diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/args.json b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/args.json new file mode 100644 index 0000000000000000000000000000000000000000..1c9508cd54f5d8a60cd2956c856be33dc90258f8 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/args.json @@ -0,0 +1 @@ +{"hellaswag": true, "attention_kind": "selective", "log_dir": "proxy_model_sweep_2/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_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": 0.000175, "decay_lr": false, "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/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/dataloader_02500.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/dataloader_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bc253f8fc6225637fb651d7b45bcde02b1c9ff0 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_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/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/dataloader_04999.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/dataloader_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..0618c479f1dc6588bdd52311cf3417cbd843ddd9 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_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/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/log2.txt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/log2.txt new file mode 100644 index 0000000000000000000000000000000000000000..e3891a51da1d3b8702bfdf644cbaa9c13cffff56 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_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=1.7500e-04) (hash(x)=22886834) +1 train 11.438657 (lr=1.7500e-04) (hash(x)=26375038) +2 train 11.131435 (lr=1.7500e-04) (hash(x)=30598777) +3 train 10.899445 (lr=1.7500e-04) (hash(x)=27234506) +4 train 10.695560 (lr=1.7500e-04) (hash(x)=27767880) +5 train 10.498874 (lr=1.7500e-04) (hash(x)=23702020) +6 train 10.487622 (lr=1.7500e-04) (hash(x)=31986844) +7 train 10.401377 (lr=1.7500e-04) (hash(x)=20782690) +8 train 10.312495 (lr=1.7500e-04) (hash(x)=25201599) +9 train 10.209208 (lr=1.7500e-04) (hash(x)=23094976) +10 train 10.176543 (lr=1.7500e-04) (hash(x)=23841096) +11 train 10.134315 (lr=1.7500e-04) (hash(x)=26532095) +12 train 10.080805 (lr=1.7500e-04) (hash(x)=24432298) +13 train 10.075252 (lr=1.7500e-04) (hash(x)=27151649) +14 train 10.013532 (lr=1.7500e-04) (hash(x)=24596846) +15 train 9.814422 (lr=1.7500e-04) (hash(x)=23890908) +16 train 9.780612 (lr=1.7500e-04) (hash(x)=28913955) +17 train 9.616980 (lr=1.7500e-04) (hash(x)=25588236) +18 train 9.673217 (lr=1.7500e-04) (hash(x)=23770034) +19 train 9.580324 (lr=1.7500e-04) (hash(x)=24011372) +20 train 9.400761 (lr=1.7500e-04) (hash(x)=25441898) +21 train 9.594710 (lr=1.7500e-04) (hash(x)=28375581) +22 train 9.281930 (lr=1.7500e-04) (hash(x)=24046679) +23 train 9.343066 (lr=1.7500e-04) (hash(x)=24611628) +24 train 9.323499 (lr=1.7500e-04) (hash(x)=26169030) +25 train 9.364222 (lr=1.7500e-04) (hash(x)=30298407) +26 train 9.127505 (lr=1.7500e-04) (hash(x)=23711112) +27 train 8.946565 (lr=1.7500e-04) (hash(x)=19245352) +28 train 8.941485 (lr=1.7500e-04) (hash(x)=21529136) +29 train 9.193770 (lr=1.7500e-04) (hash(x)=28936608) +30 train 8.777985 (lr=1.7500e-04) (hash(x)=24339013) +31 train 8.674335 (lr=1.7500e-04) (hash(x)=25767553) +32 train 8.779285 (lr=1.7500e-04) (hash(x)=26439905) +33 train 8.977733 (lr=1.7500e-04) (hash(x)=31093473) +34 train 8.572394 (lr=1.7500e-04) (hash(x)=25450374) +35 train 8.491959 (lr=1.7500e-04) (hash(x)=24809873) +36 train 8.626732 (lr=1.7500e-04) (hash(x)=23253252) +37 train 8.641044 (lr=1.7500e-04) (hash(x)=27852919) +38 train 8.492340 (lr=1.7500e-04) (hash(x)=23327497) +39 train 8.250819 (lr=1.7500e-04) (hash(x)=22512166) +40 train 8.509337 (lr=1.7500e-04) (hash(x)=22859419) +41 train 8.354020 (lr=1.7500e-04) (hash(x)=27620338) +42 train 8.417735 (lr=1.7500e-04) (hash(x)=26397837) +43 train 8.421283 (lr=1.7500e-04) (hash(x)=28092148) +44 train 8.250587 (lr=1.7500e-04) (hash(x)=24662703) +45 train 8.539096 (lr=1.7500e-04) (hash(x)=27938767) +46 train 8.666382 (lr=1.7500e-04) (hash(x)=26037988) +47 train 8.179105 (lr=1.7500e-04) (hash(x)=24732833) +48 train 8.261588 (lr=1.7500e-04) (hash(x)=25259526) +49 train 8.157195 (lr=1.7500e-04) (hash(x)=23200230) +50 val loss 8.1432 +50 val perplexity 3440.0193 +50 train 8.144030 (lr=1.7500e-04) (hash(x)=26721357) +51 train 7.990486 (lr=1.7500e-04) (hash(x)=22694718) +52 train 8.088084 (lr=1.7500e-04) (hash(x)=28066766) +53 train 8.022803 (lr=1.7500e-04) (hash(x)=23125151) +54 train 8.178612 (lr=1.7500e-04) (hash(x)=27193725) +55 train 7.971381 (lr=1.7500e-04) (hash(x)=25129410) +56 train 8.019337 (lr=1.7500e-04) (hash(x)=24263988) +57 train 7.850258 (lr=1.7500e-04) (hash(x)=23059154) +58 train 8.095183 (lr=1.7500e-04) (hash(x)=26063864) +59 train 8.309279 (lr=1.7500e-04) (hash(x)=27858570) +60 train 8.035121 (lr=1.7500e-04) (hash(x)=23874620) +61 train 7.852620 (lr=1.7500e-04) (hash(x)=22402617) +62 train 8.038846 (lr=1.7500e-04) (hash(x)=23600822) +63 train 7.868278 (lr=1.7500e-04) (hash(x)=26582391) +64 train 7.883435 (lr=1.7500e-04) (hash(x)=23225283) +65 train 8.242476 (lr=1.7500e-04) (hash(x)=26075451) +66 train 7.862293 (lr=1.7500e-04) (hash(x)=24723419) +67 train 8.044637 (lr=1.7500e-04) (hash(x)=27279806) +68 train 7.832440 (lr=1.7500e-04) (hash(x)=25870391) +69 train 8.067554 (lr=1.7500e-04) (hash(x)=26188136) +70 train 8.217994 (lr=1.7500e-04) (hash(x)=30373443) +71 train 8.117801 (lr=1.7500e-04) (hash(x)=26472336) +72 train 7.864967 (lr=1.7500e-04) (hash(x)=26651572) +73 train 8.003784 (lr=1.7500e-04) (hash(x)=26376212) +74 train 7.955095 (lr=1.7500e-04) (hash(x)=26733350) +75 train 8.113802 (lr=1.7500e-04) (hash(x)=28301589) +76 train 7.994565 (lr=1.7500e-04) (hash(x)=27599559) +77 train 7.988376 (lr=1.7500e-04) (hash(x)=28035221) +78 train 7.971046 (lr=1.7500e-04) (hash(x)=25016783) +79 train 8.058937 (lr=1.7500e-04) (hash(x)=27654289) +80 train 7.865784 (lr=1.7500e-04) (hash(x)=24597558) +81 train 7.677351 (lr=1.7500e-04) (hash(x)=21560904) +82 train 7.644996 (lr=1.7500e-04) (hash(x)=21983837) +83 train 7.846513 (lr=1.7500e-04) (hash(x)=24995715) +84 train 8.139854 (lr=1.7500e-04) (hash(x)=29876413) +85 train 7.756092 (lr=1.7500e-04) (hash(x)=23792508) +86 train 7.698886 (lr=1.7500e-04) (hash(x)=25509120) +87 train 7.955008 (lr=1.7500e-04) (hash(x)=26559876) +88 train 7.867876 (lr=1.7500e-04) (hash(x)=23569647) +89 train 7.909126 (lr=1.7500e-04) (hash(x)=25758852) +90 train 7.753784 (lr=1.7500e-04) (hash(x)=25706298) +91 train 7.900676 (lr=1.7500e-04) (hash(x)=28364895) +92 train 7.723280 (lr=1.7500e-04) (hash(x)=25304663) +93 train 7.829349 (lr=1.7500e-04) (hash(x)=25269299) +94 train 7.971723 (lr=1.7500e-04) (hash(x)=25870566) +95 train 7.566688 (lr=1.7500e-04) (hash(x)=21770329) +96 train 7.989757 (lr=1.7500e-04) (hash(x)=27595900) +97 train 7.968624 (lr=1.7500e-04) (hash(x)=24785397) +98 train 7.695737 (lr=1.7500e-04) (hash(x)=21521480) +99 train 7.787567 (lr=1.7500e-04) (hash(x)=24628606) +100 val loss 7.8317 +100 val perplexity 2519.0854 +100 train 7.928006 (lr=1.7500e-04) (hash(x)=24670150) +101 train 7.782314 (lr=1.7500e-04) (hash(x)=23181910) +102 train 7.734092 (lr=1.7500e-04) (hash(x)=22714991) +103 train 7.699625 (lr=1.7500e-04) (hash(x)=22723459) +104 train 7.696117 (lr=1.7500e-04) (hash(x)=21524316) +105 train 7.830771 (lr=1.7500e-04) (hash(x)=25506632) +106 train 7.575151 (lr=1.7500e-04) (hash(x)=21675672) +107 train 7.668791 (lr=1.7500e-04) (hash(x)=22897919) +108 train 7.684322 (lr=1.7500e-04) (hash(x)=23321631) +109 train 7.869033 (lr=1.7500e-04) (hash(x)=26546719) +110 train 8.940417 (lr=1.7500e-04) (hash(x)=31962348) +111 train 8.183363 (lr=1.7500e-04) (hash(x)=30338342) +112 train 7.785414 (lr=1.7500e-04) (hash(x)=23724471) +113 train 7.978699 (lr=1.7500e-04) (hash(x)=29175888) +114 train 7.993761 (lr=1.7500e-04) (hash(x)=23256716) +115 train 8.041042 (lr=1.7500e-04) (hash(x)=27063280) +116 train 8.034426 (lr=1.7500e-04) (hash(x)=31057659) +117 train 8.233340 (lr=1.7500e-04) (hash(x)=32915097) +118 train 8.091090 (lr=1.7500e-04) (hash(x)=28842717) +119 train 7.773098 (lr=1.7500e-04) (hash(x)=25678059) +120 train 7.627959 (lr=1.7500e-04) (hash(x)=21593510) +121 train 7.543648 (lr=1.7500e-04) (hash(x)=20083773) +122 train 7.732242 (lr=1.7500e-04) (hash(x)=23002820) +123 train 7.561595 (lr=1.7500e-04) (hash(x)=21853028) +124 train 7.821899 (lr=1.7500e-04) (hash(x)=26985625) +125 train 7.595954 (lr=1.7500e-04) (hash(x)=21808483) +126 train 7.979661 (lr=1.7500e-04) (hash(x)=28873251) +127 train 7.827313 (lr=1.7500e-04) (hash(x)=26109335) +128 train 8.032761 (lr=1.7500e-04) (hash(x)=26334674) +129 train 7.887378 (lr=1.7500e-04) (hash(x)=24916754) +130 train 7.851775 (lr=1.7500e-04) (hash(x)=25449624) +131 train 7.921094 (lr=1.7500e-04) (hash(x)=25334848) +132 train 8.230448 (lr=1.7500e-04) (hash(x)=27484863) +133 train 7.752721 (lr=1.7500e-04) (hash(x)=24917705) +134 train 7.694534 (lr=1.7500e-04) (hash(x)=25143449) +135 train 7.716515 (lr=1.7500e-04) (hash(x)=25044885) +136 train 7.928343 (lr=1.7500e-04) (hash(x)=27821028) +137 train 7.923706 (lr=1.7500e-04) (hash(x)=28747022) +138 train 7.866109 (lr=1.7500e-04) (hash(x)=27182888) +139 train 7.694700 (lr=1.7500e-04) (hash(x)=23678349) +140 train 7.850122 (lr=1.7500e-04) (hash(x)=23593235) +141 train 8.139519 (lr=1.7500e-04) (hash(x)=28529813) +142 train 8.428243 (lr=1.7500e-04) (hash(x)=32074661) +143 train 7.999008 (lr=1.7500e-04) (hash(x)=28870690) +144 train 7.994239 (lr=1.7500e-04) (hash(x)=27307705) +145 train 7.792098 (lr=1.7500e-04) (hash(x)=25044834) +146 train 7.823706 (lr=1.7500e-04) (hash(x)=23712023) +147 train 8.347925 (lr=1.7500e-04) (hash(x)=32982615) +148 train 8.121585 (lr=1.7500e-04) (hash(x)=30113660) +149 train 7.539787 (lr=1.7500e-04) (hash(x)=20970960) +150 val loss 7.7907 +150 val perplexity 2418.0278 +150 train 7.773352 (lr=1.7500e-04) (hash(x)=23132684) +151 train 9.440396 (lr=1.7500e-04) (hash(x)=35279941) +152 train 8.623078 (lr=1.7500e-04) (hash(x)=31227444) +153 train 7.745935 (lr=1.7500e-04) (hash(x)=25529472) +154 train 7.839719 (lr=1.7500e-04) (hash(x)=24350409) +155 train 8.149384 (lr=1.7500e-04) (hash(x)=26400041) +156 train 7.838608 (lr=1.7500e-04) (hash(x)=25262621) +157 train 7.847729 (lr=1.7500e-04) (hash(x)=24656138) +158 train 8.048400 (lr=1.7500e-04) (hash(x)=26803414) +159 train 7.919828 (lr=1.7500e-04) (hash(x)=25015923) +160 train 7.653201 (lr=1.7500e-04) (hash(x)=23581172) +161 train 7.759311 (lr=1.7500e-04) (hash(x)=22924885) +162 train 7.698564 (lr=1.7500e-04) (hash(x)=23414296) +163 train 7.904178 (lr=1.7500e-04) (hash(x)=24853586) +164 train 7.932958 (lr=1.7500e-04) (hash(x)=25000130) +165 train 7.833237 (lr=1.7500e-04) (hash(x)=27004780) +166 train 7.824583 (lr=1.7500e-04) (hash(x)=26148573) +167 train 7.776357 (lr=1.7500e-04) (hash(x)=26740855) +168 train 7.464161 (lr=1.7500e-04) (hash(x)=20965419) +169 train 7.746208 (lr=1.7500e-04) (hash(x)=23950114) +170 train 7.676836 (lr=1.7500e-04) (hash(x)=24951982) +171 train 7.770525 (lr=1.7500e-04) (hash(x)=24584116) +172 train 7.754990 (lr=1.7500e-04) (hash(x)=24378759) +173 train 7.744492 (lr=1.7500e-04) (hash(x)=25718516) +174 train 7.896007 (lr=1.7500e-04) (hash(x)=28424396) +175 train 7.670802 (lr=1.7500e-04) (hash(x)=22262151) +176 train 7.915946 (lr=1.7500e-04) (hash(x)=26438412) +177 train 7.677313 (lr=1.7500e-04) (hash(x)=23025303) +178 train 7.728299 (lr=1.7500e-04) (hash(x)=24190770) +179 train 7.925468 (lr=1.7500e-04) (hash(x)=26627860) +180 train 7.664577 (lr=1.7500e-04) (hash(x)=23663439) +181 train 7.527199 (lr=1.7500e-04) (hash(x)=23700532) +182 train 7.593624 (lr=1.7500e-04) (hash(x)=23075676) +183 train 7.842966 (lr=1.7500e-04) (hash(x)=26621834) +184 train 7.915450 (lr=1.7500e-04) (hash(x)=29426269) +185 train 7.553637 (lr=1.7500e-04) (hash(x)=21821465) +186 train 7.820289 (lr=1.7500e-04) (hash(x)=26506130) +187 train 8.054316 (lr=1.7500e-04) (hash(x)=26930630) +188 train 7.590949 (lr=1.7500e-04) (hash(x)=22993793) +189 train 7.470193 (lr=1.7500e-04) (hash(x)=19557946) +190 train 7.775523 (lr=1.7500e-04) (hash(x)=23572891) +191 train 7.596311 (lr=1.7500e-04) (hash(x)=23234741) +192 train 7.680486 (lr=1.7500e-04) (hash(x)=25547951) +193 train 7.818685 (lr=1.7500e-04) (hash(x)=26713563) +194 train 7.798271 (lr=1.7500e-04) (hash(x)=25913622) +195 train 8.046654 (lr=1.7500e-04) (hash(x)=28102443) +196 train 7.688838 (lr=1.7500e-04) (hash(x)=23093351) +197 train 8.467936 (lr=1.7500e-04) (hash(x)=31689122) +198 train 8.322802 (lr=1.7500e-04) (hash(x)=32252517) +199 train 7.903287 (lr=1.7500e-04) (hash(x)=25470563) +200 val loss 7.8294 +200 val perplexity 2513.5073 +200 train 7.934207 (lr=1.7500e-04) (hash(x)=25597614) +201 train 7.975775 (lr=1.7500e-04) (hash(x)=23757479) +202 train 7.794866 (lr=1.7500e-04) (hash(x)=25140048) +203 train 7.966060 (lr=1.7500e-04) (hash(x)=28282861) +204 train 7.718349 (lr=1.7500e-04) (hash(x)=24754885) +205 train 7.936359 (lr=1.7500e-04) (hash(x)=26731964) +206 train 8.035736 (lr=1.7500e-04) (hash(x)=26660561) +207 train 7.586549 (lr=1.7500e-04) (hash(x)=21799102) +208 train 7.829596 (lr=1.7500e-04) (hash(x)=27025986) +209 train 7.634454 (lr=1.7500e-04) (hash(x)=24672077) +210 train 7.730892 (lr=1.7500e-04) (hash(x)=25322984) +211 train 7.603758 (lr=1.7500e-04) (hash(x)=23471769) +212 train 7.455452 (lr=1.7500e-04) (hash(x)=20766491) +213 train 7.959914 (lr=1.7500e-04) (hash(x)=24058931) +214 train 7.630742 (lr=1.7500e-04) (hash(x)=23872843) +215 train 7.663181 (lr=1.7500e-04) (hash(x)=23275479) +216 train 7.773954 (lr=1.7500e-04) (hash(x)=24914695) +217 train 7.687154 (lr=1.7500e-04) (hash(x)=24364396) +218 train 7.919526 (lr=1.7500e-04) (hash(x)=27986474) +219 train 7.799002 (lr=1.7500e-04) (hash(x)=24473581) +220 train 7.730327 (lr=1.7500e-04) (hash(x)=22974689) +221 train 7.831924 (lr=1.7500e-04) (hash(x)=23774644) +222 train 7.768398 (lr=1.7500e-04) (hash(x)=23245327) +223 train 7.564250 (lr=1.7500e-04) (hash(x)=22091862) +224 train 7.643857 (lr=1.7500e-04) (hash(x)=24362839) +225 train 7.777779 (lr=1.7500e-04) (hash(x)=25482303) +226 train 7.848486 (lr=1.7500e-04) (hash(x)=24911853) +227 train 7.837917 (lr=1.7500e-04) (hash(x)=26018202) +228 train 7.696597 (lr=1.7500e-04) (hash(x)=26124495) +229 train 7.809100 (lr=1.7500e-04) (hash(x)=24560096) +230 train 7.768075 (lr=1.7500e-04) (hash(x)=24695331) +231 train 7.470445 (lr=1.7500e-04) (hash(x)=17430373) +232 train 7.525671 (lr=1.7500e-04) (hash(x)=21813345) +233 train 7.166393 (lr=1.7500e-04) (hash(x)=20098681) +234 train 7.534229 (lr=1.7500e-04) (hash(x)=25095928) +235 train 7.651612 (lr=1.7500e-04) (hash(x)=24078083) +236 train 7.661241 (lr=1.7500e-04) (hash(x)=22901505) +237 train 7.845979 (lr=1.7500e-04) (hash(x)=26595592) +238 train 7.737448 (lr=1.7500e-04) (hash(x)=27663196) +239 train 7.555188 (lr=1.7500e-04) (hash(x)=22954861) +240 train 7.974580 (lr=1.7500e-04) (hash(x)=30159234) +241 train 7.899693 (lr=1.7500e-04) (hash(x)=29294271) +242 train 7.891706 (lr=1.7500e-04) (hash(x)=23728322) +243 train 7.943883 (lr=1.7500e-04) (hash(x)=28695016) +244 train 8.041283 (lr=1.7500e-04) (hash(x)=26702728) +245 train 7.832955 (lr=1.7500e-04) (hash(x)=27100115) +246 train 7.721700 (lr=1.7500e-04) (hash(x)=25082752) +247 train 8.060918 (lr=1.7500e-04) (hash(x)=26671799) +248 train 7.723947 (lr=1.7500e-04) (hash(x)=23718946) +249 train 7.988888 (lr=1.7500e-04) (hash(x)=28137394) +250 val loss 7.7499 +250 val perplexity 2321.3677 +250 train 8.017415 (lr=1.7500e-04) (hash(x)=23893495) +251 train 7.794983 (lr=1.7500e-04) (hash(x)=23166092) +252 train 7.789194 (lr=1.7500e-04) (hash(x)=25907665) +253 train 7.753384 (lr=1.7500e-04) (hash(x)=25885986) +254 train 7.759634 (lr=1.7500e-04) (hash(x)=25262712) +255 train 7.731319 (lr=1.7500e-04) (hash(x)=26924723) +256 train 7.924765 (lr=1.7500e-04) (hash(x)=28744736) +257 train 7.659690 (lr=1.7500e-04) (hash(x)=26140590) +258 train 7.906934 (lr=1.7500e-04) (hash(x)=25780449) +259 train 7.706060 (lr=1.7500e-04) (hash(x)=25138659) +260 train 8.030612 (lr=1.7500e-04) (hash(x)=27244046) +261 train 7.872598 (lr=1.7500e-04) (hash(x)=27224685) +262 train 8.175685 (lr=1.7500e-04) (hash(x)=28274477) +263 train 7.654994 (lr=1.7500e-04) (hash(x)=23557495) +264 train 7.766099 (lr=1.7500e-04) (hash(x)=24680596) +265 train 7.752776 (lr=1.7500e-04) (hash(x)=23928957) +266 train 7.740359 (lr=1.7500e-04) (hash(x)=23761390) +267 train 7.661170 (lr=1.7500e-04) (hash(x)=25288123) +268 train 7.910993 (lr=1.7500e-04) (hash(x)=28705502) +269 train 7.485695 (lr=1.7500e-04) (hash(x)=23246294) +270 train 7.581639 (lr=1.7500e-04) (hash(x)=28639079) +271 train 7.500743 (lr=1.7500e-04) (hash(x)=27804380) +272 train 7.689220 (lr=1.7500e-04) (hash(x)=24172235) +273 train 7.767731 (lr=1.7500e-04) (hash(x)=23089140) +274 train 7.998631 (lr=1.7500e-04) (hash(x)=27163701) +275 train 8.114120 (lr=1.7500e-04) (hash(x)=26993263) +276 train 7.814619 (lr=1.7500e-04) (hash(x)=28224233) +277 train 8.118417 (lr=1.7500e-04) (hash(x)=27397203) +278 train 8.040538 (lr=1.7500e-04) (hash(x)=27923882) +279 train 7.839324 (lr=1.7500e-04) (hash(x)=26654908) +280 train 7.790277 (lr=1.7500e-04) (hash(x)=24213147) +281 train 7.514646 (lr=1.7500e-04) (hash(x)=21965022) +282 train 7.665895 (lr=1.7500e-04) (hash(x)=25465685) +283 train 7.873930 (lr=1.7500e-04) (hash(x)=27347722) +284 train 7.893485 (lr=1.7500e-04) (hash(x)=26732050) +285 train 8.077847 (lr=1.7500e-04) (hash(x)=28314127) +286 train 7.595760 (lr=1.7500e-04) (hash(x)=21471186) +287 train 7.523557 (lr=1.7500e-04) (hash(x)=23627518) +288 train 7.503188 (lr=1.7500e-04) (hash(x)=20870353) +289 train 7.612928 (lr=1.7500e-04) (hash(x)=25024764) +290 train 7.404242 (lr=1.7500e-04) (hash(x)=20683822) +291 train 7.733342 (lr=1.7500e-04) (hash(x)=21768671) +292 train 7.752327 (lr=1.7500e-04) (hash(x)=25557309) +293 train 7.949010 (lr=1.7500e-04) (hash(x)=25076667) +294 train 7.543361 (lr=1.7500e-04) (hash(x)=23765822) +295 train 7.545772 (lr=1.7500e-04) (hash(x)=21889990) +296 train 7.739967 (lr=1.7500e-04) (hash(x)=26339893) +297 train 7.437201 (lr=1.7500e-04) (hash(x)=20932794) +298 train 7.589685 (lr=1.7500e-04) (hash(x)=21750070) +299 train 7.782233 (lr=1.7500e-04) (hash(x)=23665838) +300 val loss 7.6912 +300 val perplexity 2189.0703 +300 train 8.564423 (lr=1.7500e-04) (hash(x)=32888061) +301 train 8.320685 (lr=1.7500e-04) (hash(x)=30223582) +302 train 8.003197 (lr=1.7500e-04) (hash(x)=26908418) +303 train 7.367591 (lr=1.7500e-04) (hash(x)=22528001) +304 train 7.882259 (lr=1.7500e-04) (hash(x)=27452187) +305 train 7.681857 (lr=1.7500e-04) (hash(x)=25181641) +306 train 7.779396 (lr=1.7500e-04) (hash(x)=25546593) +307 train 7.788107 (lr=1.7500e-04) (hash(x)=22487328) +308 train 7.973370 (lr=1.7500e-04) (hash(x)=27804274) +309 train 8.065065 (lr=1.7500e-04) (hash(x)=26544630) +310 train 8.202147 (lr=1.7500e-04) (hash(x)=27738934) +311 train 7.981194 (lr=1.7500e-04) (hash(x)=29248942) +312 train 7.710306 (lr=1.7500e-04) (hash(x)=25103452) +313 train 7.936716 (lr=1.7500e-04) (hash(x)=25052066) +314 train 7.721901 (lr=1.7500e-04) (hash(x)=24481302) +315 train 7.668897 (lr=1.7500e-04) (hash(x)=23543273) +316 train 7.659052 (lr=1.7500e-04) (hash(x)=25608244) +317 train 7.857862 (lr=1.7500e-04) (hash(x)=27451288) +318 train 7.488448 (lr=1.7500e-04) (hash(x)=22806491) +319 train 7.691651 (lr=1.7500e-04) (hash(x)=25533417) +320 train 7.709927 (lr=1.7500e-04) (hash(x)=24557997) +321 train 7.754875 (lr=1.7500e-04) (hash(x)=24432899) +322 train 8.022148 (lr=1.7500e-04) (hash(x)=27583287) +323 train 7.965763 (lr=1.7500e-04) (hash(x)=25552036) +324 train 7.631402 (lr=1.7500e-04) (hash(x)=24201868) +325 train 7.912906 (lr=1.7500e-04) (hash(x)=28149782) +326 train 7.698009 (lr=1.7500e-04) (hash(x)=25529698) +327 train 7.380179 (lr=1.7500e-04) (hash(x)=20612533) +328 train 7.427994 (lr=1.7500e-04) (hash(x)=20699000) +329 train 7.371751 (lr=1.7500e-04) (hash(x)=19774173) +330 train 7.389762 (lr=1.7500e-04) (hash(x)=21681646) +331 train 7.264192 (lr=1.7500e-04) (hash(x)=20216795) +332 train 8.040679 (lr=1.7500e-04) (hash(x)=27697998) +333 train 7.738324 (lr=1.7500e-04) (hash(x)=25896435) +334 train 7.610509 (lr=1.7500e-04) (hash(x)=21585310) +335 train 7.664408 (lr=1.7500e-04) (hash(x)=24677740) +336 train 7.494582 (lr=1.7500e-04) (hash(x)=22027900) +337 train 7.523190 (lr=1.7500e-04) (hash(x)=21835643) +338 train 7.401670 (lr=1.7500e-04) (hash(x)=20558462) +339 train 7.275144 (lr=1.7500e-04) (hash(x)=16722715) +340 train 7.456529 (lr=1.7500e-04) (hash(x)=20972655) +341 train 7.944235 (lr=1.7500e-04) (hash(x)=26303975) +342 train 7.661376 (lr=1.7500e-04) (hash(x)=22938170) +343 train 7.749018 (lr=1.7500e-04) (hash(x)=25347203) +344 train 7.680887 (lr=1.7500e-04) (hash(x)=27398686) +345 train 7.690006 (lr=1.7500e-04) (hash(x)=25973417) +346 train 7.742685 (lr=1.7500e-04) (hash(x)=26918389) +347 train 7.688956 (lr=1.7500e-04) (hash(x)=24272489) +348 train 7.795392 (lr=1.7500e-04) (hash(x)=25593714) +349 train 7.786388 (lr=1.7500e-04) (hash(x)=29260846) +350 val loss 7.7096 +350 val perplexity 2229.5396 +350 train 7.814900 (lr=1.7500e-04) (hash(x)=27951602) +351 train 7.929196 (lr=1.7500e-04) (hash(x)=28922363) +352 train 7.802583 (lr=1.7500e-04) (hash(x)=27210734) +353 train 7.869865 (lr=1.7500e-04) (hash(x)=26322572) +354 train 7.683278 (lr=1.7500e-04) (hash(x)=27084665) +355 train 7.611701 (lr=1.7500e-04) (hash(x)=25510798) +356 train 7.734113 (lr=1.7500e-04) (hash(x)=24970921) +357 train 7.742092 (lr=1.7500e-04) (hash(x)=24138948) +358 train 7.646966 (lr=1.7500e-04) (hash(x)=24790211) +359 train 7.747466 (lr=1.7500e-04) (hash(x)=25631397) +360 train 7.639870 (lr=1.7500e-04) (hash(x)=23226625) +361 train 7.679109 (lr=1.7500e-04) (hash(x)=24001903) +362 train 7.622877 (lr=1.7500e-04) (hash(x)=24587948) +363 train 7.328191 (lr=1.7500e-04) (hash(x)=21333676) +364 train 7.185182 (lr=1.7500e-04) (hash(x)=23673779) +365 train 8.737052 (lr=1.7500e-04) (hash(x)=30770484) +366 train 7.770377 (lr=1.7500e-04) (hash(x)=26564899) +367 train 7.737123 (lr=1.7500e-04) (hash(x)=26237983) +368 train 7.473118 (lr=1.7500e-04) (hash(x)=23764356) +369 train 7.859293 (lr=1.7500e-04) (hash(x)=26205744) +370 train 7.567906 (lr=1.7500e-04) (hash(x)=19208770) +371 train 7.770428 (lr=1.7500e-04) (hash(x)=25976502) +372 train 7.580566 (lr=1.7500e-04) (hash(x)=23983933) +373 train 7.555202 (lr=1.7500e-04) (hash(x)=24080636) +374 train 7.701003 (lr=1.7500e-04) (hash(x)=24404047) +375 train 7.641982 (lr=1.7500e-04) (hash(x)=24742645) +376 train 7.689429 (lr=1.7500e-04) (hash(x)=24159600) +377 train 7.939017 (lr=1.7500e-04) (hash(x)=28677257) +378 train 7.642778 (lr=1.7500e-04) (hash(x)=25604111) +379 train 7.591968 (lr=1.7500e-04) (hash(x)=27086333) +380 train 7.592072 (lr=1.7500e-04) (hash(x)=25188207) +381 train 7.818799 (lr=1.7500e-04) (hash(x)=27855233) +382 train 7.405207 (lr=1.7500e-04) (hash(x)=19470039) +383 train 7.689922 (lr=1.7500e-04) (hash(x)=26157660) +384 train 7.615396 (lr=1.7500e-04) (hash(x)=25291570) +385 train 7.596561 (lr=1.7500e-04) (hash(x)=25046062) +386 train 7.889949 (lr=1.7500e-04) (hash(x)=27020337) +387 train 7.523795 (lr=1.7500e-04) (hash(x)=23616370) +388 train 7.166601 (lr=1.7500e-04) (hash(x)=19113218) +389 train 7.526254 (lr=1.7500e-04) (hash(x)=24302232) +390 train 7.556539 (lr=1.7500e-04) (hash(x)=22188949) +391 train 7.370005 (lr=1.7500e-04) (hash(x)=22582169) +392 train 7.555988 (lr=1.7500e-04) (hash(x)=24700570) +393 train 7.466299 (lr=1.7500e-04) (hash(x)=22773833) +394 train 7.317876 (lr=1.7500e-04) (hash(x)=21875928) +395 train 7.635326 (lr=1.7500e-04) (hash(x)=26233189) +396 train 7.461598 (lr=1.7500e-04) (hash(x)=24321467) +397 train 7.768839 (lr=1.7500e-04) (hash(x)=26431507) +398 train 7.846620 (lr=1.7500e-04) (hash(x)=28690877) +399 train 7.799309 (lr=1.7500e-04) (hash(x)=26431960) +400 val loss 7.6617 +400 val perplexity 2125.4338 +400 train 7.615283 (lr=1.7500e-04) (hash(x)=24580300) +401 train 7.614981 (lr=1.7500e-04) (hash(x)=25112360) +402 train 7.716693 (lr=1.7500e-04) (hash(x)=27597243) +403 train 8.219069 (lr=1.7500e-04) (hash(x)=30707498) +404 train 7.854027 (lr=1.7500e-04) (hash(x)=28485465) +405 train 7.437431 (lr=1.7500e-04) (hash(x)=22586447) +406 train 7.615166 (lr=1.7500e-04) (hash(x)=23175270) +407 train 7.711012 (lr=1.7500e-04) (hash(x)=25716176) +408 train 7.769342 (lr=1.7500e-04) (hash(x)=26861373) +409 train 7.859297 (lr=1.7500e-04) (hash(x)=25118971) +410 train 7.356431 (lr=1.7500e-04) (hash(x)=19829066) +411 train 7.535391 (lr=1.7500e-04) (hash(x)=26256420) +412 train 7.816931 (lr=1.7500e-04) (hash(x)=27796153) +413 train 7.550957 (lr=1.7500e-04) (hash(x)=22633318) +414 train 7.552754 (lr=1.7500e-04) (hash(x)=22589383) +415 train 8.002383 (lr=1.7500e-04) (hash(x)=28019788) +416 train 7.924721 (lr=1.7500e-04) (hash(x)=28970440) +417 train 7.566503 (lr=1.7500e-04) (hash(x)=27396089) +418 train 7.546724 (lr=1.7500e-04) (hash(x)=21183513) +419 train 7.606873 (lr=1.7500e-04) (hash(x)=23510110) +420 train 7.806772 (lr=1.7500e-04) (hash(x)=28833467) +421 train 7.734850 (lr=1.7500e-04) (hash(x)=23646926) +422 train 7.643341 (lr=1.7500e-04) (hash(x)=24697272) +423 train 7.449602 (lr=1.7500e-04) (hash(x)=20382963) +424 train 7.464162 (lr=1.7500e-04) (hash(x)=23467595) +425 train 7.610089 (lr=1.7500e-04) (hash(x)=24304768) +426 train 7.542616 (lr=1.7500e-04) (hash(x)=21392328) +427 train 7.529735 (lr=1.7500e-04) (hash(x)=25339466) +428 train 7.507633 (lr=1.7500e-04) (hash(x)=22092542) +429 train 7.592358 (lr=1.7500e-04) (hash(x)=22088696) +430 train 7.504070 (lr=1.7500e-04) (hash(x)=22184471) +431 train 7.612329 (lr=1.7500e-04) (hash(x)=24489647) +432 train 7.614722 (lr=1.7500e-04) (hash(x)=26794132) +433 train 7.357021 (lr=1.7500e-04) (hash(x)=22940357) +434 train 7.592001 (lr=1.7500e-04) (hash(x)=23719522) +435 train 7.456587 (lr=1.7500e-04) (hash(x)=22927699) +436 train 7.615390 (lr=1.7500e-04) (hash(x)=26068576) +437 train 7.741121 (lr=1.7500e-04) (hash(x)=27631132) +438 train 7.621921 (lr=1.7500e-04) (hash(x)=26739991) +439 train 7.713733 (lr=1.7500e-04) (hash(x)=25128502) +440 train 7.731494 (lr=1.7500e-04) (hash(x)=25657260) +441 train 7.492943 (lr=1.7500e-04) (hash(x)=23576982) +442 train 7.751355 (lr=1.7500e-04) (hash(x)=27117886) +443 train 7.720943 (lr=1.7500e-04) (hash(x)=25808969) +444 train 7.632292 (lr=1.7500e-04) (hash(x)=24738238) +445 train 7.685066 (lr=1.7500e-04) (hash(x)=23429962) +446 train 7.819129 (lr=1.7500e-04) (hash(x)=25075165) +447 train 7.608167 (lr=1.7500e-04) (hash(x)=25231390) +448 train 7.416733 (lr=1.7500e-04) (hash(x)=22055054) +449 train 7.638399 (lr=1.7500e-04) (hash(x)=25395441) +450 val loss 7.6252 +450 val perplexity 2049.1831 +450 train 7.681772 (lr=1.7500e-04) (hash(x)=25863209) +451 train 7.321452 (lr=1.7500e-04) (hash(x)=21154388) +452 train 7.314236 (lr=1.7500e-04) (hash(x)=21600876) +453 train 7.474202 (lr=1.7500e-04) (hash(x)=24278611) +454 train 7.324168 (lr=1.7500e-04) (hash(x)=23221720) +455 train 7.560623 (lr=1.7500e-04) (hash(x)=22708977) +456 train 8.173945 (lr=1.7500e-04) (hash(x)=23637758) +457 train 7.871805 (lr=1.7500e-04) (hash(x)=28228490) +458 train 7.876717 (lr=1.7500e-04) (hash(x)=28638071) +459 train 7.737503 (lr=1.7500e-04) (hash(x)=27258353) +460 train 7.721482 (lr=1.7500e-04) (hash(x)=26604728) +461 train 7.603168 (lr=1.7500e-04) (hash(x)=23252199) +462 train 7.696648 (lr=1.7500e-04) (hash(x)=26441427) +463 train 7.429977 (lr=1.7500e-04) (hash(x)=24364920) +464 train 7.584375 (lr=1.7500e-04) (hash(x)=25623792) +465 train 7.467000 (lr=1.7500e-04) (hash(x)=23283905) +466 train 7.942864 (lr=1.7500e-04) (hash(x)=26025267) +467 train 7.700404 (lr=1.7500e-04) (hash(x)=27243972) +468 train 8.001654 (lr=1.7500e-04) (hash(x)=30449945) +469 train 7.766005 (lr=1.7500e-04) (hash(x)=28113043) +470 train 7.625829 (lr=1.7500e-04) (hash(x)=25182521) +471 train 7.625806 (lr=1.7500e-04) (hash(x)=24932925) +472 train 7.426604 (lr=1.7500e-04) (hash(x)=20353098) +473 train 7.320743 (lr=1.7500e-04) (hash(x)=19001259) +474 train 7.902437 (lr=1.7500e-04) (hash(x)=27585685) +475 train 7.579237 (lr=1.7500e-04) (hash(x)=26371091) +476 train 7.411672 (lr=1.7500e-04) (hash(x)=24891798) +477 train 7.443655 (lr=1.7500e-04) (hash(x)=24258817) +478 train 7.532842 (lr=1.7500e-04) (hash(x)=24330263) +479 train 7.625954 (lr=1.7500e-04) (hash(x)=26913684) +480 train 7.624290 (lr=1.7500e-04) (hash(x)=26338455) +481 train 7.914064 (lr=1.7500e-04) (hash(x)=27753043) +482 train 7.631314 (lr=1.7500e-04) (hash(x)=26123289) +483 train 7.735554 (lr=1.7500e-04) (hash(x)=29239611) +484 train 7.629131 (lr=1.7500e-04) (hash(x)=26553003) +485 train 7.586790 (lr=1.7500e-04) (hash(x)=22984557) +486 train 7.054608 (lr=1.7500e-04) (hash(x)=16947491) +487 train 7.045165 (lr=1.7500e-04) (hash(x)=18017792) +488 train 7.237781 (lr=1.7500e-04) (hash(x)=19918608) +489 train 7.823936 (lr=1.7500e-04) (hash(x)=23374526) +490 train 7.646807 (lr=1.7500e-04) (hash(x)=25009505) +491 train 7.605385 (lr=1.7500e-04) (hash(x)=27574089) +492 train 7.772190 (lr=1.7500e-04) (hash(x)=24122664) +493 train 7.647609 (lr=1.7500e-04) (hash(x)=26154906) +494 train 7.596139 (lr=1.7500e-04) (hash(x)=25192767) +495 train 7.744456 (lr=1.7500e-04) (hash(x)=28613882) +496 train 7.715546 (lr=1.7500e-04) (hash(x)=23547219) +497 train 7.705785 (lr=1.7500e-04) (hash(x)=25272182) +498 train 7.577881 (lr=1.7500e-04) (hash(x)=24992761) +499 train 7.815488 (lr=1.7500e-04) (hash(x)=26981914) +500 val loss 7.6781 +500 val perplexity 2160.5471 +500 train 7.604817 (lr=1.7500e-04) (hash(x)=22051933) +501 train 7.748894 (lr=1.7500e-04) (hash(x)=24232348) +502 train 7.693137 (lr=1.7500e-04) (hash(x)=23158331) +503 train 7.509989 (lr=1.7500e-04) (hash(x)=22652243) +504 train 7.556460 (lr=1.7500e-04) (hash(x)=23805602) +505 train 7.905390 (lr=1.7500e-04) (hash(x)=25411991) +506 train 7.156589 (lr=1.7500e-04) (hash(x)=18827215) +507 train 6.842640 (lr=1.7500e-04) (hash(x)=15446025) +508 train 7.187931 (lr=1.7500e-04) (hash(x)=20516263) +509 train 7.714601 (lr=1.7500e-04) (hash(x)=27846176) +510 train 7.395412 (lr=1.7500e-04) (hash(x)=23342449) +511 train 7.687712 (lr=1.7500e-04) (hash(x)=27194521) +512 train 7.509900 (lr=1.7500e-04) (hash(x)=23008284) +513 train 8.026713 (lr=1.7500e-04) (hash(x)=29430001) +514 train 7.347332 (lr=1.7500e-04) (hash(x)=22579319) +515 train 7.401065 (lr=1.7500e-04) (hash(x)=25264518) +516 train 7.739863 (lr=1.7500e-04) (hash(x)=25359075) +517 train 7.735364 (lr=1.7500e-04) (hash(x)=25568956) +518 train 8.002393 (lr=1.7500e-04) (hash(x)=32004108) +519 train 7.703346 (lr=1.7500e-04) (hash(x)=24936836) +520 train 7.855420 (lr=1.7500e-04) (hash(x)=27263338) +521 train 7.843690 (lr=1.7500e-04) (hash(x)=27452099) +522 train 7.747316 (lr=1.7500e-04) (hash(x)=25965406) +523 train 7.928598 (lr=1.7500e-04) (hash(x)=28197282) +524 train 7.671284 (lr=1.7500e-04) (hash(x)=22466209) +525 train 7.668308 (lr=1.7500e-04) (hash(x)=22931889) +526 train 7.762501 (lr=1.7500e-04) (hash(x)=26903920) +527 train 7.662006 (lr=1.7500e-04) (hash(x)=24765578) +528 train 7.824369 (lr=1.7500e-04) (hash(x)=27811359) +529 train 7.579021 (lr=1.7500e-04) (hash(x)=25078649) +530 train 7.761678 (lr=1.7500e-04) (hash(x)=25572416) +531 train 7.850418 (lr=1.7500e-04) (hash(x)=27448185) +532 train 7.901395 (lr=1.7500e-04) (hash(x)=25923719) +533 train 7.717999 (lr=1.7500e-04) (hash(x)=24804856) +534 train 7.814827 (lr=1.7500e-04) (hash(x)=23207829) +535 train 7.711961 (lr=1.7500e-04) (hash(x)=23107416) +536 train 7.546657 (lr=1.7500e-04) (hash(x)=26739531) +537 train 7.579764 (lr=1.7500e-04) (hash(x)=24960796) +538 train 7.666964 (lr=1.7500e-04) (hash(x)=24667802) +539 train 7.750543 (lr=1.7500e-04) (hash(x)=26755138) +540 train 7.611848 (lr=1.7500e-04) (hash(x)=25537132) +541 train 7.550252 (lr=1.7500e-04) (hash(x)=24542526) +542 train 7.342086 (lr=1.7500e-04) (hash(x)=21296355) +543 train 7.858284 (lr=1.7500e-04) (hash(x)=29314255) +544 train 7.587522 (lr=1.7500e-04) (hash(x)=26001799) +545 train 7.629426 (lr=1.7500e-04) (hash(x)=27347755) +546 train 7.621729 (lr=1.7500e-04) (hash(x)=25107798) +547 train 7.431222 (lr=1.7500e-04) (hash(x)=22112669) +548 train 7.423465 (lr=1.7500e-04) (hash(x)=21897967) +549 train 7.572244 (lr=1.7500e-04) (hash(x)=25161929) +550 val loss 7.5974 +550 val perplexity 1992.9783 +550 train 7.481168 (lr=1.7500e-04) (hash(x)=27465106) +551 train 7.608296 (lr=1.7500e-04) (hash(x)=24013079) +552 train 7.487996 (lr=1.7500e-04) (hash(x)=23142015) +553 train 7.617113 (lr=1.7500e-04) (hash(x)=26768629) +554 train 7.614934 (lr=1.7500e-04) (hash(x)=26393383) +555 train 7.493425 (lr=1.7500e-04) (hash(x)=22537194) +556 train 7.775176 (lr=1.7500e-04) (hash(x)=24046036) +557 train 7.683475 (lr=1.7500e-04) (hash(x)=24974360) +558 train 7.901051 (lr=1.7500e-04) (hash(x)=28379928) +559 train 7.596149 (lr=1.7500e-04) (hash(x)=25322001) +560 train 7.702229 (lr=1.7500e-04) (hash(x)=26622031) +561 train 7.385844 (lr=1.7500e-04) (hash(x)=20562247) +562 train 7.764058 (lr=1.7500e-04) (hash(x)=27381885) +563 train 7.833650 (lr=1.7500e-04) (hash(x)=27028126) +564 train 7.672435 (lr=1.7500e-04) (hash(x)=28882928) +565 train 7.598373 (lr=1.7500e-04) (hash(x)=25666355) +566 train 7.711927 (lr=1.7500e-04) (hash(x)=24330810) +567 train 7.601028 (lr=1.7500e-04) (hash(x)=26690440) +568 train 7.502579 (lr=1.7500e-04) (hash(x)=22923592) +569 train 7.589410 (lr=1.7500e-04) (hash(x)=27348418) +570 train 7.663103 (lr=1.7500e-04) (hash(x)=28849848) +571 train 7.678109 (lr=1.7500e-04) (hash(x)=26967331) +572 train 7.487088 (lr=1.7500e-04) (hash(x)=22831467) +573 train 7.533836 (lr=1.7500e-04) (hash(x)=24765121) +574 train 7.523123 (lr=1.7500e-04) (hash(x)=24331857) +575 train 7.400887 (lr=1.7500e-04) (hash(x)=22598512) +576 train 7.594524 (lr=1.7500e-04) (hash(x)=25149353) +577 train 7.441486 (lr=1.7500e-04) (hash(x)=23725598) +578 train 7.658021 (lr=1.7500e-04) (hash(x)=26449557) +579 train 7.690756 (lr=1.7500e-04) (hash(x)=24697985) +580 train 7.693581 (lr=1.7500e-04) (hash(x)=26923059) +581 train 7.511295 (lr=1.7500e-04) (hash(x)=25201962) +582 train 7.171454 (lr=1.7500e-04) (hash(x)=20931520) +583 train 7.254121 (lr=1.7500e-04) (hash(x)=18473911) +584 train 7.366308 (lr=1.7500e-04) (hash(x)=21306267) +585 train 7.621200 (lr=1.7500e-04) (hash(x)=25982840) +586 train 7.507683 (lr=1.7500e-04) (hash(x)=25364874) +587 train 7.410573 (lr=1.7500e-04) (hash(x)=23172124) +588 train 7.721614 (lr=1.7500e-04) (hash(x)=27876897) +589 train 8.348855 (lr=1.7500e-04) (hash(x)=34646114) +590 train 8.697610 (lr=1.7500e-04) (hash(x)=35153576) +591 train 7.586574 (lr=1.7500e-04) (hash(x)=22322442) +592 train 7.780309 (lr=1.7500e-04) (hash(x)=27907331) +593 train 7.641839 (lr=1.7500e-04) (hash(x)=26211794) +594 train 7.818691 (lr=1.7500e-04) (hash(x)=29291512) +595 train 8.068387 (lr=1.7500e-04) (hash(x)=29659121) +596 train 7.918535 (lr=1.7500e-04) (hash(x)=29674399) +597 train 7.550002 (lr=1.7500e-04) (hash(x)=23538306) +598 train 7.659981 (lr=1.7500e-04) (hash(x)=21991524) +599 train 7.576856 (lr=1.7500e-04) (hash(x)=26324153) +600 val loss 7.5660 +600 val perplexity 1931.4553 +600 train 7.552530 (lr=1.7500e-04) (hash(x)=23712082) +601 train 7.619988 (lr=1.7500e-04) (hash(x)=24910403) +602 train 7.581554 (lr=1.7500e-04) (hash(x)=26737205) +603 train 7.670219 (lr=1.7500e-04) (hash(x)=26939970) +604 train 7.542717 (lr=1.7500e-04) (hash(x)=27651943) +605 train 7.889143 (lr=1.7500e-04) (hash(x)=27515446) +606 train 7.764444 (lr=1.7500e-04) (hash(x)=26753129) +607 train 7.438115 (lr=1.7500e-04) (hash(x)=23446058) +608 train 7.770102 (lr=1.7500e-04) (hash(x)=27587849) +609 train 7.671402 (lr=1.7500e-04) (hash(x)=25308253) +610 train 7.660863 (lr=1.7500e-04) (hash(x)=26615098) +611 train 7.740029 (lr=1.7500e-04) (hash(x)=29981801) +612 train 7.790702 (lr=1.7500e-04) (hash(x)=29592345) +613 train 7.792853 (lr=1.7500e-04) (hash(x)=23470413) +614 train 7.706511 (lr=1.7500e-04) (hash(x)=24742370) +615 train 7.681160 (lr=1.7500e-04) (hash(x)=24843741) +616 train 7.610027 (lr=1.7500e-04) (hash(x)=25192548) +617 train 7.649458 (lr=1.7500e-04) (hash(x)=27176996) +618 train 7.563224 (lr=1.7500e-04) (hash(x)=23964552) +619 train 7.515044 (lr=1.7500e-04) (hash(x)=22855363) +620 train 7.480485 (lr=1.7500e-04) (hash(x)=26332996) +621 train 7.315389 (lr=1.7500e-04) (hash(x)=22960957) +622 train 7.629409 (lr=1.7500e-04) (hash(x)=22752597) +623 train 7.537978 (lr=1.7500e-04) (hash(x)=23197102) +624 train 8.032784 (lr=1.7500e-04) (hash(x)=27383319) +625 train 7.598120 (lr=1.7500e-04) (hash(x)=26132276) +626 train 7.493788 (lr=1.7500e-04) (hash(x)=19810497) +627 train 7.561935 (lr=1.7500e-04) (hash(x)=25704919) +628 train 7.739064 (lr=1.7500e-04) (hash(x)=27174264) +629 train 7.884796 (lr=1.7500e-04) (hash(x)=22280814) +630 train 8.559997 (lr=1.7500e-04) (hash(x)=24279448) +631 train 8.053922 (lr=1.7500e-04) (hash(x)=23054940) +632 train 8.127254 (lr=1.7500e-04) (hash(x)=23942400) +633 train 8.345246 (lr=1.7500e-04) (hash(x)=24712416) +634 train 7.986995 (lr=1.7500e-04) (hash(x)=24564658) +635 train 7.713727 (lr=1.7500e-04) (hash(x)=24909904) +636 train 7.759989 (lr=1.7500e-04) (hash(x)=23049534) +637 train 7.800726 (lr=1.7500e-04) (hash(x)=24321591) +638 train 7.564338 (lr=1.7500e-04) (hash(x)=26153298) +639 train 7.576488 (lr=1.7500e-04) (hash(x)=27140757) +640 train 7.345502 (lr=1.7500e-04) (hash(x)=25115907) +641 train 7.394324 (lr=1.7500e-04) (hash(x)=26563770) +642 train 7.578546 (lr=1.7500e-04) (hash(x)=28089252) +643 train 7.497168 (lr=1.7500e-04) (hash(x)=25993110) +644 train 7.466611 (lr=1.7500e-04) (hash(x)=25150008) +645 train 7.715793 (lr=1.7500e-04) (hash(x)=28520222) +646 train 7.374059 (lr=1.7500e-04) (hash(x)=21349943) +647 train 7.435524 (lr=1.7500e-04) (hash(x)=25149419) +648 train 7.645555 (lr=1.7500e-04) (hash(x)=25730641) +649 train 7.792584 (lr=1.7500e-04) (hash(x)=26112813) +650 val loss 7.5644 +650 val perplexity 1928.3265 +650 train 7.608704 (lr=1.7500e-04) (hash(x)=25907805) +651 train 7.624097 (lr=1.7500e-04) (hash(x)=27623643) +652 train 7.568183 (lr=1.7500e-04) (hash(x)=26484959) +653 train 7.602118 (lr=1.7500e-04) (hash(x)=29199854) +654 train 7.585883 (lr=1.7500e-04) (hash(x)=28369628) +655 train 7.460411 (lr=1.7500e-04) (hash(x)=24727764) +656 train 7.244513 (lr=1.7500e-04) (hash(x)=22610673) +657 train 7.213680 (lr=1.7500e-04) (hash(x)=22667179) +658 train 7.012147 (lr=1.7500e-04) (hash(x)=18477300) +659 train 7.366347 (lr=1.7500e-04) (hash(x)=23155773) +660 train 7.135773 (lr=1.7500e-04) (hash(x)=19461032) +661 train 7.458971 (lr=1.7500e-04) (hash(x)=23453788) +662 train 7.572063 (lr=1.7500e-04) (hash(x)=24543466) +663 train 7.338427 (lr=1.7500e-04) (hash(x)=21935931) +664 train 7.164578 (lr=1.7500e-04) (hash(x)=19910292) +665 train 7.463190 (lr=1.7500e-04) (hash(x)=24481079) +666 train 7.190952 (lr=1.7500e-04) (hash(x)=18922411) +667 train 7.230655 (lr=1.7500e-04) (hash(x)=20054917) +668 train 7.465093 (lr=1.7500e-04) (hash(x)=24850470) +669 train 7.495442 (lr=1.7500e-04) (hash(x)=25907741) +670 train 7.665971 (lr=1.7500e-04) (hash(x)=26873522) +671 train 7.714803 (lr=1.7500e-04) (hash(x)=27606073) +672 train 7.815775 (lr=1.7500e-04) (hash(x)=26209645) +673 train 7.650095 (lr=1.7500e-04) (hash(x)=25202001) +674 train 7.668556 (lr=1.7500e-04) (hash(x)=25569462) +675 train 7.607051 (lr=1.7500e-04) (hash(x)=26534487) +676 train 7.613033 (lr=1.7500e-04) (hash(x)=26455057) +677 train 7.475682 (lr=1.7500e-04) (hash(x)=24095850) +678 train 7.718694 (lr=1.7500e-04) (hash(x)=25287752) +679 train 7.197081 (lr=1.7500e-04) (hash(x)=22450341) +680 train 7.921970 (lr=1.7500e-04) (hash(x)=29004853) +681 train 7.597096 (lr=1.7500e-04) (hash(x)=27993763) +682 train 7.461422 (lr=1.7500e-04) (hash(x)=26382658) +683 train 7.600185 (lr=1.7500e-04) (hash(x)=25013073) +684 train 7.599290 (lr=1.7500e-04) (hash(x)=30595809) +685 train 7.702811 (lr=1.7500e-04) (hash(x)=30934371) +686 train 8.256792 (lr=1.7500e-04) (hash(x)=33060834) +687 train 7.567496 (lr=1.7500e-04) (hash(x)=25945859) +688 train 7.426053 (lr=1.7500e-04) (hash(x)=23375678) +689 train 7.479306 (lr=1.7500e-04) (hash(x)=25218689) +690 train 7.608769 (lr=1.7500e-04) (hash(x)=28127397) +691 train 7.494304 (lr=1.7500e-04) (hash(x)=24418091) +692 train 7.442383 (lr=1.7500e-04) (hash(x)=22761099) +693 train 7.428160 (lr=1.7500e-04) (hash(x)=24615466) +694 train 7.570212 (lr=1.7500e-04) (hash(x)=24699240) +695 train 7.453819 (lr=1.7500e-04) (hash(x)=21613707) +696 train 7.539325 (lr=1.7500e-04) (hash(x)=24977554) +697 train 7.478545 (lr=1.7500e-04) (hash(x)=24348175) +698 train 7.640060 (lr=1.7500e-04) (hash(x)=25102767) +699 train 7.581326 (lr=1.7500e-04) (hash(x)=26386157) +700 val loss 7.5003 +700 val perplexity 1808.6339 +700 train 7.532131 (lr=1.7500e-04) (hash(x)=26423460) +701 train 7.449039 (lr=1.7500e-04) (hash(x)=25771047) +702 train 7.504472 (lr=1.7500e-04) (hash(x)=26999875) +703 train 7.500427 (lr=1.7500e-04) (hash(x)=24396519) +704 train 7.496449 (lr=1.7500e-04) (hash(x)=22588122) +705 train 7.816066 (lr=1.7500e-04) (hash(x)=25142399) +706 train 7.533771 (lr=1.7500e-04) (hash(x)=20440214) +707 train 7.402005 (lr=1.7500e-04) (hash(x)=23265507) +708 train 7.514795 (lr=1.7500e-04) (hash(x)=24563470) +709 train 7.417448 (lr=1.7500e-04) (hash(x)=22514858) +710 train 7.736566 (lr=1.7500e-04) (hash(x)=26691212) +711 train 7.792604 (lr=1.7500e-04) (hash(x)=29138828) +712 train 7.750674 (lr=1.7500e-04) (hash(x)=28028528) +713 train 7.581098 (lr=1.7500e-04) (hash(x)=20531210) +714 train 7.471057 (lr=1.7500e-04) (hash(x)=25075352) +715 train 7.529644 (lr=1.7500e-04) (hash(x)=24265353) +716 train 7.641602 (lr=1.7500e-04) (hash(x)=24635726) +717 train 7.502071 (lr=1.7500e-04) (hash(x)=24999726) +718 train 7.650838 (lr=1.7500e-04) (hash(x)=27412910) +719 train 7.466821 (lr=1.7500e-04) (hash(x)=24685515) +720 train 7.491228 (lr=1.7500e-04) (hash(x)=23780329) +721 train 7.350838 (lr=1.7500e-04) (hash(x)=25071701) +722 train 7.484081 (lr=1.7500e-04) (hash(x)=23767130) +723 train 7.418570 (lr=1.7500e-04) (hash(x)=24876269) +724 train 7.553269 (lr=1.7500e-04) (hash(x)=26405773) +725 train 7.949794 (lr=1.7500e-04) (hash(x)=31733180) +726 train 7.180550 (lr=1.7500e-04) (hash(x)=21337509) +727 train 7.335159 (lr=1.7500e-04) (hash(x)=22825749) +728 train 7.675841 (lr=1.7500e-04) (hash(x)=28638695) +729 train 7.558187 (lr=1.7500e-04) (hash(x)=26393943) +730 train 7.702094 (lr=1.7500e-04) (hash(x)=27563583) +731 train 7.232281 (lr=1.7500e-04) (hash(x)=21239652) +732 train 7.384890 (lr=1.7500e-04) (hash(x)=23986428) +733 train 7.326100 (lr=1.7500e-04) (hash(x)=24943881) +734 train 7.843841 (lr=1.7500e-04) (hash(x)=29691448) +735 train 7.790572 (lr=1.7500e-04) (hash(x)=28767869) +736 train 7.483119 (lr=1.7500e-04) (hash(x)=23628188) +737 train 7.764581 (lr=1.7500e-04) (hash(x)=29341482) +738 train 7.589167 (lr=1.7500e-04) (hash(x)=30336570) +739 train 7.576435 (lr=1.7500e-04) (hash(x)=25614301) +740 train 7.422157 (lr=1.7500e-04) (hash(x)=24160500) +741 train 7.637523 (lr=1.7500e-04) (hash(x)=26030058) +742 train 7.974133 (lr=1.7500e-04) (hash(x)=29243936) +743 train 7.287095 (lr=1.7500e-04) (hash(x)=21159060) +744 train 7.401210 (lr=1.7500e-04) (hash(x)=23701853) +745 train 7.597969 (lr=1.7500e-04) (hash(x)=24629937) +746 train 7.495767 (lr=1.7500e-04) (hash(x)=25110108) +747 train 7.567555 (lr=1.7500e-04) (hash(x)=26751788) +748 train 7.589889 (lr=1.7500e-04) (hash(x)=26430427) +749 train 7.417226 (lr=1.7500e-04) (hash(x)=26012353) +750 val loss 7.4840 +750 val perplexity 1779.2917 +750 train 7.571089 (lr=1.7500e-04) (hash(x)=22735910) +751 train 7.374980 (lr=1.7500e-04) (hash(x)=25045397) +752 train 7.148426 (lr=1.7500e-04) (hash(x)=21554427) +753 train 7.251886 (lr=1.7500e-04) (hash(x)=23751143) +754 train 7.961453 (lr=1.7500e-04) (hash(x)=28602273) +755 train 7.977301 (lr=1.7500e-04) (hash(x)=29989709) +756 train 7.429015 (lr=1.7500e-04) (hash(x)=22331648) +757 train 7.810451 (lr=1.7500e-04) (hash(x)=31017246) +758 train 7.774237 (lr=1.7500e-04) (hash(x)=29709045) +759 train 7.805094 (lr=1.7500e-04) (hash(x)=25560928) +760 train 7.500845 (lr=1.7500e-04) (hash(x)=25075464) +761 train 7.561115 (lr=1.7500e-04) (hash(x)=27352253) +762 train 7.762602 (lr=1.7500e-04) (hash(x)=28187891) +763 train 7.631160 (lr=1.7500e-04) (hash(x)=26062687) +764 train 7.612175 (lr=1.7500e-04) (hash(x)=27427811) +765 train 7.677094 (lr=1.7500e-04) (hash(x)=27614522) +766 train 7.458817 (lr=1.7500e-04) (hash(x)=26129544) +767 train 8.003530 (lr=1.7500e-04) (hash(x)=28959222) +768 train 7.608940 (lr=1.7500e-04) (hash(x)=26860067) +769 train 7.384252 (lr=1.7500e-04) (hash(x)=25122598) +770 train 7.479161 (lr=1.7500e-04) (hash(x)=25245030) +771 train 7.509263 (lr=1.7500e-04) (hash(x)=25434884) +772 train 7.535243 (lr=1.7500e-04) (hash(x)=27732790) +773 train 7.537230 (lr=1.7500e-04) (hash(x)=27824438) +774 train 7.661378 (lr=1.7500e-04) (hash(x)=27201953) +775 train 7.400951 (lr=1.7500e-04) (hash(x)=21248405) +776 train 7.208531 (lr=1.7500e-04) (hash(x)=22805934) +777 train 7.524553 (lr=1.7500e-04) (hash(x)=26482588) +778 train 7.600501 (lr=1.7500e-04) (hash(x)=24153691) +779 train 7.699942 (lr=1.7500e-04) (hash(x)=25044192) +780 train 7.629530 (lr=1.7500e-04) (hash(x)=25910078) +781 train 7.597488 (lr=1.7500e-04) (hash(x)=28645524) +782 train 7.468704 (lr=1.7500e-04) (hash(x)=24368498) +783 train 7.564649 (lr=1.7500e-04) (hash(x)=25830182) +784 train 7.692058 (lr=1.7500e-04) (hash(x)=29181807) +785 train 7.612691 (lr=1.7500e-04) (hash(x)=25585137) +786 train 7.504141 (lr=1.7500e-04) (hash(x)=24798246) +787 train 7.597637 (lr=1.7500e-04) (hash(x)=26621419) +788 train 7.153249 (lr=1.7500e-04) (hash(x)=21446891) +789 train 7.090726 (lr=1.7500e-04) (hash(x)=22165286) +790 train 7.318669 (lr=1.7500e-04) (hash(x)=23477219) +791 train 7.577304 (lr=1.7500e-04) (hash(x)=25173113) +792 train 7.493880 (lr=1.7500e-04) (hash(x)=25853788) +793 train 7.613543 (lr=1.7500e-04) (hash(x)=27267091) +794 train 7.426459 (lr=1.7500e-04) (hash(x)=23743694) +795 train 7.386683 (lr=1.7500e-04) (hash(x)=24400133) +796 train 7.464972 (lr=1.7500e-04) (hash(x)=23663639) +797 train 7.335460 (lr=1.7500e-04) (hash(x)=23103223) +798 train 7.858362 (lr=1.7500e-04) (hash(x)=28748411) +799 train 7.185689 (lr=1.7500e-04) (hash(x)=23486277) +800 val loss 7.4873 +800 val perplexity 1785.2373 +800 train 7.466350 (lr=1.7500e-04) (hash(x)=25678518) +801 train 7.425147 (lr=1.7500e-04) (hash(x)=23421286) +802 train 7.568503 (lr=1.7500e-04) (hash(x)=26054104) +803 train 7.572492 (lr=1.7500e-04) (hash(x)=25978130) +804 train 7.600664 (lr=1.7500e-04) (hash(x)=26006525) +805 train 7.517650 (lr=1.7500e-04) (hash(x)=25769432) +806 train 7.314024 (lr=1.7500e-04) (hash(x)=22430795) +807 train 7.730274 (lr=1.7500e-04) (hash(x)=28916006) +808 train 7.490091 (lr=1.7500e-04) (hash(x)=25166800) +809 train 7.627557 (lr=1.7500e-04) (hash(x)=24226056) +810 train 7.445061 (lr=1.7500e-04) (hash(x)=25057934) +811 train 8.294478 (lr=1.7500e-04) (hash(x)=33195100) +812 train 7.631687 (lr=1.7500e-04) (hash(x)=26312888) +813 train 7.798380 (lr=1.7500e-04) (hash(x)=27730410) +814 train 7.667867 (lr=1.7500e-04) (hash(x)=27372474) +815 train 7.519309 (lr=1.7500e-04) (hash(x)=25556929) +816 train 7.590018 (lr=1.7500e-04) (hash(x)=26909985) +817 train 7.374174 (lr=1.7500e-04) (hash(x)=25991247) +818 train 7.575542 (lr=1.7500e-04) (hash(x)=27438141) +819 train 7.737886 (lr=1.7500e-04) (hash(x)=29536986) +820 train 7.466397 (lr=1.7500e-04) (hash(x)=24478391) +821 train 7.441967 (lr=1.7500e-04) (hash(x)=26125216) +822 train 7.494466 (lr=1.7500e-04) (hash(x)=26422130) +823 train 7.685241 (lr=1.7500e-04) (hash(x)=29648798) +824 train 7.384827 (lr=1.7500e-04) (hash(x)=21247770) +825 train 7.498898 (lr=1.7500e-04) (hash(x)=23195388) +826 train 7.415112 (lr=1.7500e-04) (hash(x)=25796725) +827 train 7.505316 (lr=1.7500e-04) (hash(x)=23124767) +828 train 7.534744 (lr=1.7500e-04) (hash(x)=25233464) +829 train 7.504005 (lr=1.7500e-04) (hash(x)=25713275) +830 train 7.450072 (lr=1.7500e-04) (hash(x)=25550167) +831 train 7.348304 (lr=1.7500e-04) (hash(x)=24976217) +832 train 7.647533 (lr=1.7500e-04) (hash(x)=28536827) +833 train 7.554760 (lr=1.7500e-04) (hash(x)=27500801) +834 train 7.385510 (lr=1.7500e-04) (hash(x)=25545765) +835 train 7.463449 (lr=1.7500e-04) (hash(x)=23632825) +836 train 7.485750 (lr=1.7500e-04) (hash(x)=25708009) +837 train 7.569826 (lr=1.7500e-04) (hash(x)=24456276) +838 train 7.665231 (lr=1.7500e-04) (hash(x)=29189855) +839 train 7.892982 (lr=1.7500e-04) (hash(x)=31019606) +840 train 7.782461 (lr=1.7500e-04) (hash(x)=26328013) +841 train 7.685041 (lr=1.7500e-04) (hash(x)=25027904) +842 train 7.642349 (lr=1.7500e-04) (hash(x)=23734189) +843 train 7.897407 (lr=1.7500e-04) (hash(x)=28236580) +844 train 7.725879 (lr=1.7500e-04) (hash(x)=26509780) +845 train 7.768111 (lr=1.7500e-04) (hash(x)=25386473) +846 train 7.735318 (lr=1.7500e-04) (hash(x)=24052671) +847 train 7.842248 (lr=1.7500e-04) (hash(x)=28269421) +848 train 7.276422 (lr=1.7500e-04) (hash(x)=22251724) +849 train 7.519605 (lr=1.7500e-04) (hash(x)=24308447) +850 val loss 7.5751 +850 val perplexity 1948.9612 +850 train 7.452107 (lr=1.7500e-04) (hash(x)=24242830) +851 train 7.595599 (lr=1.7500e-04) (hash(x)=25563279) +852 train 7.619998 (lr=1.7500e-04) (hash(x)=26354481) +853 train 7.729393 (lr=1.7500e-04) (hash(x)=26152637) +854 train 7.778084 (lr=1.7500e-04) (hash(x)=28051025) +855 train 7.603670 (lr=1.7500e-04) (hash(x)=24865358) +856 train 7.478933 (lr=1.7500e-04) (hash(x)=24288911) +857 train 7.362055 (lr=1.7500e-04) (hash(x)=22230964) +858 train 7.247631 (lr=1.7500e-04) (hash(x)=21303832) +859 train 7.441173 (lr=1.7500e-04) (hash(x)=22155546) +860 train 7.552505 (lr=1.7500e-04) (hash(x)=25296428) +861 train 7.700271 (lr=1.7500e-04) (hash(x)=29142319) +862 train 7.520694 (lr=1.7500e-04) (hash(x)=25545430) +863 train 7.307149 (lr=1.7500e-04) (hash(x)=26984272) +864 train 7.504467 (lr=1.7500e-04) (hash(x)=25429005) +865 train 7.580850 (lr=1.7500e-04) (hash(x)=27077032) +866 train 7.594506 (lr=1.7500e-04) (hash(x)=26494424) +867 train 7.571471 (lr=1.7500e-04) (hash(x)=23193673) +868 train 7.600482 (lr=1.7500e-04) (hash(x)=25075134) +869 train 7.605119 (lr=1.7500e-04) (hash(x)=27112558) +870 train 7.768301 (lr=1.7500e-04) (hash(x)=27436608) +871 train 7.469556 (lr=1.7500e-04) (hash(x)=24544116) +872 train 7.791693 (lr=1.7500e-04) (hash(x)=31632686) +873 train 7.493390 (lr=1.7500e-04) (hash(x)=25890184) +874 train 7.610923 (lr=1.7500e-04) (hash(x)=22887555) +875 train 7.448509 (lr=1.7500e-04) (hash(x)=24547533) +876 train 7.576961 (lr=1.7500e-04) (hash(x)=26553496) +877 train 7.681484 (lr=1.7500e-04) (hash(x)=27467688) +878 train 7.413136 (lr=1.7500e-04) (hash(x)=24766934) +879 train 7.336182 (lr=1.7500e-04) (hash(x)=22059850) +880 train 7.691164 (lr=1.7500e-04) (hash(x)=22871702) +881 train 7.524491 (lr=1.7500e-04) (hash(x)=23893130) +882 train 7.545572 (lr=1.7500e-04) (hash(x)=25125691) +883 train 7.491301 (lr=1.7500e-04) (hash(x)=25994573) +884 train 7.552158 (lr=1.7500e-04) (hash(x)=26076345) +885 train 7.498138 (lr=1.7500e-04) (hash(x)=26577783) +886 train 7.631542 (lr=1.7500e-04) (hash(x)=27395225) +887 train 7.431426 (lr=1.7500e-04) (hash(x)=23926632) +888 train 7.286192 (lr=1.7500e-04) (hash(x)=21737239) +889 train 7.557686 (lr=1.7500e-04) (hash(x)=23574207) +890 train 7.229337 (lr=1.7500e-04) (hash(x)=24365231) +891 train 7.387240 (lr=1.7500e-04) (hash(x)=27111369) +892 train 7.694339 (lr=1.7500e-04) (hash(x)=27290015) +893 train 7.435281 (lr=1.7500e-04) (hash(x)=23979820) +894 train 7.546453 (lr=1.7500e-04) (hash(x)=26450121) +895 train 7.446971 (lr=1.7500e-04) (hash(x)=27025333) +896 train 7.439038 (lr=1.7500e-04) (hash(x)=23624605) +897 train 7.284598 (lr=1.7500e-04) (hash(x)=22846386) +898 train 7.345957 (lr=1.7500e-04) (hash(x)=22970561) +899 train 7.199277 (lr=1.7500e-04) (hash(x)=16908068) +900 val loss 7.4557 +900 val perplexity 1729.6703 +900 train 7.407154 (lr=1.7500e-04) (hash(x)=24661446) +901 train 7.553349 (lr=1.7500e-04) (hash(x)=25664727) +902 train 7.486505 (lr=1.7500e-04) (hash(x)=25667011) +903 train 7.538350 (lr=1.7500e-04) (hash(x)=29120407) +904 train 7.573706 (lr=1.7500e-04) (hash(x)=23385735) +905 train 7.620168 (lr=1.7500e-04) (hash(x)=25564213) +906 train 7.677637 (lr=1.7500e-04) (hash(x)=25413898) +907 train 7.613008 (lr=1.7500e-04) (hash(x)=27092710) +908 train 7.374074 (lr=1.7500e-04) (hash(x)=25789923) +909 train 7.471066 (lr=1.7500e-04) (hash(x)=28533197) +910 train 7.280168 (lr=1.7500e-04) (hash(x)=22982996) +911 train 7.371724 (lr=1.7500e-04) (hash(x)=23827393) +912 train 7.039115 (lr=1.7500e-04) (hash(x)=21242640) +913 train 7.473882 (lr=1.7500e-04) (hash(x)=24154233) +914 train 7.479494 (lr=1.7500e-04) (hash(x)=24331967) +915 train 7.781083 (lr=1.7500e-04) (hash(x)=32812727) +916 train 7.441473 (lr=1.7500e-04) (hash(x)=23572994) +917 train 7.432493 (lr=1.7500e-04) (hash(x)=26305435) +918 train 7.483561 (lr=1.7500e-04) (hash(x)=26268355) +919 train 7.628336 (lr=1.7500e-04) (hash(x)=27230027) +920 train 7.428694 (lr=1.7500e-04) (hash(x)=23885377) +921 train 7.353568 (lr=1.7500e-04) (hash(x)=23532437) +922 train 7.458452 (lr=1.7500e-04) (hash(x)=25577034) +923 train 7.605784 (lr=1.7500e-04) (hash(x)=25703381) +924 train 7.591214 (lr=1.7500e-04) (hash(x)=27113866) +925 train 7.420835 (lr=1.7500e-04) (hash(x)=26961429) +926 train 7.233224 (lr=1.7500e-04) (hash(x)=21355372) +927 train 7.367800 (lr=1.7500e-04) (hash(x)=24968260) +928 train 7.352069 (lr=1.7500e-04) (hash(x)=25357517) +929 train 7.431559 (lr=1.7500e-04) (hash(x)=24854265) +930 train 7.222905 (lr=1.7500e-04) (hash(x)=21102770) +931 train 7.519861 (lr=1.7500e-04) (hash(x)=25676468) +932 train 7.409265 (lr=1.7500e-04) (hash(x)=22809869) +933 train 7.535611 (lr=1.7500e-04) (hash(x)=25503865) +934 train 7.400999 (lr=1.7500e-04) (hash(x)=24853995) +935 train 7.587636 (lr=1.7500e-04) (hash(x)=27544803) +936 train 7.653526 (lr=1.7500e-04) (hash(x)=25981933) +937 train 7.406422 (lr=1.7500e-04) (hash(x)=24658683) +938 train 7.579388 (lr=1.7500e-04) (hash(x)=23855201) +939 train 7.532005 (lr=1.7500e-04) (hash(x)=24331407) +940 train 7.691742 (lr=1.7500e-04) (hash(x)=29265551) +941 train 7.349556 (lr=1.7500e-04) (hash(x)=21892556) +942 train 7.361261 (lr=1.7500e-04) (hash(x)=27183405) +943 train 7.328289 (lr=1.7500e-04) (hash(x)=26540663) +944 train 7.303599 (lr=1.7500e-04) (hash(x)=25718393) +945 train 7.499362 (lr=1.7500e-04) (hash(x)=26819462) +946 train 7.486422 (lr=1.7500e-04) (hash(x)=27427540) +947 train 7.488599 (lr=1.7500e-04) (hash(x)=25532657) +948 train 7.692464 (lr=1.7500e-04) (hash(x)=27641372) +949 train 7.430267 (lr=1.7500e-04) (hash(x)=26515570) +950 val loss 7.4398 +950 val perplexity 1702.3866 +950 train 7.639112 (lr=1.7500e-04) (hash(x)=26911957) +951 train 7.807433 (lr=1.7500e-04) (hash(x)=25856625) +952 train 7.315128 (lr=1.7500e-04) (hash(x)=25219129) +953 train 7.324497 (lr=1.7500e-04) (hash(x)=25260471) +954 train 7.694683 (lr=1.7500e-04) (hash(x)=29373370) +955 train 7.257001 (lr=1.7500e-04) (hash(x)=23437426) +956 train 7.577347 (lr=1.7500e-04) (hash(x)=23769521) +957 train 7.574832 (lr=1.7500e-04) (hash(x)=25961833) +958 train 7.313478 (lr=1.7500e-04) (hash(x)=23582666) +959 train 7.401462 (lr=1.7500e-04) (hash(x)=23164356) +960 train 7.350257 (lr=1.7500e-04) (hash(x)=24443114) +961 train 7.432600 (lr=1.7500e-04) (hash(x)=25052665) +962 train 7.569678 (lr=1.7500e-04) (hash(x)=27802272) +963 train 7.407266 (lr=1.7500e-04) (hash(x)=25957896) +964 train 7.454549 (lr=1.7500e-04) (hash(x)=26737251) +965 train 7.566611 (lr=1.7500e-04) (hash(x)=24723263) +966 train 7.499735 (lr=1.7500e-04) (hash(x)=24707011) +967 train 7.460788 (lr=1.7500e-04) (hash(x)=25646282) +968 train 7.520233 (lr=1.7500e-04) (hash(x)=27544665) +969 train 7.420677 (lr=1.7500e-04) (hash(x)=25851993) +970 train 7.714299 (lr=1.7500e-04) (hash(x)=29059700) +971 train 7.472631 (lr=1.7500e-04) (hash(x)=21513584) +972 train 7.153545 (lr=1.7500e-04) (hash(x)=23151267) +973 train 7.457607 (lr=1.7500e-04) (hash(x)=26017176) +974 train 7.520819 (lr=1.7500e-04) (hash(x)=26979518) +975 train 7.508008 (lr=1.7500e-04) (hash(x)=23843233) +976 train 7.721962 (lr=1.7500e-04) (hash(x)=24193010) +977 train 7.422731 (lr=1.7500e-04) (hash(x)=21476847) +978 train 7.295234 (lr=1.7500e-04) (hash(x)=21366504) +979 train 7.339740 (lr=1.7500e-04) (hash(x)=23226697) +980 train 7.128482 (lr=1.7500e-04) (hash(x)=19961773) +981 train 7.031003 (lr=1.7500e-04) (hash(x)=19772969) +982 train 7.307733 (lr=1.7500e-04) (hash(x)=23110142) +983 train 7.546332 (lr=1.7500e-04) (hash(x)=24506028) +984 train 7.549211 (lr=1.7500e-04) (hash(x)=25480731) +985 train 7.374660 (lr=1.7500e-04) (hash(x)=21077417) +986 train 7.335085 (lr=1.7500e-04) (hash(x)=23686713) +987 train 7.412134 (lr=1.7500e-04) (hash(x)=26024321) +988 train 7.521736 (lr=1.7500e-04) (hash(x)=27424109) +989 train 7.652687 (lr=1.7500e-04) (hash(x)=27786174) +990 train 7.430222 (lr=1.7500e-04) (hash(x)=25232502) +991 train 7.445886 (lr=1.7500e-04) (hash(x)=22781277) +992 train 7.522009 (lr=1.7500e-04) (hash(x)=26184527) +993 train 7.474256 (lr=1.7500e-04) (hash(x)=24459895) +994 train 7.435775 (lr=1.7500e-04) (hash(x)=25244624) +995 train 7.526952 (lr=1.7500e-04) (hash(x)=24451843) +996 train 7.552074 (lr=1.7500e-04) (hash(x)=22129897) +997 train 7.394544 (lr=1.7500e-04) (hash(x)=21116390) +998 train 7.212599 (lr=1.7500e-04) (hash(x)=20650070) +999 train 7.620099 (lr=1.7500e-04) (hash(x)=24948650) +1000 val loss 7.4874 +1000 val perplexity 1785.4246 +1000 train 7.482121 (lr=1.7500e-04) (hash(x)=25444553) +1001 train 7.438818 (lr=1.7500e-04) (hash(x)=25617781) +1002 train 7.327928 (lr=1.7500e-04) (hash(x)=23862434) +1003 train 7.334672 (lr=1.7500e-04) (hash(x)=25559534) +1004 train 7.532141 (lr=1.7500e-04) (hash(x)=26577585) +1005 train 7.413329 (lr=1.7500e-04) (hash(x)=25546274) +1006 train 7.467506 (lr=1.7500e-04) (hash(x)=26284202) +1007 train 7.501541 (lr=1.7500e-04) (hash(x)=26373991) +1008 train 7.413097 (lr=1.7500e-04) (hash(x)=24612851) +1009 train 7.470013 (lr=1.7500e-04) (hash(x)=26410662) +1010 train 7.515427 (lr=1.7500e-04) (hash(x)=23824841) +1011 train 7.837996 (lr=1.7500e-04) (hash(x)=27756673) +1012 train 7.537847 (lr=1.7500e-04) (hash(x)=25427447) +1013 train 7.522437 (lr=1.7500e-04) (hash(x)=23661686) +1014 train 7.444168 (lr=1.7500e-04) (hash(x)=25129504) +1015 train 7.388440 (lr=1.7500e-04) (hash(x)=23402396) +1016 train 7.640402 (lr=1.7500e-04) (hash(x)=26145557) +1017 train 7.386009 (lr=1.7500e-04) (hash(x)=26547918) +1018 train 7.513662 (lr=1.7500e-04) (hash(x)=26653070) +1019 train 7.516582 (lr=1.7500e-04) (hash(x)=28250354) +1020 train 7.524126 (lr=1.7500e-04) (hash(x)=25437401) +1021 train 7.556924 (lr=1.7500e-04) (hash(x)=25598861) +1022 train 7.347998 (lr=1.7500e-04) (hash(x)=24572587) +1023 train 7.451474 (lr=1.7500e-04) (hash(x)=21562133) +1024 train 7.859436 (lr=1.7500e-04) (hash(x)=27718876) +1025 train 7.419868 (lr=1.7500e-04) (hash(x)=25312391) +1026 train 7.509199 (lr=1.7500e-04) (hash(x)=26579535) +1027 train 7.710379 (lr=1.7500e-04) (hash(x)=27253861) +1028 train 7.562892 (lr=1.7500e-04) (hash(x)=28451867) +1029 train 7.307785 (lr=1.7500e-04) (hash(x)=26795921) +1030 train 7.445110 (lr=1.7500e-04) (hash(x)=26147208) +1031 train 7.499616 (lr=1.7500e-04) (hash(x)=25009210) +1032 train 7.395140 (lr=1.7500e-04) (hash(x)=25213771) +1033 train 7.302021 (lr=1.7500e-04) (hash(x)=26254538) +1034 train 7.334751 (lr=1.7500e-04) (hash(x)=25565614) +1035 train 7.196240 (lr=1.7500e-04) (hash(x)=23052577) +1036 train 8.016413 (lr=1.7500e-04) (hash(x)=29630613) +1037 train 7.262398 (lr=1.7500e-04) (hash(x)=23667224) +1038 train 7.357564 (lr=1.7500e-04) (hash(x)=25740670) +1039 train 7.467157 (lr=1.7500e-04) (hash(x)=27161811) +1040 train 7.590257 (lr=1.7500e-04) (hash(x)=26385663) +1041 train 7.287741 (lr=1.7500e-04) (hash(x)=26313522) +1042 train 7.401296 (lr=1.7500e-04) (hash(x)=26814686) +1043 train 7.542745 (lr=1.7500e-04) (hash(x)=27302459) +1044 train 7.818761 (lr=1.7500e-04) (hash(x)=26758132) +1045 train 7.430023 (lr=1.7500e-04) (hash(x)=26837963) +1046 train 7.207488 (lr=1.7500e-04) (hash(x)=22089547) +1047 train 7.745154 (lr=1.7500e-04) (hash(x)=29515100) +1048 train 7.428613 (lr=1.7500e-04) (hash(x)=25471442) +1049 train 7.419579 (lr=1.7500e-04) (hash(x)=26674478) +1050 val loss 7.4219 +1050 val perplexity 1672.2050 +1050 train 7.369960 (lr=1.7500e-04) (hash(x)=25373386) +1051 train 7.417150 (lr=1.7500e-04) (hash(x)=25318001) +1052 train 7.560469 (lr=1.7500e-04) (hash(x)=27255021) +1053 train 7.515752 (lr=1.7500e-04) (hash(x)=25174043) +1054 train 7.253044 (lr=1.7500e-04) (hash(x)=23857597) +1055 train 7.485250 (lr=1.7500e-04) (hash(x)=25305929) +1056 train 7.533376 (lr=1.7500e-04) (hash(x)=27009246) +1057 train 7.597083 (lr=1.7500e-04) (hash(x)=26175477) +1058 train 7.288756 (lr=1.7500e-04) (hash(x)=22700025) +1059 train 7.340544 (lr=1.7500e-04) (hash(x)=24339043) +1060 train 7.211281 (lr=1.7500e-04) (hash(x)=22139900) +1061 train 7.968450 (lr=1.7500e-04) (hash(x)=25412772) +1062 train 7.416695 (lr=1.7500e-04) (hash(x)=27020849) +1063 train 7.349837 (lr=1.7500e-04) (hash(x)=26808543) +1064 train 7.148118 (lr=1.7500e-04) (hash(x)=23061527) +1065 train 7.349430 (lr=1.7500e-04) (hash(x)=24738650) +1066 train 7.197568 (lr=1.7500e-04) (hash(x)=24036715) +1067 train 7.267236 (lr=1.7500e-04) (hash(x)=25763991) +1068 train 7.528669 (lr=1.7500e-04) (hash(x)=27393753) +1069 train 7.694199 (lr=1.7500e-04) (hash(x)=28182190) +1070 train 7.288875 (lr=1.7500e-04) (hash(x)=23358569) +1071 train 7.484949 (lr=1.7500e-04) (hash(x)=25669509) +1072 train 7.592507 (lr=1.7500e-04) (hash(x)=29139024) +1073 train 7.507384 (lr=1.7500e-04) (hash(x)=25616522) +1074 train 7.404752 (lr=1.7500e-04) (hash(x)=25695789) +1075 train 7.581354 (lr=1.7500e-04) (hash(x)=27676869) +1076 train 7.445602 (lr=1.7500e-04) (hash(x)=25952695) +1077 train 7.453461 (lr=1.7500e-04) (hash(x)=26316170) +1078 train 7.333678 (lr=1.7500e-04) (hash(x)=24081867) +1079 train 7.556418 (lr=1.7500e-04) (hash(x)=28435805) +1080 train 7.420377 (lr=1.7500e-04) (hash(x)=23375063) +1081 train 7.408380 (lr=1.7500e-04) (hash(x)=26869022) +1082 train 7.309647 (lr=1.7500e-04) (hash(x)=25793007) +1083 train 7.287109 (lr=1.7500e-04) (hash(x)=23455211) +1084 train 7.304548 (lr=1.7500e-04) (hash(x)=20441501) +1085 train 7.691333 (lr=1.7500e-04) (hash(x)=29321187) +1086 train 7.876087 (lr=1.7500e-04) (hash(x)=32627505) +1087 train 7.361022 (lr=1.7500e-04) (hash(x)=26482758) +1088 train 7.199904 (lr=1.7500e-04) (hash(x)=21431511) +1089 train 7.430164 (lr=1.7500e-04) (hash(x)=26046639) +1090 train 7.504412 (lr=1.7500e-04) (hash(x)=27464841) +1091 train 7.365758 (lr=1.7500e-04) (hash(x)=27068280) +1092 train 7.269091 (lr=1.7500e-04) (hash(x)=23119133) +1093 train 7.431848 (lr=1.7500e-04) (hash(x)=26782091) +1094 train 7.468540 (lr=1.7500e-04) (hash(x)=26265326) +1095 train 7.500001 (lr=1.7500e-04) (hash(x)=24929929) +1096 train 7.336209 (lr=1.7500e-04) (hash(x)=23158628) +1097 train 7.422856 (lr=1.7500e-04) (hash(x)=25950541) +1098 train 7.241127 (lr=1.7500e-04) (hash(x)=22093912) +1099 train 7.393285 (lr=1.7500e-04) (hash(x)=25373676) +1100 val loss 7.4102 +1100 val perplexity 1652.7792 +1100 train 7.151862 (lr=1.7500e-04) (hash(x)=18986670) +1101 train 7.651880 (lr=1.7500e-04) (hash(x)=27283187) +1102 train 7.376002 (lr=1.7500e-04) (hash(x)=25474743) +1103 train 7.294557 (lr=1.7500e-04) (hash(x)=25043037) +1104 train 7.238220 (lr=1.7500e-04) (hash(x)=23156261) +1105 train 7.691566 (lr=1.7500e-04) (hash(x)=27027534) +1106 train 7.240763 (lr=1.7500e-04) (hash(x)=22733630) +1107 train 7.506341 (lr=1.7500e-04) (hash(x)=27906976) +1108 train 7.489959 (lr=1.7500e-04) (hash(x)=27848655) +1109 train 7.412692 (lr=1.7500e-04) (hash(x)=23889709) +1110 train 8.417629 (lr=1.7500e-04) (hash(x)=33189918) +1111 train 7.949933 (lr=1.7500e-04) (hash(x)=29151257) +1112 train 7.669029 (lr=1.7500e-04) (hash(x)=23881512) +1113 train 7.352018 (lr=1.7500e-04) (hash(x)=21307974) +1114 train 7.474010 (lr=1.7500e-04) (hash(x)=25264524) +1115 train 7.591330 (lr=1.7500e-04) (hash(x)=26405613) +1116 train 7.383835 (lr=1.7500e-04) (hash(x)=21918678) +1117 train 7.377378 (lr=1.7500e-04) (hash(x)=24233887) +1118 train 7.015126 (lr=1.7500e-04) (hash(x)=19490509) +1119 train 7.509693 (lr=1.7500e-04) (hash(x)=26400365) +1120 train 7.718874 (lr=1.7500e-04) (hash(x)=28572086) +1121 train 7.180145 (lr=1.7500e-04) (hash(x)=22293114) +1122 train 7.334109 (lr=1.7500e-04) (hash(x)=26845479) +1123 train 7.231884 (lr=1.7500e-04) (hash(x)=23971905) +1124 train 7.470516 (lr=1.7500e-04) (hash(x)=25639959) +1125 train 7.039809 (lr=1.7500e-04) (hash(x)=20076502) +1126 train 7.496830 (lr=1.7500e-04) (hash(x)=25089255) +1127 train 7.359818 (lr=1.7500e-04) (hash(x)=24098812) +1128 train 7.363980 (lr=1.7500e-04) (hash(x)=23493707) +1129 train 7.615081 (lr=1.7500e-04) (hash(x)=27610410) +1130 train 7.318950 (lr=1.7500e-04) (hash(x)=24540186) +1131 train 7.628874 (lr=1.7500e-04) (hash(x)=29402976) +1132 train 7.212093 (lr=1.7500e-04) (hash(x)=23776025) +1133 train 7.013091 (lr=1.7500e-04) (hash(x)=19032564) +1134 train 7.550034 (lr=1.7500e-04) (hash(x)=26921117) +1135 train 7.192134 (lr=1.7500e-04) (hash(x)=20967666) +1136 train 7.230679 (lr=1.7500e-04) (hash(x)=23394540) +1137 train 7.293869 (lr=1.7500e-04) (hash(x)=22666342) +1138 train 7.442297 (lr=1.7500e-04) (hash(x)=23482498) +1139 train 7.477598 (lr=1.7500e-04) (hash(x)=24287610) +1140 train 7.488179 (lr=1.7500e-04) (hash(x)=24512831) +1141 train 7.740933 (lr=1.7500e-04) (hash(x)=28637634) +1142 train 8.006017 (lr=1.7500e-04) (hash(x)=24107127) +1143 train 7.657132 (lr=1.7500e-04) (hash(x)=28667963) +1144 train 7.567323 (lr=1.7500e-04) (hash(x)=26302492) +1145 train 7.557458 (lr=1.7500e-04) (hash(x)=23621685) +1146 train 7.282669 (lr=1.7500e-04) (hash(x)=23997414) +1147 train 7.365224 (lr=1.7500e-04) (hash(x)=25974316) +1148 train 7.327252 (lr=1.7500e-04) (hash(x)=23464988) +1149 train 7.411688 (lr=1.7500e-04) (hash(x)=24487710) +1150 val loss 7.4082 +1150 val perplexity 1649.4174 +1150 train 7.644067 (lr=1.7500e-04) (hash(x)=29610350) +1151 train 7.744110 (lr=1.7500e-04) (hash(x)=27083417) +1152 train 7.125008 (lr=1.7500e-04) (hash(x)=20666288) +1153 train 7.220984 (lr=1.7500e-04) (hash(x)=22850633) +1154 train 7.346050 (lr=1.7500e-04) (hash(x)=24741872) +1155 train 7.692173 (lr=1.7500e-04) (hash(x)=28605205) +1156 train 7.178925 (lr=1.7500e-04) (hash(x)=22624463) +1157 train 7.436625 (lr=1.7500e-04) (hash(x)=24786468) +1158 train 7.157999 (lr=1.7500e-04) (hash(x)=21365399) +1159 train 7.379352 (lr=1.7500e-04) (hash(x)=23649001) +1160 train 7.481714 (lr=1.7500e-04) (hash(x)=28203982) +1161 train 7.390049 (lr=1.7500e-04) (hash(x)=26473994) +1162 train 7.019773 (lr=1.7500e-04) (hash(x)=19476441) +1163 train 7.341606 (lr=1.7500e-04) (hash(x)=25921700) +1164 train 7.145497 (lr=1.7500e-04) (hash(x)=23064343) +1165 train 7.318118 (lr=1.7500e-04) (hash(x)=24117626) +1166 train 7.249626 (lr=1.7500e-04) (hash(x)=21764556) +1167 train 8.118590 (lr=1.7500e-04) (hash(x)=31338300) +1168 train 7.573110 (lr=1.7500e-04) (hash(x)=27443187) +1169 train 6.988605 (lr=1.7500e-04) (hash(x)=21337692) +1170 train 7.514854 (lr=1.7500e-04) (hash(x)=27845383) +1171 train 7.347947 (lr=1.7500e-04) (hash(x)=23862328) +1172 train 7.525281 (lr=1.7500e-04) (hash(x)=23811014) +1173 train 7.482503 (lr=1.7500e-04) (hash(x)=24380098) +1174 train 7.184547 (lr=1.7500e-04) (hash(x)=22351136) +1175 train 7.432231 (lr=1.7500e-04) (hash(x)=30603174) +1176 train 7.491704 (lr=1.7500e-04) (hash(x)=27924596) +1177 train 7.901785 (lr=1.7500e-04) (hash(x)=30882548) +1178 train 7.322298 (lr=1.7500e-04) (hash(x)=22339464) +1179 train 7.106163 (lr=1.7500e-04) (hash(x)=23603806) +1180 train 7.511470 (lr=1.7500e-04) (hash(x)=24809041) +1181 train 7.310611 (lr=1.7500e-04) (hash(x)=24382442) +1182 train 7.311258 (lr=1.7500e-04) (hash(x)=23134077) +1183 train 7.326618 (lr=1.7500e-04) (hash(x)=24830965) +1184 train 7.420527 (lr=1.7500e-04) (hash(x)=25527259) +1185 train 7.448982 (lr=1.7500e-04) (hash(x)=25547480) +1186 train 7.326740 (lr=1.7500e-04) (hash(x)=24424314) +1187 train 7.703398 (lr=1.7500e-04) (hash(x)=32488729) +1188 train 7.597212 (lr=1.7500e-04) (hash(x)=31168462) +1189 train 7.861780 (lr=1.7500e-04) (hash(x)=31331643) +1190 train 7.532160 (lr=1.7500e-04) (hash(x)=28746633) +1191 train 7.492737 (lr=1.7500e-04) (hash(x)=27269893) +1192 train 7.289448 (lr=1.7500e-04) (hash(x)=23484031) +1193 train 7.303673 (lr=1.7500e-04) (hash(x)=23278725) +1194 train 7.431194 (lr=1.7500e-04) (hash(x)=25440745) +1195 train 7.462082 (lr=1.7500e-04) (hash(x)=25215077) +1196 train 7.546208 (lr=1.7500e-04) (hash(x)=28309266) +1197 train 7.218327 (lr=1.7500e-04) (hash(x)=22442404) +1198 train 7.287649 (lr=1.7500e-04) (hash(x)=20775262) +1199 train 7.370769 (lr=1.7500e-04) (hash(x)=24825041) +1200 val loss 7.3932 +1200 val perplexity 1624.8392 +1200 train 7.523193 (lr=1.7500e-04) (hash(x)=29016896) +1201 train 7.442453 (lr=1.7500e-04) (hash(x)=25590276) +1202 train 7.288124 (lr=1.7500e-04) (hash(x)=22816384) +1203 train 7.439584 (lr=1.7500e-04) (hash(x)=25893804) +1204 train 7.315941 (lr=1.7500e-04) (hash(x)=23983816) +1205 train 7.226734 (lr=1.7500e-04) (hash(x)=22222468) +1206 train 7.268478 (lr=1.7500e-04) (hash(x)=23039141) +1207 train 7.230505 (lr=1.7500e-04) (hash(x)=22724871) +1208 train 7.280513 (lr=1.7500e-04) (hash(x)=25253062) +1209 train 7.260653 (lr=1.7500e-04) (hash(x)=25140744) +1210 train 7.333684 (lr=1.7500e-04) (hash(x)=24717218) +1211 train 7.413999 (lr=1.7500e-04) (hash(x)=27317554) +1212 train 7.023259 (lr=1.7500e-04) (hash(x)=22013236) +1213 train 7.619514 (lr=1.7500e-04) (hash(x)=26692343) +1214 train 7.131438 (lr=1.7500e-04) (hash(x)=19859225) +1215 train 7.117337 (lr=1.7500e-04) (hash(x)=24683717) +1216 train 7.201903 (lr=1.7500e-04) (hash(x)=21932013) +1217 train 7.415630 (lr=1.7500e-04) (hash(x)=26849303) +1218 train 7.469846 (lr=1.7500e-04) (hash(x)=26458000) +1219 train 7.291989 (lr=1.7500e-04) (hash(x)=21584083) +1220 train 7.658814 (lr=1.7500e-04) (hash(x)=23598625) +1221 train 7.384983 (lr=1.7500e-04) (hash(x)=26059939) +1222 train 7.633907 (lr=1.7500e-04) (hash(x)=25481982) +1223 train 7.503301 (lr=1.7500e-04) (hash(x)=26190337) +1224 train 7.645667 (lr=1.7500e-04) (hash(x)=28767755) +1225 train 7.244440 (lr=1.7500e-04) (hash(x)=23663918) +1226 train 7.384106 (lr=1.7500e-04) (hash(x)=21293227) +1227 train 7.402731 (lr=1.7500e-04) (hash(x)=22249019) +1228 train 7.477695 (lr=1.7500e-04) (hash(x)=26886529) +1229 train 7.300840 (lr=1.7500e-04) (hash(x)=25779849) +1230 train 7.423257 (lr=1.7500e-04) (hash(x)=26228964) +1231 train 7.344022 (lr=1.7500e-04) (hash(x)=23086289) +1232 train 7.447383 (lr=1.7500e-04) (hash(x)=23198922) +1233 train 7.493884 (lr=1.7500e-04) (hash(x)=27523941) +1234 train 7.263604 (lr=1.7500e-04) (hash(x)=24293992) +1235 train 8.022964 (lr=1.7500e-04) (hash(x)=28047044) +1236 train 7.497148 (lr=1.7500e-04) (hash(x)=23688671) +1237 train 7.359643 (lr=1.7500e-04) (hash(x)=25125498) +1238 train 7.206716 (lr=1.7500e-04) (hash(x)=21977292) +1239 train 7.312901 (lr=1.7500e-04) (hash(x)=23593875) +1240 train 7.236798 (lr=1.7500e-04) (hash(x)=22659030) +1241 train 7.348396 (lr=1.7500e-04) (hash(x)=25117733) +1242 train 7.326705 (lr=1.7500e-04) (hash(x)=22322808) +1243 train 7.370485 (lr=1.7500e-04) (hash(x)=26059735) +1244 train 7.327001 (lr=1.7500e-04) (hash(x)=22485526) +1245 train 7.267011 (lr=1.7500e-04) (hash(x)=23028679) +1246 train 7.227756 (lr=1.7500e-04) (hash(x)=22906035) +1247 train 7.152873 (lr=1.7500e-04) (hash(x)=22414190) +1248 train 7.451969 (lr=1.7500e-04) (hash(x)=26229624) +1249 train 7.235071 (lr=1.7500e-04) (hash(x)=22223137) +1250 val loss 7.3629 +1250 val perplexity 1576.4230 +1250 train 7.470580 (lr=1.7500e-04) (hash(x)=24911520) +1251 train 7.672495 (lr=1.7500e-04) (hash(x)=24204591) +1252 train 7.232118 (lr=1.7500e-04) (hash(x)=24379601) +1253 train 7.201335 (lr=1.7500e-04) (hash(x)=22922475) +1254 train 7.230126 (lr=1.7500e-04) (hash(x)=23426249) +1255 train 7.507977 (lr=1.7500e-04) (hash(x)=26758114) +1256 train 7.165993 (lr=1.7500e-04) (hash(x)=24027111) +1257 train 7.343359 (lr=1.7500e-04) (hash(x)=25358064) +1258 train 7.239502 (lr=1.7500e-04) (hash(x)=22571285) +1259 train 7.595087 (lr=1.7500e-04) (hash(x)=20084233) +1260 train 7.450008 (lr=1.7500e-04) (hash(x)=18786581) +1261 train 7.350354 (lr=1.7500e-04) (hash(x)=26395104) +1262 train 7.271005 (lr=1.7500e-04) (hash(x)=24212567) +1263 train 7.057693 (lr=1.7500e-04) (hash(x)=21563184) +1264 train 7.392966 (lr=1.7500e-04) (hash(x)=26490150) +1265 train 7.431787 (lr=1.7500e-04) (hash(x)=25207694) +1266 train 7.324960 (lr=1.7500e-04) (hash(x)=23914544) +1267 train 7.314764 (lr=1.7500e-04) (hash(x)=23861489) +1268 train 7.778156 (lr=1.7500e-04) (hash(x)=30714540) +1269 train 7.275093 (lr=1.7500e-04) (hash(x)=23471007) +1270 train 7.293657 (lr=1.7500e-04) (hash(x)=23244293) +1271 train 7.265627 (lr=1.7500e-04) (hash(x)=19218470) +1272 train 7.488452 (lr=1.7500e-04) (hash(x)=26965136) +1273 train 7.263731 (lr=1.7500e-04) (hash(x)=22944035) +1274 train 7.277586 (lr=1.7500e-04) (hash(x)=22002714) +1275 train 7.558963 (lr=1.7500e-04) (hash(x)=28469562) +1276 train 7.636734 (lr=1.7500e-04) (hash(x)=26889992) +1277 train 7.644062 (lr=1.7500e-04) (hash(x)=26452814) +1278 train 7.430385 (lr=1.7500e-04) (hash(x)=28397488) +1279 train 7.516316 (lr=1.7500e-04) (hash(x)=25588469) +1280 train 7.410962 (lr=1.7500e-04) (hash(x)=24833139) +1281 train 7.289459 (lr=1.7500e-04) (hash(x)=24788298) +1282 train 7.511764 (lr=1.7500e-04) (hash(x)=24979383) +1283 train 7.522549 (lr=1.7500e-04) (hash(x)=25236367) +1284 train 7.335542 (lr=1.7500e-04) (hash(x)=22638257) +1285 train 7.186626 (lr=1.7500e-04) (hash(x)=23069067) +1286 train 7.364360 (lr=1.7500e-04) (hash(x)=25133239) +1287 train 7.959474 (lr=1.7500e-04) (hash(x)=30433767) +1288 train 7.938306 (lr=1.7500e-04) (hash(x)=34319079) +1289 train 7.792629 (lr=1.7500e-04) (hash(x)=29268881) +1290 train 7.408096 (lr=1.7500e-04) (hash(x)=24528336) +1291 train 7.570149 (lr=1.7500e-04) (hash(x)=26302626) +1292 train 7.562025 (lr=1.7500e-04) (hash(x)=25479111) +1293 train 7.746674 (lr=1.7500e-04) (hash(x)=24749682) +1294 train 7.386854 (lr=1.7500e-04) (hash(x)=24111393) +1295 train 7.028451 (lr=1.7500e-04) (hash(x)=17851621) +1296 train 7.326997 (lr=1.7500e-04) (hash(x)=26463070) +1297 train 7.350824 (lr=1.7500e-04) (hash(x)=25620741) +1298 train 7.995802 (lr=1.7500e-04) (hash(x)=28225676) +1299 train 7.789472 (lr=1.7500e-04) (hash(x)=27028191) +1300 val loss 7.3610 +1300 val perplexity 1573.3710 +1300 train 7.417120 (lr=1.7500e-04) (hash(x)=29006516) +1301 train 7.565976 (lr=1.7500e-04) (hash(x)=27590299) +1302 train 7.667032 (lr=1.7500e-04) (hash(x)=28678983) +1303 train 7.516284 (lr=1.7500e-04) (hash(x)=25183690) +1304 train 7.051884 (lr=1.7500e-04) (hash(x)=19918097) +1305 train 7.883333 (lr=1.7500e-04) (hash(x)=31114252) +1306 train 7.829399 (lr=1.7500e-04) (hash(x)=30913255) +1307 train 7.379737 (lr=1.7500e-04) (hash(x)=26182243) +1308 train 7.617993 (lr=1.7500e-04) (hash(x)=27420668) +1309 train 7.843630 (lr=1.7500e-04) (hash(x)=30419908) +1310 train 7.726415 (lr=1.7500e-04) (hash(x)=29002281) +1311 train 7.419689 (lr=1.7500e-04) (hash(x)=27040642) +1312 train 7.305043 (lr=1.7500e-04) (hash(x)=26929300) +1313 train 7.397373 (lr=1.7500e-04) (hash(x)=26240761) +1314 train 7.473741 (lr=1.7500e-04) (hash(x)=27161876) +1315 train 7.295921 (lr=1.7500e-04) (hash(x)=24489607) +1316 train 7.703777 (lr=1.7500e-04) (hash(x)=27040115) +1317 train 7.357866 (lr=1.7500e-04) (hash(x)=25012872) +1318 train 7.010936 (lr=1.7500e-04) (hash(x)=20894720) +1319 train 7.163681 (lr=1.7500e-04) (hash(x)=22183303) +1320 train 7.317933 (lr=1.7500e-04) (hash(x)=26291778) +1321 train 7.463560 (lr=1.7500e-04) (hash(x)=27682633) +1322 train 7.264885 (lr=1.7500e-04) (hash(x)=26490892) +1323 train 7.716894 (lr=1.7500e-04) (hash(x)=28844646) +1324 train 8.019637 (lr=1.7500e-04) (hash(x)=29545304) +1325 train 8.102023 (lr=1.7500e-04) (hash(x)=31082070) +1326 train 7.726995 (lr=1.7500e-04) (hash(x)=27486316) +1327 train 7.705677 (lr=1.7500e-04) (hash(x)=27537063) +1328 train 7.455927 (lr=1.7500e-04) (hash(x)=26955557) +1329 train 7.442758 (lr=1.7500e-04) (hash(x)=26125988) +1330 train 7.426987 (lr=1.7500e-04) (hash(x)=22800125) +1331 train 7.596239 (lr=1.7500e-04) (hash(x)=25446686) +1332 train 7.643372 (lr=1.7500e-04) (hash(x)=28743746) +1333 train 7.385675 (lr=1.7500e-04) (hash(x)=19819857) +1334 train 7.154812 (lr=1.7500e-04) (hash(x)=23518628) +1335 train 7.061156 (lr=1.7500e-04) (hash(x)=19492832) +1336 train 7.370027 (lr=1.7500e-04) (hash(x)=24627720) +1337 train 7.244400 (lr=1.7500e-04) (hash(x)=23741214) +1338 train 7.339942 (lr=1.7500e-04) (hash(x)=25837914) +1339 train 7.264287 (lr=1.7500e-04) (hash(x)=25484958) +1340 train 7.247210 (lr=1.7500e-04) (hash(x)=23671284) +1341 train 7.379173 (lr=1.7500e-04) (hash(x)=25525370) +1342 train 7.479085 (lr=1.7500e-04) (hash(x)=26585300) +1343 train 7.516936 (lr=1.7500e-04) (hash(x)=25951629) +1344 train 7.684914 (lr=1.7500e-04) (hash(x)=28743135) +1345 train 7.861269 (lr=1.7500e-04) (hash(x)=28557663) +1346 train 7.221191 (lr=1.7500e-04) (hash(x)=22642751) +1347 train 7.173201 (lr=1.7500e-04) (hash(x)=23462798) +1348 train 7.068636 (lr=1.7500e-04) (hash(x)=24292328) +1349 train 7.398488 (lr=1.7500e-04) (hash(x)=27320280) +1350 val loss 7.3809 +1350 val perplexity 1605.0795 +1350 train 7.548387 (lr=1.7500e-04) (hash(x)=27352812) +1351 train 7.393317 (lr=1.7500e-04) (hash(x)=22408682) +1352 train 7.306005 (lr=1.7500e-04) (hash(x)=23144732) +1353 train 7.180174 (lr=1.7500e-04) (hash(x)=22230799) +1354 train 7.563953 (lr=1.7500e-04) (hash(x)=29747687) +1355 train 7.750669 (lr=1.7500e-04) (hash(x)=31317970) +1356 train 7.012564 (lr=1.7500e-04) (hash(x)=20131758) +1357 train 7.406174 (lr=1.7500e-04) (hash(x)=24020983) +1358 train 7.225698 (lr=1.7500e-04) (hash(x)=23998051) +1359 train 7.331174 (lr=1.7500e-04) (hash(x)=27633457) +1360 train 7.056117 (lr=1.7500e-04) (hash(x)=20155247) +1361 train 7.341819 (lr=1.7500e-04) (hash(x)=23766987) +1362 train 7.222435 (lr=1.7500e-04) (hash(x)=25960383) +1363 train 7.484088 (lr=1.7500e-04) (hash(x)=23729283) +1364 train 7.592646 (lr=1.7500e-04) (hash(x)=27775445) +1365 train 7.488133 (lr=1.7500e-04) (hash(x)=25975834) +1366 train 7.298997 (lr=1.7500e-04) (hash(x)=22765259) +1367 train 7.513949 (lr=1.7500e-04) (hash(x)=27635080) +1368 train 7.277170 (lr=1.7500e-04) (hash(x)=23848542) +1369 train 7.430225 (lr=1.7500e-04) (hash(x)=27181156) +1370 train 7.559574 (lr=1.7500e-04) (hash(x)=28321340) +1371 train 7.329919 (lr=1.7500e-04) (hash(x)=25918780) +1372 train 7.347538 (lr=1.7500e-04) (hash(x)=23338297) +1373 train 7.471823 (lr=1.7500e-04) (hash(x)=22370417) +1374 train 7.436143 (lr=1.7500e-04) (hash(x)=24272668) +1375 train 7.093026 (lr=1.7500e-04) (hash(x)=22287596) +1376 train 7.253949 (lr=1.7500e-04) (hash(x)=25257403) +1377 train 7.217162 (lr=1.7500e-04) (hash(x)=21584419) +1378 train 7.375041 (lr=1.7500e-04) (hash(x)=25318823) +1379 train 7.168215 (lr=1.7500e-04) (hash(x)=22694623) +1380 train 7.318974 (lr=1.7500e-04) (hash(x)=23743406) +1381 train 7.545424 (lr=1.7500e-04) (hash(x)=30820846) +1382 train 8.054171 (lr=1.7500e-04) (hash(x)=34639557) +1383 train 7.949322 (lr=1.7500e-04) (hash(x)=35895440) +1384 train 7.379220 (lr=1.7500e-04) (hash(x)=26304839) +1385 train 7.555065 (lr=1.7500e-04) (hash(x)=27058657) +1386 train 7.398093 (lr=1.7500e-04) (hash(x)=25209529) +1387 train 7.330090 (lr=1.7500e-04) (hash(x)=24298886) +1388 train 7.444541 (lr=1.7500e-04) (hash(x)=26200200) +1389 train 7.342766 (lr=1.7500e-04) (hash(x)=27303061) +1390 train 7.410952 (lr=1.7500e-04) (hash(x)=26531628) +1391 train 7.452891 (lr=1.7500e-04) (hash(x)=25888847) +1392 train 7.585218 (lr=1.7500e-04) (hash(x)=28924067) +1393 train 7.048947 (lr=1.7500e-04) (hash(x)=21267641) +1394 train 7.608868 (lr=1.7500e-04) (hash(x)=29419156) +1395 train 7.875614 (lr=1.7500e-04) (hash(x)=30860646) +1396 train 7.382147 (lr=1.7500e-04) (hash(x)=25744434) +1397 train 7.349899 (lr=1.7500e-04) (hash(x)=26881837) +1398 train 7.333711 (lr=1.7500e-04) (hash(x)=26676176) +1399 train 7.537849 (lr=1.7500e-04) (hash(x)=26518800) +1400 val loss 7.3520 +1400 val perplexity 1559.3340 +1400 train 7.303977 (lr=1.7500e-04) (hash(x)=25043238) +1401 train 7.527761 (lr=1.7500e-04) (hash(x)=25863277) +1402 train 7.244863 (lr=1.7500e-04) (hash(x)=24073623) +1403 train 7.284935 (lr=1.7500e-04) (hash(x)=25385523) +1404 train 7.347269 (lr=1.7500e-04) (hash(x)=24958112) +1405 train 7.203738 (lr=1.7500e-04) (hash(x)=23362519) +1406 train 7.516771 (lr=1.7500e-04) (hash(x)=29262616) +1407 train 7.894544 (lr=1.7500e-04) (hash(x)=37519283) +1408 train 8.175967 (lr=1.7500e-04) (hash(x)=33716930) +1409 train 7.336887 (lr=1.7500e-04) (hash(x)=23392584) +1410 train 7.788545 (lr=1.7500e-04) (hash(x)=22877779) +1411 train 8.167500 (lr=1.7500e-04) (hash(x)=20564397) +1412 train 7.591496 (lr=1.7500e-04) (hash(x)=24366235) +1413 train 7.431278 (lr=1.7500e-04) (hash(x)=27065499) +1414 train 7.279687 (lr=1.7500e-04) (hash(x)=26844114) +1415 train 7.438741 (lr=1.7500e-04) (hash(x)=25141945) +1416 train 7.653418 (lr=1.7500e-04) (hash(x)=28813116) +1417 train 7.446187 (lr=1.7500e-04) (hash(x)=25466598) +1418 train 7.315639 (lr=1.7500e-04) (hash(x)=22800032) +1419 train 7.370293 (lr=1.7500e-04) (hash(x)=22717866) +1420 train 7.857353 (lr=1.7500e-04) (hash(x)=28040763) +1421 train 7.970152 (lr=1.7500e-04) (hash(x)=29648992) +1422 train 7.943717 (lr=1.7500e-04) (hash(x)=31747228) +1423 train 7.391821 (lr=1.7500e-04) (hash(x)=28527939) +1424 train 7.339507 (lr=1.7500e-04) (hash(x)=21563992) +1425 train 7.312215 (lr=1.7500e-04) (hash(x)=25134784) +1426 train 7.540369 (lr=1.7500e-04) (hash(x)=28442823) +1427 train 8.037374 (lr=1.7500e-04) (hash(x)=32757059) +1428 train 7.257806 (lr=1.7500e-04) (hash(x)=24110500) +1429 train 7.390213 (lr=1.7500e-04) (hash(x)=24145729) +1430 train 7.384559 (lr=1.7500e-04) (hash(x)=23541086) +1431 train 7.245332 (lr=1.7500e-04) (hash(x)=21942471) +1432 train 7.353683 (lr=1.7500e-04) (hash(x)=24736836) +1433 train 7.459464 (lr=1.7500e-04) (hash(x)=25325444) +1434 train 7.443590 (lr=1.7500e-04) (hash(x)=25188954) +1435 train 8.006314 (lr=1.7500e-04) (hash(x)=24247339) +1436 train 7.476158 (lr=1.7500e-04) (hash(x)=23773363) +1437 train 7.238979 (lr=1.7500e-04) (hash(x)=24142989) +1438 train 7.258788 (lr=1.7500e-04) (hash(x)=24226952) +1439 train 7.441247 (lr=1.7500e-04) (hash(x)=24955630) +1440 train 7.387848 (lr=1.7500e-04) (hash(x)=24563233) +1441 train 7.491901 (lr=1.7500e-04) (hash(x)=25491335) +1442 train 7.817451 (lr=1.7500e-04) (hash(x)=33253763) +1443 train 7.248422 (lr=1.7500e-04) (hash(x)=21368780) +1444 train 7.306142 (lr=1.7500e-04) (hash(x)=26615500) +1445 train 7.529674 (lr=1.7500e-04) (hash(x)=27146278) +1446 train 7.366986 (lr=1.7500e-04) (hash(x)=25904861) +1447 train 7.230727 (lr=1.7500e-04) (hash(x)=25541230) +1448 train 7.376901 (lr=1.7500e-04) (hash(x)=25434227) +1449 train 7.352278 (lr=1.7500e-04) (hash(x)=25375355) +1450 val loss 7.3296 +1450 val perplexity 1524.7360 +1450 train 7.175500 (lr=1.7500e-04) (hash(x)=21921129) +1451 train 7.184558 (lr=1.7500e-04) (hash(x)=23098806) +1452 train 7.243862 (lr=1.7500e-04) (hash(x)=22000544) +1453 train 7.168849 (lr=1.7500e-04) (hash(x)=22061174) +1454 train 7.235080 (lr=1.7500e-04) (hash(x)=24326286) +1455 train 7.218688 (lr=1.7500e-04) (hash(x)=23501481) +1456 train 7.401134 (lr=1.7500e-04) (hash(x)=26397938) +1457 train 7.402943 (lr=1.7500e-04) (hash(x)=24656430) +1458 train 7.128589 (lr=1.7500e-04) (hash(x)=23494971) +1459 train 7.237290 (lr=1.7500e-04) (hash(x)=23802681) +1460 train 7.251306 (lr=1.7500e-04) (hash(x)=21990153) +1461 train 7.279352 (lr=1.7500e-04) (hash(x)=23496118) +1462 train 7.267635 (lr=1.7500e-04) (hash(x)=24233822) +1463 train 7.581531 (lr=1.7500e-04) (hash(x)=22754988) +1464 train 7.289159 (lr=1.7500e-04) (hash(x)=23116635) +1465 train 7.005615 (lr=1.7500e-04) (hash(x)=21461650) +1466 train 7.124855 (lr=1.7500e-04) (hash(x)=22274473) +1467 train 7.155579 (lr=1.7500e-04) (hash(x)=22183009) +1468 train 7.413185 (lr=1.7500e-04) (hash(x)=24972441) +1469 train 7.190967 (lr=1.7500e-04) (hash(x)=22300616) +1470 train 6.953142 (lr=1.7500e-04) (hash(x)=21443060) +1471 train 7.224542 (lr=1.7500e-04) (hash(x)=23475070) +1472 train 7.141082 (lr=1.7500e-04) (hash(x)=22316810) +1473 train 7.575944 (lr=1.7500e-04) (hash(x)=24508407) +1474 train 7.546984 (lr=1.7500e-04) (hash(x)=24603557) +1475 train 7.217233 (lr=1.7500e-04) (hash(x)=23359061) +1476 train 7.279825 (lr=1.7500e-04) (hash(x)=22950844) +1477 train 7.342559 (lr=1.7500e-04) (hash(x)=22588667) +1478 train 7.458885 (lr=1.7500e-04) (hash(x)=26083526) +1479 train 7.354387 (lr=1.7500e-04) (hash(x)=23609959) +1480 train 7.352144 (lr=1.7500e-04) (hash(x)=24088171) +1481 train 7.370134 (lr=1.7500e-04) (hash(x)=25394852) +1482 train 7.312809 (lr=1.7500e-04) (hash(x)=24503040) +1483 train 7.066049 (lr=1.7500e-04) (hash(x)=22408449) +1484 train 7.326663 (lr=1.7500e-04) (hash(x)=25069325) +1485 train 7.361150 (lr=1.7500e-04) (hash(x)=26947398) +1486 train 6.853867 (lr=1.7500e-04) (hash(x)=17527161) +1487 train 7.253369 (lr=1.7500e-04) (hash(x)=23441847) +1488 train 7.261257 (lr=1.7500e-04) (hash(x)=25592861) +1489 train 7.168956 (lr=1.7500e-04) (hash(x)=23101350) +1490 train 7.157304 (lr=1.7500e-04) (hash(x)=24201380) +1491 train 7.253230 (lr=1.7500e-04) (hash(x)=23676365) +1492 train 7.333472 (lr=1.7500e-04) (hash(x)=26668088) +1493 train 7.463375 (lr=1.7500e-04) (hash(x)=26488811) +1494 train 7.465085 (lr=1.7500e-04) (hash(x)=27248109) +1495 train 7.500099 (lr=1.7500e-04) (hash(x)=23096292) +1496 train 7.426769 (lr=1.7500e-04) (hash(x)=22101981) +1497 train 7.566349 (lr=1.7500e-04) (hash(x)=24512380) +1498 train 7.379354 (lr=1.7500e-04) (hash(x)=25367738) +1499 train 7.353957 (lr=1.7500e-04) (hash(x)=27706294) +1500 val loss 7.3311 +1500 val perplexity 1527.1064 +1500 train 7.473871 (lr=1.7500e-04) (hash(x)=24154026) +1501 train 7.182040 (lr=1.7500e-04) (hash(x)=21892472) +1502 train 7.268299 (lr=1.7500e-04) (hash(x)=23662543) +1503 train 7.308718 (lr=1.7500e-04) (hash(x)=26171093) +1504 train 7.346469 (lr=1.7500e-04) (hash(x)=25974292) +1505 train 7.195487 (lr=1.7500e-04) (hash(x)=23191101) +1506 train 7.487012 (lr=1.7500e-04) (hash(x)=26498861) +1507 train 7.956646 (lr=1.7500e-04) (hash(x)=34946941) +1508 train 7.599607 (lr=1.7500e-04) (hash(x)=25442719) +1509 train 7.407360 (lr=1.7500e-04) (hash(x)=25569942) +1510 train 7.137920 (lr=1.7500e-04) (hash(x)=21265828) +1511 train 7.020232 (lr=1.7500e-04) (hash(x)=20060838) +1512 train 7.233985 (lr=1.7500e-04) (hash(x)=22588251) +1513 train 7.201869 (lr=1.7500e-04) (hash(x)=24581020) +1514 train 7.173662 (lr=1.7500e-04) (hash(x)=21882493) +1515 train 7.131261 (lr=1.7500e-04) (hash(x)=21591702) +1516 train 7.155966 (lr=1.7500e-04) (hash(x)=19813285) +1517 train 7.266328 (lr=1.7500e-04) (hash(x)=21870012) +1518 train 7.287453 (lr=1.7500e-04) (hash(x)=26895498) +1519 train 7.310840 (lr=1.7500e-04) (hash(x)=25451055) +1520 train 7.362557 (lr=1.7500e-04) (hash(x)=25395865) +1521 train 6.810439 (lr=1.7500e-04) (hash(x)=18989695) +1522 train 6.725877 (lr=1.7500e-04) (hash(x)=17040678) +1523 train 6.844818 (lr=1.7500e-04) (hash(x)=18691455) +1524 train 6.990345 (lr=1.7500e-04) (hash(x)=19017167) +1525 train 7.283134 (lr=1.7500e-04) (hash(x)=22406503) +1526 train 7.448666 (lr=1.7500e-04) (hash(x)=23036138) +1527 train 7.319931 (lr=1.7500e-04) (hash(x)=24934792) +1528 train 7.322438 (lr=1.7500e-04) (hash(x)=22843127) +1529 train 7.252594 (lr=1.7500e-04) (hash(x)=24249677) +1530 train 7.121236 (lr=1.7500e-04) (hash(x)=23318555) +1531 train 7.174961 (lr=1.7500e-04) (hash(x)=23864361) +1532 train 7.078195 (lr=1.7500e-04) (hash(x)=20242060) +1533 train 7.237161 (lr=1.7500e-04) (hash(x)=21549554) +1534 train 7.112878 (lr=1.7500e-04) (hash(x)=21642024) +1535 train 7.573946 (lr=1.7500e-04) (hash(x)=25367597) +1536 train 7.760617 (lr=1.7500e-04) (hash(x)=27224144) +1537 train 7.297863 (lr=1.7500e-04) (hash(x)=24409290) +1538 train 7.368278 (lr=1.7500e-04) (hash(x)=24987180) +1539 train 7.268311 (lr=1.7500e-04) (hash(x)=27016702) +1540 train 7.499991 (lr=1.7500e-04) (hash(x)=25819636) +1541 train 7.422706 (lr=1.7500e-04) (hash(x)=25520453) +1542 train 7.166272 (lr=1.7500e-04) (hash(x)=23580496) +1543 train 7.387938 (lr=1.7500e-04) (hash(x)=25022148) +1544 train 7.447291 (lr=1.7500e-04) (hash(x)=25447327) +1545 train 7.434069 (lr=1.7500e-04) (hash(x)=25010319) +1546 train 7.338991 (lr=1.7500e-04) (hash(x)=25511777) +1547 train 7.299947 (lr=1.7500e-04) (hash(x)=24459012) +1548 train 7.335483 (lr=1.7500e-04) (hash(x)=25082785) +1549 train 7.368166 (lr=1.7500e-04) (hash(x)=26528670) +1550 val loss 7.3383 +1550 val perplexity 1538.0323 +1550 train 7.355002 (lr=1.7500e-04) (hash(x)=26684367) +1551 train 7.313663 (lr=1.7500e-04) (hash(x)=25431365) +1552 train 7.290009 (lr=1.7500e-04) (hash(x)=24802747) +1553 train 7.124177 (lr=1.7500e-04) (hash(x)=24229522) +1554 train 7.352130 (lr=1.7500e-04) (hash(x)=24757176) +1555 train 7.485279 (lr=1.7500e-04) (hash(x)=25958785) +1556 train 7.473398 (lr=1.7500e-04) (hash(x)=26810735) +1557 train 7.121979 (lr=1.7500e-04) (hash(x)=22882640) +1558 train 7.647123 (lr=1.7500e-04) (hash(x)=27220057) +1559 train 7.926620 (lr=1.7500e-04) (hash(x)=29307788) +1560 train 7.301445 (lr=1.7500e-04) (hash(x)=25214030) +1561 train 7.100947 (lr=1.7500e-04) (hash(x)=23167825) +1562 train 7.202800 (lr=1.7500e-04) (hash(x)=24658511) +1563 train 7.363006 (lr=1.7500e-04) (hash(x)=24965435) +1564 train 7.118492 (lr=1.7500e-04) (hash(x)=23620579) +1565 train 7.109039 (lr=1.7500e-04) (hash(x)=23772949) +1566 train 7.309122 (lr=1.7500e-04) (hash(x)=23807939) +1567 train 7.492588 (lr=1.7500e-04) (hash(x)=25651929) +1568 train 7.379013 (lr=1.7500e-04) (hash(x)=25549933) +1569 train 7.157707 (lr=1.7500e-04) (hash(x)=23146724) +1570 train 7.222274 (lr=1.7500e-04) (hash(x)=24099275) +1571 train 7.403371 (lr=1.7500e-04) (hash(x)=28451031) +1572 train 7.521733 (lr=1.7500e-04) (hash(x)=25488511) +1573 train 7.294243 (lr=1.7500e-04) (hash(x)=23796771) +1574 train 7.302528 (lr=1.7500e-04) (hash(x)=22642764) +1575 train 7.418778 (lr=1.7500e-04) (hash(x)=26312387) +1576 train 7.218805 (lr=1.7500e-04) (hash(x)=22486223) +1577 train 7.226584 (lr=1.7500e-04) (hash(x)=21257377) +1578 train 7.389533 (lr=1.7500e-04) (hash(x)=24328365) +1579 train 7.496649 (lr=1.7500e-04) (hash(x)=25326650) +1580 train 7.411014 (lr=1.7500e-04) (hash(x)=26484837) +1581 train 7.184696 (lr=1.7500e-04) (hash(x)=24605603) +1582 train 7.276787 (lr=1.7500e-04) (hash(x)=24668537) +1583 train 7.206501 (lr=1.7500e-04) (hash(x)=23804913) +1584 train 7.455487 (lr=1.7500e-04) (hash(x)=23615391) +1585 train 7.400060 (lr=1.7500e-04) (hash(x)=24322926) +1586 train 7.220876 (lr=1.7500e-04) (hash(x)=19753104) +1587 train 7.641903 (lr=1.7500e-04) (hash(x)=25537529) +1588 train 7.037715 (lr=1.7500e-04) (hash(x)=22835476) +1589 train 7.229974 (lr=1.7500e-04) (hash(x)=25707197) +1590 train 7.205049 (lr=1.7500e-04) (hash(x)=24191203) +1591 train 7.462112 (lr=1.7500e-04) (hash(x)=26115519) +1592 train 7.353074 (lr=1.7500e-04) (hash(x)=25781547) +1593 train 7.206070 (lr=1.7500e-04) (hash(x)=24850654) +1594 train 7.118730 (lr=1.7500e-04) (hash(x)=23300928) +1595 train 7.345656 (lr=1.7500e-04) (hash(x)=25494804) +1596 train 7.395128 (lr=1.7500e-04) (hash(x)=28169410) +1597 train 7.145219 (lr=1.7500e-04) (hash(x)=21972022) +1598 train 7.645721 (lr=1.7500e-04) (hash(x)=27687290) +1599 train 7.517572 (lr=1.7500e-04) (hash(x)=23210747) +1600 val loss 7.3177 +1600 val perplexity 1506.6848 +1600 train 7.537033 (lr=1.7500e-04) (hash(x)=20362758) +1601 train 7.379106 (lr=1.7500e-04) (hash(x)=17064773) +1602 train 7.366935 (lr=1.7500e-04) (hash(x)=17173694) +1603 train 7.384905 (lr=1.7500e-04) (hash(x)=15717069) +1604 train 7.511611 (lr=1.7500e-04) (hash(x)=15117973) +1605 train 7.262343 (lr=1.7500e-04) (hash(x)=16189636) +1606 train 7.212141 (lr=1.7500e-04) (hash(x)=16552095) +1607 train 7.081215 (lr=1.7500e-04) (hash(x)=18463712) +1608 train 7.255269 (lr=1.7500e-04) (hash(x)=17572155) +1609 train 7.236829 (lr=1.7500e-04) (hash(x)=19970072) +1610 train 7.286327 (lr=1.7500e-04) (hash(x)=20463871) +1611 train 7.332588 (lr=1.7500e-04) (hash(x)=20705573) +1612 train 7.228568 (lr=1.7500e-04) (hash(x)=24441646) +1613 train 7.379080 (lr=1.7500e-04) (hash(x)=22913147) +1614 train 7.487595 (lr=1.7500e-04) (hash(x)=23081598) +1615 train 7.247196 (lr=1.7500e-04) (hash(x)=23245699) +1616 train 7.247745 (lr=1.7500e-04) (hash(x)=23003072) +1617 train 7.525005 (lr=1.7500e-04) (hash(x)=27121904) +1618 train 7.284557 (lr=1.7500e-04) (hash(x)=25092305) +1619 train 7.305719 (lr=1.7500e-04) (hash(x)=23444521) +1620 train 7.320690 (lr=1.7500e-04) (hash(x)=22130531) +1621 train 7.112874 (lr=1.7500e-04) (hash(x)=20917937) +1622 train 7.253011 (lr=1.7500e-04) (hash(x)=22526838) +1623 train 7.367971 (lr=1.7500e-04) (hash(x)=21770300) +1624 train 8.431434 (lr=1.7500e-04) (hash(x)=22333537) +1625 train 8.452890 (lr=1.7500e-04) (hash(x)=24642519) +1626 train 7.684105 (lr=1.7500e-04) (hash(x)=25199038) +1627 train 7.386024 (lr=1.7500e-04) (hash(x)=23334569) +1628 train 7.329906 (lr=1.7500e-04) (hash(x)=23785360) +1629 train 7.052162 (lr=1.7500e-04) (hash(x)=21796200) +1630 train 7.100349 (lr=1.7500e-04) (hash(x)=22389081) +1631 train 7.394821 (lr=1.7500e-04) (hash(x)=25387532) +1632 train 6.969037 (lr=1.7500e-04) (hash(x)=17247578) +1633 train 7.255301 (lr=1.7500e-04) (hash(x)=22203733) +1634 train 7.490755 (lr=1.7500e-04) (hash(x)=24387455) +1635 train 7.934138 (lr=1.7500e-04) (hash(x)=29466743) +1636 train 7.317472 (lr=1.7500e-04) (hash(x)=25354152) +1637 train 7.382728 (lr=1.7500e-04) (hash(x)=21756102) +1638 train 7.319530 (lr=1.7500e-04) (hash(x)=23544029) +1639 train 7.461070 (lr=1.7500e-04) (hash(x)=27718703) +1640 train 7.438875 (lr=1.7500e-04) (hash(x)=25697138) +1641 train 7.277030 (lr=1.7500e-04) (hash(x)=22978681) +1642 train 7.831118 (lr=1.7500e-04) (hash(x)=29527067) +1643 train 6.957982 (lr=1.7500e-04) (hash(x)=17631973) +1644 train 7.336188 (lr=1.7500e-04) (hash(x)=24860172) +1645 train 7.674645 (lr=1.7500e-04) (hash(x)=27947891) +1646 train 7.313074 (lr=1.7500e-04) (hash(x)=23819556) +1647 train 7.419769 (lr=1.7500e-04) (hash(x)=27661052) +1648 train 7.178288 (lr=1.7500e-04) (hash(x)=23014209) +1649 train 7.122237 (lr=1.7500e-04) (hash(x)=23061452) +1650 val loss 7.3803 +1650 val perplexity 1604.0090 +1650 train 7.267853 (lr=1.7500e-04) (hash(x)=21949051) +1651 train 7.301589 (lr=1.7500e-04) (hash(x)=22244096) +1652 train 7.277878 (lr=1.7500e-04) (hash(x)=25997585) +1653 train 7.364867 (lr=1.7500e-04) (hash(x)=25389713) +1654 train 7.360129 (lr=1.7500e-04) (hash(x)=24390520) +1655 train 7.544255 (lr=1.7500e-04) (hash(x)=26538928) +1656 train 7.471816 (lr=1.7500e-04) (hash(x)=28708088) +1657 train 7.651513 (lr=1.7500e-04) (hash(x)=25685569) +1658 train 7.142729 (lr=1.7500e-04) (hash(x)=22163531) +1659 train 7.330047 (lr=1.7500e-04) (hash(x)=26256802) +1660 train 7.745879 (lr=1.7500e-04) (hash(x)=30016026) +1661 train 7.385741 (lr=1.7500e-04) (hash(x)=24412323) +1662 train 7.430593 (lr=1.7500e-04) (hash(x)=24722307) +1663 train 7.318776 (lr=1.7500e-04) (hash(x)=21772654) +1664 train 7.211969 (lr=1.7500e-04) (hash(x)=24984527) +1665 train 7.296838 (lr=1.7500e-04) (hash(x)=25456825) +1666 train 7.693018 (lr=1.7500e-04) (hash(x)=24383976) +1667 train 7.635005 (lr=1.7500e-04) (hash(x)=25026277) +1668 train 7.533193 (lr=1.7500e-04) (hash(x)=28121715) +1669 train 7.552886 (lr=1.7500e-04) (hash(x)=26855439) +1670 train 7.627973 (lr=1.7500e-04) (hash(x)=33370924) +1671 train 7.486600 (lr=1.7500e-04) (hash(x)=26263254) +1672 train 7.881589 (lr=1.7500e-04) (hash(x)=29958158) +1673 train 7.205160 (lr=1.7500e-04) (hash(x)=21917396) +1674 train 7.325021 (lr=1.7500e-04) (hash(x)=24196295) +1675 train 7.356607 (lr=1.7500e-04) (hash(x)=24726314) +1676 train 7.145679 (lr=1.7500e-04) (hash(x)=22137742) +1677 train 7.295158 (lr=1.7500e-04) (hash(x)=24375100) +1678 train 7.254341 (lr=1.7500e-04) (hash(x)=23965039) +1679 train 7.298776 (lr=1.7500e-04) (hash(x)=23552356) +1680 train 7.272997 (lr=1.7500e-04) (hash(x)=26136969) +1681 train 7.508687 (lr=1.7500e-04) (hash(x)=25343112) +1682 train 7.200353 (lr=1.7500e-04) (hash(x)=22831508) +1683 train 7.441898 (lr=1.7500e-04) (hash(x)=26699819) +1684 train 7.585524 (lr=1.7500e-04) (hash(x)=25435504) +1685 train 7.740723 (lr=1.7500e-04) (hash(x)=25218858) +1686 train 8.378463 (lr=1.7500e-04) (hash(x)=25664448) +1687 train 7.389749 (lr=1.7500e-04) (hash(x)=22707141) +1688 train 7.562458 (lr=1.7500e-04) (hash(x)=28001383) +1689 train 7.759890 (lr=1.7500e-04) (hash(x)=29168269) +1690 train 7.748669 (lr=1.7500e-04) (hash(x)=29637522) +1691 train 7.777272 (lr=1.7500e-04) (hash(x)=25676149) +1692 train 7.172195 (lr=1.7500e-04) (hash(x)=20919831) +1693 train 7.346746 (lr=1.7500e-04) (hash(x)=24324401) +1694 train 7.461658 (lr=1.7500e-04) (hash(x)=26862625) +1695 train 7.835426 (lr=1.7500e-04) (hash(x)=34234481) +1696 train 7.396817 (lr=1.7500e-04) (hash(x)=27415195) +1697 train 7.239458 (lr=1.7500e-04) (hash(x)=24511386) +1698 train 7.400908 (lr=1.7500e-04) (hash(x)=26904299) +1699 train 7.232771 (lr=1.7500e-04) (hash(x)=25401624) +1700 val loss 7.3658 +1700 val perplexity 1581.0557 +1700 train 7.316087 (lr=1.7500e-04) (hash(x)=26498489) +1701 train 7.295554 (lr=1.7500e-04) (hash(x)=22340685) +1702 train 7.353828 (lr=1.7500e-04) (hash(x)=26396757) +1703 train 7.911847 (lr=1.7500e-04) (hash(x)=35008670) +1704 train 7.718174 (lr=1.7500e-04) (hash(x)=31782020) +1705 train 7.580162 (lr=1.7500e-04) (hash(x)=29662286) +1706 train 7.777986 (lr=1.7500e-04) (hash(x)=34215782) +1707 train 7.290337 (lr=1.7500e-04) (hash(x)=25682280) +1708 train 7.516811 (lr=1.7500e-04) (hash(x)=27109048) +1709 train 7.563741 (lr=1.7500e-04) (hash(x)=27686498) +1710 train 7.362608 (lr=1.7500e-04) (hash(x)=24247565) +1711 train 7.373761 (lr=1.7500e-04) (hash(x)=25891543) +1712 train 7.438916 (lr=1.7500e-04) (hash(x)=26436778) +1713 train 7.089149 (lr=1.7500e-04) (hash(x)=22538881) +1714 train 7.113422 (lr=1.7500e-04) (hash(x)=21993512) +1715 train 7.595585 (lr=1.7500e-04) (hash(x)=25962407) +1716 train 7.363503 (lr=1.7500e-04) (hash(x)=24130284) +1717 train 7.198396 (lr=1.7500e-04) (hash(x)=24819073) +1718 train 7.085295 (lr=1.7500e-04) (hash(x)=23496648) +1719 train 7.193332 (lr=1.7500e-04) (hash(x)=21971224) +1720 train 7.050096 (lr=1.7500e-04) (hash(x)=21498081) +1721 train 7.133302 (lr=1.7500e-04) (hash(x)=20951317) +1722 train 7.622163 (lr=1.7500e-04) (hash(x)=28848134) +1723 train 7.635811 (lr=1.7500e-04) (hash(x)=30838142) +1724 train 7.584501 (lr=1.7500e-04) (hash(x)=28844392) +1725 train 7.240121 (lr=1.7500e-04) (hash(x)=23102419) +1726 train 7.332239 (lr=1.7500e-04) (hash(x)=22374479) +1727 train 7.546482 (lr=1.7500e-04) (hash(x)=27312186) +1728 train 7.857713 (lr=1.7500e-04) (hash(x)=34362559) +1729 train 7.822499 (lr=1.7500e-04) (hash(x)=30920030) +1730 train 7.249776 (lr=1.7500e-04) (hash(x)=23684126) +1731 train 7.445339 (lr=1.7500e-04) (hash(x)=23657081) +1732 train 7.594978 (lr=1.7500e-04) (hash(x)=28463299) +1733 train 7.830449 (lr=1.7500e-04) (hash(x)=35351214) +1734 train 7.434758 (lr=1.7500e-04) (hash(x)=28855662) +1735 train 7.000812 (lr=1.7500e-04) (hash(x)=22163749) +1736 train 7.023740 (lr=1.7500e-04) (hash(x)=22024585) +1737 train 7.143346 (lr=1.7500e-04) (hash(x)=24629160) +1738 train 7.280914 (lr=1.7500e-04) (hash(x)=25220941) +1739 train 7.211946 (lr=1.7500e-04) (hash(x)=24829818) +1740 train 7.610675 (lr=1.7500e-04) (hash(x)=28453898) +1741 train 7.643696 (lr=1.7500e-04) (hash(x)=25424550) +1742 train 7.312712 (lr=1.7500e-04) (hash(x)=23437814) +1743 train 7.317732 (lr=1.7500e-04) (hash(x)=25942888) +1744 train 7.305118 (lr=1.7500e-04) (hash(x)=24503801) +1745 train 7.573457 (lr=1.7500e-04) (hash(x)=26418501) +1746 train 7.476086 (lr=1.7500e-04) (hash(x)=27177691) +1747 train 7.198990 (lr=1.7500e-04) (hash(x)=23785671) +1748 train 7.634095 (lr=1.7500e-04) (hash(x)=27362772) +1749 train 7.376743 (lr=1.7500e-04) (hash(x)=25097859) +1750 val loss 7.3488 +1750 val perplexity 1554.3171 +1750 train 7.319759 (lr=1.7500e-04) (hash(x)=24662466) +1751 train 7.209752 (lr=1.7500e-04) (hash(x)=25493916) +1752 train 7.302930 (lr=1.7500e-04) (hash(x)=24655868) +1753 train 7.612330 (lr=1.7500e-04) (hash(x)=19819210) +1754 train 7.154823 (lr=1.7500e-04) (hash(x)=21377155) +1755 train 8.044275 (lr=1.7500e-04) (hash(x)=28618702) +1756 train 7.930225 (lr=1.7500e-04) (hash(x)=27324953) +1757 train 7.641848 (lr=1.7500e-04) (hash(x)=29707907) +1758 train 7.419470 (lr=1.7500e-04) (hash(x)=24485921) +1759 train 7.487749 (lr=1.7500e-04) (hash(x)=24289951) +1760 train 7.167041 (lr=1.7500e-04) (hash(x)=22496716) +1761 train 7.325498 (lr=1.7500e-04) (hash(x)=25147026) +1762 train 7.392548 (lr=1.7500e-04) (hash(x)=26851828) +1763 train 7.361173 (lr=1.7500e-04) (hash(x)=26331486) +1764 train 7.229332 (lr=1.7500e-04) (hash(x)=24383054) +1765 train 7.457447 (lr=1.7500e-04) (hash(x)=25885126) +1766 train 7.389589 (lr=1.7500e-04) (hash(x)=25848470) +1767 train 7.188965 (lr=1.7500e-04) (hash(x)=23648671) +1768 train 7.148010 (lr=1.7500e-04) (hash(x)=23168674) +1769 train 7.029407 (lr=1.7500e-04) (hash(x)=20252079) +1770 train 7.236272 (lr=1.7500e-04) (hash(x)=23914287) +1771 train 7.550054 (lr=1.7500e-04) (hash(x)=27292797) +1772 train 6.787399 (lr=1.7500e-04) (hash(x)=16175151) +1773 train 6.899899 (lr=1.7500e-04) (hash(x)=18317379) +1774 train 7.262486 (lr=1.7500e-04) (hash(x)=24464271) +1775 train 7.229366 (lr=1.7500e-04) (hash(x)=24992055) +1776 train 7.883054 (lr=1.7500e-04) (hash(x)=26032451) +1777 train 7.633043 (lr=1.7500e-04) (hash(x)=24734221) +1778 train 7.608160 (lr=1.7500e-04) (hash(x)=25413430) +1779 train 7.488883 (lr=1.7500e-04) (hash(x)=24398330) +1780 train 7.355686 (lr=1.7500e-04) (hash(x)=24568049) +1781 train 7.323162 (lr=1.7500e-04) (hash(x)=23573984) +1782 train 7.498007 (lr=1.7500e-04) (hash(x)=27338410) +1783 train 7.441052 (lr=1.7500e-04) (hash(x)=26005549) +1784 train 7.322430 (lr=1.7500e-04) (hash(x)=24332331) +1785 train 7.123072 (lr=1.7500e-04) (hash(x)=22583878) +1786 train 7.266028 (lr=1.7500e-04) (hash(x)=24599113) +1787 train 7.701778 (lr=1.7500e-04) (hash(x)=30259737) +1788 train 7.490015 (lr=1.7500e-04) (hash(x)=26504237) +1789 train 7.355536 (lr=1.7500e-04) (hash(x)=25196470) +1790 train 7.280223 (lr=1.7500e-04) (hash(x)=23607871) +1791 train 7.197656 (lr=1.7500e-04) (hash(x)=21046554) +1792 train 7.462096 (lr=1.7500e-04) (hash(x)=27285635) +1793 train 7.407779 (lr=1.7500e-04) (hash(x)=25454371) +1794 train 7.443178 (lr=1.7500e-04) (hash(x)=26486575) +1795 train 6.926748 (lr=1.7500e-04) (hash(x)=18773877) +1796 train 7.124875 (lr=1.7500e-04) (hash(x)=22506761) +1797 train 7.314829 (lr=1.7500e-04) (hash(x)=24645168) +1798 train 7.404937 (lr=1.7500e-04) (hash(x)=25046236) +1799 train 7.462805 (lr=1.7500e-04) (hash(x)=26321539) +1800 val loss 7.3380 +1800 val perplexity 1537.5975 +1800 train 7.270461 (lr=1.7500e-04) (hash(x)=24602494) +1801 train 7.460840 (lr=1.7500e-04) (hash(x)=25722713) +1802 train 7.219043 (lr=1.7500e-04) (hash(x)=23711219) +1803 train 7.318668 (lr=1.7500e-04) (hash(x)=22850804) +1804 train 7.594442 (lr=1.7500e-04) (hash(x)=25829388) +1805 train 7.139122 (lr=1.7500e-04) (hash(x)=22503524) +1806 train 7.418091 (lr=1.7500e-04) (hash(x)=26669453) +1807 train 7.331113 (lr=1.7500e-04) (hash(x)=27807872) +1808 train 7.343381 (lr=1.7500e-04) (hash(x)=23543560) +1809 train 7.507942 (lr=1.7500e-04) (hash(x)=25845590) +1810 train 7.278590 (lr=1.7500e-04) (hash(x)=23026635) +1811 train 7.245347 (lr=1.7500e-04) (hash(x)=25545137) +1812 train 7.704586 (lr=1.7500e-04) (hash(x)=27746841) +1813 train 7.152308 (lr=1.7500e-04) (hash(x)=25471231) +1814 train 7.294228 (lr=1.7500e-04) (hash(x)=24333204) +1815 train 7.178035 (lr=1.7500e-04) (hash(x)=21555364) +1816 train 7.382717 (lr=1.7500e-04) (hash(x)=26317977) +1817 train 7.397457 (lr=1.7500e-04) (hash(x)=24474988) +1818 train 7.125200 (lr=1.7500e-04) (hash(x)=21975953) +1819 train 7.688639 (lr=1.7500e-04) (hash(x)=27243798) +1820 train 7.316934 (lr=1.7500e-04) (hash(x)=25097367) +1821 train 7.209252 (lr=1.7500e-04) (hash(x)=24419085) +1822 train 7.172397 (lr=1.7500e-04) (hash(x)=23058837) +1823 train 7.277808 (lr=1.7500e-04) (hash(x)=26325324) +1824 train 7.031337 (lr=1.7500e-04) (hash(x)=20581023) +1825 train 7.368942 (lr=1.7500e-04) (hash(x)=24822111) +1826 train 7.151462 (lr=1.7500e-04) (hash(x)=24336304) +1827 train 7.322826 (lr=1.7500e-04) (hash(x)=26228728) +1828 train 7.410986 (lr=1.7500e-04) (hash(x)=26445781) +1829 train 7.467038 (lr=1.7500e-04) (hash(x)=24707042) +1830 train 7.701603 (lr=1.7500e-04) (hash(x)=27882744) +1831 train 7.294226 (lr=1.7500e-04) (hash(x)=24956294) +1832 train 7.096831 (lr=1.7500e-04) (hash(x)=20984728) +1833 train 7.095966 (lr=1.7500e-04) (hash(x)=23424737) +1834 train 7.506299 (lr=1.7500e-04) (hash(x)=26207120) +1835 train 7.538092 (lr=1.7500e-04) (hash(x)=25592289) +1836 train 7.237345 (lr=1.7500e-04) (hash(x)=24326649) +1837 train 7.354973 (lr=1.7500e-04) (hash(x)=26826109) +1838 train 7.346889 (lr=1.7500e-04) (hash(x)=24759294) +1839 train 7.340201 (lr=1.7500e-04) (hash(x)=24429389) +1840 train 7.274936 (lr=1.7500e-04) (hash(x)=25537519) +1841 train 7.231167 (lr=1.7500e-04) (hash(x)=24747421) +1842 train 7.128320 (lr=1.7500e-04) (hash(x)=23079065) +1843 train 7.558147 (lr=1.7500e-04) (hash(x)=28733708) +1844 train 7.304203 (lr=1.7500e-04) (hash(x)=23937742) +1845 train 7.621191 (lr=1.7500e-04) (hash(x)=29704803) +1846 train 7.820114 (lr=1.7500e-04) (hash(x)=34617155) +1847 train 7.540696 (lr=1.7500e-04) (hash(x)=27929846) +1848 train 7.871506 (lr=1.7500e-04) (hash(x)=28280878) +1849 train 6.862770 (lr=1.7500e-04) (hash(x)=18961171) +1850 val loss 7.3347 +1850 val perplexity 1532.5740 +1850 train 7.444097 (lr=1.7500e-04) (hash(x)=27146015) +1851 train 7.189389 (lr=1.7500e-04) (hash(x)=22417476) +1852 train 7.352674 (lr=1.7500e-04) (hash(x)=24583152) +1853 train 7.363468 (lr=1.7500e-04) (hash(x)=26364120) +1854 train 7.567951 (lr=1.7500e-04) (hash(x)=25946767) +1855 train 7.390855 (lr=1.7500e-04) (hash(x)=25282897) +1856 train 7.369144 (lr=1.7500e-04) (hash(x)=25154557) +1857 train 7.075878 (lr=1.7500e-04) (hash(x)=22082503) +1858 train 7.108920 (lr=1.7500e-04) (hash(x)=23974606) +1859 train 7.262223 (lr=1.7500e-04) (hash(x)=22278062) +1860 train 7.149494 (lr=1.7500e-04) (hash(x)=19509639) +1861 train 7.456375 (lr=1.7500e-04) (hash(x)=24271468) +1862 train 7.040284 (lr=1.7500e-04) (hash(x)=21943809) +1863 train 7.348263 (lr=1.7500e-04) (hash(x)=26802508) +1864 train 7.969106 (lr=1.7500e-04) (hash(x)=34178409) +1865 train 8.109801 (lr=1.7500e-04) (hash(x)=33468379) +1866 train 7.158309 (lr=1.7500e-04) (hash(x)=22109262) +1867 train 6.933054 (lr=1.7500e-04) (hash(x)=22094832) +1868 train 7.149091 (lr=1.7500e-04) (hash(x)=24016953) +1869 train 7.420332 (lr=1.7500e-04) (hash(x)=26759850) +1870 train 7.261461 (lr=1.7500e-04) (hash(x)=23570779) +1871 train 7.650907 (lr=1.7500e-04) (hash(x)=28390416) +1872 train 7.668823 (lr=1.7500e-04) (hash(x)=26215770) +1873 train 7.502281 (lr=1.7500e-04) (hash(x)=22727956) +1874 train 7.331034 (lr=1.7500e-04) (hash(x)=21304587) +1875 train 7.636838 (lr=1.7500e-04) (hash(x)=26379331) +1876 train 7.719009 (lr=1.7500e-04) (hash(x)=25252419) +1877 train 7.535491 (lr=1.7500e-04) (hash(x)=25048158) +1878 train 7.503393 (lr=1.7500e-04) (hash(x)=23588991) +1879 train 7.525951 (lr=1.7500e-04) (hash(x)=26292451) +1880 train 7.412118 (lr=1.7500e-04) (hash(x)=23617086) +1881 train 7.301191 (lr=1.7500e-04) (hash(x)=23336031) +1882 train 7.303998 (lr=1.7500e-04) (hash(x)=19198742) +1883 train 8.033381 (lr=1.7500e-04) (hash(x)=26301866) +1884 train 8.069072 (lr=1.7500e-04) (hash(x)=30114703) +1885 train 7.586888 (lr=1.7500e-04) (hash(x)=26687040) +1886 train 7.403751 (lr=1.7500e-04) (hash(x)=25810717) +1887 train 7.210687 (lr=1.7500e-04) (hash(x)=22915344) +1888 train 7.505468 (lr=1.7500e-04) (hash(x)=27046189) +1889 train 7.061977 (lr=1.7500e-04) (hash(x)=19831900) +1890 train 7.450829 (lr=1.7500e-04) (hash(x)=27786987) +1891 train 7.340599 (lr=1.7500e-04) (hash(x)=25448318) +1892 train 7.339821 (lr=1.7500e-04) (hash(x)=25166953) +1893 train 7.307433 (lr=1.7500e-04) (hash(x)=24993116) +1894 train 7.377912 (lr=1.7500e-04) (hash(x)=25748002) +1895 train 7.570851 (lr=1.7500e-04) (hash(x)=24744383) +1896 train 7.328232 (lr=1.7500e-04) (hash(x)=25560120) +1897 train 7.165002 (lr=1.7500e-04) (hash(x)=23731849) +1898 train 7.174648 (lr=1.7500e-04) (hash(x)=24115851) +1899 train 7.178295 (lr=1.7500e-04) (hash(x)=22835201) +1900 val loss 7.3074 +1900 val perplexity 1491.2930 +1900 train 6.944365 (lr=1.7500e-04) (hash(x)=21927896) +1901 train 7.341442 (lr=1.7500e-04) (hash(x)=24652361) +1902 train 7.519481 (lr=1.7500e-04) (hash(x)=27332405) +1903 train 7.325695 (lr=1.7500e-04) (hash(x)=26284678) +1904 train 7.265434 (lr=1.7500e-04) (hash(x)=23441305) +1905 train 7.380344 (lr=1.7500e-04) (hash(x)=27522881) +1906 train 7.423058 (lr=1.7500e-04) (hash(x)=25521191) +1907 train 7.203799 (lr=1.7500e-04) (hash(x)=24745936) +1908 train 7.089283 (lr=1.7500e-04) (hash(x)=21653364) +1909 train 7.164178 (lr=1.7500e-04) (hash(x)=21973969) +1910 train 7.176019 (lr=1.7500e-04) (hash(x)=24318192) +1911 train 7.128364 (lr=1.7500e-04) (hash(x)=21654269) +1912 train 7.180438 (lr=1.7500e-04) (hash(x)=24142904) +1913 train 7.078772 (lr=1.7500e-04) (hash(x)=21708739) +1914 train 7.281607 (lr=1.7500e-04) (hash(x)=22937923) +1915 train 7.875669 (lr=1.7500e-04) (hash(x)=32387999) +1916 train 8.013471 (lr=1.7500e-04) (hash(x)=28958671) +1917 train 8.077368 (lr=1.7500e-04) (hash(x)=32662682) +1918 train 7.988037 (lr=1.7500e-04) (hash(x)=31364539) +1919 train 8.060367 (lr=1.7500e-04) (hash(x)=29466268) +1920 train 8.031554 (lr=1.7500e-04) (hash(x)=31407564) +1921 train 7.823752 (lr=1.7500e-04) (hash(x)=28372973) +1922 train 7.936067 (lr=1.7500e-04) (hash(x)=28620993) +1923 train 7.985387 (lr=1.7500e-04) (hash(x)=30736727) +1924 train 7.906896 (lr=1.7500e-04) (hash(x)=30370374) +1925 train 7.846779 (lr=1.7500e-04) (hash(x)=29935562) +1926 train 7.904350 (lr=1.7500e-04) (hash(x)=30528627) +1927 train 7.939964 (lr=1.7500e-04) (hash(x)=32616762) +1928 train 7.770645 (lr=1.7500e-04) (hash(x)=29150044) +1929 train 7.955017 (lr=1.7500e-04) (hash(x)=32861403) +1930 train 7.888030 (lr=1.7500e-04) (hash(x)=31053918) +1931 train 7.789752 (lr=1.7500e-04) (hash(x)=29358578) +1932 train 7.881705 (lr=1.7500e-04) (hash(x)=31521292) +1933 train 7.832271 (lr=1.7500e-04) (hash(x)=31218966) +1934 train 7.828701 (lr=1.7500e-04) (hash(x)=31811872) +1935 train 8.002141 (lr=1.7500e-04) (hash(x)=32201138) +1936 train 7.743344 (lr=1.7500e-04) (hash(x)=28631348) +1937 train 7.834999 (lr=1.7500e-04) (hash(x)=30545133) +1938 train 7.878894 (lr=1.7500e-04) (hash(x)=32136080) +1939 train 7.937080 (lr=1.7500e-04) (hash(x)=30041621) +1940 train 7.711414 (lr=1.7500e-04) (hash(x)=30537181) +1941 train 7.736793 (lr=1.7500e-04) (hash(x)=30371023) +1942 train 7.898599 (lr=1.7500e-04) (hash(x)=30734634) +1943 train 7.830726 (lr=1.7500e-04) (hash(x)=33683468) +1944 train 7.820149 (lr=1.7500e-04) (hash(x)=30472451) +1945 train 7.697403 (lr=1.7500e-04) (hash(x)=29809830) +1946 train 7.542487 (lr=1.7500e-04) (hash(x)=26077593) +1947 train 7.527275 (lr=1.7500e-04) (hash(x)=26837755) +1948 train 7.531320 (lr=1.7500e-04) (hash(x)=23910920) +1949 train 7.480501 (lr=1.7500e-04) (hash(x)=26084089) +1950 val loss 7.4399 +1950 val perplexity 1702.6017 +1950 train 7.623292 (lr=1.7500e-04) (hash(x)=26963533) +1951 train 7.492011 (lr=1.7500e-04) (hash(x)=27498125) +1952 train 7.638752 (lr=1.7500e-04) (hash(x)=29512508) +1953 train 7.970384 (lr=1.7500e-04) (hash(x)=34478395) +1954 train 7.599341 (lr=1.7500e-04) (hash(x)=25357046) +1955 train 7.380698 (lr=1.7500e-04) (hash(x)=22372507) +1956 train 7.309335 (lr=1.7500e-04) (hash(x)=24501779) +1957 train 7.408157 (lr=1.7500e-04) (hash(x)=25638879) +1958 train 7.235316 (lr=1.7500e-04) (hash(x)=24243109) +1959 train 7.202963 (lr=1.7500e-04) (hash(x)=25164318) +1960 train 7.368135 (lr=1.7500e-04) (hash(x)=24139533) +1961 train 7.372179 (lr=1.7500e-04) (hash(x)=27271900) +1962 train 7.215496 (lr=1.7500e-04) (hash(x)=24869232) +1963 train 7.405678 (lr=1.7500e-04) (hash(x)=26562947) +1964 train 7.299663 (lr=1.7500e-04) (hash(x)=26477326) +1965 train 7.402490 (lr=1.7500e-04) (hash(x)=24917192) +1966 train 7.196562 (lr=1.7500e-04) (hash(x)=23110147) +1967 train 7.273103 (lr=1.7500e-04) (hash(x)=25690221) +1968 train 7.713973 (lr=1.7500e-04) (hash(x)=26999273) +1969 train 7.335964 (lr=1.7500e-04) (hash(x)=24807841) +1970 train 7.245531 (lr=1.7500e-04) (hash(x)=23918831) +1971 train 7.194129 (lr=1.7500e-04) (hash(x)=21947305) +1972 train 7.267331 (lr=1.7500e-04) (hash(x)=22874486) +1973 train 7.206748 (lr=1.7500e-04) (hash(x)=22195089) +1974 train 7.318738 (lr=1.7500e-04) (hash(x)=25345359) +1975 train 7.445661 (lr=1.7500e-04) (hash(x)=29031550) +1976 train 7.407140 (lr=1.7500e-04) (hash(x)=29947423) +1977 train 7.624607 (lr=1.7500e-04) (hash(x)=29395823) +1978 train 7.387088 (lr=1.7500e-04) (hash(x)=26968216) +1979 train 7.425079 (lr=1.7500e-04) (hash(x)=26551589) +1980 train 7.391728 (lr=1.7500e-04) (hash(x)=25657210) +1981 train 7.356832 (lr=1.7500e-04) (hash(x)=23689487) +1982 train 7.462367 (lr=1.7500e-04) (hash(x)=25744240) +1983 train 7.466228 (lr=1.7500e-04) (hash(x)=24094093) +1984 train 7.178092 (lr=1.7500e-04) (hash(x)=21724872) +1985 train 7.213525 (lr=1.7500e-04) (hash(x)=24106453) +1986 train 7.257471 (lr=1.7500e-04) (hash(x)=25004577) +1987 train 7.270182 (lr=1.7500e-04) (hash(x)=23639076) +1988 train 7.549588 (lr=1.7500e-04) (hash(x)=29408797) +1989 train 7.206487 (lr=1.7500e-04) (hash(x)=25107314) +1990 train 9.774579 (lr=1.7500e-04) (hash(x)=49896019) +1991 train 11.149146 (lr=1.7500e-04) (hash(x)=61455960) +1992 train 10.798696 (lr=1.7500e-04) (hash(x)=63788199) +1993 train 10.689506 (lr=1.7500e-04) (hash(x)=63899424) +1994 train 10.265940 (lr=1.7500e-04) (hash(x)=66412689) +1995 train 9.804089 (lr=1.7500e-04) (hash(x)=65636572) +1996 train 9.873570 (lr=1.7500e-04) (hash(x)=69649789) +1997 train 9.663495 (lr=1.7500e-04) (hash(x)=71578682) +1998 train 9.260776 (lr=1.7500e-04) (hash(x)=58341730) +1999 train 9.260299 (lr=1.7500e-04) (hash(x)=61104710) +2000 val loss 8.6468 +2000 val perplexity 5691.6919 +2000 train 8.830493 (lr=1.7500e-04) (hash(x)=52865322) +2001 train 8.393127 (lr=1.7500e-04) (hash(x)=23633693) +2002 train 8.044871 (lr=1.7500e-04) (hash(x)=25297571) +2003 train 7.943780 (lr=1.7500e-04) (hash(x)=24123821) +2004 train 7.127225 (lr=1.7500e-04) (hash(x)=20161517) +2005 train 6.976158 (lr=1.7500e-04) (hash(x)=19919984) +2006 train 6.922025 (lr=1.7500e-04) (hash(x)=18626507) +2007 train 7.200261 (lr=1.7500e-04) (hash(x)=20881126) +2008 train 7.604597 (lr=1.7500e-04) (hash(x)=26261448) +2009 train 7.865365 (lr=1.7500e-04) (hash(x)=27528050) +2010 train 7.868439 (lr=1.7500e-04) (hash(x)=26692097) +2011 train 7.575240 (lr=1.7500e-04) (hash(x)=23209969) +2012 train 7.584776 (lr=1.7500e-04) (hash(x)=26083446) +2013 train 7.853149 (lr=1.7500e-04) (hash(x)=28426467) +2014 train 7.543990 (lr=1.7500e-04) (hash(x)=26158154) +2015 train 7.601660 (lr=1.7500e-04) (hash(x)=26920243) +2016 train 7.273458 (lr=1.7500e-04) (hash(x)=21365321) +2017 train 7.395119 (lr=1.7500e-04) (hash(x)=25730699) +2018 train 7.436672 (lr=1.7500e-04) (hash(x)=25177106) +2019 train 7.376264 (lr=1.7500e-04) (hash(x)=26127756) +2020 train 6.934791 (lr=1.7500e-04) (hash(x)=19770037) +2021 train 7.408004 (lr=1.7500e-04) (hash(x)=26479346) +2022 train 7.377118 (lr=1.7500e-04) (hash(x)=25967643) +2023 train 7.342088 (lr=1.7500e-04) (hash(x)=21970343) +2024 train 7.586356 (lr=1.7500e-04) (hash(x)=26449648) +2025 train 7.450166 (lr=1.7500e-04) (hash(x)=24874094) +2026 train 7.084155 (lr=1.7500e-04) (hash(x)=21399697) +2027 train 7.288152 (lr=1.7500e-04) (hash(x)=24097897) +2028 train 7.347682 (lr=1.7500e-04) (hash(x)=24453548) +2029 train 7.454784 (lr=1.7500e-04) (hash(x)=26692093) +2030 train 7.280405 (lr=1.7500e-04) (hash(x)=27217002) +2031 train 7.696445 (lr=1.7500e-04) (hash(x)=31676352) +2032 train 7.393970 (lr=1.7500e-04) (hash(x)=23396350) +2033 train 7.400692 (lr=1.7500e-04) (hash(x)=26245173) +2034 train 7.485184 (lr=1.7500e-04) (hash(x)=24821033) +2035 train 7.447427 (lr=1.7500e-04) (hash(x)=23908053) +2036 train 7.190870 (lr=1.7500e-04) (hash(x)=23469373) +2037 train 7.240010 (lr=1.7500e-04) (hash(x)=24102198) +2038 train 7.271240 (lr=1.7500e-04) (hash(x)=24712135) +2039 train 7.537055 (lr=1.7500e-04) (hash(x)=25600562) +2040 train 7.456625 (lr=1.7500e-04) (hash(x)=23193393) +2041 train 7.426126 (lr=1.7500e-04) (hash(x)=24776954) +2042 train 7.590935 (lr=1.7500e-04) (hash(x)=28066546) +2043 train 7.110970 (lr=1.7500e-04) (hash(x)=23549168) +2044 train 7.179700 (lr=1.7500e-04) (hash(x)=22681487) +2045 train 7.392984 (lr=1.7500e-04) (hash(x)=26663184) +2046 train 7.344072 (lr=1.7500e-04) (hash(x)=23320809) +2047 train 7.212723 (lr=1.7500e-04) (hash(x)=22022924) +2048 train 7.553658 (lr=1.7500e-04) (hash(x)=27960930) +2049 train 7.379327 (lr=1.7500e-04) (hash(x)=24899178) +2050 val loss 7.4015 +2050 val perplexity 1638.4196 +2050 train 7.316159 (lr=1.7500e-04) (hash(x)=24450711) +2051 train 7.286572 (lr=1.7500e-04) (hash(x)=23294980) +2052 train 7.171543 (lr=1.7500e-04) (hash(x)=23243665) +2053 train 7.060604 (lr=1.7500e-04) (hash(x)=21004461) +2054 train 7.380492 (lr=1.7500e-04) (hash(x)=24493583) +2055 train 7.293495 (lr=1.7500e-04) (hash(x)=22777085) +2056 train 7.218324 (lr=1.7500e-04) (hash(x)=25169889) +2057 train 7.922966 (lr=1.7500e-04) (hash(x)=28395880) +2058 train 7.855063 (lr=1.7500e-04) (hash(x)=29603726) +2059 train 7.447112 (lr=1.7500e-04) (hash(x)=26271115) +2060 train 7.422517 (lr=1.7500e-04) (hash(x)=25616212) +2061 train 7.541148 (lr=1.7500e-04) (hash(x)=26398325) +2062 train 7.239896 (lr=1.7500e-04) (hash(x)=23836586) +2063 train 7.161067 (lr=1.7500e-04) (hash(x)=21727744) +2064 train 7.362349 (lr=1.7500e-04) (hash(x)=25183195) +2065 train 7.489775 (lr=1.7500e-04) (hash(x)=27108132) +2066 train 7.202264 (lr=1.7500e-04) (hash(x)=20987812) +2067 train 7.503789 (lr=1.7500e-04) (hash(x)=22729318) +2068 train 7.269394 (lr=1.7500e-04) (hash(x)=23129709) +2069 train 7.842250 (lr=1.7500e-04) (hash(x)=32820084) +2070 train 7.930004 (lr=1.7500e-04) (hash(x)=33763489) +2071 train 7.295062 (lr=1.7500e-04) (hash(x)=20701998) +2072 train 7.551056 (lr=1.7500e-04) (hash(x)=27765988) +2073 train 7.254158 (lr=1.7500e-04) (hash(x)=24157446) +2074 train 7.200157 (lr=1.7500e-04) (hash(x)=22014978) +2075 train 7.752746 (lr=1.7500e-04) (hash(x)=27928398) +2076 train 7.585591 (lr=1.7500e-04) (hash(x)=27880142) +2077 train 7.895828 (lr=1.7500e-04) (hash(x)=34991795) +2078 train 7.457340 (lr=1.7500e-04) (hash(x)=25944128) +2079 train 7.178377 (lr=1.7500e-04) (hash(x)=20863982) +2080 train 7.578570 (lr=1.7500e-04) (hash(x)=28036097) +2081 train 7.589363 (lr=1.7500e-04) (hash(x)=25813615) +2082 train 7.050362 (lr=1.7500e-04) (hash(x)=22862316) +2083 train 7.096770 (lr=1.7500e-04) (hash(x)=22827054) +2084 train 7.162309 (lr=1.7500e-04) (hash(x)=23996531) +2085 train 7.302302 (lr=1.7500e-04) (hash(x)=25756087) +2086 train 7.354703 (lr=1.7500e-04) (hash(x)=23165889) +2087 train 7.547678 (lr=1.7500e-04) (hash(x)=25084926) +2088 train 7.397739 (lr=1.7500e-04) (hash(x)=26063862) +2089 train 7.409086 (lr=1.7500e-04) (hash(x)=27843638) +2090 train 7.682061 (lr=1.7500e-04) (hash(x)=27375554) +2091 train 7.408821 (lr=1.7500e-04) (hash(x)=25540961) +2092 train 7.109979 (lr=1.7500e-04) (hash(x)=22933785) +2093 train 7.293989 (lr=1.7500e-04) (hash(x)=23996956) +2094 train 7.040040 (lr=1.7500e-04) (hash(x)=22915854) +2095 train 7.310557 (lr=1.7500e-04) (hash(x)=24412897) +2096 train 7.334254 (lr=1.7500e-04) (hash(x)=25152336) +2097 train 7.628688 (lr=1.7500e-04) (hash(x)=29525589) +2098 train 7.465195 (lr=1.7500e-04) (hash(x)=26435656) +2099 train 7.347705 (lr=1.7500e-04) (hash(x)=26269869) +2100 val loss 7.3066 +2100 val perplexity 1490.0668 +2100 train 7.111169 (lr=1.7500e-04) (hash(x)=23856783) +2101 train 7.406784 (lr=1.7500e-04) (hash(x)=26039611) +2102 train 7.141496 (lr=1.7500e-04) (hash(x)=25048861) +2103 train 7.221354 (lr=1.7500e-04) (hash(x)=25434913) +2104 train 7.447495 (lr=1.7500e-04) (hash(x)=24203891) +2105 train 7.288581 (lr=1.7500e-04) (hash(x)=26016998) +2106 train 7.423377 (lr=1.7500e-04) (hash(x)=23986767) +2107 train 7.316458 (lr=1.7500e-04) (hash(x)=25157653) +2108 train 7.461399 (lr=1.7500e-04) (hash(x)=30193751) +2109 train 7.258840 (lr=1.7500e-04) (hash(x)=22630574) +2110 train 7.167161 (lr=1.7500e-04) (hash(x)=23475467) +2111 train 7.490476 (lr=1.7500e-04) (hash(x)=26302544) +2112 train 7.252355 (lr=1.7500e-04) (hash(x)=21276592) +2113 train 7.484752 (lr=1.7500e-04) (hash(x)=27566393) +2114 train 7.251357 (lr=1.7500e-04) (hash(x)=25028015) +2115 train 7.019714 (lr=1.7500e-04) (hash(x)=22010703) +2116 train 7.386295 (lr=1.7500e-04) (hash(x)=23711709) +2117 train 7.430912 (lr=1.7500e-04) (hash(x)=26105026) +2118 train 7.809781 (lr=1.7500e-04) (hash(x)=34433894) +2119 train 7.851500 (lr=1.7500e-04) (hash(x)=34976197) +2120 train 7.349521 (lr=1.7500e-04) (hash(x)=27690727) +2121 train 7.244978 (lr=1.7500e-04) (hash(x)=24368234) +2122 train 7.208568 (lr=1.7500e-04) (hash(x)=25095726) +2123 train 7.391613 (lr=1.7500e-04) (hash(x)=28248301) +2124 train 7.155291 (lr=1.7500e-04) (hash(x)=23322302) +2125 train 7.577949 (lr=1.7500e-04) (hash(x)=26416200) +2126 train 7.209534 (lr=1.7500e-04) (hash(x)=26577567) +2127 train 7.300620 (lr=1.7500e-04) (hash(x)=23870805) +2128 train 7.216116 (lr=1.7500e-04) (hash(x)=25440544) +2129 train 7.340605 (lr=1.7500e-04) (hash(x)=25795021) +2130 train 7.219792 (lr=1.7500e-04) (hash(x)=20896402) +2131 train 7.262521 (lr=1.7500e-04) (hash(x)=24457252) +2132 train 7.288944 (lr=1.7500e-04) (hash(x)=25926760) +2133 train 7.151341 (lr=1.7500e-04) (hash(x)=23503725) +2134 train 7.701530 (lr=1.7500e-04) (hash(x)=28728828) +2135 train 7.218807 (lr=1.7500e-04) (hash(x)=25041103) +2136 train 7.265305 (lr=1.7500e-04) (hash(x)=22863770) +2137 train 7.112365 (lr=1.7500e-04) (hash(x)=23037755) +2138 train 7.311659 (lr=1.7500e-04) (hash(x)=25848413) +2139 train 7.376977 (lr=1.7500e-04) (hash(x)=25998487) +2140 train 7.212738 (lr=1.7500e-04) (hash(x)=22754440) +2141 train 7.478342 (lr=1.7500e-04) (hash(x)=27705382) +2142 train 7.485925 (lr=1.7500e-04) (hash(x)=27629095) +2143 train 7.393333 (lr=1.7500e-04) (hash(x)=26041745) +2144 train 7.106091 (lr=1.7500e-04) (hash(x)=21909712) +2145 train 7.317871 (lr=1.7500e-04) (hash(x)=24353905) +2146 train 7.265789 (lr=1.7500e-04) (hash(x)=24482587) +2147 train 7.407897 (lr=1.7500e-04) (hash(x)=27249810) +2148 train 7.527378 (lr=1.7500e-04) (hash(x)=26709938) +2149 train 7.181614 (lr=1.7500e-04) (hash(x)=23831457) +2150 val loss 7.2885 +2150 val perplexity 1463.3088 +2150 train 7.519574 (lr=1.7500e-04) (hash(x)=29776243) +2151 train 7.002338 (lr=1.7500e-04) (hash(x)=24068619) +2152 train 7.264630 (lr=1.7500e-04) (hash(x)=22208671) +2153 train 7.396356 (lr=1.7500e-04) (hash(x)=26680905) +2154 train 7.256824 (lr=1.7500e-04) (hash(x)=23567808) +2155 train 7.530376 (lr=1.7500e-04) (hash(x)=26359528) +2156 train 7.287215 (lr=1.7500e-04) (hash(x)=23787652) +2157 train 7.558969 (lr=1.7500e-04) (hash(x)=28347177) +2158 train 7.231899 (lr=1.7500e-04) (hash(x)=25266519) +2159 train 7.173262 (lr=1.7500e-04) (hash(x)=25441262) +2160 train 7.119827 (lr=1.7500e-04) (hash(x)=23959943) +2161 train 7.366194 (lr=1.7500e-04) (hash(x)=27888093) +2162 train 7.224178 (lr=1.7500e-04) (hash(x)=25547833) +2163 train 7.179160 (lr=1.7500e-04) (hash(x)=24413659) +2164 train 8.577232 (lr=1.7500e-04) (hash(x)=34397626) +2165 train 7.172322 (lr=1.7500e-04) (hash(x)=21159323) +2166 train 7.385404 (lr=1.7500e-04) (hash(x)=25360269) +2167 train 7.361721 (lr=1.7500e-04) (hash(x)=29181867) +2168 train 7.209741 (lr=1.7500e-04) (hash(x)=22501613) +2169 train 7.276701 (lr=1.7500e-04) (hash(x)=26469077) +2170 train 7.244046 (lr=1.7500e-04) (hash(x)=26665118) +2171 train 7.884098 (lr=1.7500e-04) (hash(x)=31551575) +2172 train 7.189554 (lr=1.7500e-04) (hash(x)=24803935) +2173 train 7.103595 (lr=1.7500e-04) (hash(x)=20896465) +2174 train 7.542726 (lr=1.7500e-04) (hash(x)=25702284) +2175 train 7.596431 (lr=1.7500e-04) (hash(x)=27093757) +2176 train 7.284730 (lr=1.7500e-04) (hash(x)=26024255) +2177 train 7.474796 (lr=1.7500e-04) (hash(x)=26443521) +2178 train 7.411960 (lr=1.7500e-04) (hash(x)=25478467) +2179 train 7.250123 (lr=1.7500e-04) (hash(x)=23624298) +2180 train 7.371652 (lr=1.7500e-04) (hash(x)=27304178) +2181 train 7.163893 (lr=1.7500e-04) (hash(x)=23016570) +2182 train 7.104683 (lr=1.7500e-04) (hash(x)=21073756) +2183 train 7.187404 (lr=1.7500e-04) (hash(x)=25150275) +2184 train 6.982448 (lr=1.7500e-04) (hash(x)=21004187) +2185 train 7.240843 (lr=1.7500e-04) (hash(x)=25876062) +2186 train 7.199790 (lr=1.7500e-04) (hash(x)=24221275) +2187 train 7.452943 (lr=1.7500e-04) (hash(x)=26239886) +2188 train 7.133185 (lr=1.7500e-04) (hash(x)=23299261) +2189 train 7.607237 (lr=1.7500e-04) (hash(x)=31024703) +2190 train 7.744153 (lr=1.7500e-04) (hash(x)=30084774) +2191 train 8.033092 (lr=1.7500e-04) (hash(x)=33457102) +2192 train 7.257449 (lr=1.7500e-04) (hash(x)=22423723) +2193 train 7.329271 (lr=1.7500e-04) (hash(x)=21989055) +2194 train 7.251949 (lr=1.7500e-04) (hash(x)=23286499) +2195 train 7.162632 (lr=1.7500e-04) (hash(x)=17499738) +2196 train 7.232057 (lr=1.7500e-04) (hash(x)=25329557) +2197 train 7.136694 (lr=1.7500e-04) (hash(x)=24195578) +2198 train 7.386003 (lr=1.7500e-04) (hash(x)=26646383) +2199 train 7.264902 (lr=1.7500e-04) (hash(x)=25755322) +2200 val loss 7.2765 +2200 val perplexity 1445.9767 +2200 train 7.286890 (lr=1.7500e-04) (hash(x)=27592223) +2201 train 7.512169 (lr=1.7500e-04) (hash(x)=26164625) +2202 train 7.368437 (lr=1.7500e-04) (hash(x)=21856341) +2203 train 7.246934 (lr=1.7500e-04) (hash(x)=23722795) +2204 train 7.336701 (lr=1.7500e-04) (hash(x)=25409645) +2205 train 7.270329 (lr=1.7500e-04) (hash(x)=23415339) +2206 train 7.256288 (lr=1.7500e-04) (hash(x)=24147928) +2207 train 7.155480 (lr=1.7500e-04) (hash(x)=23630794) +2208 train 7.247758 (lr=1.7500e-04) (hash(x)=27361452) +2209 train 7.244508 (lr=1.7500e-04) (hash(x)=25632158) +2210 train 7.123106 (lr=1.7500e-04) (hash(x)=21159789) +2211 train 7.211477 (lr=1.7500e-04) (hash(x)=23374168) +2212 train 7.289861 (lr=1.7500e-04) (hash(x)=24844739) +2213 train 7.192728 (lr=1.7500e-04) (hash(x)=23461285) +2214 train 7.251974 (lr=1.7500e-04) (hash(x)=27958481) +2215 train 7.137694 (lr=1.7500e-04) (hash(x)=25167987) +2216 train 7.339910 (lr=1.7500e-04) (hash(x)=22873204) +2217 train 7.902002 (lr=1.7500e-04) (hash(x)=31038116) +2218 train 7.377885 (lr=1.7500e-04) (hash(x)=28883155) +2219 train 7.256931 (lr=1.7500e-04) (hash(x)=30941010) +2220 train 7.248773 (lr=1.7500e-04) (hash(x)=24947521) +2221 train 7.290032 (lr=1.7500e-04) (hash(x)=22703293) +2222 train 7.258027 (lr=1.7500e-04) (hash(x)=23976007) +2223 train 7.193825 (lr=1.7500e-04) (hash(x)=24043224) +2224 train 7.156845 (lr=1.7500e-04) (hash(x)=23981093) +2225 train 7.251718 (lr=1.7500e-04) (hash(x)=26445994) +2226 train 7.527330 (lr=1.7500e-04) (hash(x)=27252393) +2227 train 7.489008 (lr=1.7500e-04) (hash(x)=29736627) +2228 train 7.441109 (lr=1.7500e-04) (hash(x)=24698933) +2229 train 7.097026 (lr=1.7500e-04) (hash(x)=24357840) +2230 train 7.301624 (lr=1.7500e-04) (hash(x)=25384498) +2231 train 7.418012 (lr=1.7500e-04) (hash(x)=24665411) +2232 train 7.287817 (lr=1.7500e-04) (hash(x)=24646352) +2233 train 7.272420 (lr=1.7500e-04) (hash(x)=25670741) +2234 train 7.357971 (lr=1.7500e-04) (hash(x)=26648242) +2235 train 7.581892 (lr=1.7500e-04) (hash(x)=27916043) +2236 train 7.279921 (lr=1.7500e-04) (hash(x)=25963100) +2237 train 7.356370 (lr=1.7500e-04) (hash(x)=27357379) +2238 train 7.211018 (lr=1.7500e-04) (hash(x)=21852360) +2239 train 7.202614 (lr=1.7500e-04) (hash(x)=17321657) +2240 train 7.190797 (lr=1.7500e-04) (hash(x)=18446645) +2241 train 6.947011 (lr=1.7500e-04) (hash(x)=17550988) +2242 train 7.254910 (lr=1.7500e-04) (hash(x)=27052347) +2243 train 7.141303 (lr=1.7500e-04) (hash(x)=23829833) +2244 train 7.350319 (lr=1.7500e-04) (hash(x)=27267264) +2245 train 7.522014 (lr=1.7500e-04) (hash(x)=24673611) +2246 train 7.485802 (lr=1.7500e-04) (hash(x)=25248507) +2247 train 7.749859 (lr=1.7500e-04) (hash(x)=27932591) +2248 train 7.574386 (lr=1.7500e-04) (hash(x)=26078877) +2249 train 7.643029 (lr=1.7500e-04) (hash(x)=26067367) +2250 val loss 7.3080 +2250 val perplexity 1492.1600 +2250 train 7.576271 (lr=1.7500e-04) (hash(x)=29143527) +2251 train 7.545101 (lr=1.7500e-04) (hash(x)=28206079) +2252 train 8.073674 (lr=1.7500e-04) (hash(x)=28894494) +2253 train 7.721335 (lr=1.7500e-04) (hash(x)=27977422) +2254 train 7.393356 (lr=1.7500e-04) (hash(x)=26446420) +2255 train 7.551163 (lr=1.7500e-04) (hash(x)=29447954) +2256 train 7.452521 (lr=1.7500e-04) (hash(x)=22181789) +2257 train 7.524316 (lr=1.7500e-04) (hash(x)=24976337) +2258 train 7.434219 (lr=1.7500e-04) (hash(x)=23277532) +2259 train 7.582323 (lr=1.7500e-04) (hash(x)=25935364) +2260 train 7.711337 (lr=1.7500e-04) (hash(x)=26988889) +2261 train 7.518442 (lr=1.7500e-04) (hash(x)=26887303) +2262 train 7.472085 (lr=1.7500e-04) (hash(x)=25021426) +2263 train 7.356729 (lr=1.7500e-04) (hash(x)=24621816) +2264 train 7.190927 (lr=1.7500e-04) (hash(x)=22132007) +2265 train 7.131856 (lr=1.7500e-04) (hash(x)=22648602) +2266 train 7.378648 (lr=1.7500e-04) (hash(x)=23132242) +2267 train 7.396553 (lr=1.7500e-04) (hash(x)=24070405) +2268 train 7.057586 (lr=1.7500e-04) (hash(x)=21412906) +2269 train 7.708394 (lr=1.7500e-04) (hash(x)=27547292) +2270 train 7.462657 (lr=1.7500e-04) (hash(x)=27740500) +2271 train 7.186728 (lr=1.7500e-04) (hash(x)=24682294) +2272 train 7.599744 (lr=1.7500e-04) (hash(x)=27969424) +2273 train 7.302660 (lr=1.7500e-04) (hash(x)=22172182) +2274 train 7.312303 (lr=1.7500e-04) (hash(x)=26485905) +2275 train 7.183942 (lr=1.7500e-04) (hash(x)=24050209) +2276 train 7.395861 (lr=1.7500e-04) (hash(x)=28802650) +2277 train 7.172185 (lr=1.7500e-04) (hash(x)=23644616) +2278 train 7.409393 (lr=1.7500e-04) (hash(x)=25409768) +2279 train 7.532014 (lr=1.7500e-04) (hash(x)=28057095) +2280 train 8.072878 (lr=1.7500e-04) (hash(x)=31689723) +2281 train 7.244755 (lr=1.7500e-04) (hash(x)=22252427) +2282 train 7.455214 (lr=1.7500e-04) (hash(x)=24142092) +2283 train 7.431039 (lr=1.7500e-04) (hash(x)=22523232) +2284 train 7.597122 (lr=1.7500e-04) (hash(x)=26017294) +2285 train 7.438589 (lr=1.7500e-04) (hash(x)=25025388) +2286 train 7.214348 (lr=1.7500e-04) (hash(x)=23819479) +2287 train 7.420719 (lr=1.7500e-04) (hash(x)=24547536) +2288 train 7.182259 (lr=1.7500e-04) (hash(x)=22622789) +2289 train 7.175355 (lr=1.7500e-04) (hash(x)=23874051) +2290 train 7.501315 (lr=1.7500e-04) (hash(x)=25015641) +2291 train 7.356268 (lr=1.7500e-04) (hash(x)=24978712) +2292 train 7.488533 (lr=1.7500e-04) (hash(x)=25311986) +2293 train 7.244401 (lr=1.7500e-04) (hash(x)=24298295) +2294 train 7.294400 (lr=1.7500e-04) (hash(x)=26481527) +2295 train 7.028795 (lr=1.7500e-04) (hash(x)=18987545) +2296 train 7.278077 (lr=1.7500e-04) (hash(x)=24617990) +2297 train 7.275350 (lr=1.7500e-04) (hash(x)=23903200) +2298 train 7.561565 (lr=1.7500e-04) (hash(x)=26278697) +2299 train 7.262853 (lr=1.7500e-04) (hash(x)=24092784) +2300 val loss 7.3335 +2300 val perplexity 1530.7772 +2300 train 7.220337 (lr=1.7500e-04) (hash(x)=22894919) +2301 train 7.312974 (lr=1.7500e-04) (hash(x)=24253964) +2302 train 7.342243 (lr=1.7500e-04) (hash(x)=23750610) +2303 train 7.314332 (lr=1.7500e-04) (hash(x)=26745063) +2304 train 7.214141 (lr=1.7500e-04) (hash(x)=21407001) +2305 train 7.483655 (lr=1.7500e-04) (hash(x)=26680082) +2306 train 7.415073 (lr=1.7500e-04) (hash(x)=26722122) +2307 train 7.252026 (lr=1.7500e-04) (hash(x)=22539112) +2308 train 7.000825 (lr=1.7500e-04) (hash(x)=19927356) +2309 train 7.086222 (lr=1.7500e-04) (hash(x)=21431267) +2310 train 7.042203 (lr=1.7500e-04) (hash(x)=21073487) +2311 train 7.071883 (lr=1.7500e-04) (hash(x)=21447406) +2312 train 7.053004 (lr=1.7500e-04) (hash(x)=22667253) +2313 train 7.028496 (lr=1.7500e-04) (hash(x)=20849089) +2314 train 6.998633 (lr=1.7500e-04) (hash(x)=19168351) +2315 train 7.038788 (lr=1.7500e-04) (hash(x)=21082139) +2316 train 7.011815 (lr=1.7500e-04) (hash(x)=21493530) +2317 train 6.959038 (lr=1.7500e-04) (hash(x)=19506447) +2318 train 7.083734 (lr=1.7500e-04) (hash(x)=23128797) +2319 train 7.254385 (lr=1.7500e-04) (hash(x)=24650655) +2320 train 7.034687 (lr=1.7500e-04) (hash(x)=21833080) +2321 train 7.545204 (lr=1.7500e-04) (hash(x)=26355512) +2322 train 7.684608 (lr=1.7500e-04) (hash(x)=26746363) +2323 train 7.158362 (lr=1.7500e-04) (hash(x)=22130721) +2324 train 7.500712 (lr=1.7500e-04) (hash(x)=28301752) +2325 train 7.308635 (lr=1.7500e-04) (hash(x)=26444359) +2326 train 7.676357 (lr=1.7500e-04) (hash(x)=24836130) +2327 train 8.092314 (lr=1.7500e-04) (hash(x)=26519976) +2328 train 9.524657 (lr=1.7500e-04) (hash(x)=35558906) +2329 train 7.782863 (lr=1.7500e-04) (hash(x)=30877729) +2330 train 7.564498 (lr=1.7500e-04) (hash(x)=28028485) +2331 train 7.728500 (lr=1.7500e-04) (hash(x)=25582440) +2332 train 8.056541 (lr=1.7500e-04) (hash(x)=29402491) +2333 train 7.384442 (lr=1.7500e-04) (hash(x)=25200284) +2334 train 7.386155 (lr=1.7500e-04) (hash(x)=26288480) +2335 train 7.203694 (lr=1.7500e-04) (hash(x)=20106514) +2336 train 7.152801 (lr=1.7500e-04) (hash(x)=22522123) +2337 train 7.114680 (lr=1.7500e-04) (hash(x)=23362041) +2338 train 7.245917 (lr=1.7500e-04) (hash(x)=26003099) +2339 train 7.342548 (lr=1.7500e-04) (hash(x)=25695510) +2340 train 7.319766 (lr=1.7500e-04) (hash(x)=27225904) +2341 train 7.042324 (lr=1.7500e-04) (hash(x)=21573008) +2342 train 7.514375 (lr=1.7500e-04) (hash(x)=21386628) +2343 train 7.235312 (lr=1.7500e-04) (hash(x)=20117808) +2344 train 7.339650 (lr=1.7500e-04) (hash(x)=21592790) +2345 train 7.238530 (lr=1.7500e-04) (hash(x)=19909192) +2346 train 7.390053 (lr=1.7500e-04) (hash(x)=22529262) +2347 train 7.439070 (lr=1.7500e-04) (hash(x)=24501900) +2348 train 7.343988 (lr=1.7500e-04) (hash(x)=25912171) +2349 train 7.428702 (lr=1.7500e-04) (hash(x)=25606665) +2350 val loss 7.3509 +2350 val perplexity 1557.5809 +2350 train 7.346162 (lr=1.7500e-04) (hash(x)=24487351) +2351 train 7.529719 (lr=1.7500e-04) (hash(x)=25510334) +2352 train 7.457223 (lr=1.7500e-04) (hash(x)=25357989) +2353 train 7.094949 (lr=1.7500e-04) (hash(x)=24656801) +2354 train 7.164854 (lr=1.7500e-04) (hash(x)=23312772) +2355 train 7.044022 (lr=1.7500e-04) (hash(x)=22099158) +2356 train 7.095970 (lr=1.7500e-04) (hash(x)=26507898) +2357 train 7.344174 (lr=1.7500e-04) (hash(x)=28351614) +2358 train 7.396546 (lr=1.7500e-04) (hash(x)=27489567) +2359 train 7.355388 (lr=1.7500e-04) (hash(x)=25749120) +2360 train 7.661878 (lr=1.7500e-04) (hash(x)=31711338) +2361 train 7.813349 (lr=1.7500e-04) (hash(x)=29645018) +2362 train 7.853527 (lr=1.7500e-04) (hash(x)=29713268) +2363 train 7.014659 (lr=1.7500e-04) (hash(x)=21720691) +2364 train 7.119472 (lr=1.7500e-04) (hash(x)=24316633) +2365 train 7.120043 (lr=1.7500e-04) (hash(x)=21597124) +2366 train 7.100849 (lr=1.7500e-04) (hash(x)=22520345) +2367 train 7.145235 (lr=1.7500e-04) (hash(x)=24357241) +2368 train 7.276277 (lr=1.7500e-04) (hash(x)=24085450) +2369 train 7.190970 (lr=1.7500e-04) (hash(x)=25136495) +2370 train 7.618948 (lr=1.7500e-04) (hash(x)=26073986) +2371 train 7.585501 (lr=1.7500e-04) (hash(x)=28911272) +2372 train 7.390413 (lr=1.7500e-04) (hash(x)=26667356) +2373 train 7.168678 (lr=1.7500e-04) (hash(x)=25225894) +2374 train 7.229845 (lr=1.7500e-04) (hash(x)=24404081) +2375 train 7.299327 (lr=1.7500e-04) (hash(x)=25584945) +2376 train 7.197998 (lr=1.7500e-04) (hash(x)=23831571) +2377 train 7.134485 (lr=1.7500e-04) (hash(x)=23521916) +2378 train 7.169891 (lr=1.7500e-04) (hash(x)=25318634) +2379 train 7.080300 (lr=1.7500e-04) (hash(x)=21847287) +2380 train 7.363000 (lr=1.7500e-04) (hash(x)=23877060) +2381 train 7.155736 (lr=1.7500e-04) (hash(x)=24069020) +2382 train 6.990157 (lr=1.7500e-04) (hash(x)=21724290) +2383 train 7.215664 (lr=1.7500e-04) (hash(x)=25198897) +2384 train 7.075265 (lr=1.7500e-04) (hash(x)=24109958) +2385 train 6.956053 (lr=1.7500e-04) (hash(x)=20122390) +2386 train 7.220578 (lr=1.7500e-04) (hash(x)=24062305) +2387 train 6.990491 (lr=1.7500e-04) (hash(x)=22436833) +2388 train 7.312337 (lr=1.7500e-04) (hash(x)=26013214) +2389 train 7.702593 (lr=1.7500e-04) (hash(x)=27691436) +2390 train 7.807207 (lr=1.7500e-04) (hash(x)=30802878) +2391 train 6.949973 (lr=1.7500e-04) (hash(x)=23475891) +2392 train 6.948048 (lr=1.7500e-04) (hash(x)=23118133) +2393 train 6.866614 (lr=1.7500e-04) (hash(x)=21469159) +2394 train 7.249956 (lr=1.7500e-04) (hash(x)=26444484) +2395 train 7.108670 (lr=1.7500e-04) (hash(x)=25083992) +2396 train 7.438516 (lr=1.7500e-04) (hash(x)=23461229) +2397 train 7.259847 (lr=1.7500e-04) (hash(x)=20441653) +2398 train 7.372088 (lr=1.7500e-04) (hash(x)=28024211) +2399 train 7.214448 (lr=1.7500e-04) (hash(x)=23644804) +2400 val loss 7.2445 +2400 val perplexity 1400.3411 +2400 train 7.015480 (lr=1.7500e-04) (hash(x)=26685301) +2401 train 6.946639 (lr=1.7500e-04) (hash(x)=20820913) +2402 train 7.124397 (lr=1.7500e-04) (hash(x)=22178190) +2403 train 7.640602 (lr=1.7500e-04) (hash(x)=31377168) +2404 train 7.852941 (lr=1.7500e-04) (hash(x)=33795307) +2405 train 7.983351 (lr=1.7500e-04) (hash(x)=34450341) +2406 train 7.231101 (lr=1.7500e-04) (hash(x)=25834183) +2407 train 7.443058 (lr=1.7500e-04) (hash(x)=25629584) +2408 train 7.184916 (lr=1.7500e-04) (hash(x)=25080123) +2409 train 7.072890 (lr=1.7500e-04) (hash(x)=21975628) +2410 train 7.610376 (lr=1.7500e-04) (hash(x)=27430197) +2411 train 7.748265 (lr=1.7500e-04) (hash(x)=29285135) +2412 train 7.387403 (lr=1.7500e-04) (hash(x)=24640105) +2413 train 7.590574 (lr=1.7500e-04) (hash(x)=29628864) +2414 train 7.821353 (lr=1.7500e-04) (hash(x)=30096444) +2415 train 7.607584 (lr=1.7500e-04) (hash(x)=29797280) +2416 train 6.978103 (lr=1.7500e-04) (hash(x)=22686143) +2417 train 7.580660 (lr=1.7500e-04) (hash(x)=28346842) +2418 train 7.536144 (lr=1.7500e-04) (hash(x)=28167937) +2419 train 7.746243 (lr=1.7500e-04) (hash(x)=33122326) +2420 train 7.780143 (lr=1.7500e-04) (hash(x)=33044913) +2421 train 7.554877 (lr=1.7500e-04) (hash(x)=31250981) +2422 train 7.794879 (lr=1.7500e-04) (hash(x)=29827111) +2423 train 7.739809 (lr=1.7500e-04) (hash(x)=30026394) +2424 train 7.791353 (lr=1.7500e-04) (hash(x)=26998238) +2425 train 7.689651 (lr=1.7500e-04) (hash(x)=24850684) +2426 train 7.988789 (lr=1.7500e-04) (hash(x)=36659853) +2427 train 7.835874 (lr=1.7500e-04) (hash(x)=34353164) +2428 train 7.213704 (lr=1.7500e-04) (hash(x)=23630644) +2429 train 7.281574 (lr=1.7500e-04) (hash(x)=24528186) +2430 train 7.177595 (lr=1.7500e-04) (hash(x)=22665222) +2431 train 7.305530 (lr=1.7500e-04) (hash(x)=26594177) +2432 train 7.713292 (lr=1.7500e-04) (hash(x)=29300546) +2433 train 7.136479 (lr=1.7500e-04) (hash(x)=21331715) +2434 train 7.446100 (lr=1.7500e-04) (hash(x)=26290885) +2435 train 7.327526 (lr=1.7500e-04) (hash(x)=25554738) +2436 train 7.540699 (lr=1.7500e-04) (hash(x)=26744311) +2437 train 7.446861 (lr=1.7500e-04) (hash(x)=26872344) +2438 train 7.497530 (lr=1.7500e-04) (hash(x)=27636081) +2439 train 7.254957 (lr=1.7500e-04) (hash(x)=23766256) +2440 train 7.416375 (lr=1.7500e-04) (hash(x)=24434438) +2441 train 7.255397 (lr=1.7500e-04) (hash(x)=22992618) +2442 train 7.110544 (lr=1.7500e-04) (hash(x)=22393467) +2443 train 7.353135 (lr=1.7500e-04) (hash(x)=26853444) +2444 train 7.298706 (lr=1.7500e-04) (hash(x)=25101020) +2445 train 7.166246 (lr=1.7500e-04) (hash(x)=24705456) +2446 train 7.495706 (lr=1.7500e-04) (hash(x)=26798611) +2447 train 7.153806 (lr=1.7500e-04) (hash(x)=24250150) +2448 train 7.221759 (lr=1.7500e-04) (hash(x)=24494331) +2449 train 7.245567 (lr=1.7500e-04) (hash(x)=27579257) +2450 val loss 7.2852 +2450 val perplexity 1458.5432 +2450 train 6.977880 (lr=1.7500e-04) (hash(x)=22377407) +2451 train 7.328242 (lr=1.7500e-04) (hash(x)=26289588) +2452 train 7.251802 (lr=1.7500e-04) (hash(x)=25871900) +2453 train 7.134859 (lr=1.7500e-04) (hash(x)=23437197) +2454 train 7.395923 (lr=1.7500e-04) (hash(x)=23557786) +2455 train 7.333197 (lr=1.7500e-04) (hash(x)=26108817) +2456 train 7.250960 (lr=1.7500e-04) (hash(x)=26440482) +2457 train 7.218752 (lr=1.7500e-04) (hash(x)=24583191) +2458 train 7.192376 (lr=1.7500e-04) (hash(x)=23756440) +2459 train 7.091383 (lr=1.7500e-04) (hash(x)=23814987) +2460 train 7.462147 (lr=1.7500e-04) (hash(x)=28508433) +2461 train 7.120841 (lr=1.7500e-04) (hash(x)=25692442) +2462 train 7.127193 (lr=1.7500e-04) (hash(x)=24699197) +2463 train 6.829259 (lr=1.7500e-04) (hash(x)=18582688) +2464 train 7.125309 (lr=1.7500e-04) (hash(x)=23266625) +2465 train 7.462019 (lr=1.7500e-04) (hash(x)=26565489) +2466 train 6.967013 (lr=1.7500e-04) (hash(x)=21686599) +2467 train 7.293307 (lr=1.7500e-04) (hash(x)=25558792) +2468 train 7.054801 (lr=1.7500e-04) (hash(x)=25110035) +2469 train 7.421010 (lr=1.7500e-04) (hash(x)=26263661) +2470 train 7.178802 (lr=1.7500e-04) (hash(x)=22282189) +2471 train 7.152892 (lr=1.7500e-04) (hash(x)=23272705) +2472 train 7.219627 (lr=1.7500e-04) (hash(x)=25300067) +2473 train 7.416658 (lr=1.7500e-04) (hash(x)=26802369) +2474 train 7.156034 (lr=1.7500e-04) (hash(x)=24646471) +2475 train 7.091220 (lr=1.7500e-04) (hash(x)=24709241) +2476 train 7.173076 (lr=1.7500e-04) (hash(x)=26747197) +2477 train 7.233518 (lr=1.7500e-04) (hash(x)=25201108) +2478 train 7.336940 (lr=1.7500e-04) (hash(x)=24962427) +2479 train 7.207073 (lr=1.7500e-04) (hash(x)=24793412) +2480 train 7.203725 (lr=1.7500e-04) (hash(x)=24452301) +2481 train 7.231679 (lr=1.7500e-04) (hash(x)=25177251) +2482 train 7.187459 (lr=1.7500e-04) (hash(x)=25801499) +2483 train 7.371648 (lr=1.7500e-04) (hash(x)=27256707) +2484 train 7.592577 (lr=1.7500e-04) (hash(x)=25303237) +2485 train 7.187252 (lr=1.7500e-04) (hash(x)=21641481) +2486 train 7.227092 (lr=1.7500e-04) (hash(x)=23818831) +2487 train 7.049956 (lr=1.7500e-04) (hash(x)=19280989) +2488 train 7.445514 (lr=1.7500e-04) (hash(x)=24075167) +2489 train 7.436172 (lr=1.7500e-04) (hash(x)=26651546) +2490 train 7.254651 (lr=1.7500e-04) (hash(x)=25367186) +2491 train 7.205401 (lr=1.7500e-04) (hash(x)=26508642) +2492 train 7.299459 (lr=1.7500e-04) (hash(x)=25294182) +2493 train 7.225025 (lr=1.7500e-04) (hash(x)=23916886) +2494 train 7.028355 (lr=1.7500e-04) (hash(x)=21189910) +2495 train 7.145257 (lr=1.7500e-04) (hash(x)=22751150) +2496 train 7.531873 (lr=1.7500e-04) (hash(x)=26608502) +2497 train 7.957452 (lr=1.7500e-04) (hash(x)=25372010) +2498 train 7.190802 (lr=1.7500e-04) (hash(x)=22006251) +2499 train 7.134605 (lr=1.7500e-04) (hash(x)=23880160) +2500 val loss 7.2620 +2500 val perplexity 1425.0775 +2500 train 7.092052 (lr=1.7500e-04) (hash(x)=23225337) +2501 train 7.255709 (lr=1.7500e-04) (hash(x)=24932950) +2502 train 6.964531 (lr=1.7500e-04) (hash(x)=20022340) +2503 train 7.309628 (lr=1.7500e-04) (hash(x)=23537942) +2504 train 7.200700 (lr=1.7500e-04) (hash(x)=24884288) +2505 train 6.846634 (lr=1.7500e-04) (hash(x)=21296580) +2506 train 7.115004 (lr=1.7500e-04) (hash(x)=23001455) +2507 train 7.429710 (lr=1.7500e-04) (hash(x)=26975313) +2508 train 7.405770 (lr=1.7500e-04) (hash(x)=26029962) +2509 train 7.094186 (lr=1.7500e-04) (hash(x)=24302204) +2510 train 6.824314 (lr=1.7500e-04) (hash(x)=22997203) +2511 train 6.960131 (lr=1.7500e-04) (hash(x)=23748375) +2512 train 7.191603 (lr=1.7500e-04) (hash(x)=24453191) +2513 train 6.920330 (lr=1.7500e-04) (hash(x)=22026776) +2514 train 7.063616 (lr=1.7500e-04) (hash(x)=19934168) +2515 train 7.314914 (lr=1.7500e-04) (hash(x)=25541754) +2516 train 7.597528 (lr=1.7500e-04) (hash(x)=26604471) +2517 train 7.582391 (lr=1.7500e-04) (hash(x)=27900386) +2518 train 7.532601 (lr=1.7500e-04) (hash(x)=26403431) +2519 train 7.548679 (lr=1.7500e-04) (hash(x)=27413825) +2520 train 7.605837 (lr=1.7500e-04) (hash(x)=28332637) +2521 train 7.441053 (lr=1.7500e-04) (hash(x)=27223027) +2522 train 7.428112 (lr=1.7500e-04) (hash(x)=23843387) +2523 train 7.442770 (lr=1.7500e-04) (hash(x)=27075951) +2524 train 7.591794 (lr=1.7500e-04) (hash(x)=29300154) +2525 train 7.242619 (lr=1.7500e-04) (hash(x)=28100582) +2526 train 7.364917 (lr=1.7500e-04) (hash(x)=28051084) +2527 train 7.089197 (lr=1.7500e-04) (hash(x)=21682445) +2528 train 7.269402 (lr=1.7500e-04) (hash(x)=24062589) +2529 train 7.494702 (lr=1.7500e-04) (hash(x)=29616079) +2530 train 7.397602 (lr=1.7500e-04) (hash(x)=25170523) +2531 train 6.994831 (lr=1.7500e-04) (hash(x)=23361504) +2532 train 7.191952 (lr=1.7500e-04) (hash(x)=24444462) +2533 train 7.196654 (lr=1.7500e-04) (hash(x)=24035993) +2534 train 7.181326 (lr=1.7500e-04) (hash(x)=24696651) +2535 train 7.141847 (lr=1.7500e-04) (hash(x)=22040184) +2536 train 7.073171 (lr=1.7500e-04) (hash(x)=27400103) +2537 train 7.398693 (lr=1.7500e-04) (hash(x)=27383080) +2538 train 7.233492 (lr=1.7500e-04) (hash(x)=24212212) +2539 train 7.105217 (lr=1.7500e-04) (hash(x)=23727731) +2540 train 7.233981 (lr=1.7500e-04) (hash(x)=24149487) +2541 train 7.015407 (lr=1.7500e-04) (hash(x)=23794649) +2542 train 7.176523 (lr=1.7500e-04) (hash(x)=26147774) +2543 train 7.268945 (lr=1.7500e-04) (hash(x)=24463229) +2544 train 7.354579 (lr=1.7500e-04) (hash(x)=26361238) +2545 train 7.042980 (lr=1.7500e-04) (hash(x)=18891545) +2546 train 7.543713 (lr=1.7500e-04) (hash(x)=30380438) +2547 train 7.732016 (lr=1.7500e-04) (hash(x)=32663792) +2548 train 7.146503 (lr=1.7500e-04) (hash(x)=25175499) +2549 train 7.341606 (lr=1.7500e-04) (hash(x)=26702407) +2550 val loss 7.2447 +2550 val perplexity 1400.7097 +2550 train 7.165971 (lr=1.7500e-04) (hash(x)=24578061) +2551 train 7.198634 (lr=1.7500e-04) (hash(x)=24091954) +2552 train 7.228944 (lr=1.7500e-04) (hash(x)=23041778) +2553 train 7.043398 (lr=1.7500e-04) (hash(x)=23686239) +2554 train 7.173770 (lr=1.7500e-04) (hash(x)=22745355) +2555 train 7.151500 (lr=1.7500e-04) (hash(x)=23599013) +2556 train 7.101798 (lr=1.7500e-04) (hash(x)=26033088) +2557 train 7.142240 (lr=1.7500e-04) (hash(x)=21634218) +2558 train 7.123217 (lr=1.7500e-04) (hash(x)=20985281) +2559 train 7.328200 (lr=1.7500e-04) (hash(x)=26670219) +2560 train 7.126064 (lr=1.7500e-04) (hash(x)=26499936) +2561 train 7.239606 (lr=1.7500e-04) (hash(x)=23547908) +2562 train 7.117374 (lr=1.7500e-04) (hash(x)=22306373) +2563 train 7.182423 (lr=1.7500e-04) (hash(x)=24380893) +2564 train 7.137249 (lr=1.7500e-04) (hash(x)=23726190) +2565 train 7.213058 (lr=1.7500e-04) (hash(x)=26967512) +2566 train 7.239056 (lr=1.7500e-04) (hash(x)=23414576) +2567 train 7.456149 (lr=1.7500e-04) (hash(x)=25558986) +2568 train 7.373090 (lr=1.7500e-04) (hash(x)=27057505) +2569 train 7.357680 (lr=1.7500e-04) (hash(x)=26048135) +2570 train 7.352718 (lr=1.7500e-04) (hash(x)=26991032) +2571 train 7.344110 (lr=1.7500e-04) (hash(x)=25729492) +2572 train 6.957169 (lr=1.7500e-04) (hash(x)=20611723) +2573 train 7.030309 (lr=1.7500e-04) (hash(x)=24563606) +2574 train 7.084345 (lr=1.7500e-04) (hash(x)=23330043) +2575 train 7.215700 (lr=1.7500e-04) (hash(x)=19218943) +2576 train 7.497595 (lr=1.7500e-04) (hash(x)=20985122) +2577 train 7.152544 (lr=1.7500e-04) (hash(x)=24133609) +2578 train 7.437596 (lr=1.7500e-04) (hash(x)=28368610) +2579 train 7.212036 (lr=1.7500e-04) (hash(x)=23952206) +2580 train 7.131276 (lr=1.7500e-04) (hash(x)=23068957) +2581 train 7.240378 (lr=1.7500e-04) (hash(x)=25365277) +2582 train 7.500615 (lr=1.7500e-04) (hash(x)=24721184) +2583 train 7.242231 (lr=1.7500e-04) (hash(x)=24551402) +2584 train 7.017423 (lr=1.7500e-04) (hash(x)=20469327) +2585 train 7.384831 (lr=1.7500e-04) (hash(x)=24966478) +2586 train 7.144853 (lr=1.7500e-04) (hash(x)=18626184) +2587 train 7.116997 (lr=1.7500e-04) (hash(x)=24007642) +2588 train 7.104558 (lr=1.7500e-04) (hash(x)=23521875) +2589 train 7.272987 (lr=1.7500e-04) (hash(x)=25204207) +2590 train 7.086315 (lr=1.7500e-04) (hash(x)=25449801) +2591 train 7.307675 (lr=1.7500e-04) (hash(x)=25229281) +2592 train 7.169853 (lr=1.7500e-04) (hash(x)=23202696) +2593 train 7.023492 (lr=1.7500e-04) (hash(x)=22435944) +2594 train 7.002053 (lr=1.7500e-04) (hash(x)=20787439) +2595 train 6.671690 (lr=1.7500e-04) (hash(x)=18214283) +2596 train 6.814598 (lr=1.7500e-04) (hash(x)=20851477) +2597 train 6.791872 (lr=1.7500e-04) (hash(x)=20609675) +2598 train 6.888115 (lr=1.7500e-04) (hash(x)=20061218) +2599 train 6.942584 (lr=1.7500e-04) (hash(x)=21251127) +2600 val loss 7.2393 +2600 val perplexity 1393.1354 +2600 train 7.468080 (lr=1.7500e-04) (hash(x)=30948038) +2601 train 7.692516 (lr=1.7500e-04) (hash(x)=32279160) +2602 train 7.380715 (lr=1.7500e-04) (hash(x)=26607151) +2603 train 7.245183 (lr=1.7500e-04) (hash(x)=25097619) +2604 train 6.853178 (lr=1.7500e-04) (hash(x)=20892421) +2605 train 7.017219 (lr=1.7500e-04) (hash(x)=22212821) +2606 train 7.292778 (lr=1.7500e-04) (hash(x)=24720588) +2607 train 7.301529 (lr=1.7500e-04) (hash(x)=25800857) +2608 train 7.142457 (lr=1.7500e-04) (hash(x)=22901279) +2609 train 7.004016 (lr=1.7500e-04) (hash(x)=20921910) +2610 train 7.244783 (lr=1.7500e-04) (hash(x)=24846267) +2611 train 7.132561 (lr=1.7500e-04) (hash(x)=22918428) +2612 train 7.063802 (lr=1.7500e-04) (hash(x)=22805901) +2613 train 7.230430 (lr=1.7500e-04) (hash(x)=24345816) +2614 train 7.073918 (lr=1.7500e-04) (hash(x)=22962012) +2615 train 7.311960 (lr=1.7500e-04) (hash(x)=25836189) +2616 train 7.362988 (lr=1.7500e-04) (hash(x)=27922916) +2617 train 7.073301 (lr=1.7500e-04) (hash(x)=21697866) +2618 train 7.071916 (lr=1.7500e-04) (hash(x)=24283369) +2619 train 6.983987 (lr=1.7500e-04) (hash(x)=24504567) +2620 train 7.084903 (lr=1.7500e-04) (hash(x)=25557725) +2621 train 7.116602 (lr=1.7500e-04) (hash(x)=23135849) +2622 train 7.051392 (lr=1.7500e-04) (hash(x)=22888908) +2623 train 7.263670 (lr=1.7500e-04) (hash(x)=25999255) +2624 train 7.116890 (lr=1.7500e-04) (hash(x)=24446851) +2625 train 6.822941 (lr=1.7500e-04) (hash(x)=21137520) +2626 train 7.159906 (lr=1.7500e-04) (hash(x)=26245754) +2627 train 7.501144 (lr=1.7500e-04) (hash(x)=27308968) +2628 train 7.223917 (lr=1.7500e-04) (hash(x)=23961169) +2629 train 7.186881 (lr=1.7500e-04) (hash(x)=25924731) +2630 train 7.268865 (lr=1.7500e-04) (hash(x)=25782315) +2631 train 7.385478 (lr=1.7500e-04) (hash(x)=20149394) +2632 train 7.408905 (lr=1.7500e-04) (hash(x)=23801981) +2633 train 7.196600 (lr=1.7500e-04) (hash(x)=23830286) +2634 train 7.086620 (lr=1.7500e-04) (hash(x)=25325236) +2635 train 7.110287 (lr=1.7500e-04) (hash(x)=24498556) +2636 train 7.062824 (lr=1.7500e-04) (hash(x)=23693078) +2637 train 7.221604 (lr=1.7500e-04) (hash(x)=25484922) +2638 train 6.952157 (lr=1.7500e-04) (hash(x)=22645025) +2639 train 6.892536 (lr=1.7500e-04) (hash(x)=21999338) +2640 train 7.123925 (lr=1.7500e-04) (hash(x)=21758019) +2641 train 7.072141 (lr=1.7500e-04) (hash(x)=24064168) +2642 train 7.115696 (lr=1.7500e-04) (hash(x)=26847292) +2643 train 6.943479 (lr=1.7500e-04) (hash(x)=23280568) +2644 train 6.992775 (lr=1.7500e-04) (hash(x)=21749161) +2645 train 7.625906 (lr=1.7500e-04) (hash(x)=30082352) +2646 train 7.533308 (lr=1.7500e-04) (hash(x)=28334297) +2647 train 7.622270 (lr=1.7500e-04) (hash(x)=27611302) +2648 train 8.040870 (lr=1.7500e-04) (hash(x)=31007436) +2649 train 6.982036 (lr=1.7500e-04) (hash(x)=22356183) +2650 val loss 7.2955 +2650 val perplexity 1473.7250 +2650 train 7.034799 (lr=1.7500e-04) (hash(x)=23071731) +2651 train 7.030507 (lr=1.7500e-04) (hash(x)=23982308) +2652 train 7.338901 (lr=1.7500e-04) (hash(x)=25673823) +2653 train 7.119754 (lr=1.7500e-04) (hash(x)=22973788) +2654 train 7.277048 (lr=1.7500e-04) (hash(x)=25386647) +2655 train 7.003365 (lr=1.7500e-04) (hash(x)=22778356) +2656 train 7.212183 (lr=1.7500e-04) (hash(x)=26669130) +2657 train 6.956274 (lr=1.7500e-04) (hash(x)=23542930) +2658 train 7.095590 (lr=1.7500e-04) (hash(x)=23307871) +2659 train 7.031328 (lr=1.7500e-04) (hash(x)=23467046) +2660 train 7.192850 (lr=1.7500e-04) (hash(x)=24728872) +2661 train 7.828491 (lr=1.7500e-04) (hash(x)=29719902) +2662 train 7.100885 (lr=1.7500e-04) (hash(x)=25114165) +2663 train 7.005019 (lr=1.7500e-04) (hash(x)=24195959) +2664 train 7.239168 (lr=1.7500e-04) (hash(x)=26938509) +2665 train 7.430187 (lr=1.7500e-04) (hash(x)=27168434) +2666 train 7.551132 (lr=1.7500e-04) (hash(x)=27488221) +2667 train 8.204161 (lr=1.7500e-04) (hash(x)=32710438) +2668 train 7.363499 (lr=1.7500e-04) (hash(x)=25073185) +2669 train 7.353267 (lr=1.7500e-04) (hash(x)=26951664) +2670 train 7.515080 (lr=1.7500e-04) (hash(x)=24886228) +2671 train 6.974854 (lr=1.7500e-04) (hash(x)=19127465) +2672 train 7.248878 (lr=1.7500e-04) (hash(x)=27134917) +2673 train 7.152899 (lr=1.7500e-04) (hash(x)=25673955) +2674 train 7.741042 (lr=1.7500e-04) (hash(x)=27111776) +2675 train 7.618299 (lr=1.7500e-04) (hash(x)=28962580) +2676 train 7.178913 (lr=1.7500e-04) (hash(x)=25593381) +2677 train 7.259748 (lr=1.7500e-04) (hash(x)=25238916) +2678 train 7.130257 (lr=1.7500e-04) (hash(x)=27453574) +2679 train 7.081651 (lr=1.7500e-04) (hash(x)=22426274) +2680 train 7.133809 (lr=1.7500e-04) (hash(x)=22974780) +2681 train 7.160262 (lr=1.7500e-04) (hash(x)=24668644) +2682 train 7.168889 (lr=1.7500e-04) (hash(x)=26182084) +2683 train 7.327928 (lr=1.7500e-04) (hash(x)=25606512) +2684 train 7.156089 (lr=1.7500e-04) (hash(x)=24885252) +2685 train 6.960369 (lr=1.7500e-04) (hash(x)=21290254) +2686 train 6.911533 (lr=1.7500e-04) (hash(x)=21367078) +2687 train 7.084729 (lr=1.7500e-04) (hash(x)=23785205) +2688 train 7.058309 (lr=1.7500e-04) (hash(x)=24640056) +2689 train 7.445999 (lr=1.7500e-04) (hash(x)=27083886) +2690 train 7.126641 (lr=1.7500e-04) (hash(x)=23603571) +2691 train 7.167524 (lr=1.7500e-04) (hash(x)=24779414) +2692 train 6.914253 (lr=1.7500e-04) (hash(x)=22200693) +2693 train 7.337187 (lr=1.7500e-04) (hash(x)=26907868) +2694 train 7.636086 (lr=1.7500e-04) (hash(x)=32034827) +2695 train 7.453232 (lr=1.7500e-04) (hash(x)=28505676) +2696 train 7.064327 (lr=1.7500e-04) (hash(x)=23805750) +2697 train 7.366028 (lr=1.7500e-04) (hash(x)=29804750) +2698 train 7.648839 (lr=1.7500e-04) (hash(x)=28443583) +2699 train 7.523295 (lr=1.7500e-04) (hash(x)=29156288) +2700 val loss 7.2010 +2700 val perplexity 1340.7673 +2700 train 7.209909 (lr=1.7500e-04) (hash(x)=25895743) +2701 train 6.846701 (lr=1.7500e-04) (hash(x)=21173795) +2702 train 6.756511 (lr=1.7500e-04) (hash(x)=20790866) +2703 train 7.365544 (lr=1.7500e-04) (hash(x)=27706477) +2704 train 7.492015 (lr=1.7500e-04) (hash(x)=30358985) +2705 train 7.091789 (lr=1.7500e-04) (hash(x)=23548492) +2706 train 7.288391 (lr=1.7500e-04) (hash(x)=25879696) +2707 train 7.124658 (lr=1.7500e-04) (hash(x)=23711800) +2708 train 7.663426 (lr=1.7500e-04) (hash(x)=28763123) +2709 train 7.237869 (lr=1.7500e-04) (hash(x)=23327642) +2710 train 7.311610 (lr=1.7500e-04) (hash(x)=25634166) +2711 train 7.212793 (lr=1.7500e-04) (hash(x)=28684175) +2712 train 7.267168 (lr=1.7500e-04) (hash(x)=23996278) +2713 train 6.957248 (lr=1.7500e-04) (hash(x)=21795980) +2714 train 7.229289 (lr=1.7500e-04) (hash(x)=24840769) +2715 train 7.184724 (lr=1.7500e-04) (hash(x)=25225466) +2716 train 7.456243 (lr=1.7500e-04) (hash(x)=27500471) +2717 train 7.161829 (lr=1.7500e-04) (hash(x)=24703036) +2718 train 7.271549 (lr=1.7500e-04) (hash(x)=24294293) +2719 train 7.228294 (lr=1.7500e-04) (hash(x)=28003600) +2720 train 7.000689 (lr=1.7500e-04) (hash(x)=22822962) +2721 train 6.935577 (lr=1.7500e-04) (hash(x)=24189246) +2722 train 7.019708 (lr=1.7500e-04) (hash(x)=22608951) +2723 train 7.649748 (lr=1.7500e-04) (hash(x)=27989890) +2724 train 7.304993 (lr=1.7500e-04) (hash(x)=24175838) +2725 train 7.203850 (lr=1.7500e-04) (hash(x)=24781792) +2726 train 7.033774 (lr=1.7500e-04) (hash(x)=23413276) +2727 train 7.432134 (lr=1.7500e-04) (hash(x)=27586845) +2728 train 7.236770 (lr=1.7500e-04) (hash(x)=27336264) +2729 train 7.259763 (lr=1.7500e-04) (hash(x)=26808464) +2730 train 7.105641 (lr=1.7500e-04) (hash(x)=22312009) +2731 train 7.154965 (lr=1.7500e-04) (hash(x)=22373927) +2732 train 7.125897 (lr=1.7500e-04) (hash(x)=23428834) +2733 train 7.118853 (lr=1.7500e-04) (hash(x)=25304441) +2734 train 7.135986 (lr=1.7500e-04) (hash(x)=24798164) +2735 train 6.907594 (lr=1.7500e-04) (hash(x)=21176405) +2736 train 7.006543 (lr=1.7500e-04) (hash(x)=22343075) +2737 train 7.102484 (lr=1.7500e-04) (hash(x)=23825332) +2738 train 7.123108 (lr=1.7500e-04) (hash(x)=24191865) +2739 train 6.938385 (lr=1.7500e-04) (hash(x)=23806052) +2740 train 7.007076 (lr=1.7500e-04) (hash(x)=21764591) +2741 train 7.150775 (lr=1.7500e-04) (hash(x)=25548695) +2742 train 7.336542 (lr=1.7500e-04) (hash(x)=26847535) +2743 train 7.081261 (lr=1.7500e-04) (hash(x)=25888433) +2744 train 7.033157 (lr=1.7500e-04) (hash(x)=24327454) +2745 train 6.957852 (lr=1.7500e-04) (hash(x)=22543301) +2746 train 7.377226 (lr=1.7500e-04) (hash(x)=24593022) +2747 train 7.966385 (lr=1.7500e-04) (hash(x)=27797727) +2748 train 7.427672 (lr=1.7500e-04) (hash(x)=28067682) +2749 train 7.115436 (lr=1.7500e-04) (hash(x)=25278538) +2750 val loss 7.2245 +2750 val perplexity 1372.5980 +2750 train 7.043747 (lr=1.7500e-04) (hash(x)=23875731) +2751 train 7.178020 (lr=1.7500e-04) (hash(x)=27916982) +2752 train 7.160738 (lr=1.7500e-04) (hash(x)=25726799) +2753 train 7.026046 (lr=1.7500e-04) (hash(x)=25227141) +2754 train 7.301961 (lr=1.7500e-04) (hash(x)=27679212) +2755 train 6.871030 (lr=1.7500e-04) (hash(x)=24621793) +2756 train 6.906026 (lr=1.7500e-04) (hash(x)=21962296) +2757 train 7.235191 (lr=1.7500e-04) (hash(x)=24899679) +2758 train 6.945656 (lr=1.7500e-04) (hash(x)=21452158) +2759 train 7.042774 (lr=1.7500e-04) (hash(x)=24334708) +2760 train 7.309538 (lr=1.7500e-04) (hash(x)=25523041) +2761 train 7.373157 (lr=1.7500e-04) (hash(x)=30389813) +2762 train 6.971805 (lr=1.7500e-04) (hash(x)=22426014) +2763 train 7.080104 (lr=1.7500e-04) (hash(x)=24419143) +2764 train 7.160236 (lr=1.7500e-04) (hash(x)=24850536) +2765 train 7.226995 (lr=1.7500e-04) (hash(x)=24181393) +2766 train 6.765443 (lr=1.7500e-04) (hash(x)=18882503) +2767 train 7.240743 (lr=1.7500e-04) (hash(x)=25617709) +2768 train 7.102498 (lr=1.7500e-04) (hash(x)=24076662) +2769 train 7.051182 (lr=1.7500e-04) (hash(x)=21656802) +2770 train 7.006693 (lr=1.7500e-04) (hash(x)=21014265) +2771 train 7.127399 (lr=1.7500e-04) (hash(x)=24556034) +2772 train 6.913675 (lr=1.7500e-04) (hash(x)=22046665) +2773 train 7.208717 (lr=1.7500e-04) (hash(x)=26761579) +2774 train 8.744025 (lr=1.7500e-04) (hash(x)=41414315) +2775 train 7.103115 (lr=1.7500e-04) (hash(x)=25152362) +2776 train 7.262672 (lr=1.7500e-04) (hash(x)=25567641) +2777 train 7.161742 (lr=1.7500e-04) (hash(x)=25427935) +2778 train 7.265008 (lr=1.7500e-04) (hash(x)=25824457) +2779 train 7.171945 (lr=1.7500e-04) (hash(x)=24326376) +2780 train 7.197172 (lr=1.7500e-04) (hash(x)=27447230) +2781 train 7.023772 (lr=1.7500e-04) (hash(x)=24003710) +2782 train 6.952031 (lr=1.7500e-04) (hash(x)=24157390) +2783 train 7.053458 (lr=1.7500e-04) (hash(x)=24276512) +2784 train 6.876989 (lr=1.7500e-04) (hash(x)=21503752) +2785 train 6.767075 (lr=1.7500e-04) (hash(x)=20031488) +2786 train 6.817688 (lr=1.7500e-04) (hash(x)=21788715) +2787 train 7.022424 (lr=1.7500e-04) (hash(x)=24344695) +2788 train 7.097811 (lr=1.7500e-04) (hash(x)=22927763) +2789 train 6.991251 (lr=1.7500e-04) (hash(x)=23710755) +2790 train 7.240544 (lr=1.7500e-04) (hash(x)=26924620) +2791 train 7.556851 (lr=1.7500e-04) (hash(x)=26776133) +2792 train 6.991748 (lr=1.7500e-04) (hash(x)=19936770) +2793 train 7.163914 (lr=1.7500e-04) (hash(x)=25440959) +2794 train 7.100931 (lr=1.7500e-04) (hash(x)=25146097) +2795 train 6.915362 (lr=1.7500e-04) (hash(x)=21847282) +2796 train 7.122615 (lr=1.7500e-04) (hash(x)=25639784) +2797 train 6.910199 (lr=1.7500e-04) (hash(x)=21199921) +2798 train 7.090299 (lr=1.7500e-04) (hash(x)=22360806) +2799 train 6.511188 (lr=1.7500e-04) (hash(x)=20254159) +2800 val loss 7.1850 +2800 val perplexity 1319.5515 +2800 train 6.627760 (lr=1.7500e-04) (hash(x)=23348345) +2801 train 7.281492 (lr=1.7500e-04) (hash(x)=24908033) +2802 train 7.021743 (lr=1.7500e-04) (hash(x)=23350309) +2803 train 7.132036 (lr=1.7500e-04) (hash(x)=25044762) +2804 train 6.995710 (lr=1.7500e-04) (hash(x)=24071026) +2805 train 6.807176 (lr=1.7500e-04) (hash(x)=22169363) +2806 train 7.066528 (lr=1.7500e-04) (hash(x)=23757564) +2807 train 7.488694 (lr=1.7500e-04) (hash(x)=27873855) +2808 train 7.258489 (lr=1.7500e-04) (hash(x)=26577893) +2809 train 7.310597 (lr=1.7500e-04) (hash(x)=27001634) +2810 train 7.084784 (lr=1.7500e-04) (hash(x)=24796541) +2811 train 6.988630 (lr=1.7500e-04) (hash(x)=22575615) +2812 train 7.099718 (lr=1.7500e-04) (hash(x)=25876475) +2813 train 7.102927 (lr=1.7500e-04) (hash(x)=24765155) +2814 train 7.050439 (lr=1.7500e-04) (hash(x)=25785699) +2815 train 7.250773 (lr=1.7500e-04) (hash(x)=25113614) +2816 train 7.100433 (lr=1.7500e-04) (hash(x)=24415748) +2817 train 7.166195 (lr=1.7500e-04) (hash(x)=25140622) +2818 train 7.125791 (lr=1.7500e-04) (hash(x)=24845866) +2819 train 7.557644 (lr=1.7500e-04) (hash(x)=28062905) +2820 train 7.089897 (lr=1.7500e-04) (hash(x)=22041086) +2821 train 7.175196 (lr=1.7500e-04) (hash(x)=24957184) +2822 train 7.071096 (lr=1.7500e-04) (hash(x)=24360380) +2823 train 7.264249 (lr=1.7500e-04) (hash(x)=26192886) +2824 train 7.124527 (lr=1.7500e-04) (hash(x)=25001858) +2825 train 7.075258 (lr=1.7500e-04) (hash(x)=24721193) +2826 train 7.159318 (lr=1.7500e-04) (hash(x)=26186227) +2827 train 7.067783 (lr=1.7500e-04) (hash(x)=25770338) +2828 train 7.162485 (lr=1.7500e-04) (hash(x)=25920767) +2829 train 7.109001 (lr=1.7500e-04) (hash(x)=25060684) +2830 train 6.803524 (lr=1.7500e-04) (hash(x)=22933946) +2831 train 6.958360 (lr=1.7500e-04) (hash(x)=24614912) +2832 train 6.757565 (lr=1.7500e-04) (hash(x)=19955522) +2833 train 6.787144 (lr=1.7500e-04) (hash(x)=21111215) +2834 train 7.604823 (lr=1.7500e-04) (hash(x)=28817924) +2835 train 7.154167 (lr=1.7500e-04) (hash(x)=26934071) +2836 train 7.088675 (lr=1.7500e-04) (hash(x)=24768851) +2837 train 7.086412 (lr=1.7500e-04) (hash(x)=25706447) +2838 train 6.915286 (lr=1.7500e-04) (hash(x)=19579834) +2839 train 7.137086 (lr=1.7500e-04) (hash(x)=25397093) +2840 train 7.551742 (lr=1.7500e-04) (hash(x)=27902141) +2841 train 7.170978 (lr=1.7500e-04) (hash(x)=25383069) +2842 train 6.975000 (lr=1.7500e-04) (hash(x)=22007373) +2843 train 7.068204 (lr=1.7500e-04) (hash(x)=25925963) +2844 train 7.078343 (lr=1.7500e-04) (hash(x)=25711128) +2845 train 6.888883 (lr=1.7500e-04) (hash(x)=21881216) +2846 train 6.959761 (lr=1.7500e-04) (hash(x)=20277075) +2847 train 7.023777 (lr=1.7500e-04) (hash(x)=19811802) +2848 train 6.998018 (lr=1.7500e-04) (hash(x)=23878906) +2849 train 7.220140 (lr=1.7500e-04) (hash(x)=25034966) +2850 val loss 7.1690 +2850 val perplexity 1298.5815 +2850 train 7.269586 (lr=1.7500e-04) (hash(x)=24359507) +2851 train 6.987720 (lr=1.7500e-04) (hash(x)=23248423) +2852 train 6.994706 (lr=1.7500e-04) (hash(x)=21782773) +2853 train 7.083095 (lr=1.7500e-04) (hash(x)=23804418) +2854 train 7.158605 (lr=1.7500e-04) (hash(x)=22525078) +2855 train 7.129788 (lr=1.7500e-04) (hash(x)=25579655) +2856 train 7.244564 (lr=1.7500e-04) (hash(x)=27048876) +2857 train 7.375177 (lr=1.7500e-04) (hash(x)=26468479) +2858 train 7.096458 (lr=1.7500e-04) (hash(x)=23854933) +2859 train 7.455669 (lr=1.7500e-04) (hash(x)=25537603) +2860 train 6.872310 (lr=1.7500e-04) (hash(x)=20979252) +2861 train 7.511376 (lr=1.7500e-04) (hash(x)=26504374) +2862 train 7.302128 (lr=1.7500e-04) (hash(x)=27561842) +2863 train 7.268559 (lr=1.7500e-04) (hash(x)=26096514) +2864 train 7.342452 (lr=1.7500e-04) (hash(x)=25926899) +2865 train 7.372670 (lr=1.7500e-04) (hash(x)=26058348) +2866 train 7.327732 (lr=1.7500e-04) (hash(x)=29802259) +2867 train 7.266994 (lr=1.7500e-04) (hash(x)=24132888) +2868 train 6.935298 (lr=1.7500e-04) (hash(x)=23369410) +2869 train 7.151325 (lr=1.7500e-04) (hash(x)=25387506) +2870 train 7.352231 (lr=1.7500e-04) (hash(x)=27375344) +2871 train 7.042134 (lr=1.7500e-04) (hash(x)=22589633) +2872 train 7.205820 (lr=1.7500e-04) (hash(x)=23250237) +2873 train 7.136618 (lr=1.7500e-04) (hash(x)=25511322) +2874 train 6.665932 (lr=1.7500e-04) (hash(x)=18356418) +2875 train 7.191883 (lr=1.7500e-04) (hash(x)=27781566) +2876 train 7.100751 (lr=1.7500e-04) (hash(x)=24878173) +2877 train 7.539466 (lr=1.7500e-04) (hash(x)=30018637) +2878 train 7.368955 (lr=1.7500e-04) (hash(x)=27168416) +2879 train 7.373518 (lr=1.7500e-04) (hash(x)=26757147) +2880 train 7.396504 (lr=1.7500e-04) (hash(x)=26637081) +2881 train 7.286064 (lr=1.7500e-04) (hash(x)=24795024) +2882 train 7.528001 (lr=1.7500e-04) (hash(x)=29787745) +2883 train 7.366390 (lr=1.7500e-04) (hash(x)=26649864) +2884 train 7.159183 (lr=1.7500e-04) (hash(x)=27306612) +2885 train 7.251373 (lr=1.7500e-04) (hash(x)=27568311) +2886 train 7.297287 (lr=1.7500e-04) (hash(x)=27440150) +2887 train 7.001602 (lr=1.7500e-04) (hash(x)=24963730) +2888 train 7.049251 (lr=1.7500e-04) (hash(x)=23619807) +2889 train 7.613582 (lr=1.7500e-04) (hash(x)=29447356) +2890 train 7.146713 (lr=1.7500e-04) (hash(x)=25144675) +2891 train 7.053125 (lr=1.7500e-04) (hash(x)=25249959) +2892 train 7.005979 (lr=1.7500e-04) (hash(x)=26608712) +2893 train 7.021401 (lr=1.7500e-04) (hash(x)=26333258) +2894 train 6.861125 (lr=1.7500e-04) (hash(x)=20682182) +2895 train 7.235977 (lr=1.7500e-04) (hash(x)=27703124) +2896 train 7.096009 (lr=1.7500e-04) (hash(x)=23228180) +2897 train 6.974621 (lr=1.7500e-04) (hash(x)=25252411) +2898 train 6.938149 (lr=1.7500e-04) (hash(x)=22879178) +2899 train 7.253221 (lr=1.7500e-04) (hash(x)=26459082) +2900 val loss 7.2418 +2900 val perplexity 1396.5834 +2900 train 7.087810 (lr=1.7500e-04) (hash(x)=24569501) +2901 train 6.903267 (lr=1.7500e-04) (hash(x)=19803884) +2902 train 6.953936 (lr=1.7500e-04) (hash(x)=18799747) +2903 train 7.188237 (lr=1.7500e-04) (hash(x)=24781713) +2904 train 7.281708 (lr=1.7500e-04) (hash(x)=25016590) +2905 train 7.479315 (lr=1.7500e-04) (hash(x)=29006906) +2906 train 7.252061 (lr=1.7500e-04) (hash(x)=24069959) +2907 train 7.410309 (lr=1.7500e-04) (hash(x)=26597693) +2908 train 7.003560 (lr=1.7500e-04) (hash(x)=25014146) +2909 train 7.237289 (lr=1.7500e-04) (hash(x)=24943747) +2910 train 7.163567 (lr=1.7500e-04) (hash(x)=27847542) +2911 train 7.095203 (lr=1.7500e-04) (hash(x)=24720476) +2912 train 6.953125 (lr=1.7500e-04) (hash(x)=24388804) +2913 train 7.060781 (lr=1.7500e-04) (hash(x)=23567535) +2914 train 7.356862 (lr=1.7500e-04) (hash(x)=29673625) +2915 train 7.142606 (lr=1.7500e-04) (hash(x)=23691295) +2916 train 7.481346 (lr=1.7500e-04) (hash(x)=26572819) +2917 train 7.144185 (lr=1.7500e-04) (hash(x)=23237812) +2918 train 7.355206 (lr=1.7500e-04) (hash(x)=26531016) +2919 train 6.906671 (lr=1.7500e-04) (hash(x)=23481301) +2920 train 7.174587 (lr=1.7500e-04) (hash(x)=24839184) +2921 train 7.019309 (lr=1.7500e-04) (hash(x)=23327755) +2922 train 7.258400 (lr=1.7500e-04) (hash(x)=26347114) +2923 train 7.004760 (lr=1.7500e-04) (hash(x)=23295676) +2924 train 7.026355 (lr=1.7500e-04) (hash(x)=24557178) +2925 train 7.084080 (lr=1.7500e-04) (hash(x)=26067788) +2926 train 7.005565 (lr=1.7500e-04) (hash(x)=25694982) +2927 train 7.099760 (lr=1.7500e-04) (hash(x)=25641033) +2928 train 7.166412 (lr=1.7500e-04) (hash(x)=24906422) +2929 train 7.356650 (lr=1.7500e-04) (hash(x)=27803515) +2930 train 7.349922 (lr=1.7500e-04) (hash(x)=26208803) +2931 train 6.798453 (lr=1.7500e-04) (hash(x)=22441379) +2932 train 7.048191 (lr=1.7500e-04) (hash(x)=24741626) +2933 train 6.947259 (lr=1.7500e-04) (hash(x)=24595257) +2934 train 6.960193 (lr=1.7500e-04) (hash(x)=23939167) +2935 train 7.244102 (lr=1.7500e-04) (hash(x)=27369437) +2936 train 6.907089 (lr=1.7500e-04) (hash(x)=21409783) +2937 train 7.190312 (lr=1.7500e-04) (hash(x)=25923735) +2938 train 7.172760 (lr=1.7500e-04) (hash(x)=29559511) +2939 train 7.053982 (lr=1.7500e-04) (hash(x)=24482272) +2940 train 7.042799 (lr=1.7500e-04) (hash(x)=24767658) +2941 train 7.243824 (lr=1.7500e-04) (hash(x)=26425020) +2942 train 7.548850 (lr=1.7500e-04) (hash(x)=27444868) +2943 train 7.066782 (lr=1.7500e-04) (hash(x)=24760900) +2944 train 7.127953 (lr=1.7500e-04) (hash(x)=25605407) +2945 train 6.968846 (lr=1.7500e-04) (hash(x)=22886951) +2946 train 7.287488 (lr=1.7500e-04) (hash(x)=26112205) +2947 train 7.124971 (lr=1.7500e-04) (hash(x)=23919156) +2948 train 7.097509 (lr=1.7500e-04) (hash(x)=23729312) +2949 train 7.345559 (lr=1.7500e-04) (hash(x)=30440878) +2950 val loss 7.1811 +2950 val perplexity 1314.3418 +2950 train 6.827104 (lr=1.7500e-04) (hash(x)=20004041) +2951 train 6.767864 (lr=1.7500e-04) (hash(x)=21692546) +2952 train 6.843368 (lr=1.7500e-04) (hash(x)=23021681) +2953 train 7.219931 (lr=1.7500e-04) (hash(x)=26663597) +2954 train 7.059988 (lr=1.7500e-04) (hash(x)=23727385) +2955 train 7.037320 (lr=1.7500e-04) (hash(x)=27692087) +2956 train 7.090042 (lr=1.7500e-04) (hash(x)=24003378) +2957 train 7.703537 (lr=1.7500e-04) (hash(x)=29534673) +2958 train 6.967847 (lr=1.7500e-04) (hash(x)=22875068) +2959 train 6.979300 (lr=1.7500e-04) (hash(x)=22720391) +2960 train 6.741879 (lr=1.7500e-04) (hash(x)=17997400) +2961 train 6.962419 (lr=1.7500e-04) (hash(x)=22853822) +2962 train 7.025658 (lr=1.7500e-04) (hash(x)=25238004) +2963 train 7.143003 (lr=1.7500e-04) (hash(x)=26146560) +2964 train 7.265130 (lr=1.7500e-04) (hash(x)=21894867) +2965 train 7.214340 (lr=1.7500e-04) (hash(x)=23001150) +2966 train 6.973134 (lr=1.7500e-04) (hash(x)=23392923) +2967 train 7.040297 (lr=1.7500e-04) (hash(x)=24376979) +2968 train 6.979001 (lr=1.7500e-04) (hash(x)=23781449) +2969 train 7.165488 (lr=1.7500e-04) (hash(x)=25315495) +2970 train 7.266121 (lr=1.7500e-04) (hash(x)=27165470) +2971 train 7.102196 (lr=1.7500e-04) (hash(x)=22917712) +2972 train 7.402341 (lr=1.7500e-04) (hash(x)=27928456) +2973 train 6.893837 (lr=1.7500e-04) (hash(x)=19890855) +2974 train 6.843039 (lr=1.7500e-04) (hash(x)=21318134) +2975 train 6.956619 (lr=1.7500e-04) (hash(x)=22244509) +2976 train 6.862511 (lr=1.7500e-04) (hash(x)=21293137) +2977 train 7.007733 (lr=1.7500e-04) (hash(x)=23465789) +2978 train 6.935184 (lr=1.7500e-04) (hash(x)=21169753) +2979 train 7.285118 (lr=1.7500e-04) (hash(x)=25243385) +2980 train 7.313790 (lr=1.7500e-04) (hash(x)=27465812) +2981 train 7.045317 (lr=1.7500e-04) (hash(x)=24615492) +2982 train 7.011409 (lr=1.7500e-04) (hash(x)=23081307) +2983 train 6.779174 (lr=1.7500e-04) (hash(x)=21831960) +2984 train 6.896872 (lr=1.7500e-04) (hash(x)=23242850) +2985 train 7.032693 (lr=1.7500e-04) (hash(x)=24308188) +2986 train 7.179276 (lr=1.7500e-04) (hash(x)=28541601) +2987 train 7.090309 (lr=1.7500e-04) (hash(x)=24842373) +2988 train 6.823541 (lr=1.7500e-04) (hash(x)=21967126) +2989 train 7.016056 (lr=1.7500e-04) (hash(x)=22951616) +2990 train 7.105682 (lr=1.7500e-04) (hash(x)=24325714) +2991 train 6.917528 (lr=1.7500e-04) (hash(x)=24921535) +2992 train 7.154134 (lr=1.7500e-04) (hash(x)=25937112) +2993 train 6.872718 (lr=1.7500e-04) (hash(x)=20716218) +2994 train 7.137373 (lr=1.7500e-04) (hash(x)=25450724) +2995 train 7.090937 (lr=1.7500e-04) (hash(x)=24344615) +2996 train 6.855202 (lr=1.7500e-04) (hash(x)=20299058) +2997 train 7.040631 (lr=1.7500e-04) (hash(x)=23859426) +2998 train 7.057246 (lr=1.7500e-04) (hash(x)=23094397) +2999 train 7.324637 (lr=1.7500e-04) (hash(x)=25381251) +3000 val loss 7.1781 +3000 val perplexity 1310.4337 +3000 train 7.077592 (lr=1.7500e-04) (hash(x)=23586527) +3001 train 6.979138 (lr=1.7500e-04) (hash(x)=24220410) +3002 train 6.836333 (lr=1.7500e-04) (hash(x)=20597347) +3003 train 6.977251 (lr=1.7500e-04) (hash(x)=22887303) +3004 train 7.239293 (lr=1.7500e-04) (hash(x)=25869462) +3005 train 7.028099 (lr=1.7500e-04) (hash(x)=22098530) +3006 train 7.239326 (lr=1.7500e-04) (hash(x)=26246291) +3007 train 7.211915 (lr=1.7500e-04) (hash(x)=25687352) +3008 train 6.920334 (lr=1.7500e-04) (hash(x)=25425646) +3009 train 7.141959 (lr=1.7500e-04) (hash(x)=26021124) +3010 train 7.178105 (lr=1.7500e-04) (hash(x)=25392057) +3011 train 7.238155 (lr=1.7500e-04) (hash(x)=27791412) +3012 train 7.099927 (lr=1.7500e-04) (hash(x)=23181098) +3013 train 7.068264 (lr=1.7500e-04) (hash(x)=25521889) +3014 train 6.886258 (lr=1.7500e-04) (hash(x)=21685795) +3015 train 7.019195 (lr=1.7500e-04) (hash(x)=25221654) +3016 train 7.236395 (lr=1.7500e-04) (hash(x)=24888744) +3017 train 7.152788 (lr=1.7500e-04) (hash(x)=24200150) +3018 train 7.076468 (lr=1.7500e-04) (hash(x)=26943942) +3019 train 7.053499 (lr=1.7500e-04) (hash(x)=23243731) +3020 train 6.976125 (lr=1.7500e-04) (hash(x)=21068284) +3021 train 7.105314 (lr=1.7500e-04) (hash(x)=23876902) +3022 train 7.191475 (lr=1.7500e-04) (hash(x)=25337639) +3023 train 7.126707 (lr=1.7500e-04) (hash(x)=24469863) +3024 train 7.542474 (lr=1.7500e-04) (hash(x)=27850876) +3025 train 7.380535 (lr=1.7500e-04) (hash(x)=20515778) +3026 train 7.179919 (lr=1.7500e-04) (hash(x)=29019173) +3027 train 6.862883 (lr=1.7500e-04) (hash(x)=22484936) +3028 train 7.015626 (lr=1.7500e-04) (hash(x)=24639400) +3029 train 7.194014 (lr=1.7500e-04) (hash(x)=26835174) +3030 train 7.299837 (lr=1.7500e-04) (hash(x)=29843763) +3031 train 7.028665 (lr=1.7500e-04) (hash(x)=25291413) +3032 train 6.989250 (lr=1.7500e-04) (hash(x)=24590244) +3033 train 7.201889 (lr=1.7500e-04) (hash(x)=28880142) +3034 train 6.950281 (lr=1.7500e-04) (hash(x)=23372199) +3035 train 6.938675 (lr=1.7500e-04) (hash(x)=23952225) +3036 train 7.059258 (lr=1.7500e-04) (hash(x)=24589186) +3037 train 7.063288 (lr=1.7500e-04) (hash(x)=23260323) +3038 train 7.229596 (lr=1.7500e-04) (hash(x)=25824498) +3039 train 7.156667 (lr=1.7500e-04) (hash(x)=25744274) +3040 train 7.116098 (lr=1.7500e-04) (hash(x)=21610247) +3041 train 7.216732 (lr=1.7500e-04) (hash(x)=25079786) +3042 train 6.861989 (lr=1.7500e-04) (hash(x)=23219195) +3043 train 6.875006 (lr=1.7500e-04) (hash(x)=22616739) +3044 train 7.097450 (lr=1.7500e-04) (hash(x)=24908480) +3045 train 6.961802 (lr=1.7500e-04) (hash(x)=22293489) +3046 train 6.965755 (lr=1.7500e-04) (hash(x)=23557651) +3047 train 7.033784 (lr=1.7500e-04) (hash(x)=24246963) +3048 train 7.135561 (lr=1.7500e-04) (hash(x)=24490083) +3049 train 7.141893 (lr=1.7500e-04) (hash(x)=22372895) +3050 val loss 7.1672 +3050 val perplexity 1296.1818 +3050 train 6.839357 (lr=1.7500e-04) (hash(x)=21759470) +3051 train 6.729503 (lr=1.7500e-04) (hash(x)=19407094) +3052 train 7.085852 (lr=1.7500e-04) (hash(x)=23957047) +3053 train 7.220882 (lr=1.7500e-04) (hash(x)=24719318) +3054 train 7.035237 (lr=1.7500e-04) (hash(x)=20719314) +3055 train 6.959976 (lr=1.7500e-04) (hash(x)=19724058) +3056 train 6.842484 (lr=1.7500e-04) (hash(x)=14407266) +3057 train 6.715085 (lr=1.7500e-04) (hash(x)=12468292) +3058 train 6.964498 (lr=1.7500e-04) (hash(x)=16098279) +3059 train 7.023407 (lr=1.7500e-04) (hash(x)=18836491) +3060 train 6.838771 (lr=1.7500e-04) (hash(x)=19132277) +3061 train 7.002957 (lr=1.7500e-04) (hash(x)=22814208) +3062 train 7.021204 (lr=1.7500e-04) (hash(x)=24838508) +3063 train 6.911620 (lr=1.7500e-04) (hash(x)=20705649) +3064 train 7.877033 (lr=1.7500e-04) (hash(x)=29416914) +3065 train 7.335779 (lr=1.7500e-04) (hash(x)=25972430) +3066 train 6.760529 (lr=1.7500e-04) (hash(x)=23705805) +3067 train 6.855470 (lr=1.7500e-04) (hash(x)=21325875) +3068 train 7.051743 (lr=1.7500e-04) (hash(x)=23526506) +3069 train 7.519605 (lr=1.7500e-04) (hash(x)=27282337) +3070 train 7.406103 (lr=1.7500e-04) (hash(x)=27968043) +3071 train 7.147077 (lr=1.7500e-04) (hash(x)=24938685) +3072 train 7.312244 (lr=1.7500e-04) (hash(x)=26942737) +3073 train 7.231843 (lr=1.7500e-04) (hash(x)=23506879) +3074 train 6.973566 (lr=1.7500e-04) (hash(x)=23589913) +3075 train 7.116994 (lr=1.7500e-04) (hash(x)=25152403) +3076 train 7.213085 (lr=1.7500e-04) (hash(x)=23425868) +3077 train 7.333133 (lr=1.7500e-04) (hash(x)=23966181) +3078 train 7.408744 (lr=1.7500e-04) (hash(x)=27312570) +3079 train 7.113866 (lr=1.7500e-04) (hash(x)=21707000) +3080 train 7.047475 (lr=1.7500e-04) (hash(x)=25600427) +3081 train 7.180202 (lr=1.7500e-04) (hash(x)=24270631) +3082 train 7.249341 (lr=1.7500e-04) (hash(x)=25199537) +3083 train 6.715019 (lr=1.7500e-04) (hash(x)=17952018) +3084 train 6.757597 (lr=1.7500e-04) (hash(x)=18733143) +3085 train 7.270631 (lr=1.7500e-04) (hash(x)=26946100) +3086 train 7.083402 (lr=1.7500e-04) (hash(x)=25547515) +3087 train 7.039586 (lr=1.7500e-04) (hash(x)=24948980) +3088 train 8.179268 (lr=1.7500e-04) (hash(x)=35461645) +3089 train 7.245294 (lr=1.7500e-04) (hash(x)=28330877) +3090 train 7.210943 (lr=1.7500e-04) (hash(x)=27687861) +3091 train 7.325111 (lr=1.7500e-04) (hash(x)=28012110) +3092 train 7.183170 (lr=1.7500e-04) (hash(x)=24684480) +3093 train 7.137203 (lr=1.7500e-04) (hash(x)=26225786) +3094 train 6.927021 (lr=1.7500e-04) (hash(x)=23098156) +3095 train 7.414894 (lr=1.7500e-04) (hash(x)=30773958) +3096 train 7.743846 (lr=1.7500e-04) (hash(x)=28640406) +3097 train 7.684067 (lr=1.7500e-04) (hash(x)=28201086) +3098 train 7.989316 (lr=1.7500e-04) (hash(x)=35002344) +3099 train 7.473962 (lr=1.7500e-04) (hash(x)=29481068) +3100 val loss 7.1848 +3100 val perplexity 1319.2469 +3100 train 7.086868 (lr=1.7500e-04) (hash(x)=26374528) +3101 train 7.045560 (lr=1.7500e-04) (hash(x)=24153602) +3102 train 7.083069 (lr=1.7500e-04) (hash(x)=25478746) +3103 train 7.375187 (lr=1.7500e-04) (hash(x)=26769046) +3104 train 7.023197 (lr=1.7500e-04) (hash(x)=21841970) +3105 train 7.256094 (lr=1.7500e-04) (hash(x)=27693052) +3106 train 6.775561 (lr=1.7500e-04) (hash(x)=20689448) +3107 train 7.175872 (lr=1.7500e-04) (hash(x)=26755048) +3108 train 7.131598 (lr=1.7500e-04) (hash(x)=24431904) +3109 train 6.967197 (lr=1.7500e-04) (hash(x)=21009792) +3110 train 7.100776 (lr=1.7500e-04) (hash(x)=21909003) +3111 train 7.131267 (lr=1.7500e-04) (hash(x)=18849656) +3112 train 7.272668 (lr=1.7500e-04) (hash(x)=22223376) +3113 train 7.507572 (lr=1.7500e-04) (hash(x)=25652491) +3114 train 7.403620 (lr=1.7500e-04) (hash(x)=23521434) +3115 train 7.420798 (lr=1.7500e-04) (hash(x)=25449800) +3116 train 7.716462 (lr=1.7500e-04) (hash(x)=27655847) +3117 train 7.763945 (lr=1.7500e-04) (hash(x)=29878248) +3118 train 7.744442 (lr=1.7500e-04) (hash(x)=30444094) +3119 train 7.516643 (lr=1.7500e-04) (hash(x)=24624950) +3120 train 6.908266 (lr=1.7500e-04) (hash(x)=20798511) +3121 train 7.268268 (lr=1.7500e-04) (hash(x)=26581679) +3122 train 7.133344 (lr=1.7500e-04) (hash(x)=25333422) +3123 train 7.215451 (lr=1.7500e-04) (hash(x)=26174069) +3124 train 7.269390 (lr=1.7500e-04) (hash(x)=25219475) +3125 train 7.176430 (lr=1.7500e-04) (hash(x)=20919061) +3126 train 7.113425 (lr=1.7500e-04) (hash(x)=23828688) +3127 train 7.588227 (lr=1.7500e-04) (hash(x)=27299605) +3128 train 6.953815 (lr=1.7500e-04) (hash(x)=23797514) +3129 train 7.222162 (lr=1.7500e-04) (hash(x)=23601883) +3130 train 7.436985 (lr=1.7500e-04) (hash(x)=31003964) +3131 train 7.140743 (lr=1.7500e-04) (hash(x)=24777273) +3132 train 7.019304 (lr=1.7500e-04) (hash(x)=25403249) +3133 train 7.256382 (lr=1.7500e-04) (hash(x)=28913150) +3134 train 7.220694 (lr=1.7500e-04) (hash(x)=26541508) +3135 train 7.159791 (lr=1.7500e-04) (hash(x)=24113445) +3136 train 6.935541 (lr=1.7500e-04) (hash(x)=25464565) +3137 train 7.214225 (lr=1.7500e-04) (hash(x)=26581432) +3138 train 7.068610 (lr=1.7500e-04) (hash(x)=23074513) +3139 train 6.929410 (lr=1.7500e-04) (hash(x)=23970384) +3140 train 7.157924 (lr=1.7500e-04) (hash(x)=26694495) +3141 train 7.132736 (lr=1.7500e-04) (hash(x)=26883445) +3142 train 7.291393 (lr=1.7500e-04) (hash(x)=28632211) +3143 train 7.692796 (lr=1.7500e-04) (hash(x)=32644465) +3144 train 7.412136 (lr=1.7500e-04) (hash(x)=27490443) +3145 train 7.025802 (lr=1.7500e-04) (hash(x)=23814853) +3146 train 7.462759 (lr=1.7500e-04) (hash(x)=29664236) +3147 train 7.783157 (lr=1.7500e-04) (hash(x)=29951548) +3148 train 7.442010 (lr=1.7500e-04) (hash(x)=28426503) +3149 train 6.904700 (lr=1.7500e-04) (hash(x)=23727657) +3150 val loss 7.1610 +3150 val perplexity 1288.2117 +3150 train 7.043793 (lr=1.7500e-04) (hash(x)=21430659) +3151 train 7.079157 (lr=1.7500e-04) (hash(x)=25829219) +3152 train 7.256853 (lr=1.7500e-04) (hash(x)=29735208) +3153 train 7.339278 (lr=1.7500e-04) (hash(x)=28173447) +3154 train 6.981911 (lr=1.7500e-04) (hash(x)=22909641) +3155 train 7.143596 (lr=1.7500e-04) (hash(x)=20556094) +3156 train 6.928108 (lr=1.7500e-04) (hash(x)=24013769) +3157 train 6.926052 (lr=1.7500e-04) (hash(x)=22525971) +3158 train 6.968019 (lr=1.7500e-04) (hash(x)=25492728) +3159 train 7.054905 (lr=1.7500e-04) (hash(x)=25194550) +3160 train 7.168049 (lr=1.7500e-04) (hash(x)=25610603) +3161 train 7.157547 (lr=1.7500e-04) (hash(x)=23848640) +3162 train 6.978967 (lr=1.7500e-04) (hash(x)=24082226) +3163 train 7.362483 (lr=1.7500e-04) (hash(x)=28482186) +3164 train 7.258897 (lr=1.7500e-04) (hash(x)=27542978) +3165 train 7.022974 (lr=1.7500e-04) (hash(x)=22540954) +3166 train 7.121362 (lr=1.7500e-04) (hash(x)=26103641) +3167 train 7.077260 (lr=1.7500e-04) (hash(x)=25941804) +3168 train 7.133865 (lr=1.7500e-04) (hash(x)=25965921) +3169 train 7.352153 (lr=1.7500e-04) (hash(x)=25631269) +3170 train 6.985292 (lr=1.7500e-04) (hash(x)=23471525) +3171 train 7.183412 (lr=1.7500e-04) (hash(x)=27049208) +3172 train 7.216469 (lr=1.7500e-04) (hash(x)=27074992) +3173 train 7.118244 (lr=1.7500e-04) (hash(x)=25712617) +3174 train 7.111630 (lr=1.7500e-04) (hash(x)=25884917) +3175 train 7.098470 (lr=1.7500e-04) (hash(x)=24075727) +3176 train 6.991020 (lr=1.7500e-04) (hash(x)=23681759) +3177 train 7.235797 (lr=1.7500e-04) (hash(x)=25786577) +3178 train 7.259106 (lr=1.7500e-04) (hash(x)=27307614) +3179 train 7.279164 (lr=1.7500e-04) (hash(x)=25082806) +3180 train 7.236469 (lr=1.7500e-04) (hash(x)=26098308) +3181 train 7.042701 (lr=1.7500e-04) (hash(x)=24080140) +3182 train 7.208194 (lr=1.7500e-04) (hash(x)=26399395) +3183 train 7.244639 (lr=1.7500e-04) (hash(x)=23104539) +3184 train 6.933986 (lr=1.7500e-04) (hash(x)=23356930) +3185 train 7.172368 (lr=1.7500e-04) (hash(x)=27972420) +3186 train 6.836319 (lr=1.7500e-04) (hash(x)=21338924) +3187 train 7.269454 (lr=1.7500e-04) (hash(x)=25351113) +3188 train 7.211229 (lr=1.7500e-04) (hash(x)=26019439) +3189 train 7.255437 (lr=1.7500e-04) (hash(x)=30149312) +3190 train 6.986867 (lr=1.7500e-04) (hash(x)=23028152) +3191 train 7.303534 (lr=1.7500e-04) (hash(x)=23018983) +3192 train 6.982841 (lr=1.7500e-04) (hash(x)=23190787) +3193 train 7.391089 (lr=1.7500e-04) (hash(x)=27798543) +3194 train 7.144574 (lr=1.7500e-04) (hash(x)=25193663) +3195 train 7.006139 (lr=1.7500e-04) (hash(x)=25302106) +3196 train 7.117762 (lr=1.7500e-04) (hash(x)=24325364) +3197 train 7.163515 (lr=1.7500e-04) (hash(x)=25399101) +3198 train 6.972734 (lr=1.7500e-04) (hash(x)=23606439) +3199 train 7.066774 (lr=1.7500e-04) (hash(x)=24422929) +3200 val loss 7.1575 +3200 val perplexity 1283.7035 +3200 train 7.210978 (lr=1.7500e-04) (hash(x)=24760381) +3201 train 6.840621 (lr=1.7500e-04) (hash(x)=23278576) +3202 train 7.117383 (lr=1.7500e-04) (hash(x)=24897511) +3203 train 7.368072 (lr=1.7500e-04) (hash(x)=29052117) +3204 train 7.126006 (lr=1.7500e-04) (hash(x)=25772923) +3205 train 7.293387 (lr=1.7500e-04) (hash(x)=25885977) +3206 train 7.061847 (lr=1.7500e-04) (hash(x)=21985272) +3207 train 7.008473 (lr=1.7500e-04) (hash(x)=23389696) +3208 train 6.926134 (lr=1.7500e-04) (hash(x)=25299042) +3209 train 7.148393 (lr=1.7500e-04) (hash(x)=23703987) +3210 train 7.070008 (lr=1.7500e-04) (hash(x)=23362342) +3211 train 7.141629 (lr=1.7500e-04) (hash(x)=23962503) +3212 train 7.027849 (lr=1.7500e-04) (hash(x)=21216023) +3213 train 7.133648 (lr=1.7500e-04) (hash(x)=25841931) +3214 train 7.064238 (lr=1.7500e-04) (hash(x)=23631428) +3215 train 7.458093 (lr=1.7500e-04) (hash(x)=29102969) +3216 train 7.234357 (lr=1.7500e-04) (hash(x)=25782766) +3217 train 7.514339 (lr=1.7500e-04) (hash(x)=28825867) +3218 train 7.411815 (lr=1.7500e-04) (hash(x)=24609499) +3219 train 7.395941 (lr=1.7500e-04) (hash(x)=24948166) +3220 train 7.383586 (lr=1.7500e-04) (hash(x)=26919841) +3221 train 7.242690 (lr=1.7500e-04) (hash(x)=27236198) +3222 train 7.041771 (lr=1.7500e-04) (hash(x)=24029305) +3223 train 7.551357 (lr=1.7500e-04) (hash(x)=28359859) +3224 train 7.348105 (lr=1.7500e-04) (hash(x)=24886008) +3225 train 7.157516 (lr=1.7500e-04) (hash(x)=27159867) +3226 train 7.410347 (lr=1.7500e-04) (hash(x)=20672023) +3227 train 7.107216 (lr=1.7500e-04) (hash(x)=22360298) +3228 train 7.502493 (lr=1.7500e-04) (hash(x)=27478658) +3229 train 7.304738 (lr=1.7500e-04) (hash(x)=26575886) +3230 train 7.482227 (lr=1.7500e-04) (hash(x)=26890615) +3231 train 7.084275 (lr=1.7500e-04) (hash(x)=24630955) +3232 train 7.355739 (lr=1.7500e-04) (hash(x)=27016054) +3233 train 7.570104 (lr=1.7500e-04) (hash(x)=28444407) +3234 train 6.988646 (lr=1.7500e-04) (hash(x)=24053336) +3235 train 7.301804 (lr=1.7500e-04) (hash(x)=26897402) +3236 train 7.455142 (lr=1.7500e-04) (hash(x)=29451214) +3237 train 7.251577 (lr=1.7500e-04) (hash(x)=27268677) +3238 train 7.360761 (lr=1.7500e-04) (hash(x)=27494000) +3239 train 7.026864 (lr=1.7500e-04) (hash(x)=22969113) +3240 train 6.987864 (lr=1.7500e-04) (hash(x)=21944576) +3241 train 7.209199 (lr=1.7500e-04) (hash(x)=21671079) +3242 train 7.079146 (lr=1.7500e-04) (hash(x)=23912980) +3243 train 7.047283 (lr=1.7500e-04) (hash(x)=25205781) +3244 train 7.057874 (lr=1.7500e-04) (hash(x)=25654244) +3245 train 6.967327 (lr=1.7500e-04) (hash(x)=23335929) +3246 train 7.367068 (lr=1.7500e-04) (hash(x)=27953926) +3247 train 7.147697 (lr=1.7500e-04) (hash(x)=27004415) +3248 train 6.841556 (lr=1.7500e-04) (hash(x)=20471566) +3249 train 7.015058 (lr=1.7500e-04) (hash(x)=25797941) +3250 val loss 7.1474 +3250 val perplexity 1270.7611 +3250 train 6.964276 (lr=1.7500e-04) (hash(x)=21787064) +3251 train 6.914678 (lr=1.7500e-04) (hash(x)=22974875) +3252 train 7.251522 (lr=1.7500e-04) (hash(x)=28431267) +3253 train 7.097882 (lr=1.7500e-04) (hash(x)=25584910) +3254 train 6.909697 (lr=1.7500e-04) (hash(x)=23888922) +3255 train 7.124433 (lr=1.7500e-04) (hash(x)=22265063) +3256 train 6.822380 (lr=1.7500e-04) (hash(x)=21926624) +3257 train 7.032625 (lr=1.7500e-04) (hash(x)=23073191) +3258 train 7.052111 (lr=1.7500e-04) (hash(x)=24409183) +3259 train 7.108142 (lr=1.7500e-04) (hash(x)=23312114) +3260 train 6.995422 (lr=1.7500e-04) (hash(x)=21001289) +3261 train 7.178102 (lr=1.7500e-04) (hash(x)=25514824) +3262 train 6.947548 (lr=1.7500e-04) (hash(x)=22526800) +3263 train 7.356418 (lr=1.7500e-04) (hash(x)=26905990) +3264 train 7.042505 (lr=1.7500e-04) (hash(x)=24469631) +3265 train 6.903506 (lr=1.7500e-04) (hash(x)=21149081) +3266 train 7.079740 (lr=1.7500e-04) (hash(x)=24696215) +3267 train 7.402442 (lr=1.7500e-04) (hash(x)=27089280) +3268 train 6.928382 (lr=1.7500e-04) (hash(x)=23100446) +3269 train 7.208334 (lr=1.7500e-04) (hash(x)=25061229) +3270 train 7.106979 (lr=1.7500e-04) (hash(x)=24337543) +3271 train 7.183310 (lr=1.7500e-04) (hash(x)=24047679) +3272 train 7.227606 (lr=1.7500e-04) (hash(x)=27616773) +3273 train 7.113374 (lr=1.7500e-04) (hash(x)=25315110) +3274 train 7.200028 (lr=1.7500e-04) (hash(x)=28354645) +3275 train 7.055183 (lr=1.7500e-04) (hash(x)=25034684) +3276 train 7.104527 (lr=1.7500e-04) (hash(x)=23550342) +3277 train 7.752319 (lr=1.7500e-04) (hash(x)=28661487) +3278 train 7.317528 (lr=1.7500e-04) (hash(x)=24724622) +3279 train 7.229446 (lr=1.7500e-04) (hash(x)=26905582) +3280 train 7.325096 (lr=1.7500e-04) (hash(x)=26838818) +3281 train 7.063447 (lr=1.7500e-04) (hash(x)=23949017) +3282 train 6.583404 (lr=1.7500e-04) (hash(x)=18846300) +3283 train 6.894512 (lr=1.7500e-04) (hash(x)=21406950) +3284 train 6.774353 (lr=1.7500e-04) (hash(x)=21157696) +3285 train 6.844669 (lr=1.7500e-04) (hash(x)=21440152) +3286 train 7.025944 (lr=1.7500e-04) (hash(x)=26749182) +3287 train 7.239377 (lr=1.7500e-04) (hash(x)=29018970) +3288 train 7.162273 (lr=1.7500e-04) (hash(x)=27577517) +3289 train 6.825613 (lr=1.7500e-04) (hash(x)=19190537) +3290 train 6.847927 (lr=1.7500e-04) (hash(x)=21957991) +3291 train 6.921039 (lr=1.7500e-04) (hash(x)=20853530) +3292 train 6.827934 (lr=1.7500e-04) (hash(x)=22291731) +3293 train 6.984787 (lr=1.7500e-04) (hash(x)=23786853) +3294 train 7.174705 (lr=1.7500e-04) (hash(x)=25740147) +3295 train 7.331352 (lr=1.7500e-04) (hash(x)=24503315) +3296 train 7.027004 (lr=1.7500e-04) (hash(x)=22541728) +3297 train 7.291989 (lr=1.7500e-04) (hash(x)=27067328) +3298 train 6.971250 (lr=1.7500e-04) (hash(x)=22600715) +3299 train 6.986787 (lr=1.7500e-04) (hash(x)=23080074) +3300 val loss 7.1402 +3300 val perplexity 1261.6881 +3300 train 6.791318 (lr=1.7500e-04) (hash(x)=22097758) +3301 train 6.952255 (lr=1.7500e-04) (hash(x)=24105430) +3302 train 6.814991 (lr=1.7500e-04) (hash(x)=23343775) +3303 train 7.061583 (lr=1.7500e-04) (hash(x)=22607537) +3304 train 7.148815 (lr=1.7500e-04) (hash(x)=26501182) +3305 train 7.398313 (lr=1.7500e-04) (hash(x)=26063650) +3306 train 7.009855 (lr=1.7500e-04) (hash(x)=23486602) +3307 train 8.190028 (lr=1.7500e-04) (hash(x)=32179773) +3308 train 11.753247 (lr=1.7500e-04) (hash(x)=66155855) +3309 train 8.541724 (lr=1.7500e-04) (hash(x)=37724427) +3310 train 7.553449 (lr=1.7500e-04) (hash(x)=28861610) +3311 train 7.504314 (lr=1.7500e-04) (hash(x)=26690225) +3312 train 7.117397 (lr=1.7500e-04) (hash(x)=24136450) +3313 train 7.356938 (lr=1.7500e-04) (hash(x)=23702010) +3314 train 7.529008 (lr=1.7500e-04) (hash(x)=28761762) +3315 train 6.914485 (lr=1.7500e-04) (hash(x)=22109609) +3316 train 7.281629 (lr=1.7500e-04) (hash(x)=25168631) +3317 train 7.174951 (lr=1.7500e-04) (hash(x)=24503786) +3318 train 7.242912 (lr=1.7500e-04) (hash(x)=23698606) +3319 train 7.208584 (lr=1.7500e-04) (hash(x)=24226255) +3320 train 7.800180 (lr=1.7500e-04) (hash(x)=31110577) +3321 train 7.161284 (lr=1.7500e-04) (hash(x)=24752754) +3322 train 6.989809 (lr=1.7500e-04) (hash(x)=21135610) +3323 train 6.916419 (lr=1.7500e-04) (hash(x)=23013573) +3324 train 6.697486 (lr=1.7500e-04) (hash(x)=20289715) +3325 train 6.931018 (lr=1.7500e-04) (hash(x)=22700287) +3326 train 7.039196 (lr=1.7500e-04) (hash(x)=21320362) +3327 train 7.137834 (lr=1.7500e-04) (hash(x)=23622702) +3328 train 7.482096 (lr=1.7500e-04) (hash(x)=27435461) +3329 train 7.225006 (lr=1.7500e-04) (hash(x)=25435452) +3330 train 7.200794 (lr=1.7500e-04) (hash(x)=27952557) +3331 train 6.885974 (lr=1.7500e-04) (hash(x)=21517429) +3332 train 7.028159 (lr=1.7500e-04) (hash(x)=24288985) +3333 train 7.150601 (lr=1.7500e-04) (hash(x)=23374788) +3334 train 6.889312 (lr=1.7500e-04) (hash(x)=22042499) +3335 train 7.213384 (lr=1.7500e-04) (hash(x)=23910425) +3336 train 7.518922 (lr=1.7500e-04) (hash(x)=28118508) +3337 train 7.275724 (lr=1.7500e-04) (hash(x)=26737440) +3338 train 7.047891 (lr=1.7500e-04) (hash(x)=24472271) +3339 train 7.013773 (lr=1.7500e-04) (hash(x)=24407484) +3340 train 7.544167 (lr=1.7500e-04) (hash(x)=27908937) +3341 train 7.656087 (lr=1.7500e-04) (hash(x)=29038937) +3342 train 7.482044 (lr=1.7500e-04) (hash(x)=24802580) +3343 train 7.469516 (lr=1.7500e-04) (hash(x)=27213318) +3344 train 7.495901 (lr=1.7500e-04) (hash(x)=28693458) +3345 train 6.854120 (lr=1.7500e-04) (hash(x)=20332324) +3346 train 7.188713 (lr=1.7500e-04) (hash(x)=26726007) +3347 train 7.166356 (lr=1.7500e-04) (hash(x)=25524191) +3348 train 7.224420 (lr=1.7500e-04) (hash(x)=25553293) +3349 train 7.180773 (lr=1.7500e-04) (hash(x)=25614848) +3350 val loss 7.1723 +3350 val perplexity 1302.8120 +3350 train 7.191109 (lr=1.7500e-04) (hash(x)=25747903) +3351 train 7.175708 (lr=1.7500e-04) (hash(x)=26701577) +3352 train 6.935063 (lr=1.7500e-04) (hash(x)=21964135) +3353 train 7.025764 (lr=1.7500e-04) (hash(x)=24461007) +3354 train 7.011850 (lr=1.7500e-04) (hash(x)=25818495) +3355 train 6.877687 (lr=1.7500e-04) (hash(x)=22091266) +3356 train 6.953931 (lr=1.7500e-04) (hash(x)=24476213) +3357 train 7.234984 (lr=1.7500e-04) (hash(x)=24500423) +3358 train 6.951775 (lr=1.7500e-04) (hash(x)=21754841) +3359 train 7.313455 (lr=1.7500e-04) (hash(x)=26216794) +3360 train 6.841376 (lr=1.7500e-04) (hash(x)=24267249) +3361 train 7.187599 (lr=1.7500e-04) (hash(x)=23143515) +3362 train 7.034561 (lr=1.7500e-04) (hash(x)=24120302) +3363 train 7.094448 (lr=1.7500e-04) (hash(x)=20817340) +3364 train 7.102859 (lr=1.7500e-04) (hash(x)=22285847) +3365 train 7.444482 (lr=1.7500e-04) (hash(x)=28151597) +3366 train 7.873030 (lr=1.7500e-04) (hash(x)=31593285) +3367 train 7.503781 (lr=1.7500e-04) (hash(x)=27579623) +3368 train 7.146414 (lr=1.7500e-04) (hash(x)=24995988) +3369 train 6.844210 (lr=1.7500e-04) (hash(x)=22166810) +3370 train 7.036275 (lr=1.7500e-04) (hash(x)=23948298) +3371 train 6.915143 (lr=1.7500e-04) (hash(x)=21532187) +3372 train 7.019825 (lr=1.7500e-04) (hash(x)=23571652) +3373 train 7.400546 (lr=1.7500e-04) (hash(x)=26911513) +3374 train 7.328864 (lr=1.7500e-04) (hash(x)=24011329) +3375 train 7.513686 (lr=1.7500e-04) (hash(x)=26086198) +3376 train 7.058293 (lr=1.7500e-04) (hash(x)=22844402) +3377 train 7.034212 (lr=1.7500e-04) (hash(x)=21817762) +3378 train 7.146253 (lr=1.7500e-04) (hash(x)=23903232) +3379 train 7.056647 (lr=1.7500e-04) (hash(x)=23911729) +3380 train 7.071306 (lr=1.7500e-04) (hash(x)=24485288) +3381 train 7.263398 (lr=1.7500e-04) (hash(x)=27955492) +3382 train 6.968929 (lr=1.7500e-04) (hash(x)=25884586) +3383 train 7.134427 (lr=1.7500e-04) (hash(x)=24863441) +3384 train 7.384078 (lr=1.7500e-04) (hash(x)=22045992) +3385 train 7.552307 (lr=1.7500e-04) (hash(x)=29174796) +3386 train 7.814861 (lr=1.7500e-04) (hash(x)=32589942) +3387 train 7.465740 (lr=1.7500e-04) (hash(x)=28856978) +3388 train 6.964976 (lr=1.7500e-04) (hash(x)=21667904) +3389 train 6.945020 (lr=1.7500e-04) (hash(x)=23431801) +3390 train 6.826439 (lr=1.7500e-04) (hash(x)=20877285) +3391 train 7.006465 (lr=1.7500e-04) (hash(x)=25236385) +3392 train 7.220442 (lr=1.7500e-04) (hash(x)=25373071) +3393 train 7.425226 (lr=1.7500e-04) (hash(x)=25713464) +3394 train 7.429379 (lr=1.7500e-04) (hash(x)=25713475) +3395 train 7.274927 (lr=1.7500e-04) (hash(x)=24278687) +3396 train 7.368627 (lr=1.7500e-04) (hash(x)=27491349) +3397 train 7.269774 (lr=1.7500e-04) (hash(x)=24513692) +3398 train 7.347581 (lr=1.7500e-04) (hash(x)=26853415) +3399 train 7.387937 (lr=1.7500e-04) (hash(x)=25330803) +3400 val loss 7.1597 +3400 val perplexity 1286.5229 +3400 train 7.364240 (lr=1.7500e-04) (hash(x)=26578066) +3401 train 7.378873 (lr=1.7500e-04) (hash(x)=26811522) +3402 train 7.089369 (lr=1.7500e-04) (hash(x)=25611092) +3403 train 6.948939 (lr=1.7500e-04) (hash(x)=21568545) +3404 train 6.948222 (lr=1.7500e-04) (hash(x)=22756484) +3405 train 7.156212 (lr=1.7500e-04) (hash(x)=27927608) +3406 train 7.211287 (lr=1.7500e-04) (hash(x)=27497018) +3407 train 7.057658 (lr=1.7500e-04) (hash(x)=22508532) +3408 train 7.476480 (lr=1.7500e-04) (hash(x)=26673287) +3409 train 7.123804 (lr=1.7500e-04) (hash(x)=23675869) +3410 train 7.103549 (lr=1.7500e-04) (hash(x)=25496948) +3411 train 7.037792 (lr=1.7500e-04) (hash(x)=24850662) +3412 train 7.299570 (lr=1.7500e-04) (hash(x)=29790167) +3413 train 6.997850 (lr=1.7500e-04) (hash(x)=24193434) +3414 train 7.322447 (lr=1.7500e-04) (hash(x)=25310919) +3415 train 6.986441 (lr=1.7500e-04) (hash(x)=21799261) +3416 train 7.314770 (lr=1.7500e-04) (hash(x)=26620074) +3417 train 7.257268 (lr=1.7500e-04) (hash(x)=26719309) +3418 train 7.486835 (lr=1.7500e-04) (hash(x)=23190530) +3419 train 7.183415 (lr=1.7500e-04) (hash(x)=24884891) +3420 train 7.213873 (lr=1.7500e-04) (hash(x)=25545849) +3421 train 7.166431 (lr=1.7500e-04) (hash(x)=26021405) +3422 train 7.120420 (lr=1.7500e-04) (hash(x)=23887343) +3423 train 7.194095 (lr=1.7500e-04) (hash(x)=26311168) +3424 train 6.885400 (lr=1.7500e-04) (hash(x)=21051541) +3425 train 7.261508 (lr=1.7500e-04) (hash(x)=23553179) +3426 train 7.118367 (lr=1.7500e-04) (hash(x)=24345540) +3427 train 7.539843 (lr=1.7500e-04) (hash(x)=27549895) +3428 train 6.903366 (lr=1.7500e-04) (hash(x)=22559753) +3429 train 6.883457 (lr=1.7500e-04) (hash(x)=21647642) +3430 train 6.749942 (lr=1.7500e-04) (hash(x)=20130901) +3431 train 6.887747 (lr=1.7500e-04) (hash(x)=20977430) +3432 train 6.889501 (lr=1.7500e-04) (hash(x)=21356429) +3433 train 6.911274 (lr=1.7500e-04) (hash(x)=23494380) +3434 train 7.145531 (lr=1.7500e-04) (hash(x)=23805501) +3435 train 7.085725 (lr=1.7500e-04) (hash(x)=23448855) +3436 train 7.462500 (lr=1.7500e-04) (hash(x)=26000319) +3437 train 6.959353 (lr=1.7500e-04) (hash(x)=21760032) +3438 train 7.051581 (lr=1.7500e-04) (hash(x)=24424886) +3439 train 7.430901 (lr=1.7500e-04) (hash(x)=26941617) +3440 train 7.490906 (lr=1.7500e-04) (hash(x)=26798528) +3441 train 7.499722 (lr=1.7500e-04) (hash(x)=27464193) +3442 train 7.392787 (lr=1.7500e-04) (hash(x)=25649118) +3443 train 7.387764 (lr=1.7500e-04) (hash(x)=26953192) +3444 train 7.219925 (lr=1.7500e-04) (hash(x)=22224958) +3445 train 7.018676 (lr=1.7500e-04) (hash(x)=24044587) +3446 train 7.435754 (lr=1.7500e-04) (hash(x)=29584466) +3447 train 7.823983 (lr=1.7500e-04) (hash(x)=30008957) +3448 train 7.671762 (lr=1.7500e-04) (hash(x)=26059290) +3449 train 6.691388 (lr=1.7500e-04) (hash(x)=19733965) +3450 val loss 7.1520 +3450 val perplexity 1276.6445 +3450 train 7.208761 (lr=1.7500e-04) (hash(x)=23960200) +3451 train 7.393759 (lr=1.7500e-04) (hash(x)=27069893) +3452 train 6.975605 (lr=1.7500e-04) (hash(x)=23947772) +3453 train 7.076297 (lr=1.7500e-04) (hash(x)=22707406) +3454 train 7.257429 (lr=1.7500e-04) (hash(x)=27832550) +3455 train 7.135204 (lr=1.7500e-04) (hash(x)=27125962) +3456 train 7.024718 (lr=1.7500e-04) (hash(x)=24510254) +3457 train 6.844201 (lr=1.7500e-04) (hash(x)=23545652) +3458 train 6.925184 (lr=1.7500e-04) (hash(x)=23554751) +3459 train 7.021343 (lr=1.7500e-04) (hash(x)=23341415) +3460 train 7.171093 (lr=1.7500e-04) (hash(x)=21784583) +3461 train 6.999105 (lr=1.7500e-04) (hash(x)=22214769) +3462 train 7.059021 (lr=1.7500e-04) (hash(x)=24206922) +3463 train 7.156841 (lr=1.7500e-04) (hash(x)=25888358) +3464 train 6.953642 (lr=1.7500e-04) (hash(x)=22689666) +3465 train 7.072027 (lr=1.7500e-04) (hash(x)=24918697) +3466 train 7.347877 (lr=1.7500e-04) (hash(x)=28237214) +3467 train 7.440694 (lr=1.7500e-04) (hash(x)=26761645) +3468 train 7.150291 (lr=1.7500e-04) (hash(x)=26979307) +3469 train 7.026437 (lr=1.7500e-04) (hash(x)=23553754) +3470 train 7.208766 (lr=1.7500e-04) (hash(x)=25256849) +3471 train 7.122548 (lr=1.7500e-04) (hash(x)=21725719) +3472 train 7.166109 (lr=1.7500e-04) (hash(x)=24897801) +3473 train 7.095201 (lr=1.7500e-04) (hash(x)=26175307) +3474 train 6.898605 (lr=1.7500e-04) (hash(x)=23309218) +3475 train 7.009048 (lr=1.7500e-04) (hash(x)=25746493) +3476 train 7.305762 (lr=1.7500e-04) (hash(x)=27169613) +3477 train 7.023416 (lr=1.7500e-04) (hash(x)=22937341) +3478 train 7.140618 (lr=1.7500e-04) (hash(x)=24250636) +3479 train 7.005024 (lr=1.7500e-04) (hash(x)=21669704) +3480 train 6.994879 (lr=1.7500e-04) (hash(x)=24431839) +3481 train 7.015013 (lr=1.7500e-04) (hash(x)=22763387) +3482 train 7.006412 (lr=1.7500e-04) (hash(x)=20489446) +3483 train 6.961530 (lr=1.7500e-04) (hash(x)=21167493) +3484 train 6.960449 (lr=1.7500e-04) (hash(x)=23465087) +3485 train 7.202396 (lr=1.7500e-04) (hash(x)=26175023) +3486 train 7.241490 (lr=1.7500e-04) (hash(x)=24986207) +3487 train 6.906887 (lr=1.7500e-04) (hash(x)=23166993) +3488 train 7.140598 (lr=1.7500e-04) (hash(x)=25281216) +3489 train 6.914476 (lr=1.7500e-04) (hash(x)=21824285) +3490 train 6.967544 (lr=1.7500e-04) (hash(x)=22352750) +3491 train 7.235209 (lr=1.7500e-04) (hash(x)=23947208) +3492 train 7.236273 (lr=1.7500e-04) (hash(x)=26257363) +3493 train 7.118634 (lr=1.7500e-04) (hash(x)=25103214) +3494 train 7.163177 (lr=1.7500e-04) (hash(x)=25267583) +3495 train 7.229260 (lr=1.7500e-04) (hash(x)=26235974) +3496 train 7.371095 (lr=1.7500e-04) (hash(x)=26430769) +3497 train 7.768583 (lr=1.7500e-04) (hash(x)=28282027) +3498 train 7.670128 (lr=1.7500e-04) (hash(x)=28386462) +3499 train 7.281337 (lr=1.7500e-04) (hash(x)=29822604) +3500 val loss 7.1623 +3500 val perplexity 1289.9003 +3500 train 7.161780 (lr=1.7500e-04) (hash(x)=29225386) +3501 train 7.082816 (lr=1.7500e-04) (hash(x)=25249294) +3502 train 6.859853 (lr=1.7500e-04) (hash(x)=20020741) +3503 train 7.041598 (lr=1.7500e-04) (hash(x)=25426430) +3504 train 7.017082 (lr=1.7500e-04) (hash(x)=25720411) +3505 train 7.009720 (lr=1.7500e-04) (hash(x)=25602639) +3506 train 7.167655 (lr=1.7500e-04) (hash(x)=26724388) +3507 train 7.030766 (lr=1.7500e-04) (hash(x)=26043735) +3508 train 7.033649 (lr=1.7500e-04) (hash(x)=24955163) +3509 train 6.960768 (lr=1.7500e-04) (hash(x)=20936107) +3510 train 6.955119 (lr=1.7500e-04) (hash(x)=20317378) +3511 train 7.041889 (lr=1.7500e-04) (hash(x)=22966314) +3512 train 7.358407 (lr=1.7500e-04) (hash(x)=25870930) +3513 train 7.166677 (lr=1.7500e-04) (hash(x)=24656635) +3514 train 7.387955 (lr=1.7500e-04) (hash(x)=28576810) +3515 train 7.312627 (lr=1.7500e-04) (hash(x)=27944619) +3516 train 7.188219 (lr=1.7500e-04) (hash(x)=27421509) +3517 train 6.907046 (lr=1.7500e-04) (hash(x)=20844620) +3518 train 7.077152 (lr=1.7500e-04) (hash(x)=28569406) +3519 train 7.039501 (lr=1.7500e-04) (hash(x)=23448505) +3520 train 7.170144 (lr=1.7500e-04) (hash(x)=24852577) +3521 train 7.058159 (lr=1.7500e-04) (hash(x)=23963103) +3522 train 6.961614 (lr=1.7500e-04) (hash(x)=24816516) +3523 train 7.154230 (lr=1.7500e-04) (hash(x)=24205942) +3524 train 6.788138 (lr=1.7500e-04) (hash(x)=20988660) +3525 train 6.890996 (lr=1.7500e-04) (hash(x)=21631366) +3526 train 7.080603 (lr=1.7500e-04) (hash(x)=23499370) +3527 train 7.194627 (lr=1.7500e-04) (hash(x)=26330693) +3528 train 6.858247 (lr=1.7500e-04) (hash(x)=23937176) +3529 train 7.061096 (lr=1.7500e-04) (hash(x)=27345885) +3530 train 6.816927 (lr=1.7500e-04) (hash(x)=21104610) +3531 train 7.153006 (lr=1.7500e-04) (hash(x)=24844466) +3532 train 6.574697 (lr=1.7500e-04) (hash(x)=21055483) +3533 train 6.851823 (lr=1.7500e-04) (hash(x)=23229414) +3534 train 7.162071 (lr=1.7500e-04) (hash(x)=26676920) +3535 train 7.137455 (lr=1.7500e-04) (hash(x)=29550596) +3536 train 6.936055 (lr=1.7500e-04) (hash(x)=22231942) +3537 train 7.080327 (lr=1.7500e-04) (hash(x)=25843852) +3538 train 7.231854 (lr=1.7500e-04) (hash(x)=27110533) +3539 train 6.811754 (lr=1.7500e-04) (hash(x)=20506540) +3540 train 6.893936 (lr=1.7500e-04) (hash(x)=21599346) +3541 train 7.091966 (lr=1.7500e-04) (hash(x)=26395519) +3542 train 7.059380 (lr=1.7500e-04) (hash(x)=25892512) +3543 train 7.158497 (lr=1.7500e-04) (hash(x)=22124892) +3544 train 6.977965 (lr=1.7500e-04) (hash(x)=21882567) +3545 train 7.078069 (lr=1.7500e-04) (hash(x)=24316212) +3546 train 6.988523 (lr=1.7500e-04) (hash(x)=24296310) +3547 train 7.056581 (lr=1.7500e-04) (hash(x)=24867036) +3548 train 7.050365 (lr=1.7500e-04) (hash(x)=23351896) +3549 train 7.045500 (lr=1.7500e-04) (hash(x)=21576408) +3550 val loss 7.1517 +3550 val perplexity 1276.2653 +3550 train 7.134718 (lr=1.7500e-04) (hash(x)=26377338) +3551 train 6.986444 (lr=1.7500e-04) (hash(x)=25607640) +3552 train 7.311121 (lr=1.7500e-04) (hash(x)=27619776) +3553 train 6.831207 (lr=1.7500e-04) (hash(x)=23454533) +3554 train 6.982948 (lr=1.7500e-04) (hash(x)=22542519) +3555 train 7.088820 (lr=1.7500e-04) (hash(x)=26176930) +3556 train 6.854880 (lr=1.7500e-04) (hash(x)=22815181) +3557 train 6.880360 (lr=1.7500e-04) (hash(x)=21821757) +3558 train 6.886158 (lr=1.7500e-04) (hash(x)=23988293) +3559 train 6.792653 (lr=1.7500e-04) (hash(x)=23795894) +3560 train 6.732559 (lr=1.7500e-04) (hash(x)=22898969) +3561 train 6.750221 (lr=1.7500e-04) (hash(x)=21510825) +3562 train 6.665001 (lr=1.7500e-04) (hash(x)=22499317) +3563 train 6.692358 (lr=1.7500e-04) (hash(x)=23756298) +3564 train 6.725007 (lr=1.7500e-04) (hash(x)=23964512) +3565 train 6.913257 (lr=1.7500e-04) (hash(x)=23262803) +3566 train 7.125930 (lr=1.7500e-04) (hash(x)=23347279) +3567 train 7.012026 (lr=1.7500e-04) (hash(x)=24165449) +3568 train 7.149513 (lr=1.7500e-04) (hash(x)=25503946) +3569 train 7.139252 (lr=1.7500e-04) (hash(x)=26532839) +3570 train 6.819815 (lr=1.7500e-04) (hash(x)=21889816) +3571 train 7.111526 (lr=1.7500e-04) (hash(x)=26643739) +3572 train 7.319412 (lr=1.7500e-04) (hash(x)=26826130) +3573 train 7.312299 (lr=1.7500e-04) (hash(x)=25810624) +3574 train 7.234935 (lr=1.7500e-04) (hash(x)=23080331) +3575 train 7.326925 (lr=1.7500e-04) (hash(x)=24697756) +3576 train 7.173556 (lr=1.7500e-04) (hash(x)=25158900) +3577 train 7.304939 (lr=1.7500e-04) (hash(x)=25793633) +3578 train 6.979768 (lr=1.7500e-04) (hash(x)=21468493) +3579 train 7.162035 (lr=1.7500e-04) (hash(x)=24431101) +3580 train 7.036739 (lr=1.7500e-04) (hash(x)=27314357) +3581 train 7.247882 (lr=1.7500e-04) (hash(x)=26286249) +3582 train 7.471935 (lr=1.7500e-04) (hash(x)=25954856) +3583 train 7.394560 (lr=1.7500e-04) (hash(x)=27218899) +3584 train 7.210980 (lr=1.7500e-04) (hash(x)=24249114) +3585 train 7.035263 (lr=1.7500e-04) (hash(x)=23659934) +3586 train 7.043041 (lr=1.7500e-04) (hash(x)=25995600) +3587 train 6.938167 (lr=1.7500e-04) (hash(x)=29462219) +3588 train 7.147493 (lr=1.7500e-04) (hash(x)=23346714) +3589 train 7.146894 (lr=1.7500e-04) (hash(x)=27168432) +3590 train 7.071409 (lr=1.7500e-04) (hash(x)=23954240) +3591 train 6.993951 (lr=1.7500e-04) (hash(x)=24748522) +3592 train 7.191901 (lr=1.7500e-04) (hash(x)=24887007) +3593 train 6.953894 (lr=1.7500e-04) (hash(x)=25539383) +3594 train 6.870262 (lr=1.7500e-04) (hash(x)=20104613) +3595 train 7.373897 (lr=1.7500e-04) (hash(x)=24843486) +3596 train 7.351035 (lr=1.7500e-04) (hash(x)=24357864) +3597 train 7.074669 (lr=1.7500e-04) (hash(x)=23873745) +3598 train 7.244047 (lr=1.7500e-04) (hash(x)=25142829) +3599 train 7.296944 (lr=1.7500e-04) (hash(x)=24965317) +3600 val loss 7.1446 +3600 val perplexity 1267.2236 +3600 train 6.756383 (lr=1.7500e-04) (hash(x)=18505205) +3601 train 6.772910 (lr=1.7500e-04) (hash(x)=23632877) +3602 train 7.022922 (lr=1.7500e-04) (hash(x)=23704554) +3603 train 7.164852 (lr=1.7500e-04) (hash(x)=26584754) +3604 train 6.851146 (lr=1.7500e-04) (hash(x)=20667709) +3605 train 6.702628 (lr=1.7500e-04) (hash(x)=20573248) +3606 train 6.824588 (lr=1.7500e-04) (hash(x)=23998997) +3607 train 6.995632 (lr=1.7500e-04) (hash(x)=22031210) +3608 train 7.062558 (lr=1.7500e-04) (hash(x)=24124536) +3609 train 6.946050 (lr=1.7500e-04) (hash(x)=22650144) +3610 train 7.086483 (lr=1.7500e-04) (hash(x)=23796998) +3611 train 7.082790 (lr=1.7500e-04) (hash(x)=24860582) +3612 train 6.626107 (lr=1.7500e-04) (hash(x)=20591300) +3613 train 7.037895 (lr=1.7500e-04) (hash(x)=23447130) +3614 train 7.041807 (lr=1.7500e-04) (hash(x)=26237963) +3615 train 7.145923 (lr=1.7500e-04) (hash(x)=25877990) +3616 train 6.913954 (lr=1.7500e-04) (hash(x)=24808003) +3617 train 7.121577 (lr=1.7500e-04) (hash(x)=24103543) +3618 train 7.009771 (lr=1.7500e-04) (hash(x)=24877184) +3619 train 7.062706 (lr=1.7500e-04) (hash(x)=24970646) +3620 train 7.055370 (lr=1.7500e-04) (hash(x)=25764524) +3621 train 7.243247 (lr=1.7500e-04) (hash(x)=25313591) +3622 train 7.111894 (lr=1.7500e-04) (hash(x)=23260940) +3623 train 6.983791 (lr=1.7500e-04) (hash(x)=24382381) +3624 train 6.960766 (lr=1.7500e-04) (hash(x)=24618902) +3625 train 7.127574 (lr=1.7500e-04) (hash(x)=25074871) +3626 train 6.867099 (lr=1.7500e-04) (hash(x)=24472251) +3627 train 7.014516 (lr=1.7500e-04) (hash(x)=25221746) +3628 train 7.110420 (lr=1.7500e-04) (hash(x)=27448790) +3629 train 7.077625 (lr=1.7500e-04) (hash(x)=25221431) +3630 train 6.637292 (lr=1.7500e-04) (hash(x)=22034366) +3631 train 7.181438 (lr=1.7500e-04) (hash(x)=24551999) +3632 train 6.921247 (lr=1.7500e-04) (hash(x)=24330217) +3633 train 7.041942 (lr=1.7500e-04) (hash(x)=22792380) +3634 train 6.852638 (lr=1.7500e-04) (hash(x)=22393767) +3635 train 7.161491 (lr=1.7500e-04) (hash(x)=28151378) +3636 train 7.190040 (lr=1.7500e-04) (hash(x)=26999341) +3637 train 7.196481 (lr=1.7500e-04) (hash(x)=27251870) +3638 train 7.146278 (lr=1.7500e-04) (hash(x)=23439462) +3639 train 7.184513 (lr=1.7500e-04) (hash(x)=25765516) +3640 train 7.166009 (lr=1.7500e-04) (hash(x)=24720171) +3641 train 7.351238 (lr=1.7500e-04) (hash(x)=23927187) +3642 train 7.105958 (lr=1.7500e-04) (hash(x)=23879561) +3643 train 7.169510 (lr=1.7500e-04) (hash(x)=25630696) +3644 train 6.786704 (lr=1.7500e-04) (hash(x)=22030016) +3645 train 7.245650 (lr=1.7500e-04) (hash(x)=28781600) +3646 train 7.267190 (lr=1.7500e-04) (hash(x)=26668019) +3647 train 7.297291 (lr=1.7500e-04) (hash(x)=25204247) +3648 train 7.553140 (lr=1.7500e-04) (hash(x)=31261394) +3649 train 7.309079 (lr=1.7500e-04) (hash(x)=26193103) +3650 val loss 7.2096 +3650 val perplexity 1352.4150 +3650 train 7.104302 (lr=1.7500e-04) (hash(x)=23872456) +3651 train 6.975322 (lr=1.7500e-04) (hash(x)=26326447) +3652 train 6.998006 (lr=1.7500e-04) (hash(x)=26449631) +3653 train 7.297344 (lr=1.7500e-04) (hash(x)=26373461) +3654 train 7.133830 (lr=1.7500e-04) (hash(x)=24882768) +3655 train 7.175804 (lr=1.7500e-04) (hash(x)=26321813) +3656 train 7.258021 (lr=1.7500e-04) (hash(x)=27056428) +3657 train 7.148351 (lr=1.7500e-04) (hash(x)=24583976) +3658 train 6.877173 (lr=1.7500e-04) (hash(x)=22259624) +3659 train 6.996349 (lr=1.7500e-04) (hash(x)=25400396) +3660 train 6.843816 (lr=1.7500e-04) (hash(x)=21095507) +3661 train 7.127723 (lr=1.7500e-04) (hash(x)=27231042) +3662 train 6.919797 (lr=1.7500e-04) (hash(x)=27292771) +3663 train 7.310035 (lr=1.7500e-04) (hash(x)=25528323) +3664 train 7.068820 (lr=1.7500e-04) (hash(x)=24374502) +3665 train 6.921024 (lr=1.7500e-04) (hash(x)=22463800) +3666 train 7.167010 (lr=1.7500e-04) (hash(x)=25413960) +3667 train 7.080982 (lr=1.7500e-04) (hash(x)=24035353) +3668 train 7.020515 (lr=1.7500e-04) (hash(x)=24815852) +3669 train 6.915547 (lr=1.7500e-04) (hash(x)=22995856) +3670 train 7.160233 (lr=1.7500e-04) (hash(x)=28128238) +3671 train 7.202710 (lr=1.7500e-04) (hash(x)=25114729) +3672 train 6.933829 (lr=1.7500e-04) (hash(x)=19337726) +3673 train 7.342889 (lr=1.7500e-04) (hash(x)=26674420) +3674 train 6.848432 (lr=1.7500e-04) (hash(x)=22553270) +3675 train 6.747121 (lr=1.7500e-04) (hash(x)=21634962) +3676 train 6.913437 (lr=1.7500e-04) (hash(x)=23362669) +3677 train 7.079550 (lr=1.7500e-04) (hash(x)=24781824) +3678 train 6.537833 (lr=1.7500e-04) (hash(x)=17909688) +3679 train 7.868327 (lr=1.7500e-04) (hash(x)=31341964) +3680 train 7.340618 (lr=1.7500e-04) (hash(x)=29071335) +3681 train 6.726160 (lr=1.7500e-04) (hash(x)=19486640) +3682 train 6.890023 (lr=1.7500e-04) (hash(x)=24301133) +3683 train 7.074474 (lr=1.7500e-04) (hash(x)=29172813) +3684 train 7.611695 (lr=1.7500e-04) (hash(x)=31501337) +3685 train 7.236371 (lr=1.7500e-04) (hash(x)=27377840) +3686 train 7.021051 (lr=1.7500e-04) (hash(x)=24499761) +3687 train 7.069660 (lr=1.7500e-04) (hash(x)=26326024) +3688 train 7.116516 (lr=1.7500e-04) (hash(x)=23179996) +3689 train 6.775382 (lr=1.7500e-04) (hash(x)=20963675) +3690 train 6.989636 (lr=1.7500e-04) (hash(x)=26650521) +3691 train 6.894153 (lr=1.7500e-04) (hash(x)=20140071) +3692 train 6.801037 (lr=1.7500e-04) (hash(x)=21734340) +3693 train 7.035060 (lr=1.7500e-04) (hash(x)=23848422) +3694 train 7.085641 (lr=1.7500e-04) (hash(x)=27499953) +3695 train 7.301401 (lr=1.7500e-04) (hash(x)=27273311) +3696 train 7.253574 (lr=1.7500e-04) (hash(x)=25741091) +3697 train 6.971586 (lr=1.7500e-04) (hash(x)=22010794) +3698 train 7.053398 (lr=1.7500e-04) (hash(x)=24616138) +3699 train 7.453886 (lr=1.7500e-04) (hash(x)=31276487) +3700 val loss 7.1392 +3700 val perplexity 1260.4025 +3700 train 7.122342 (lr=1.7500e-04) (hash(x)=24042922) +3701 train 6.918781 (lr=1.7500e-04) (hash(x)=21985431) +3702 train 6.766098 (lr=1.7500e-04) (hash(x)=21336316) +3703 train 6.610224 (lr=1.7500e-04) (hash(x)=17819313) +3704 train 7.221564 (lr=1.7500e-04) (hash(x)=27033851) +3705 train 7.255390 (lr=1.7500e-04) (hash(x)=27260043) +3706 train 7.315324 (lr=1.7500e-04) (hash(x)=26847649) +3707 train 7.238898 (lr=1.7500e-04) (hash(x)=25843618) +3708 train 7.199658 (lr=1.7500e-04) (hash(x)=25828009) +3709 train 7.240031 (lr=1.7500e-04) (hash(x)=24960960) +3710 train 7.338370 (lr=1.7500e-04) (hash(x)=24852741) +3711 train 6.900010 (lr=1.7500e-04) (hash(x)=23769243) +3712 train 7.088365 (lr=1.7500e-04) (hash(x)=27110690) +3713 train 7.079293 (lr=1.7500e-04) (hash(x)=22817285) +3714 train 6.787477 (lr=1.7500e-04) (hash(x)=19618355) +3715 train 7.331577 (lr=1.7500e-04) (hash(x)=28731298) +3716 train 7.115422 (lr=1.7500e-04) (hash(x)=23091196) +3717 train 7.691569 (lr=1.7500e-04) (hash(x)=28825233) +3718 train 7.206233 (lr=1.7500e-04) (hash(x)=25778506) +3719 train 7.106592 (lr=1.7500e-04) (hash(x)=23788738) +3720 train 6.517451 (lr=1.7500e-04) (hash(x)=16684794) +3721 train 7.041908 (lr=1.7500e-04) (hash(x)=24755102) +3722 train 7.313560 (lr=1.7500e-04) (hash(x)=26839238) +3723 train 7.387203 (lr=1.7500e-04) (hash(x)=26599031) +3724 train 7.258800 (lr=1.7500e-04) (hash(x)=25945650) +3725 train 7.451567 (lr=1.7500e-04) (hash(x)=27434751) +3726 train 7.276639 (lr=1.7500e-04) (hash(x)=24814591) +3727 train 7.170150 (lr=1.7500e-04) (hash(x)=24818744) +3728 train 7.280303 (lr=1.7500e-04) (hash(x)=25649817) +3729 train 7.229150 (lr=1.7500e-04) (hash(x)=24987021) +3730 train 7.172883 (lr=1.7500e-04) (hash(x)=24667779) +3731 train 7.130886 (lr=1.7500e-04) (hash(x)=23053871) +3732 train 6.838345 (lr=1.7500e-04) (hash(x)=19264856) +3733 train 7.364003 (lr=1.7500e-04) (hash(x)=23718117) +3734 train 7.087123 (lr=1.7500e-04) (hash(x)=21904779) +3735 train 7.358542 (lr=1.7500e-04) (hash(x)=23472795) +3736 train 7.621593 (lr=1.7500e-04) (hash(x)=24650440) +3737 train 7.562246 (lr=1.7500e-04) (hash(x)=25243911) +3738 train 7.920882 (lr=1.7500e-04) (hash(x)=30423616) +3739 train 7.907599 (lr=1.7500e-04) (hash(x)=29748225) +3740 train 7.359729 (lr=1.7500e-04) (hash(x)=25180684) +3741 train 7.319959 (lr=1.7500e-04) (hash(x)=25619065) +3742 train 7.626939 (lr=1.7500e-04) (hash(x)=31847002) +3743 train 7.229557 (lr=1.7500e-04) (hash(x)=24991832) +3744 train 7.131853 (lr=1.7500e-04) (hash(x)=23836263) +3745 train 7.039171 (lr=1.7500e-04) (hash(x)=24651902) +3746 train 7.602945 (lr=1.7500e-04) (hash(x)=22936538) +3747 train 7.543764 (lr=1.7500e-04) (hash(x)=23681545) +3748 train 6.946161 (lr=1.7500e-04) (hash(x)=21140825) +3749 train 7.096544 (lr=1.7500e-04) (hash(x)=24932453) +3750 val loss 7.1590 +3750 val perplexity 1285.5872 +3750 train 7.234466 (lr=1.7500e-04) (hash(x)=25919062) +3751 train 7.061727 (lr=1.7500e-04) (hash(x)=22424066) +3752 train 7.111489 (lr=1.7500e-04) (hash(x)=23542210) +3753 train 7.017625 (lr=1.7500e-04) (hash(x)=22113561) +3754 train 6.869606 (lr=1.7500e-04) (hash(x)=24892794) +3755 train 7.351032 (lr=1.7500e-04) (hash(x)=25262748) +3756 train 7.112517 (lr=1.7500e-04) (hash(x)=24477975) +3757 train 6.926251 (lr=1.7500e-04) (hash(x)=24681189) +3758 train 6.937773 (lr=1.7500e-04) (hash(x)=24052603) +3759 train 7.171448 (lr=1.7500e-04) (hash(x)=26474878) +3760 train 7.674501 (lr=1.7500e-04) (hash(x)=28228836) +3761 train 7.215375 (lr=1.7500e-04) (hash(x)=23832522) +3762 train 7.179744 (lr=1.7500e-04) (hash(x)=24416789) +3763 train 6.947571 (lr=1.7500e-04) (hash(x)=23930593) +3764 train 7.037624 (lr=1.7500e-04) (hash(x)=23895092) +3765 train 6.968301 (lr=1.7500e-04) (hash(x)=26865287) +3766 train 6.984939 (lr=1.7500e-04) (hash(x)=21330722) +3767 train 7.045743 (lr=1.7500e-04) (hash(x)=22704349) +3768 train 7.167476 (lr=1.7500e-04) (hash(x)=27740886) +3769 train 7.171840 (lr=1.7500e-04) (hash(x)=24935936) +3770 train 7.007770 (lr=1.7500e-04) (hash(x)=23497487) +3771 train 7.197814 (lr=1.7500e-04) (hash(x)=24801048) +3772 train 6.978273 (lr=1.7500e-04) (hash(x)=25490486) +3773 train 7.013656 (lr=1.7500e-04) (hash(x)=21166466) +3774 train 7.210225 (lr=1.7500e-04) (hash(x)=23225244) +3775 train 6.991963 (lr=1.7500e-04) (hash(x)=22293673) +3776 train 7.271511 (lr=1.7500e-04) (hash(x)=25700016) +3777 train 6.815146 (lr=1.7500e-04) (hash(x)=22370207) +3778 train 7.157189 (lr=1.7500e-04) (hash(x)=25224849) +3779 train 7.074217 (lr=1.7500e-04) (hash(x)=23311934) +3780 train 6.834611 (lr=1.7500e-04) (hash(x)=19627124) +3781 train 7.250533 (lr=1.7500e-04) (hash(x)=27132838) +3782 train 7.266934 (lr=1.7500e-04) (hash(x)=27242104) +3783 train 6.756345 (lr=1.7500e-04) (hash(x)=21785487) +3784 train 7.086700 (lr=1.7500e-04) (hash(x)=25798262) +3785 train 6.982621 (lr=1.7500e-04) (hash(x)=24806937) +3786 train 6.851404 (lr=1.7500e-04) (hash(x)=24098756) +3787 train 6.825050 (lr=1.7500e-04) (hash(x)=22981456) +3788 train 7.263535 (lr=1.7500e-04) (hash(x)=22441908) +3789 train 7.166040 (lr=1.7500e-04) (hash(x)=25867804) +3790 train 7.113018 (lr=1.7500e-04) (hash(x)=22835586) +3791 train 7.292447 (lr=1.7500e-04) (hash(x)=25251063) +3792 train 7.121939 (lr=1.7500e-04) (hash(x)=27059729) +3793 train 7.073024 (lr=1.7500e-04) (hash(x)=23819311) +3794 train 6.791841 (lr=1.7500e-04) (hash(x)=21345757) +3795 train 7.057693 (lr=1.7500e-04) (hash(x)=25796422) +3796 train 6.730096 (lr=1.7500e-04) (hash(x)=21414971) +3797 train 7.044347 (lr=1.7500e-04) (hash(x)=26120920) +3798 train 6.959386 (lr=1.7500e-04) (hash(x)=22008247) +3799 train 7.096945 (lr=1.7500e-04) (hash(x)=22722211) +3800 val loss 7.1229 +3800 val perplexity 1240.0378 +3800 train 6.779973 (lr=1.7500e-04) (hash(x)=24484513) +3801 train 7.124880 (lr=1.7500e-04) (hash(x)=24463866) +3802 train 7.159654 (lr=1.7500e-04) (hash(x)=26470775) +3803 train 7.130144 (lr=1.7500e-04) (hash(x)=24296755) +3804 train 7.134779 (lr=1.7500e-04) (hash(x)=24381309) +3805 train 7.352535 (lr=1.7500e-04) (hash(x)=26781262) +3806 train 6.772106 (lr=1.7500e-04) (hash(x)=23563137) +3807 train 7.000966 (lr=1.7500e-04) (hash(x)=24522269) +3808 train 6.893163 (lr=1.7500e-04) (hash(x)=22871995) +3809 train 7.187186 (lr=1.7500e-04) (hash(x)=24751946) +3810 train 6.998573 (lr=1.7500e-04) (hash(x)=19879741) +3811 train 7.111553 (lr=1.7500e-04) (hash(x)=25617184) +3812 train 6.788494 (lr=1.7500e-04) (hash(x)=21776722) +3813 train 6.897717 (lr=1.7500e-04) (hash(x)=22663402) +3814 train 7.189493 (lr=1.7500e-04) (hash(x)=26072046) +3815 train 6.937006 (lr=1.7500e-04) (hash(x)=23329475) +3816 train 6.985401 (lr=1.7500e-04) (hash(x)=25519031) +3817 train 6.928861 (lr=1.7500e-04) (hash(x)=22846270) +3818 train 6.973792 (lr=1.7500e-04) (hash(x)=20299429) +3819 train 7.390459 (lr=1.7500e-04) (hash(x)=30652062) +3820 train 6.744897 (lr=1.7500e-04) (hash(x)=19824665) +3821 train 7.307926 (lr=1.7500e-04) (hash(x)=26698904) +3822 train 7.125148 (lr=1.7500e-04) (hash(x)=27612163) +3823 train 6.908027 (lr=1.7500e-04) (hash(x)=24735165) +3824 train 6.632562 (lr=1.7500e-04) (hash(x)=19965890) +3825 train 6.821988 (lr=1.7500e-04) (hash(x)=23518594) +3826 train 6.861836 (lr=1.7500e-04) (hash(x)=22388460) +3827 train 6.922562 (lr=1.7500e-04) (hash(x)=23795686) +3828 train 6.803861 (lr=1.7500e-04) (hash(x)=24470150) +3829 train 6.500591 (lr=1.7500e-04) (hash(x)=19483392) +3830 train 6.919266 (lr=1.7500e-04) (hash(x)=23304516) +3831 train 7.292246 (lr=1.7500e-04) (hash(x)=27002892) +3832 train 6.972056 (lr=1.7500e-04) (hash(x)=22114813) +3833 train 7.187085 (lr=1.7500e-04) (hash(x)=26221916) +3834 train 6.707548 (lr=1.7500e-04) (hash(x)=27261960) +3835 train 7.012345 (lr=1.7500e-04) (hash(x)=21189101) +3836 train 6.670270 (lr=1.7500e-04) (hash(x)=20638173) +3837 train 7.103108 (lr=1.7500e-04) (hash(x)=25497439) +3838 train 6.622261 (lr=1.7500e-04) (hash(x)=20460499) +3839 train 7.053175 (lr=1.7500e-04) (hash(x)=23499349) +3840 train 7.845582 (lr=1.7500e-04) (hash(x)=22671939) +3841 train 7.816507 (lr=1.7500e-04) (hash(x)=26809295) +3842 train 7.104710 (lr=1.7500e-04) (hash(x)=28094504) +3843 train 7.080048 (lr=1.7500e-04) (hash(x)=26807896) +3844 train 7.173297 (lr=1.7500e-04) (hash(x)=24749334) +3845 train 7.071690 (lr=1.7500e-04) (hash(x)=25031330) +3846 train 7.003369 (lr=1.7500e-04) (hash(x)=23008126) +3847 train 6.988106 (lr=1.7500e-04) (hash(x)=22461589) +3848 train 7.108556 (lr=1.7500e-04) (hash(x)=24959391) +3849 train 7.136516 (lr=1.7500e-04) (hash(x)=24239512) +3850 val loss 7.1463 +3850 val perplexity 1269.3730 +3850 train 6.945925 (lr=1.7500e-04) (hash(x)=24760422) +3851 train 7.444281 (lr=1.7500e-04) (hash(x)=26904123) +3852 train 6.651521 (lr=1.7500e-04) (hash(x)=17986444) +3853 train 6.952333 (lr=1.7500e-04) (hash(x)=21618533) +3854 train 6.981004 (lr=1.7500e-04) (hash(x)=27107027) +3855 train 7.224953 (lr=1.7500e-04) (hash(x)=26415040) +3856 train 7.801605 (lr=1.7500e-04) (hash(x)=28682703) +3857 train 6.963844 (lr=1.7500e-04) (hash(x)=22824767) +3858 train 7.096686 (lr=1.7500e-04) (hash(x)=24540450) +3859 train 7.080588 (lr=1.7500e-04) (hash(x)=24463181) +3860 train 7.023053 (lr=1.7500e-04) (hash(x)=22832558) +3861 train 7.162857 (lr=1.7500e-04) (hash(x)=26582384) +3862 train 7.759853 (lr=1.7500e-04) (hash(x)=32327364) +3863 train 7.220100 (lr=1.7500e-04) (hash(x)=26349465) +3864 train 6.937004 (lr=1.7500e-04) (hash(x)=23079414) +3865 train 6.993993 (lr=1.7500e-04) (hash(x)=23464639) +3866 train 6.856813 (lr=1.7500e-04) (hash(x)=21406620) +3867 train 6.751331 (lr=1.7500e-04) (hash(x)=21205988) +3868 train 6.781086 (lr=1.7500e-04) (hash(x)=22742634) +3869 train 6.809173 (lr=1.7500e-04) (hash(x)=24868938) +3870 train 7.183597 (lr=1.7500e-04) (hash(x)=28095283) +3871 train 6.892732 (lr=1.7500e-04) (hash(x)=21596677) +3872 train 7.123850 (lr=1.7500e-04) (hash(x)=26884381) +3873 train 7.193309 (lr=1.7500e-04) (hash(x)=26410272) +3874 train 6.935699 (lr=1.7500e-04) (hash(x)=22915785) +3875 train 6.988667 (lr=1.7500e-04) (hash(x)=23575666) +3876 train 6.943741 (lr=1.7500e-04) (hash(x)=25313223) +3877 train 6.545316 (lr=1.7500e-04) (hash(x)=16319719) +3878 train 7.067157 (lr=1.7500e-04) (hash(x)=23227579) +3879 train 6.992166 (lr=1.7500e-04) (hash(x)=24117012) +3880 train 7.041584 (lr=1.7500e-04) (hash(x)=24681517) +3881 train 6.945804 (lr=1.7500e-04) (hash(x)=23186527) +3882 train 6.973583 (lr=1.7500e-04) (hash(x)=23472784) +3883 train 7.008173 (lr=1.7500e-04) (hash(x)=26013014) +3884 train 7.183337 (lr=1.7500e-04) (hash(x)=25952206) +3885 train 7.292181 (lr=1.7500e-04) (hash(x)=23897834) +3886 train 7.037388 (lr=1.7500e-04) (hash(x)=26350364) +3887 train 7.094793 (lr=1.7500e-04) (hash(x)=24105761) +3888 train 7.157428 (lr=1.7500e-04) (hash(x)=22801707) +3889 train 7.063360 (lr=1.7500e-04) (hash(x)=21821937) +3890 train 6.948085 (lr=1.7500e-04) (hash(x)=24264640) +3891 train 6.873772 (lr=1.7500e-04) (hash(x)=20369133) +3892 train 6.836573 (lr=1.7500e-04) (hash(x)=24313506) +3893 train 6.866278 (lr=1.7500e-04) (hash(x)=22104086) +3894 train 7.140894 (lr=1.7500e-04) (hash(x)=25312602) +3895 train 7.185773 (lr=1.7500e-04) (hash(x)=25725049) +3896 train 6.996125 (lr=1.7500e-04) (hash(x)=22981231) +3897 train 6.855145 (lr=1.7500e-04) (hash(x)=18021467) +3898 train 6.835079 (lr=1.7500e-04) (hash(x)=17960254) +3899 train 6.971187 (lr=1.7500e-04) (hash(x)=19808118) +3900 val loss 7.1692 +3900 val perplexity 1298.7889 +3900 train 6.746300 (lr=1.7500e-04) (hash(x)=21022829) +3901 train 6.926883 (lr=1.7500e-04) (hash(x)=22434663) +3902 train 6.679383 (lr=1.7500e-04) (hash(x)=20208091) +3903 train 6.818985 (lr=1.7500e-04) (hash(x)=22892776) +3904 train 6.933121 (lr=1.7500e-04) (hash(x)=21554367) +3905 train 7.018708 (lr=1.7500e-04) (hash(x)=23704875) +3906 train 7.006340 (lr=1.7500e-04) (hash(x)=21690340) +3907 train 6.971759 (lr=1.7500e-04) (hash(x)=23736780) +3908 train 6.792221 (lr=1.7500e-04) (hash(x)=21060920) +3909 train 6.756012 (lr=1.7500e-04) (hash(x)=20091559) +3910 train 7.005003 (lr=1.7500e-04) (hash(x)=22147974) +3911 train 6.940530 (lr=1.7500e-04) (hash(x)=21630383) +3912 train 7.240372 (lr=1.7500e-04) (hash(x)=28339385) +3913 train 7.000998 (lr=1.7500e-04) (hash(x)=25355505) +3914 train 6.864872 (lr=1.7500e-04) (hash(x)=20843914) +3915 train 7.423795 (lr=1.7500e-04) (hash(x)=25397467) +3916 train 7.125259 (lr=1.7500e-04) (hash(x)=23587501) +3917 train 6.689180 (lr=1.7500e-04) (hash(x)=19036533) +3918 train 6.844091 (lr=1.7500e-04) (hash(x)=29749389) +3919 train 6.699217 (lr=1.7500e-04) (hash(x)=24727094) +3920 train 6.783891 (lr=1.7500e-04) (hash(x)=22723450) +3921 train 6.959980 (lr=1.7500e-04) (hash(x)=24424680) +3922 train 7.104625 (lr=1.7500e-04) (hash(x)=25817917) +3923 train 6.899901 (lr=1.7500e-04) (hash(x)=23951182) +3924 train 6.917522 (lr=1.7500e-04) (hash(x)=21177944) +3925 train 6.782265 (lr=1.7500e-04) (hash(x)=23533768) +3926 train 6.986061 (lr=1.7500e-04) (hash(x)=24263615) +3927 train 6.829948 (lr=1.7500e-04) (hash(x)=22835000) +3928 train 7.053888 (lr=1.7500e-04) (hash(x)=26076156) +3929 train 7.023358 (lr=1.7500e-04) (hash(x)=25171508) +3930 train 7.128253 (lr=1.7500e-04) (hash(x)=22021396) +3931 train 7.220873 (lr=1.7500e-04) (hash(x)=28767849) +3932 train 7.163413 (lr=1.7500e-04) (hash(x)=29497606) +3933 train 6.861519 (lr=1.7500e-04) (hash(x)=22723124) +3934 train 7.167442 (lr=1.7500e-04) (hash(x)=27106616) +3935 train 7.070882 (lr=1.7500e-04) (hash(x)=22839049) +3936 train 7.110885 (lr=1.7500e-04) (hash(x)=25101923) +3937 train 7.033246 (lr=1.7500e-04) (hash(x)=25945975) +3938 train 7.149356 (lr=1.7500e-04) (hash(x)=25382013) +3939 train 6.711400 (lr=1.7500e-04) (hash(x)=19930900) +3940 train 6.835754 (lr=1.7500e-04) (hash(x)=22202373) +3941 train 7.043536 (lr=1.7500e-04) (hash(x)=24592992) +3942 train 6.912354 (lr=1.7500e-04) (hash(x)=25002271) +3943 train 6.755657 (lr=1.7500e-04) (hash(x)=20654136) +3944 train 6.841411 (lr=1.7500e-04) (hash(x)=20061590) +3945 train 6.768555 (lr=1.7500e-04) (hash(x)=21441361) +3946 train 6.955210 (lr=1.7500e-04) (hash(x)=20055468) +3947 train 7.659822 (lr=1.7500e-04) (hash(x)=28495621) +3948 train 7.131892 (lr=1.7500e-04) (hash(x)=25959236) +3949 train 7.457363 (lr=1.7500e-04) (hash(x)=26750193) +3950 val loss 7.1778 +3950 val perplexity 1310.0770 +3950 train 7.248425 (lr=1.7500e-04) (hash(x)=25882605) +3951 train 7.341062 (lr=1.7500e-04) (hash(x)=26776000) +3952 train 7.004630 (lr=1.7500e-04) (hash(x)=24155107) +3953 train 7.020663 (lr=1.7500e-04) (hash(x)=23441845) +3954 train 6.963985 (lr=1.7500e-04) (hash(x)=22860915) +3955 train 6.790315 (lr=1.7500e-04) (hash(x)=21584429) +3956 train 6.405107 (lr=1.7500e-04) (hash(x)=16535556) +3957 train 6.446974 (lr=1.7500e-04) (hash(x)=17946180) +3958 train 7.017012 (lr=1.7500e-04) (hash(x)=25367610) +3959 train 6.900350 (lr=1.7500e-04) (hash(x)=22560658) +3960 train 7.122685 (lr=1.7500e-04) (hash(x)=23809585) +3961 train 7.331839 (lr=1.7500e-04) (hash(x)=20438213) +3962 train 7.732608 (lr=1.7500e-04) (hash(x)=30520037) +3963 train 7.366634 (lr=1.7500e-04) (hash(x)=25276565) +3964 train 7.098744 (lr=1.7500e-04) (hash(x)=26796532) +3965 train 6.924423 (lr=1.7500e-04) (hash(x)=22850475) +3966 train 7.322890 (lr=1.7500e-04) (hash(x)=25983698) +3967 train 7.255138 (lr=1.7500e-04) (hash(x)=25995933) +3968 train 7.460120 (lr=1.7500e-04) (hash(x)=25319339) +3969 train 7.058972 (lr=1.7500e-04) (hash(x)=25066892) +3970 train 7.266829 (lr=1.7500e-04) (hash(x)=26931819) +3971 train 7.214391 (lr=1.7500e-04) (hash(x)=24163910) +3972 train 7.132323 (lr=1.7500e-04) (hash(x)=25359634) +3973 train 6.994405 (lr=1.7500e-04) (hash(x)=24323444) +3974 train 7.147167 (lr=1.7500e-04) (hash(x)=26529231) +3975 train 7.155099 (lr=1.7500e-04) (hash(x)=24635394) +3976 train 7.435863 (lr=1.7500e-04) (hash(x)=24783093) +3977 train 7.541638 (lr=1.7500e-04) (hash(x)=26710509) +3978 train 7.030713 (lr=1.7500e-04) (hash(x)=25396630) +3979 train 6.945780 (lr=1.7500e-04) (hash(x)=22556381) +3980 train 7.262043 (lr=1.7500e-04) (hash(x)=26912161) +3981 train 6.863524 (lr=1.7500e-04) (hash(x)=22268078) +3982 train 7.893466 (lr=1.7500e-04) (hash(x)=30430328) +3983 train 7.503238 (lr=1.7500e-04) (hash(x)=27537228) +3984 train 6.992772 (lr=1.7500e-04) (hash(x)=24468603) +3985 train 7.235729 (lr=1.7500e-04) (hash(x)=27006663) +3986 train 7.452372 (lr=1.7500e-04) (hash(x)=27014728) +3987 train 6.938655 (lr=1.7500e-04) (hash(x)=20883633) +3988 train 7.077693 (lr=1.7500e-04) (hash(x)=23361791) +3989 train 7.208221 (lr=1.7500e-04) (hash(x)=26775925) +3990 train 7.633672 (lr=1.7500e-04) (hash(x)=30648934) +3991 train 7.240959 (lr=1.7500e-04) (hash(x)=26496730) +3992 train 7.014159 (lr=1.7500e-04) (hash(x)=25942897) +3993 train 7.025608 (lr=1.7500e-04) (hash(x)=24887111) +3994 train 6.945331 (lr=1.7500e-04) (hash(x)=22908550) +3995 train 6.710077 (lr=1.7500e-04) (hash(x)=20342150) +3996 train 7.048318 (lr=1.7500e-04) (hash(x)=22261760) +3997 train 7.050777 (lr=1.7500e-04) (hash(x)=22731641) +3998 train 6.911477 (lr=1.7500e-04) (hash(x)=20669749) +3999 train 6.871130 (lr=1.7500e-04) (hash(x)=16533310) +4000 val loss 7.1902 +4000 val perplexity 1326.3669 +4000 train 7.001363 (lr=1.7500e-04) (hash(x)=23661341) +4001 train 7.055852 (lr=1.7500e-04) (hash(x)=24644301) +4002 train 6.926729 (lr=1.7500e-04) (hash(x)=22938438) +4003 train 7.031780 (lr=1.7500e-04) (hash(x)=24315862) +4004 train 7.167857 (lr=1.7500e-04) (hash(x)=25169315) +4005 train 7.199574 (lr=1.7500e-04) (hash(x)=24752796) +4006 train 7.094057 (lr=1.7500e-04) (hash(x)=23103706) +4007 train 7.181320 (lr=1.7500e-04) (hash(x)=24881176) +4008 train 7.130283 (lr=1.7500e-04) (hash(x)=23971947) +4009 train 7.335295 (lr=1.7500e-04) (hash(x)=27741054) +4010 train 7.731621 (lr=1.7500e-04) (hash(x)=30956251) +4011 train 7.159678 (lr=1.7500e-04) (hash(x)=23649686) +4012 train 6.943126 (lr=1.7500e-04) (hash(x)=23344798) +4013 train 7.560187 (lr=1.7500e-04) (hash(x)=29529498) +4014 train 7.124754 (lr=1.7500e-04) (hash(x)=24688359) +4015 train 7.169879 (lr=1.7500e-04) (hash(x)=25593613) +4016 train 7.262846 (lr=1.7500e-04) (hash(x)=25674488) +4017 train 6.720335 (lr=1.7500e-04) (hash(x)=21345346) +4018 train 7.006973 (lr=1.7500e-04) (hash(x)=21978324) +4019 train 7.071916 (lr=1.7500e-04) (hash(x)=23669244) +4020 train 6.930271 (lr=1.7500e-04) (hash(x)=22479613) +4021 train 6.864910 (lr=1.7500e-04) (hash(x)=22855256) +4022 train 7.258064 (lr=1.7500e-04) (hash(x)=19759826) +4023 train 7.171739 (lr=1.7500e-04) (hash(x)=22886646) +4024 train 7.128755 (lr=1.7500e-04) (hash(x)=25553008) +4025 train 7.053554 (lr=1.7500e-04) (hash(x)=25487028) +4026 train 7.599037 (lr=1.7500e-04) (hash(x)=26799246) +4027 train 7.913742 (lr=1.7500e-04) (hash(x)=30728540) +4028 train 7.321089 (lr=1.7500e-04) (hash(x)=23966676) +4029 train 6.978940 (lr=1.7500e-04) (hash(x)=22118783) +4030 train 7.116379 (lr=1.7500e-04) (hash(x)=24744703) +4031 train 7.150578 (lr=1.7500e-04) (hash(x)=21407676) +4032 train 7.070984 (lr=1.7500e-04) (hash(x)=20623349) +4033 train 6.913759 (lr=1.7500e-04) (hash(x)=24723788) +4034 train 7.163954 (lr=1.7500e-04) (hash(x)=25030709) +4035 train 7.239818 (lr=1.7500e-04) (hash(x)=26326164) +4036 train 7.086511 (lr=1.7500e-04) (hash(x)=23754475) +4037 train 7.682054 (lr=1.7500e-04) (hash(x)=30112933) +4038 train 7.475792 (lr=1.7500e-04) (hash(x)=27474299) +4039 train 6.936018 (lr=1.7500e-04) (hash(x)=21720304) +4040 train 7.311349 (lr=1.7500e-04) (hash(x)=25142674) +4041 train 7.570190 (lr=1.7500e-04) (hash(x)=25284552) +4042 train 7.477615 (lr=1.7500e-04) (hash(x)=24554942) +4043 train 7.198925 (lr=1.7500e-04) (hash(x)=23773870) +4044 train 6.978756 (lr=1.7500e-04) (hash(x)=23896338) +4045 train 7.727820 (lr=1.7500e-04) (hash(x)=34984911) +4046 train 7.089873 (lr=1.7500e-04) (hash(x)=23854263) +4047 train 7.305758 (lr=1.7500e-04) (hash(x)=27263416) +4048 train 7.065480 (lr=1.7500e-04) (hash(x)=24989642) +4049 train 7.070796 (lr=1.7500e-04) (hash(x)=24492055) +4050 val loss 7.2085 +4050 val perplexity 1350.8308 +4050 train 6.986615 (lr=1.7500e-04) (hash(x)=21579916) +4051 train 7.252483 (lr=1.7500e-04) (hash(x)=25274710) +4052 train 7.135365 (lr=1.7500e-04) (hash(x)=24701947) +4053 train 7.092514 (lr=1.7500e-04) (hash(x)=25477340) +4054 train 7.016235 (lr=1.7500e-04) (hash(x)=23774195) +4055 train 7.281478 (lr=1.7500e-04) (hash(x)=25840801) +4056 train 7.402980 (lr=1.7500e-04) (hash(x)=27972529) +4057 train 7.232570 (lr=1.7500e-04) (hash(x)=26952458) +4058 train 6.788099 (lr=1.7500e-04) (hash(x)=22683653) +4059 train 6.862982 (lr=1.7500e-04) (hash(x)=20984129) +4060 train 6.997232 (lr=1.7500e-04) (hash(x)=22816482) +4061 train 7.238082 (lr=1.7500e-04) (hash(x)=24285302) +4062 train 7.599051 (lr=1.7500e-04) (hash(x)=31517950) +4063 train 7.795150 (lr=1.7500e-04) (hash(x)=31424568) +4064 train 7.492294 (lr=1.7500e-04) (hash(x)=29497876) +4065 train 7.404587 (lr=1.7500e-04) (hash(x)=27277376) +4066 train 7.183843 (lr=1.7500e-04) (hash(x)=26832588) +4067 train 6.993196 (lr=1.7500e-04) (hash(x)=25149712) +4068 train 7.003058 (lr=1.7500e-04) (hash(x)=23728457) +4069 train 6.934005 (lr=1.7500e-04) (hash(x)=25265136) +4070 train 7.410837 (lr=1.7500e-04) (hash(x)=25241681) +4071 train 7.149995 (lr=1.7500e-04) (hash(x)=23403065) +4072 train 7.089302 (lr=1.7500e-04) (hash(x)=25808207) +4073 train 7.029121 (lr=1.7500e-04) (hash(x)=23904844) +4074 train 6.708298 (lr=1.7500e-04) (hash(x)=18865309) +4075 train 7.096141 (lr=1.7500e-04) (hash(x)=23531744) +4076 train 7.139725 (lr=1.7500e-04) (hash(x)=25784275) +4077 train 6.917447 (lr=1.7500e-04) (hash(x)=22417529) +4078 train 6.925752 (lr=1.7500e-04) (hash(x)=23095491) +4079 train 7.017859 (lr=1.7500e-04) (hash(x)=22656033) +4080 train 7.050022 (lr=1.7500e-04) (hash(x)=25865435) +4081 train 7.136197 (lr=1.7500e-04) (hash(x)=25699377) +4082 train 7.183090 (lr=1.7500e-04) (hash(x)=20854084) +4083 train 6.764809 (lr=1.7500e-04) (hash(x)=18950799) +4084 train 6.965416 (lr=1.7500e-04) (hash(x)=22633739) +4085 train 7.772226 (lr=1.7500e-04) (hash(x)=34054446) +4086 train 7.353693 (lr=1.7500e-04) (hash(x)=27599387) +4087 train 7.144257 (lr=1.7500e-04) (hash(x)=26869295) +4088 train 7.095152 (lr=1.7500e-04) (hash(x)=24075139) +4089 train 7.541482 (lr=1.7500e-04) (hash(x)=29784110) +4090 train 7.874413 (lr=1.7500e-04) (hash(x)=34273918) +4091 train 8.107766 (lr=1.7500e-04) (hash(x)=34472685) +4092 train 7.523589 (lr=1.7500e-04) (hash(x)=30113791) +4093 train 6.932845 (lr=1.7500e-04) (hash(x)=22366381) +4094 train 7.193391 (lr=1.7500e-04) (hash(x)=24922935) +4095 train 7.297199 (lr=1.7500e-04) (hash(x)=25504151) +4096 train 7.275319 (lr=1.7500e-04) (hash(x)=24517375) +4097 train 8.100451 (lr=1.7500e-04) (hash(x)=25871651) +4098 train 7.011829 (lr=1.7500e-04) (hash(x)=23480225) +4099 train 6.863047 (lr=1.7500e-04) (hash(x)=22559978) +4100 val loss 7.1797 +4100 val perplexity 1312.5162 +4100 train 7.302173 (lr=1.7500e-04) (hash(x)=25795272) +4101 train 7.246925 (lr=1.7500e-04) (hash(x)=25440399) +4102 train 6.930419 (lr=1.7500e-04) (hash(x)=21581806) +4103 train 7.025310 (lr=1.7500e-04) (hash(x)=25781518) +4104 train 7.066051 (lr=1.7500e-04) (hash(x)=24682372) +4105 train 6.948570 (lr=1.7500e-04) (hash(x)=22440094) +4106 train 7.063207 (lr=1.7500e-04) (hash(x)=23661032) +4107 train 7.301172 (lr=1.7500e-04) (hash(x)=26966012) +4108 train 7.345162 (lr=1.7500e-04) (hash(x)=26232227) +4109 train 7.036708 (lr=1.7500e-04) (hash(x)=24110656) +4110 train 7.268198 (lr=1.7500e-04) (hash(x)=25938621) +4111 train 7.106520 (lr=1.7500e-04) (hash(x)=26432850) +4112 train 7.105449 (lr=1.7500e-04) (hash(x)=25387672) +4113 train 6.908002 (lr=1.7500e-04) (hash(x)=22740017) +4114 train 7.255072 (lr=1.7500e-04) (hash(x)=26384190) +4115 train 6.941106 (lr=1.7500e-04) (hash(x)=24725583) +4116 train 7.066254 (lr=1.7500e-04) (hash(x)=23986700) +4117 train 7.059970 (lr=1.7500e-04) (hash(x)=18529900) +4118 train 7.073429 (lr=1.7500e-04) (hash(x)=22236257) +4119 train 6.692163 (lr=1.7500e-04) (hash(x)=20155894) +4120 train 6.481449 (lr=1.7500e-04) (hash(x)=17423813) +4121 train 6.440514 (lr=1.7500e-04) (hash(x)=18905183) +4122 train 6.854169 (lr=1.7500e-04) (hash(x)=22534398) +4123 train 7.533800 (lr=1.7500e-04) (hash(x)=25247868) +4124 train 7.094603 (lr=1.7500e-04) (hash(x)=23994188) +4125 train 6.947841 (lr=1.7500e-04) (hash(x)=22929754) +4126 train 6.767443 (lr=1.7500e-04) (hash(x)=22485897) +4127 train 6.887136 (lr=1.7500e-04) (hash(x)=22270169) +4128 train 6.889068 (lr=1.7500e-04) (hash(x)=23638027) +4129 train 7.111791 (lr=1.7500e-04) (hash(x)=23821210) +4130 train 7.053847 (lr=1.7500e-04) (hash(x)=25021512) +4131 train 7.088382 (lr=1.7500e-04) (hash(x)=25240141) +4132 train 7.057205 (lr=1.7500e-04) (hash(x)=22833160) +4133 train 7.032522 (lr=1.7500e-04) (hash(x)=22909944) +4134 train 7.239694 (lr=1.7500e-04) (hash(x)=26163558) +4135 train 6.989758 (lr=1.7500e-04) (hash(x)=22108461) +4136 train 6.960543 (lr=1.7500e-04) (hash(x)=22549232) +4137 train 7.182928 (lr=1.7500e-04) (hash(x)=24701302) +4138 train 7.181497 (lr=1.7500e-04) (hash(x)=25206013) +4139 train 7.191320 (lr=1.7500e-04) (hash(x)=27896130) +4140 train 6.963105 (lr=1.7500e-04) (hash(x)=24106243) +4141 train 7.499809 (lr=1.7500e-04) (hash(x)=27158651) +4142 train 7.085965 (lr=1.7500e-04) (hash(x)=23841147) +4143 train 7.040126 (lr=1.7500e-04) (hash(x)=24802848) +4144 train 7.342868 (lr=1.7500e-04) (hash(x)=24911295) +4145 train 7.147683 (lr=1.7500e-04) (hash(x)=26473900) +4146 train 7.176093 (lr=1.7500e-04) (hash(x)=26785092) +4147 train 7.444455 (lr=1.7500e-04) (hash(x)=30188532) +4148 train 6.992165 (lr=1.7500e-04) (hash(x)=25010649) +4149 train 6.975523 (lr=1.7500e-04) (hash(x)=22409016) +4150 val loss 7.1837 +4150 val perplexity 1317.7814 +4150 train 7.702561 (lr=1.7500e-04) (hash(x)=31675024) +4151 train 7.077733 (lr=1.7500e-04) (hash(x)=25086604) +4152 train 7.036462 (lr=1.7500e-04) (hash(x)=24429343) +4153 train 7.214267 (lr=1.7500e-04) (hash(x)=25014232) +4154 train 7.147316 (lr=1.7500e-04) (hash(x)=25366275) +4155 train 7.621786 (lr=1.7500e-04) (hash(x)=24031473) +4156 train 7.132665 (lr=1.7500e-04) (hash(x)=26651059) +4157 train 7.252090 (lr=1.7500e-04) (hash(x)=26069721) +4158 train 7.382520 (lr=1.7500e-04) (hash(x)=28114382) +4159 train 7.352545 (lr=1.7500e-04) (hash(x)=26983186) +4160 train 6.764072 (lr=1.7500e-04) (hash(x)=21944670) +4161 train 7.445862 (lr=1.7500e-04) (hash(x)=28155702) +4162 train 6.927765 (lr=1.7500e-04) (hash(x)=24765002) +4163 train 7.185156 (lr=1.7500e-04) (hash(x)=26492636) +4164 train 7.123038 (lr=1.7500e-04) (hash(x)=24063705) +4165 train 7.421989 (lr=1.7500e-04) (hash(x)=27079573) +4166 train 7.090865 (lr=1.7500e-04) (hash(x)=24912201) +4167 train 7.231154 (lr=1.7500e-04) (hash(x)=27208507) +4168 train 7.089723 (lr=1.7500e-04) (hash(x)=25824320) +4169 train 7.578606 (lr=1.7500e-04) (hash(x)=29641677) +4170 train 7.286584 (lr=1.7500e-04) (hash(x)=26275614) +4171 train 7.162998 (lr=1.7500e-04) (hash(x)=25227725) +4172 train 7.184945 (lr=1.7500e-04) (hash(x)=27417375) +4173 train 7.409331 (lr=1.7500e-04) (hash(x)=25581973) +4174 train 7.640458 (lr=1.7500e-04) (hash(x)=30360417) +4175 train 6.975270 (lr=1.7500e-04) (hash(x)=23862845) +4176 train 7.008232 (lr=1.7500e-04) (hash(x)=25415130) +4177 train 6.994325 (lr=1.7500e-04) (hash(x)=23111123) +4178 train 6.949319 (lr=1.7500e-04) (hash(x)=24022804) +4179 train 7.027178 (lr=1.7500e-04) (hash(x)=25148490) +4180 train 7.130949 (lr=1.7500e-04) (hash(x)=22792092) +4181 train 7.310864 (lr=1.7500e-04) (hash(x)=24779698) +4182 train 7.221675 (lr=1.7500e-04) (hash(x)=24870844) +4183 train 6.899203 (lr=1.7500e-04) (hash(x)=22664494) +4184 train 6.976438 (lr=1.7500e-04) (hash(x)=22599729) +4185 train 7.143285 (lr=1.7500e-04) (hash(x)=24707078) +4186 train 6.920532 (lr=1.7500e-04) (hash(x)=23823945) +4187 train 6.663333 (lr=1.7500e-04) (hash(x)=22219856) +4188 train 7.328804 (lr=1.7500e-04) (hash(x)=27061401) +4189 train 7.041309 (lr=1.7500e-04) (hash(x)=23398766) +4190 train 7.165486 (lr=1.7500e-04) (hash(x)=27916730) +4191 train 7.017190 (lr=1.7500e-04) (hash(x)=24092927) +4192 train 7.075250 (lr=1.7500e-04) (hash(x)=24723657) +4193 train 7.112228 (lr=1.7500e-04) (hash(x)=24676155) +4194 train 6.996059 (lr=1.7500e-04) (hash(x)=23455369) +4195 train 6.942634 (lr=1.7500e-04) (hash(x)=21999890) +4196 train 6.885499 (lr=1.7500e-04) (hash(x)=23385567) +4197 train 7.064878 (lr=1.7500e-04) (hash(x)=25120814) +4198 train 6.767447 (lr=1.7500e-04) (hash(x)=21308113) +4199 train 7.113201 (lr=1.7500e-04) (hash(x)=27213812) +4200 val loss 7.1070 +4200 val perplexity 1220.5375 +4200 train 6.670887 (lr=1.7500e-04) (hash(x)=19675382) +4201 train 6.961095 (lr=1.7500e-04) (hash(x)=23882161) +4202 train 6.916908 (lr=1.7500e-04) (hash(x)=24338567) +4203 train 7.228249 (lr=1.7500e-04) (hash(x)=27649723) +4204 train 7.061105 (lr=1.7500e-04) (hash(x)=27563514) +4205 train 7.055874 (lr=1.7500e-04) (hash(x)=23128552) +4206 train 6.921327 (lr=1.7500e-04) (hash(x)=26203283) +4207 train 7.013397 (lr=1.7500e-04) (hash(x)=23929955) +4208 train 6.664058 (lr=1.7500e-04) (hash(x)=20978691) +4209 train 6.967471 (lr=1.7500e-04) (hash(x)=21875178) +4210 train 7.023564 (lr=1.7500e-04) (hash(x)=23563293) +4211 train 7.127299 (lr=1.7500e-04) (hash(x)=25538503) +4212 train 7.236263 (lr=1.7500e-04) (hash(x)=24171014) +4213 train 7.072864 (lr=1.7500e-04) (hash(x)=22306665) +4214 train 7.020576 (lr=1.7500e-04) (hash(x)=26082318) +4215 train 6.817777 (lr=1.7500e-04) (hash(x)=23025790) +4216 train 6.863750 (lr=1.7500e-04) (hash(x)=21146597) +4217 train 7.211961 (lr=1.7500e-04) (hash(x)=27470230) +4218 train 6.959953 (lr=1.7500e-04) (hash(x)=22691005) +4219 train 6.756285 (lr=1.7500e-04) (hash(x)=21550313) +4220 train 6.839855 (lr=1.7500e-04) (hash(x)=20618443) +4221 train 6.962483 (lr=1.7500e-04) (hash(x)=25260787) +4222 train 7.057837 (lr=1.7500e-04) (hash(x)=25249873) +4223 train 6.705806 (lr=1.7500e-04) (hash(x)=20452272) +4224 train 7.035844 (lr=1.7500e-04) (hash(x)=25649764) +4225 train 6.863628 (lr=1.7500e-04) (hash(x)=19589460) +4226 train 7.275687 (lr=1.7500e-04) (hash(x)=26477595) +4227 train 7.478415 (lr=1.7500e-04) (hash(x)=27585442) +4228 train 7.213787 (lr=1.7500e-04) (hash(x)=25821343) +4229 train 7.104995 (lr=1.7500e-04) (hash(x)=24549919) +4230 train 7.080699 (lr=1.7500e-04) (hash(x)=26124522) +4231 train 7.343610 (lr=1.7500e-04) (hash(x)=26473464) +4232 train 7.369731 (lr=1.7500e-04) (hash(x)=28883028) +4233 train 7.328694 (lr=1.7500e-04) (hash(x)=29611296) +4234 train 7.163254 (lr=1.7500e-04) (hash(x)=29059941) +4235 train 7.041588 (lr=1.7500e-04) (hash(x)=26368203) +4236 train 7.131339 (lr=1.7500e-04) (hash(x)=27021360) +4237 train 7.031146 (lr=1.7500e-04) (hash(x)=26135379) +4238 train 6.848911 (lr=1.7500e-04) (hash(x)=25862549) +4239 train 7.160118 (lr=1.7500e-04) (hash(x)=28276603) +4240 train 6.788919 (lr=1.7500e-04) (hash(x)=22170090) +4241 train 7.098873 (lr=1.7500e-04) (hash(x)=22625589) +4242 train 7.093582 (lr=1.7500e-04) (hash(x)=25751475) +4243 train 7.042695 (lr=1.7500e-04) (hash(x)=25836838) +4244 train 6.964964 (lr=1.7500e-04) (hash(x)=23938214) +4245 train 6.907640 (lr=1.7500e-04) (hash(x)=22759365) +4246 train 6.903309 (lr=1.7500e-04) (hash(x)=24964628) +4247 train 6.537491 (lr=1.7500e-04) (hash(x)=21480367) +4248 train 7.164173 (lr=1.7500e-04) (hash(x)=25974694) +4249 train 7.470494 (lr=1.7500e-04) (hash(x)=29830546) +4250 val loss 7.1065 +4250 val perplexity 1219.8998 +4250 train 7.102458 (lr=1.7500e-04) (hash(x)=26283200) +4251 train 7.199074 (lr=1.7500e-04) (hash(x)=25605672) +4252 train 6.829280 (lr=1.7500e-04) (hash(x)=21439107) +4253 train 6.766222 (lr=1.7500e-04) (hash(x)=22626883) +4254 train 7.083556 (lr=1.7500e-04) (hash(x)=25627150) +4255 train 7.231052 (lr=1.7500e-04) (hash(x)=24658642) +4256 train 7.287477 (lr=1.7500e-04) (hash(x)=29755505) +4257 train 7.019628 (lr=1.7500e-04) (hash(x)=22750846) +4258 train 6.967262 (lr=1.7500e-04) (hash(x)=21892651) +4259 train 7.040643 (lr=1.7500e-04) (hash(x)=22487960) +4260 train 7.066219 (lr=1.7500e-04) (hash(x)=24059869) +4261 train 6.859638 (lr=1.7500e-04) (hash(x)=21090180) +4262 train 6.958578 (lr=1.7500e-04) (hash(x)=22716452) +4263 train 7.188899 (lr=1.7500e-04) (hash(x)=26854801) +4264 train 7.036253 (lr=1.7500e-04) (hash(x)=23815428) +4265 train 6.853766 (lr=1.7500e-04) (hash(x)=23368704) +4266 train 6.953880 (lr=1.7500e-04) (hash(x)=24301098) +4267 train 7.182527 (lr=1.7500e-04) (hash(x)=25025039) +4268 train 6.949477 (lr=1.7500e-04) (hash(x)=25425736) +4269 train 7.135807 (lr=1.7500e-04) (hash(x)=27439380) +4270 train 6.784027 (lr=1.7500e-04) (hash(x)=18682756) +4271 train 6.858596 (lr=1.7500e-04) (hash(x)=17862226) +4272 train 7.298510 (lr=1.7500e-04) (hash(x)=29946491) +4273 train 6.617489 (lr=1.7500e-04) (hash(x)=21392062) +4274 train 7.101375 (lr=1.7500e-04) (hash(x)=25195556) +4275 train 7.085672 (lr=1.7500e-04) (hash(x)=26682036) +4276 train 6.997792 (lr=1.7500e-04) (hash(x)=21235260) +4277 train 6.843641 (lr=1.7500e-04) (hash(x)=22118984) +4278 train 6.888005 (lr=1.7500e-04) (hash(x)=24094510) +4279 train 7.398637 (lr=1.7500e-04) (hash(x)=28519182) +4280 train 7.008360 (lr=1.7500e-04) (hash(x)=26652859) +4281 train 6.980931 (lr=1.7500e-04) (hash(x)=24463139) +4282 train 6.973431 (lr=1.7500e-04) (hash(x)=23281870) +4283 train 7.188820 (lr=1.7500e-04) (hash(x)=29181174) +4284 train 6.833325 (lr=1.7500e-04) (hash(x)=24797417) +4285 train 7.181496 (lr=1.7500e-04) (hash(x)=29026537) +4286 train 7.012378 (lr=1.7500e-04) (hash(x)=23045165) +4287 train 6.914928 (lr=1.7500e-04) (hash(x)=25193694) +4288 train 6.943740 (lr=1.7500e-04) (hash(x)=23475407) +4289 train 7.137113 (lr=1.7500e-04) (hash(x)=24875410) +4290 train 7.050106 (lr=1.7500e-04) (hash(x)=26328101) +4291 train 7.281043 (lr=1.7500e-04) (hash(x)=26273661) +4292 train 7.000175 (lr=1.7500e-04) (hash(x)=23271891) +4293 train 6.970685 (lr=1.7500e-04) (hash(x)=23300732) +4294 train 7.047971 (lr=1.7500e-04) (hash(x)=24243693) +4295 train 7.127213 (lr=1.7500e-04) (hash(x)=25642620) +4296 train 7.188531 (lr=1.7500e-04) (hash(x)=27730411) +4297 train 7.022406 (lr=1.7500e-04) (hash(x)=25485335) +4298 train 6.866549 (lr=1.7500e-04) (hash(x)=25268789) +4299 train 7.283952 (lr=1.7500e-04) (hash(x)=28917143) +4300 val loss 7.1428 +4300 val perplexity 1264.9525 +4300 train 7.380126 (lr=1.7500e-04) (hash(x)=28987991) +4301 train 7.096602 (lr=1.7500e-04) (hash(x)=25989151) +4302 train 7.018548 (lr=1.7500e-04) (hash(x)=25658195) +4303 train 7.005959 (lr=1.7500e-04) (hash(x)=25765909) +4304 train 7.010466 (lr=1.7500e-04) (hash(x)=25704261) +4305 train 7.015743 (lr=1.7500e-04) (hash(x)=24438198) +4306 train 6.897994 (lr=1.7500e-04) (hash(x)=22871710) +4307 train 6.723451 (lr=1.7500e-04) (hash(x)=20160896) +4308 train 7.207530 (lr=1.7500e-04) (hash(x)=24218641) +4309 train 6.700130 (lr=1.7500e-04) (hash(x)=22073751) +4310 train 6.964074 (lr=1.7500e-04) (hash(x)=26434959) +4311 train 6.691770 (lr=1.7500e-04) (hash(x)=20750531) +4312 train 6.836042 (lr=1.7500e-04) (hash(x)=22232293) +4313 train 7.065011 (lr=1.7500e-04) (hash(x)=27324521) +4314 train 6.785091 (lr=1.7500e-04) (hash(x)=22217862) +4315 train 7.196172 (lr=1.7500e-04) (hash(x)=25741958) +4316 train 6.996031 (lr=1.7500e-04) (hash(x)=22738456) +4317 train 7.040755 (lr=1.7500e-04) (hash(x)=25387302) +4318 train 7.014905 (lr=1.7500e-04) (hash(x)=24669014) +4319 train 7.149021 (lr=1.7500e-04) (hash(x)=24917098) +4320 train 7.083441 (lr=1.7500e-04) (hash(x)=26698227) +4321 train 6.878963 (lr=1.7500e-04) (hash(x)=23518293) +4322 train 6.810700 (lr=1.7500e-04) (hash(x)=23643971) +4323 train 7.014501 (lr=1.7500e-04) (hash(x)=25659505) +4324 train 6.785041 (lr=1.7500e-04) (hash(x)=22697720) +4325 train 7.318468 (lr=1.7500e-04) (hash(x)=25082178) +4326 train 6.872654 (lr=1.7500e-04) (hash(x)=24166546) +4327 train 7.010214 (lr=1.7500e-04) (hash(x)=24499766) +4328 train 7.129918 (lr=1.7500e-04) (hash(x)=24338607) +4329 train 6.908906 (lr=1.7500e-04) (hash(x)=23225420) +4330 train 7.056700 (lr=1.7500e-04) (hash(x)=25907032) +4331 train 6.843013 (lr=1.7500e-04) (hash(x)=24634979) +4332 train 6.937880 (lr=1.7500e-04) (hash(x)=22161377) +4333 train 7.093163 (lr=1.7500e-04) (hash(x)=22559939) +4334 train 6.903866 (lr=1.7500e-04) (hash(x)=20840022) +4335 train 7.175992 (lr=1.7500e-04) (hash(x)=25067358) +4336 train 6.868628 (lr=1.7500e-04) (hash(x)=23432626) +4337 train 6.980373 (lr=1.7500e-04) (hash(x)=23820385) +4338 train 7.730299 (lr=1.7500e-04) (hash(x)=31594930) +4339 train 7.192368 (lr=1.7500e-04) (hash(x)=27138750) +4340 train 7.408720 (lr=1.7500e-04) (hash(x)=30031341) +4341 train 6.983176 (lr=1.7500e-04) (hash(x)=24602807) +4342 train 6.772835 (lr=1.7500e-04) (hash(x)=21584976) +4343 train 7.159880 (lr=1.7500e-04) (hash(x)=27479796) +4344 train 6.894506 (lr=1.7500e-04) (hash(x)=22746241) +4345 train 7.038727 (lr=1.7500e-04) (hash(x)=19728452) +4346 train 6.861301 (lr=1.7500e-04) (hash(x)=24502020) +4347 train 7.305876 (lr=1.7500e-04) (hash(x)=28225954) +4348 train 6.956972 (lr=1.7500e-04) (hash(x)=23893447) +4349 train 7.239072 (lr=1.7500e-04) (hash(x)=25654586) +4350 val loss 7.1449 +4350 val perplexity 1267.5693 +4350 train 7.102319 (lr=1.7500e-04) (hash(x)=23856469) +4351 train 7.001012 (lr=1.7500e-04) (hash(x)=23136080) +4352 train 7.153427 (lr=1.7500e-04) (hash(x)=26532918) +4353 train 7.022318 (lr=1.7500e-04) (hash(x)=25461947) +4354 train 7.061990 (lr=1.7500e-04) (hash(x)=26590231) +4355 train 6.815564 (lr=1.7500e-04) (hash(x)=21441985) +4356 train 7.088727 (lr=1.7500e-04) (hash(x)=26507941) +4357 train 7.390579 (lr=1.7500e-04) (hash(x)=26245238) +4358 train 7.143541 (lr=1.7500e-04) (hash(x)=24879059) +4359 train 7.388731 (lr=1.7500e-04) (hash(x)=29810074) +4360 train 6.796245 (lr=1.7500e-04) (hash(x)=24258069) +4361 train 6.955223 (lr=1.7500e-04) (hash(x)=25229360) +4362 train 7.173777 (lr=1.7500e-04) (hash(x)=25440206) +4363 train 6.999785 (lr=1.7500e-04) (hash(x)=23222125) +4364 train 6.898576 (lr=1.7500e-04) (hash(x)=23353186) +4365 train 7.103778 (lr=1.7500e-04) (hash(x)=26995240) +4366 train 7.047716 (lr=1.7500e-04) (hash(x)=24135899) +4367 train 7.064230 (lr=1.7500e-04) (hash(x)=24765539) +4368 train 7.113111 (lr=1.7500e-04) (hash(x)=26051004) +4369 train 6.952275 (lr=1.7500e-04) (hash(x)=22559142) +4370 train 6.866576 (lr=1.7500e-04) (hash(x)=20364388) +4371 train 7.246991 (lr=1.7500e-04) (hash(x)=25938817) +4372 train 7.277291 (lr=1.7500e-04) (hash(x)=26060945) +4373 train 7.225324 (lr=1.7500e-04) (hash(x)=27866714) +4374 train 7.109702 (lr=1.7500e-04) (hash(x)=27104972) +4375 train 6.805991 (lr=1.7500e-04) (hash(x)=22216309) +4376 train 6.872656 (lr=1.7500e-04) (hash(x)=20781533) +4377 train 6.806471 (lr=1.7500e-04) (hash(x)=18784350) +4378 train 6.900343 (lr=1.7500e-04) (hash(x)=21102897) +4379 train 7.124701 (lr=1.7500e-04) (hash(x)=25647489) +4380 train 6.946046 (lr=1.7500e-04) (hash(x)=24486462) +4381 train 7.222438 (lr=1.7500e-04) (hash(x)=26539114) +4382 train 6.878729 (lr=1.7500e-04) (hash(x)=20026045) +4383 train 7.189941 (lr=1.7500e-04) (hash(x)=20613861) +4384 train 6.842113 (lr=1.7500e-04) (hash(x)=20676237) +4385 train 7.063283 (lr=1.7500e-04) (hash(x)=24893163) +4386 train 6.567828 (lr=1.7500e-04) (hash(x)=17299395) +4387 train 6.772278 (lr=1.7500e-04) (hash(x)=19580191) +4388 train 6.994658 (lr=1.7500e-04) (hash(x)=25588218) +4389 train 7.104179 (lr=1.7500e-04) (hash(x)=26433063) +4390 train 7.197750 (lr=1.7500e-04) (hash(x)=24917693) +4391 train 6.842305 (lr=1.7500e-04) (hash(x)=23462447) +4392 train 7.071188 (lr=1.7500e-04) (hash(x)=27185416) +4393 train 7.194590 (lr=1.7500e-04) (hash(x)=24109010) +4394 train 6.950430 (lr=1.7500e-04) (hash(x)=21486000) +4395 train 6.850349 (lr=1.7500e-04) (hash(x)=22230006) +4396 train 7.272448 (lr=1.7500e-04) (hash(x)=26092311) +4397 train 7.006215 (lr=1.7500e-04) (hash(x)=24112426) +4398 train 6.821372 (lr=1.7500e-04) (hash(x)=21881373) +4399 train 6.957394 (lr=1.7500e-04) (hash(x)=26739455) +4400 val loss 7.1124 +4400 val perplexity 1227.0908 +4400 train 6.900436 (lr=1.7500e-04) (hash(x)=22873602) +4401 train 6.899585 (lr=1.7500e-04) (hash(x)=26748712) +4402 train 7.116135 (lr=1.7500e-04) (hash(x)=26306618) +4403 train 7.285230 (lr=1.7500e-04) (hash(x)=26898808) +4404 train 7.016198 (lr=1.7500e-04) (hash(x)=25067751) +4405 train 7.048543 (lr=1.7500e-04) (hash(x)=25397145) +4406 train 7.202237 (lr=1.7500e-04) (hash(x)=24796962) +4407 train 7.010589 (lr=1.7500e-04) (hash(x)=23222996) +4408 train 6.970451 (lr=1.7500e-04) (hash(x)=24820189) +4409 train 7.402780 (lr=1.7500e-04) (hash(x)=27669038) +4410 train 6.972522 (lr=1.7500e-04) (hash(x)=24283976) +4411 train 7.149507 (lr=1.7500e-04) (hash(x)=25018789) +4412 train 7.097815 (lr=1.7500e-04) (hash(x)=26247064) +4413 train 7.109131 (lr=1.7500e-04) (hash(x)=22942904) +4414 train 6.990490 (lr=1.7500e-04) (hash(x)=23918746) +4415 train 7.095737 (lr=1.7500e-04) (hash(x)=26489285) +4416 train 6.174469 (lr=1.7500e-04) (hash(x)=14942495) +4417 train 6.974243 (lr=1.7500e-04) (hash(x)=23908505) +4418 train 7.188638 (lr=1.7500e-04) (hash(x)=25854036) +4419 train 7.072122 (lr=1.7500e-04) (hash(x)=27522868) +4420 train 6.993984 (lr=1.7500e-04) (hash(x)=26549205) +4421 train 6.825458 (lr=1.7500e-04) (hash(x)=24565522) +4422 train 7.174377 (lr=1.7500e-04) (hash(x)=23919123) +4423 train 7.025684 (lr=1.7500e-04) (hash(x)=25185942) +4424 train 7.038682 (lr=1.7500e-04) (hash(x)=24818969) +4425 train 7.115839 (lr=1.7500e-04) (hash(x)=26750372) +4426 train 7.108359 (lr=1.7500e-04) (hash(x)=25621536) +4427 train 7.525836 (lr=1.7500e-04) (hash(x)=28037060) +4428 train 7.558313 (lr=1.7500e-04) (hash(x)=30829517) +4429 train 7.150163 (lr=1.7500e-04) (hash(x)=28728766) +4430 train 7.074642 (lr=1.7500e-04) (hash(x)=25936895) +4431 train 7.284708 (lr=1.7500e-04) (hash(x)=27476158) +4432 train 6.953571 (lr=1.7500e-04) (hash(x)=23297921) +4433 train 6.909794 (lr=1.7500e-04) (hash(x)=23201299) +4434 train 6.859412 (lr=1.7500e-04) (hash(x)=22681766) +4435 train 6.878274 (lr=1.7500e-04) (hash(x)=23217512) +4436 train 7.344362 (lr=1.7500e-04) (hash(x)=29322443) +4437 train 6.943019 (lr=1.7500e-04) (hash(x)=23502072) +4438 train 7.010511 (lr=1.7500e-04) (hash(x)=28873527) +4439 train 7.034156 (lr=1.7500e-04) (hash(x)=23653175) +4440 train 6.804891 (lr=1.7500e-04) (hash(x)=21635879) +4441 train 6.900556 (lr=1.7500e-04) (hash(x)=22201854) +4442 train 6.779583 (lr=1.7500e-04) (hash(x)=23101164) +4443 train 7.209867 (lr=1.7500e-04) (hash(x)=25475122) +4444 train 6.970821 (lr=1.7500e-04) (hash(x)=25124825) +4445 train 7.112471 (lr=1.7500e-04) (hash(x)=26883852) +4446 train 6.868442 (lr=1.7500e-04) (hash(x)=24731829) +4447 train 6.846488 (lr=1.7500e-04) (hash(x)=22405076) +4448 train 7.024175 (lr=1.7500e-04) (hash(x)=27633869) +4449 train 7.099560 (lr=1.7500e-04) (hash(x)=25162594) +4450 val loss 7.1127 +4450 val perplexity 1227.4894 +4450 train 7.082954 (lr=1.7500e-04) (hash(x)=26438149) +4451 train 7.110100 (lr=1.7500e-04) (hash(x)=26748800) +4452 train 6.857396 (lr=1.7500e-04) (hash(x)=22971620) +4453 train 7.002971 (lr=1.7500e-04) (hash(x)=25886430) +4454 train 6.754205 (lr=1.7500e-04) (hash(x)=21084137) +4455 train 6.930908 (lr=1.7500e-04) (hash(x)=25673545) +4456 train 7.607714 (lr=1.7500e-04) (hash(x)=29389002) +4457 train 6.687821 (lr=1.7500e-04) (hash(x)=21676076) +4458 train 6.766918 (lr=1.7500e-04) (hash(x)=22616647) +4459 train 7.240474 (lr=1.7500e-04) (hash(x)=22771197) +4460 train 7.105809 (lr=1.7500e-04) (hash(x)=26393514) +4461 train 7.328421 (lr=1.7500e-04) (hash(x)=24996433) +4462 train 6.961356 (lr=1.7500e-04) (hash(x)=19594028) +4463 train 7.092368 (lr=1.7500e-04) (hash(x)=22675428) +4464 train 7.106622 (lr=1.7500e-04) (hash(x)=26566551) +4465 train 7.126617 (lr=1.7500e-04) (hash(x)=22469290) +4466 train 7.571964 (lr=1.7500e-04) (hash(x)=29821654) +4467 train 7.040587 (lr=1.7500e-04) (hash(x)=26305388) +4468 train 6.959989 (lr=1.7500e-04) (hash(x)=21998506) +4469 train 7.346590 (lr=1.7500e-04) (hash(x)=23953315) +4470 train 7.021478 (lr=1.7500e-04) (hash(x)=23985456) +4471 train 7.417279 (lr=1.7500e-04) (hash(x)=28168456) +4472 train 7.061865 (lr=1.7500e-04) (hash(x)=25126411) +4473 train 6.858317 (lr=1.7500e-04) (hash(x)=24619336) +4474 train 6.994794 (lr=1.7500e-04) (hash(x)=24467798) +4475 train 7.844757 (lr=1.7500e-04) (hash(x)=31673254) +4476 train 7.630435 (lr=1.7500e-04) (hash(x)=29929610) +4477 train 7.365678 (lr=1.7500e-04) (hash(x)=29412572) +4478 train 7.523161 (lr=1.7500e-04) (hash(x)=31910006) +4479 train 7.178441 (lr=1.7500e-04) (hash(x)=26072586) +4480 train 7.107488 (lr=1.7500e-04) (hash(x)=25782825) +4481 train 6.967590 (lr=1.7500e-04) (hash(x)=21131363) +4482 train 7.039028 (lr=1.7500e-04) (hash(x)=25071223) +4483 train 7.701118 (lr=1.7500e-04) (hash(x)=32249577) +4484 train 6.931676 (lr=1.7500e-04) (hash(x)=24752808) +4485 train 6.957326 (lr=1.7500e-04) (hash(x)=24970539) +4486 train 6.881783 (lr=1.7500e-04) (hash(x)=24191005) +4487 train 7.120189 (lr=1.7500e-04) (hash(x)=24974331) +4488 train 7.262846 (lr=1.7500e-04) (hash(x)=27043409) +4489 train 6.911826 (lr=1.7500e-04) (hash(x)=11320385) +4490 train 6.885559 (lr=1.7500e-04) (hash(x)=11919565) +4491 train 6.827835 (lr=1.7500e-04) (hash(x)=10404694) +4492 train 6.798361 (lr=1.7500e-04) (hash(x)=12393159) +4493 train 6.600420 (lr=1.7500e-04) (hash(x)=11843609) +4494 train 6.595790 (lr=1.7500e-04) (hash(x)=12632729) +4495 train 7.074004 (lr=1.7500e-04) (hash(x)=21951984) +4496 train 7.917647 (lr=1.7500e-04) (hash(x)=19411544) +4497 train 7.827414 (lr=1.7500e-04) (hash(x)=21000228) +4498 train 7.308177 (lr=1.7500e-04) (hash(x)=26018207) +4499 train 7.364645 (lr=1.7500e-04) (hash(x)=24659058) +4500 val loss 7.2224 +4500 val perplexity 1369.7734 +4500 train 7.514611 (lr=1.7500e-04) (hash(x)=27919597) +4501 train 7.084221 (lr=1.7500e-04) (hash(x)=26232596) +4502 train 7.244340 (lr=1.7500e-04) (hash(x)=26248912) +4503 train 7.154767 (lr=1.7500e-04) (hash(x)=25403751) +4504 train 7.053992 (lr=1.7500e-04) (hash(x)=21096637) +4505 train 7.224683 (lr=1.7500e-04) (hash(x)=26560941) +4506 train 7.241886 (lr=1.7500e-04) (hash(x)=24942406) +4507 train 7.307146 (lr=1.7500e-04) (hash(x)=24405748) +4508 train 7.141798 (lr=1.7500e-04) (hash(x)=22975455) +4509 train 7.111810 (lr=1.7500e-04) (hash(x)=26358820) +4510 train 7.097421 (lr=1.7500e-04) (hash(x)=24211938) +4511 train 7.246799 (lr=1.7500e-04) (hash(x)=26396012) +4512 train 6.885783 (lr=1.7500e-04) (hash(x)=22534410) +4513 train 7.006852 (lr=1.7500e-04) (hash(x)=23855025) +4514 train 6.889453 (lr=1.7500e-04) (hash(x)=22722345) +4515 train 6.884996 (lr=1.7500e-04) (hash(x)=22779251) +4516 train 7.167856 (lr=1.7500e-04) (hash(x)=23973078) +4517 train 7.040654 (lr=1.7500e-04) (hash(x)=19886228) +4518 train 7.083931 (lr=1.7500e-04) (hash(x)=23849694) +4519 train 7.521263 (lr=1.7500e-04) (hash(x)=24827190) +4520 train 7.054914 (lr=1.7500e-04) (hash(x)=25111498) +4521 train 7.877168 (lr=1.7500e-04) (hash(x)=29752556) +4522 train 7.367671 (lr=1.7500e-04) (hash(x)=25606805) +4523 train 7.131032 (lr=1.7500e-04) (hash(x)=22209714) +4524 train 6.825515 (lr=1.7500e-04) (hash(x)=24991834) +4525 train 7.100447 (lr=1.7500e-04) (hash(x)=27808158) +4526 train 7.069881 (lr=1.7500e-04) (hash(x)=23041199) +4527 train 7.103597 (lr=1.7500e-04) (hash(x)=24847458) +4528 train 7.074441 (lr=1.7500e-04) (hash(x)=25091787) +4529 train 7.952985 (lr=1.7500e-04) (hash(x)=29745551) +4530 train 6.795902 (lr=1.7500e-04) (hash(x)=20447167) +4531 train 7.045883 (lr=1.7500e-04) (hash(x)=20720911) +4532 train 7.104160 (lr=1.7500e-04) (hash(x)=24803353) +4533 train 7.170837 (lr=1.7500e-04) (hash(x)=23780724) +4534 train 7.156176 (lr=1.7500e-04) (hash(x)=23423120) +4535 train 6.854730 (lr=1.7500e-04) (hash(x)=22159088) +4536 train 7.046083 (lr=1.7500e-04) (hash(x)=25820304) +4537 train 6.849726 (lr=1.7500e-04) (hash(x)=22813612) +4538 train 7.178220 (lr=1.7500e-04) (hash(x)=27827979) +4539 train 7.175392 (lr=1.7500e-04) (hash(x)=25737179) +4540 train 7.417167 (lr=1.7500e-04) (hash(x)=23401504) +4541 train 7.066661 (lr=1.7500e-04) (hash(x)=25071988) +4542 train 7.142597 (lr=1.7500e-04) (hash(x)=22844541) +4543 train 6.855976 (lr=1.7500e-04) (hash(x)=22140034) +4544 train 7.116691 (lr=1.7500e-04) (hash(x)=26522091) +4545 train 7.142949 (lr=1.7500e-04) (hash(x)=24099725) +4546 train 6.680800 (lr=1.7500e-04) (hash(x)=19127182) +4547 train 6.795557 (lr=1.7500e-04) (hash(x)=18992693) +4548 train 7.805429 (lr=1.7500e-04) (hash(x)=26723015) +4549 train 7.599594 (lr=1.7500e-04) (hash(x)=30389969) +4550 val loss 7.1720 +4550 val perplexity 1302.4673 +4550 train 6.993732 (lr=1.7500e-04) (hash(x)=24065654) +4551 train 6.746611 (lr=1.7500e-04) (hash(x)=19044797) +4552 train 7.214717 (lr=1.7500e-04) (hash(x)=24919665) +4553 train 7.300506 (lr=1.7500e-04) (hash(x)=22780968) +4554 train 7.028773 (lr=1.7500e-04) (hash(x)=24549699) +4555 train 6.900822 (lr=1.7500e-04) (hash(x)=21374811) +4556 train 6.982660 (lr=1.7500e-04) (hash(x)=25225950) +4557 train 7.091712 (lr=1.7500e-04) (hash(x)=25691882) +4558 train 7.017639 (lr=1.7500e-04) (hash(x)=24685235) +4559 train 6.828872 (lr=1.7500e-04) (hash(x)=23932794) +4560 train 7.419189 (lr=1.7500e-04) (hash(x)=28152043) +4561 train 6.921200 (lr=1.7500e-04) (hash(x)=23417051) +4562 train 6.994627 (lr=1.7500e-04) (hash(x)=26250211) +4563 train 7.231483 (lr=1.7500e-04) (hash(x)=25428813) +4564 train 7.342789 (lr=1.7500e-04) (hash(x)=27477379) +4565 train 7.153554 (lr=1.7500e-04) (hash(x)=23015212) +4566 train 6.887961 (lr=1.7500e-04) (hash(x)=22837608) +4567 train 6.943177 (lr=1.7500e-04) (hash(x)=25256890) +4568 train 6.839485 (lr=1.7500e-04) (hash(x)=22742827) +4569 train 7.241637 (lr=1.7500e-04) (hash(x)=30167922) +4570 train 6.959383 (lr=1.7500e-04) (hash(x)=24540265) +4571 train 7.264345 (lr=1.7500e-04) (hash(x)=26752941) +4572 train 7.071613 (lr=1.7500e-04) (hash(x)=25094026) +4573 train 7.751232 (lr=1.7500e-04) (hash(x)=28508785) +4574 train 7.200665 (lr=1.7500e-04) (hash(x)=26501871) +4575 train 6.947867 (lr=1.7500e-04) (hash(x)=24161711) +4576 train 6.870737 (lr=1.7500e-04) (hash(x)=24313695) +4577 train 7.299759 (lr=1.7500e-04) (hash(x)=28248933) +4578 train 7.446537 (lr=1.7500e-04) (hash(x)=28445722) +4579 train 7.041597 (lr=1.7500e-04) (hash(x)=24589015) +4580 train 7.228458 (lr=1.7500e-04) (hash(x)=26192193) +4581 train 6.918031 (lr=1.7500e-04) (hash(x)=25131316) +4582 train 7.005292 (lr=1.7500e-04) (hash(x)=26631504) +4583 train 6.846464 (lr=1.7500e-04) (hash(x)=22036817) +4584 train 7.384862 (lr=1.7500e-04) (hash(x)=28361254) +4585 train 7.102940 (lr=1.7500e-04) (hash(x)=24828340) +4586 train 6.785722 (lr=1.7500e-04) (hash(x)=24067304) +4587 train 6.594727 (lr=1.7500e-04) (hash(x)=20733289) +4588 train 6.525433 (lr=1.7500e-04) (hash(x)=19526622) +4589 train 6.871487 (lr=1.7500e-04) (hash(x)=22148688) +4590 train 7.054565 (lr=1.7500e-04) (hash(x)=24141800) +4591 train 7.089830 (lr=1.7500e-04) (hash(x)=26663208) +4592 train 6.809528 (lr=1.7500e-04) (hash(x)=22536305) +4593 train 7.081886 (lr=1.7500e-04) (hash(x)=23608185) +4594 train 6.903867 (lr=1.7500e-04) (hash(x)=23348495) +4595 train 7.068006 (lr=1.7500e-04) (hash(x)=25409759) +4596 train 7.052815 (lr=1.7500e-04) (hash(x)=25572131) +4597 train 7.030762 (lr=1.7500e-04) (hash(x)=21782039) +4598 train 6.993367 (lr=1.7500e-04) (hash(x)=24643923) +4599 train 6.955698 (lr=1.7500e-04) (hash(x)=24072213) +4600 val loss 7.1354 +4600 val perplexity 1255.6270 +4600 train 6.896392 (lr=1.7500e-04) (hash(x)=23925612) +4601 train 6.986859 (lr=1.7500e-04) (hash(x)=23315415) +4602 train 7.014752 (lr=1.7500e-04) (hash(x)=21793800) +4603 train 6.929297 (lr=1.7500e-04) (hash(x)=24921200) +4604 train 7.139450 (lr=1.7500e-04) (hash(x)=27226113) +4605 train 6.956831 (lr=1.7500e-04) (hash(x)=22920960) +4606 train 6.890992 (lr=1.7500e-04) (hash(x)=21947750) +4607 train 6.981548 (lr=1.7500e-04) (hash(x)=22766044) +4608 train 7.350783 (lr=1.7500e-04) (hash(x)=28237005) +4609 train 6.806916 (lr=1.7500e-04) (hash(x)=24922621) +4610 train 7.083870 (lr=1.7500e-04) (hash(x)=24899830) +4611 train 7.441251 (lr=1.7500e-04) (hash(x)=32920298) +4612 train 6.881612 (lr=1.7500e-04) (hash(x)=25083835) +4613 train 6.933241 (lr=1.7500e-04) (hash(x)=22863054) +4614 train 6.986885 (lr=1.7500e-04) (hash(x)=24841464) +4615 train 7.258446 (lr=1.7500e-04) (hash(x)=27871153) +4616 train 7.304950 (lr=1.7500e-04) (hash(x)=28025163) +4617 train 6.884561 (lr=1.7500e-04) (hash(x)=24659561) +4618 train 6.975351 (lr=1.7500e-04) (hash(x)=25067194) +4619 train 7.025748 (lr=1.7500e-04) (hash(x)=22731460) +4620 train 6.955396 (lr=1.7500e-04) (hash(x)=20445873) +4621 train 7.051474 (lr=1.7500e-04) (hash(x)=26033948) +4622 train 6.944663 (lr=1.7500e-04) (hash(x)=22473213) +4623 train 7.501720 (lr=1.7500e-04) (hash(x)=24037280) +4624 train 7.966820 (lr=1.7500e-04) (hash(x)=25624131) +4625 train 7.559694 (lr=1.7500e-04) (hash(x)=26799867) +4626 train 7.071013 (lr=1.7500e-04) (hash(x)=27187602) +4627 train 7.031326 (lr=1.7500e-04) (hash(x)=23277695) +4628 train 7.019418 (lr=1.7500e-04) (hash(x)=24748234) +4629 train 7.135560 (lr=1.7500e-04) (hash(x)=26103104) +4630 train 7.054318 (lr=1.7500e-04) (hash(x)=24327389) +4631 train 7.140790 (lr=1.7500e-04) (hash(x)=24121850) +4632 train 7.002394 (lr=1.7500e-04) (hash(x)=23714590) +4633 train 7.079024 (lr=1.7500e-04) (hash(x)=22379412) +4634 train 7.285748 (lr=1.7500e-04) (hash(x)=24454713) +4635 train 7.005144 (lr=1.7500e-04) (hash(x)=22966977) +4636 train 6.954584 (lr=1.7500e-04) (hash(x)=23764884) +4637 train 6.810939 (lr=1.7500e-04) (hash(x)=23827429) +4638 train 7.072034 (lr=1.7500e-04) (hash(x)=24088592) +4639 train 6.987057 (lr=1.7500e-04) (hash(x)=24380031) +4640 train 7.094594 (lr=1.7500e-04) (hash(x)=26065050) +4641 train 7.015021 (lr=1.7500e-04) (hash(x)=24442902) +4642 train 6.618497 (lr=1.7500e-04) (hash(x)=18548782) +4643 train 7.099091 (lr=1.7500e-04) (hash(x)=26957303) +4644 train 7.104202 (lr=1.7500e-04) (hash(x)=25032727) +4645 train 6.987469 (lr=1.7500e-04) (hash(x)=27224706) +4646 train 7.136072 (lr=1.7500e-04) (hash(x)=27508476) +4647 train 6.847945 (lr=1.7500e-04) (hash(x)=23055215) +4648 train 6.974508 (lr=1.7500e-04) (hash(x)=24496194) +4649 train 8.078059 (lr=1.7500e-04) (hash(x)=13982941) +4650 val loss 7.1263 +4650 val perplexity 1244.3025 +4650 train 7.372904 (lr=1.7500e-04) (hash(x)=16721547) +4651 train 7.007012 (lr=1.7500e-04) (hash(x)=22929154) +4652 train 6.947191 (lr=1.7500e-04) (hash(x)=23323994) +4653 train 7.275989 (lr=1.7500e-04) (hash(x)=24877951) +4654 train 7.137231 (lr=1.7500e-04) (hash(x)=24096183) +4655 train 6.989414 (lr=1.7500e-04) (hash(x)=25329724) +4656 train 6.941872 (lr=1.7500e-04) (hash(x)=23877337) +4657 train 6.557182 (lr=1.7500e-04) (hash(x)=20923083) +4658 train 6.841167 (lr=1.7500e-04) (hash(x)=23807996) +4659 train 6.998610 (lr=1.7500e-04) (hash(x)=24370475) +4660 train 7.413621 (lr=1.7500e-04) (hash(x)=28202255) +4661 train 7.131105 (lr=1.7500e-04) (hash(x)=26142119) +4662 train 6.896498 (lr=1.7500e-04) (hash(x)=21387743) +4663 train 7.043756 (lr=1.7500e-04) (hash(x)=25662408) +4664 train 7.057080 (lr=1.7500e-04) (hash(x)=23962815) +4665 train 7.026367 (lr=1.7500e-04) (hash(x)=23987677) +4666 train 7.278028 (lr=1.7500e-04) (hash(x)=26554284) +4667 train 7.302551 (lr=1.7500e-04) (hash(x)=25991817) +4668 train 7.025933 (lr=1.7500e-04) (hash(x)=24256966) +4669 train 6.782987 (lr=1.7500e-04) (hash(x)=22187158) +4670 train 7.072624 (lr=1.7500e-04) (hash(x)=26295320) +4671 train 7.119562 (lr=1.7500e-04) (hash(x)=26346814) +4672 train 7.410239 (lr=1.7500e-04) (hash(x)=26594196) +4673 train 7.166975 (lr=1.7500e-04) (hash(x)=24322101) +4674 train 7.202241 (lr=1.7500e-04) (hash(x)=27274566) +4675 train 7.054610 (lr=1.7500e-04) (hash(x)=24505725) +4676 train 7.207559 (lr=1.7500e-04) (hash(x)=26167371) +4677 train 7.276065 (lr=1.7500e-04) (hash(x)=28062311) +4678 train 6.994720 (lr=1.7500e-04) (hash(x)=23476009) +4679 train 7.111716 (lr=1.7500e-04) (hash(x)=25283256) +4680 train 6.813015 (lr=1.7500e-04) (hash(x)=22033246) +4681 train 6.845026 (lr=1.7500e-04) (hash(x)=22716214) +4682 train 7.047307 (lr=1.7500e-04) (hash(x)=25672672) +4683 train 6.867331 (lr=1.7500e-04) (hash(x)=22979072) +4684 train 7.067035 (lr=1.7500e-04) (hash(x)=27439204) +4685 train 6.966386 (lr=1.7500e-04) (hash(x)=24857737) +4686 train 7.307570 (lr=1.7500e-04) (hash(x)=29615897) +4687 train 6.828994 (lr=1.7500e-04) (hash(x)=24021771) +4688 train 7.019406 (lr=1.7500e-04) (hash(x)=27410807) +4689 train 6.819627 (lr=1.7500e-04) (hash(x)=22850411) +4690 train 7.097543 (lr=1.7500e-04) (hash(x)=24949696) +4691 train 6.891466 (lr=1.7500e-04) (hash(x)=22956381) +4692 train 7.423378 (lr=1.7500e-04) (hash(x)=28193458) +4693 train 6.957568 (lr=1.7500e-04) (hash(x)=25596844) +4694 train 6.895070 (lr=1.7500e-04) (hash(x)=22101377) +4695 train 6.820043 (lr=1.7500e-04) (hash(x)=23576840) +4696 train 6.781311 (lr=1.7500e-04) (hash(x)=21849758) +4697 train 6.986720 (lr=1.7500e-04) (hash(x)=26431349) +4698 train 7.141427 (lr=1.7500e-04) (hash(x)=22960758) +4699 train 7.024680 (lr=1.7500e-04) (hash(x)=23243097) +4700 val loss 7.1063 +4700 val perplexity 1219.5922 +4700 train 6.891342 (lr=1.7500e-04) (hash(x)=23715370) +4701 train 7.525217 (lr=1.7500e-04) (hash(x)=30678293) +4702 train 7.595863 (lr=1.7500e-04) (hash(x)=32481620) +4703 train 7.192128 (lr=1.7500e-04) (hash(x)=26414858) +4704 train 7.091576 (lr=1.7500e-04) (hash(x)=24768691) +4705 train 6.798102 (lr=1.7500e-04) (hash(x)=21627762) +4706 train 6.867720 (lr=1.7500e-04) (hash(x)=21024917) +4707 train 6.773379 (lr=1.7500e-04) (hash(x)=23570951) +4708 train 6.891390 (lr=1.7500e-04) (hash(x)=23729185) +4709 train 7.247278 (lr=1.7500e-04) (hash(x)=25933754) +4710 train 6.752493 (lr=1.7500e-04) (hash(x)=23091014) +4711 train 6.824156 (lr=1.7500e-04) (hash(x)=20099261) +4712 train 7.006239 (lr=1.7500e-04) (hash(x)=26807297) +4713 train 6.838999 (lr=1.7500e-04) (hash(x)=25332115) +4714 train 6.866513 (lr=1.7500e-04) (hash(x)=23247605) +4715 train 6.751999 (lr=1.7500e-04) (hash(x)=23786549) +4716 train 6.883462 (lr=1.7500e-04) (hash(x)=23981166) +4717 train 7.014409 (lr=1.7500e-04) (hash(x)=25967754) +4718 train 6.925237 (lr=1.7500e-04) (hash(x)=23659116) +4719 train 6.976562 (lr=1.7500e-04) (hash(x)=22453718) +4720 train 6.845764 (lr=1.7500e-04) (hash(x)=22597951) +4721 train 7.100304 (lr=1.7500e-04) (hash(x)=25284885) +4722 train 7.047435 (lr=1.7500e-04) (hash(x)=24748569) +4723 train 6.672109 (lr=1.7500e-04) (hash(x)=19448608) +4724 train 7.012447 (lr=1.7500e-04) (hash(x)=24888040) +4725 train 6.843946 (lr=1.7500e-04) (hash(x)=23203503) +4726 train 6.607776 (lr=1.7500e-04) (hash(x)=20387787) +4727 train 6.717639 (lr=1.7500e-04) (hash(x)=22529445) +4728 train 7.016317 (lr=1.7500e-04) (hash(x)=22455471) +4729 train 7.004571 (lr=1.7500e-04) (hash(x)=25661132) +4730 train 6.995080 (lr=1.7500e-04) (hash(x)=24997711) +4731 train 7.109337 (lr=1.7500e-04) (hash(x)=22575521) +4732 train 6.878627 (lr=1.7500e-04) (hash(x)=22640285) +4733 train 6.738213 (lr=1.7500e-04) (hash(x)=18637357) +4734 train 6.837934 (lr=1.7500e-04) (hash(x)=22845826) +4735 train 7.080840 (lr=1.7500e-04) (hash(x)=24484543) +4736 train 6.938785 (lr=1.7500e-04) (hash(x)=23352320) +4737 train 6.725721 (lr=1.7500e-04) (hash(x)=21544758) +4738 train 6.522745 (lr=1.7500e-04) (hash(x)=18292136) +4739 train 7.171741 (lr=1.7500e-04) (hash(x)=24893614) +4740 train 7.023208 (lr=1.7500e-04) (hash(x)=28103443) +4741 train 6.859921 (lr=1.7500e-04) (hash(x)=22233356) +4742 train 6.726717 (lr=1.7500e-04) (hash(x)=21133541) +4743 train 6.994423 (lr=1.7500e-04) (hash(x)=24043998) +4744 train 7.300260 (lr=1.7500e-04) (hash(x)=24801185) +4745 train 7.077065 (lr=1.7500e-04) (hash(x)=23858358) +4746 train 7.074848 (lr=1.7500e-04) (hash(x)=23926989) +4747 train 7.138233 (lr=1.7500e-04) (hash(x)=24813708) +4748 train 6.981454 (lr=1.7500e-04) (hash(x)=26339467) +4749 train 6.822656 (lr=1.7500e-04) (hash(x)=21850656) +4750 val loss 7.0990 +4750 val perplexity 1210.7141 +4750 train 6.807538 (lr=1.7500e-04) (hash(x)=21475802) +4751 train 7.005914 (lr=1.7500e-04) (hash(x)=24301906) +4752 train 6.841510 (lr=1.7500e-04) (hash(x)=22748495) +4753 train 7.004253 (lr=1.7500e-04) (hash(x)=25649256) +4754 train 6.878082 (lr=1.7500e-04) (hash(x)=23934346) +4755 train 7.015076 (lr=1.7500e-04) (hash(x)=26332892) +4756 train 6.875137 (lr=1.7500e-04) (hash(x)=23279389) +4757 train 6.965362 (lr=1.7500e-04) (hash(x)=23146858) +4758 train 7.324520 (lr=1.7500e-04) (hash(x)=26892932) +4759 train 6.876909 (lr=1.7500e-04) (hash(x)=26328881) +4760 train 6.925916 (lr=1.7500e-04) (hash(x)=24394655) +4761 train 6.918846 (lr=1.7500e-04) (hash(x)=22122308) +4762 train 7.078157 (lr=1.7500e-04) (hash(x)=24200369) +4763 train 7.194200 (lr=1.7500e-04) (hash(x)=26841776) +4764 train 7.172798 (lr=1.7500e-04) (hash(x)=27196641) +4765 train 6.914791 (lr=1.7500e-04) (hash(x)=24912822) +4766 train 7.146778 (lr=1.7500e-04) (hash(x)=25946055) +4767 train 6.780074 (lr=1.7500e-04) (hash(x)=23101508) +4768 train 6.949377 (lr=1.7500e-04) (hash(x)=24287798) +4769 train 7.035095 (lr=1.7500e-04) (hash(x)=22798964) +4770 train 6.923381 (lr=1.7500e-04) (hash(x)=24164479) +4771 train 7.010239 (lr=1.7500e-04) (hash(x)=24946464) +4772 train 7.123395 (lr=1.7500e-04) (hash(x)=25154423) +4773 train 6.871847 (lr=1.7500e-04) (hash(x)=23173476) +4774 train 7.083847 (lr=1.7500e-04) (hash(x)=25373559) +4775 train 7.060484 (lr=1.7500e-04) (hash(x)=23527176) +4776 train 6.964174 (lr=1.7500e-04) (hash(x)=24865403) +4777 train 6.943678 (lr=1.7500e-04) (hash(x)=24451067) +4778 train 7.515311 (lr=1.7500e-04) (hash(x)=28187162) +4779 train 7.697026 (lr=1.7500e-04) (hash(x)=31163350) +4780 train 7.996385 (lr=1.7500e-04) (hash(x)=33563280) +4781 train 8.050170 (lr=1.7500e-04) (hash(x)=34939183) +4782 train 7.542406 (lr=1.7500e-04) (hash(x)=30263543) +4783 train 6.901245 (lr=1.7500e-04) (hash(x)=22705673) +4784 train 6.801995 (lr=1.7500e-04) (hash(x)=21415023) +4785 train 7.025751 (lr=1.7500e-04) (hash(x)=26079097) +4786 train 7.359833 (lr=1.7500e-04) (hash(x)=25503836) +4787 train 7.207101 (lr=1.7500e-04) (hash(x)=24705721) +4788 train 7.085626 (lr=1.7500e-04) (hash(x)=24384657) +4789 train 6.985368 (lr=1.7500e-04) (hash(x)=22550579) +4790 train 7.003650 (lr=1.7500e-04) (hash(x)=22452164) +4791 train 7.258467 (lr=1.7500e-04) (hash(x)=28664796) +4792 train 7.610797 (lr=1.7500e-04) (hash(x)=26139280) +4793 train 7.230995 (lr=1.7500e-04) (hash(x)=23862341) +4794 train 6.831105 (lr=1.7500e-04) (hash(x)=23784757) +4795 train 6.700763 (lr=1.7500e-04) (hash(x)=22659441) +4796 train 7.451528 (lr=1.7500e-04) (hash(x)=29744216) +4797 train 7.405090 (lr=1.7500e-04) (hash(x)=25822591) +4798 train 6.835914 (lr=1.7500e-04) (hash(x)=22370895) +4799 train 7.234263 (lr=1.7500e-04) (hash(x)=27102890) +4800 val loss 7.1185 +4800 val perplexity 1234.6093 +4800 train 7.262348 (lr=1.7500e-04) (hash(x)=27014625) +4801 train 7.037796 (lr=1.7500e-04) (hash(x)=25755963) +4802 train 7.271214 (lr=1.7500e-04) (hash(x)=29675278) +4803 train 7.423630 (lr=1.7500e-04) (hash(x)=26660930) +4804 train 7.316419 (lr=1.7500e-04) (hash(x)=24557060) +4805 train 7.420755 (lr=1.7500e-04) (hash(x)=24622741) +4806 train 7.493041 (lr=1.7500e-04) (hash(x)=23952601) +4807 train 7.151272 (lr=1.7500e-04) (hash(x)=26787259) +4808 train 7.361515 (lr=1.7500e-04) (hash(x)=28919605) +4809 train 7.682420 (lr=1.7500e-04) (hash(x)=37061654) +4810 train 7.496076 (lr=1.7500e-04) (hash(x)=30379739) +4811 train 7.234116 (lr=1.7500e-04) (hash(x)=26097180) +4812 train 7.392285 (lr=1.7500e-04) (hash(x)=26327092) +4813 train 7.146948 (lr=1.7500e-04) (hash(x)=23258030) +4814 train 7.230910 (lr=1.7500e-04) (hash(x)=25582015) +4815 train 6.898590 (lr=1.7500e-04) (hash(x)=23396088) +4816 train 6.902883 (lr=1.7500e-04) (hash(x)=21904146) +4817 train 7.106231 (lr=1.7500e-04) (hash(x)=26281676) +4818 train 6.881092 (lr=1.7500e-04) (hash(x)=23140470) +4819 train 7.174245 (lr=1.7500e-04) (hash(x)=24611098) +4820 train 7.003568 (lr=1.7500e-04) (hash(x)=23832642) +4821 train 7.147785 (lr=1.7500e-04) (hash(x)=21439671) +4822 train 6.965550 (lr=1.7500e-04) (hash(x)=25128845) +4823 train 6.936719 (lr=1.7500e-04) (hash(x)=24911831) +4824 train 7.073650 (lr=1.7500e-04) (hash(x)=26051723) +4825 train 7.124611 (lr=1.7500e-04) (hash(x)=26479565) +4826 train 7.237741 (lr=1.7500e-04) (hash(x)=26228987) +4827 train 7.116625 (lr=1.7500e-04) (hash(x)=25131300) +4828 train 6.844521 (lr=1.7500e-04) (hash(x)=19921978) +4829 train 6.840680 (lr=1.7500e-04) (hash(x)=23173449) +4830 train 7.167722 (lr=1.7500e-04) (hash(x)=24791832) +4831 train 6.871216 (lr=1.7500e-04) (hash(x)=23453491) +4832 train 7.058960 (lr=1.7500e-04) (hash(x)=22564139) +4833 train 6.875249 (lr=1.7500e-04) (hash(x)=21659918) +4834 train 7.016883 (lr=1.7500e-04) (hash(x)=22956076) +4835 train 7.153249 (lr=1.7500e-04) (hash(x)=22237612) +4836 train 7.239302 (lr=1.7500e-04) (hash(x)=24736427) +4837 train 7.322922 (lr=1.7500e-04) (hash(x)=24939751) +4838 train 7.194998 (lr=1.7500e-04) (hash(x)=25059298) +4839 train 7.120403 (lr=1.7500e-04) (hash(x)=23453396) +4840 train 6.666296 (lr=1.7500e-04) (hash(x)=17919338) +4841 train 7.139098 (lr=1.7500e-04) (hash(x)=23428815) +4842 train 7.348772 (lr=1.7500e-04) (hash(x)=27042659) +4843 train 7.381634 (lr=1.7500e-04) (hash(x)=25161278) +4844 train 7.199674 (lr=1.7500e-04) (hash(x)=24113253) +4845 train 7.308431 (lr=1.7500e-04) (hash(x)=26139263) +4846 train 7.334677 (lr=1.7500e-04) (hash(x)=27787006) +4847 train 7.093866 (lr=1.7500e-04) (hash(x)=23869612) +4848 train 7.211361 (lr=1.7500e-04) (hash(x)=26092193) +4849 train 7.292240 (lr=1.7500e-04) (hash(x)=29351182) +4850 val loss 7.1071 +4850 val perplexity 1220.5684 +4850 train 7.403520 (lr=1.7500e-04) (hash(x)=28773463) +4851 train 7.367145 (lr=1.7500e-04) (hash(x)=28207741) +4852 train 6.935646 (lr=1.7500e-04) (hash(x)=23280878) +4853 train 7.372486 (lr=1.7500e-04) (hash(x)=26742336) +4854 train 7.144474 (lr=1.7500e-04) (hash(x)=23543321) +4855 train 7.582853 (lr=1.7500e-04) (hash(x)=26581590) +4856 train 6.977327 (lr=1.7500e-04) (hash(x)=22728668) +4857 train 6.839541 (lr=1.7500e-04) (hash(x)=19854534) +4858 train 7.230709 (lr=1.7500e-04) (hash(x)=26612813) +4859 train 7.368410 (lr=1.7500e-04) (hash(x)=25827863) +4860 train 6.991214 (lr=1.7500e-04) (hash(x)=24574997) +4861 train 7.175144 (lr=1.7500e-04) (hash(x)=26187830) +4862 train 7.102264 (lr=1.7500e-04) (hash(x)=25105823) +4863 train 7.194727 (lr=1.7500e-04) (hash(x)=28056342) +4864 train 7.085080 (lr=1.7500e-04) (hash(x)=21885801) +4865 train 7.211456 (lr=1.7500e-04) (hash(x)=25659043) +4866 train 7.244844 (lr=1.7500e-04) (hash(x)=23852824) +4867 train 7.065683 (lr=1.7500e-04) (hash(x)=23965470) +4868 train 7.073429 (lr=1.7500e-04) (hash(x)=25035012) +4869 train 7.239137 (lr=1.7500e-04) (hash(x)=26639165) +4870 train 7.254572 (lr=1.7500e-04) (hash(x)=29205362) +4871 train 7.094254 (lr=1.7500e-04) (hash(x)=25900866) +4872 train 7.139383 (lr=1.7500e-04) (hash(x)=25636242) +4873 train 7.193941 (lr=1.7500e-04) (hash(x)=25430698) +4874 train 7.215253 (lr=1.7500e-04) (hash(x)=27629981) +4875 train 7.203180 (lr=1.7500e-04) (hash(x)=27682625) +4876 train 7.420448 (lr=1.7500e-04) (hash(x)=27549409) +4877 train 7.210515 (lr=1.7500e-04) (hash(x)=24661627) +4878 train 7.303226 (lr=1.7500e-04) (hash(x)=25196542) +4879 train 7.196482 (lr=1.7500e-04) (hash(x)=24549177) +4880 train 7.205328 (lr=1.7500e-04) (hash(x)=23740600) +4881 train 7.074552 (lr=1.7500e-04) (hash(x)=21460850) +4882 train 7.334857 (lr=1.7500e-04) (hash(x)=27101400) +4883 train 7.270821 (lr=1.7500e-04) (hash(x)=24193076) +4884 train 7.225105 (lr=1.7500e-04) (hash(x)=24582947) +4885 train 7.124245 (lr=1.7500e-04) (hash(x)=25133839) +4886 train 7.154036 (lr=1.7500e-04) (hash(x)=24759454) +4887 train 7.227252 (lr=1.7500e-04) (hash(x)=28239583) +4888 train 7.482163 (lr=1.7500e-04) (hash(x)=29594489) +4889 train 7.201865 (lr=1.7500e-04) (hash(x)=23833431) +4890 train 7.147241 (lr=1.7500e-04) (hash(x)=23139411) +4891 train 7.105855 (lr=1.7500e-04) (hash(x)=20885864) +4892 train 7.426122 (lr=1.7500e-04) (hash(x)=26217418) +4893 train 7.234013 (lr=1.7500e-04) (hash(x)=27321870) +4894 train 6.827816 (lr=1.7500e-04) (hash(x)=19912955) +4895 train 7.115895 (lr=1.7500e-04) (hash(x)=23223554) +4896 train 7.259323 (lr=1.7500e-04) (hash(x)=25667219) +4897 train 7.405801 (lr=1.7500e-04) (hash(x)=28007972) +4898 train 7.248372 (lr=1.7500e-04) (hash(x)=27748764) +4899 train 7.212235 (lr=1.7500e-04) (hash(x)=27425770) +4900 val loss 7.1179 +4900 val perplexity 1233.8635 +4900 train 7.311634 (lr=1.7500e-04) (hash(x)=28394020) +4901 train 7.139014 (lr=1.7500e-04) (hash(x)=24080235) +4902 train 7.039947 (lr=1.7500e-04) (hash(x)=23309527) +4903 train 7.025633 (lr=1.7500e-04) (hash(x)=24793480) +4904 train 7.217383 (lr=1.7500e-04) (hash(x)=25344456) +4905 train 7.156232 (lr=1.7500e-04) (hash(x)=24590670) +4906 train 7.138844 (lr=1.7500e-04) (hash(x)=26937171) +4907 train 7.233974 (lr=1.7500e-04) (hash(x)=26949097) +4908 train 7.025562 (lr=1.7500e-04) (hash(x)=22443915) +4909 train 7.116531 (lr=1.7500e-04) (hash(x)=23814995) +4910 train 7.039785 (lr=1.7500e-04) (hash(x)=26135871) +4911 train 6.947887 (lr=1.7500e-04) (hash(x)=25415570) +4912 train 7.218560 (lr=1.7500e-04) (hash(x)=26756326) +4913 train 7.089059 (lr=1.7500e-04) (hash(x)=22920200) +4914 train 7.139076 (lr=1.7500e-04) (hash(x)=26710977) +4915 train 7.067691 (lr=1.7500e-04) (hash(x)=24985634) +4916 train 7.155666 (lr=1.7500e-04) (hash(x)=26004335) +4917 train 7.123193 (lr=1.7500e-04) (hash(x)=25637457) +4918 train 7.302676 (lr=1.7500e-04) (hash(x)=26645180) +4919 train 7.172897 (lr=1.7500e-04) (hash(x)=24425760) +4920 train 7.420859 (lr=1.7500e-04) (hash(x)=28223544) +4921 train 7.091159 (lr=1.7500e-04) (hash(x)=25538618) +4922 train 7.406465 (lr=1.7500e-04) (hash(x)=26984784) +4923 train 7.395226 (lr=1.7500e-04) (hash(x)=29154578) +4924 train 7.086778 (lr=1.7500e-04) (hash(x)=25308123) +4925 train 7.430738 (lr=1.7500e-04) (hash(x)=27939259) +4926 train 7.079712 (lr=1.7500e-04) (hash(x)=21984545) +4927 train 7.060478 (lr=1.7500e-04) (hash(x)=23707134) +4928 train 7.062232 (lr=1.7500e-04) (hash(x)=27201034) +4929 train 7.531955 (lr=1.7500e-04) (hash(x)=31623877) +4930 train 7.063188 (lr=1.7500e-04) (hash(x)=22162782) +4931 train 6.970249 (lr=1.7500e-04) (hash(x)=20049335) +4932 train 6.969725 (lr=1.7500e-04) (hash(x)=25594665) +4933 train 7.066391 (lr=1.7500e-04) (hash(x)=25265312) +4934 train 7.170586 (lr=1.7500e-04) (hash(x)=27094896) +4935 train 7.433255 (lr=1.7500e-04) (hash(x)=28321697) +4936 train 7.056630 (lr=1.7500e-04) (hash(x)=25006013) +4937 train 7.274494 (lr=1.7500e-04) (hash(x)=24596431) +4938 train 7.292089 (lr=1.7500e-04) (hash(x)=25150510) +4939 train 6.829391 (lr=1.7500e-04) (hash(x)=21497535) +4940 train 7.084627 (lr=1.7500e-04) (hash(x)=25094669) +4941 train 6.943765 (lr=1.7500e-04) (hash(x)=24024557) +4942 train 7.210903 (lr=1.7500e-04) (hash(x)=24370776) +4943 train 7.103590 (lr=1.7500e-04) (hash(x)=23434031) +4944 train 7.072823 (lr=1.7500e-04) (hash(x)=24383517) +4945 train 7.103000 (lr=1.7500e-04) (hash(x)=25858759) +4946 train 6.666864 (lr=1.7500e-04) (hash(x)=20409561) +4947 train 7.372066 (lr=1.7500e-04) (hash(x)=27469117) +4948 train 6.943026 (lr=1.7500e-04) (hash(x)=22086623) +4949 train 7.192235 (lr=1.7500e-04) (hash(x)=25759281) +4950 val loss 7.0794 +4950 val perplexity 1187.2815 +4950 train 7.124424 (lr=1.7500e-04) (hash(x)=27130117) +4951 train 7.017721 (lr=1.7500e-04) (hash(x)=27003481) +4952 train 7.296585 (lr=1.7500e-04) (hash(x)=26725937) +4953 train 7.039019 (lr=1.7500e-04) (hash(x)=22691119) +4954 train 7.047006 (lr=1.7500e-04) (hash(x)=17272898) +4955 train 6.873363 (lr=1.7500e-04) (hash(x)=17850370) +4956 train 6.839621 (lr=1.7500e-04) (hash(x)=18729639) +4957 train 7.121887 (lr=1.7500e-04) (hash(x)=25327160) +4958 train 7.308771 (lr=1.7500e-04) (hash(x)=28709044) +4959 train 6.895305 (lr=1.7500e-04) (hash(x)=22236893) +4960 train 6.833978 (lr=1.7500e-04) (hash(x)=21729251) +4961 train 6.947246 (lr=1.7500e-04) (hash(x)=23852346) +4962 train 7.170206 (lr=1.7500e-04) (hash(x)=23974368) +4963 train 7.095707 (lr=1.7500e-04) (hash(x)=25764691) +4964 train 7.424085 (lr=1.7500e-04) (hash(x)=28341865) +4965 train 7.005746 (lr=1.7500e-04) (hash(x)=23856238) +4966 train 7.201768 (lr=1.7500e-04) (hash(x)=24568904) +4967 train 7.109036 (lr=1.7500e-04) (hash(x)=26857458) +4968 train 6.932083 (lr=1.7500e-04) (hash(x)=20507972) +4969 train 7.159412 (lr=1.7500e-04) (hash(x)=23139455) +4970 train 7.007271 (lr=1.7500e-04) (hash(x)=24853703) +4971 train 7.069008 (lr=1.7500e-04) (hash(x)=25654849) +4972 train 6.885987 (lr=1.7500e-04) (hash(x)=22963710) +4973 train 7.226810 (lr=1.7500e-04) (hash(x)=25652110) +4974 train 7.155472 (lr=1.7500e-04) (hash(x)=24085957) +4975 train 7.415194 (lr=1.7500e-04) (hash(x)=26413122) +4976 train 7.539549 (lr=1.7500e-04) (hash(x)=26989387) +4977 train 7.152802 (lr=1.7500e-04) (hash(x)=22784033) +4978 train 7.514581 (lr=1.7500e-04) (hash(x)=26694945) +4979 train 7.420862 (lr=1.7500e-04) (hash(x)=24507726) +4980 train 7.489508 (lr=1.7500e-04) (hash(x)=26490335) +4981 train 7.377614 (lr=1.7500e-04) (hash(x)=25624751) +4982 train 7.397446 (lr=1.7500e-04) (hash(x)=27846204) +4983 train 7.334591 (lr=1.7500e-04) (hash(x)=27696537) +4984 train 7.199464 (lr=1.7500e-04) (hash(x)=28915842) +4985 train 7.281933 (lr=1.7500e-04) (hash(x)=28274576) +4986 train 7.357091 (lr=1.7500e-04) (hash(x)=28923892) +4987 train 6.911487 (lr=1.7500e-04) (hash(x)=21602520) +4988 train 6.877708 (lr=1.7500e-04) (hash(x)=21061011) +4989 train 7.341011 (lr=1.7500e-04) (hash(x)=28060542) +4990 train 7.193832 (lr=1.7500e-04) (hash(x)=24838134) +4991 train 7.110864 (lr=1.7500e-04) (hash(x)=21950234) +4992 train 7.337322 (lr=1.7500e-04) (hash(x)=27192740) +4993 train 7.352830 (lr=1.7500e-04) (hash(x)=26770105) +4994 train 6.999849 (lr=1.7500e-04) (hash(x)=23721261) +4995 train 7.066547 (lr=1.7500e-04) (hash(x)=26064895) +4996 train 7.258615 (lr=1.7500e-04) (hash(x)=25651075) +4997 train 7.090702 (lr=1.7500e-04) (hash(x)=25029447) +4998 train 7.223561 (lr=1.7500e-04) (hash(x)=26088225) +4999 val loss 7.1196 +4999 val perplexity 1235.9321 +4999 train 7.133684 (lr=1.7500e-04) (hash(x)=24051952) diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/model_02500.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/model_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..3af41f6be0097a3a0e70da99af78a9a82e2eadc5 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/model_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de1983f1201d9aa186ad723d92da6a7336f765079f74583f4dcff1d40324e65b +size 38587970 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/model_04999.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/model_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..8f719356e7f6ca5db663daf7b33adf8f7db81a50 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/model_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b48de39c7e8bb2fd0bebcbeed03e8e6974840f14757db32fd3c3a1f8ecf9f447 +size 38587970 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/optimizer_02500.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/optimizer_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..66188c3d29d74ddca36f8d7f33ee6d8acc82a480 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/optimizer_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71355b5051258c219cf395d4d7e9a949c14855fdb11cc9e863541579ae73e194 +size 70895430 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/optimizer_04999.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/optimizer_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..12361a76eb36d6feae5a25a4efebc63879d3ab98 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps200_seed1338/optimizer_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c05db57db306f9a14a2a18bf33052841f57dd9015caf253f80e7fbd46172c3a +size 70895430