val loss 7.4844 +1550 val perplexity 1780.0876 +1550 train 7.498116 (lr=1.6710e-04) (hash(x)=26684367) +1551 train 7.449254 (lr=1.6705e-04) (hash(x)=25431365) +1552 train 7.415426 (lr=1.6700e-04) (hash(x)=24802747) +1553 train 7.280109 (lr=1.6696e-04) (hash(x)=24229522) +1554 train 7.469954 (lr=1.6691e-04) (hash(x)=24757176) +1555 train 7.591037 (lr=1.6687e-04) (hash(x)=25958785) +1556 train 7.597562 (lr=1.6682e-04) (hash(x)=26810735) +1557 train 7.244243 (lr=1.6678e-04) (hash(x)=22882640) +1558 train 7.671839 (lr=1.6673e-04) (hash(x)=27220057) +1559 train 7.941506 (lr=1.6668e-04) (hash(x)=29307788) +1560 train 7.416032 (lr=1.6664e-04) (hash(x)=25214030) +1561 train 7.251059 (lr=1.6659e-04) (hash(x)=23167825) +1562 train 7.351398 (lr=1.6655e-04) (hash(x)=24658511) +1563 train 7.493893 (lr=1.6650e-04) (hash(x)=24965435) +1564 train 7.277653 (lr=1.6646e-04) (hash(x)=23620579) +1565 train 7.261409 (lr=1.6641e-04) (hash(x)=23772949) +1566 train 7.394545 (lr=1.6636e-04) (hash(x)=23807939) +1567 train 7.604978 (lr=1.6632e-04) (hash(x)=25651929) +1568 train 7.526993 (lr=1.6627e-04) (hash(x)=25549933) +1569 train 7.269614 (lr=1.6623e-04) (hash(x)=23146724) +1570 train 7.349729 (lr=1.6618e-04) (hash(x)=24099275) +1571 train 7.564294 (lr=1.6613e-04) (hash(x)=28451031) +1572 train 7.634023 (lr=1.6609e-04) (hash(x)=25488511) +1573 train 7.454061 (lr=1.6604e-04) (hash(x)=23796771) +1574 train 7.498845 (lr=1.6600e-04) (hash(x)=22642764) +1575 train 7.591023 (lr=1.6595e-04) (hash(x)=26312387) +1576 train 7.441207 (lr=1.6590e-04) (hash(x)=22486223) +1577 train 7.414834 (lr=1.6586e-04) (hash(x)=21257377) +1578 train 7.527553 (lr=1.6581e-04) (hash(x)=24328365) +1579 train 7.583750 (lr=1.6576e-04) (hash(x)=25326650) +1580 train 7.506108 (lr=1.6572e-04) (hash(x)=26484837) +1581 train 7.290288 (lr=1.6567e-04) (hash(x)=24605603) +1582 train 7.410015 (lr=1.6563e-04) (hash(x)=24668537) +1583 train 7.327508 (lr=1.6558e-04) (hash(x)=23804913) +1584 train 7.610004 (lr=1.6553e-04) (hash(x)=23615391) +1585 train 7.565464 (lr=1.6549e-04) (hash(x)=24322926) +1586 train 7.395378 (lr=1.6544e-04) (hash(x)=19753104) +1587 train 7.758770 (lr=1.6539e-04) (hash(x)=25537529) +1588 train 7.233151 (lr=1.6535e-04) (hash(x)=22835476) +1589 train 7.390834 (lr=1.6530e-04) (hash(x)=25707197) +1590 train 7.370675 (lr=1.6525e-04) (hash(x)=24191203) +1591 train 7.605278 (lr=1.6521e-04) (hash(x)=26115519) +1592 train 7.486830 (lr=1.6516e-04) (hash(x)=25781547) +1593 train 7.325334 (lr=1.6512e-04) (hash(x)=24850654) +1594 train 7.277158 (lr=1.6507e-04) (hash(x)=23300928) +1595 train 7.483366 (lr=1.6502e-04) (hash(x)=25494804) +1596 train 7.520346 (lr=1.6498e-04) (hash(x)=28169410) +1597 train 7.245889 (lr=1.6493e-04) (hash(x)=21972022) +1598 train 7.800948 (lr=1.6488e-04) (hash(x)=27687290) +1599 train 7.666265 (lr=1.6484e-04) (hash(x)=23210747) +1600 val loss 7.4583 +1600 val perplexity 1734.1398 +1600 train 7.650438 (lr=1.6479e-04) (hash(x)=20362758) +1601 train 7.438220 (lr=1.6474e-04) (hash(x)=17064773) +1602 train 7.452606 (lr=1.6470e-04) (hash(x)=17173694) +1603 train 7.507311 (lr=1.6465e-04) (hash(x)=15717069) +1604 train 7.626447 (lr=1.6460e-04) (hash(x)=15117973) +1605 train 7.431843 (lr=1.6455e-04) (hash(x)=16189636) +1606 train 7.410262 (lr=1.6451e-04) (hash(x)=16552095) +1607 train 7.279168 (lr=1.6446e-04) (hash(x)=18463712) +1608 train 7.450971 (lr=1.6441e-04) (hash(x)=17572155) +1609 train 7.447827 (lr=1.6437e-04) (hash(x)=19970072) +1610 train 7.456465 (lr=1.6432e-04) (hash(x)=20463871) +1611 train 7.490855 (lr=1.6427e-04) (hash(x)=20705573) +1612 train 7.311301 (lr=1.6423e-04) (hash(x)=24441646) +1613 train 7.500128 (lr=1.6418e-04) (hash(x)=22913147) +1614 train 7.600305 (lr=1.6413e-04) (hash(x)=23081598) +1615 train 7.373859 (lr=1.6408e-04) (hash(x)=23245699) +1616 train 7.343280 (lr=1.6404e-04) (hash(x)=23003072) +1617 train 7.636830 (lr=1.6399e-04) (hash(x)=27121904) +1618 train 7.369911 (lr=1.6394e-04) (hash(x)=25092305) +1619 train 7.414686 (lr=1.6390e-04) (hash(x)=23444521) +1620 train 7.413704 (lr=1.6385e-04) (hash(x)=22130531) +1621 train 7.207078 (lr=1.6380e-04) (hash(x)=20917937) +1622 train 7.335964 (lr=1.6375e-04) (hash(x)=22526838) +1623 train 7.431499 (lr=1.6371e-04) (hash(x)=21770300) +1624 train 8.583829 (lr=1.6366e-04) (hash(x)=22333537) +1625 train 8.596271 (lr=1.6361e-04) (hash(x)=24642519) +1626 train 7.746205 (lr=1.6357e-04) (hash(x)=25199038) +1627 train 7.491199 (lr=1.6352e-04) (hash(x)=23334569) +1628 train 7.386453 (lr=1.6347e-04) (hash(x)=23785360) +1629 train 7.110973 (lr=1.6342e-04) (hash(x)=21796200) +1630 train 7.151086 (lr=1.6338e-04) (hash(x)=22389081) +1631 train 7.401006 (lr=1.6333e-04) (hash(x)=25387532) +1632 train 7.022634 (lr=1.6328e-04) (hash(x)=17247578) +1633 train 7.353024 (lr=1.6323e-04) (hash(x)=22203733) +1634 train 7.565408 (lr=1.6319e-04) (hash(x)=24387455) +1635 train 8.085174 (lr=1.6314e-04) (hash(x)=29466743) +1636 train 7.494256 (lr=1.6309e-04) (hash(x)=25354152) +1637 train 7.554764 (lr=1.6304e-04) (hash(x)=21756102) +1638 train 7.460011 (lr=1.6300e-04) (hash(x)=23544029) +1639 train 7.566226 (lr=1.6295e-04) (hash(x)=27718703) +1640 train 7.535486 (lr=1.6290e-04) (hash(x)=25697138) +1641 train 7.403035 (lr=1.6285e-04) (hash(x)=22978681) +1642 train 7.905775 (lr=1.6281e-04) (hash(x)=29527067) +1643 train 7.109387 (lr=1.6276e-04) (hash(x)=17631973) +1644 train 7.461477 (lr=1.6271e-04) (hash(x)=24860172) +1645 train 7.765110 (lr=1.6266e-04) (hash(x)=27947891) +1646 train 7.473409 (lr=1.6261e-04) (hash(x)=23819556) +1647 train 7.534935 (lr=1.6257e-04) (hash(x)=27661052) +1648 train 7.275224 (lr=1.6252e-04) (hash(x)=23014209) +1649 train 7.210765 (lr=1.6247e-04) (hash(x)=23061452) +1650 val loss 7.4639 +1650 val perplexity 1743.9397 +1650 train 7.342313 (lr=1.6242e-04) (hash(x)=21949051) +1651 train 7.370368 (lr=1.6238e-04) (hash(x)=22244096) +1652 train 7.370853 (lr=1.6233e-04) (hash(x)=25997585) +1653 train 7.482896 (lr=1.6228e-04) (hash(x)=25389713) +1654 train 7.432195 (lr=1.6223e-04) (hash(x)=24390520) +1655 train 7.650922 (lr=1.6218e-04) (hash(x)=26538928) +1656 train 7.546745 (lr=1.6214e-04) (hash(x)=28708088) +1657 train 7.672567 (lr=1.6209e-04) (hash(x)=25685569) +1658 train 7.205113 (lr=1.6204e-04) (hash(x)=22163531) +1659 train 7.361678 (lr=1.6199e-04) (hash(x)=26256802) +1660 train 7.786092 (lr=1.6194e-04) (hash(x)=30016026) +1661 train 7.435150 (lr=1.6189e-04) (hash(x)=24412323) +1662 train 7.541714 (lr=1.6185e-04) (hash(x)=24722307) +1663 train 7.441422 (lr=1.6180e-04) (hash(x)=21772654) +1664 train 7.356751 (lr=1.6175e-04) (hash(x)=24984527) +1665 train 7.417503 (lr=1.6170e-04) (hash(x)=25456825) +1666 train 7.753764 (lr=1.6165e-04) (hash(x)=24383976) +1667 train 7.696259 (lr=1.6161e-04) (hash(x)=25026277) +1668 train 7.618027 (lr=1.6156e-04) (hash(x)=28121715) +1669 train 7.624944 (lr=1.6151e-04) (hash(x)=26855439) +1670 train 7.654987 (lr=1.6146e-04) (hash(x)=33370924) +1671 train 7.564973 (lr=1.6141e-04) (hash(x)=26263254) +1672 train 7.947171 (lr=1.6136e-04) (hash(x)=29958158) +1673 train 7.316991 (lr=1.6132e-04) (hash(x)=21917396) +1674 train 7.427911 (lr=1.6127e-04) (hash(x)=24196295) +1675 train 7.466362 (lr=1.6122e-04) (hash(x)=24726314) +1676 train 7.235260 (lr=1.6117e-04) (hash(x)=22137742) +1677 train 7.411915 (lr=1.6112e-04) (hash(x)=24375100) +1678 train 7.338532 (lr=1.6107e-04) (hash(x)=23965039) +1679 train 7.385644 (lr=1.6103e-04) (hash(x)=23552356) +1680 train 7.343307 (lr=1.6098e-04) (hash(x)=26136969) +1681 train 7.594827 (lr=1.6093e-04) (hash(x)=25343112) +1682 train 7.316196 (lr=1.6088e-04) (hash(x)=22831508) +1683 train 7.536129 (lr=1.6083e-04) (hash(x)=26699819) +1684 train 7.673690 (lr=1.6078e-04) (hash(x)=25435504) +1685 train 7.820609 (lr=1.6073e-04) (hash(x)=25218858) +1686 train 8.434452 (lr=1.6068e-04) (hash(x)=25664448) +1687 train 7.500242 (lr=1.6064e-04) (hash(x)=22707141) +1688 train 7.634827 (lr=1.6059e-04) (hash(x)=28001383) +1689 train 7.853843 (lr=1.6054e-04) (hash(x)=29168269) +1690 train 7.814233 (lr=1.6049e-04) (hash(x)=29637522) +1691 train 7.817879 (lr=1.6044e-04) (hash(x)=25676149) +1692 train 7.334581 (lr=1.6039e-04) (hash(x)=20919831) +1693 train 7.489621 (lr=1.6034e-04) (hash(x)=24324401) +1694 train 7.544212 (lr=1.6029e-04) (hash(x)=26862625) +1695 train 7.889121 (lr=1.6025e-04) (hash(x)=34234481) +1696 train 7.505029 (lr=1.6020e-04) (hash(x)=27415195) +1697 train 7.377965 (lr=1.6015e-04) (hash(x)=24511386) +1698 train 7.516170 (lr=1.6010e-04) (hash(x)=26904299) +1699 train 7.368928 (lr=1.6005e-04) (hash(x)=25401624) +1700 val loss 7.5008 +1700 val perplexity 1809.5759 +1700 train 7.466300 (lr=1.6000e-04) (hash(x)=26498489) +1701 train 7.424204 (lr=1.5995e-04) (hash(x)=22340685) +1702 train 7.513387 (lr=1.5990e-04) (hash(x)=26396757) +1703 train 8.048815 (lr=1.5985e-04) (hash(x)=35008670) +1704 train 7.826347 (lr=1.5981e-04) (hash(x)=31782020) +1705 train 7.707675 (lr=1.5976e-04) (hash(x)=29662286) +1706 train 7.848071 (lr=1.5971e-04) (hash(x)=34215782) +1707 train 7.388251 (lr=1.5966e-04) (hash(x)=25682280) +1708 train 7.663765 (lr=1.5961e-04) (hash(x)=27109048) +1709 train 7.739820 (lr=1.5956e-04) (hash(x)=27686498) +1710 train 7.506961 (lr=1.5951e-04) (hash(x)=24247565) +1711 train 7.543440 (lr=1.5946e-04) (hash(x)=25891543) +1712 train 7.633829 (lr=1.5941e-04) (hash(x)=26436778) +1713 train 7.324903 (lr=1.5936e-04) (hash(x)=22538881) +1714 train 7.305013 (lr=1.5931e-04) (hash(x)=21993512) +1715 train 7.699031 (lr=1.5926e-04) (hash(x)=25962407) +1716 train 7.462497 (lr=1.5921e-04) (hash(x)=24130284) +1717 train 7.331148 (lr=1.5917e-04) (hash(x)=24819073) +1718 train 7.231046 (lr=1.5912e-04) (hash(x)=23496648) +1719 train 7.320697 (lr=1.5907e-04) (hash(x)=21971224) +1720 train 7.192762 (lr=1.5902e-04) (hash(x)=21498081) +1721 train 7.255573 (lr=1.5897e-04) (hash(x)=20951317) +1722 train 7.783933 (lr=1.5892e-04) (hash(x)=28848134) +1723 train 7.781991 (lr=1.5887e-04) (hash(x)=30838142) +1724 train 7.752496 (lr=1.5882e-04) (hash(x)=28844392) +1725 train 7.364082 (lr=1.5877e-04) (hash(x)=23102419) +1726 train 7.410283 (lr=1.5872e-04) (hash(x)=22374479) +1727 train 7.635931 (lr=1.5867e-04) (hash(x)=27312186) +1728 train 7.907679 (lr=1.5862e-04) (hash(x)=34362559) +1729 train 7.804239 (lr=1.5857e-04) (hash(x)=30920030) +1730 train 7.283072 (lr=1.5852e-04) (hash(x)=23684126) +1731 train 7.493563 (lr=1.5847e-04) (hash(x)=23657081) +1732 train 7.662784 (lr=1.5842e-04) (hash(x)=28463299) +1733 train 7.881268 (lr=1.5837e-04) (hash(x)=35351214) +1734 train 7.506760 (lr=1.5832e-04) (hash(x)=28855662) +1735 train 7.145015 (lr=1.5827e-04) (hash(x)=22163749) +1736 train 7.142571 (lr=1.5822e-04) (hash(x)=22024585) +1737 train 7.258577 (lr=1.5817e-04) (hash(x)=24629160) +1738 train 7.356951 (lr=1.5812e-04) (hash(x)=25220941) +1739 train 7.313465 (lr=1.5808e-04) (hash(x)=24829818) +1740 train 7.649757 (lr=1.5803e-04) (hash(x)=28453898) +1741 train 7.740860 (lr=1.5798e-04) (hash(x)=25424550) +1742 train 7.403226 (lr=1.5793e-04) (hash(x)=23437814) +1743 train 7.451754 (lr=1.5788e-04) (hash(x)=25942888) +1744 train 7.431355 (lr=1.5783e-04) (hash(x)=24503801) +1745 train 7.687958 (lr=1.5778e-04) (hash(x)=26418501) +1746 train 7.559010 (lr=1.5773e-04) (hash(x)=27177691) +1747 train 7.306326 (lr=1.5768e-04) (hash(x)=23785671) +1748 train 7.695742 (lr=1.5763e-04) (hash(x)=27362772) +1749 train 7.489478 (lr=1.5758e-04) (hash(x)=25097859) +1750 val loss 7.4461 +1750 val perplexity 1713.1863 +1750 train 7.404180 (lr=1.5753e-04) (hash(x)=24662466) +1751 train 7.313100 (lr=1.5748e-04) (hash(x)=25493916) +1752 train 7.447713 (lr=1.5743e-04) (hash(x)=24655868) +1753 train 7.754603 (lr=1.5738e-04) (hash(x)=19819210) +1754 train 7.308534 (lr=1.5733e-04) (hash(x)=21377155) +1755 train 8.114079 (lr=1.5728e-04) (hash(x)=28618702) +1756 train 8.028522 (lr=1.5723e-04) (hash(x)=27324953) +1757 train 7.743896 (lr=1.5718e-04) (hash(x)=29707907) +1758 train 7.548435 (lr=1.5713e-04) (hash(x)=24485921) +1759 train 7.615674 (lr=1.5708e-04) (hash(x)=24289951) +1760 train 7.315845 (lr=1.5702e-04) (hash(x)=22496716) +1761 train 7.455164 (lr=1.5697e-04) (hash(x)=25147026) +1762 train 7.551529 (lr=1.5692e-04) (hash(x)=26851828) +1763 train 7.477766 (lr=1.5687e-04) (hash(x)=26331486) +1764 train 7.346273 (lr=1.5682e-04) (hash(x)=24383054) +1765 train 7.577478 (lr=1.5677e-04) (hash(x)=25885126) +1766 train 7.492454 (lr=1.5672e-04) (hash(x)=25848470) +1767 train 7.311540 (lr=1.5667e-04) (hash(x)=23648671) +1768 train 7.305799 (lr=1.5662e-04) (hash(x)=23168674) +1769 train 7.170887 (lr=1.5657e-04) (hash(x)=20252079) +1770 train 7.388121 (lr=1.5652e-04) (hash(x)=23914287) +1771 train 7.634792 (lr=1.5647e-04) (hash(x)=27292797) +1772 train 6.966623 (lr=1.5642e-04) (hash(x)=16175151) +1773 train 7.066080 (lr=1.5637e-04) (hash(x)=18317379) +1774 train 7.365691 (lr=1.5632e-04) (hash(x)=24464271) +1775 train 7.335898 (lr=1.5627e-04) (hash(x)=24992055) +1776 train 7.966716 (lr=1.5622e-04) (hash(x)=26032451) +1777 train 7.714855 (lr=1.5617e-04) (hash(x)=24734221) +1778 train 7.747357 (lr=1.5612e-04) (hash(x)=25413430) +1779 train 7.584229 (lr=1.5607e-04) (hash(x)=24398330) +1780 train 7.457108 (lr=1.5602e-04) (hash(x)=24568049) +1781 train 7.347441 (lr=1.5597e-04) (hash(x)=23573984) +1782 train 7.530836 (lr=1.5592e-04) (hash(x)=27338410) +1783 train 7.488903 (lr=1.5586e-04) (hash(x)=26005549) +1784 train 7.374824 (lr=1.5581e-04) (hash(x)=24332331) +1785 train 7.186195 (lr=1.5576e-04) (hash(x)=22583878) +1786 train 7.363150 (lr=1.5571e-04) (hash(x)=24599113) +1787 train 7.807585 (lr=1.5566e-04) (hash(x)=30259737) +1788 train 7.580136 (lr=1.5561e-04) (hash(x)=26504237) +1789 train 7.440670 (lr=1.5556e-04) (hash(x)=25196470) +1790 train 7.347418 (lr=1.5551e-04) (hash(x)=23607871) +1791 train 7.271036 (lr=1.5546e-04) (hash(x)=21046554) +1792 train 7.529700 (lr=1.5541e-04) (hash(x)=27285635) +1793 train 7.472217 (lr=1.5536e-04) (hash(x)=25454371) +1794 train 7.554303 (lr=1.5531e-04) (hash(x)=26486575) +1795 train 7.058809 (lr=1.5525e-04) (hash(x)=18773877) +1796 train 7.225829 (lr=1.5520e-04) (hash(x)=22506761) +1797 train 7.462791 (lr=1.5515e-04) (hash(x)=24645168) +1798 train 7.495488 (lr=1.5510e-04) (hash(x)=25046236) +1799 train 7.592740 (lr=1.5505e-04) (hash(x)=26321539) +1800 val loss 7.4395 +1800 val perplexity 1701.8274 +1800 train 7.357141 (lr=1.5500e-04) (hash(x)=24602494) +1801 train 7.551228 (lr=1.5495e-04) (hash(x)=25722713) +1802 train 7.308655 (lr=1.5490e-04) (hash(x)=23711219) +1803 train 7.419583 (lr=1.5485e-04) (hash(x)=22850804) +1804 train 7.730902 (lr=1.5480e-04) (hash(x)=25829388) +1805 train 7.277222 (lr=1.5474e-04) (hash(x)=22503524) +1806 train 7.536218 (lr=1.5469e-04) (hash(x)=26669453) +1807 train 7.462619 (lr=1.5464e-04) (hash(x)=27807872) +1808 train 7.477150 (lr=1.5459e-04) (hash(x)=23543560) +1809 train 7.593819 (lr=1.5454e-04) (hash(x)=25845590) +1810 train 7.423265 (lr=1.5449e-04) (hash(x)=23026635) +1811 train 7.404869 (lr=1.5444e-04) (hash(x)=25545137) +1812 train 7.857344 (lr=1.5439e-04) (hash(x)=27746841) +1813 train 7.271920 (lr=1.5434e-04) (hash(x)=25471231) +1814 train 7.406534 (lr=1.5428e-04) (hash(x)=24333204) +1815 train 7.236687 (lr=1.5423e-04) (hash(x)=21555364) +1816 train 7.448247 (lr=1.5418e-04) (hash(x)=26317977) +1817 train 7.498670 (lr=1.5413e-04) (hash(x)=24474988) +1818 train 7.271751 (lr=1.5408e-04) (hash(x)=21975953) +1819 train 7.774630 (lr=1.5403e-04) (hash(x)=27243798) +1820 train 7.409393 (lr=1.5398e-04) (hash(x)=25097367) +1821 train 7.373831 (lr=1.5392e-04) (hash(x)=24419085) +1822 train 7.291867 (lr=1.5387e-04) (hash(x)=23058837) +1823 train 7.410224 (lr=1.5382e-04) (hash(x)=26325324) +1824 train 7.159225 (lr=1.5377e-04) (hash(x)=20581023) +1825 train 7.482697 (lr=1.5372e-04) (hash(x)=24822111) +1826 train 7.293607 (lr=1.5367e-04) (hash(x)=24336304) +1827 train 7.466261 (lr=1.5362e-04) (hash(x)=26228728) +1828 train 7.571012 (lr=1.5356e-04) (hash(x)=26445781) +1829 train 7.576034 (lr=1.5351e-04) (hash(x)=24707042) +1830 train 7.835158 (lr=1.5346e-04) (hash(x)=27882744) +1831 train 7.392812 (lr=1.5341e-04) (hash(x)=24956294) +1832 train 7.254492 (lr=1.5336e-04) (hash(x)=20984728) +1833 train 7.233158 (lr=1.5331e-04) (hash(x)=23424737) +1834 train 7.631618 (lr=1.5325e-04) (hash(x)=26207120) +1835 train 7.611148 (lr=1.5320e-04) (hash(x)=25592289) +1836 train 7.297101 (lr=1.5315e-04) (hash(x)=24326649) +1837 train 7.480600 (lr=1.5310e-04) (hash(x)=26826109) +1838 train 7.417397 (lr=1.5305e-04) (hash(x)=24759294) +1839 train 7.419116 (lr=1.5300e-04) (hash(x)=24429389) +1840 train 7.400369 (lr=1.5294e-04) (hash(x)=25537519) +1841 train 7.394660 (lr=1.5289e-04) (hash(x)=24747421) +1842 train 7.273558 (lr=1.5284e-04) (hash(x)=23079065) +1843 train 7.673758 (lr=1.5279e-04) (hash(x)=28733708) +1844 train 7.416669 (lr=1.5274e-04) (hash(x)=23937742) +1845 train 7.691936 (lr=1.5269e-04) (hash(x)=29704803) +1846 train 7.855667 (lr=1.5263e-04) (hash(x)=34617155) +1847 train 7.570529 (lr=1.5258e-04) (hash(x)=27929846) +1848 train 7.912138 (lr=1.5253e-04) (hash(x)=28280878) +1849 train 7.064165 (lr=1.5248e-04) (hash(x)=18961171) +1850 val loss 7.4618 +1850 val perplexity 1740.2762 +1850 train 7.543828 (lr=1.5243e-04) (hash(x)=27146015) +1851 train 7.351551 (lr=1.5237e-04) (hash(x)=22417476) +1852 train 7.494110 (lr=1.5232e-04) (hash(x)=24583152) +1853 train 7.516623 (lr=1.5227e-04) (hash(x)=26364120) +1854 train 7.695019 (lr=1.5222e-04) (hash(x)=25946767) +1855 train 7.489197 (lr=1.5217e-04) (hash(x)=25282897) +1856 train 7.481834 (lr=1.5211e-04) (hash(x)=25154557) +1857 train 7.184819 (lr=1.5206e-04) (hash(x)=22082503) +1858 train 7.195578 (lr=1.5201e-04) (hash(x)=23974606) +1859 train 7.358536 (lr=1.5196e-04) (hash(x)=22278062) +1860 train 7.216318 (lr=1.5191e-04) (hash(x)=19509639) +1861 train 7.543610 (lr=1.5185e-04) (hash(x)=24271468) +1862 train 7.150296 (lr=1.5180e-04) (hash(x)=21943809) +1863 train 7.392880 (lr=1.5175e-04) (hash(x)=26802508) +1864 train 7.976118 (lr=1.5170e-04) (hash(x)=34178409) +1865 train 8.055609 (lr=1.5164e-04) (hash(x)=33468379) +1866 train 7.264576 (lr=1.5159e-04) (hash(x)=22109262) +1867 train 7.102787 (lr=1.5154e-04) (hash(x)=22094832) +1868 train 7.291779 (lr=1.5149e-04) (hash(x)=24016953) +1869 train 7.564445 (lr=1.5144e-04) (hash(x)=26759850) +1870 train 7.421271 (lr=1.5138e-04) (hash(x)=23570779) +1871 train 7.763182 (lr=1.5133e-04) (hash(x)=28390416) +1872 train 7.745191 (lr=1.5128e-04) (hash(x)=26215770) +1873 train 7.602341 (lr=1.5123e-04) (hash(x)=22727956) +1874 train 7.446147 (lr=1.5117e-04) (hash(x)=21304587) +1875 train 7.737979 (lr=1.5112e-04) (hash(x)=26379331) +1876 train 7.816030 (lr=1.5107e-04) (hash(x)=25252419) +1877 train 7.667572 (lr=1.5102e-04) (hash(x)=25048158) +1878 train 7.599309 (lr=1.5096e-04) (hash(x)=23588991) +1879 train 7.582271 (lr=1.5091e-04) (hash(x)=26292451) +1880 train 7.459917 (lr=1.5086e-04) (hash(x)=23617086) +1881 train 7.371318 (lr=1.5081e-04) (hash(x)=23336031) +1882 train 7.401620 (lr=1.5075e-04) (hash(x)=19198742) +1883 train 8.084235 (lr=1.5070e-04) (hash(x)=26301866) +1884 train 8.027652 (lr=1.5065e-04) (hash(x)=30114703) +1885 train 7.572943 (lr=1.5060e-04) (hash(x)=26687040) +1886 train 7.422828 (lr=1.5054e-04) (hash(x)=25810717) +1887 train 7.257200 (lr=1.5049e-04) (hash(x)=22915344) +1888 train 7.548178 (lr=1.5044e-04) (hash(x)=27046189) +1889 train 7.100745 (lr=1.5039e-04) (hash(x)=19831900) +1890 train 7.522078 (lr=1.5033e-04) (hash(x)=27786987) +1891 train 7.402170 (lr=1.5028e-04) (hash(x)=25448318) +1892 train 7.425524 (lr=1.5023e-04) (hash(x)=25166953) +1893 train 7.409303 (lr=1.5018e-04) (hash(x)=24993116) +1894 train 7.471789 (lr=1.5012e-04) (hash(x)=25748002) +1895 train 7.659554 (lr=1.5007e-04) (hash(x)=24744383) +1896 train 7.387191 (lr=1.5002e-04) (hash(x)=25560120) +1897 train 7.238616 (lr=1.4996e-04) (hash(x)=23731849) +1898 train 7.272869 (lr=1.4991e-04) (hash(x)=24115851) +1899 train 7.293686 (lr=1.4986e-04) (hash(x)=22835201) +1900 val loss 7.4141 +1900 val perplexity 1659.1538 +1900 train 7.080648 (lr=1.4981e-04) (hash(x)=21927896) +1901 train 7.426693 (lr=1.4975e-04) (hash(x)=24652361) +1902 train 7.590089 (lr=1.4970e-04) (hash(x)=27332405) +1903 train 7.420166 (lr=1.4965e-04) (hash(x)=26284678) +1904 train 7.389656 (lr=1.4959e-04) (hash(x)=23441305) +1905 train 7.471706 (lr=1.4954e-04) (hash(x)=27522881) +1906 train 7.510664 (lr=1.4949e-04) (hash(x)=25521191) +1907 train 7.290953 (lr=1.4944e-04) (hash(x)=24745936) +1908 train 7.216285 (lr=1.4938e-04) (hash(x)=21653364) +1909 train 7.249771 (lr=1.4933e-04) (hash(x)=21973969) +1910 train 7.282971 (lr=1.4928e-04) (hash(x)=24318192) +1911 train 7.220603 (lr=1.4922e-04) (hash(x)=21654269) +1912 train 7.281548 (lr=1.4917e-04) (hash(x)=24142904) +1913 train 7.182055 (lr=1.4912e-04) (hash(x)=21708739) +1914 train 7.380574 (lr=1.4906e-04) (hash(x)=22937923) +1915 train 7.943425 (lr=1.4901e-04) (hash(x)=32387999) +1916 train 8.109539 (lr=1.4896e-04) (hash(x)=28958671) +1917 train 8.162799 (lr=1.4891e-04) (hash(x)=32662682) +1918 train 8.067157 (lr=1.4885e-04) (hash(x)=31364539) +1919 train 8.124600 (lr=1.4880e-04) (hash(x)=29466268) +1920 train 8.102570 (lr=1.4875e-04) (hash(x)=31407564) +1921 train 7.950414 (lr=1.4869e-04) (hash(x)=28372973) +1922 train 8.057078 (lr=1.4864e-04) (hash(x)=28620993) +1923 train 8.078952 (lr=1.4859e-04) (hash(x)=30736727) +1924 train 8.044124 (lr=1.4853e-04) (hash(x)=30370374) +1925 train 7.962939 (lr=1.4848e-04) (hash(x)=29935562) +1926 train 7.976053 (lr=1.4843e-04) (hash(x)=30528627) +1927 train 7.972473 (lr=1.4837e-04) (hash(x)=32616762) +1928 train 7.819488 (lr=1.4832e-04) (hash(x)=29150044) +1929 train 8.005696 (lr=1.4827e-04) (hash(x)=32861403) +1930 train 7.949023 (lr=1.4821e-04) (hash(x)=31053918) +1931 train 7.875083 (lr=1.4816e-04) (hash(x)=29358578) +1932 train 7.934309 (lr=1.4811e-04) (hash(x)=31521292) +1933 train 7.896264 (lr=1.4805e-04) (hash(x)=31218966) +1934 train 7.897098 (lr=1.4800e-04) (hash(x)=31811872) +1935 train 8.056424 (lr=1.4795e-04) (hash(x)=32201138) +1936 train 7.826445 (lr=1.4789e-04) (hash(x)=28631348) +1937 train 7.901677 (lr=1.4784e-04) (hash(x)=30545133) +1938 train 7.949484 (lr=1.4779e-04) (hash(x)=32136080) +1939 train 8.035228 (lr=1.4773e-04) (hash(x)=30041621) +1940 train 7.807034 (lr=1.4768e-04) (hash(x)=30537181) +1941 train 7.821217 (lr=1.4763e-04) (hash(x)=30371023) +1942 train 7.964223 (lr=1.4757e-04) (hash(x)=30734634) +1943 train 7.868003 (lr=1.4752e-04) (hash(x)=33683468) +1944 train 7.918496 (lr=1.4747e-04) (hash(x)=30472451) +1945 train 7.775551 (lr=1.4741e-04) (hash(x)=29809830) +1946 train 7.568110 (lr=1.4736e-04) (hash(x)=26077593) +1947 train 7.578279 (lr=1.4730e-04) (hash(x)=26837755) +1948 train 7.579106 (lr=1.4725e-04) (hash(x)=23910920) +1949 train 7.596046 (lr=1.4720e-04) (hash(x)=26084089) +1950 val loss 7.5538 +1950 val perplexity 1908.0314 +1950 train 7.726337 (lr=1.4714e-04) (hash(x)=26963533) +1951 train 7.608400 (lr=1.4709e-04) (hash(x)=27498125) +1952 train 7.724641 (lr=1.4704e-04) (hash(x)=29512508) +1953 train 7.910314 (lr=1.4698e-04) (hash(x)=34478395) +1954 train 7.683721 (lr=1.4693e-04) (hash(x)=25357046) +1955 train 7.485549 (lr=1.4688e-04) (hash(x)=22372507) +1956 train 7.414316 (lr=1.4682e-04) (hash(x)=24501779) +1957 train 7.492435 (lr=1.4677e-04) (hash(x)=25638879) +1958 train 7.358984 (lr=1.4671e-04) (hash(x)=24243109) +1959 train 7.315471 (lr=1.4666e-04) (hash(x)=25164318) +1960 train 7.468840 (lr=1.4661e-04) (hash(x)=24139533) +1961 train 7.448295 (lr=1.4655e-04) (hash(x)=27271900) +1962 train 7.321925 (lr=1.4650e-04) (hash(x)=24869232) +1963 train 7.518537 (lr=1.4644e-04) (hash(x)=26562947) +1964 train 7.430706 (lr=1.4639e-04) (hash(x)=26477326) +1965 train 7.503629 (lr=1.4634e-04) (hash(x)=24917192) +1966 train 7.271244 (lr=1.4628e-04) (hash(x)=23110147) +1967 train 7.432177 (lr=1.4623e-04) (hash(x)=25690221) +1968 train 7.794334 (lr=1.4618e-04) (hash(x)=26999273) +1969 train 7.433342 (lr=1.4612e-04) (hash(x)=24807841) +1970 train 7.352280 (lr=1.4607e-04) (hash(x)=23918831) +1971 train 7.336047 (lr=1.4601e-04) (hash(x)=21947305) +1972 train 7.408524 (lr=1.4596e-04) (hash(x)=22874486) +1973 train 7.324978 (lr=1.4591e-04) (hash(x)=22195089) +1974 train 7.416095 (lr=1.4585e-04) (hash(x)=25345359) +1975 train 7.507318 (lr=1.4580e-04) (hash(x)=29031550) +1976 train 7.504421 (lr=1.4574e-04) (hash(x)=29947423) +1977 train 7.710368 (lr=1.4569e-04) (hash(x)=29395823) +1978 train 7.467381 (lr=1.4564e-04) (hash(x)=26968216) +1979 train 7.536160 (lr=1.4558e-04) (hash(x)=26551589) +1980 train 7.493221 (lr=1.4553e-04) (hash(x)=25657210) +1981 train 7.455242 (lr=1.4547e-04) (hash(x)=23689487) +1982 train 7.529329 (lr=1.4542e-04) (hash(x)=25744240) +1983 train 7.550536 (lr=1.4536e-04) (hash(x)=24094093) +1984 train 7.318515 (lr=1.4531e-04) (hash(x)=21724872) +1985 train 7.347073 (lr=1.4526e-04) (hash(x)=24106453) +1986 train 7.356104 (lr=1.4520e-04) (hash(x)=25004577) +1987 train 7.378625 (lr=1.4515e-04) (hash(x)=23639076) +1988 train 7.631131 (lr=1.4509e-04) (hash(x)=29408797) +1989 train 7.279614 (lr=1.4504e-04) (hash(x)=25107314) +1990 train 9.951433 (lr=1.4498e-04) (hash(x)=49896019) +1991 train 11.485460 (lr=1.4493e-04) (hash(x)=61455960) +1992 train 11.350850 (lr=1.4488e-04) (hash(x)=63788199) +1993 train 11.438143 (lr=1.4482e-04) (hash(x)=63899424) +1994 train 11.089297 (lr=1.4477e-04) (hash(x)=66412689) +1995 train 10.637164 (lr=1.4471e-04) (hash(x)=65636572) +1996 train 10.733424 (lr=1.4466e-04) (hash(x)=69649789) +1997 train 10.392569 (lr=1.4460e-04) (hash(x)=71578682) +1998 train 9.463357 (lr=1.4455e-04) (hash(x)=58341730) +1999 train 9.368764 (lr=1.4450e-04) (hash(x)=61104710) +2000 val loss 8.0363 +2000 val perplexity 3091.0388 +2000 train 8.863409 (lr=1.4444e-04) (hash(x)=52865322) +2001 train 8.150393 (lr=1.4439e-04) (hash(x)=23633693) +2002 train 8.189076 (lr=1.4433e-04) (hash(x)=25297571) +2003 train 8.382312 (lr=1.4428e-04) (hash(x)=24123821) +2004 train 7.921867 (lr=1.4422e-04) (hash(x)=20161517) +2005 train 7.880876 (lr=1.4417e-04) (hash(x)=19919984) +2006 train 7.917966 (lr=1.4411e-04) (hash(x)=18626507) +2007 train 8.036601 (lr=1.4406e-04) (hash(x)=20881126) +2008 train 8.136530 (lr=1.4401e-04) (hash(x)=26261448) +2009 train 8.163889 (lr=1.4395e-04) (hash(x)=27528050) +2010 train 8.088910 (lr=1.4390e-04) (hash(x)=26692097) +2011 train 7.811456 (lr=1.4384e-04) (hash(x)=23209969) +2012 train 7.694728 (lr=1.4379e-04) (hash(x)=26083446) +2013 train 7.838125 (lr=1.4373e-04) (hash(x)=28426467) +2014 train 7.605810 (lr=1.4368e-04) (hash(x)=26158154) +2015 train 7.705707 (lr=1.4362e-04) (hash(x)=26920243) +2016 train 7.374446 (lr=1.4357e-04) (hash(x)=21365321) +2017 train 7.448337 (lr=1.4351e-04) (hash(x)=25730699) +2018 train 7.506036 (lr=1.4346e-04) (hash(x)=25177106) +2019 train 7.426013 (lr=1.4340e-04) (hash(x)=26127756) +2020 train 7.053918 (lr=1.4335e-04) (hash(x)=19770037) +2021 train 7.437814 (lr=1.4330e-04) (hash(x)=26479346) +2022 train 7.512989 (lr=1.4324e-04) (hash(x)=25967643) +2023 train 7.438237 (lr=1.4319e-04) (hash(x)=21970343) +2024 train 7.647771 (lr=1.4313e-04) (hash(x)=26449648) +2025 train 7.639464 (lr=1.4308e-04) (hash(x)=24874094) +2026 train 7.209038 (lr=1.4302e-04) (hash(x)=21399697) +2027 train 7.409018 (lr=1.4297e-04) (hash(x)=24097897) +2028 train 7.463986 (lr=1.4291e-04) (hash(x)=24453548) +2029 train 7.558227 (lr=1.4286e-04) (hash(x)=26692093) +2030 train 7.372926 (lr=1.4280e-04) (hash(x)=27217002) +2031 train 7.718278 (lr=1.4275e-04) (hash(x)=31676352) +2032 train 7.421190 (lr=1.4269e-04) (hash(x)=23396350) +2033 train 7.418336 (lr=1.4264e-04) (hash(x)=26245173) +2034 train 7.505471 (lr=1.4258e-04) (hash(x)=24821033) +2035 train 7.497667 (lr=1.4253e-04) (hash(x)=23908053) +2036 train 7.302153 (lr=1.4247e-04) (hash(x)=23469373) +2037 train 7.372570 (lr=1.4242e-04) (hash(x)=24102198) +2038 train 7.375812 (lr=1.4236e-04) (hash(x)=24712135) +2039 train 7.606683 (lr=1.4231e-04) (hash(x)=25600562) +2040 train 7.515444 (lr=1.4225e-04) (hash(x)=23193393) +2041 train 7.482410 (lr=1.4220e-04) (hash(x)=24776954) +2042 train 7.612703 (lr=1.4214e-04) (hash(x)=28066546) +2043 train 7.223550 (lr=1.4209e-04) (hash(x)=23549168) +2044 train 7.249619 (lr=1.4203e-04) (hash(x)=22681487) +2045 train 7.476093 (lr=1.4198e-04) (hash(x)=26663184) +2046 train 7.420094 (lr=1.4192e-04) (hash(x)=23320809) +2047 train 7.292368 (lr=1.4187e-04) (hash(x)=22022924) +2048 train 7.568445 (lr=1.4181e-04) (hash(x)=27960930) +2049 train 7.414338 (lr=1.4176e-04) (hash(x)=24899178) +2050 val loss 7.4167 +2050 val perplexity 1663.5647 +2050 train 7.295087 (lr=1.4170e-04) (hash(x)=24450711) +2051 train 7.271599 (lr=1.4165e-04) (hash(x)=23294980) +2052 train 7.203133 (lr=1.4159e-04) (hash(x)=23243665) +2053 train 7.113933 (lr=1.4154e-04) (hash(x)=21004461) +2054 train 7.383675 (lr=1.4148e-04) (hash(x)=24493583) +2055 train 7.302574 (lr=1.4143e-04) (hash(x)=22777085) +2056 train 7.267009 (lr=1.4137e-04) (hash(x)=25169889) +2057 train 7.903025 (lr=1.4132e-04) (hash(x)=28395880) +2058 train 7.842755 (lr=1.4126e-04) (hash(x)=29603726) +2059 train 7.454462 (lr=1.4121e-04) (hash(x)=26271115) +2060 train 7.491081 (lr=1.4115e-04) (hash(x)=25616212) +2061 train 7.544632 (lr=1.4110e-04) (hash(x)=26398325) +2062 train 7.293243 (lr=1.4104e-04) (hash(x)=23836586) +2063 train 7.245586 (lr=1.4098e-04) (hash(x)=21727744) +2064 train 7.412939 (lr=1.4093e-04) (hash(x)=25183195) +2065 train 7.529920 (lr=1.4087e-04) (hash(x)=27108132) +2066 train 7.269122 (lr=1.4082e-04) (hash(x)=20987812) +2067 train 7.530866 (lr=1.4076e-04) (hash(x)=22729318) +2068 train 7.367095 (lr=1.4071e-04) (hash(x)=23129709) +2069 train 7.853110 (lr=1.4065e-04) (hash(x)=32820084) +2070 train 7.938300 (lr=1.4060e-04) (hash(x)=33763489) +2071 train 7.379604 (lr=1.4054e-04) (hash(x)=20701998) +2072 train 7.618453 (lr=1.4049e-04) (hash(x)=27765988) +2073 train 7.325046 (lr=1.4043e-04) (hash(x)=24157446) +2074 train 7.286833 (lr=1.4038e-04) (hash(x)=22014978) +2075 train 7.809415 (lr=1.4032e-04) (hash(x)=27928398) +2076 train 7.631119 (lr=1.4026e-04) (hash(x)=27880142) +2077 train 7.927469 (lr=1.4021e-04) (hash(x)=34991795) +2078 train 7.502014 (lr=1.4015e-04) (hash(x)=25944128) +2079 train 7.303514 (lr=1.4010e-04) (hash(x)=20863982) +2080 train 7.637828 (lr=1.4004e-04) (hash(x)=28036097) +2081 train 7.667202 (lr=1.3999e-04) (hash(x)=25813615) +2082 train 7.210503 (lr=1.3993e-04) (hash(x)=22862316) +2083 train 7.217493 (lr=1.3988e-04) (hash(x)=22827054) +2084 train 7.290174 (lr=1.3982e-04) (hash(x)=23996531) +2085 train 7.385262 (lr=1.3976e-04) (hash(x)=25756087) +2086 train 7.441606 (lr=1.3971e-04) (hash(x)=23165889) +2087 train 7.610188 (lr=1.3965e-04) (hash(x)=25084926) +2088 train 7.464268 (lr=1.3960e-04) (hash(x)=26063862) +2089 train 7.508101 (lr=1.3954e-04) (hash(x)=27843638) +2090 train 7.769406 (lr=1.3949e-04) (hash(x)=27375554) +2091 train 7.508554 (lr=1.3943e-04) (hash(x)=25540961) +2092 train 7.243057 (lr=1.3938e-04) (hash(x)=22933785) +2093 train 7.437757 (lr=1.3932e-04) (hash(x)=23996956) +2094 train 7.188892 (lr=1.3926e-04) (hash(x)=22915854) +2095 train 7.431609 (lr=1.3921e-04) (hash(x)=24412897) +2096 train 7.472140 (lr=1.3915e-04) (hash(x)=25152336) +2097 train 7.749272 (lr=1.3910e-04) (hash(x)=29525589) +2098 train 7.554495 (lr=1.3904e-04) (hash(x)=26435656) +2099 train 7.473119 (lr=1.3899e-04) (hash(x)=26269869) +2100 val loss 7.4262 +2100 val perplexity 1679.4062 +2100 train 7.196425 (lr=1.3893e-04) (hash(x)=23856783) +2101 train 7.512033 (lr=1.3887e-04) (hash(x)=26039611) +2102 train 7.243268 (lr=1.3882e-04) (hash(x)=25048861) +2103 train 7.360297 (lr=1.3876e-04) (hash(x)=25434913) +2104 train 7.548508 (lr=1.3871e-04) (hash(x)=24203891) +2105 train 7.373256 (lr=1.3865e-04) (hash(x)=26016998) +2106 train 7.527702 (lr=1.3859e-04) (hash(x)=23986767) +2107 train 7.401068 (lr=1.3854e-04) (hash(x)=25157653) +2108 train 7.550893 (lr=1.3848e-04) (hash(x)=30193751) +2109 train 7.407956 (lr=1.3843e-04) (hash(x)=22630574) +2110 train 7.311195 (lr=1.3837e-04) (hash(x)=23475467) +2111 train 7.606445 (lr=1.3832e-04) (hash(x)=26302544) +2112 train 7.380627 (lr=1.3826e-04) (hash(x)=21276592) +2113 train 7.617764 (lr=1.3820e-04) (hash(x)=27566393) +2114 train 7.383217 (lr=1.3815e-04) (hash(x)=25028015) +2115 train 7.150008 (lr=1.3809e-04) (hash(x)=22010703) +2116 train 7.479135 (lr=1.3804e-04) (hash(x)=23711709) +2117 train 7.558794 (lr=1.3798e-04) (hash(x)=26105026) +2118 train 7.899770 (lr=1.3792e-04) (hash(x)=34433894) +2119 train 7.958089 (lr=1.3787e-04) (hash(x)=34976197) +2120 train 7.452031 (lr=1.3781e-04) (hash(x)=27690727) +2121 train 7.288593 (lr=1.3776e-04) (hash(x)=24368234) +2122 train 7.313867 (lr=1.3770e-04) (hash(x)=25095726) +2123 train 7.454275 (lr=1.3764e-04) (hash(x)=28248301) +2124 train 7.240080 (lr=1.3759e-04) (hash(x)=23322302) +2125 train 7.664505 (lr=1.3753e-04) (hash(x)=26416200) +2126 train 7.330774 (lr=1.3748e-04) (hash(x)=26577567) +2127 train 7.386875 (lr=1.3742e-04) (hash(x)=23870805) +2128 train 7.339650 (lr=1.3736e-04) (hash(x)=25440544) +2129 train 7.441728 (lr=1.3731e-04) (hash(x)=25795021) +2130 train 7.330982 (lr=1.3725e-04) (hash(x)=20896402) +2131 train 7.348194 (lr=1.3719e-04) (hash(x)=24457252) +2132 train 7.399323 (lr=1.3714e-04) (hash(x)=25926760) +2133 train 7.272191 (lr=1.3708e-04) (hash(x)=23503725) +2134 train 7.826106 (lr=1.3703e-04) (hash(x)=28728828) +2135 train 7.337556 (lr=1.3697e-04) (hash(x)=25041103) +2136 train 7.334434 (lr=1.3691e-04) (hash(x)=22863770) +2137 train 7.246303 (lr=1.3686e-04) (hash(x)=23037755) +2138 train 7.436345 (lr=1.3680e-04) (hash(x)=25848413) +2139 train 7.486923 (lr=1.3674e-04) (hash(x)=25998487) +2140 train 7.323461 (lr=1.3669e-04) (hash(x)=22754440) +2141 train 7.604067 (lr=1.3663e-04) (hash(x)=27705382) +2142 train 7.634206 (lr=1.3658e-04) (hash(x)=27629095) +2143 train 7.512111 (lr=1.3652e-04) (hash(x)=26041745) +2144 train 7.242864 (lr=1.3646e-04) (hash(x)=21909712) +2145 train 7.412720 (lr=1.3641e-04) (hash(x)=24353905) +2146 train 7.379500 (lr=1.3635e-04) (hash(x)=24482587) +2147 train 7.519448 (lr=1.3629e-04) (hash(x)=27249810) +2148 train 7.630979 (lr=1.3624e-04) (hash(x)=26709938) +2149 train 7.292749 (lr=1.3618e-04) (hash(x)=23831457) +2150 val loss 7.3978 +2150 val perplexity 1632.3829 +2150 train 7.620416 (lr=1.3613e-04) (hash(x)=29776243) +2151 train 7.131967 (lr=1.3607e-04) (hash(x)=24068619) +2152 train 7.401338 (lr=1.3601e-04) (hash(x)=22208671) +2153 train 7.526976 (lr=1.3596e-04) (hash(x)=26680905) +2154 train 7.388326 (lr=1.3590e-04) (hash(x)=23567808) +2155 train 7.631523 (lr=1.3584e-04) (hash(x)=26359528) +2156 train 7.408951 (lr=1.3579e-04) (hash(x)=23787652) +2157 train 7.675075 (lr=1.3573e-04) (hash(x)=28347177) +2158 train 7.367162 (lr=1.3567e-04) (hash(x)=25266519) +2159 train 7.311807 (lr=1.3562e-04) (hash(x)=25441262) +2160 train 7.240218 (lr=1.3556e-04) (hash(x)=23959943) +2161 train 7.479962 (lr=1.3550e-04) (hash(x)=27888093) +2162 train 7.366859 (lr=1.3545e-04) (hash(x)=25547833) +2163 train 7.300946 (lr=1.3539e-04) (hash(x)=24413659) +2164 train 8.520543 (lr=1.3534e-04) (hash(x)=34397626) +2165 train 7.261926 (lr=1.3528e-04) (hash(x)=21159323) +2166 train 7.480231 (lr=1.3522e-04) (hash(x)=25360269) +2167 train 7.505568 (lr=1.3517e-04) (hash(x)=29181867) +2168 train 7.285850 (lr=1.3511e-04) (hash(x)=22501613) +2169 train 7.393496 (lr=1.3505e-04) (hash(x)=26469077) +2170 train 7.359084 (lr=1.3500e-04) (hash(x)=26665118) +2171 train 8.005722 (lr=1.3494e-04) (hash(x)=31551575) +2172 train 7.318155 (lr=1.3488e-04) (hash(x)=24803935) +2173 train 7.216316 (lr=1.3483e-04) (hash(x)=20896465) +2174 train 7.747618 (lr=1.3477e-04) (hash(x)=25702284) +2175 train 7.705854 (lr=1.3471e-04) (hash(x)=27093757) +2176 train 7.416111 (lr=1.3466e-04) (hash(x)=26024255) +2177 train 7.562058 (lr=1.3460e-04) (hash(x)=26443521) +2178 train 7.524316 (lr=1.3454e-04) (hash(x)=25478467) +2179 train 7.383485 (lr=1.3449e-04) (hash(x)=23624298) +2180 train 7.481409 (lr=1.3443e-04) (hash(x)=27304178) +2181 train 7.249678 (lr=1.3437e-04) (hash(x)=23016570) +2182 train 7.208417 (lr=1.3432e-04) (hash(x)=21073756) +2183 train 7.317394 (lr=1.3426e-04) (hash(x)=25150275) +2184 train 7.091876 (lr=1.3420e-04) (hash(x)=21004187) +2185 train 7.346223 (lr=1.3415e-04) (hash(x)=25876062) +2186 train 7.321956 (lr=1.3409e-04) (hash(x)=24221275) +2187 train 7.609006 (lr=1.3403e-04) (hash(x)=26239886) +2188 train 7.286148 (lr=1.3398e-04) (hash(x)=23299261) +2189 train 7.740337 (lr=1.3392e-04) (hash(x)=31024703) +2190 train 7.876527 (lr=1.3386e-04) (hash(x)=30084774) +2191 train 8.206192 (lr=1.3381e-04) (hash(x)=33457102) +2192 train 7.321903 (lr=1.3375e-04) (hash(x)=22423723) +2193 train 7.348100 (lr=1.3369e-04) (hash(x)=21989055) +2194 train 7.341207 (lr=1.3363e-04) (hash(x)=23286499) +2195 train 7.272953 (lr=1.3358e-04) (hash(x)=17499738) +2196 train 7.340588 (lr=1.3352e-04) (hash(x)=25329557) +2197 train 7.271993 (lr=1.3346e-04) (hash(x)=24195578) +2198 train 7.451660 (lr=1.3341e-04) (hash(x)=26646383) +2199 train 7.364954 (lr=1.3335e-04) (hash(x)=25755322) +2200 val loss 7.3904 +2200 val perplexity 1620.4313 +2200 train 7.413821 (lr=1.3329e-04) (hash(x)=27592223) +2201 train 7.604916 (lr=1.3324e-04) (hash(x)=26164625) +2202 train 7.463043 (lr=1.3318e-04) (hash(x)=21856341) +2203 train 7.356619 (lr=1.3312e-04) (hash(x)=23722795) +2204 train 7.420433 (lr=1.3307e-04) (hash(x)=25409645) +2205 train 7.373575 (lr=1.3301e-04) (hash(x)=23415339) +2206 train 7.346105 (lr=1.3295e-04) (hash(x)=24147928) +2207 train 7.221072 (lr=1.3290e-04) (hash(x)=23630794) +2208 train 7.304355 (lr=1.3284e-04) (hash(x)=27361452) +2209 train 7.357194 (lr=1.3278e-04) (hash(x)=25632158) +2210 train 7.207889 (lr=1.3272e-04) (hash(x)=21159789) +2211 train 7.318114 (lr=1.3267e-04) (hash(x)=23374168) +2212 train 7.361153 (lr=1.3261e-04) (hash(x)=24844739) +2213 train 7.279351 (lr=1.3255e-04) (hash(x)=23461285) +2214 train 7.352743 (lr=1.3250e-04) (hash(x)=27958481) +2215 train 7.260251 (lr=1.3244e-04) (hash(x)=25167987) +2216 train 7.451365 (lr=1.3238e-04) (hash(x)=22873204) +2217 train 8.052510 (lr=1.3233e-04) (hash(x)=31038116) +2218 train 7.472709 (lr=1.3227e-04) (hash(x)=28883155) +2219 train 7.389917 (lr=1.3221e-04) (hash(x)=30941010) +2220 train 7.348104 (lr=1.3215e-04) (hash(x)=24947521) +2221 train 7.371456 (lr=1.3210e-04) (hash(x)=22703293) +2222 train 7.321855 (lr=1.3204e-04) (hash(x)=23976007) +2223 train 7.241988 (lr=1.3198e-04) (hash(x)=24043224) +2224 train 7.190648 (lr=1.3193e-04) (hash(x)=23981093) +2225 train 7.354507 (lr=1.3187e-04) (hash(x)=26445994) +2226 train 7.656748 (lr=1.3181e-04) (hash(x)=27252393) +2227 train 7.607179 (lr=1.3175e-04) (hash(x)=29736627) +2228 train 7.560269 (lr=1.3170e-04) (hash(x)=24698933) +2229 train 7.186641 (lr=1.3164e-04) (hash(x)=24357840) +2230 train 7.392209 (lr=1.3158e-04) (hash(x)=25384498) +2231 train 7.488654 (lr=1.3153e-04) (hash(x)=24665411) +2232 train 7.373683 (lr=1.3147e-04) (hash(x)=24646352) +2233 train 7.357202 (lr=1.3141e-04) (hash(x)=25670741) +2234 train 7.404098 (lr=1.3135e-04) (hash(x)=26648242) +2235 train 7.599729 (lr=1.3130e-04) (hash(x)=27916043) +2236 train 7.392353 (lr=1.3124e-04) (hash(x)=25963100) +2237 train 7.503955 (lr=1.3118e-04) (hash(x)=27357379) +2238 train 7.348953 (lr=1.3112e-04) (hash(x)=21852360) +2239 train 7.360768 (lr=1.3107e-04) (hash(x)=17321657) +2240 train 7.344423 (lr=1.3101e-04) (hash(x)=18446645) +2241 train 7.186761 (lr=1.3095e-04) (hash(x)=17550988) +2242 train 7.426365 (lr=1.3090e-04) (hash(x)=27052347) +2243 train 7.316222 (lr=1.3084e-04) (hash(x)=23829833) +2244 train 7.509377 (lr=1.3078e-04) (hash(x)=27267264) +2245 train 7.674694 (lr=1.3072e-04) (hash(x)=24673611) +2246 train 7.565966 (lr=1.3067e-04) (hash(x)=25248507) +2247 train 7.794271 (lr=1.3061e-04) (hash(x)=27932591) +2248 train 7.624500 (lr=1.3055e-04) (hash(x)=26078877) +2249 train 7.671930 (lr=1.3049e-04) (hash(x)=26067367) +2250 val loss 7.3753 +2250 val perplexity 1596.1428 +2250 train 7.740746 (lr=1.3044e-04) (hash(x)=29143527) +2251 train 7.754074 (lr=1.3038e-04) (hash(x)=28206079) +2252 train 8.301836 (lr=1.3032e-04) (hash(x)=28894494) +2253 train 7.752512 (lr=1.3026e-04) (hash(x)=27977422) +2254 train 7.386445 (lr=1.3021e-04) (hash(x)=26446420) +2255 train 7.617794 (lr=1.3015e-04) (hash(x)=29447954) +2256 train 7.420942 (lr=1.3009e-04) (hash(x)=22181789) +2257 train 7.453237 (lr=1.3004e-04) (hash(x)=24976337) +2258 train 7.441991 (lr=1.2998e-04) (hash(x)=23277532) +2259 train 7.535033 (lr=1.2992e-04) (hash(x)=25935364) +2260 train 7.640528 (lr=1.2986e-04) (hash(x)=26988889) +2261 train 7.462605 (lr=1.2981e-04) (hash(x)=26887303) +2262 train 7.435973 (lr=1.2975e-04) (hash(x)=25021426) +2263 train 7.374495 (lr=1.2969e-04) (hash(x)=24621816) +2264 train 7.263322 (lr=1.2963e-04) (hash(x)=22132007) +2265 train 7.259441 (lr=1.2958e-04) (hash(x)=22648602) +2266 train 7.494837 (lr=1.2952e-04) (hash(x)=23132242) +2267 train 7.559741 (lr=1.2946e-04) (hash(x)=24070405) +2268 train 7.165215 (lr=1.2940e-04) (hash(x)=21412906) +2269 train 7.825490 (lr=1.2935e-04) (hash(x)=27547292) +2270 train 7.572338 (lr=1.2929e-04) (hash(x)=27740500) +2271 train 7.305210 (lr=1.2923e-04) (hash(x)=24682294) +2272 train 7.698049 (lr=1.2917e-04) (hash(x)=27969424) +2273 train 7.409398 (lr=1.2912e-04) (hash(x)=22172182) +2274 train 7.416645 (lr=1.2906e-04) (hash(x)=26485905) +2275 train 7.266721 (lr=1.2900e-04) (hash(x)=24050209) +2276 train 7.446065 (lr=1.2894e-04) (hash(x)=28802650) +2277 train 7.219123 (lr=1.2888e-04) (hash(x)=23644616) +2278 train 7.400608 (lr=1.2883e-04) (hash(x)=25409768) +2279 train 7.537039 (lr=1.2877e-04) (hash(x)=28057095) +2280 train 8.014178 (lr=1.2871e-04) (hash(x)=31689723) +2281 train 7.250911 (lr=1.2865e-04) (hash(x)=22252427) +2282 train 7.446451 (lr=1.2860e-04) (hash(x)=24142092) +2283 train 7.380955 (lr=1.2854e-04) (hash(x)=22523232) +2284 train 7.578253 (lr=1.2848e-04) (hash(x)=26017294) +2285 train 7.419533 (lr=1.2842e-04) (hash(x)=25025388) +2286 train 7.193336 (lr=1.2837e-04) (hash(x)=23819479) +2287 train 7.352580 (lr=1.2831e-04) (hash(x)=24547536) +2288 train 7.138948 (lr=1.2825e-04) (hash(x)=22622789) +2289 train 7.163193 (lr=1.2819e-04) (hash(x)=23874051) +2290 train 7.475617 (lr=1.2814e-04) (hash(x)=25015641) +2291 train 7.375310 (lr=1.2808e-04) (hash(x)=24978712) +2292 train 7.454492 (lr=1.2802e-04) (hash(x)=25311986) +2293 train 7.215984 (lr=1.2796e-04) (hash(x)=24298295) +2294 train 7.317266 (lr=1.2790e-04) (hash(x)=26481527) +2295 train 7.058569 (lr=1.2785e-04) (hash(x)=18987545) +2296 train 7.296785 (lr=1.2779e-04) (hash(x)=24617990) +2297 train 7.300046 (lr=1.2773e-04) (hash(x)=23903200) +2298 train 7.570601 (lr=1.2767e-04) (hash(x)=26278697) +2299 train 7.333884 (lr=1.2762e-04) (hash(x)=24092784) +2300 val loss 7.3734 +2300 val perplexity 1593.0436 +2300 train 7.283247 (lr=1.2756e-04) (hash(x)=22894919) +2301 train 7.374416 (lr=1.2750e-04) (hash(x)=24253964) +2302 train 7.333369 (lr=1.2744e-04) (hash(x)=23750610) +2303 train 7.357900 (lr=1.2738e-04) (hash(x)=26745063) +2304 train 7.188211 (lr=1.2733e-04) (hash(x)=21407001) +2305 train 7.551024 (lr=1.2727e-04) (hash(x)=26680082) +2306 train 7.471445 (lr=1.2721e-04) (hash(x)=26722122) +2307 train 7.315581 (lr=1.2715e-04) (hash(x)=22539112) +2308 train 7.078645 (lr=1.2710e-04) (hash(x)=19927356) +2309 train 7.187886 (lr=1.2704e-04) (hash(x)=21431267) +2310 train 7.151521 (lr=1.2698e-04) (hash(x)=21073487) +2311 train 7.181075 (lr=1.2692e-04) (hash(x)=21447406) +2312 train 7.147491 (lr=1.2686e-04) (hash(x)=22667253) +2313 train 7.118425 (lr=1.2681e-04) (hash(x)=20849089) +2314 train 7.106548 (lr=1.2675e-04) (hash(x)=19168351) +2315 train 7.131097 (lr=1.2669e-04) (hash(x)=21082139) +2316 train 7.115973 (lr=1.2663e-04) (hash(x)=21493530) +2317 train 7.064277 (lr=1.2657e-04) (hash(x)=19506447) +2318 train 7.172981 (lr=1.2652e-04) (hash(x)=23128797) +2319 train 7.298347 (lr=1.2646e-04) (hash(x)=24650655) +2320 train 7.075222 (lr=1.2640e-04) (hash(x)=21833080) +2321 train 7.587706 (lr=1.2634e-04) (hash(x)=26355512) +2322 train 7.761742 (lr=1.2629e-04) (hash(x)=26746363) +2323 train 7.208364 (lr=1.2623e-04) (hash(x)=22130721) +2324 train 7.569200 (lr=1.2617e-04) (hash(x)=28301752) +2325 train 7.371823 (lr=1.2611e-04) (hash(x)=26444359) +2326 train 7.760744 (lr=1.2605e-04) (hash(x)=24836130) +2327 train 8.069687 (lr=1.2600e-04) (hash(x)=26519976) +2328 train 9.370750 (lr=1.2594e-04) (hash(x)=35558906) +2329 train 7.823644 (lr=1.2588e-04) (hash(x)=30877729) +2330 train 7.664176 (lr=1.2582e-04) (hash(x)=28028485) +2331 train 7.773779 (lr=1.2576e-04) (hash(x)=25582440) +2332 train 8.076015 (lr=1.2571e-04) (hash(x)=29402491) +2333 train 7.414142 (lr=1.2565e-04) (hash(x)=25200284) +2334 train 7.486798 (lr=1.2559e-04) (hash(x)=26288480) +2335 train 7.361150 (lr=1.2553e-04) (hash(x)=20106514) +2336 train 7.281419 (lr=1.2547e-04) (hash(x)=22522123) +2337 train 7.245880 (lr=1.2542e-04) (hash(x)=23362041) +2338 train 7.336962 (lr=1.2536e-04) (hash(x)=26003099) +2339 train 7.369511 (lr=1.2530e-04) (hash(x)=25695510) +2340 train 7.375268 (lr=1.2524e-04) (hash(x)=27225904) +2341 train 7.099666 (lr=1.2518e-04) (hash(x)=21573008) +2342 train 7.564244 (lr=1.2513e-04) (hash(x)=21386628) +2343 train 7.313353 (lr=1.2507e-04) (hash(x)=20117808) +2344 train 7.472522 (lr=1.2501e-04) (hash(x)=21592790) +2345 train 7.375003 (lr=1.2495e-04) (hash(x)=19909192) +2346 train 7.521488 (lr=1.2489e-04) (hash(x)=22529262) +2347 train 7.533139 (lr=1.2483e-04) (hash(x)=24501900) +2348 train 7.340415 (lr=1.2478e-04) (hash(x)=25912171) +2349 train 7.466352 (lr=1.2472e-04) (hash(x)=25606665) +2350 val loss 7.4083 +2350 val perplexity 1649.6981 +2350 train 7.363462 (lr=1.2466e-04) (hash(x)=24487351) +2351 train 7.603448 (lr=1.2460e-04) (hash(x)=25510334) +2352 train 7.517197 (lr=1.2454e-04) (hash(x)=25357989) +2353 train 7.151106 (lr=1.2449e-04) (hash(x)=24656801) +2354 train 7.230157 (lr=1.2443e-04) (hash(x)=23312772) +2355 train 7.096550 (lr=1.2437e-04) (hash(x)=22099158) +2356 train 7.174672 (lr=1.2431e-04) (hash(x)=26507898) +2357 train 7.427638 (lr=1.2425e-04) (hash(x)=28351614) +2358 train 7.469048 (lr=1.2420e-04) (hash(x)=27489567) +2359 train 7.439224 (lr=1.2414e-04) (hash(x)=25749120) +2360 train 7.768402 (lr=1.2408e-04) (hash(x)=31711338) +2361 train 7.888962 (lr=1.2402e-04) (hash(x)=29645018) +2362 train 7.923517 (lr=1.2396e-04) (hash(x)=29713268) +2363 train 7.115960 (lr=1.2390e-04) (hash(x)=21720691) +2364 train 7.246280 (lr=1.2385e-04) (hash(x)=24316633) +2365 train 7.202148 (lr=1.2379e-04) (hash(x)=21597124) +2366 train 7.216046 (lr=1.2373e-04) (hash(x)=22520345) +2367 train 7.261952 (lr=1.2367e-04) (hash(x)=24357241) +2368 train 7.387600 (lr=1.2361e-04) (hash(x)=24085450) +2369 train 7.259911 (lr=1.2356e-04) (hash(x)=25136495) +2370 train 7.719245 (lr=1.2350e-04) (hash(x)=26073986) +2371 train 7.698548 (lr=1.2344e-04) (hash(x)=28911272) +2372 train 7.465549 (lr=1.2338e-04) (hash(x)=26667356) +2373 train 7.294187 (lr=1.2332e-04) (hash(x)=25225894) +2374 train 7.326918 (lr=1.2326e-04) (hash(x)=24404081) +2375 train 7.412405 (lr=1.2321e-04) (hash(x)=25584945) +2376 train 7.269937 (lr=1.2315e-04) (hash(x)=23831571) +2377 train 7.238679 (lr=1.2309e-04) (hash(x)=23521916) +2378 train 7.273769 (lr=1.2303e-04) (hash(x)=25318634) +2379 train 7.177162 (lr=1.2297e-04) (hash(x)=21847287) +2380 train 7.503868 (lr=1.2291e-04) (hash(x)=23877060) +2381 train 7.265054 (lr=1.2286e-04) (hash(x)=24069020) +2382 train 7.104056 (lr=1.2280e-04) (hash(x)=21724290) +2383 train 7.326422 (lr=1.2274e-04) (hash(x)=25198897) +2384 train 7.207851 (lr=1.2268e-04) (hash(x)=24109958) +2385 train 7.110322 (lr=1.2262e-04) (hash(x)=20122390) +2386 train 7.346530 (lr=1.2256e-04) (hash(x)=24062305) +2387 train 7.114360 (lr=1.2251e-04) (hash(x)=22436833) +2388 train 7.447952 (lr=1.2245e-04) (hash(x)=26013214) +2389 train 7.781624 (lr=1.2239e-04) (hash(x)=27691436) +2390 train 7.916641 (lr=1.2233e-04) (hash(x)=30802878) +2391 train 7.109229 (lr=1.2227e-04) (hash(x)=23475891) +2392 train 7.065329 (lr=1.2221e-04) (hash(x)=23118133) +2393 train 6.998166 (lr=1.2216e-04) (hash(x)=21469159) +2394 train 7.392959 (lr=1.2210e-04) (hash(x)=26444484) +2395 train 7.251892 (lr=1.2204e-04) (hash(x)=25083992) +2396 train 7.572656 (lr=1.2198e-04) (hash(x)=23461229) +2397 train 7.421259 (lr=1.2192e-04) (hash(x)=20441653) +2398 train 7.527422 (lr=1.2186e-04) (hash(x)=28024211) +2399 train 7.378675 (lr=1.2181e-04) (hash(x)=23644804) +2400 val loss 7.3844 +2400 val perplexity 1610.6770 +2400 train 7.186485 (lr=1.2175e-04) (hash(x)=26685301) +2401 train 7.094252 (lr=1.2169e-04) (hash(x)=20820913) +2402 train 7.281387 (lr=1.2163e-04) (hash(x)=22178190) +2403 train 7.747384 (lr=1.2157e-04) (hash(x)=31377168) +2404 train 7.952355 (lr=1.2151e-04) (hash(x)=33795307) +2405 train 8.112018 (lr=1.2146e-04) (hash(x)=34450341) +2406 train 7.362312 (lr=1.2140e-04) (hash(x)=25834183) +2407 train 7.556526 (lr=1.2134e-04) (hash(x)=25629584) +2408 train 7.318513 (lr=1.2128e-04) (hash(x)=25080123) +2409 train 7.253060 (lr=1.2122e-04) (hash(x)=21975628) +2410 train 7.748075 (lr=1.2116e-04) (hash(x)=27430197) +2411 train 7.882428 (lr=1.2110e-04) (hash(x)=29285135) +2412 train 7.560265 (lr=1.2105e-04) (hash(x)=24640105) +2413 train 7.708046 (lr=1.2099e-04) (hash(x)=29628864) +2414 train 7.869870 (lr=1.2093e-04) (hash(x)=30096444) +2415 train 7.753530 (lr=1.2087e-04) (hash(x)=29797280) +2416 train 7.149053 (lr=1.2081e-04) (hash(x)=22686143) +2417 train 7.670584 (lr=1.2075e-04) (hash(x)=28346842) +2418 train 7.645053 (lr=1.2070e-04) (hash(x)=28167937) +2419 train 7.865658 (lr=1.2064e-04) (hash(x)=33122326) +2420 train 7.915848 (lr=1.2058e-04) (hash(x)=33044913) +2421 train 7.701555 (lr=1.2052e-04) (hash(x)=31250981) +2422 train 7.973446 (lr=1.2046e-04) (hash(x)=29827111) +2423 train 7.941193 (lr=1.2040e-04) (hash(x)=30026394) +2424 train 8.069022 (lr=1.2034e-04) (hash(x)=26998238) +2425 train 8.085744 (lr=1.2029e-04) (hash(x)=24850684) +2426 train 8.193757 (lr=1.2023e-04) (hash(x)=36659853) +2427 train 8.095360 (lr=1.2017e-04) (hash(x)=34353164) +2428 train 7.453740 (lr=1.2011e-04) (hash(x)=23630644) +2429 train 7.363124 (lr=1.2005e-04) (hash(x)=24528186) +2430 train 7.290524 (lr=1.1999e-04) (hash(x)=22665222) +2431 train 7.428014 (lr=1.1993e-04) (hash(x)=26594177) +2432 train 7.771450 (lr=1.1988e-04) (hash(x)=29300546) +2433 train 7.234643 (lr=1.1982e-04) (hash(x)=21331715) +2434 train 7.539250 (lr=1.1976e-04) (hash(x)=26290885) +2435 train 7.427927 (lr=1.1970e-04) (hash(x)=25554738) +2436 train 7.637523 (lr=1.1964e-04) (hash(x)=26744311) +2437 train 7.580833 (lr=1.1958e-04) (hash(x)=26872344) +2438 train 7.593595 (lr=1.1952e-04) (hash(x)=27636081) +2439 train 7.383571 (lr=1.1947e-04) (hash(x)=23766256) +2440 train 7.522946 (lr=1.1941e-04) (hash(x)=24434438) +2441 train 7.336640 (lr=1.1935e-04) (hash(x)=22992618) +2442 train 7.203866 (lr=1.1929e-04) (hash(x)=22393467) +2443 train 7.450162 (lr=1.1923e-04) (hash(x)=26853444) +2444 train 7.415323 (lr=1.1917e-04) (hash(x)=25101020) +2445 train 7.298381 (lr=1.1911e-04) (hash(x)=24705456) +2446 train 7.571449 (lr=1.1906e-04) (hash(x)=26798611) +2447 train 7.276543 (lr=1.1900e-04) (hash(x)=24250150) +2448 train 7.349430 (lr=1.1894e-04) (hash(x)=24494331) +2449 train 7.329674 (lr=1.1888e-04) (hash(x)=27579257) +2450 val loss 7.3892 +2450 val perplexity 1618.4390 +2450 train 7.123906 (lr=1.1882e-04) (hash(x)=22377407) +2451 train 7.402240 (lr=1.1876e-04) (hash(x)=26289588) +2452 train 7.318221 (lr=1.1870e-04) (hash(x)=25871900) +2453 train 7.226753 (lr=1.1865e-04) (hash(x)=23437197) +2454 train 7.492078 (lr=1.1859e-04) (hash(x)=23557786) +2455 train 7.382707 (lr=1.1853e-04) (hash(x)=26108817) +2456 train 7.342691 (lr=1.1847e-04) (hash(x)=26440482) +2457 train 7.310837 (lr=1.1841e-04) (hash(x)=24583191) +2458 train 7.297283 (lr=1.1835e-04) (hash(x)=23756440) +2459 train 7.198080 (lr=1.1829e-04) (hash(x)=23814987) +2460 train 7.568775 (lr=1.1824e-04) (hash(x)=28508433) +2461 train 7.266666 (lr=1.1818e-04) (hash(x)=25692442) +2462 train 7.276085 (lr=1.1812e-04) (hash(x)=24699197) +2463 train 6.961832 (lr=1.1806e-04) (hash(x)=18582688) +2464 train 7.267917 (lr=1.1800e-04) (hash(x)=23266625) +2465 train 7.517864 (lr=1.1794e-04) (hash(x)=26565489) +2466 train 7.084564 (lr=1.1788e-04) (hash(x)=21686599) +2467 train 7.403965 (lr=1.1782e-04) (hash(x)=25558792) +2468 train 7.165411 (lr=1.1777e-04) (hash(x)=25110035) +2469 train 7.456649 (lr=1.1771e-04) (hash(x)=26263661) +2470 train 7.241332 (lr=1.1765e-04) (hash(x)=22282189) +2471 train 7.189792 (lr=1.1759e-04) (hash(x)=23272705) +2472 train 7.261362 (lr=1.1753e-04) (hash(x)=25300067) +2473 train 7.463763 (lr=1.1747e-04) (hash(x)=26802369) +2474 train 7.191933 (lr=1.1741e-04) (hash(x)=24646471) +2475 train 7.128418 (lr=1.1735e-04) (hash(x)=24709241) +2476 train 7.230220 (lr=1.1730e-04) (hash(x)=26747197) +2477 train 7.268364 (lr=1.1724e-04) (hash(x)=25201108) +2478 train 7.404489 (lr=1.1718e-04) (hash(x)=24962427) +2479 train 7.251188 (lr=1.1712e-04) (hash(x)=24793412) +2480 train 7.264637 (lr=1.1706e-04) (hash(x)=24452301) +2481 train 7.284227 (lr=1.1700e-04) (hash(x)=25177251) +2482 train 7.246006 (lr=1.1694e-04) (hash(x)=25801499) +2483 train 7.381925 (lr=1.1689e-04) (hash(x)=27256707) +2484 train 7.670261 (lr=1.1683e-04) (hash(x)=25303237) +2485 train 7.239719 (lr=1.1677e-04) (hash(x)=21641481) +2486 train 7.234645 (lr=1.1671e-04) (hash(x)=23818831) +2487 train 7.052537 (lr=1.1665e-04) (hash(x)=19280989) +2488 train 7.405473 (lr=1.1659e-04) (hash(x)=24075167) +2489 train 7.424380 (lr=1.1653e-04) (hash(x)=26651546) +2490 train 7.348125 (lr=1.1647e-04) (hash(x)=25367186) +2491 train 7.277187 (lr=1.1642e-04) (hash(x)=26508642) +2492 train 7.404193 (lr=1.1636e-04) (hash(x)=25294182) +2493 train 7.323438 (lr=1.1630e-04) (hash(x)=23916886) +2494 train 7.173500 (lr=1.1624e-04) (hash(x)=21189910) +2495 train 7.264801 (lr=1.1618e-04) (hash(x)=22751150) +2496 train 7.623978 (lr=1.1612e-04) (hash(x)=26608502) +2497 train 8.043101 (lr=1.1606e-04) (hash(x)=25372010) +2498 train 7.342723 (lr=1.1600e-04) (hash(x)=22006251) +2499 train 7.252394 (lr=1.1595e-04) (hash(x)=23880160) +2500 val loss 7.3686 +2500 val perplexity 1585.4570 +2500 train 7.218347 (lr=1.1589e-04) (hash(x)=23225337) +2501 train 7.335805 (lr=1.1583e-04) (hash(x)=24932950) +2502 train 7.053938 (lr=1.1577e-04) (hash(x)=20022340) +2503 train 7.431919 (lr=1.1571e-04) (hash(x)=23537942) +2504 train 7.315534 (lr=1.1565e-04) (hash(x)=24884288) +2505 train 6.983917 (lr=1.1559e-04) (hash(x)=21296580) +2506 train 7.238605 (lr=1.1553e-04) (hash(x)=23001455) +2507 train 7.526385 (lr=1.1547e-04) (hash(x)=26975313) +2508 train 7.502432 (lr=1.1542e-04) (hash(x)=26029962) +2509 train 7.229109 (lr=1.1536e-04) (hash(x)=24302204) +2510 train 6.943336 (lr=1.1530e-04) (hash(x)=22997203) +2511 train 7.078017 (lr=1.1524e-04) (hash(x)=23748375) +2512 train 7.269351 (lr=1.1518e-04) (hash(x)=24453191) +2513 train 7.013814 (lr=1.1512e-04) (hash(x)=22026776) +2514 train 7.130306 (lr=1.1506e-04) (hash(x)=19934168) +2515 train 7.377216 (lr=1.1500e-04) (hash(x)=25541754) +2516 train 7.704766 (lr=1.1495e-04) (hash(x)=26604471) +2517 train 7.654167 (lr=1.1489e-04) (hash(x)=27900386) +2518 train 7.610784 (lr=1.1483e-04) (hash(x)=26403431) +2519 train 7.650360 (lr=1.1477e-04) (hash(x)=27413825) +2520 train 7.746979 (lr=1.1471e-04) (hash(x)=28332637) +2521 train 7.544731 (lr=1.1465e-04) (hash(x)=27223027) +2522 train 7.545681 (lr=1.1459e-04) (hash(x)=23843387) +2523 train 7.523932 (lr=1.1453e-04) (hash(x)=27075951) +2524 train 7.694904 (lr=1.1447e-04) (hash(x)=29300154) +2525 train 7.384073 (lr=1.1442e-04) (hash(x)=28100582) +2526 train 7.455965 (lr=1.1436e-04) (hash(x)=28051084) +2527 train 7.221228 (lr=1.1430e-04) (hash(x)=21682445) +2528 train 7.365225 (lr=1.1424e-04) (hash(x)=24062589) +2529 train 7.561424 (lr=1.1418e-04) (hash(x)=29616079) +2530 train 7.508798 (lr=1.1412e-04) (hash(x)=25170523) +2531 train 7.093738 (lr=1.1406e-04) (hash(x)=23361504) +2532 train 7.312267 (lr=1.1400e-04) (hash(x)=24444462) +2533 train 7.301614 (lr=1.1395e-04) (hash(x)=24035993) +2534 train 7.266220 (lr=1.1389e-04) (hash(x)=24696651) +2535 train 7.247579 (lr=1.1383e-04) (hash(x)=22040184) +2536 train 7.159863 (lr=1.1377e-04) (hash(x)=27400103) +2537 train 7.499396 (lr=1.1371e-04) (hash(x)=27383080) +2538 train 7.311110 (lr=1.1365e-04) (hash(x)=24212212) +2539 train 7.190125 (lr=1.1359e-04) (hash(x)=23727731) +2540 train 7.314839 (lr=1.1353e-04) (hash(x)=24149487) +2541 train 7.108936 (lr=1.1347e-04) (hash(x)=23794649) +2542 train 7.285995 (lr=1.1342e-04) (hash(x)=26147774) +2543 train 7.435999 (lr=1.1336e-04) (hash(x)=24463229) +2544 train 7.447254 (lr=1.1330e-04) (hash(x)=26361238) +2545 train 7.161064 (lr=1.1324e-04) (hash(x)=18891545) +2546 train 7.645273 (lr=1.1318e-04) (hash(x)=30380438) +2547 train 7.847151 (lr=1.1312e-04) (hash(x)=32663792) +2548 train 7.327500 (lr=1.1306e-04) (hash(x)=25175499) +2549 train 7.462166 (lr=1.1300e-04) (hash(x)=26702407) +2550 val loss 7.3814 +2550 val perplexity 1605.7783 +2550 train 7.280287 (lr=1.1294e-04) (hash(x)=24578061) +2551 train 7.322733 (lr=1.1289e-04) (hash(x)=24091954) +2552 train 7.370572 (lr=1.1283e-04) (hash(x)=23041778) +2553 train 7.183488 (lr=1.1277e-04) (hash(x)=23686239) +2554 train 7.269218 (lr=1.1271e-04) (hash(x)=22745355) +2555 train 7.300299 (lr=1.1265e-04) (hash(x)=23599013) +2556 train 7.198638 (lr=1.1259e-04) (hash(x)=26033088) +2557 train 7.224245 (lr=1.1253e-04) (hash(x)=21634218) +2558 train 7.183019 (lr=1.1247e-04) (hash(x)=20985281) +2559 train 7.462703 (lr=1.1241e-04) (hash(x)=26670219) +2560 train 7.258588 (lr=1.1236e-04) (hash(x)=26499936) +2561 train 7.332287 (lr=1.1230e-04) (hash(x)=23547908) +2562 train 7.178185 (lr=1.1224e-04) (hash(x)=22306373) +2563 train 7.275789 (lr=1.1218e-04) (hash(x)=24380893) +2564 train 7.229581 (lr=1.1212e-04) (hash(x)=23726190) +2565 train 7.262074 (lr=1.1206e-04) (hash(x)=26967512) +2566 train 7.349027 (lr=1.1200e-04) (hash(x)=23414576) +2567 train 7.537057 (lr=1.1194e-04) (hash(x)=25558986) +2568 train 7.417479 (lr=1.1188e-04) (hash(x)=27057505) +2569 train 7.429822 (lr=1.1183e-04) (hash(x)=26048135) +2570 train 7.392413 (lr=1.1177e-04) (hash(x)=26991032) +2571 train 7.446616 (lr=1.1171e-04) (hash(x)=25729492) +2572 train 7.034714 (lr=1.1165e-04) (hash(x)=20611723) +2573 train 7.128955 (lr=1.1159e-04) (hash(x)=24563606) +2574 train 7.169248 (lr=1.1153e-04) (hash(x)=23330043) +2575 train 7.291828 (lr=1.1147e-04) (hash(x)=19218943) +2576 train 7.645074 (lr=1.1141e-04) (hash(x)=20985122) +2577 train 7.208530 (lr=1.1135e-04) (hash(x)=24133609) +2578 train 7.502087 (lr=1.1130e-04) (hash(x)=28368610) +2579 train 7.275134 (lr=1.1124e-04) (hash(x)=23952206) +2580 train 7.182730 (lr=1.1118e-04) (hash(x)=23068957) +2581 train 7.292478 (lr=1.1112e-04) (hash(x)=25365277) +2582 train 7.585874 (lr=1.1106e-04) (hash(x)=24721184) +2583 train 7.300991 (lr=1.1100e-04) (hash(x)=24551402) +2584 train 7.038728 (lr=1.1094e-04) (hash(x)=20469327) +2585 train 7.433441 (lr=1.1088e-04) (hash(x)=24966478) +2586 train 7.175235 (lr=1.1082e-04) (hash(x)=18626184) +2587 train 7.202196 (lr=1.1077e-04) (hash(x)=24007642) +2588 train 7.192892 (lr=1.1071e-04) (hash(x)=23521875) +2589 train 7.364357 (lr=1.1065e-04) (hash(x)=25204207) +2590 train 7.183705 (lr=1.1059e-04) (hash(x)=25449801) +2591 train 7.358762 (lr=1.1053e-04) (hash(x)=25229281) +2592 train 7.204692 (lr=1.1047e-04) (hash(x)=23202696) +2593 train 7.097168 (lr=1.1041e-04) (hash(x)=22435944) +2594 train 7.054581 (lr=1.1035e-04) (hash(x)=20787439) +2595 train 6.746411 (lr=1.1029e-04) (hash(x)=18214283) +2596 train 6.919895 (lr=1.1024e-04) (hash(x)=20851477) +2597 train 6.894584 (lr=1.1018e-04) (hash(x)=20609675) +2598 train 7.004979 (lr=1.1012e-04) (hash(x)=20061218) +2599 train 7.041215 (lr=1.1006e-04) (hash(x)=21251127) +2600 val loss 7.3398 +2600 val perplexity 1540.4449 +2600 train 7.525539 (lr=1.1000e-04) (hash(x)=30948038) +2601 train 7.815479 (lr=1.0994e-04) (hash(x)=32279160) +2602 train 7.494465 (lr=1.0988e-04) (hash(x)=26607151) +2603 train 7.314912 (lr=1.0982e-04) (hash(x)=25097619) +2604 train 6.921793 (lr=1.0976e-04) (hash(x)=20892421) +2605 train 7.075840 (lr=1.0971e-04) (hash(x)=22212821) +2606 train 7.364700 (lr=1.0965e-04) (hash(x)=24720588) +2607 train 7.376583 (lr=1.0959e-04) (hash(x)=25800857) +2608 train 7.234864 (lr=1.0953e-04) (hash(x)=22901279) +2609 train 7.091011 (lr=1.0947e-04) (hash(x)=20921910) +2610 train 7.300632 (lr=1.0941e-04) (hash(x)=24846267) +2611 train 7.196190 (lr=1.0935e-04) (hash(x)=22918428) +2612 train 7.178041 (lr=1.0929e-04) (hash(x)=22805901) +2613 train 7.304219 (lr=1.0923e-04) (hash(x)=24345816) +2614 train 7.150887 (lr=1.0918e-04) (hash(x)=22962012) +2615 train 7.392523 (lr=1.0912e-04) (hash(x)=25836189) +2616 train 7.425015 (lr=1.0906e-04) (hash(x)=27922916) +2617 train 7.208023 (lr=1.0900e-04) (hash(x)=21697866) +2618 train 7.152979 (lr=1.0894e-04) (hash(x)=24283369) +2619 train 7.089560 (lr=1.0888e-04) (hash(x)=24504567) +2620 train 7.183330 (lr=1.0882e-04) (hash(x)=25557725) +2621 train 7.210129 (lr=1.0876e-04) (hash(x)=23135849) +2622 train 7.146003 (lr=1.0870e-04) (hash(x)=22888908) +2623 train 7.353498 (lr=1.0865e-04) (hash(x)=25999255) +2624 train 7.203083 (lr=1.0859e-04) (hash(x)=24446851) +2625 train 6.975334 (lr=1.0853e-04) (hash(x)=21137520) +2626 train 7.296447 (lr=1.0847e-04) (hash(x)=26245754) +2627 train 7.571299 (lr=1.0841e-04) (hash(x)=27308968) +2628 train 7.325331 (lr=1.0835e-04) (hash(x)=23961169) +2629 train 7.297971 (lr=1.0829e-04) (hash(x)=25924731) +2630 train 7.368816 (lr=1.0823e-04) (hash(x)=25782315) +2631 train 7.440216 (lr=1.0817e-04) (hash(x)=20149394) +2632 train 7.491486 (lr=1.0812e-04) (hash(x)=23801981) +2633 train 7.277054 (lr=1.0806e-04) (hash(x)=23830286) +2634 train 7.199480 (lr=1.0800e-04) (hash(x)=25325236) +2635 train 7.208034 (lr=1.0794e-04) (hash(x)=24498556) +2636 train 7.165174 (lr=1.0788e-04) (hash(x)=23693078) +2637 train 7.348343 (lr=1.0782e-04) (hash(x)=25484922) +2638 train 7.077689 (lr=1.0776e-04) (hash(x)=22645025) +2639 train 7.005315 (lr=1.0770e-04) (hash(x)=21999338) +2640 train 7.216718 (lr=1.0764e-04) (hash(x)=21758019) +2641 train 7.173770 (lr=1.0759e-04) (hash(x)=24064168) +2642 train 7.189051 (lr=1.0753e-04) (hash(x)=26847292) +2643 train 7.057329 (lr=1.0747e-04) (hash(x)=23280568) +2644 train 7.076704 (lr=1.0741e-04) (hash(x)=21749161) +2645 train 7.668501 (lr=1.0735e-04) (hash(x)=30082352) +2646 train 7.522716 (lr=1.0729e-04) (hash(x)=28334297) +2647 train 7.684566 (lr=1.0723e-04) (hash(x)=27611302) +2648 train 8.075442 (lr=1.0717e-04) (hash(x)=31007436) +2649 train 7.059517 (lr=1.0711e-04) (hash(x)=22356183) +2650 val loss 7.3344 +2650 val perplexity 1532.1721 +2650 train 7.068488 (lr=1.0706e-04) (hash(x)=23071731) +2651 train 7.083119 (lr=1.0700e-04) (hash(x)=23982308) +2652 train 7.381255 (lr=1.0694e-04) (hash(x)=25673823) +2653 train 7.179654 (lr=1.0688e-04) (hash(x)=22973788) +2654 train 7.345659 (lr=1.0682e-04) (hash(x)=25386647) +2655 train 7.123922 (lr=1.0676e-04) (hash(x)=22778356) +2656 train 7.301561 (lr=1.0670e-04) (hash(x)=26669130) +2657 train 7.046213 (lr=1.0664e-04) (hash(x)=23542930) +2658 train 7.158379 (lr=1.0658e-04) (hash(x)=23307871) +2659 train 7.138902 (lr=1.0653e-04) (hash(x)=23467046) +2660 train 7.263802 (lr=1.0647e-04) (hash(x)=24728872) +2661 train 7.871449 (lr=1.0641e-04) (hash(x)=29719902) +2662 train 7.196632 (lr=1.0635e-04) (hash(x)=25114165) +2663 train 7.101935 (lr=1.0629e-04) (hash(x)=24195959) +2664 train 7.332911 (lr=1.0623e-04) (hash(x)=26938509) +2665 train 7.472777 (lr=1.0617e-04) (hash(x)=27168434) +2666 train 7.654521 (lr=1.0611e-04) (hash(x)=27488221) +2667 train 8.316396 (lr=1.0605e-04) (hash(x)=32710438) +2668 train 7.429479 (lr=1.0600e-04) (hash(x)=25073185) +2669 train 7.439865 (lr=1.0594e-04) (hash(x)=26951664) +2670 train 7.575649 (lr=1.0588e-04) (hash(x)=24886228) +2671 train 7.103220 (lr=1.0582e-04) (hash(x)=19127465) +2672 train 7.335126 (lr=1.0576e-04) (hash(x)=27134917) +2673 train 7.254952 (lr=1.0570e-04) (hash(x)=25673955) +2674 train 7.795224 (lr=1.0564e-04) (hash(x)=27111776) +2675 train 7.728528 (lr=1.0558e-04) (hash(x)=28962580) +2676 train 7.253798 (lr=1.0553e-04) (hash(x)=25593381) +2677 train 7.317758 (lr=1.0547e-04) (hash(x)=25238916) +2678 train 7.265368 (lr=1.0541e-04) (hash(x)=27453574) +2679 train 7.195778 (lr=1.0535e-04) (hash(x)=22426274) +2680 train 7.207572 (lr=1.0529e-04) (hash(x)=22974780) +2681 train 7.240373 (lr=1.0523e-04) (hash(x)=24668644) +2682 train 7.236226 (lr=1.0517e-04) (hash(x)=26182084) +2683 train 7.466550 (lr=1.0511e-04) (hash(x)=25606512) +2684 train 7.260410 (lr=1.0505e-04) (hash(x)=24885252) +2685 train 7.089003 (lr=1.0500e-04) (hash(x)=21290254) +2686 train 7.025917 (lr=1.0494e-04) (hash(x)=21367078) +2687 train 7.225788 (lr=1.0488e-04) (hash(x)=23785205) +2688 train 7.164318 (lr=1.0482e-04) (hash(x)=24640056) +2689 train 7.530739 (lr=1.0476e-04) (hash(x)=27083886) +2690 train 7.222995 (lr=1.0470e-04) (hash(x)=23603571) +2691 train 7.301647 (lr=1.0464e-04) (hash(x)=24779414) +2692 train 7.018122 (lr=1.0458e-04) (hash(x)=22200693) +2693 train 7.409513 (lr=1.0453e-04) (hash(x)=26907868) +2694 train 7.695912 (lr=1.0447e-04) (hash(x)=32034827) +2695 train 7.506505 (lr=1.0441e-04) (hash(x)=28505676) +2696 train 7.150227 (lr=1.0435e-04) (hash(x)=23805750) +2697 train 7.476120 (lr=1.0429e-04) (hash(x)=29804750) +2698 train 7.747852 (lr=1.0423e-04) (hash(x)=28443583) +2699 train 7.663366 (lr=1.0417e-04) (hash(x)=29156288) +2700 val loss 7.3372 +2700 val perplexity 1536.3341 +2700 train 7.365112 (lr=1.0411e-04) (hash(x)=25895743) +2701 train 7.003854 (lr=1.0405e-04) (hash(x)=21173795) +2702 train 6.916342 (lr=1.0400e-04) (hash(x)=20790866) +2703 train 7.467220 (lr=1.0394e-04) (hash(x)=27706477) +2704 train 7.593540 (lr=1.0388e-04) (hash(x)=30358985) +2705 train 7.193681 (lr=1.0382e-04) (hash(x)=23548492) +2706 train 7.305687 (lr=1.0376e-04) (hash(x)=25879696) +2707 train 7.174306 (lr=1.0370e-04) (hash(x)=23711800) +2708 train 7.704136 (lr=1.0364e-04) (hash(x)=28763123) +2709 train 7.302026 (lr=1.0358e-04) (hash(x)=23327642) +2710 train 7.385978 (lr=1.0353e-04) (hash(x)=25634166) +2711 train 7.279948 (lr=1.0347e-04) (hash(x)=28684175) +2712 train 7.377756 (lr=1.0341e-04) (hash(x)=23996278) +2713 train 7.011086 (lr=1.0335e-04) (hash(x)=21795980) +2714 train 7.324089 (lr=1.0329e-04) (hash(x)=24840769) +2715 train 7.277940 (lr=1.0323e-04) (hash(x)=25225466) +2716 train 7.564921 (lr=1.0317e-04) (hash(x)=27500471) +2717 train 7.281986 (lr=1.0311e-04) (hash(x)=24703036) +2718 train 7.379582 (lr=1.0306e-04) (hash(x)=24294293) +2719 train 7.335906 (lr=1.0300e-04) (hash(x)=28003600) +2720 train 7.102334 (lr=1.0294e-04) (hash(x)=22822962) +2721 train 7.075235 (lr=1.0288e-04) (hash(x)=24189246) +2722 train 7.180715 (lr=1.0282e-04) (hash(x)=22608951) +2723 train 7.834127 (lr=1.0276e-04) (hash(x)=27989890) +2724 train 7.449008 (lr=1.0270e-04) (hash(x)=24175838) +2725 train 7.299790 (lr=1.0265e-04) (hash(x)=24781792) +2726 train 7.144859 (lr=1.0259e-04) (hash(x)=23413276) +2727 train 7.572850 (lr=1.0253e-04) (hash(x)=27586845) +2728 train 7.356654 (lr=1.0247e-04) (hash(x)=27336264) +2729 train 7.388444 (lr=1.0241e-04) (hash(x)=26808464) +2730 train 7.219861 (lr=1.0235e-04) (hash(x)=22312009) +2731 train 7.297013 (lr=1.0229e-04) (hash(x)=22373927) +2732 train 7.243722 (lr=1.0223e-04) (hash(x)=23428834) +2733 train 7.204465 (lr=1.0218e-04) (hash(x)=25304441) +2734 train 7.230548 (lr=1.0212e-04) (hash(x)=24798164) +2735 train 7.040428 (lr=1.0206e-04) (hash(x)=21176405) +2736 train 7.139847 (lr=1.0200e-04) (hash(x)=22343075) +2737 train 7.226141 (lr=1.0194e-04) (hash(x)=23825332) +2738 train 7.241116 (lr=1.0188e-04) (hash(x)=24191865) +2739 train 7.048554 (lr=1.0182e-04) (hash(x)=23806052) +2740 train 7.138626 (lr=1.0176e-04) (hash(x)=21764591) +2741 train 7.275200 (lr=1.0171e-04) (hash(x)=25548695) +2742 train 7.460230 (lr=1.0165e-04) (hash(x)=26847535) +2743 train 7.218999 (lr=1.0159e-04) (hash(x)=25888433) +2744 train 7.175916 (lr=1.0153e-04) (hash(x)=24327454) +2745 train 7.083620 (lr=1.0147e-04) (hash(x)=22543301) +2746 train 7.491361 (lr=1.0141e-04) (hash(x)=24593022) +2747 train 8.070780 (lr=1.0135e-04) (hash(x)=27797727) +2748 train 7.536115 (lr=1.0130e-04) (hash(x)=28067682) +2749 train 7.211750 (lr=1.0124e-04) (hash(x)=25278538) +2750 val loss 7.3398 +2750 val perplexity 1540.4603 +2750 train 7.146896 (lr=1.0118e-04) (hash(x)=23875731) +2751 train 7.332152 (lr=1.0112e-04) (hash(x)=27916982) +2752 train 7.293526 (lr=1.0106e-04) (hash(x)=25726799) +2753 train 7.151100 (lr=1.0100e-04) (hash(x)=25227141) +2754 train 7.413141 (lr=1.0094e-04) (hash(x)=27679212) +2755 train 7.079049 (lr=1.0089e-04) (hash(x)=24621793) +2756 train 7.051001 (lr=1.0083e-04) (hash(x)=21962296) +2757 train 7.343386 (lr=1.0077e-04) (hash(x)=24899679) +2758 train 7.100193 (lr=1.0071e-04) (hash(x)=21452158) +2759 train 7.168126 (lr=1.0065e-04) (hash(x)=24334708) +2760 train 7.391638 (lr=1.0059e-04) (hash(x)=25523041) +2761 train 7.491588 (lr=1.0053e-04) (hash(x)=30389813) +2762 train 7.066919 (lr=1.0048e-04) (hash(x)=22426014) +2763 train 7.165543 (lr=1.0042e-04) (hash(x)=24419143) +2764 train 7.240537 (lr=1.0036e-04) (hash(x)=24850536) +2765 train 7.341749 (lr=1.0030e-04) (hash(x)=24181393) +2766 train 6.896924 (lr=1.0024e-04) (hash(x)=18882503) +2767 train 7.346572 (lr=1.0018e-04) (hash(x)=25617709) +2768 train 7.254776 (lr=1.0012e-04) (hash(x)=24076662) +2769 train 7.154594 (lr=1.0007e-04) (hash(x)=21656802) +2770 train 7.139724 (lr=1.0001e-04) (hash(x)=21014265) +2771 train 7.256130 (lr=9.9948e-05) (hash(x)=24556034) +2772 train 7.064639 (lr=9.9890e-05) (hash(x)=22046665) +2773 train 7.332382 (lr=9.9831e-05) (hash(x)=26761579) +2774 train 8.764308 (lr=9.9773e-05) (hash(x)=41414315) +2775 train 7.204916 (lr=9.9714e-05) (hash(x)=25152362) +2776 train 7.367519 (lr=9.9656e-05) (hash(x)=25567641) +2777 train 7.304019 (lr=9.9597e-05) (hash(x)=25427935) +2778 train 7.392961 (lr=9.9539e-05) (hash(x)=25824457) +2779 train 7.322137 (lr=9.9480e-05) (hash(x)=24326376) +2780 train 7.303452 (lr=9.9422e-05) (hash(x)=27447230) +2781 train 7.176147 (lr=9.9363e-05) (hash(x)=24003710) +2782 train 7.088025 (lr=9.9305e-05) (hash(x)=24157390) +2783 train 7.229405 (lr=9.9246e-05) (hash(x)=24276512) +2784 train 7.095270 (lr=9.9188e-05) (hash(x)=21503752) +2785 train 6.988012 (lr=9.9129e-05) (hash(x)=20031488) +2786 train 7.082803 (lr=9.9071e-05) (hash(x)=21788715) +2787 train 7.210705 (lr=9.9012e-05) (hash(x)=24344695) +2788 train 7.214203 (lr=9.8954e-05) (hash(x)=22927763) +2789 train 7.142184 (lr=9.8895e-05) (hash(x)=23710755) +2790 train 7.360817 (lr=9.8837e-05) (hash(x)=26924620) +2791 train 7.696132 (lr=9.8778e-05) (hash(x)=26776133) +2792 train 7.164577 (lr=9.8720e-05) (hash(x)=19936770) +2793 train 7.296510 (lr=9.8662e-05) (hash(x)=25440959) +2794 train 7.256621 (lr=9.8603e-05) (hash(x)=25146097) +2795 train 7.018009 (lr=9.8545e-05) (hash(x)=21847282) +2796 train 7.221626 (lr=9.8486e-05) (hash(x)=25639784) +2797 train 7.023141 (lr=9.8428e-05) (hash(x)=21199921) +2798 train 7.216671 (lr=9.8369e-05) (hash(x)=22360806) +2799 train 6.678482 (lr=9.8311e-05) (hash(x)=20254159) +2800 val loss 7.3138 +2800 val perplexity 1500.8494 +2800 train 6.838234 (lr=9.8253e-05) (hash(x)=23348345) +2801 train 7.381130 (lr=9.8194e-05) (hash(x)=24908033) +2802 train 7.158418 (lr=9.8136e-05) (hash(x)=23350309) +2803 train 7.272580 (lr=9.8077e-05) (hash(x)=25044762) +2804 train 7.158879 (lr=9.8019e-05) (hash(x)=24071026) +2805 train 6.959999 (lr=9.7961e-05) (hash(x)=22169363) +2806 train 7.208783 (lr=9.7902e-05) (hash(x)=23757564) +2807 train 7.637393 (lr=9.7844e-05) (hash(x)=27873855) +2808 train 7.433254 (lr=9.7786e-05) (hash(x)=26577893) +2809 train 7.450466 (lr=9.7727e-05) (hash(x)=27001634) +2810 train 7.212596 (lr=9.7669e-05) (hash(x)=24796541) +2811 train 7.144888 (lr=9.7611e-05) (hash(x)=22575615) +2812 train 7.206618 (lr=9.7552e-05) (hash(x)=25876475) +2813 train 7.213631 (lr=9.7494e-05) (hash(x)=24765155) +2814 train 7.193032 (lr=9.7436e-05) (hash(x)=25785699) +2815 train 7.390579 (lr=9.7377e-05) (hash(x)=25113614) +2816 train 7.209648 (lr=9.7319e-05) (hash(x)=24415748) +2817 train 7.333789 (lr=9.7261e-05) (hash(x)=25140622) +2818 train 7.240067 (lr=9.7202e-05) (hash(x)=24845866) +2819 train 7.642851 (lr=9.7144e-05) (hash(x)=28062905) +2820 train 7.229478 (lr=9.7086e-05) (hash(x)=22041086) +2821 train 7.297431 (lr=9.7027e-05) (hash(x)=24957184) +2822 train 7.243123 (lr=9.6969e-05) (hash(x)=24360380) +2823 train 7.370584 (lr=9.6911e-05) (hash(x)=26192886) +2824 train 7.275553 (lr=9.6853e-05) (hash(x)=25001858) +2825 train 7.243019 (lr=9.6794e-05) (hash(x)=24721193) +2826 train 7.299031 (lr=9.6736e-05) (hash(x)=26186227) +2827 train 7.262524 (lr=9.6678e-05) (hash(x)=25770338) +2828 train 7.316566 (lr=9.6619e-05) (hash(x)=25920767) +2829 train 7.258195 (lr=9.6561e-05) (hash(x)=25060684) +2830 train 6.975984 (lr=9.6503e-05) (hash(x)=22933946) +2831 train 7.130574 (lr=9.6445e-05) (hash(x)=24614912) +2832 train 6.927886 (lr=9.6387e-05) (hash(x)=19955522) +2833 train 6.964955 (lr=9.6328e-05) (hash(x)=21111215) +2834 train 7.773105 (lr=9.6270e-05) (hash(x)=28817924) +2835 train 7.285883 (lr=9.6212e-05) (hash(x)=26934071) +2836 train 7.252182 (lr=9.6154e-05) (hash(x)=24768851) +2837 train 7.209146 (lr=9.6095e-05) (hash(x)=25706447) +2838 train 7.050347 (lr=9.6037e-05) (hash(x)=19579834) +2839 train 7.296043 (lr=9.5979e-05) (hash(x)=25397093) +2840 train 7.714308 (lr=9.5921e-05) (hash(x)=27902141) +2841 train 7.317589 (lr=9.5863e-05) (hash(x)=25383069) +2842 train 7.155618 (lr=9.5805e-05) (hash(x)=22007373) +2843 train 7.191745 (lr=9.5746e-05) (hash(x)=25925963) +2844 train 7.252900 (lr=9.5688e-05) (hash(x)=25711128) +2845 train 7.063475 (lr=9.5630e-05) (hash(x)=21881216) +2846 train 7.150214 (lr=9.5572e-05) (hash(x)=20277075) +2847 train 7.204206 (lr=9.5514e-05) (hash(x)=19811802) +2848 train 7.129973 (lr=9.5456e-05) (hash(x)=23878906) +2849 train 7.304462 (lr=9.5398e-05) (hash(x)=25034966) +2850 val loss 7.3062 +2850 val perplexity 1489.5092 +2850 train 7.386137 (lr=9.5339e-05) (hash(x)=24359507) +2851 train 7.146464 (lr=9.5281e-05) (hash(x)=23248423) +2852 train 7.145927 (lr=9.5223e-05) (hash(x)=21782773) +2853 train 7.245819 (lr=9.5165e-05) (hash(x)=23804418) +2854 train 7.281057 (lr=9.5107e-05) (hash(x)=22525078) +2855 train 7.242582 (lr=9.5049e-05) (hash(x)=25579655) +2856 train 7.380309 (lr=9.4991e-05) (hash(x)=27048876) +2857 train 7.510609 (lr=9.4933e-05) (hash(x)=26468479) +2858 train 7.230467 (lr=9.4875e-05) (hash(x)=23854933) +2859 train 7.532569 (lr=9.4817e-05) (hash(x)=25537603) +2860 train 7.007641 (lr=9.4759e-05) (hash(x)=20979252) +2861 train 7.530206 (lr=9.4700e-05) (hash(x)=26504374) +2862 train 7.379407 (lr=9.4642e-05) (hash(x)=27561842) +2863 train 7.348349 (lr=9.4584e-05) (hash(x)=26096514) +2864 train 7.359684 (lr=9.4526e-05) (hash(x)=25926899) +2865 train 7.392873 (lr=9.4468e-05) (hash(x)=26058348) +2866 train 7.398319 (lr=9.4410e-05) (hash(x)=29802259) +2867 train 7.288151 (lr=9.4352e-05) (hash(x)=24132888) +2868 train 6.999971 (lr=9.4294e-05) (hash(x)=23369410) +2869 train 7.202796 (lr=9.4236e-05) (hash(x)=25387506) +2870 train 7.382698 (lr=9.4178e-05) (hash(x)=27375344) +2871 train 7.087965 (lr=9.4120e-05) (hash(x)=22589633) +2872 train 7.255945 (lr=9.4062e-05) (hash(x)=23250237) +2873 train 7.213104 (lr=9.4004e-05) (hash(x)=25511322) +2874 train 6.858552 (lr=9.3946e-05) (hash(x)=18356418) +2875 train 7.268517 (lr=9.3888e-05) (hash(x)=27781566) +2876 train 7.128696 (lr=9.3831e-05) (hash(x)=24878173) +2877 train 7.616806 (lr=9.3773e-05) (hash(x)=30018637) +2878 train 7.488620 (lr=9.3715e-05) (hash(x)=27168416) +2879 train 7.442050 (lr=9.3657e-05) (hash(x)=26757147) +2880 train 7.462068 (lr=9.3599e-05) (hash(x)=26637081) +2881 train 7.341712 (lr=9.3541e-05) (hash(x)=24795024) +2882 train 7.571529 (lr=9.3483e-05) (hash(x)=29787745) +2883 train 7.426052 (lr=9.3425e-05) (hash(x)=26649864) +2884 train 7.270690 (lr=9.3367e-05) (hash(x)=27306612) +2885 train 7.376853 (lr=9.3309e-05) (hash(x)=27568311) +2886 train 7.406325 (lr=9.3251e-05) (hash(x)=27440150) +2887 train 7.136436 (lr=9.3194e-05) (hash(x)=24963730) +2888 train 7.151721 (lr=9.3136e-05) (hash(x)=23619807) +2889 train 7.637908 (lr=9.3078e-05) (hash(x)=29447356) +2890 train 7.199819 (lr=9.3020e-05) (hash(x)=25144675) +2891 train 7.141264 (lr=9.2962e-05) (hash(x)=25249959) +2892 train 7.132851 (lr=9.2904e-05) (hash(x)=26608712) +2893 train 7.154037 (lr=9.2846e-05) (hash(x)=26333258) +2894 train 6.946951 (lr=9.2789e-05) (hash(x)=20682182) +2895 train 7.344594 (lr=9.2731e-05) (hash(x)=27703124) +2896 train 7.177793 (lr=9.2673e-05) (hash(x)=23228180) +2897 train 7.062666 (lr=9.2615e-05) (hash(x)=25252411) +2898 train 7.019506 (lr=9.2557e-05) (hash(x)=22879178) +2899 train 7.276844 (lr=9.2500e-05) (hash(x)=26459082) +2900 val loss 7.3031 +2900 val perplexity 1484.9188 +2900 train 7.127435 (lr=9.2442e-05) (hash(x)=24569501) +2901 train 6.939636 (lr=9.2384e-05) (hash(x)=19803884) +2902 train 7.027669 (lr=9.2326e-05) (hash(x)=18799747) +2903 train 7.264431 (lr=9.2269e-05) (hash(x)=24781713) +2904 train 7.386008 (lr=9.2211e-05) (hash(x)=25016590) +2905 train 7.568639 (lr=9.2153e-05) (hash(x)=29006906) +2906 train 7.326516 (lr=9.2095e-05) (hash(x)=24069959) +2907 train 7.463508 (lr=9.2038e-05) (hash(x)=26597693) +2908 train 7.072061 (lr=9.1980e-05) (hash(x)=25014146) +2909 train 7.328341 (lr=9.1922e-05) (hash(x)=24943747) +2910 train 7.247052 (lr=9.1865e-05) (hash(x)=27847542) +2911 train 7.192186 (lr=9.1807e-05) (hash(x)=24720476) +2912 train 7.055440 (lr=9.1749e-05) (hash(x)=24388804) +2913 train 7.180192 (lr=9.1691e-05) (hash(x)=23567535) +2914 train 7.471330 (lr=9.1634e-05) (hash(x)=29673625) +2915 train 7.243573 (lr=9.1576e-05) (hash(x)=23691295) +2916 train 7.603746 (lr=9.1518e-05) (hash(x)=26572819) +2917 train 7.266843 (lr=9.1461e-05) (hash(x)=23237812) +2918 train 7.493130 (lr=9.1403e-05) (hash(x)=26531016) +2919 train 7.059743 (lr=9.1346e-05) (hash(x)=23481301) +2920 train 7.304045 (lr=9.1288e-05) (hash(x)=24839184) +2921 train 7.149621 (lr=9.1230e-05) (hash(x)=23327755) +2922 train 7.376302 (lr=9.1173e-05) (hash(x)=26347114) +2923 train 7.095254 (lr=9.1115e-05) (hash(x)=23295676) +2924 train 7.128053 (lr=9.1058e-05) (hash(x)=24557178) +2925 train 7.180815 (lr=9.1000e-05) (hash(x)=26067788) +2926 train 7.135910 (lr=9.0942e-05) (hash(x)=25694982) +2927 train 7.224313 (lr=9.0885e-05) (hash(x)=25641033) +2928 train 7.268804 (lr=9.0827e-05) (hash(x)=24906422) +2929 train 7.473056 (lr=9.0770e-05) (hash(x)=27803515) +2930 train 7.430984 (lr=9.0712e-05) (hash(x)=26208803) +2931 train 6.958528 (lr=9.0655e-05) (hash(x)=22441379) +2932 train 7.196691 (lr=9.0597e-05) (hash(x)=24741626) +2933 train 7.088117 (lr=9.0540e-05) (hash(x)=24595257) +2934 train 7.105044 (lr=9.0482e-05) (hash(x)=23939167) +2935 train 7.395889 (lr=9.0425e-05) (hash(x)=27369437) +2936 train 7.067361 (lr=9.0367e-05) (hash(x)=21409783) +2937 train 7.321725 (lr=9.0310e-05) (hash(x)=25923735) +2938 train 7.312370 (lr=9.0252e-05) (hash(x)=29559511) +2939 train 7.227715 (lr=9.0195e-05) (hash(x)=24482272) +2940 train 7.188033 (lr=9.0137e-05) (hash(x)=24767658) +2941 train 7.376317 (lr=9.0080e-05) (hash(x)=26425020) +2942 train 7.688489 (lr=9.0022e-05) (hash(x)=27444868) +2943 train 7.196720 (lr=8.9965e-05) (hash(x)=24760900) +2944 train 7.262544 (lr=8.9907e-05) (hash(x)=25605407) +2945 train 7.100482 (lr=8.9850e-05) (hash(x)=22886951) +2946 train 7.410989 (lr=8.9793e-05) (hash(x)=26112205) +2947 train 7.231731 (lr=8.9735e-05) (hash(x)=23919156) +2948 train 7.192539 (lr=8.9678e-05) (hash(x)=23729312) +2949 train 7.496913 (lr=8.9621e-05) (hash(x)=30440878) +2950 val loss 7.2926 +2950 val perplexity 1469.3262 +2950 train 6.971757 (lr=8.9563e-05) (hash(x)=20004041) +2951 train 6.913471 (lr=8.9506e-05) (hash(x)=21692546) +2952 train 6.963555 (lr=8.9448e-05) (hash(x)=23021681) +2953 train 7.324646 (lr=8.9391e-05) (hash(x)=26663597) +2954 train 7.164104 (lr=8.9334e-05) (hash(x)=23727385) +2955 train 7.186522 (lr=8.9276e-05) (hash(x)=27692087) +2956 train 7.224515 (lr=8.9219e-05) (hash(x)=24003378) +2957 train 7.831256 (lr=8.9162e-05) (hash(x)=29534673) +2958 train 7.115051 (lr=8.9104e-05) (hash(x)=22875068) +2959 train 7.141991 (lr=8.9047e-05) (hash(x)=22720391) +2960 train 6.919338 (lr=8.8990e-05) (hash(x)=17997400) +2961 train 7.102728 (lr=8.8933e-05) (hash(x)=22853822) +2962 train 7.189579 (lr=8.8875e-05) (hash(x)=25238004) +2963 train 7.259349 (lr=8.8818e-05) (hash(x)=26146560) +2964 train 7.398027 (lr=8.8761e-05) (hash(x)=21894867) +2965 train 7.412041 (lr=8.8704e-05) (hash(x)=23001150) +2966 train 7.132300 (lr=8.8646e-05) (hash(x)=23392923) +2967 train 7.194911 (lr=8.8589e-05) (hash(x)=24376979) +2968 train 7.147775 (lr=8.8532e-05) (hash(x)=23781449) +2969 train 7.323907 (lr=8.8475e-05) (hash(x)=25315495) +2970 train 7.420662 (lr=8.8418e-05) (hash(x)=27165470) +2971 train 7.261791 (lr=8.8360e-05) (hash(x)=22917712) +2972 train 7.626534 (lr=8.8303e-05) (hash(x)=27928456) +2973 train 7.070414 (lr=8.8246e-05) (hash(x)=19890855) +2974 train 7.041913 (lr=8.8189e-05) (hash(x)=21318134) +2975 train 7.119177 (lr=8.8132e-05) (hash(x)=22244509) +2976 train 7.032364 (lr=8.8075e-05) (hash(x)=21293137) +2977 train 7.209941 (lr=8.8018e-05) (hash(x)=23465789) +2978 train 7.142396 (lr=8.7960e-05) (hash(x)=21169753) +2979 train 7.485578 (lr=8.7903e-05) (hash(x)=25243385) +2980 train 7.488305 (lr=8.7846e-05) (hash(x)=27465812) +2981 train 7.220895 (lr=8.7789e-05) (hash(x)=24615492) +2982 train 7.159862 (lr=8.7732e-05) (hash(x)=23081307) +2983 train 6.927368 (lr=8.7675e-05) (hash(x)=21831960) +2984 train 7.065830 (lr=8.7618e-05) (hash(x)=23242850) +2985 train 7.176057 (lr=8.7561e-05) (hash(x)=24308188) +2986 train 7.341155 (lr=8.7504e-05) (hash(x)=28541601) +2987 train 7.228209 (lr=8.7447e-05) (hash(x)=24842373) +2988 train 6.981864 (lr=8.7390e-05) (hash(x)=21967126) +2989 train 7.160128 (lr=8.7333e-05) (hash(x)=22951616) +2990 train 7.267161 (lr=8.7276e-05) (hash(x)=24325714) +2991 train 7.082738 (lr=8.7219e-05) (hash(x)=24921535) +2992 train 7.297237 (lr=8.7162e-05) (hash(x)=25937112) +2993 train 7.025169 (lr=8.7105e-05) (hash(x)=20716218) +2994 train 7.255765 (lr=8.7048e-05) (hash(x)=25450724) +2995 train 7.182066 (lr=8.6991e-05) (hash(x)=24344615) +2996 train 6.938771 (lr=8.6934e-05) (hash(x)=20299058) +2997 train 7.178586 (lr=8.6877e-05) (hash(x)=23859426) +2998 train 7.204376 (lr=8.6820e-05) (hash(x)=23094397) +2999 train 7.485147 (lr=8.6763e-05) (hash(x)=25381251) +3000 val loss 7.2948 +3000 val perplexity 1472.6108 +3000 train 7.185324 (lr=8.6706e-05) (hash(x)=23586527) +3001 train 7.080072 (lr=8.6649e-05) (hash(x)=24220410) +3002 train 6.958899 (lr=8.6593e-05) (hash(x)=20597347) +3003 train 7.076212 (lr=8.6536e-05) (hash(x)=22887303) +3004 train 7.338090 (lr=8.6479e-05) (hash(x)=25869462) +3005 train 7.128601 (lr=8.6422e-05) (hash(x)=22098530) +3006 train 7.365320 (lr=8.6365e-05) (hash(x)=26246291) +3007 train 7.312105 (lr=8.6308e-05) (hash(x)=25687352) +3008 train 7.043643 (lr=8.6251e-05) (hash(x)=25425646) +3009 train 7.259064 (lr=8.6195e-05) (hash(x)=26021124) +3010 train 7.290242 (lr=8.6138e-05) (hash(x)=25392057) +3011 train 7.380787 (lr=8.6081e-05) (hash(x)=27791412) +3012 train 7.202806 (lr=8.6024e-05) (hash(x)=23181098) +3013 train 7.221189 (lr=8.5967e-05) (hash(x)=25521889) +3014 train 7.044946 (lr=8.5911e-05) (hash(x)=21685795) +3015 train 7.155634 (lr=8.5854e-05) (hash(x)=25221654) +3016 train 7.371807 (lr=8.5797e-05) (hash(x)=24888744) +3017 train 7.276541 (lr=8.5740e-05) (hash(x)=24200150) +3018 train 7.229425 (lr=8.5684e-05) (hash(x)=26943942) +3019 train 7.240623 (lr=8.5627e-05) (hash(x)=23243731) +3020 train 7.137930 (lr=8.5570e-05) (hash(x)=21068284) +3021 train 7.263790 (lr=8.5514e-05) (hash(x)=23876902) +3022 train 7.346028 (lr=8.5457e-05) (hash(x)=25337639) +3023 train 7.257204 (lr=8.5400e-05) (hash(x)=24469863) +3024 train 7.724023 (lr=8.5344e-05) (hash(x)=27850876) +3025 train 7.488318 (lr=8.5287e-05) (hash(x)=20515778) +3026 train 7.309536 (lr=8.5230e-05) (hash(x)=29019173) +3027 train 7.005002 (lr=8.5174e-05) (hash(x)=22484936) +3028 train 7.122882 (lr=8.5117e-05) (hash(x)=24639400) +3029 train 7.323872 (lr=8.5061e-05) (hash(x)=26835174) +3030 train 7.373445 (lr=8.5004e-05) (hash(x)=29843763) +3031 train 7.164404 (lr=8.4947e-05) (hash(x)=25291413) +3032 train 7.095553 (lr=8.4891e-05) (hash(x)=24590244) +3033 train 7.316832 (lr=8.4834e-05) (hash(x)=28880142) +3034 train 7.097988 (lr=8.4778e-05) (hash(x)=23372199) +3035 train 7.091322 (lr=8.4721e-05) (hash(x)=23952225) +3036 train 7.198600 (lr=8.4665e-05) (hash(x)=24589186) +3037 train 7.199990 (lr=8.4608e-05) (hash(x)=23260323) +3038 train 7.350626 (lr=8.4552e-05) (hash(x)=25824498) +3039 train 7.227378 (lr=8.4495e-05) (hash(x)=25744274) +3040 train 7.248222 (lr=8.4439e-05) (hash(x)=21610247) +3041 train 7.321416 (lr=8.4382e-05) (hash(x)=25079786) +3042 train 6.989358 (lr=8.4326e-05) (hash(x)=23219195) +3043 train 6.940498 (lr=8.4269e-05) (hash(x)=22616739) +3044 train 7.215692 (lr=8.4213e-05) (hash(x)=24908480) +3045 train 7.022163 (lr=8.4156e-05) (hash(x)=22293489) +3046 train 7.078785 (lr=8.4100e-05) (hash(x)=23557651) +3047 train 7.139624 (lr=8.4044e-05) (hash(x)=24246963) +3048 train 7.251831 (lr=8.3987e-05) (hash(x)=24490083) +3049 train 7.264196 (lr=8.3931e-05) (hash(x)=22372895) +3050 val loss 7.2838 +3050 val perplexity 1456.4451 +3050 train 6.992739 (lr=8.3874e-05) (hash(x)=21759470) +3051 train 6.905221 (lr=8.3818e-05) (hash(x)=19407094) +3052 train 7.194753 (lr=8.3762e-05) (hash(x)=23957047) +3053 train 7.316573 (lr=8.3705e-05) (hash(x)=24719318) +3054 train 7.143580 (lr=8.3649e-05) (hash(x)=20719314) +3055 train 7.060503 (lr=8.3593e-05) (hash(x)=19724058) +3056 train 6.962299 (lr=8.3536e-05) (hash(x)=14407266) +3057 train 6.843732 (lr=8.3480e-05) (hash(x)=12468292) +3058 train 7.052566 (lr=8.3424e-05) (hash(x)=16098279) +3059 train 7.153543 (lr=8.3368e-05) (hash(x)=18836491) +3060 train 6.969727 (lr=8.3311e-05) (hash(x)=19132277) +3061 train 7.143739 (lr=8.3255e-05) (hash(x)=22814208) +3062 train 7.134997 (lr=8.3199e-05) (hash(x)=24838508) +3063 train 7.034740 (lr=8.3143e-05) (hash(x)=20705649) +3064 train 8.008156 (lr=8.3086e-05) (hash(x)=29416914) +3065 train 7.458492 (lr=8.3030e-05) (hash(x)=25972430) +3066 train 6.862232 (lr=8.2974e-05) (hash(x)=23705805) +3067 train 6.944443 (lr=8.2918e-05) (hash(x)=21325875) +3068 train 7.138268 (lr=8.2862e-05) (hash(x)=23526506) +3069 train 7.612222 (lr=8.2805e-05) (hash(x)=27282337) +3070 train 7.480983 (lr=8.2749e-05) (hash(x)=27968043) +3071 train 7.260452 (lr=8.2693e-05) (hash(x)=24938685) +3072 train 7.479747 (lr=8.2637e-05) (hash(x)=26942737) +3073 train 7.395664 (lr=8.2581e-05) (hash(x)=23506879) +3074 train 7.090448 (lr=8.2525e-05) (hash(x)=23589913) +3075 train 7.235748 (lr=8.2469e-05) (hash(x)=25152403) +3076 train 7.364638 (lr=8.2413e-05) (hash(x)=23425868) +3077 train 7.551149 (lr=8.2357e-05) (hash(x)=23966181) +3078 train 7.602995 (lr=8.2301e-05) (hash(x)=27312570) +3079 train 7.198310 (lr=8.2244e-05) (hash(x)=21707000) +3080 train 7.161212 (lr=8.2188e-05) (hash(x)=25600427) +3081 train 7.246617 (lr=8.2132e-05) (hash(x)=24270631) +3082 train 7.376260 (lr=8.2076e-05) (hash(x)=25199537) +3083 train 6.724260 (lr=8.2020e-05) (hash(x)=17952018) +3084 train 6.813541 (lr=8.1964e-05) (hash(x)=18733143) +3085 train 7.411540 (lr=8.1909e-05) (hash(x)=26946100) +3086 train 7.206090 (lr=8.1853e-05) (hash(x)=25547515) +3087 train 7.170590 (lr=8.1797e-05) (hash(x)=24948980) +3088 train 8.317919 (lr=8.1741e-05) (hash(x)=35461645) +3089 train 7.411902 (lr=8.1685e-05) (hash(x)=28330877) +3090 train 7.317293 (lr=8.1629e-05) (hash(x)=27687861) +3091 train 7.433431 (lr=8.1573e-05) (hash(x)=28012110) +3092 train 7.291223 (lr=8.1517e-05) (hash(x)=24684480) +3093 train 7.236841 (lr=8.1461e-05) (hash(x)=26225786) +3094 train 6.967981 (lr=8.1405e-05) (hash(x)=23098156) +3095 train 7.553596 (lr=8.1349e-05) (hash(x)=30773958) +3096 train 7.831175 (lr=8.1294e-05) (hash(x)=28640406) +3097 train 7.755714 (lr=8.1238e-05) (hash(x)=28201086) +3098 train 8.122397 (lr=8.1182e-05) (hash(x)=35002344) +3099 train 7.644536 (lr=8.1126e-05) (hash(x)=29481068) +3100 val loss 7.3009 +3100 val perplexity 1481.5911 +3100 train 7.176161 (lr=8.1070e-05) (hash(x)=26374528) +3101 train 7.197241 (lr=8.1015e-05) (hash(x)=24153602) +3102 train 7.217304 (lr=8.0959e-05) (hash(x)=25478746) +3103 train 7.501625 (lr=8.0903e-05) (hash(x)=26769046) +3104 train 7.186805 (lr=8.0847e-05) (hash(x)=21841970) +3105 train 7.397069 (lr=8.0792e-05) (hash(x)=27693052) +3106 train 6.961632 (lr=8.0736e-05) (hash(x)=20689448) +3107 train 7.263175 (lr=8.0680e-05) (hash(x)=26755048) +3108 train 7.259103 (lr=8.0625e-05) (hash(x)=24431904) +3109 train 7.112427 (lr=8.0569e-05) (hash(x)=21009792) +3110 train 7.170737 (lr=8.0513e-05) (hash(x)=21909003) +3111 train 7.221537 (lr=8.0458e-05) (hash(x)=18849656) +3112 train 7.350117 (lr=8.0402e-05) (hash(x)=22223376) +3113 train 7.617604 (lr=8.0346e-05) (hash(x)=25652491) +3114 train 7.533597 (lr=8.0291e-05) (hash(x)=23521434) +3115 train 7.593033 (lr=8.0235e-05) (hash(x)=25449800) +3116 train 7.967026 (lr=8.0180e-05) (hash(x)=27655847) +3117 train 8.009819 (lr=8.0124e-05) (hash(x)=29878248) +3118 train 8.067372 (lr=8.0068e-05) (hash(x)=30444094) +3119 train 7.656363 (lr=8.0013e-05) (hash(x)=24624950) +3120 train 6.947979 (lr=7.9957e-05) (hash(x)=20798511) +3121 train 7.330127 (lr=7.9902e-05) (hash(x)=26581679) +3122 train 7.250722 (lr=7.9846e-05) (hash(x)=25333422) +3123 train 7.294158 (lr=7.9791e-05) (hash(x)=26174069) +3124 train 7.343990 (lr=7.9735e-05) (hash(x)=25219475) +3125 train 7.254767 (lr=7.9680e-05) (hash(x)=20919061) +3126 train 7.199871 (lr=7.9624e-05) (hash(x)=23828688) +3127 train 7.738739 (lr=7.9569e-05) (hash(x)=27299605) +3128 train 7.092406 (lr=7.9514e-05) (hash(x)=23797514) +3129 train 7.330029 (lr=7.9458e-05) (hash(x)=23601883) +3130 train 7.547919 (lr=7.9403e-05) (hash(x)=31003964) +3131 train 7.268299 (lr=7.9347e-05) (hash(x)=24777273) +3132 train 7.160710 (lr=7.9292e-05) (hash(x)=25403249) +3133 train 7.371260 (lr=7.9237e-05) (hash(x)=28913150) +3134 train 7.366573 (lr=7.9181e-05) (hash(x)=26541508) +3135 train 7.296860 (lr=7.9126e-05) (hash(x)=24113445) +3136 train 7.092065 (lr=7.9071e-05) (hash(x)=25464565) +3137 train 7.336853 (lr=7.9015e-05) (hash(x)=26581432) +3138 train 7.189313 (lr=7.8960e-05) (hash(x)=23074513) +3139 train 7.055466 (lr=7.8905e-05) (hash(x)=23970384) +3140 train 7.285016 (lr=7.8849e-05) (hash(x)=26694495) +3141 train 7.232970 (lr=7.8794e-05) (hash(x)=26883445) +3142 train 7.404420 (lr=7.8739e-05) (hash(x)=28632211) +3143 train 7.803848 (lr=7.8684e-05) (hash(x)=32644465) +3144 train 7.559273 (lr=7.8629e-05) (hash(x)=27490443) +3145 train 7.134624 (lr=7.8573e-05) (hash(x)=23814853) +3146 train 7.573946 (lr=7.8518e-05) (hash(x)=29664236) +3147 train 7.860059 (lr=7.8463e-05) (hash(x)=29951548) +3148 train 7.655454 (lr=7.8408e-05) (hash(x)=28426503) +3149 train 7.047211 (lr=7.8353e-05) (hash(x)=23727657) +3150 val loss 7.2928 +3150 val perplexity 1469.6786 +3150 train 7.170350 (lr=7.8297e-05) (hash(x)=21430659) +3151 train 7.222411 (lr=7.8242e-05) (hash(x)=25829219) +3152 train 7.389049 (lr=7.8187e-05) (hash(x)=29735208) +3153 train 7.423022 (lr=7.8132e-05) (hash(x)=28173447) +3154 train 7.132661 (lr=7.8077e-05) (hash(x)=22909641) +3155 train 7.314195 (lr=7.8022e-05) (hash(x)=20556094) +3156 train 7.069695 (lr=7.7967e-05) (hash(x)=24013769) +3157 train 7.051836 (lr=7.7912e-05) (hash(x)=22525971) +3158 train 7.115750 (lr=7.7857e-05) (hash(x)=25492728) +3159 train 7.177668 (lr=7.7802e-05) (hash(x)=25194550) +3160 train 7.265999 (lr=7.7747e-05) (hash(x)=25610603) +3161 train 7.257761 (lr=7.7692e-05) (hash(x)=23848640) +3162 train 7.090215 (lr=7.7637e-05) (hash(x)=24082226) +3163 train 7.463649 (lr=7.7582e-05) (hash(x)=28482186) +3164 train 7.363455 (lr=7.7527e-05) (hash(x)=27542978) +3165 train 7.118462 (lr=7.7472e-05) (hash(x)=22540954) +3166 train 7.239920 (lr=7.7417e-05) (hash(x)=26103641) +3167 train 7.210251 (lr=7.7362e-05) (hash(x)=25941804) +3168 train 7.229224 (lr=7.7307e-05) (hash(x)=25965921) +3169 train 7.462787 (lr=7.7253e-05) (hash(x)=25631269) +3170 train 7.068012 (lr=7.7198e-05) (hash(x)=23471525) +3171 train 7.315103 (lr=7.7143e-05) (hash(x)=27049208) +3172 train 7.319556 (lr=7.7088e-05) (hash(x)=27074992) +3173 train 7.247779 (lr=7.7033e-05) (hash(x)=25712617) +3174 train 7.210895 (lr=7.6978e-05) (hash(x)=25884917) +3175 train 7.230940 (lr=7.6924e-05) (hash(x)=24075727) +3176 train 7.113464 (lr=7.6869e-05) (hash(x)=23681759) +3177 train 7.381869 (lr=7.6814e-05) (hash(x)=25786577) +3178 train 7.396717 (lr=7.6759e-05) (hash(x)=27307614) +3179 train 7.411659 (lr=7.6705e-05) (hash(x)=25082806) +3180 train 7.358928 (lr=7.6650e-05) (hash(x)=26098308) +3181 train 7.170990 (lr=7.6595e-05) (hash(x)=24080140) +3182 train 7.330969 (lr=7.6540e-05) (hash(x)=26399395) +3183 train 7.430266 (lr=7.6486e-05) (hash(x)=23104539) +3184 train 7.055261 (lr=7.6431e-05) (hash(x)=23356930) +3185 train 7.301942 (lr=7.6376e-05) (hash(x)=27972420) +3186 train 6.975779 (lr=7.6322e-05) (hash(x)=21338924) +3187 train 7.399616 (lr=7.6267e-05) (hash(x)=25351113) +3188 train 7.315051 (lr=7.6213e-05) (hash(x)=26019439) +3189 train 7.380105 (lr=7.6158e-05) (hash(x)=30149312) +3190 train 7.078269 (lr=7.6103e-05) (hash(x)=23028152) +3191 train 7.490486 (lr=7.6049e-05) (hash(x)=23018983) +3192 train 7.060562 (lr=7.5994e-05) (hash(x)=23190787) +3193 train 7.484170 (lr=7.5940e-05) (hash(x)=27798543) +3194 train 7.246121 (lr=7.5885e-05) (hash(x)=25193663) +3195 train 7.078042 (lr=7.5831e-05) (hash(x)=25302106) +3196 train 7.204208 (lr=7.5776e-05) (hash(x)=24325364) +3197 train 7.245560 (lr=7.5722e-05) (hash(x)=25399101) +3198 train 7.080525 (lr=7.5667e-05) (hash(x)=23606439) +3199 train 7.152420 (lr=7.5613e-05) (hash(x)=24422929) +3200 val loss 7.2703 +3200 val perplexity 1436.9923 +3200 train 7.299563 (lr=7.5558e-05) (hash(x)=24760381) +3201 train 6.984029 (lr=7.5504e-05) (hash(x)=23278576) +3202 train 7.219166 (lr=7.5450e-05) (hash(x)=24897511) +3203 train 7.493605 (lr=7.5395e-05) (hash(x)=29052117) +3204 train 7.251967 (lr=7.5341e-05) (hash(x)=25772923) +3205 train 7.395178 (lr=7.5287e-05) (hash(x)=25885977) +3206 train 7.177345 (lr=7.5232e-05) (hash(x)=21985272) +3207 train 7.107812 (lr=7.5178e-05) (hash(x)=23389696) +3208 train 7.025453 (lr=7.5124e-05) (hash(x)=25299042) +3209 train 7.297447 (lr=7.5069e-05) (hash(x)=23703987) +3210 train 7.173492 (lr=7.5015e-05) (hash(x)=23362342) +3211 train 7.235206 (lr=7.4961e-05) (hash(x)=23962503) +3212 train 7.150188 (lr=7.4907e-05) (hash(x)=21216023) +3213 train 7.197483 (lr=7.4852e-05) (hash(x)=25841931) +3214 train 7.105237 (lr=7.4798e-05) (hash(x)=23631428) +3215 train 7.466020 (lr=7.4744e-05) (hash(x)=29102969) +3216 train 7.295597 (lr=7.4690e-05) (hash(x)=25782766) +3217 train 7.463098 (lr=7.4635e-05) (hash(x)=28825867) +3218 train 7.417713 (lr=7.4581e-05) (hash(x)=24609499) +3219 train 7.358890 (lr=7.4527e-05) (hash(x)=24948166) +3220 train 7.413792 (lr=7.4473e-05) (hash(x)=26919841) +3221 train 7.265663 (lr=7.4419e-05) (hash(x)=27236198) +3222 train 7.052101 (lr=7.4365e-05) (hash(x)=24029305) +3223 train 7.602630 (lr=7.4311e-05) (hash(x)=28359859) +3224 train 7.408144 (lr=7.4257e-05) (hash(x)=24886008) +3225 train 7.222097 (lr=7.4203e-05) (hash(x)=27159867) +3226 train 7.479727 (lr=7.4149e-05) (hash(x)=20672023) +3227 train 7.177516 (lr=7.4095e-05) (hash(x)=22360298) +3228 train 7.584453 (lr=7.4041e-05) (hash(x)=27478658) +3229 train 7.377017 (lr=7.3987e-05) (hash(x)=26575886) +3230 train 7.560407 (lr=7.3933e-05) (hash(x)=26890615) +3231 train 7.184711 (lr=7.3879e-05) (hash(x)=24630955) +3232 train 7.459930 (lr=7.3825e-05) (hash(x)=27016054) +3233 train 7.672386 (lr=7.3771e-05) (hash(x)=28444407) +3234 train 7.077791 (lr=7.3717e-05) (hash(x)=24053336) +3235 train 7.363689 (lr=7.3663e-05) (hash(x)=26897402) +3236 train 7.526464 (lr=7.3609e-05) (hash(x)=29451214) +3237 train 7.329697 (lr=7.3555e-05) (hash(x)=27268677) +3238 train 7.445668 (lr=7.3501e-05) (hash(x)=27494000) +3239 train 7.107826 (lr=7.3448e-05) (hash(x)=22969113) +3240 train 7.103394 (lr=7.3394e-05) (hash(x)=21944576) +3241 train 7.323760 (lr=7.3340e-05) (hash(x)=21671079) +3242 train 7.190549 (lr=7.3286e-05) (hash(x)=23912980) +3243 train 7.146383 (lr=7.3232e-05) (hash(x)=25205781) +3244 train 7.123277 (lr=7.3179e-05) (hash(x)=25654244) +3245 train 7.076825 (lr=7.3125e-05) (hash(x)=23335929) +3246 train 7.445565 (lr=7.3071e-05) (hash(x)=27953926) +3247 train 7.252544 (lr=7.3017e-05) (hash(x)=27004415) +3248 train 6.959052 (lr=7.2964e-05) (hash(x)=20471566) +3249 train 7.172947 (lr=7.2910e-05) (hash(x)=25797941) +3250 val loss 7.2572 +3250 val perplexity 1418.2524 +3250 train 7.070431 (lr=7.2856e-05) (hash(x)=21787064) +3251 train 7.036131 (lr=7.2803e-05) (hash(x)=22974875) +3252 train 7.303688 (lr=7.2749e-05) (hash(x)=28431267) +3253 train 7.164587 (lr=7.2695e-05) (hash(x)=25584910) +3254 train 6.979034 (lr=7.2642e-05) (hash(x)=23888922) +3255 train 7.191067 (lr=7.2588e-05) (hash(x)=22265063) +3256 train 6.868307 (lr=7.2535e-05) (hash(x)=21926624) +3257 train 7.101614 (lr=7.2481e-05) (hash(x)=23073191) +3258 train 7.136356 (lr=7.2428e-05) (hash(x)=24409183) +3259 train 7.172363 (lr=7.2374e-05) (hash(x)=23312114) +3260 train 7.093180 (lr=7.2321e-05) (hash(x)=21001289) +3261 train 7.264932 (lr=7.2267e-05) (hash(x)=25514824) +3262 train 7.063798 (lr=7.2214e-05) (hash(x)=22526800) +3263 train 7.441292 (lr=7.2160e-05) (hash(x)=26905990) +3264 train 7.138917 (lr=7.2107e-05) (hash(x)=24469631) +3265 train 7.023517 (lr=7.2053e-05) (hash(x)=21149081) +3266 train 7.185192 (lr=7.2000e-05) (hash(x)=24696215) +3267 train 7.511002 (lr=7.1947e-05) (hash(x)=27089280) +3268 train 7.043167 (lr=7.1893e-05) (hash(x)=23100446) +3269 train 7.301759 (lr=7.1840e-05) (hash(x)=25061229) +3270 train 7.178266 (lr=7.1786e-05) (hash(x)=24337543) +3271 train 7.273011 (lr=7.1733e-05) (hash(x)=24047679) +3272 train 7.290674 (lr=7.1680e-05) (hash(x)=27616773) +3273 train 7.208025 (lr=7.1627e-05) (hash(x)=25315110) +3274 train 7.300073 (lr=7.1573e-05) (hash(x)=28354645) +3275 train 7.156206 (lr=7.1520e-05) (hash(x)=25034684) +3276 train 7.196484 (lr=7.1467e-05) (hash(x)=23550342) +3277 train 7.848349 (lr=7.1414e-05) (hash(x)=28661487) +3278 train 7.453146 (lr=7.1360e-05) (hash(x)=24724622) +3279 train 7.403637 (lr=7.1307e-05) (hash(x)=26905582) +3280 train 7.460052 (lr=7.1254e-05) (hash(x)=26838818) +3281 train 7.213808 (lr=7.1201e-05) (hash(x)=23949017) +3282 train 6.720365 (lr=7.1148e-05) (hash(x)=18846300) +3283 train 7.052247 (lr=7.1095e-05) (hash(x)=21406950) +3284 train 6.889596 (lr=7.1041e-05) (hash(x)=21157696) +3285 train 6.966901 (lr=7.0988e-05) (hash(x)=21440152) +3286 train 7.137338 (lr=7.0935e-05) (hash(x)=26749182) +3287 train 7.317708 (lr=7.0882e-05) (hash(x)=29018970) +3288 train 7.278453 (lr=7.0829e-05) (hash(x)=27577517) +3289 train 6.939701 (lr=7.0776e-05) (hash(x)=19190537) +3290 train 6.984253 (lr=7.0723e-05) (hash(x)=21957991) +3291 train 7.021606 (lr=7.0670e-05) (hash(x)=20853530) +3292 train 6.939045 (lr=7.0617e-05) (hash(x)=22291731) +3293 train 7.106599 (lr=7.0564e-05) (hash(x)=23786853) +3294 train 7.275398 (lr=7.0511e-05) (hash(x)=25740147) +3295 train 7.388440 (lr=7.0458e-05) (hash(x)=24503315) +3296 train 7.087157 (lr=7.0405e-05) (hash(x)=22541728) +3297 train 7.427827 (lr=7.0353e-05) (hash(x)=27067328) +3298 train 7.094557 (lr=7.0300e-05) (hash(x)=22600715) +3299 train 7.126567 (lr=7.0247e-05) (hash(x)=23080074) +3300 val loss 7.2618 +3300 val perplexity 1424.8824 +3300 train 6.940019 (lr=7.0194e-05) (hash(x)=22097758) +3301 train 7.060716 (lr=7.0141e-05) (hash(x)=24105430) +3302 train 6.927723 (lr=7.0088e-05) (hash(x)=23343775) +3303 train 7.176199 (lr=7.0036e-05) (hash(x)=22607537) +3304 train 7.272737 (lr=6.9983e-05) (hash(x)=26501182) +3305 train 7.530617 (lr=6.9930e-05) (hash(x)=26063650) +3306 train 7.125835 (lr=6.9877e-05) (hash(x)=23486602) +3307 train 8.098636 (lr=6.9825e-05) (hash(x)=32179773) +3308 train 11.338395 (lr=6.9772e-05) (hash(x)=66155855) +3309 train 8.562957 (lr=6.9719e-05) (hash(x)=37724427) +3310 train 7.583431 (lr=6.9667e-05) (hash(x)=28861610) +3311 train 7.535863 (lr=6.9614e-05) (hash(x)=26690225) +3312 train 7.092330 (lr=6.9561e-05) (hash(x)=24136450) +3313 train 7.317485 (lr=6.9509e-05) (hash(x)=23702010) +3314 train 7.564586 (lr=6.9456e-05) (hash(x)=28761762) +3315 train 6.909091 (lr=6.9403e-05) (hash(x)=22109609) +3316 train 7.257768 (lr=6.9351e-05) (hash(x)=25168631) +3317 train 7.154271 (lr=6.9298e-05) (hash(x)=24503786) +3318 train 7.201402 (lr=6.9246e-05) (hash(x)=23698606) +3319 train 7.208967 (lr=6.9193e-05) (hash(x)=24226255) +3320 train 7.754468 (lr=6.9141e-05) (hash(x)=31110577) +3321 train 7.209592 (lr=6.9088e-05) (hash(x)=24752754) +3322 train 7.036383 (lr=6.9036e-05) (hash(x)=21135610) +3323 train 6.993446 (lr=6.8983e-05) (hash(x)=23013573) +3324 train 6.776317 (lr=6.8931e-05) (hash(x)=20289715) +3325 train 7.011440 (lr=6.8879e-05) (hash(x)=22700287) +3326 train 7.074762 (lr=6.8826e-05) (hash(x)=21320362) +3327 train 7.220186 (lr=6.8774e-05) (hash(x)=23622702) +3328 train 7.510953 (lr=6.8722e-05) (hash(x)=27435461) +3329 train 7.258386 (lr=6.8669e-05) (hash(x)=25435452) +3330 train 7.218736 (lr=6.8617e-05) (hash(x)=27952557) +3331 train 6.918172 (lr=6.8565e-05) (hash(x)=21517429) +3332 train 7.056295 (lr=6.8512e-05) (hash(x)=24288985) +3333 train 7.190741 (lr=6.8460e-05) (hash(x)=23374788) +3334 train 7.036641 (lr=6.8408e-05) (hash(x)=22042499) +3335 train 7.277918 (lr=6.8356e-05) (hash(x)=23910425) +3336 train 7.594593 (lr=6.8303e-05) (hash(x)=28118508) +3337 train 7.358621 (lr=6.8251e-05) (hash(x)=26737440) +3338 train 7.097046 (lr=6.8199e-05) (hash(x)=24472271) +3339 train 7.095119 (lr=6.8147e-05) (hash(x)=24407484) +3340 train 7.621695 (lr=6.8095e-05) (hash(x)=27908937) +3341 train 7.731084 (lr=6.8043e-05) (hash(x)=29038937) +3342 train 7.529777 (lr=6.7990e-05) (hash(x)=24802580) +3343 train 7.510592 (lr=6.7938e-05) (hash(x)=27213318) +3344 train 7.535655 (lr=6.7886e-05) (hash(x)=28693458) +3345 train 6.891506 (lr=6.7834e-05) (hash(x)=20332324) +3346 train 7.217304 (lr=6.7782e-05) (hash(x)=26726007) +3347 train 7.182302 (lr=6.7730e-05) (hash(x)=25524191) +3348 train 7.237982 (lr=6.7678e-05) (hash(x)=25553293) +3349 train 7.207161 (lr=6.7626e-05) (hash(x)=25614848) +3350 val loss 7.2431 +3350 val perplexity 1398.4299 +3350 train 7.246777 (lr=6.7574e-05) (hash(x)=25747903) +3351 train 7.246971 (lr=6.7522e-05) (hash(x)=26701577) +3352 train 7.001260 (lr=6.7470e-05) (hash(x)=21964135) +3353 train 7.104843 (lr=6.7419e-05) (hash(x)=24461007) +3354 train 7.133212 (lr=6.7367e-05) (hash(x)=25818495) +3355 train 6.982436 (lr=6.7315e-05) (hash(x)=22091266) +3356 train 6.980396 (lr=6.7263e-05) (hash(x)=24476213) +3357 train 7.335571 (lr=6.7211e-05) (hash(x)=24500423) +3358 train 7.096429 (lr=6.7159e-05) (hash(x)=21754841) +3359 train 7.443025 (lr=6.7107e-05) (hash(x)=26216794) +3360 train 6.960117 (lr=6.7056e-05) (hash(x)=24267249) +3361 train 7.246427 (lr=6.7004e-05) (hash(x)=23143515) +3362 train 7.155623 (lr=6.6952e-05) (hash(x)=24120302) +3363 train 7.269968 (lr=6.6900e-05) (hash(x)=20817340) +3364 train 7.246942 (lr=6.6849e-05) (hash(x)=22285847) +3365 train 7.553413 (lr=6.6797e-05) (hash(x)=28151597) +3366 train 7.967218 (lr=6.6745e-05) (hash(x)=31593285) +3367 train 7.587515 (lr=6.6694e-05) (hash(x)=27579623) +3368 train 7.263879 (lr=6.6642e-05) (hash(x)=24995988) +3369 train 6.937136 (lr=6.6591e-05) (hash(x)=22166810) +3370 train 7.137783 (lr=6.6539e-05) (hash(x)=23948298) +3371 train 7.028160 (lr=6.6487e-05) (hash(x)=21532187) +3372 train 7.128661 (lr=6.6436e-05) (hash(x)=23571652) +3373 train 7.512912 (lr=6.6384e-05) (hash(x)=26911513) +3374 train 7.415022 (lr=6.6333e-05) (hash(x)=24011329) +3375 train 7.600152 (lr=6.6281e-05) (hash(x)=26086198) +3376 train 7.200723 (lr=6.6230e-05) (hash(x)=22844402) +3377 train 7.168446 (lr=6.6178e-05) (hash(x)=21817762) +3378 train 7.281150 (lr=6.6127e-05) (hash(x)=23903232) +3379 train 7.165346 (lr=6.6075e-05) (hash(x)=23911729) +3380 train 7.164468 (lr=6.6024e-05) (hash(x)=24485288) +3381 train 7.343900 (lr=6.5973e-05) (hash(x)=27955492) +3382 train 7.082241 (lr=6.5921e-05) (hash(x)=25884586) +3383 train 7.281744 (lr=6.5870e-05) (hash(x)=24863441) +3384 train 7.518617 (lr=6.5819e-05) (hash(x)=22045992) +3385 train 7.643143 (lr=6.5767e-05) (hash(x)=29174796) +3386 train 7.933418 (lr=6.5716e-05) (hash(x)=32589942) +3387 train 7.566848 (lr=6.5665e-05) (hash(x)=28856978) +3388 train 7.060913 (lr=6.5614e-05) (hash(x)=21667904) +3389 train 7.062252 (lr=6.5562e-05) (hash(x)=23431801) +3390 train 6.904175 (lr=6.5511e-05) (hash(x)=20877285) +3391 train 7.127717 (lr=6.5460e-05) (hash(x)=25236385) +3392 train 7.353495 (lr=6.5409e-05) (hash(x)=25373071) +3393 train 7.500797 (lr=6.5358e-05) (hash(x)=25713464) +3394 train 7.476093 (lr=6.5306e-05) (hash(x)=25713475) +3395 train 7.322705 (lr=6.5255e-05) (hash(x)=24278687) +3396 train 7.447740 (lr=6.5204e-05) (hash(x)=27491349) +3397 train 7.351276 (lr=6.5153e-05) (hash(x)=24513692) +3398 train 7.431906 (lr=6.5102e-05) (hash(x)=26853415) +3399 train 7.507927 (lr=6.5051e-05) (hash(x)=25330803) +3400 val loss 7.2640 +3400 val perplexity 1427.9120 +3400 train 7.476099 (lr=6.5000e-05) (hash(x)=26578066) +3401 train 7.503193 (lr=6.4949e-05) (hash(x)=26811522) +3402 train 7.197974 (lr=6.4898e-05) (hash(x)=25611092) +3403 train 7.005356 (lr=6.4847e-05) (hash(x)=21568545) +3404 train 6.997925 (lr=6.4796e-05) (hash(x)=22756484) +3405 train 7.286429 (lr=6.4745e-05) (hash(x)=27927608) +3406 train 7.323633 (lr=6.4694e-05) (hash(x)=27497018) +3407 train 7.086175 (lr=6.4643e-05) (hash(x)=22508532) +3408 train 7.523599 (lr=6.4593e-05) (hash(x)=26673287) +3409 train 7.206014 (lr=6.4542e-05) (hash(x)=23675869) +3410 train 7.113116 (lr=6.4491e-05) (hash(x)=25496948) +3411 train 7.086591 (lr=6.4440e-05) (hash(x)=24850662) +3412 train 7.353017 (lr=6.4389e-05) (hash(x)=29790167) +3413 train 7.033745 (lr=6.4338e-05) (hash(x)=24193434) +3414 train 7.417152 (lr=6.4288e-05) (hash(x)=25310919) +3415 train 7.062009 (lr=6.4237e-05) (hash(x)=21799261) +3416 train 7.399938 (lr=6.4186e-05) (hash(x)=26620074) +3417 train 7.312480 (lr=6.4136e-05) (hash(x)=26719309) +3418 train 7.696591 (lr=6.4085e-05) (hash(x)=23190530) +3419 train 7.255640 (lr=6.4034e-05) (hash(x)=24884891) +3420 train 7.254010 (lr=6.3984e-05) (hash(x)=25545849) +3421 train 7.194294 (lr=6.3933e-05) (hash(x)=26021405) +3422 train 7.149930 (lr=6.3882e-05) (hash(x)=23887343) +3423 train 7.219152 (lr=6.3832e-05) (hash(x)=26311168) +3424 train 6.945579 (lr=6.3781e-05) (hash(x)=21051541) +3425 train 7.283103 (lr=6.3731e-05) (hash(x)=23553179) +3426 train 7.173975 (lr=6.3680e-05) (hash(x)=24345540) +3427 train 7.599454 (lr=6.3630e-05) (hash(x)=27549895) +3428 train 6.953223 (lr=6.3579e-05) (hash(x)=22559753) +3429 train 6.928136 (lr=6.3529e-05) (hash(x)=21647642) +3430 train 6.809168 (lr=6.3478e-05) (hash(x)=20130901) +3431 train 6.959148 (lr=6.3428e-05) (hash(x)=20977430) +3432 train 6.946169 (lr=6.3378e-05) (hash(x)=21356429) +3433 train 6.964598 (lr=6.3327e-05) (hash(x)=23494380) +3434 train 7.206023 (lr=6.3277e-05) (hash(x)=23805501) +3435 train 7.141190 (lr=6.3227e-05) (hash(x)=23448855) +3436 train 7.526357 (lr=6.3176e-05) (hash(x)=26000319) +3437 train 7.000064 (lr=6.3126e-05) (hash(x)=21760032) +3438 train 7.110372 (lr=6.3076e-05) (hash(x)=24424886) +3439 train 7.494870 (lr=6.3025e-05) (hash(x)=26941617) +3440 train 7.517806 (lr=6.2975e-05) (hash(x)=26798528) +3441 train 7.553171 (lr=6.2925e-05) (hash(x)=27464193) +3442 train 7.453204 (lr=6.2875e-05) (hash(x)=25649118) +3443 train 7.480820 (lr=6.2825e-05) (hash(x)=26953192) +3444 train 7.321367 (lr=6.2774e-05) (hash(x)=22224958) +3445 train 7.088776 (lr=6.2724e-05) (hash(x)=24044587) +3446 train 7.503354 (lr=6.2674e-05) (hash(x)=29584466) +3447 train 7.915012 (lr=6.2624e-05) (hash(x)=30008957) +3448 train 7.818307 (lr=6.2574e-05) (hash(x)=26059290) +3449 train 6.794753 (lr=6.2524e-05) (hash(x)=19733965) +3450 val loss 7.2560 +3450 val perplexity 1416.6012 +3450 train 7.313916 (lr=6.2474e-05) (hash(x)=23960200) +3451 train 7.479224 (lr=6.2424e-05) (hash(x)=27069893) +3452 train 7.110449 (lr=6.2374e-05) (hash(x)=23947772) +3453 train 7.208728 (lr=6.2324e-05) (hash(x)=22707406) +3454 train 7.419360 (lr=6.2274e-05) (hash(x)=27832550) +3455 train 7.271977 (lr=6.2224e-05) (hash(x)=27125962) +3456 train 7.143884 (lr=6.2174e-05) (hash(x)=24510254) +3457 train 6.950426 (lr=6.2124e-05) (hash(x)=23545652) +3458 train 7.027093 (lr=6.2074e-05) (hash(x)=23554751) +3459 train 7.110991 (lr=6.2025e-05) (hash(x)=23341415) +3460 train 7.273988 (lr=6.1975e-05) (hash(x)=21784583) +3461 train 7.075062 (lr=6.1925e-05) (hash(x)=22214769) +3462 train 7.151946 (lr=6.1875e-05) (hash(x)=24206922) +3463 train 7.237068 (lr=6.1825e-05) (hash(x)=25888358) +3464 train 7.070562 (lr=6.1776e-05) (hash(x)=22689666) +3465 train 7.193740 (lr=6.1726e-05) (hash(x)=24918697) +3466 train 7.480838 (lr=6.1676e-05) (hash(x)=28237214) +3467 train 7.559587 (lr=6.1626e-05) (hash(x)=26761645) +3468 train 7.224609 (lr=6.1577e-05) (hash(x)=26979307) +3469 train 7.121442 (lr=6.1527e-05) (hash(x)=23553754) +3470 train 7.295810 (lr=6.1478e-05) (hash(x)=25256849) +3471 train 7.193388 (lr=6.1428e-05) (hash(x)=21725719) +3472 train 7.252408 (lr=6.1378e-05) (hash(x)=24897801) +3473 train 7.165078 (lr=6.1329e-05) (hash(x)=26175307) +3474 train 6.981112 (lr=6.1279e-05) (hash(x)=23309218) +3475 train 7.082009 (lr=6.1230e-05) (hash(x)=25746493) +3476 train 7.369490 (lr=6.1180e-05) (hash(x)=27169613) +3477 train 7.065814 (lr=6.1131e-05) (hash(x)=22937341) +3478 train 7.192693 (lr=6.1081e-05) (hash(x)=24250636) +3479 train 7.046645 (lr=6.1032e-05) (hash(x)=21669704) +3480 train 7.043922 (lr=6.0982e-05) (hash(x)=24431839) +3481 train 7.056276 (lr=6.0933e-05) (hash(x)=22763387) +3482 train 7.051572 (lr=6.0884e-05) (hash(x)=20489446) +3483 train 7.005135 (lr=6.0834e-05) (hash(x)=21167493) +3484 train 7.017734 (lr=6.0785e-05) (hash(x)=23465087) +3485 train 7.236507 (lr=6.0736e-05) (hash(x)=26175023) +3486 train 7.355007 (lr=6.0686e-05) (hash(x)=24986207) +3487 train 6.940536 (lr=6.0637e-05) (hash(x)=23166993) +3488 train 7.170318 (lr=6.0588e-05) (hash(x)=25281216) +3489 train 6.976924 (lr=6.0539e-05) (hash(x)=21824285) +3490 train 7.033807 (lr=6.0490e-05) (hash(x)=22352750) +3491 train 7.263071 (lr=6.0440e-05) (hash(x)=23947208) +3492 train 7.328282 (lr=6.0391e-05) (hash(x)=26257363) +3493 train 7.183248 (lr=6.0342e-05) (hash(x)=25103214) +3494 train 7.198317 (lr=6.0293e-05) (hash(x)=25267583) +3495 train 7.292114 (lr=6.0244e-05) (hash(x)=26235974) +3496 train 7.499884 (lr=6.0195e-05) (hash(x)=26430769) +3497 train 7.918015 (lr=6.0146e-05) (hash(x)=28282027) +3498 train 7.740976 (lr=6.0097e-05) (hash(x)=28386462) +3499 train 7.371637 (lr=6.0048e-05) (hash(x)=29822604) +3500 val loss 7.2532 +3500 val perplexity 1412.6875 +3500 train 7.283324 (lr=5.9999e-05) (hash(x)=29225386) +3501 train 7.165972 (lr=5.9950e-05) (hash(x)=25249294) +3502 train 6.949169 (lr=5.9901e-05) (hash(x)=20020741) +3503 train 7.120392 (lr=5.9852e-05) (hash(x)=25426430) +3504 train 7.068808 (lr=5.9803e-05) (hash(x)=25720411) +3505 train 7.077872 (lr=5.9754e-05) (hash(x)=25602639) +3506 train 7.223211 (lr=5.9705e-05) (hash(x)=26724388) +3507 train 7.102174 (lr=5.9656e-05) (hash(x)=26043735) +3508 train 7.079340 (lr=5.9608e-05) (hash(x)=24955163) +3509 train 7.065605 (lr=5.9559e-05) (hash(x)=20936107) +3510 train 7.018116 (lr=5.9510e-05) (hash(x)=20317378) +3511 train 7.083118 (lr=5.9461e-05) (hash(x)=22966314) +3512 train 7.406423 (lr=5.9412e-05) (hash(x)=25870930) +3513 train 7.219336 (lr=5.9364e-05) (hash(x)=24656635) +3514 train 7.480658 (lr=5.9315e-05) (hash(x)=28576810) +3515 train 7.387372 (lr=5.9266e-05) (hash(x)=27944619) +3516 train 7.237640 (lr=5.9218e-05) (hash(x)=27421509) +3517 train 6.973274 (lr=5.9169e-05) (hash(x)=20844620) +3518 train 7.165614 (lr=5.9121e-05) (hash(x)=28569406) +3519 train 7.088002 (lr=5.9072e-05) (hash(x)=23448505) +3520 train 7.233674 (lr=5.9023e-05) (hash(x)=24852577) +3521 train 7.126489 (lr=5.8975e-05) (hash(x)=23963103) +3522 train 7.016346 (lr=5.8926e-05) (hash(x)=24816516) +3523 train 7.191751 (lr=5.8878e-05) (hash(x)=24205942) +3524 train 6.833223 (lr=5.8829e-05) (hash(x)=20988660) +3525 train 6.908258 (lr=5.8781e-05) (hash(x)=21631366) +3526 train 7.130357 (lr=5.8733e-05) (hash(x)=23499370) +3527 train 7.228405 (lr=5.8684e-05) (hash(x)=26330693) +3528 train 6.884329 (lr=5.8636e-05) (hash(x)=23937176) +3529 train 7.143245 (lr=5.8587e-05) (hash(x)=27345885) +3530 train 6.855920 (lr=5.8539e-05) (hash(x)=21104610) +3531 train 7.253796 (lr=5.8491e-05) (hash(x)=24844466) +3532 train 6.617653 (lr=5.8442e-05) (hash(x)=21055483) +3533 train 6.944265 (lr=5.8394e-05) (hash(x)=23229414) +3534 train 7.243141 (lr=5.8346e-05) (hash(x)=26676920) +3535 train 7.185896 (lr=5.8298e-05) (hash(x)=29550596) +3536 train 6.976972 (lr=5.8250e-05) (hash(x)=22231942) +3537 train 7.152466 (lr=5.8201e-05) (hash(x)=25843852) +3538 train 7.288815 (lr=5.8153e-05) (hash(x)=27110533) +3539 train 6.892371 (lr=5.8105e-05) (hash(x)=20506540) +3540 train 6.998114 (lr=5.8057e-05) (hash(x)=21599346) +3541 train 7.167453 (lr=5.8009e-05) (hash(x)=26395519) +3542 train 7.137784 (lr=5.7961e-05) (hash(x)=25892512) +3543 train 7.188011 (lr=5.7913e-05) (hash(x)=22124892) +3544 train 7.068760 (lr=5.7865e-05) (hash(x)=21882567) +3545 train 7.162769 (lr=5.7817e-05) (hash(x)=24316212) +3546 train 7.047470 (lr=5.7769e-05) (hash(x)=24296310) +3547 train 7.148372 (lr=5.7721e-05) (hash(x)=24867036) +3548 train 7.172179 (lr=5.7673e-05) (hash(x)=23351896) +3549 train 7.123430 (lr=5.7625e-05) (hash(x)=21576408) +3550 val loss 7.2291 +3550 val perplexity 1378.9141 +3550 train 7.230908 (lr=5.7577e-05) (hash(x)=26377338) +3551 train 7.052881 (lr=5.7529e-05) (hash(x)=25607640) +3552 train 7.400452 (lr=5.7481e-05) (hash(x)=27619776) +3553 train 6.888229 (lr=5.7433e-05) (hash(x)=23454533) +3554 train 7.076093 (lr=5.7386e-05) (hash(x)=22542519) +3555 train 7.120331 (lr=5.7338e-05) (hash(x)=26176930) +3556 train 6.896526 (lr=5.7290e-05) (hash(x)=22815181) +3557 train 6.886730 (lr=5.7242e-05) (hash(x)=21821757) +3558 train 6.927832 (lr=5.7195e-05) (hash(x)=23988293) +3559 train 6.861372 (lr=5.7147e-05) (hash(x)=23795894) +3560 train 6.810860 (lr=5.7099e-05) (hash(x)=22898969) +3561 train 6.824499 (lr=5.7052e-05) (hash(x)=21510825) +3562 train 6.753745 (lr=5.7004e-05) (hash(x)=22499317) +3563 train 6.784895 (lr=5.6956e-05) (hash(x)=23756298) +3564 train 6.844592 (lr=5.6909e-05) (hash(x)=23964512) +3565 train 6.934961 (lr=5.6861e-05) (hash(x)=23262803) +3566 train 7.133260 (lr=5.6814e-05) (hash(x)=23347279) +3567 train 7.053511 (lr=5.6766e-05) (hash(x)=24165449) +3568 train 7.179538 (lr=5.6719e-05) (hash(x)=25503946) +3569 train 7.167577 (lr=5.6671e-05) (hash(x)=26532839) +3570 train 6.799882 (lr=5.6624e-05) (hash(x)=21889816) +3571 train 7.082080 (lr=5.6576e-05) (hash(x)=26643739) +3572 train 7.261743 (lr=5.6529e-05) (hash(x)=26826130) +3573 train 7.269676 (lr=5.6482e-05) (hash(x)=25810624) +3574 train 7.138652 (lr=5.6434e-05) (hash(x)=23080331) +3575 train 7.289104 (lr=5.6387e-05) (hash(x)=24697756) +3576 train 7.127936 (lr=5.6340e-05) (hash(x)=25158900) +3577 train 7.293200 (lr=5.6292e-05) (hash(x)=25793633) +3578 train 6.924355 (lr=5.6245e-05) (hash(x)=21468493) +3579 train 7.178877 (lr=5.6198e-05) (hash(x)=24431101) +3580 train 7.018634 (lr=5.6151e-05) (hash(x)=27314357) +3581 train 7.238071 (lr=5.6104e-05) (hash(x)=26286249) +3582 train 7.501920 (lr=5.6056e-05) (hash(x)=25954856) +3583 train 7.376964 (lr=5.6009e-05) (hash(x)=27218899) +3584 train 7.174413 (lr=5.5962e-05) (hash(x)=24249114) +3585 train 7.032301 (lr=5.5915e-05) (hash(x)=23659934) +3586 train 7.051980 (lr=5.5868e-05) (hash(x)=25995600) +3587 train 6.988754 (lr=5.5821e-05) (hash(x)=29462219) +3588 train 7.134262 (lr=5.5774e-05) (hash(x)=23346714) +3589 train 7.260512 (lr=5.5727e-05) (hash(x)=27168432) +3590 train 7.082364 (lr=5.5680e-05) (hash(x)=23954240) +3591 train 7.036602 (lr=5.5633e-05) (hash(x)=24748522) +3592 train 7.221807 (lr=5.5586e-05) (hash(x)=24887007) +3593 train 7.000206 (lr=5.5539e-05) (hash(x)=25539383) +3594 train 6.952635 (lr=5.5492e-05) (hash(x)=20104613) +3595 train 7.425541 (lr=5.5445e-05) (hash(x)=24843486) +3596 train 7.456139 (lr=5.5399e-05) (hash(x)=24357864) +3597 train 7.103296 (lr=5.5352e-05) (hash(x)=23873745) +3598 train 7.267636 (lr=5.5305e-05) (hash(x)=25142829) +3599 train 7.328576 (lr=5.5258e-05) (hash(x)=24965317) +3600 val loss 7.2290 +3600 val perplexity 1378.7793 +3600 train 6.822596 (lr=5.5211e-05) (hash(x)=18505205) +3601 train 6.860911 (lr=5.5165e-05) (hash(x)=23632877) +3602 train 7.092083 (lr=5.5118e-05) (hash(x)=23704554) +3603 train 7.245821 (lr=5.5071e-05) (hash(x)=26584754) +3604 train 6.910536 (lr=5.5025e-05) (hash(x)=20667709) +3605 train 6.784311 (lr=5.4978e-05) (hash(x)=20573248) +3606 train 6.893229 (lr=5.4932e-05) (hash(x)=23998997) +3607 train 7.089426 (lr=5.4885e-05) (hash(x)=22031210) +3608 train 7.148366 (lr=5.4838e-05) (hash(x)=24124536) +3609 train 7.048761 (lr=5.4792e-05) (hash(x)=22650144) +3610 train 7.135188 (lr=5.4745e-05) (hash(x)=23796998) +3611 train 7.167023 (lr=5.4699e-05) (hash(x)=24860582) +3612 train 6.735216 (lr=5.4652e-05) (hash(x)=20591300) +3613 train 7.134588 (lr=5.4606e-05) (hash(x)=23447130) +3614 train 7.138587 (lr=5.4560e-05) (hash(x)=26237963) +3615 train 7.252797 (lr=5.4513e-05) (hash(x)=25877990) +3616 train 7.032288 (lr=5.4467e-05) (hash(x)=24808003) +3617 train 7.221353 (lr=5.4420e-05) (hash(x)=24103543) +3618 train 7.115575 (lr=5.4374e-05) (hash(x)=24877184) +3619 train 7.225667 (lr=5.4328e-05) (hash(x)=24970646) +3620 train 7.169724 (lr=5.4282e-05) (hash(x)=25764524) +3621 train 7.318803 (lr=5.4235e-05) (hash(x)=25313591) +3622 train 7.189731 (lr=5.4189e-05) (hash(x)=23260940) +3623 train 7.144103 (lr=5.4143e-05) (hash(x)=24382381) +3624 train 7.102826 (lr=5.4097e-05) (hash(x)=24618902) +3625 train 7.244768 (lr=5.4051e-05) (hash(x)=25074871) +3626 train 6.959953 (lr=5.4004e-05) (hash(x)=24472251) +3627 train 7.103845 (lr=5.3958e-05) (hash(x)=25221746) +3628 train 7.204072 (lr=5.3912e-05) (hash(x)=27448790) +3629 train 7.170241 (lr=5.3866e-05) (hash(x)=25221431) +3630 train 6.768412 (lr=5.3820e-05) (hash(x)=22034366) +3631 train 7.303708 (lr=5.3774e-05) (hash(x)=24551999) +3632 train 7.016267 (lr=5.3728e-05) (hash(x)=24330217) +3633 train 7.090892 (lr=5.3682e-05) (hash(x)=22792380) +3634 train 6.941287 (lr=5.3636e-05) (hash(x)=22393767) +3635 train 7.252351 (lr=5.3590e-05) (hash(x)=28151378) +3636 train 7.253620 (lr=5.3544e-05) (hash(x)=26999341) +3637 train 7.229683 (lr=5.3499e-05) (hash(x)=27251870) +3638 train 7.180926 (lr=5.3453e-05) (hash(x)=23439462) +3639 train 7.288639 (lr=5.3407e-05) (hash(x)=25765516) +3640 train 7.130863 (lr=5.3361e-05) (hash(x)=24720171) +3641 train 7.362068 (lr=5.3315e-05) (hash(x)=23927187) +3642 train 7.120393 (lr=5.3270e-05) (hash(x)=23879561) +3643 train 7.232426 (lr=5.3224e-05) (hash(x)=25630696) +3644 train 6.845676 (lr=5.3178e-05) (hash(x)=22030016) +3645 train 7.292261 (lr=5.3133e-05) (hash(x)=28781600) +3646 train 7.293813 (lr=5.3087e-05) (hash(x)=26668019) +3647 train 7.320093 (lr=5.3041e-05) (hash(x)=25204247) +3648 train 7.552826 (lr=5.2996e-05) (hash(x)=31261394) +3649 train 7.336444 (lr=5.2950e-05) (hash(x)=26193103) +3650 val loss 7.2364 +3650 val perplexity 1389.0441 +3650 train 7.168783 (lr=5.2905e-05) (hash(x)=23872456) +3651 train 7.052508 (lr=5.2859e-05) (hash(x)=26326447) +3652 train 7.079021 (lr=5.2814e-05) (hash(x)=26449631) +3653 train 7.340370 (lr=5.2768e-05) (hash(x)=26373461) +3654 train 7.204036 (lr=5.2723e-05) (hash(x)=24882768) +3655 train 7.267770 (lr=5.2677e-05) (hash(x)=26321813) +3656 train 7.315703 (lr=5.2632e-05) (hash(x)=27056428) +3657 train 7.235660 (lr=5.2586e-05) (hash(x)=24583976) +3658 train 6.956422 (lr=5.2541e-05) (hash(x)=22259624) +3659 train 7.098615 (lr=5.2496e-05) (hash(x)=25400396) +3660 train 6.958798 (lr=5.2450e-05) (hash(x)=21095507) +3661 train 7.209863 (lr=5.2405e-05) (hash(x)=27231042) +3662 train 6.968654 (lr=5.2360e-05) (hash(x)=27292771) +3663 train 7.451978 (lr=5.2315e-05) (hash(x)=25528323) +3664 train 7.176054 (lr=5.2270e-05) (hash(x)=24374502) +3665 train 7.009520 (lr=5.2224e-05) (hash(x)=22463800) +3666 train 7.263977 (lr=5.2179e-05) (hash(x)=25413960) +3667 train 7.173293 (lr=5.2134e-05) (hash(x)=24035353) +3668 train 7.125180 (lr=5.2089e-05) (hash(x)=24815852) +3669 train 7.000183 (lr=5.2044e-05) (hash(x)=22995856) +3670 train 7.271556 (lr=5.1999e-05) (hash(x)=28128238) +3671 train 7.267091 (lr=5.1954e-05) (hash(x)=25114729) +3672 train 7.010945 (lr=5.1909e-05) (hash(x)=19337726) +3673 train 7.446329 (lr=5.1864e-05) (hash(x)=26674420) +3674 train 6.947884 (lr=5.1819e-05) (hash(x)=22553270) +3675 train 6.807168 (lr=5.1774e-05) (hash(x)=21634962) +3676 train 6.995262 (lr=5.1729e-05) (hash(x)=23362669) +3677 train 7.155832 (lr=5.1684e-05) (hash(x)=24781824) +3678 train 6.692188 (lr=5.1639e-05) (hash(x)=17909688) +3679 train 7.931047 (lr=5.1594e-05) (hash(x)=31341964) +3680 train 7.438927 (lr=5.1550e-05) (hash(x)=29071335) +3681 train 6.838203 (lr=5.1505e-05) (hash(x)=19486640) +3682 train 6.999753 (lr=5.1460e-05) (hash(x)=24301133) +3683 train 7.162876 (lr=5.1415e-05) (hash(x)=29172813) +3684 train 7.703300 (lr=5.1371e-05) (hash(x)=31501337) +3685 train 7.299400 (lr=5.1326e-05) (hash(x)=27377840) +3686 train 7.096368 (lr=5.1281e-05) (hash(x)=24499761) +3687 train 7.122627 (lr=5.1237e-05) (hash(x)=26326024) +3688 train 7.166881 (lr=5.1192e-05) (hash(x)=23179996) +3689 train 6.804875 (lr=5.1148e-05) (hash(x)=20963675) +3690 train 7.113470 (lr=5.1103e-05) (hash(x)=26650521) +3691 train 6.894690 (lr=5.1058e-05) (hash(x)=20140071) +3692 train 6.843185 (lr=5.1014e-05) (hash(x)=21734340) +3693 train 7.130481 (lr=5.0970e-05) (hash(x)=23848422) +3694 train 7.178234 (lr=5.0925e-05) (hash(x)=27499953) +3695 train 7.421052 (lr=5.0881e-05) (hash(x)=27273311) +3696 train 7.324267 (lr=5.0836e-05) (hash(x)=25741091) +3697 train 7.076895 (lr=5.0792e-05) (hash(x)=22010794) +3698 train 7.165542 (lr=5.0748e-05) (hash(x)=24616138) +3699 train 7.517124 (lr=5.0703e-05) (hash(x)=31276487) +3700 val loss 7.2346 +3700 val perplexity 1386.5948 +3700 train 7.188775 (lr=5.0659e-05) (hash(x)=24042922) +3701 train 6.984999 (lr=5.0615e-05) (hash(x)=21985431) +3702 train 6.831161 (lr=5.0570e-05) (hash(x)=21336316) +3703 train 6.685278 (lr=5.0526e-05) (hash(x)=17819313) +3704 train 7.311908 (lr=5.0482e-05) (hash(x)=27033851) +3705 train 7.313718 (lr=5.0438e-05) (hash(x)=27260043) +3706 train 7.395812 (lr=5.0394e-05) (hash(x)=26847649) +3707 train 7.323903 (lr=5.0349e-05) (hash(x)=25843618) +3708 train 7.313874 (lr=5.0305e-05) (hash(x)=25828009) +3709 train 7.318874 (lr=5.0261e-05) (hash(x)=24960960) +3710 train 7.439737 (lr=5.0217e-05) (hash(x)=24852741) +3711 train 6.908496 (lr=5.0173e-05) (hash(x)=23769243) +3712 train 7.085994 (lr=5.0129e-05) (hash(x)=27110690) +3713 train 7.141071 (lr=5.0085e-05) (hash(x)=22817285) +3714 train 6.833308 (lr=5.0041e-05) (hash(x)=19618355) +3715 train 7.367148 (lr=4.9997e-05) (hash(x)=28731298) +3716 train 7.154247 (lr=4.9954e-05) (hash(x)=23091196) +3717 train 7.662727 (lr=4.9910e-05) (hash(x)=28825233) +3718 train 7.213071 (lr=4.9866e-05) (hash(x)=25778506) +3719 train 7.182714 (lr=4.9822e-05) (hash(x)=23788738) +3720 train 6.574889 (lr=4.9778e-05) (hash(x)=16684794) +3721 train 7.069927 (lr=4.9734e-05) (hash(x)=24755102) +3722 train 7.311872 (lr=4.9691e-05) (hash(x)=26839238) +3723 train 7.341000 (lr=4.9647e-05) (hash(x)=26599031) +3724 train 7.230144 (lr=4.9603e-05) (hash(x)=25945650) +3725 train 7.387517 (lr=4.9560e-05) (hash(x)=27434751) +3726 train 7.149458 (lr=4.9516e-05) (hash(x)=24814591) +3727 train 7.093621 (lr=4.9472e-05) (hash(x)=24818744) +3728 train 7.192440 (lr=4.9429e-05) (hash(x)=25649817) +3729 train 7.086945 (lr=4.9385e-05) (hash(x)=24987021) +3730 train 7.015024 (lr=4.9342e-05) (hash(x)=24667779) +3731 train 6.996488 (lr=4.9298e-05) (hash(x)=23053871) +3732 train 6.719000 (lr=4.9255e-05) (hash(x)=19264856) +3733 train 7.274216 (lr=4.9211e-05) (hash(x)=23718117) +3734 train 7.007768 (lr=4.9168e-05) (hash(x)=21904779) +3735 train 7.227626 (lr=4.9125e-05) (hash(x)=23472795) +3736 train 7.475100 (lr=4.9081e-05) (hash(x)=24650440) +3737 train 7.523537 (lr=4.9038e-05) (hash(x)=25243911) +3738 train 7.887946 (lr=4.8994e-05) (hash(x)=30423616) +3739 train 7.899335 (lr=4.8951e-05) (hash(x)=29748225) +3740 train 7.258047 (lr=4.8908e-05) (hash(x)=25180684) +3741 train 7.280379 (lr=4.8865e-05) (hash(x)=25619065) +3742 train 7.638861 (lr=4.8821e-05) (hash(x)=31847002) +3743 train 7.211937 (lr=4.8778e-05) (hash(x)=24991832) +3744 train 7.142958 (lr=4.8735e-05) (hash(x)=23836263) +3745 train 7.022180 (lr=4.8692e-05) (hash(x)=24651902) +3746 train 7.570451 (lr=4.8649e-05) (hash(x)=22936538) +3747 train 7.553542 (lr=4.8606e-05) (hash(x)=23681545) +3748 train 6.974210 (lr=4.8563e-05) (hash(x)=21140825) +3749 train 7.121873 (lr=4.8520e-05) (hash(x)=24932453) +3750 val loss 7.2330 +3750 val perplexity 1384.3295 +3750 train 7.325923 (lr=4.8477e-05) (hash(x)=25919062) +3751 train 7.109593 (lr=4.8434e-05) (hash(x)=22424066) +3752 train 7.168907 (lr=4.8391e-05) (hash(x)=23542210) +3753 train 7.045694 (lr=4.8348e-05) (hash(x)=22113561) +3754 train 6.959058 (lr=4.8305e-05) (hash(x)=24892794) +3755 train 7.421489 (lr=4.8262e-05) (hash(x)=25262748) +3756 train 7.187608 (lr=4.8219e-05) (hash(x)=24477975) +3757 train 7.010397 (lr=4.8176e-05) (hash(x)=24681189) +3758 train 7.040883 (lr=4.8134e-05) (hash(x)=24052603) +3759 train 7.255500 (lr=4.8091e-05) (hash(x)=26474878) +3760 train 7.784088 (lr=4.8048e-05) (hash(x)=28228836) +3761 train 7.295445 (lr=4.8005e-05) (hash(x)=23832522) +3762 train 7.258612 (lr=4.7963e-05) (hash(x)=24416789) +3763 train 7.047327 (lr=4.7920e-05) (hash(x)=23930593) +3764 train 7.111470 (lr=4.7877e-05) (hash(x)=23895092) +3765 train 7.032468 (lr=4.7835e-05) (hash(x)=26865287) +3766 train 7.080039 (lr=4.7792e-05) (hash(x)=21330722) +3767 train 7.164620 (lr=4.7750e-05) (hash(x)=22704349) +3768 train 7.263126 (lr=4.7707e-05) (hash(x)=27740886) +3769 train 7.245227 (lr=4.7665e-05) (hash(x)=24935936) +3770 train 7.129431 (lr=4.7622e-05) (hash(x)=23497487) +3771 train 7.312097 (lr=4.7580e-05) (hash(x)=24801048) +3772 train 7.069808 (lr=4.7537e-05) (hash(x)=25490486) +3773 train 7.084348 (lr=4.7495e-05) (hash(x)=21166466) +3774 train 7.301038 (lr=4.7453e-05) (hash(x)=23225244) +3775 train 7.089489 (lr=4.7410e-05) (hash(x)=22293673) +3776 train 7.379881 (lr=4.7368e-05) (hash(x)=25700016) +3777 train 6.922999 (lr=4.7326e-05) (hash(x)=22370207) +3778 train 7.250931 (lr=4.7283e-05) (hash(x)=25224849) +3779 train 7.146537 (lr=4.7241e-05) (hash(x)=23311934) +3780 train 6.935048 (lr=4.7199e-05) (hash(x)=19627124) +3781 train 7.476213 (lr=4.7157e-05) (hash(x)=27132838) +3782 train 7.328216 (lr=4.7115e-05) (hash(x)=27242104) +3783 train 6.857991 (lr=4.7072e-05) (hash(x)=21785487) +3784 train 7.180936 (lr=4.7030e-05) (hash(x)=25798262) +3785 train 7.069760 (lr=4.6988e-05) (hash(x)=24806937) +3786 train 6.911977 (lr=4.6946e-05) (hash(x)=24098756) +3787 train 6.918859 (lr=4.6904e-05) (hash(x)=22981456) +3788 train 7.400259 (lr=4.6862e-05) (hash(x)=22441908) +3789 train 7.303144 (lr=4.6820e-05) (hash(x)=25867804) +3790 train 7.199405 (lr=4.6778e-05) (hash(x)=22835586) +3791 train 7.413345 (lr=4.6736e-05) (hash(x)=25251063) +3792 train 7.218872 (lr=4.6694e-05) (hash(x)=27059729) +3793 train 7.194667 (lr=4.6653e-05) (hash(x)=23819311) +3794 train 6.919559 (lr=4.6611e-05) (hash(x)=21345757) +3795 train 7.162824 (lr=4.6569e-05) (hash(x)=25796422) +3796 train 6.823434 (lr=4.6527e-05) (hash(x)=21414971) +3797 train 7.125351 (lr=4.6485e-05) (hash(x)=26120920) +3798 train 7.082701 (lr=4.6444e-05) (hash(x)=22008247) +3799 train 7.142786 (lr=4.6402e-05) (hash(x)=22722211) +3800 val loss 7.2249 +3800 val perplexity 1373.2449 +3800 train 6.890678 (lr=4.6360e-05) (hash(x)=24484513) +3801 train 7.239092 (lr=4.6319e-05) (hash(x)=24463866) +3802 train 7.248007 (lr=4.6277e-05) (hash(x)=26470775) +3803 train 7.222660 (lr=4.6236e-05) (hash(x)=24296755) +3804 train 7.212066 (lr=4.6194e-05) (hash(x)=24381309) +3805 train 7.410130 (lr=4.6152e-05) (hash(x)=26781262) +3806 train 6.934274 (lr=4.6111e-05) (hash(x)=23563137) +3807 train 7.112602 (lr=4.6069e-05) (hash(x)=24522269) +3808 train 6.965403 (lr=4.6028e-05) (hash(x)=22871995) +3809 train 7.278564 (lr=4.5987e-05) (hash(x)=24751946) +3810 train 7.099500 (lr=4.5945e-05) (hash(x)=19879741) +3811 train 7.168900 (lr=4.5904e-05) (hash(x)=25617184) +3812 train 6.880291 (lr=4.5863e-05) (hash(x)=21776722) +3813 train 6.960978 (lr=4.5821e-05) (hash(x)=22663402) +3814 train 7.289052 (lr=4.5780e-05) (hash(x)=26072046) +3815 train 6.990888 (lr=4.5739e-05) (hash(x)=23329475) +3816 train 7.057588 (lr=4.5697e-05) (hash(x)=25519031) +3817 train 7.024595 (lr=4.5656e-05) (hash(x)=22846270) +3818 train 7.050924 (lr=4.5615e-05) (hash(x)=20299429) +3819 train 7.486414 (lr=4.5574e-05) (hash(x)=30652062) +3820 train 6.828743 (lr=4.5533e-05) (hash(x)=19824665) +3821 train 7.363865 (lr=4.5492e-05) (hash(x)=26698904) +3822 train 7.190273 (lr=4.5451e-05) (hash(x)=27612163) +3823 train 6.997888 (lr=4.5410e-05) (hash(x)=24735165) +3824 train 6.781043 (lr=4.5369e-05) (hash(x)=19965890) +3825 train 6.898656 (lr=4.5328e-05) (hash(x)=23518594) +3826 train 6.910880 (lr=4.5287e-05) (hash(x)=22388460) +3827 train 6.997580 (lr=4.5246e-05) (hash(x)=23795686) +3828 train 6.866573 (lr=4.5205e-05) (hash(x)=24470150) +3829 train 6.579424 (lr=4.5164e-05) (hash(x)=19483392) +3830 train 7.019876 (lr=4.5123e-05) (hash(x)=23304516) +3831 train 7.337300 (lr=4.5082e-05) (hash(x)=27002892) +3832 train 7.055550 (lr=4.5042e-05) (hash(x)=22114813) +3833 train 7.199425 (lr=4.5001e-05) (hash(x)=26221916) +3834 train 6.779347 (lr=4.4960e-05) (hash(x)=27261960) +3835 train 7.044023 (lr=4.4919e-05) (hash(x)=21189101) +3836 train 6.753264 (lr=4.4879e-05) (hash(x)=20638173) +3837 train 7.163086 (lr=4.4838e-05) (hash(x)=25497439) +3838 train 6.656638 (lr=4.4797e-05) (hash(x)=20460499) +3839 train 7.088096 (lr=4.4757e-05) (hash(x)=23499349) +3840 train 7.924832 (lr=4.4716e-05) (hash(x)=22671939) +3841 train 7.935468 (lr=4.4676e-05) (hash(x)=26809295) +3842 train 7.168267 (lr=4.4635e-05) (hash(x)=28094504) +3843 train 7.163212 (lr=4.4595e-05) (hash(x)=26807896) +3844 train 7.249261 (lr=4.4554e-05) (hash(x)=24749334) +3845 train 7.146984 (lr=4.4514e-05) (hash(x)=25031330) +3846 train 7.072235 (lr=4.4474e-05) (hash(x)=23008126) +3847 train 7.005879 (lr=4.4433e-05) (hash(x)=22461589) +3848 train 7.319626 (lr=4.4393e-05) (hash(x)=24959391) +3849 train 7.185219 (lr=4.4353e-05) (hash(x)=24239512) +3850 val loss 7.2211 +3850 val perplexity 1367.9987 +3850 train 7.014766 (lr=4.4312e-05) (hash(x)=24760422) +3851 train 7.495835 (lr=4.4272e-05) (hash(x)=26904123) +3852 train 6.670949 (lr=4.4232e-05) (hash(x)=17986444) +3853 train 7.019743 (lr=4.4192e-05) (hash(x)=21618533) +3854 train 7.078020 (lr=4.4151e-05) (hash(x)=27107027) +3855 train 7.310206 (lr=4.4111e-05) (hash(x)=26415040) +3856 train 7.850705 (lr=4.4071e-05) (hash(x)=28682703) +3857 train 7.011232 (lr=4.4031e-05) (hash(x)=22824767) +3858 train 7.176604 (lr=4.3991e-05) (hash(x)=24540450) +3859 train 7.149446 (lr=4.3951e-05) (hash(x)=24463181) +3860 train 7.044699 (lr=4.3911e-05) (hash(x)=22832558) +3861 train 7.245406 (lr=4.3871e-05) (hash(x)=26582384) +3862 train 7.908494 (lr=4.3831e-05) (hash(x)=32327364) +3863 train 7.307738 (lr=4.3791e-05) (hash(x)=26349465) +3864 train 7.032002 (lr=4.3751e-05) (hash(x)=23079414) +3865 train 7.075299 (lr=4.3711e-05) (hash(x)=23464639) +3866 train 6.919412 (lr=4.3672e-05) (hash(x)=21406620) +3867 train 6.792539 (lr=4.3632e-05) (hash(x)=21205988) +3868 train 6.844169 (lr=4.3592e-05) (hash(x)=22742634) +3869 train 6.888883 (lr=4.3552e-05) (hash(x)=24868938) +3870 train 7.242323 (lr=4.3513e-05) (hash(x)=28095283) +3871 train 6.977010 (lr=4.3473e-05) (hash(x)=21596677) +3872 train 7.214860 (lr=4.3433e-05) (hash(x)=26884381) +3873 train 7.254717 (lr=4.3394e-05) (hash(x)=26410272) +3874 train 7.038349 (lr=4.3354e-05) (hash(x)=22915785) +3875 train 7.020386 (lr=4.3314e-05) (hash(x)=23575666) +3876 train 7.025250 (lr=4.3275e-05) (hash(x)=25313223) +3877 train 6.537620 (lr=4.3235e-05) (hash(x)=16319719) +3878 train 7.098821 (lr=4.3196e-05) (hash(x)=23227579) +3879 train 7.042897 (lr=4.3156e-05) (hash(x)=24117012) +3880 train 7.109818 (lr=4.3117e-05) (hash(x)=24681517) +3881 train 7.045316 (lr=4.3078e-05) (hash(x)=23186527) +3882 train 7.015900 (lr=4.3038e-05) (hash(x)=23472784) +3883 train 7.033195 (lr=4.2999e-05) (hash(x)=26013014) +3884 train 7.278419 (lr=4.2960e-05) (hash(x)=25952206) +3885 train 7.345390 (lr=4.2920e-05) (hash(x)=23897834) +3886 train 7.066856 (lr=4.2881e-05) (hash(x)=26350364) +3887 train 7.123190 (lr=4.2842e-05) (hash(x)=24105761) +3888 train 7.213158 (lr=4.2803e-05) (hash(x)=22801707) +3889 train 7.053972 (lr=4.2763e-05) (hash(x)=21821937) +3890 train 6.994514 (lr=4.2724e-05) (hash(x)=24264640) +3891 train 6.966426 (lr=4.2685e-05) (hash(x)=20369133) +3892 train 6.940575 (lr=4.2646e-05) (hash(x)=24313506) +3893 train 6.947057 (lr=4.2607e-05) (hash(x)=22104086) +3894 train 7.196084 (lr=4.2568e-05) (hash(x)=25312602) +3895 train 7.226780 (lr=4.2529e-05) (hash(x)=25725049) +3896 train 7.053205 (lr=4.2490e-05) (hash(x)=22981231) +3897 train 6.903602 (lr=4.2451e-05) (hash(x)=18021467) +3898 train 6.911366 (lr=4.2412e-05) (hash(x)=17960254) +3899 train 7.053183 (lr=4.2373e-05) (hash(x)=19808118) +3900 val loss 7.2159 +3900 val perplexity 1360.8395 +3900 train 6.804812 (lr=4.2334e-05) (hash(x)=21022829) +3901 train 6.977565 (lr=4.2296e-05) (hash(x)=22434663) +3902 train 6.746358 (lr=4.2257e-05) (hash(x)=20208091) +3903 train 6.889873 (lr=4.2218e-05) (hash(x)=22892776) +3904 train 6.980339 (lr=4.2179e-05) (hash(x)=21554367) +3905 train 7.120012 (lr=4.2141e-05) (hash(x)=23704875) +3906 train 7.078804 (lr=4.2102e-05) (hash(x)=21690340) +3907 train 7.013251 (lr=4.2063e-05) (hash(x)=23736780) +3908 train 6.894249 (lr=4.2025e-05) (hash(x)=21060920) +3909 train 6.864463 (lr=4.1986e-05) (hash(x)=20091559) +3910 train 7.142696 (lr=4.1947e-05) (hash(x)=22147974) +3911 train 7.063143 (lr=4.1909e-05) (hash(x)=21630383) +3912 train 7.317865 (lr=4.1870e-05) (hash(x)=28339385) +3913 train 7.097571 (lr=4.1832e-05) (hash(x)=25355505) +3914 train 7.000020 (lr=4.1794e-05) (hash(x)=20843914) +3915 train 7.499311 (lr=4.1755e-05) (hash(x)=25397467) +3916 train 7.159121 (lr=4.1717e-05) (hash(x)=23587501) +3917 train 6.774484 (lr=4.1678e-05) (hash(x)=19036533) +3918 train 6.956029 (lr=4.1640e-05) (hash(x)=29749389) +3919 train 6.832524 (lr=4.1602e-05) (hash(x)=24727094) +3920 train 6.892632 (lr=4.1563e-05) (hash(x)=22723450) +3921 train 7.073765 (lr=4.1525e-05) (hash(x)=24424680) +3922 train 7.201121 (lr=4.1487e-05) (hash(x)=25817917) +3923 train 7.019196 (lr=4.1449e-05) (hash(x)=23951182) +3924 train 7.031240 (lr=4.1411e-05) (hash(x)=21177944) +3925 train 6.910165 (lr=4.1373e-05) (hash(x)=23533768) +3926 train 7.082356 (lr=4.1334e-05) (hash(x)=24263615) +3927 train 6.928586 (lr=4.1296e-05) (hash(x)=22835000) +3928 train 7.159851 (lr=4.1258e-05) (hash(x)=26076156) +3929 train 7.107201 (lr=4.1220e-05) (hash(x)=25171508) +3930 train 7.131966 (lr=4.1182e-05) (hash(x)=22021396) +3931 train 7.475591 (lr=4.1144e-05) (hash(x)=28767849) +3932 train 7.340479 (lr=4.1107e-05) (hash(x)=29497606) +3933 train 6.955376 (lr=4.1069e-05) (hash(x)=22723124) +3934 train 7.240602 (lr=4.1031e-05) (hash(x)=27106616) +3935 train 7.104722 (lr=4.0993e-05) (hash(x)=22839049) +3936 train 7.115804 (lr=4.0955e-05) (hash(x)=25101923) +3937 train 7.085285 (lr=4.0917e-05) (hash(x)=25945975) +3938 train 7.228010 (lr=4.0880e-05) (hash(x)=25382013) +3939 train 6.764559 (lr=4.0842e-05) (hash(x)=19930900) +3940 train 6.905069 (lr=4.0804e-05) (hash(x)=22202373) +3941 train 7.085906 (lr=4.0767e-05) (hash(x)=24592992) +3942 train 6.994750 (lr=4.0729e-05) (hash(x)=25002271) +3943 train 6.852381 (lr=4.0691e-05) (hash(x)=20654136) +3944 train 6.950521 (lr=4.0654e-05) (hash(x)=20061590) +3945 train 6.875741 (lr=4.0616e-05) (hash(x)=21441361) +3946 train 7.068248 (lr=4.0579e-05) (hash(x)=20055468) +3947 train 7.774902 (lr=4.0541e-05) (hash(x)=28495621) +3948 train 7.182146 (lr=4.0504e-05) (hash(x)=25959236) +3949 train 7.514272 (lr=4.0466e-05) (hash(x)=26750193) +3950 val loss 7.2230 +3950 val perplexity 1370.5752 +3950 train 7.356261 (lr=4.0429e-05) (hash(x)=25882605) +3951 train 7.402176 (lr=4.0392e-05) (hash(x)=26776000) +3952 train 7.018936 (lr=4.0354e-05) (hash(x)=24155107) +3953 train 7.086993 (lr=4.0317e-05) (hash(x)=23441845) +3954 train 6.997964 (lr=4.0280e-05) (hash(x)=22860915) +3955 train 6.839679 (lr=4.0243e-05) (hash(x)=21584429) +3956 train 6.431957 (lr=4.0205e-05) (hash(x)=16535556) +3957 train 6.500490 (lr=4.0168e-05) (hash(x)=17946180) +3958 train 7.031975 (lr=4.0131e-05) (hash(x)=25367610) +3959 train 6.916953 (lr=4.0094e-05) (hash(x)=22560658) +3960 train 7.176537 (lr=4.0057e-05) (hash(x)=23809585) +3961 train 7.399723 (lr=4.0020e-05) (hash(x)=20438213) +3962 train 7.786855 (lr=3.9983e-05) (hash(x)=30520037) +3963 train 7.411342 (lr=3.9946e-05) (hash(x)=25276565) +3964 train 7.140420 (lr=3.9909e-05) (hash(x)=26796532) +3965 train 6.954532 (lr=3.9872e-05) (hash(x)=22850475) +3966 train 7.417245 (lr=3.9835e-05) (hash(x)=25983698) +3967 train 7.302459 (lr=3.9798e-05) (hash(x)=25995933) +3968 train 7.511218 (lr=3.9761e-05) (hash(x)=25319339) +3969 train 7.126503 (lr=3.9724e-05) (hash(x)=25066892) +3970 train 7.328748 (lr=3.9688e-05) (hash(x)=26931819) +3971 train 7.269516 (lr=3.9651e-05) (hash(x)=24163910) +3972 train 7.182771 (lr=3.9614e-05) (hash(x)=25359634) +3973 train 7.090460 (lr=3.9577e-05) (hash(x)=24323444) +3974 train 7.238174 (lr=3.9541e-05) (hash(x)=26529231) +3975 train 7.273642 (lr=3.9504e-05) (hash(x)=24635394) +3976 train 7.572134 (lr=3.9468e-05) (hash(x)=24783093) +3977 train 7.686691 (lr=3.9431e-05) (hash(x)=26710509) +3978 train 7.086597 (lr=3.9394e-05) (hash(x)=25396630) +3979 train 7.001768 (lr=3.9358e-05) (hash(x)=22556381) +3980 train 7.284343 (lr=3.9321e-05) (hash(x)=26912161) +3981 train 6.892401 (lr=3.9285e-05) (hash(x)=22268078) +3982 train 7.881472 (lr=3.9249e-05) (hash(x)=30430328) +3983 train 7.488511 (lr=3.9212e-05) (hash(x)=27537228) +3984 train 6.975019 (lr=3.9176e-05) (hash(x)=24468603) +3985 train 7.284492 (lr=3.9140e-05) (hash(x)=27006663) +3986 train 7.502257 (lr=3.9103e-05) (hash(x)=27014728) +3987 train 6.964447 (lr=3.9067e-05) (hash(x)=20883633) +3988 train 7.076694 (lr=3.9031e-05) (hash(x)=23361791) +3989 train 7.186038 (lr=3.8994e-05) (hash(x)=26775925) +3990 train 7.719181 (lr=3.8958e-05) (hash(x)=30648934) +3991 train 7.264731 (lr=3.8922e-05) (hash(x)=26496730) +3992 train 7.046750 (lr=3.8886e-05) (hash(x)=25942897) +3993 train 7.037428 (lr=3.8850e-05) (hash(x)=24887111) +3994 train 6.971192 (lr=3.8814e-05) (hash(x)=22908550) +3995 train 6.694734 (lr=3.8778e-05) (hash(x)=20342150) +3996 train 6.982475 (lr=3.8742e-05) (hash(x)=22261760) +3997 train 7.046442 (lr=3.8706e-05) (hash(x)=22731641) +3998 train 6.909578 (lr=3.8670e-05) (hash(x)=20669749) +3999 train 6.834686 (lr=3.8634e-05) (hash(x)=16533310) +4000 val loss 7.2128 +4000 val perplexity 1356.6469 +4000 train 7.030014 (lr=3.8598e-05) (hash(x)=23661341) +4001 train 7.064260 (lr=3.8562e-05) (hash(x)=24644301) +4002 train 6.900340 (lr=3.8527e-05) (hash(x)=22938438) +4003 train 6.994980 (lr=3.8491e-05) (hash(x)=24315862) +4004 train 7.172836 (lr=3.8455e-05) (hash(x)=25169315) +4005 train 7.152199 (lr=3.8419e-05) (hash(x)=24752796) +4006 train 7.129460 (lr=3.8384e-05) (hash(x)=23103706) +4007 train 7.200252 (lr=3.8348e-05) (hash(x)=24881176) +4008 train 7.102965 (lr=3.8312e-05) (hash(x)=23971947) +4009 train 7.399260 (lr=3.8277e-05) (hash(x)=27741054) +4010 train 7.771428 (lr=3.8241e-05) (hash(x)=30956251) +4011 train 7.161996 (lr=3.8206e-05) (hash(x)=23649686) +4012 train 6.987757 (lr=3.8170e-05) (hash(x)=23344798) +4013 train 7.630921 (lr=3.8135e-05) (hash(x)=29529498) +4014 train 7.159415 (lr=3.8099e-05) (hash(x)=24688359) +4015 train 7.156677 (lr=3.8064e-05) (hash(x)=25593613) +4016 train 7.265007 (lr=3.8028e-05) (hash(x)=25674488) +4017 train 6.772127 (lr=3.7993e-05) (hash(x)=21345346) +4018 train 7.020332 (lr=3.7958e-05) (hash(x)=21978324) +4019 train 7.043901 (lr=3.7922e-05) (hash(x)=23669244) +4020 train 6.919866 (lr=3.7887e-05) (hash(x)=22479613) +4021 train 6.920660 (lr=3.7852e-05) (hash(x)=22855256) +4022 train 7.269983 (lr=3.7817e-05) (hash(x)=19759826) +4023 train 7.198908 (lr=3.7782e-05) (hash(x)=22886646) +4024 train 7.126920 (lr=3.7746e-05) (hash(x)=25553008) +4025 train 7.057227 (lr=3.7711e-05) (hash(x)=25487028) +4026 train 7.545300 (lr=3.7676e-05) (hash(x)=26799246) +4027 train 7.858694 (lr=3.7641e-05) (hash(x)=30728540) +4028 train 7.323318 (lr=3.7606e-05) (hash(x)=23966676) +4029 train 7.057024 (lr=3.7571e-05) (hash(x)=22118783) +4030 train 7.171208 (lr=3.7536e-05) (hash(x)=24744703) +4031 train 7.106201 (lr=3.7501e-05) (hash(x)=21407676) +4032 train 7.100353 (lr=3.7466e-05) (hash(x)=20623349) +4033 train 6.889223 (lr=3.7432e-05) (hash(x)=24723788) +4034 train 7.186275 (lr=3.7397e-05) (hash(x)=25030709) +4035 train 7.238265 (lr=3.7362e-05) (hash(x)=26326164) +4036 train 7.103911 (lr=3.7327e-05) (hash(x)=23754475) +4037 train 7.716132 (lr=3.7292e-05) (hash(x)=30112933) +4038 train 7.469281 (lr=3.7258e-05) (hash(x)=27474299) +4039 train 6.916400 (lr=3.7223e-05) (hash(x)=21720304) +4040 train 7.330982 (lr=3.7188e-05) (hash(x)=25142674) +4041 train 7.550642 (lr=3.7154e-05) (hash(x)=25284552) +4042 train 7.450304 (lr=3.7119e-05) (hash(x)=24554942) +4043 train 7.205696 (lr=3.7085e-05) (hash(x)=23773870) +4044 train 6.980658 (lr=3.7050e-05) (hash(x)=23896338) +4045 train 7.765418 (lr=3.7016e-05) (hash(x)=34984911) +4046 train 7.077352 (lr=3.6981e-05) (hash(x)=23854263) +4047 train 7.351884 (lr=3.6947e-05) (hash(x)=27263416) +4048 train 7.039046 (lr=3.6912e-05) (hash(x)=24989642) +4049 train 7.067636 (lr=3.6878e-05) (hash(x)=24492055) +4050 val loss 7.2174 +4050 val perplexity 1362.8942 +4050 train 6.940366 (lr=3.6844e-05) (hash(x)=21579916) +4051 train 7.206308 (lr=3.6810e-05) (hash(x)=25274710) +4052 train 7.089858 (lr=3.6775e-05) (hash(x)=24701947) +4053 train 7.085695 (lr=3.6741e-05) (hash(x)=25477340) +4054 train 6.971286 (lr=3.6707e-05) (hash(x)=23774195) +4055 train 7.229946 (lr=3.6673e-05) (hash(x)=25840801) +4056 train 7.423125 (lr=3.6638e-05) (hash(x)=27972529) +4057 train 7.180995 (lr=3.6604e-05) (hash(x)=26952458) +4058 train 6.692926 (lr=3.6570e-05) (hash(x)=22683653) +4059 train 6.771722 (lr=3.6536e-05) (hash(x)=20984129) +4060 train 6.966028 (lr=3.6502e-05) (hash(x)=22816482) +4061 train 7.201607 (lr=3.6468e-05) (hash(x)=24285302) +4062 train 7.611119 (lr=3.6434e-05) (hash(x)=31517950) +4063 train 7.857638 (lr=3.6400e-05) (hash(x)=31424568) +4064 train 7.600554 (lr=3.6367e-05) (hash(x)=29497876) +4065 train 7.468526 (lr=3.6333e-05) (hash(x)=27277376) +4066 train 7.174252 (lr=3.6299e-05) (hash(x)=26832588) +4067 train 7.006355 (lr=3.6265e-05) (hash(x)=25149712) +4068 train 7.021408 (lr=3.6231e-05) (hash(x)=23728457) +4069 train 6.955322 (lr=3.6198e-05) (hash(x)=25265136) +4070 train 7.434769 (lr=3.6164e-05) (hash(x)=25241681) +4071 train 7.154733 (lr=3.6130e-05) (hash(x)=23403065) +4072 train 7.121331 (lr=3.6097e-05) (hash(x)=25808207) +4073 train 7.038580 (lr=3.6063e-05) (hash(x)=23904844) +4074 train 6.742749 (lr=3.6029e-05) (hash(x)=18865309) +4075 train 7.181149 (lr=3.5996e-05) (hash(x)=23531744) +4076 train 7.201100 (lr=3.5962e-05) (hash(x)=25784275) +4077 train 6.949772 (lr=3.5929e-05) (hash(x)=22417529) +4078 train 6.961203 (lr=3.5895e-05) (hash(x)=23095491) +4079 train 7.085652 (lr=3.5862e-05) (hash(x)=22656033) +4080 train 7.077405 (lr=3.5829e-05) (hash(x)=25865435) +4081 train 7.190166 (lr=3.5795e-05) (hash(x)=25699377) +4082 train 7.223088 (lr=3.5762e-05) (hash(x)=20854084) +4083 train 6.804878 (lr=3.5729e-05) (hash(x)=18950799) +4084 train 7.021947 (lr=3.5695e-05) (hash(x)=22633739) +4085 train 7.859288 (lr=3.5662e-05) (hash(x)=34054446) +4086 train 7.326566 (lr=3.5629e-05) (hash(x)=27599387) +4087 train 7.151311 (lr=3.5596e-05) (hash(x)=26869295) +4088 train 7.141912 (lr=3.5563e-05) (hash(x)=24075139) +4089 train 7.581426 (lr=3.5530e-05) (hash(x)=29784110) +4090 train 7.886302 (lr=3.5497e-05) (hash(x)=34273918) +4091 train 8.259117 (lr=3.5464e-05) (hash(x)=34472685) +4092 train 7.621410 (lr=3.5431e-05) (hash(x)=30113791) +4093 train 6.886302 (lr=3.5398e-05) (hash(x)=22366381) +4094 train 7.124504 (lr=3.5365e-05) (hash(x)=24922935) +4095 train 7.303136 (lr=3.5332e-05) (hash(x)=25504151) +4096 train 7.313098 (lr=3.5299e-05) (hash(x)=24517375) +4097 train 7.925345 (lr=3.5266e-05) (hash(x)=25871651) +4098 train 7.005074 (lr=3.5233e-05) (hash(x)=23480225) +4099 train 6.882055 (lr=3.5200e-05) (hash(x)=22559978) +4100 val loss 7.2104 +4100 val perplexity 1353.4053 +4100 train 7.302495 (lr=3.5168e-05) (hash(x)=25795272) +4101 train 7.282271 (lr=3.5135e-05) (hash(x)=25440399) +4102 train 6.962028 (lr=3.5102e-05) (hash(x)=21581806) +4103 train 7.038631 (lr=3.5070e-05) (hash(x)=25781518) +4104 train 7.109442 (lr=3.5037e-05) (hash(x)=24682372) +4105 train 6.965506 (lr=3.5005e-05) (hash(x)=22440094) +4106 train 7.125680 (lr=3.4972e-05) (hash(x)=23661032) +4107 train 7.364552 (lr=3.4939e-05) (hash(x)=26966012) +4108 train 7.390456 (lr=3.4907e-05) (hash(x)=26232227) +4109 train 7.045629 (lr=3.4875e-05) (hash(x)=24110656) +4110 train 7.304358 (lr=3.4842e-05) (hash(x)=25938621) +4111 train 7.159503 (lr=3.4810e-05) (hash(x)=26432850) +4112 train 7.131153 (lr=3.4777e-05) (hash(x)=25387672) +4113 train 6.898453 (lr=3.4745e-05) (hash(x)=22740017) +4114 train 7.284038 (lr=3.4713e-05) (hash(x)=26384190) +4115 train 6.983352 (lr=3.4680e-05) (hash(x)=24725583) +4116 train 7.097816 (lr=3.4648e-05) (hash(x)=23986700) +4117 train 7.108964 (lr=3.4616e-05) (hash(x)=18529900) +4118 train 7.126014 (lr=3.4584e-05) (hash(x)=22236257) +4119 train 6.783849 (lr=3.4552e-05) (hash(x)=20155894) +4120 train 6.609238 (lr=3.4520e-05) (hash(x)=17423813) +4121 train 6.546188 (lr=3.4488e-05) (hash(x)=18905183) +4122 train 6.903481 (lr=3.4456e-05) (hash(x)=22534398) +4123 train 7.563732 (lr=3.4424e-05) (hash(x)=25247868) +4124 train 7.128661 (lr=3.4392e-05) (hash(x)=23994188) +4125 train 6.963426 (lr=3.4360e-05) (hash(x)=22929754) +4126 train 6.889931 (lr=3.4328e-05) (hash(x)=22485897) +4127 train 6.943952 (lr=3.4296e-05) (hash(x)=22270169) +4128 train 6.916577 (lr=3.4264e-05) (hash(x)=23638027) +4129 train 7.168089 (lr=3.4232e-05) (hash(x)=23821210) +4130 train 7.030987 (lr=3.4200e-05) (hash(x)=25021512) +4131 train 7.145239 (lr=3.4169e-05) (hash(x)=25240141) +4132 train 7.079376 (lr=3.4137e-05) (hash(x)=22833160) +4133 train 7.041700 (lr=3.4105e-05) (hash(x)=22909944) +4134 train 7.259868 (lr=3.4074e-05) (hash(x)=26163558) +4135 train 7.035620 (lr=3.4042e-05) (hash(x)=22108461) +4136 train 6.993619 (lr=3.4010e-05) (hash(x)=22549232) +4137 train 7.181886 (lr=3.3979e-05) (hash(x)=24701302) +4138 train 7.250913 (lr=3.3947e-05) (hash(x)=25206013) +4139 train 7.241139 (lr=3.3916e-05) (hash(x)=27896130) +4140 train 6.998638 (lr=3.3884e-05) (hash(x)=24106243) +4141 train 7.561543 (lr=3.3853e-05) (hash(x)=27158651) +4142 train 7.118759 (lr=3.3822e-05) (hash(x)=23841147) +4143 train 7.127884 (lr=3.3790e-05) (hash(x)=24802848) +4144 train 7.361928 (lr=3.3759e-05) (hash(x)=24911295) +4145 train 7.158246 (lr=3.3728e-05) (hash(x)=26473900) +4146 train 7.212188 (lr=3.3696e-05) (hash(x)=26785092) +4147 train 7.477659 (lr=3.3665e-05) (hash(x)=30188532) +4148 train 7.048200 (lr=3.3634e-05) (hash(x)=25010649) +4149 train 7.038692 (lr=3.3603e-05) (hash(x)=22409016) +4150 val loss 7.2031 +4150 val perplexity 1343.5986 +4150 train 7.783664 (lr=3.3572e-05) (hash(x)=31675024) +4151 train 7.066120 (lr=3.3541e-05) (hash(x)=25086604) +4152 train 7.066571 (lr=3.3510e-05) (hash(x)=24429343) +4153 train 7.251982 (lr=3.3479e-05) (hash(x)=25014232) +4154 train 7.153546 (lr=3.3448e-05) (hash(x)=25366275) +4155 train 7.676126 (lr=3.3417e-05) (hash(x)=24031473) +4156 train 7.166214 (lr=3.3386e-05) (hash(x)=26651059) +4157 train 7.248662 (lr=3.3355e-05) (hash(x)=26069721) +4158 train 7.398445 (lr=3.3324e-05) (hash(x)=28114382) +4159 train 7.363488 (lr=3.3293e-05) (hash(x)=26983186) +4160 train 6.766754 (lr=3.3262e-05) (hash(x)=21944670) +4161 train 7.467601 (lr=3.3232e-05) (hash(x)=28155702) +4162 train 6.938015 (lr=3.3201e-05) (hash(x)=24765002) +4163 train 7.165039 (lr=3.3170e-05) (hash(x)=26492636) +4164 train 7.146428 (lr=3.3140e-05) (hash(x)=24063705) +4165 train 7.415382 (lr=3.3109e-05) (hash(x)=27079573) +4166 train 7.067010 (lr=3.3078e-05) (hash(x)=24912201) +4167 train 7.184226 (lr=3.3048e-05) (hash(x)=27208507) +4168 train 7.114661 (lr=3.3017e-05) (hash(x)=25824320) +4169 train 7.602727 (lr=3.2987e-05) (hash(x)=29641677) +4170 train 7.326555 (lr=3.2956e-05) (hash(x)=26275614) +4171 train 7.183866 (lr=3.2926e-05) (hash(x)=25227725) +4172 train 7.234842 (lr=3.2895e-05) (hash(x)=27417375) +4173 train 7.400658 (lr=3.2865e-05) (hash(x)=25581973) +4174 train 7.682621 (lr=3.2835e-05) (hash(x)=30360417) +4175 train 7.004640 (lr=3.2804e-05) (hash(x)=23862845) +4176 train 7.081864 (lr=3.2774e-05) (hash(x)=25415130) +4177 train 7.074165 (lr=3.2744e-05) (hash(x)=23111123) +4178 train 7.011626 (lr=3.2714e-05) (hash(x)=24022804) +4179 train 7.085123 (lr=3.2684e-05) (hash(x)=25148490) +4180 train 7.262143 (lr=3.2653e-05) (hash(x)=22792092) +4181 train 7.352474 (lr=3.2623e-05) (hash(x)=24779698) +4182 train 7.281821 (lr=3.2593e-05) (hash(x)=24870844) +4183 train 6.977611 (lr=3.2563e-05) (hash(x)=22664494) +4184 train 7.013396 (lr=3.2533e-05) (hash(x)=22599729) +4185 train 7.219072 (lr=3.2503e-05) (hash(x)=24707078) +4186 train 7.010087 (lr=3.2473e-05) (hash(x)=23823945) +4187 train 6.715009 (lr=3.2443e-05) (hash(x)=22219856) +4188 train 7.403014 (lr=3.2414e-05) (hash(x)=27061401) +4189 train 7.107138 (lr=3.2384e-05) (hash(x)=23398766) +4190 train 7.237019 (lr=3.2354e-05) (hash(x)=27916730) +4191 train 7.114257 (lr=3.2324e-05) (hash(x)=24092927) +4192 train 7.159526 (lr=3.2294e-05) (hash(x)=24723657) +4193 train 7.202143 (lr=3.2265e-05) (hash(x)=24676155) +4194 train 7.086757 (lr=3.2235e-05) (hash(x)=23455369) +4195 train 7.030446 (lr=3.2205e-05) (hash(x)=21999890) +4196 train 6.986181 (lr=3.2176e-05) (hash(x)=23385567) +4197 train 7.162847 (lr=3.2146e-05) (hash(x)=25120814) +4198 train 6.861291 (lr=3.2117e-05) (hash(x)=21308113) +4199 train 7.185777 (lr=3.2087e-05) (hash(x)=27213812) +4200 val loss 7.1931 +4200 val perplexity 1330.2802 +4200 train 6.756625 (lr=3.2058e-05) (hash(x)=19675382) +4201 train 7.030414 (lr=3.2028e-05) (hash(x)=23882161) +4202 train 7.042039 (lr=3.1999e-05) (hash(x)=24338567) +4203 train 7.301677 (lr=3.1970e-05) (hash(x)=27649723) +4204 train 7.131200 (lr=3.1940e-05) (hash(x)=27563514) +4205 train 7.118640 (lr=3.1911e-05) (hash(x)=23128552) +4206 train 7.024664 (lr=3.1882e-05) (hash(x)=26203283) +4207 train 7.063945 (lr=3.1852e-05) (hash(x)=23929955) +4208 train 6.754198 (lr=3.1823e-05) (hash(x)=20978691) +4209 train 7.060330 (lr=3.1794e-05) (hash(x)=21875178) +4210 train 7.112830 (lr=3.1765e-05) (hash(x)=23563293) +4211 train 7.273695 (lr=3.1736e-05) (hash(x)=25538503) +4212 train 7.290524 (lr=3.1707e-05) (hash(x)=24171014) +4213 train 7.129030 (lr=3.1678e-05) (hash(x)=22306665) +4214 train 7.076223 (lr=3.1649e-05) (hash(x)=26082318) +4215 train 6.880263 (lr=3.1620e-05) (hash(x)=23025790) +4216 train 6.930772 (lr=3.1591e-05) (hash(x)=21146597) +4217 train 7.290685 (lr=3.1562e-05) (hash(x)=27470230) +4218 train 7.061426 (lr=3.1533e-05) (hash(x)=22691005) +4219 train 6.847461 (lr=3.1504e-05) (hash(x)=21550313) +4220 train 6.947217 (lr=3.1475e-05) (hash(x)=20618443) +4221 train 7.038335 (lr=3.1447e-05) (hash(x)=25260787) +4222 train 7.150936 (lr=3.1418e-05) (hash(x)=25249873) +4223 train 6.765121 (lr=3.1389e-05) (hash(x)=20452272) +4224 train 7.011977 (lr=3.1360e-05) (hash(x)=25649764) +4225 train 6.903619 (lr=3.1332e-05) (hash(x)=19589460) +4226 train 7.346973 (lr=3.1303e-05) (hash(x)=26477595) +4227 train 7.531981 (lr=3.1275e-05) (hash(x)=27585442) +4228 train 7.315286 (lr=3.1246e-05) (hash(x)=25821343) +4229 train 7.217668 (lr=3.1218e-05) (hash(x)=24549919) +4230 train 7.130139 (lr=3.1189e-05) (hash(x)=26124522) +4231 train 7.407736 (lr=3.1161e-05) (hash(x)=26473464) +4232 train 7.408800 (lr=3.1132e-05) (hash(x)=28883028) +4233 train 7.384111 (lr=3.1104e-05) (hash(x)=29611296) +4234 train 7.257812 (lr=3.1076e-05) (hash(x)=29059941) +4235 train 7.143699 (lr=3.1047e-05) (hash(x)=26368203) +4236 train 7.160478 (lr=3.1019e-05) (hash(x)=27021360) +4237 train 7.118573 (lr=3.0991e-05) (hash(x)=26135379) +4238 train 6.907269 (lr=3.0963e-05) (hash(x)=25862549) +4239 train 7.281192 (lr=3.0935e-05) (hash(x)=28276603) +4240 train 6.898145 (lr=3.0906e-05) (hash(x)=22170090) +4241 train 7.200811 (lr=3.0878e-05) (hash(x)=22625589) +4242 train 7.238613 (lr=3.0850e-05) (hash(x)=25751475) +4243 train 7.126631 (lr=3.0822e-05) (hash(x)=25836838) +4244 train 7.090352 (lr=3.0794e-05) (hash(x)=23938214) +4245 train 7.012477 (lr=3.0766e-05) (hash(x)=22759365) +4246 train 6.986824 (lr=3.0738e-05) (hash(x)=24964628) +4247 train 6.702396 (lr=3.0711e-05) (hash(x)=21480367) +4248 train 7.261970 (lr=3.0683e-05) (hash(x)=25974694) +4249 train 7.568860 (lr=3.0655e-05) (hash(x)=29830546) +4250 val loss 7.2016 +4250 val perplexity 1341.5546 +4250 train 7.247478 (lr=3.0627e-05) (hash(x)=26283200) +4251 train 7.263724 (lr=3.0599e-05) (hash(x)=25605672) +4252 train 6.953108 (lr=3.0572e-05) (hash(x)=21439107) +4253 train 6.857728 (lr=3.0544e-05) (hash(x)=22626883) +4254 train 7.226475 (lr=3.0516e-05) (hash(x)=25627150) +4255 train 7.349491 (lr=3.0489e-05) (hash(x)=24658642) +4256 train 7.421797 (lr=3.0461e-05) (hash(x)=29755505) +4257 train 7.152740 (lr=3.0434e-05) (hash(x)=22750846) +4258 train 7.066093 (lr=3.0406e-05) (hash(x)=21892651) +4259 train 7.153521 (lr=3.0379e-05) (hash(x)=22487960) +4260 train 7.215590 (lr=3.0351e-05) (hash(x)=24059869) +4261 train 6.993873 (lr=3.0324e-05) (hash(x)=21090180) +4262 train 7.084288 (lr=3.0296e-05) (hash(x)=22716452) +4263 train 7.361276 (lr=3.0269e-05) (hash(x)=26854801) +4264 train 7.107485 (lr=3.0242e-05) (hash(x)=23815428) +4265 train 6.941143 (lr=3.0214e-05) (hash(x)=23368704) +4266 train 7.034858 (lr=3.0187e-05) (hash(x)=24301098) +4267 train 7.223787 (lr=3.0160e-05) (hash(x)=25025039) +4268 train 6.982132 (lr=3.0133e-05) (hash(x)=25425736) +4269 train 7.205226 (lr=3.0106e-05) (hash(x)=27439380) +4270 train 6.673843 (lr=3.0079e-05) (hash(x)=18682756) +4271 train 6.798939 (lr=3.0051e-05) (hash(x)=17862226) +4272 train 7.408984 (lr=3.0024e-05) (hash(x)=29946491) +4273 train 6.631622 (lr=2.9997e-05) (hash(x)=21392062) +4274 train 7.191669 (lr=2.9970e-05) (hash(x)=25195556) +4275 train 7.179433 (lr=2.9944e-05) (hash(x)=26682036) +4276 train 7.099291 (lr=2.9917e-05) (hash(x)=21235260) +4277 train 6.932901 (lr=2.9890e-05) (hash(x)=22118984) +4278 train 6.947334 (lr=2.9863e-05) (hash(x)=24094510) +4279 train 7.462405 (lr=2.9836e-05) (hash(x)=28519182) +4280 train 7.138608 (lr=2.9809e-05) (hash(x)=26652859) +4281 train 7.047015 (lr=2.9783e-05) (hash(x)=24463139) +4282 train 7.010339 (lr=2.9756e-05) (hash(x)=23281870) +4283 train 7.232372 (lr=2.9729e-05) (hash(x)=29181174) +4284 train 6.919674 (lr=2.9703e-05) (hash(x)=24797417) +4285 train 7.274953 (lr=2.9676e-05) (hash(x)=29026537) +4286 train 7.074590 (lr=2.9650e-05) (hash(x)=23045165) +4287 train 7.024361 (lr=2.9623e-05) (hash(x)=25193694) +4288 train 7.042333 (lr=2.9597e-05) (hash(x)=23475407) +4289 train 7.186599 (lr=2.9570e-05) (hash(x)=24875410) +4290 train 7.084224 (lr=2.9544e-05) (hash(x)=26328101) +4291 train 7.331966 (lr=2.9517e-05) (hash(x)=26273661) +4292 train 7.053268 (lr=2.9491e-05) (hash(x)=23271891) +4293 train 7.006017 (lr=2.9465e-05) (hash(x)=23300732) +4294 train 7.115667 (lr=2.9438e-05) (hash(x)=24243693) +4295 train 7.197330 (lr=2.9412e-05) (hash(x)=25642620) +4296 train 7.229123 (lr=2.9386e-05) (hash(x)=27730411) +4297 train 7.059188 (lr=2.9360e-05) (hash(x)=25485335) +4298 train 6.930992 (lr=2.9334e-05) (hash(x)=25268789) +4299 train 7.364766 (lr=2.9308e-05) (hash(x)=28917143) +4300 val loss 7.2009 +4300 val perplexity 1340.6810 +4300 train 7.467571 (lr=2.9281e-05) (hash(x)=28987991) +4301 train 7.214366 (lr=2.9255e-05) (hash(x)=25989151) +4302 train 7.110598 (lr=2.9229e-05) (hash(x)=25658195) +4303 train 7.088703 (lr=2.9203e-05) (hash(x)=25765909) +4304 train 7.102833 (lr=2.9178e-05) (hash(x)=25704261) +4305 train 7.093909 (lr=2.9152e-05) (hash(x)=24438198) +4306 train 6.917562 (lr=2.9126e-05) (hash(x)=22871710) +4307 train 6.780367 (lr=2.9100e-05) (hash(x)=20160896) +4308 train 7.297526 (lr=2.9074e-05) (hash(x)=24218641) +4309 train 6.754231 (lr=2.9048e-05) (hash(x)=22073751) +4310 train 7.054296 (lr=2.9023e-05) (hash(x)=26434959) +4311 train 6.751211 (lr=2.8997e-05) (hash(x)=20750531) +4312 train 6.904619 (lr=2.8971e-05) (hash(x)=22232293) +4313 train 7.226445 (lr=2.8946e-05) (hash(x)=27324521) +4314 train 6.870393 (lr=2.8920e-05) (hash(x)=22217862) +4315 train 7.319440 (lr=2.8895e-05) (hash(x)=25741958) +4316 train 7.059967 (lr=2.8869e-05) (hash(x)=22738456) +4317 train 7.093329 (lr=2.8844e-05) (hash(x)=25387302) +4318 train 7.043746 (lr=2.8818e-05) (hash(x)=24669014) +4319 train 7.173940 (lr=2.8793e-05) (hash(x)=24917098) +4320 train 7.134950 (lr=2.8767e-05) (hash(x)=26698227) +4321 train 6.929372 (lr=2.8742e-05) (hash(x)=23518293) +4322 train 6.882093 (lr=2.8717e-05) (hash(x)=23643971) +4323 train 7.068958 (lr=2.8691e-05) (hash(x)=25659505) +4324 train 6.886184 (lr=2.8666e-05) (hash(x)=22697720) +4325 train 7.360369 (lr=2.8641e-05) (hash(x)=25082178) +4326 train 6.903893 (lr=2.8616e-05) (hash(x)=24166546) +4327 train 7.081520 (lr=2.8591e-05) (hash(x)=24499766) +4328 train 7.212471 (lr=2.8566e-05) (hash(x)=24338607) +4329 train 6.976456 (lr=2.8541e-05) (hash(x)=23225420) +4330 train 7.128662 (lr=2.8515e-05) (hash(x)=25907032) +4331 train 6.931450 (lr=2.8490e-05) (hash(x)=24634979) +4332 train 7.018817 (lr=2.8466e-05) (hash(x)=22161377) +4333 train 7.125279 (lr=2.8441e-05) (hash(x)=22559939) +4334 train 6.956708 (lr=2.8416e-05) (hash(x)=20840022) +4335 train 7.248476 (lr=2.8391e-05) (hash(x)=25067358) +4336 train 6.893981 (lr=2.8366e-05) (hash(x)=23432626) +4337 train 7.060009 (lr=2.8341e-05) (hash(x)=23820385) +4338 train 7.846705 (lr=2.8317e-05) (hash(x)=31594930) +4339 train 7.294892 (lr=2.8292e-05) (hash(x)=27138750) +4340 train 7.462421 (lr=2.8267e-05) (hash(x)=30031341) +4341 train 7.028944 (lr=2.8242e-05) (hash(x)=24602807) +4342 train 6.845570 (lr=2.8218e-05) (hash(x)=21584976) +4343 train 7.233457 (lr=2.8193e-05) (hash(x)=27479796) +4344 train 6.907600 (lr=2.8169e-05) (hash(x)=22746241) +4345 train 7.045742 (lr=2.8144e-05) (hash(x)=19728452) +4346 train 6.874752 (lr=2.8120e-05) (hash(x)=24502020) +4347 train 7.340897 (lr=2.8095e-05) (hash(x)=28225954) +4348 train 6.967177 (lr=2.8071e-05) (hash(x)=23893447) +4349 train 7.291490 (lr=2.8047e-05) (hash(x)=25654586) +4350 val loss 7.1987 +4350 val perplexity 1337.7544 +4350 train 7.147139 (lr=2.8022e-05) (hash(x)=23856469) +4351 train 7.060315 (lr=2.7998e-05) (hash(x)=23136080) +4352 train 7.220737 (lr=2.7974e-05) (hash(x)=26532918) +4353 train 7.117836 (lr=2.7949e-05) (hash(x)=25461947) +4354 train 7.101230 (lr=2.7925e-05) (hash(x)=26590231) +4355 train 6.858865 (lr=2.7901e-05) (hash(x)=21441985) +4356 train 7.113472 (lr=2.7877e-05) (hash(x)=26507941) +4357 train 7.399279 (lr=2.7853e-05) (hash(x)=26245238) +4358 train 7.190835 (lr=2.7829e-05) (hash(x)=24879059) +4359 train 7.442436 (lr=2.7805e-05) (hash(x)=29810074) +4360 train 6.876163 (lr=2.7781e-05) (hash(x)=24258069) +4361 train 7.027496 (lr=2.7757e-05) (hash(x)=25229360) +4362 train 7.212485 (lr=2.7733e-05) (hash(x)=25440206) +4363 train 7.079998 (lr=2.7709e-05) (hash(x)=23222125) +4364 train 6.938252 (lr=2.7685e-05) (hash(x)=23353186) +4365 train 7.134780 (lr=2.7662e-05) (hash(x)=26995240) +4366 train 7.078094 (lr=2.7638e-05) (hash(x)=24135899) +4367 train 7.081775 (lr=2.7614e-05) (hash(x)=24765539) +4368 train 7.139191 (lr=2.7590e-05) (hash(x)=26051004) +4369 train 6.952976 (lr=2.7567e-05) (hash(x)=22559142) +4370 train 6.838838 (lr=2.7543e-05) (hash(x)=20364388) +4371 train 7.276977 (lr=2.7519e-05) (hash(x)=25938817) +4372 train 7.316958 (lr=2.7496e-05) (hash(x)=26060945) +4373 train 7.231592 (lr=2.7472e-05) (hash(x)=27866714) +4374 train 7.162430 (lr=2.7449e-05) (hash(x)=27104972) +4375 train 6.846350 (lr=2.7425e-05) (hash(x)=22216309) +4376 train 6.910348 (lr=2.7402e-05) (hash(x)=20781533) +4377 train 6.814054 (lr=2.7379e-05) (hash(x)=18784350) +4378 train 6.954813 (lr=2.7355e-05) (hash(x)=21102897) +4379 train 7.188600 (lr=2.7332e-05) (hash(x)=25647489) +4380 train 6.993712 (lr=2.7309e-05) (hash(x)=24486462) +4381 train 7.263906 (lr=2.7286e-05) (hash(x)=26539114) +4382 train 6.906883 (lr=2.7262e-05) (hash(x)=20026045) +4383 train 7.209156 (lr=2.7239e-05) (hash(x)=20613861) +4384 train 6.914296 (lr=2.7216e-05) (hash(x)=20676237) +4385 train 7.118629 (lr=2.7193e-05) (hash(x)=24893163) +4386 train 6.699193 (lr=2.7170e-05) (hash(x)=17299395) +4387 train 6.852895 (lr=2.7147e-05) (hash(x)=19580191) +4388 train 7.026421 (lr=2.7124e-05) (hash(x)=25588218) +4389 train 7.158359 (lr=2.7101e-05) (hash(x)=26433063) +4390 train 7.233837 (lr=2.7078e-05) (hash(x)=24917693) +4391 train 6.932120 (lr=2.7055e-05) (hash(x)=23462447) +4392 train 7.132527 (lr=2.7032e-05) (hash(x)=27185416) +4393 train 7.275739 (lr=2.7010e-05) (hash(x)=24109010) +4394 train 7.024523 (lr=2.6987e-05) (hash(x)=21486000) +4395 train 6.909513 (lr=2.6964e-05) (hash(x)=22230006) +4396 train 7.303783 (lr=2.6941e-05) (hash(x)=26092311) +4397 train 7.052126 (lr=2.6919e-05) (hash(x)=24112426) +4398 train 6.923707 (lr=2.6896e-05) (hash(x)=21881373) +4399 train 7.042575 (lr=2.6873e-05) (hash(x)=26739455) +4400 val loss 7.1869 +4400 val perplexity 1321.9969 +4400 train 6.932718 (lr=2.6851e-05) (hash(x)=22873602) +4401 train 6.990630 (lr=2.6828e-05) (hash(x)=26748712) +4402 train 7.210976 (lr=2.6806e-05) (hash(x)=26306618) +4403 train 7.343938 (lr=2.6783e-05) (hash(x)=26898808) +4404 train 7.086505 (lr=2.6761e-05) (hash(x)=25067751) +4405 train 7.107202 (lr=2.6739e-05) (hash(x)=25397145) +4406 train 7.270860 (lr=2.6716e-05) (hash(x)=24796962) +4407 train 7.061467 (lr=2.6694e-05) (hash(x)=23222996) +4408 train 7.040941 (lr=2.6672e-05) (hash(x)=24820189) +4409 train 7.440574 (lr=2.6649e-05) (hash(x)=27669038) +4410 train 7.037448 (lr=2.6627e-05) (hash(x)=24283976) +4411 train 7.245558 (lr=2.6605e-05) (hash(x)=25018789) +4412 train 7.140670 (lr=2.6583e-05) (hash(x)=26247064) +4413 train 7.146816 (lr=2.6561e-05) (hash(x)=22942904) +4414 train 7.049292 (lr=2.6539e-05) (hash(x)=23918746) +4415 train 7.162654 (lr=2.6517e-05) (hash(x)=26489285) +4416 train 6.188703 (lr=2.6495e-05) (hash(x)=14942495) +4417 train 6.976682 (lr=2.6473e-05) (hash(x)=23908505) +4418 train 7.200660 (lr=2.6451e-05) (hash(x)=25854036) +4419 train 7.088789 (lr=2.6429e-05) (hash(x)=27522868) +4420 train 6.996295 (lr=2.6407e-05) (hash(x)=26549205) +4421 train 6.866226 (lr=2.6385e-05) (hash(x)=24565522) +4422 train 7.198586 (lr=2.6364e-05) (hash(x)=23919123) +4423 train 7.055698 (lr=2.6342e-05) (hash(x)=25185942) +4424 train 7.078519 (lr=2.6320e-05) (hash(x)=24818969) +4425 train 7.147158 (lr=2.6298e-05) (hash(x)=26750372) +4426 train 7.152130 (lr=2.6277e-05) (hash(x)=25621536) +4427 train 7.607473 (lr=2.6255e-05) (hash(x)=28037060) +4428 train 7.618267 (lr=2.6234e-05) (hash(x)=30829517) +4429 train 7.215229 (lr=2.6212e-05) (hash(x)=28728766) +4430 train 7.146835 (lr=2.6191e-05) (hash(x)=25936895) +4431 train 7.298884 (lr=2.6169e-05) (hash(x)=27476158) +4432 train 7.016193 (lr=2.6148e-05) (hash(x)=23297921) +4433 train 7.000396 (lr=2.6126e-05) (hash(x)=23201299) +4434 train 6.922741 (lr=2.6105e-05) (hash(x)=22681766) +4435 train 6.900328 (lr=2.6084e-05) (hash(x)=23217512) +4436 train 7.387883 (lr=2.6062e-05) (hash(x)=29322443) +4437 train 6.990636 (lr=2.6041e-05) (hash(x)=23502072) +4438 train 7.092346 (lr=2.6020e-05) (hash(x)=28873527) +4439 train 7.102014 (lr=2.5999e-05) (hash(x)=23653175) +4440 train 6.936258 (lr=2.5978e-05) (hash(x)=21635879) +4441 train 6.981823 (lr=2.5957e-05) (hash(x)=22201854) +4442 train 6.893903 (lr=2.5936e-05) (hash(x)=23101164) +4443 train 7.288976 (lr=2.5915e-05) (hash(x)=25475122) +4444 train 7.058336 (lr=2.5894e-05) (hash(x)=25124825) +4445 train 7.140845 (lr=2.5873e-05) (hash(x)=26883852) +4446 train 6.986960 (lr=2.5852e-05) (hash(x)=24731829) +4447 train 6.973655 (lr=2.5831e-05) (hash(x)=22405076) +4448 train 7.097118 (lr=2.5810e-05) (hash(x)=27633869) +4449 train 7.159674 (lr=2.5789e-05) (hash(x)=25162594) +4450 val loss 7.1867 +4450 val perplexity 1321.6919 +4450 train 7.168981 (lr=2.5768e-05) (hash(x)=26438149) +4451 train 7.155174 (lr=2.5748e-05) (hash(x)=26748800) +4452 train 6.942586 (lr=2.5727e-05) (hash(x)=22971620) +4453 train 7.057056 (lr=2.5706e-05) (hash(x)=25886430) +4454 train 6.827725 (lr=2.5686e-05) (hash(x)=21084137) +4455 train 7.005918 (lr=2.5665e-05) (hash(x)=25673545) +4456 train 7.670766 (lr=2.5645e-05) (hash(x)=29389002) +4457 train 6.741626 (lr=2.5624e-05) (hash(x)=21676076) +4458 train 6.863039 (lr=2.5604e-05) (hash(x)=22616647) +4459 train 7.216994 (lr=2.5583e-05) (hash(x)=22771197) +4460 train 7.152605 (lr=2.5563e-05) (hash(x)=26393514) +4461 train 7.378152 (lr=2.5542e-05) (hash(x)=24996433) +4462 train 7.041464 (lr=2.5522e-05) (hash(x)=19594028) +4463 train 7.176459 (lr=2.5502e-05) (hash(x)=22675428) +4464 train 7.188058 (lr=2.5482e-05) (hash(x)=26566551) +4465 train 7.180451 (lr=2.5461e-05) (hash(x)=22469290) +4466 train 7.611769 (lr=2.5441e-05) (hash(x)=29821654) +4467 train 7.146079 (lr=2.5421e-05) (hash(x)=26305388) +4468 train 7.010780 (lr=2.5401e-05) (hash(x)=21998506) +4469 train 7.421558 (lr=2.5381e-05) (hash(x)=23953315) +4470 train 7.065117 (lr=2.5361e-05) (hash(x)=23985456) +4471 train 7.436176 (lr=2.5341e-05) (hash(x)=28168456) +4472 train 7.106557 (lr=2.5321e-05) (hash(x)=25126411) +4473 train 6.936267 (lr=2.5301e-05) (hash(x)=24619336) +4474 train 7.133943 (lr=2.5281e-05) (hash(x)=24467798) +4475 train 7.904553 (lr=2.5261e-05) (hash(x)=31673254) +4476 train 7.719860 (lr=2.5241e-05) (hash(x)=29929610) +4477 train 7.461418 (lr=2.5221e-05) (hash(x)=29412572) +4478 train 7.605818 (lr=2.5202e-05) (hash(x)=31910006) +4479 train 7.253095 (lr=2.5182e-05) (hash(x)=26072586) +4480 train 7.182299 (lr=2.5162e-05) (hash(x)=25782825) +4481 train 7.033622 (lr=2.5143e-05) (hash(x)=21131363) +4482 train 7.173080 (lr=2.5123e-05) (hash(x)=25071223) +4483 train 7.773585 (lr=2.5103e-05) (hash(x)=32249577) +4484 train 6.980033 (lr=2.5084e-05) (hash(x)=24752808) +4485 train 7.048793 (lr=2.5064e-05) (hash(x)=24970539) +4486 train 6.969187 (lr=2.5045e-05) (hash(x)=24191005) +4487 train 7.199949 (lr=2.5026e-05) (hash(x)=24974331) +4488 train 7.327952 (lr=2.5006e-05) (hash(x)=27043409) +4489 train 6.707556 (lr=2.4987e-05) (hash(x)=11320385) +4490 train 6.653665 (lr=2.4967e-05) (hash(x)=11919565) +4491 train 6.721107 (lr=2.4948e-05) (hash(x)=10404694) +4492 train 6.753769 (lr=2.4929e-05) (hash(x)=12393159) +4493 train 6.660604 (lr=2.4910e-05) (hash(x)=11843609) +4494 train 6.716920 (lr=2.4891e-05) (hash(x)=12632729) +4495 train 7.038150 (lr=2.4871e-05) (hash(x)=21951984) +4496 train 7.722765 (lr=2.4852e-05) (hash(x)=19411544) +4497 train 7.663837 (lr=2.4833e-05) (hash(x)=21000228) +4498 train 7.260179 (lr=2.4814e-05) (hash(x)=26018207) +4499 train 7.280594 (lr=2.4795e-05) (hash(x)=24659058) +4500 val loss 7.1885 +4500 val perplexity 1324.1798 +4500 train 7.458872 (lr=2.4776e-05) (hash(x)=27919597) +4501 train 7.044487 (lr=2.4757e-05) (hash(x)=26232596) +4502 train 7.198729 (lr=2.4738e-05) (hash(x)=26248912) +4503 train 7.084371 (lr=2.4720e-05) (hash(x)=25403751) +4504 train 6.993394 (lr=2.4701e-05) (hash(x)=21096637) +4505 train 7.128726 (lr=2.4682e-05) (hash(x)=26560941) +4506 train 7.138444 (lr=2.4663e-05) (hash(x)=24942406) +4507 train 7.203114 (lr=2.4645e-05) (hash(x)=24405748) +4508 train 7.082756 (lr=2.4626e-05) (hash(x)=22975455) +4509 train 7.022941 (lr=2.4607e-05) (hash(x)=26358820) +4510 train 7.009905 (lr=2.4589e-05) (hash(x)=24211938) +4511 train 7.218060 (lr=2.4570e-05) (hash(x)=26396012) +4512 train 6.894718 (lr=2.4552e-05) (hash(x)=22534410) +4513 train 7.019428 (lr=2.4533e-05) (hash(x)=23855025) +4514 train 6.911726 (lr=2.4515e-05) (hash(x)=22722345) +4515 train 6.892375 (lr=2.4496e-05) (hash(x)=22779251) +4516 train 7.178635 (lr=2.4478e-05) (hash(x)=23973078) +4517 train 7.055165 (lr=2.4460e-05) (hash(x)=19886228) +4518 train 7.129718 (lr=2.4441e-05) (hash(x)=23849694) +4519 train 7.493451 (lr=2.4423e-05) (hash(x)=24827190) +4520 train 7.071477 (lr=2.4405e-05) (hash(x)=25111498) +4521 train 7.882649 (lr=2.4387e-05) (hash(x)=29752556) +4522 train 7.376376 (lr=2.4369e-05) (hash(x)=25606805) +4523 train 7.089801 (lr=2.4350e-05) (hash(x)=22209714) +4524 train 6.862015 (lr=2.4332e-05) (hash(x)=24991834) +4525 train 7.128846 (lr=2.4314e-05) (hash(x)=27808158) +4526 train 7.049436 (lr=2.4296e-05) (hash(x)=23041199) +4527 train 7.122366 (lr=2.4278e-05) (hash(x)=24847458) +4528 train 7.052901 (lr=2.4260e-05) (hash(x)=25091787) +4529 train 7.979688 (lr=2.4243e-05) (hash(x)=29745551) +4530 train 6.802368 (lr=2.4225e-05) (hash(x)=20447167) +4531 train 6.989394 (lr=2.4207e-05) (hash(x)=20720911) +4532 train 7.140974 (lr=2.4189e-05) (hash(x)=24803353) +4533 train 7.218524 (lr=2.4171e-05) (hash(x)=23780724) +4534 train 7.208302 (lr=2.4154e-05) (hash(x)=23423120) +4535 train 6.885553 (lr=2.4136e-05) (hash(x)=22159088) +4536 train 7.071297 (lr=2.4118e-05) (hash(x)=25820304) +4537 train 6.866108 (lr=2.4101e-05) (hash(x)=22813612) +4538 train 7.195459 (lr=2.4083e-05) (hash(x)=27827979) +4539 train 7.206337 (lr=2.4066e-05) (hash(x)=25737179) +4540 train 7.423265 (lr=2.4048e-05) (hash(x)=23401504) +4541 train 7.069300 (lr=2.4031e-05) (hash(x)=25071988) +4542 train 7.127077 (lr=2.4013e-05) (hash(x)=22844541) +4543 train 6.847462 (lr=2.3996e-05) (hash(x)=22140034) +4544 train 7.132124 (lr=2.3979e-05) (hash(x)=26522091) +4545 train 7.148624 (lr=2.3961e-05) (hash(x)=24099725) +4546 train 6.731079 (lr=2.3944e-05) (hash(x)=19127182) +4547 train 6.848412 (lr=2.3927e-05) (hash(x)=18992693) +4548 train 7.904822 (lr=2.3910e-05) (hash(x)=26723015) +4549 train 7.634109 (lr=2.3892e-05) (hash(x)=30389969) +4550 val loss 7.1845 +4550 val perplexity 1318.8859 +4550 train 7.003648 (lr=2.3875e-05) (hash(x)=24065654) +4551 train 6.806262 (lr=2.3858e-05) (hash(x)=19044797) +4552 train 7.204212 (lr=2.3841e-05) (hash(x)=24919665) +4553 train 7.263780 (lr=2.3824e-05) (hash(x)=22780968) +4554 train 6.983449 (lr=2.3807e-05) (hash(x)=24549699) +4555 train 6.905329 (lr=2.3790e-05) (hash(x)=21374811) +4556 train 7.032815 (lr=2.3773e-05) (hash(x)=25225950) +4557 train 7.126488 (lr=2.3757e-05) (hash(x)=25691882) +4558 train 7.047159 (lr=2.3740e-05) (hash(x)=24685235) +4559 train 6.909090 (lr=2.3723e-05) (hash(x)=23932794) +4560 train 7.466886 (lr=2.3706e-05) (hash(x)=28152043) +4561 train 6.961761 (lr=2.3690e-05) (hash(x)=23417051) +4562 train 7.058107 (lr=2.3673e-05) (hash(x)=26250211) +4563 train 7.256497 (lr=2.3656e-05) (hash(x)=25428813) +4564 train 7.390480 (lr=2.3640e-05) (hash(x)=27477379) +4565 train 7.177799 (lr=2.3623e-05) (hash(x)=23015212) +4566 train 6.949420 (lr=2.3607e-05) (hash(x)=22837608) +4567 train 7.027542 (lr=2.3590e-05) (hash(x)=25256890) +4568 train 6.943939 (lr=2.3574e-05) (hash(x)=22742827) +4569 train 7.338599 (lr=2.3557e-05) (hash(x)=30167922) +4570 train 7.029915 (lr=2.3541e-05) (hash(x)=24540265) +4571 train 7.355139 (lr=2.3524e-05) (hash(x)=26752941) +4572 train 7.130083 (lr=2.3508e-05) (hash(x)=25094026) +4573 train 7.808812 (lr=2.3492e-05) (hash(x)=28508785) +4574 train 7.245040 (lr=2.3476e-05) (hash(x)=26501871) +4575 train 7.045485 (lr=2.3459e-05) (hash(x)=24161711) +4576 train 6.971448 (lr=2.3443e-05) (hash(x)=24313695) +4577 train 7.381619 (lr=2.3427e-05) (hash(x)=28248933) +4578 train 7.583009 (lr=2.3411e-05) (hash(x)=28445722) +4579 train 7.117839 (lr=2.3395e-05) (hash(x)=24589015) +4580 train 7.293871 (lr=2.3379e-05) (hash(x)=26192193) +4581 train 6.944802 (lr=2.3363e-05) (hash(x)=25131316) +4582 train 7.020299 (lr=2.3347e-05) (hash(x)=26631504) +4583 train 6.876928 (lr=2.3331e-05) (hash(x)=22036817) +4584 train 7.504983 (lr=2.3315e-05) (hash(x)=28361254) +4585 train 7.129853 (lr=2.3300e-05) (hash(x)=24828340) +4586 train 6.825090 (lr=2.3284e-05) (hash(x)=24067304) +4587 train 6.625539 (lr=2.3268e-05) (hash(x)=20733289) +4588 train 6.547043 (lr=2.3252e-05) (hash(x)=19526622) +4589 train 6.924108 (lr=2.3237e-05) (hash(x)=22148688) +4590 train 7.122280 (lr=2.3221e-05) (hash(x)=24141800) +4591 train 7.191214 (lr=2.3205e-05) (hash(x)=26663208) +4592 train 6.868971 (lr=2.3190e-05) (hash(x)=22536305) +4593 train 7.090728 (lr=2.3174e-05) (hash(x)=23608185) +4594 train 6.995299 (lr=2.3159e-05) (hash(x)=23348495) +4595 train 7.125406 (lr=2.3143e-05) (hash(x)=25409759) +4596 train 7.111961 (lr=2.3128e-05) (hash(x)=25572131) +4597 train 7.068269 (lr=2.3113e-05) (hash(x)=21782039) +4598 train 7.051559 (lr=2.3097e-05) (hash(x)=24643923) +4599 train 7.016498 (lr=2.3082e-05) (hash(x)=24072213) +4600 val loss 7.1849 +4600 val perplexity 1319.3042 +4600 train 6.940231 (lr=2.3067e-05) (hash(x)=23925612) +4601 train 7.042436 (lr=2.3051e-05) (hash(x)=23315415) +4602 train 7.071935 (lr=2.3036e-05) (hash(x)=21793800) +4603 train 6.990346 (lr=2.3021e-05) (hash(x)=24921200) +4604 train 7.243117 (lr=2.3006e-05) (hash(x)=27226113) +4605 train 7.021726 (lr=2.2991e-05) (hash(x)=22920960) +4606 train 6.990433 (lr=2.2976e-05) (hash(x)=21947750) +4607 train 7.060609 (lr=2.2961e-05) (hash(x)=22766044) +4608 train 7.417503 (lr=2.2946e-05) (hash(x)=28237005) +4609 train 6.899336 (lr=2.2931e-05) (hash(x)=24922621) +4610 train 7.128839 (lr=2.2916e-05) (hash(x)=24899830) +4611 train 7.481157 (lr=2.2901e-05) (hash(x)=32920298) +4612 train 6.967479 (lr=2.2886e-05) (hash(x)=25083835) +4613 train 6.989597 (lr=2.2872e-05) (hash(x)=22863054) +4614 train 7.043130 (lr=2.2857e-05) (hash(x)=24841464) +4615 train 7.317813 (lr=2.2842e-05) (hash(x)=27871153) +4616 train 7.357842 (lr=2.2828e-05) (hash(x)=28025163) +4617 train 6.971533 (lr=2.2813e-05) (hash(x)=24659561) +4618 train 7.058061 (lr=2.2798e-05) (hash(x)=25067194) +4619 train 7.119818 (lr=2.2784e-05) (hash(x)=22731460) +4620 train 7.010822 (lr=2.2769e-05) (hash(x)=20445873) +4621 train 7.116506 (lr=2.2755e-05) (hash(x)=26033948) +4622 train 6.998222 (lr=2.2740e-05) (hash(x)=22473213) +4623 train 7.524568 (lr=2.2726e-05) (hash(x)=24037280) +4624 train 7.986972 (lr=2.2712e-05) (hash(x)=25624131) +4625 train 7.623613 (lr=2.2697e-05) (hash(x)=26799867) +4626 train 7.160593 (lr=2.2683e-05) (hash(x)=27187602) +4627 train 7.097238 (lr=2.2669e-05) (hash(x)=23277695) +4628 train 7.084657 (lr=2.2654e-05) (hash(x)=24748234) +4629 train 7.219583 (lr=2.2640e-05) (hash(x)=26103104) +4630 train 7.135004 (lr=2.2626e-05) (hash(x)=24327389) +4631 train 7.262793 (lr=2.2612e-05) (hash(x)=24121850) +4632 train 7.079595 (lr=2.2598e-05) (hash(x)=23714590) +4633 train 7.138283 (lr=2.2584e-05) (hash(x)=22379412) +4634 train 7.393198 (lr=2.2570e-05) (hash(x)=24454713) +4635 train 7.055833 (lr=2.2556e-05) (hash(x)=22966977) +4636 train 7.022196 (lr=2.2542e-05) (hash(x)=23764884) +4637 train 6.885232 (lr=2.2528e-05) (hash(x)=23827429) +4638 train 7.130010 (lr=2.2514e-05) (hash(x)=24088592) +4639 train 7.075244 (lr=2.2500e-05) (hash(x)=24380031) +4640 train 7.154610 (lr=2.2487e-05) (hash(x)=26065050) +4641 train 7.059305 (lr=2.2473e-05) (hash(x)=24442902) +4642 train 6.678862 (lr=2.2459e-05) (hash(x)=18548782) +4643 train 7.163332 (lr=2.2446e-05) (hash(x)=26957303) +4644 train 7.172003 (lr=2.2432e-05) (hash(x)=25032727) +4645 train 7.021430 (lr=2.2418e-05) (hash(x)=27224706) +4646 train 7.204370 (lr=2.2405e-05) (hash(x)=27508476) +4647 train 6.887258 (lr=2.2391e-05) (hash(x)=23055215) +4648 train 7.041963 (lr=2.2378e-05) (hash(x)=24496194) +4649 train 8.352187 (lr=2.2364e-05) (hash(x)=13982941) +4650 val loss 7.1858 +4650 val perplexity 1320.4968 +4650 train 7.586813 (lr=2.2351e-05) (hash(x)=16721547) +4651 train 7.057560 (lr=2.2338e-05) (hash(x)=22929154) +4652 train 7.012658 (lr=2.2324e-05) (hash(x)=23323994) +4653 train 7.341531 (lr=2.2311e-05) (hash(x)=24877951) +4654 train 7.178485 (lr=2.2298e-05) (hash(x)=24096183) +4655 train 7.024770 (lr=2.2285e-05) (hash(x)=25329724) +4656 train 7.000156 (lr=2.2271e-05) (hash(x)=23877337) +4657 train 6.643065 (lr=2.2258e-05) (hash(x)=20923083) +4658 train 6.937917 (lr=2.2245e-05) (hash(x)=23807996) +4659 train 7.035831 (lr=2.2232e-05) (hash(x)=24370475) +4660 train 7.450079 (lr=2.2219e-05) (hash(x)=28202255) +4661 train 7.178243 (lr=2.2206e-05) (hash(x)=26142119) +4662 train 6.906668 (lr=2.2193e-05) (hash(x)=21387743) +4663 train 7.065880 (lr=2.2180e-05) (hash(x)=25662408) +4664 train 7.101339 (lr=2.2167e-05) (hash(x)=23962815) +4665 train 7.077260 (lr=2.2155e-05) (hash(x)=23987677) +4666 train 7.327695 (lr=2.2142e-05) (hash(x)=26554284) +4667 train 7.387511 (lr=2.2129e-05) (hash(x)=25991817) +4668 train 7.071818 (lr=2.2116e-05) (hash(x)=24256966) +4669 train 6.880023 (lr=2.2104e-05) (hash(x)=22187158) +4670 train 7.138670 (lr=2.2091e-05) (hash(x)=26295320) +4671 train 7.179774 (lr=2.2078e-05) (hash(x)=26346814) +4672 train 7.425903 (lr=2.2066e-05) (hash(x)=26594196) +4673 train 7.192194 (lr=2.2053e-05) (hash(x)=24322101) +4674 train 7.299451 (lr=2.2041e-05) (hash(x)=27274566) +4675 train 7.114841 (lr=2.2028e-05) (hash(x)=24505725) +4676 train 7.262020 (lr=2.2016e-05) (hash(x)=26167371) +4677 train 7.364351 (lr=2.2004e-05) (hash(x)=28062311) +4678 train 7.091917 (lr=2.1991e-05) (hash(x)=23476009) +4679 train 7.197849 (lr=2.1979e-05) (hash(x)=25283256) +4680 train 6.910257 (lr=2.1967e-05) (hash(x)=22033246) +4681 train 6.944988 (lr=2.1954e-05) (hash(x)=22716214) +4682 train 7.075388 (lr=2.1942e-05) (hash(x)=25672672) +4683 train 6.963634 (lr=2.1930e-05) (hash(x)=22979072) +4684 train 7.174874 (lr=2.1918e-05) (hash(x)=27439204) +4685 train 7.101470 (lr=2.1906e-05) (hash(x)=24857737) +4686 train 7.337917 (lr=2.1894e-05) (hash(x)=29615897) +4687 train 6.934627 (lr=2.1882e-05) (hash(x)=24021771) +4688 train 7.071025 (lr=2.1870e-05) (hash(x)=27410807) +4689 train 6.883062 (lr=2.1858e-05) (hash(x)=22850411) +4690 train 7.148168 (lr=2.1846e-05) (hash(x)=24949696) +4691 train 6.969566 (lr=2.1834e-05) (hash(x)=22956381) +4692 train 7.482522 (lr=2.1822e-05) (hash(x)=28193458) +4693 train 7.011936 (lr=2.1811e-05) (hash(x)=25596844) +4694 train 6.988536 (lr=2.1799e-05) (hash(x)=22101377) +4695 train 6.919876 (lr=2.1787e-05) (hash(x)=23576840) +4696 train 6.885336 (lr=2.1776e-05) (hash(x)=21849758) +4697 train 7.067293 (lr=2.1764e-05) (hash(x)=26431349) +4698 train 7.165259 (lr=2.1752e-05) (hash(x)=22960758) +4699 train 7.064293 (lr=2.1741e-05) (hash(x)=23243097) +4700 val loss 7.1821 +4700 val perplexity 1315.7327 +4700 train 7.003926 (lr=2.1729e-05) (hash(x)=23715370) +4701 train 7.646735 (lr=2.1718e-05) (hash(x)=30678293) +4702 train 7.748372 (lr=2.1706e-05) (hash(x)=32481620) +4703 train 7.243442 (lr=2.1695e-05) (hash(x)=26414858) +4704 train 7.166280 (lr=2.1684e-05) (hash(x)=24768691) +4705 train 6.885735 (lr=2.1672e-05) (hash(x)=21627762) +4706 train 6.942288 (lr=2.1661e-05) (hash(x)=21024917) +4707 train 6.848954 (lr=2.1650e-05) (hash(x)=23570951) +4708 train 7.012579 (lr=2.1639e-05) (hash(x)=23729185) +4709 train 7.311171 (lr=2.1627e-05) (hash(x)=25933754) +4710 train 6.849626 (lr=2.1616e-05) (hash(x)=23091014) +4711 train 6.930876 (lr=2.1605e-05) (hash(x)=20099261) +4712 train 7.087629 (lr=2.1594e-05) (hash(x)=26807297) +4713 train 6.992905 (lr=2.1583e-05) (hash(x)=25332115) +4714 train 6.977722 (lr=2.1572e-05) (hash(x)=23247605) +4715 train 6.868339 (lr=2.1561e-05) (hash(x)=23786549) +4716 train 6.925491 (lr=2.1550e-05) (hash(x)=23981166) +4717 train 7.089037 (lr=2.1539e-05) (hash(x)=25967754) +4718 train 6.989516 (lr=2.1529e-05) (hash(x)=23659116) +4719 train 7.023451 (lr=2.1518e-05) (hash(x)=22453718) +4720 train 6.957277 (lr=2.1507e-05) (hash(x)=22597951) +4721 train 7.171411 (lr=2.1496e-05) (hash(x)=25284885) +4722 train 7.139319 (lr=2.1486e-05) (hash(x)=24748569) +4723 train 6.761586 (lr=2.1475e-05) (hash(x)=19448608) +4724 train 7.102503 (lr=2.1464e-05) (hash(x)=24888040) +4725 train 6.940158 (lr=2.1454e-05) (hash(x)=23203503) +4726 train 6.722803 (lr=2.1443e-05) (hash(x)=20387787) +4727 train 6.808057 (lr=2.1433e-05) (hash(x)=22529445) +4728 train 7.115813 (lr=2.1422e-05) (hash(x)=22455471) +4729 train 7.068810 (lr=2.1412e-05) (hash(x)=25661132) +4730 train 7.099374 (lr=2.1402e-05) (hash(x)=24997711) +4731 train 7.166139 (lr=2.1391e-05) (hash(x)=22575521) +4732 train 6.951227 (lr=2.1381e-05) (hash(x)=22640285) +4733 train 6.816297 (lr=2.1371e-05) (hash(x)=18637357) +4734 train 6.956642 (lr=2.1360e-05) (hash(x)=22845826) +4735 train 7.156838 (lr=2.1350e-05) (hash(x)=24484543) +4736 train 7.018613 (lr=2.1340e-05) (hash(x)=23352320) +4737 train 6.831882 (lr=2.1330e-05) (hash(x)=21544758) +4738 train 6.593009 (lr=2.1320e-05) (hash(x)=18292136) +4739 train 7.268739 (lr=2.1310e-05) (hash(x)=24893614) +4740 train 7.109972 (lr=2.1300e-05) (hash(x)=28103443) +4741 train 6.971466 (lr=2.1290e-05) (hash(x)=22233356) +4742 train 6.802197 (lr=2.1280e-05) (hash(x)=21133541) +4743 train 7.056921 (lr=2.1270e-05) (hash(x)=24043998) +4744 train 7.382463 (lr=2.1260e-05) (hash(x)=24801185) +4745 train 7.127889 (lr=2.1251e-05) (hash(x)=23858358) +4746 train 7.177588 (lr=2.1241e-05) (hash(x)=23926989) +4747 train 7.214409 (lr=2.1231e-05) (hash(x)=24813708) +4748 train 7.057260 (lr=2.1221e-05) (hash(x)=26339467) +4749 train 6.900955 (lr=2.1212e-05) (hash(x)=21850656) +4750 val loss 7.1797 +4750 val perplexity 1312.5256 +4750 train 6.885616 (lr=2.1202e-05) (hash(x)=21475802) +4751 train 7.057670 (lr=2.1193e-05) (hash(x)=24301906) +4752 train 6.924135 (lr=2.1183e-05) (hash(x)=22748495) +4753 train 7.085310 (lr=2.1173e-05) (hash(x)=25649256) +4754 train 6.976636 (lr=2.1164e-05) (hash(x)=23934346) +4755 train 7.081356 (lr=2.1155e-05) (hash(x)=26332892) +4756 train 6.958815 (lr=2.1145e-05) (hash(x)=23279389) +4757 train 7.025083 (lr=2.1136e-05) (hash(x)=23146858) +4758 train 7.413725 (lr=2.1127e-05) (hash(x)=26892932) +4759 train 6.916728 (lr=2.1117e-05) (hash(x)=26328881) +4760 train 7.006954 (lr=2.1108e-05) (hash(x)=24394655) +4761 train 7.002112 (lr=2.1099e-05) (hash(x)=22122308) +4762 train 7.161339 (lr=2.1090e-05) (hash(x)=24200369) +4763 train 7.254248 (lr=2.1081e-05) (hash(x)=26841776) +4764 train 7.205525 (lr=2.1071e-05) (hash(x)=27196641) +4765 train 6.955069 (lr=2.1062e-05) (hash(x)=24912822) +4766 train 7.208451 (lr=2.1053e-05) (hash(x)=25946055) +4767 train 6.819355 (lr=2.1044e-05) (hash(x)=23101508) +4768 train 7.030307 (lr=2.1036e-05) (hash(x)=24287798) +4769 train 7.112120 (lr=2.1027e-05) (hash(x)=22798964) +4770 train 6.999860 (lr=2.1018e-05) (hash(x)=24164479) +4771 train 7.067911 (lr=2.1009e-05) (hash(x)=24946464) +4772 train 7.207723 (lr=2.1000e-05) (hash(x)=25154423) +4773 train 6.913033 (lr=2.0991e-05) (hash(x)=23173476) +4774 train 7.130032 (lr=2.0983e-05) (hash(x)=25373559) +4775 train 7.117377 (lr=2.0974e-05) (hash(x)=23527176) +4776 train 7.052147 (lr=2.0965e-05) (hash(x)=24865403) +4777 train 7.023511 (lr=2.0957e-05) (hash(x)=24451067) +4778 train 7.663895 (lr=2.0948e-05) (hash(x)=28187162) +4779 train 7.819566 (lr=2.0940e-05) (hash(x)=31163350) +4780 train 8.104613 (lr=2.0931e-05) (hash(x)=33563280) +4781 train 8.167636 (lr=2.0923e-05) (hash(x)=34939183) +4782 train 7.656459 (lr=2.0915e-05) (hash(x)=30263543) +4783 train 6.963781 (lr=2.0906e-05) (hash(x)=22705673) +4784 train 6.861764 (lr=2.0898e-05) (hash(x)=21415023) +4785 train 7.070283 (lr=2.0890e-05) (hash(x)=26079097) +4786 train 7.406640 (lr=2.0881e-05) (hash(x)=25503836) +4787 train 7.228169 (lr=2.0873e-05) (hash(x)=24705721) +4788 train 7.115834 (lr=2.0865e-05) (hash(x)=24384657) +4789 train 7.011902 (lr=2.0857e-05) (hash(x)=22550579) +4790 train 7.087490 (lr=2.0849e-05) (hash(x)=22452164) +4791 train 7.334400 (lr=2.0841e-05) (hash(x)=28664796) +4792 train 7.710426 (lr=2.0833e-05) (hash(x)=26139280) +4793 train 7.358883 (lr=2.0825e-05) (hash(x)=23862341) +4794 train 6.925079 (lr=2.0817e-05) (hash(x)=23784757) +4795 train 6.809009 (lr=2.0809e-05) (hash(x)=22659441) +4796 train 7.561711 (lr=2.0801e-05) (hash(x)=29744216) +4797 train 7.443286 (lr=2.0793e-05) (hash(x)=25822591) +4798 train 6.885149 (lr=2.0785e-05) (hash(x)=22370895) +4799 train 7.313486 (lr=2.0778e-05) (hash(x)=27102890) +4800 val loss 7.1812 +4800 val perplexity 1314.5179 +4800 train 7.354802 (lr=2.0770e-05) (hash(x)=27014625) +4801 train 7.097950 (lr=2.0762e-05) (hash(x)=25755963) +4802 train 7.338805 (lr=2.0755e-05) (hash(x)=29675278) +4803 train 7.455650 (lr=2.0747e-05) (hash(x)=26660930) +4804 train 7.417732 (lr=2.0740e-05) (hash(x)=24557060) +4805 train 7.543747 (lr=2.0732e-05) (hash(x)=24622741) +4806 train 7.586872 (lr=2.0725e-05) (hash(x)=23952601) +4807 train 7.200788 (lr=2.0717e-05) (hash(x)=26787259) +4808 train 7.479109 (lr=2.0710e-05) (hash(x)=28919605) +4809 train 7.806932 (lr=2.0702e-05) (hash(x)=37061654) +4810 train 7.553264 (lr=2.0695e-05) (hash(x)=30379739) +4811 train 7.304568 (lr=2.0688e-05) (hash(x)=26097180) +4812 train 7.481862 (lr=2.0680e-05) (hash(x)=26327092) +4813 train 7.240657 (lr=2.0673e-05) (hash(x)=23258030) +4814 train 7.279365 (lr=2.0666e-05) (hash(x)=25582015) +4815 train 6.995809 (lr=2.0659e-05) (hash(x)=23396088) +4816 train 6.985825 (lr=2.0652e-05) (hash(x)=21904146) +4817 train 7.176421 (lr=2.0645e-05) (hash(x)=26281676) +4818 train 6.946622 (lr=2.0638e-05) (hash(x)=23140470) +4819 train 7.268281 (lr=2.0631e-05) (hash(x)=24611098) +4820 train 7.061078 (lr=2.0624e-05) (hash(x)=23832642) +4821 train 7.256561 (lr=2.0617e-05) (hash(x)=21439671) +4822 train 7.096204 (lr=2.0610e-05) (hash(x)=25128845) +4823 train 7.039412 (lr=2.0603e-05) (hash(x)=24911831) +4824 train 7.190279 (lr=2.0596e-05) (hash(x)=26051723) +4825 train 7.228469 (lr=2.0590e-05) (hash(x)=26479565) +4826 train 7.320398 (lr=2.0583e-05) (hash(x)=26228987) +4827 train 7.193920 (lr=2.0576e-05) (hash(x)=25131300) +4828 train 6.933907 (lr=2.0570e-05) (hash(x)=19921978) +4829 train 6.908647 (lr=2.0563e-05) (hash(x)=23173449) +4830 train 7.255650 (lr=2.0557e-05) (hash(x)=24791832) +4831 train 6.993684 (lr=2.0550e-05) (hash(x)=23453491) +4832 train 7.144585 (lr=2.0544e-05) (hash(x)=22564139) +4833 train 6.974790 (lr=2.0537e-05) (hash(x)=21659918) +4834 train 7.088885 (lr=2.0531e-05) (hash(x)=22956076) +4835 train 7.230140 (lr=2.0524e-05) (hash(x)=22237612) +4836 train 7.299527 (lr=2.0518e-05) (hash(x)=24736427) +4837 train 7.400281 (lr=2.0512e-05) (hash(x)=24939751) +4838 train 7.217832 (lr=2.0505e-05) (hash(x)=25059298) +4839 train 7.151093 (lr=2.0499e-05) (hash(x)=23453396) +4840 train 6.691467 (lr=2.0493e-05) (hash(x)=17919338) +4841 train 7.171840 (lr=2.0487e-05) (hash(x)=23428815) +4842 train 7.438559 (lr=2.0481e-05) (hash(x)=27042659) +4843 train 7.509245 (lr=2.0475e-05) (hash(x)=25161278) +4844 train 7.287082 (lr=2.0469e-05) (hash(x)=24113253) +4845 train 7.386803 (lr=2.0463e-05) (hash(x)=26139263) +4846 train 7.431026 (lr=2.0457e-05) (hash(x)=27787006) +4847 train 7.188224 (lr=2.0451e-05) (hash(x)=23869612) +4848 train 7.312770 (lr=2.0445e-05) (hash(x)=26092193) +4849 train 7.336316 (lr=2.0439e-05) (hash(x)=29351182) +4850 val loss 7.1697 +4850 val perplexity 1299.4214 +4850 train 7.510982 (lr=2.0433e-05) (hash(x)=28773463) +4851 train 7.425949 (lr=2.0428e-05) (hash(x)=28207741) +4852 train 6.975876 (lr=2.0422e-05) (hash(x)=23280878) +4853 train 7.441068 (lr=2.0416e-05) (hash(x)=26742336) +4854 train 7.201736 (lr=2.0411e-05) (hash(x)=23543321) +4855 train 7.577965 (lr=2.0405e-05) (hash(x)=26581590) +4856 train 7.038960 (lr=2.0399e-05) (hash(x)=22728668) +4857 train 6.876361 (lr=2.0394e-05) (hash(x)=19854534) +4858 train 7.273117 (lr=2.0388e-05) (hash(x)=26612813) +4859 train 7.424461 (lr=2.0383e-05) (hash(x)=25827863) +4860 train 7.121738 (lr=2.0378e-05) (hash(x)=24574997) +4861 train 7.290187 (lr=2.0372e-05) (hash(x)=26187830) +4862 train 7.226498 (lr=2.0367e-05) (hash(x)=25105823) +4863 train 7.294745 (lr=2.0362e-05) (hash(x)=28056342) +4864 train 7.154550 (lr=2.0356e-05) (hash(x)=21885801) +4865 train 7.333161 (lr=2.0351e-05) (hash(x)=25659043) +4866 train 7.327739 (lr=2.0346e-05) (hash(x)=23852824) +4867 train 7.141315 (lr=2.0341e-05) (hash(x)=23965470) +4868 train 7.119688 (lr=2.0336e-05) (hash(x)=25035012) +4869 train 7.323332 (lr=2.0331e-05) (hash(x)=26639165) +4870 train 7.310296 (lr=2.0326e-05) (hash(x)=29205362) +4871 train 7.162385 (lr=2.0321e-05) (hash(x)=25900866) +4872 train 7.201415 (lr=2.0316e-05) (hash(x)=25636242) +4873 train 7.273304 (lr=2.0311e-05) (hash(x)=25430698) +4874 train 7.272259 (lr=2.0306e-05) (hash(x)=27629981) +4875 train 7.231880 (lr=2.0301e-05) (hash(x)=27682625) +4876 train 7.474367 (lr=2.0296e-05) (hash(x)=27549409) +4877 train 7.208325 (lr=2.0291e-05) (hash(x)=24661627) +4878 train 7.265971 (lr=2.0287e-05) (hash(x)=25196542) +4879 train 7.172913 (lr=2.0282e-05) (hash(x)=24549177) +4880 train 7.139752 (lr=2.0277e-05) (hash(x)=23740600) +4881 train 7.017755 (lr=2.0273e-05) (hash(x)=21460850) +4882 train 7.280384 (lr=2.0268e-05) (hash(x)=27101400) +4883 train 7.301811 (lr=2.0264e-05) (hash(x)=24193076) +4884 train 7.213445 (lr=2.0259e-05) (hash(x)=24582947) +4885 train 7.166660 (lr=2.0255e-05) (hash(x)=25133839) +4886 train 7.149189 (lr=2.0250e-05) (hash(x)=24759454) +4887 train 7.222473 (lr=2.0246e-05) (hash(x)=28239583) +4888 train 7.494164 (lr=2.0242e-05) (hash(x)=29594489) +4889 train 7.162682 (lr=2.0237e-05) (hash(x)=23833431) +4890 train 7.137605 (lr=2.0233e-05) (hash(x)=23139411) +4891 train 7.068405 (lr=2.0229e-05) (hash(x)=20885864) +4892 train 7.505539 (lr=2.0225e-05) (hash(x)=26217418) +4893 train 7.304279 (lr=2.0221e-05) (hash(x)=27321870) +4894 train 6.789356 (lr=2.0217e-05) (hash(x)=19912955) +4895 train 7.116394 (lr=2.0212e-05) (hash(x)=23223554) +4896 train 7.277649 (lr=2.0208e-05) (hash(x)=25667219) +4897 train 7.511006 (lr=2.0204e-05) (hash(x)=28007972) +4898 train 7.316491 (lr=2.0200e-05) (hash(x)=27748764) +4899 train 7.280539 (lr=2.0197e-05) (hash(x)=27425770) +4900 val loss 7.1727 +4900 val perplexity 1303.3774 +4900 train 7.380447 (lr=2.0193e-05) (hash(x)=28394020) +4901 train 7.216738 (lr=2.0189e-05) (hash(x)=24080235) +4902 train 7.078114 (lr=2.0185e-05) (hash(x)=23309527) +4903 train 7.087454 (lr=2.0181e-05) (hash(x)=24793480) +4904 train 7.301639 (lr=2.0178e-05) (hash(x)=25344456) +4905 train 7.234035 (lr=2.0174e-05) (hash(x)=24590670) +4906 train 7.219226 (lr=2.0170e-05) (hash(x)=26937171) +4907 train 7.321892 (lr=2.0167e-05) (hash(x)=26949097) +4908 train 7.066412 (lr=2.0163e-05) (hash(x)=22443915) +4909 train 7.138019 (lr=2.0160e-05) (hash(x)=23814995) +4910 train 7.121951 (lr=2.0156e-05) (hash(x)=26135871) +4911 train 6.976404 (lr=2.0153e-05) (hash(x)=25415570) +4912 train 7.266037 (lr=2.0149e-05) (hash(x)=26756326) +4913 train 7.188839 (lr=2.0146e-05) (hash(x)=22920200) +4914 train 7.234983 (lr=2.0143e-05) (hash(x)=26710977) +4915 train 7.130952 (lr=2.0139e-05) (hash(x)=24985634) +4916 train 7.257692 (lr=2.0136e-05) (hash(x)=26004335) +4917 train 7.192899 (lr=2.0133e-05) (hash(x)=25637457) +4918 train 7.400703 (lr=2.0130e-05) (hash(x)=26645180) +4919 train 7.234872 (lr=2.0126e-05) (hash(x)=24425760) +4920 train 7.465454 (lr=2.0123e-05) (hash(x)=28223544) +4921 train 7.184982 (lr=2.0120e-05) (hash(x)=25538618) +4922 train 7.443680 (lr=2.0117e-05) (hash(x)=26984784) +4923 train 7.453673 (lr=2.0114e-05) (hash(x)=29154578) +4924 train 7.153497 (lr=2.0111e-05) (hash(x)=25308123) +4925 train 7.471213 (lr=2.0108e-05) (hash(x)=27939259) +4926 train 7.079865 (lr=2.0106e-05) (hash(x)=21984545) +4927 train 7.115067 (lr=2.0103e-05) (hash(x)=23707134) +4928 train 7.148998 (lr=2.0100e-05) (hash(x)=27201034) +4929 train 7.550052 (lr=2.0097e-05) (hash(x)=31623877) +4930 train 7.161729 (lr=2.0094e-05) (hash(x)=22162782) +4931 train 7.074020 (lr=2.0092e-05) (hash(x)=20049335) +4932 train 7.014408 (lr=2.0089e-05) (hash(x)=25594665) +4933 train 7.115604 (lr=2.0087e-05) (hash(x)=25265312) +4934 train 7.249075 (lr=2.0084e-05) (hash(x)=27094896) +4935 train 7.609612 (lr=2.0081e-05) (hash(x)=28321697) +4936 train 7.124883 (lr=2.0079e-05) (hash(x)=25006013) +4937 train 7.345482 (lr=2.0076e-05) (hash(x)=24596431) +4938 train 7.346678 (lr=2.0074e-05) (hash(x)=25150510) +4939 train 6.884978 (lr=2.0072e-05) (hash(x)=21497535) +4940 train 7.141914 (lr=2.0069e-05) (hash(x)=25094669) +4941 train 7.029649 (lr=2.0067e-05) (hash(x)=24024557) +4942 train 7.325887 (lr=2.0065e-05) (hash(x)=24370776) +4943 train 7.156677 (lr=2.0063e-05) (hash(x)=23434031) +4944 train 7.167377 (lr=2.0060e-05) (hash(x)=24383517) +4945 train 7.184798 (lr=2.0058e-05) (hash(x)=25858759) +4946 train 6.788482 (lr=2.0056e-05) (hash(x)=20409561) +4947 train 7.463493 (lr=2.0054e-05) (hash(x)=27469117) +4948 train 7.011719 (lr=2.0052e-05) (hash(x)=22086623) +4949 train 7.293584 (lr=2.0050e-05) (hash(x)=25759281) +4950 val loss 7.1653 +4950 val perplexity 1293.7816 +4950 train 7.196138 (lr=2.0048e-05) (hash(x)=27130117) +4951 train 7.092119 (lr=2.0046e-05) (hash(x)=27003481) +4952 train 7.403160 (lr=2.0044e-05) (hash(x)=26725937) +4953 train 7.168622 (lr=2.0043e-05) (hash(x)=22691119) +4954 train 7.202170 (lr=2.0041e-05) (hash(x)=17272898) +4955 train 7.026727 (lr=2.0039e-05) (hash(x)=17850370) +4956 train 7.037735 (lr=2.0037e-05) (hash(x)=18729639) +4957 train 7.206552 (lr=2.0036e-05) (hash(x)=25327160) +4958 train 7.359796 (lr=2.0034e-05) (hash(x)=28709044) +4959 train 6.930516 (lr=2.0032e-05) (hash(x)=22236893) +4960 train 6.917877 (lr=2.0031e-05) (hash(x)=21729251) +4961 train 7.022790 (lr=2.0029e-05) (hash(x)=23852346) +4962 train 7.208749 (lr=2.0028e-05) (hash(x)=23974368) +4963 train 7.162122 (lr=2.0026e-05) (hash(x)=25764691) +4964 train 7.538887 (lr=2.0025e-05) (hash(x)=28341865) +4965 train 7.045729 (lr=2.0024e-05) (hash(x)=23856238) +4966 train 7.277025 (lr=2.0022e-05) (hash(x)=24568904) +4967 train 7.171502 (lr=2.0021e-05) (hash(x)=26857458) +4968 train 7.031163 (lr=2.0020e-05) (hash(x)=20507972) +4969 train 7.203365 (lr=2.0019e-05) (hash(x)=23139455) +4970 train 7.069604 (lr=2.0017e-05) (hash(x)=24853703) +4971 train 7.095981 (lr=2.0016e-05) (hash(x)=25654849) +4972 train 6.974890 (lr=2.0015e-05) (hash(x)=22963710) +4973 train 7.340427 (lr=2.0014e-05) (hash(x)=25652110) +4974 train 7.272401 (lr=2.0013e-05) (hash(x)=24085957) +4975 train 7.490669 (lr=2.0012e-05) (hash(x)=26413122) +4976 train 7.589636 (lr=2.0011e-05) (hash(x)=26989387) +4977 train 7.260764 (lr=2.0010e-05) (hash(x)=22784033) +4978 train 7.635446 (lr=2.0009e-05) (hash(x)=26694945) +4979 train 7.565202 (lr=2.0009e-05) (hash(x)=24507726) +4980 train 7.620510 (lr=2.0008e-05) (hash(x)=26490335) +4981 train 7.537901 (lr=2.0007e-05) (hash(x)=25624751) +4982 train 7.502252 (lr=2.0006e-05) (hash(x)=27846204) +4983 train 7.369618 (lr=2.0006e-05) (hash(x)=27696537) +4984 train 7.257073 (lr=2.0005e-05) (hash(x)=28915842) +4985 train 7.324794 (lr=2.0004e-05) (hash(x)=28274576) +4986 train 7.368111 (lr=2.0004e-05) (hash(x)=28923892) +4987 train 6.973714 (lr=2.0003e-05) (hash(x)=21602520) +4988 train 6.918670 (lr=2.0003e-05) (hash(x)=21061011) +4989 train 7.406343 (lr=2.0002e-05) (hash(x)=28060542) +4990 train 7.185988 (lr=2.0002e-05) (hash(x)=24838134) +4991 train 7.134887 (lr=2.0002e-05) (hash(x)=21950234) +4992 train 7.383577 (lr=2.0001e-05) (hash(x)=27192740) +4993 train 7.352265 (lr=2.0001e-05) (hash(x)=26770105) +4994 train 7.044887 (lr=2.0001e-05) (hash(x)=23721261) +4995 train 7.090764 (lr=2.0000e-05) (hash(x)=26064895) +4996 train 7.313068 (lr=2.0000e-05) (hash(x)=25651075) +4997 train 7.142006 (lr=2.0000e-05) (hash(x)=25029447) +4998 train 7.307744 (lr=2.0000e-05) (hash(x)=26088225) +4999 val loss 7.1677 +4999 val perplexity 1296.8378 +4999 train 7.218375 (lr=2.0000e-05) (hash(x)=24051952) diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/model_02500.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/model_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..5f5e38894ef49f47134511e2cbc7b13b498c6b14 --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/model_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66613c7cb65687baf8e2dc5587839cada7febc2d84180e40269138c40e99841a +size 38587970 diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/model_04999.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/model_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..9ca273037214b24f90b81f5719cb120fc1ee406e --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/model_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8580398b3e26fcf117c7100cf0863df8c6748f6b0eb5462d6b384815aa09ea5a +size 38587970 diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/optimizer_02500.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/optimizer_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..4fe51c4fadbbe37181cb5501c695c72ff05cc6c3 --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/optimizer_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f4ff0784f403dec2f213f4c40961d6b2b06068aa6f81c520ebca66144e072e6 +size 70895430 diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/optimizer_04999.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/optimizer_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..cf982015ae66e12c359919559a91bc993c0eb13f --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1338/optimizer_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76567e797e763adc3b8886de19098e1ece0a0a48f80bd059489024f7703b879d +size 70895430