diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/args.json b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/args.json new file mode 100644 index 0000000000000000000000000000000000000000..f3a4fc2fd1e20ea5604bf66219a6fc5f54f66c00 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/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_lrtrue_attention_kindselective_warmup_steps200_seed1339", "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": 1339, "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": true, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "n_embd": 128} \ No newline at end of file diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/dataloader_02500.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/dataloader_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bc253f8fc6225637fb651d7b45bcde02b1c9ff0 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/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_lrtrue_attention_kindselective_warmup_steps200_seed1339/dataloader_04999.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/dataloader_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..0618c479f1dc6588bdd52311cf3417cbd843ddd9 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/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_lrtrue_attention_kindselective_warmup_steps200_seed1339/log2.txt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/log2.txt new file mode 100644 index 0000000000000000000000000000000000000000..e9cdf88296a0f47b89e7e47296626af7496ab701 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/log2.txt @@ -0,0 +1,5203 @@ +max_steps: 5000 +0 val loss 11.7530 +0 val perplexity 127132.9688 +0 train 11.730812 (lr=8.7500e-07) (hash(x)=22886834) +1 train 11.759470 (lr=1.7500e-06) (hash(x)=26375038) +2 train 11.693309 (lr=2.6250e-06) (hash(x)=30598777) +3 train 11.787172 (lr=3.5000e-06) (hash(x)=27234506) +4 train 11.723483 (lr=4.3750e-06) (hash(x)=27767880) +5 train 11.744965 (lr=5.2500e-06) (hash(x)=23702020) +6 train 11.754716 (lr=6.1250e-06) (hash(x)=31986844) +7 train 11.716941 (lr=7.0000e-06) (hash(x)=20782690) +8 train 11.670815 (lr=7.8750e-06) (hash(x)=25201599) +9 train 11.668332 (lr=8.7500e-06) (hash(x)=23094976) +10 train 11.614085 (lr=9.6250e-06) (hash(x)=23841096) +11 train 11.680341 (lr=1.0500e-05) (hash(x)=26532095) +12 train 11.619052 (lr=1.1375e-05) (hash(x)=24432298) +13 train 11.609424 (lr=1.2250e-05) (hash(x)=27151649) +14 train 11.626945 (lr=1.3125e-05) (hash(x)=24596846) +15 train 11.527896 (lr=1.4000e-05) (hash(x)=23890908) +16 train 11.468596 (lr=1.4875e-05) (hash(x)=28913955) +17 train 11.429064 (lr=1.5750e-05) (hash(x)=25588236) +18 train 11.488775 (lr=1.6625e-05) (hash(x)=23770034) +19 train 11.396967 (lr=1.7500e-05) (hash(x)=24011372) +20 train 11.357566 (lr=1.8375e-05) (hash(x)=25441898) +21 train 11.408478 (lr=1.9250e-05) (hash(x)=28375581) +22 train 11.334025 (lr=2.0125e-05) (hash(x)=24046679) +23 train 11.267311 (lr=2.1000e-05) (hash(x)=24611628) +24 train 11.305053 (lr=2.1875e-05) (hash(x)=26169030) +25 train 11.276972 (lr=2.2750e-05) (hash(x)=30298407) +26 train 11.146445 (lr=2.3625e-05) (hash(x)=23711112) +27 train 11.118884 (lr=2.4500e-05) (hash(x)=19245352) +28 train 11.050555 (lr=2.5375e-05) (hash(x)=21529136) +29 train 11.162499 (lr=2.6250e-05) (hash(x)=28936608) +30 train 10.945408 (lr=2.7125e-05) (hash(x)=24339013) +31 train 10.763518 (lr=2.8000e-05) (hash(x)=25767553) +32 train 10.926085 (lr=2.8875e-05) (hash(x)=26439905) +33 train 10.979007 (lr=2.9750e-05) (hash(x)=31093473) +34 train 10.759116 (lr=3.0625e-05) (hash(x)=25450374) +35 train 10.694034 (lr=3.1500e-05) (hash(x)=24809873) +36 train 10.800422 (lr=3.2375e-05) (hash(x)=23253252) +37 train 10.803256 (lr=3.3250e-05) (hash(x)=27852919) +38 train 10.637046 (lr=3.4125e-05) (hash(x)=23327497) +39 train 10.638191 (lr=3.5000e-05) (hash(x)=22512166) +40 train 10.687598 (lr=3.5875e-05) (hash(x)=22859419) +41 train 10.612622 (lr=3.6750e-05) (hash(x)=27620338) +42 train 10.623292 (lr=3.7625e-05) (hash(x)=26397837) +43 train 10.624137 (lr=3.8500e-05) (hash(x)=28092148) +44 train 10.525693 (lr=3.9375e-05) (hash(x)=24662703) +45 train 10.478626 (lr=4.0250e-05) (hash(x)=27938767) +46 train 10.708242 (lr=4.1125e-05) (hash(x)=26037988) +47 train 10.394559 (lr=4.2000e-05) (hash(x)=24732833) +48 train 10.431396 (lr=4.2875e-05) (hash(x)=25259526) +49 train 10.525191 (lr=4.3750e-05) (hash(x)=23200230) +50 val loss 10.4520 +50 val perplexity 34612.4648 +50 train 10.479012 (lr=4.4625e-05) (hash(x)=26721357) +51 train 10.399666 (lr=4.5500e-05) (hash(x)=22694718) +52 train 10.397156 (lr=4.6375e-05) (hash(x)=28066766) +53 train 10.411891 (lr=4.7250e-05) (hash(x)=23125151) +54 train 10.302362 (lr=4.8125e-05) (hash(x)=27193725) +55 train 10.234860 (lr=4.9000e-05) (hash(x)=25129410) +56 train 10.348287 (lr=4.9875e-05) (hash(x)=24263988) +57 train 10.268717 (lr=5.0750e-05) (hash(x)=23059154) +58 train 10.330061 (lr=5.1625e-05) (hash(x)=26063864) +59 train 10.531883 (lr=5.2500e-05) (hash(x)=27858570) +60 train 10.347128 (lr=5.3375e-05) (hash(x)=23874620) +61 train 10.334792 (lr=5.4250e-05) (hash(x)=22402617) +62 train 10.258943 (lr=5.5125e-05) (hash(x)=23600822) +63 train 10.053988 (lr=5.6000e-05) (hash(x)=26582391) +64 train 10.117406 (lr=5.6875e-05) (hash(x)=23225283) +65 train 10.291306 (lr=5.7750e-05) (hash(x)=26075451) +66 train 10.244453 (lr=5.8625e-05) (hash(x)=24723419) +67 train 10.186983 (lr=5.9500e-05) (hash(x)=27279806) +68 train 10.022784 (lr=6.0375e-05) (hash(x)=25870391) +69 train 10.162241 (lr=6.1250e-05) (hash(x)=26188136) +70 train 10.144981 (lr=6.2125e-05) (hash(x)=30373443) +71 train 10.164195 (lr=6.3000e-05) (hash(x)=26472336) +72 train 10.043058 (lr=6.3875e-05) (hash(x)=26651572) +73 train 10.006866 (lr=6.4750e-05) (hash(x)=26376212) +74 train 10.079041 (lr=6.5625e-05) (hash(x)=26733350) +75 train 10.182488 (lr=6.6500e-05) (hash(x)=28301589) +76 train 10.057920 (lr=6.7375e-05) (hash(x)=27599559) +77 train 9.906568 (lr=6.8250e-05) (hash(x)=28035221) +78 train 9.959722 (lr=6.9125e-05) (hash(x)=25016783) +79 train 10.000649 (lr=7.0000e-05) (hash(x)=27654289) +80 train 10.032297 (lr=7.0875e-05) (hash(x)=24597558) +81 train 9.864293 (lr=7.1750e-05) (hash(x)=21560904) +82 train 9.787959 (lr=7.2625e-05) (hash(x)=21983837) +83 train 9.793429 (lr=7.3500e-05) (hash(x)=24995715) +84 train 9.869608 (lr=7.4375e-05) (hash(x)=29876413) +85 train 9.752993 (lr=7.5250e-05) (hash(x)=23792508) +86 train 9.735362 (lr=7.6125e-05) (hash(x)=25509120) +87 train 9.879323 (lr=7.7000e-05) (hash(x)=26559876) +88 train 9.749039 (lr=7.7875e-05) (hash(x)=23569647) +89 train 9.800189 (lr=7.8750e-05) (hash(x)=25758852) +90 train 9.535380 (lr=7.9625e-05) (hash(x)=25706298) +91 train 9.674080 (lr=8.0500e-05) (hash(x)=28364895) +92 train 9.627631 (lr=8.1375e-05) (hash(x)=25304663) +93 train 9.594040 (lr=8.2250e-05) (hash(x)=25269299) +94 train 9.787549 (lr=8.3125e-05) (hash(x)=25870566) +95 train 9.464651 (lr=8.4000e-05) (hash(x)=21770329) +96 train 9.799693 (lr=8.4875e-05) (hash(x)=27595900) +97 train 9.695180 (lr=8.5750e-05) (hash(x)=24785397) +98 train 9.438231 (lr=8.6625e-05) (hash(x)=21521480) +99 train 9.482986 (lr=8.7500e-05) (hash(x)=24628606) +100 val loss 9.4789 +100 val perplexity 13081.2754 +100 train 9.479960 (lr=8.8375e-05) (hash(x)=24670150) +101 train 9.516492 (lr=8.9250e-05) (hash(x)=23181910) +102 train 9.343198 (lr=9.0125e-05) (hash(x)=22714991) +103 train 9.449821 (lr=9.1000e-05) (hash(x)=22723459) +104 train 9.395133 (lr=9.1875e-05) (hash(x)=21524316) +105 train 9.392113 (lr=9.2750e-05) (hash(x)=25506632) +106 train 9.126719 (lr=9.3625e-05) (hash(x)=21675672) +107 train 9.154851 (lr=9.4500e-05) (hash(x)=22897919) +108 train 9.211727 (lr=9.5375e-05) (hash(x)=23321631) +109 train 9.180004 (lr=9.6250e-05) (hash(x)=26546719) +110 train 9.923734 (lr=9.7125e-05) (hash(x)=31962348) +111 train 9.219866 (lr=9.8000e-05) (hash(x)=30338342) +112 train 9.150298 (lr=9.8875e-05) (hash(x)=23724471) +113 train 9.147410 (lr=9.9750e-05) (hash(x)=29175888) +114 train 9.299620 (lr=1.0062e-04) (hash(x)=23256716) +115 train 9.168288 (lr=1.0150e-04) (hash(x)=27063280) +116 train 9.074880 (lr=1.0237e-04) (hash(x)=31057659) +117 train 9.340952 (lr=1.0325e-04) (hash(x)=32915097) +118 train 9.145021 (lr=1.0412e-04) (hash(x)=28842717) +119 train 8.939392 (lr=1.0500e-04) (hash(x)=25678059) +120 train 8.860003 (lr=1.0587e-04) (hash(x)=21593510) +121 train 8.711105 (lr=1.0675e-04) (hash(x)=20083773) +122 train 8.898929 (lr=1.0763e-04) (hash(x)=23002820) +123 train 8.758704 (lr=1.0850e-04) (hash(x)=21853028) +124 train 8.743982 (lr=1.0938e-04) (hash(x)=26985625) +125 train 8.636209 (lr=1.1025e-04) (hash(x)=21808483) +126 train 8.879956 (lr=1.1113e-04) (hash(x)=28873251) +127 train 8.762500 (lr=1.1200e-04) (hash(x)=26109335) +128 train 8.817856 (lr=1.1288e-04) (hash(x)=26334674) +129 train 8.755130 (lr=1.1375e-04) (hash(x)=24916754) +130 train 8.622989 (lr=1.1463e-04) (hash(x)=25449624) +131 train 8.673822 (lr=1.1550e-04) (hash(x)=25334848) +132 train 8.884071 (lr=1.1638e-04) (hash(x)=27484863) +133 train 8.402654 (lr=1.1725e-04) (hash(x)=24917705) +134 train 8.357076 (lr=1.1813e-04) (hash(x)=25143449) +135 train 8.398391 (lr=1.1900e-04) (hash(x)=25044885) +136 train 8.521456 (lr=1.1988e-04) (hash(x)=27821028) +137 train 8.549762 (lr=1.2075e-04) (hash(x)=28747022) +138 train 8.511079 (lr=1.2162e-04) (hash(x)=27182888) +139 train 8.253173 (lr=1.2250e-04) (hash(x)=23678349) +140 train 8.449857 (lr=1.2338e-04) (hash(x)=23593235) +141 train 8.627876 (lr=1.2425e-04) (hash(x)=28529813) +142 train 8.867019 (lr=1.2512e-04) (hash(x)=32074661) +143 train 8.428566 (lr=1.2600e-04) (hash(x)=28870690) +144 train 8.404750 (lr=1.2688e-04) (hash(x)=27307705) +145 train 8.342928 (lr=1.2775e-04) (hash(x)=25044834) +146 train 8.366438 (lr=1.2862e-04) (hash(x)=23712023) +147 train 8.712773 (lr=1.2950e-04) (hash(x)=32982615) +148 train 8.477399 (lr=1.3038e-04) (hash(x)=30113660) +149 train 8.085590 (lr=1.3125e-04) (hash(x)=20970960) +150 val loss 8.2244 +150 val perplexity 3730.8093 +150 train 8.215907 (lr=1.3212e-04) (hash(x)=23132684) +151 train 9.744678 (lr=1.3300e-04) (hash(x)=35279941) +152 train 8.970472 (lr=1.3387e-04) (hash(x)=31227444) +153 train 8.098083 (lr=1.3475e-04) (hash(x)=25529472) +154 train 8.209166 (lr=1.3563e-04) (hash(x)=24350409) +155 train 8.516598 (lr=1.3650e-04) (hash(x)=26400041) +156 train 8.180534 (lr=1.3737e-04) (hash(x)=25262621) +157 train 8.211688 (lr=1.3825e-04) (hash(x)=24656138) +158 train 8.377997 (lr=1.3913e-04) (hash(x)=26803414) +159 train 8.284930 (lr=1.4000e-04) (hash(x)=25015923) +160 train 8.047754 (lr=1.4087e-04) (hash(x)=23581172) +161 train 8.108478 (lr=1.4175e-04) (hash(x)=22924885) +162 train 8.064867 (lr=1.4262e-04) (hash(x)=23414296) +163 train 8.245097 (lr=1.4350e-04) (hash(x)=24853586) +164 train 8.317470 (lr=1.4437e-04) (hash(x)=25000130) +165 train 8.149384 (lr=1.4525e-04) (hash(x)=27004780) +166 train 8.125768 (lr=1.4612e-04) (hash(x)=26148573) +167 train 8.091803 (lr=1.4700e-04) (hash(x)=26740855) +168 train 7.732948 (lr=1.4788e-04) (hash(x)=20965419) +169 train 7.989873 (lr=1.4875e-04) (hash(x)=23950114) +170 train 7.908041 (lr=1.4962e-04) (hash(x)=24951982) +171 train 8.052742 (lr=1.5050e-04) (hash(x)=24584116) +172 train 7.997196 (lr=1.5138e-04) (hash(x)=24378759) +173 train 7.943819 (lr=1.5225e-04) (hash(x)=25718516) +174 train 8.098075 (lr=1.5312e-04) (hash(x)=28424396) +175 train 7.910573 (lr=1.5400e-04) (hash(x)=22262151) +176 train 8.137301 (lr=1.5488e-04) (hash(x)=26438412) +177 train 7.917113 (lr=1.5575e-04) (hash(x)=23025303) +178 train 7.884224 (lr=1.5662e-04) (hash(x)=24190770) +179 train 8.024399 (lr=1.5750e-04) (hash(x)=26627860) +180 train 7.870535 (lr=1.5838e-04) (hash(x)=23663439) +181 train 7.733528 (lr=1.5925e-04) (hash(x)=23700532) +182 train 7.775962 (lr=1.6013e-04) (hash(x)=23075676) +183 train 7.970390 (lr=1.6100e-04) (hash(x)=26621834) +184 train 8.032954 (lr=1.6188e-04) (hash(x)=29426269) +185 train 7.727972 (lr=1.6275e-04) (hash(x)=21821465) +186 train 7.926451 (lr=1.6363e-04) (hash(x)=26506130) +187 train 8.211446 (lr=1.6450e-04) (hash(x)=26930630) +188 train 7.780361 (lr=1.6537e-04) (hash(x)=22993793) +189 train 7.666597 (lr=1.6625e-04) (hash(x)=19557946) +190 train 7.935960 (lr=1.6712e-04) (hash(x)=23572891) +191 train 7.730696 (lr=1.6800e-04) (hash(x)=23234741) +192 train 7.845107 (lr=1.6887e-04) (hash(x)=25547951) +193 train 7.825871 (lr=1.6975e-04) (hash(x)=26713563) +194 train 7.893678 (lr=1.7062e-04) (hash(x)=25913622) +195 train 8.130229 (lr=1.7150e-04) (hash(x)=28102443) +196 train 7.818027 (lr=1.7238e-04) (hash(x)=23093351) +197 train 8.560493 (lr=1.7325e-04) (hash(x)=31689122) +198 train 8.398519 (lr=1.7412e-04) (hash(x)=32252517) +199 train 7.954915 (lr=1.7500e-04) (hash(x)=25470563) +200 val loss 7.8716 +200 val perplexity 2621.6736 +200 train 7.972818 (lr=1.7500e-04) (hash(x)=25597614) +201 train 8.013376 (lr=1.7500e-04) (hash(x)=23757479) +202 train 7.818653 (lr=1.7500e-04) (hash(x)=25140048) +203 train 8.024234 (lr=1.7500e-04) (hash(x)=28282861) +204 train 7.770902 (lr=1.7500e-04) (hash(x)=24754885) +205 train 8.012224 (lr=1.7500e-04) (hash(x)=26731964) +206 train 8.090381 (lr=1.7500e-04) (hash(x)=26660561) +207 train 7.682066 (lr=1.7500e-04) (hash(x)=21799102) +208 train 7.900830 (lr=1.7500e-04) (hash(x)=27025986) +209 train 7.730614 (lr=1.7500e-04) (hash(x)=24672077) +210 train 7.824468 (lr=1.7500e-04) (hash(x)=25322984) +211 train 7.658618 (lr=1.7500e-04) (hash(x)=23471769) +212 train 7.485881 (lr=1.7500e-04) (hash(x)=20766491) +213 train 7.978682 (lr=1.7500e-04) (hash(x)=24058931) +214 train 7.714808 (lr=1.7500e-04) (hash(x)=23872843) +215 train 7.745014 (lr=1.7500e-04) (hash(x)=23275479) +216 train 7.858354 (lr=1.7500e-04) (hash(x)=24914695) +217 train 7.722388 (lr=1.7500e-04) (hash(x)=24364396) +218 train 8.000091 (lr=1.7499e-04) (hash(x)=27986474) +219 train 7.890882 (lr=1.7499e-04) (hash(x)=24473581) +220 train 7.809412 (lr=1.7499e-04) (hash(x)=22974689) +221 train 8.528712 (lr=1.7499e-04) (hash(x)=23774644) +222 train 8.417528 (lr=1.7499e-04) (hash(x)=23245327) +223 train 7.649223 (lr=1.7499e-04) (hash(x)=22091862) +224 train 7.731952 (lr=1.7499e-04) (hash(x)=24362839) +225 train 7.866788 (lr=1.7499e-04) (hash(x)=25482303) +226 train 7.941012 (lr=1.7499e-04) (hash(x)=24911853) +227 train 7.899178 (lr=1.7499e-04) (hash(x)=26018202) +228 train 7.750541 (lr=1.7499e-04) (hash(x)=26124495) +229 train 7.790443 (lr=1.7499e-04) (hash(x)=24560096) +230 train 7.819832 (lr=1.7498e-04) (hash(x)=24695331) +231 train 7.532829 (lr=1.7498e-04) (hash(x)=17430373) +232 train 7.597174 (lr=1.7498e-04) (hash(x)=21813345) +233 train 7.246312 (lr=1.7498e-04) (hash(x)=20098681) +234 train 7.580985 (lr=1.7498e-04) (hash(x)=25095928) +235 train 7.684284 (lr=1.7498e-04) (hash(x)=24078083) +236 train 7.684877 (lr=1.7498e-04) (hash(x)=22901505) +237 train 7.909898 (lr=1.7498e-04) (hash(x)=26595592) +238 train 7.801847 (lr=1.7498e-04) (hash(x)=27663196) +239 train 7.579709 (lr=1.7497e-04) (hash(x)=22954861) +240 train 8.076896 (lr=1.7497e-04) (hash(x)=30159234) +241 train 7.977512 (lr=1.7497e-04) (hash(x)=29294271) +242 train 7.880979 (lr=1.7497e-04) (hash(x)=23728322) +243 train 7.945957 (lr=1.7497e-04) (hash(x)=28695016) +244 train 8.076485 (lr=1.7497e-04) (hash(x)=26702728) +245 train 7.875632 (lr=1.7497e-04) (hash(x)=27100115) +246 train 7.798872 (lr=1.7496e-04) (hash(x)=25082752) +247 train 8.122559 (lr=1.7496e-04) (hash(x)=26671799) +248 train 7.821764 (lr=1.7496e-04) (hash(x)=23718946) +249 train 8.076799 (lr=1.7496e-04) (hash(x)=28137394) +250 val loss 7.8235 +250 val perplexity 2498.6167 +250 train 8.072446 (lr=1.7496e-04) (hash(x)=23893495) +251 train 7.872586 (lr=1.7496e-04) (hash(x)=23166092) +252 train 7.820510 (lr=1.7495e-04) (hash(x)=25907665) +253 train 7.810581 (lr=1.7495e-04) (hash(x)=25885986) +254 train 7.862418 (lr=1.7495e-04) (hash(x)=25262712) +255 train 7.814108 (lr=1.7495e-04) (hash(x)=26924723) +256 train 8.019591 (lr=1.7495e-04) (hash(x)=28744736) +257 train 7.754393 (lr=1.7495e-04) (hash(x)=26140590) +258 train 7.944272 (lr=1.7494e-04) (hash(x)=25780449) +259 train 7.759838 (lr=1.7494e-04) (hash(x)=25138659) +260 train 8.072536 (lr=1.7494e-04) (hash(x)=27244046) +261 train 7.920161 (lr=1.7494e-04) (hash(x)=27224685) +262 train 8.182660 (lr=1.7494e-04) (hash(x)=28274477) +263 train 7.714522 (lr=1.7493e-04) (hash(x)=23557495) +264 train 7.814266 (lr=1.7493e-04) (hash(x)=24680596) +265 train 7.832933 (lr=1.7493e-04) (hash(x)=23928957) +266 train 7.747910 (lr=1.7493e-04) (hash(x)=23761390) +267 train 7.686502 (lr=1.7492e-04) (hash(x)=25288123) +268 train 7.986868 (lr=1.7492e-04) (hash(x)=28705502) +269 train 7.584558 (lr=1.7492e-04) (hash(x)=23246294) +270 train 7.676309 (lr=1.7492e-04) (hash(x)=28639079) +271 train 7.605594 (lr=1.7491e-04) (hash(x)=27804380) +272 train 7.773768 (lr=1.7491e-04) (hash(x)=24172235) +273 train 7.816329 (lr=1.7491e-04) (hash(x)=23089140) +274 train 8.056314 (lr=1.7491e-04) (hash(x)=27163701) +275 train 8.142756 (lr=1.7491e-04) (hash(x)=26993263) +276 train 7.872862 (lr=1.7490e-04) (hash(x)=28224233) +277 train 8.137013 (lr=1.7490e-04) (hash(x)=27397203) +278 train 8.043307 (lr=1.7490e-04) (hash(x)=27923882) +279 train 7.872258 (lr=1.7489e-04) (hash(x)=26654908) +280 train 7.814822 (lr=1.7489e-04) (hash(x)=24213147) +281 train 7.553932 (lr=1.7489e-04) (hash(x)=21965022) +282 train 7.734128 (lr=1.7489e-04) (hash(x)=25465685) +283 train 7.938356 (lr=1.7488e-04) (hash(x)=27347722) +284 train 7.934387 (lr=1.7488e-04) (hash(x)=26732050) +285 train 8.090283 (lr=1.7488e-04) (hash(x)=28314127) +286 train 7.640742 (lr=1.7488e-04) (hash(x)=21471186) +287 train 7.621701 (lr=1.7487e-04) (hash(x)=23627518) +288 train 7.568725 (lr=1.7487e-04) (hash(x)=20870353) +289 train 7.706493 (lr=1.7487e-04) (hash(x)=25024764) +290 train 7.500989 (lr=1.7486e-04) (hash(x)=20683822) +291 train 7.782640 (lr=1.7486e-04) (hash(x)=21768671) +292 train 7.814355 (lr=1.7486e-04) (hash(x)=25557309) +293 train 7.976698 (lr=1.7485e-04) (hash(x)=25076667) +294 train 7.623000 (lr=1.7485e-04) (hash(x)=23765822) +295 train 7.597791 (lr=1.7485e-04) (hash(x)=21889990) +296 train 7.842546 (lr=1.7484e-04) (hash(x)=26339893) +297 train 7.604930 (lr=1.7484e-04) (hash(x)=20932794) +298 train 7.700426 (lr=1.7484e-04) (hash(x)=21750070) +299 train 7.839921 (lr=1.7483e-04) (hash(x)=23665838) +300 val loss 7.7540 +300 val perplexity 2330.7644 +300 train 8.615311 (lr=1.7483e-04) (hash(x)=32888061) +301 train 8.372769 (lr=1.7483e-04) (hash(x)=30223582) +302 train 8.057961 (lr=1.7482e-04) (hash(x)=26908418) +303 train 7.386359 (lr=1.7482e-04) (hash(x)=22528001) +304 train 7.955968 (lr=1.7482e-04) (hash(x)=27452187) +305 train 7.777036 (lr=1.7481e-04) (hash(x)=25181641) +306 train 7.878448 (lr=1.7481e-04) (hash(x)=25546593) +307 train 7.887053 (lr=1.7481e-04) (hash(x)=22487328) +308 train 8.015404 (lr=1.7480e-04) (hash(x)=27804274) +309 train 8.055972 (lr=1.7480e-04) (hash(x)=26544630) +310 train 8.179609 (lr=1.7480e-04) (hash(x)=27738934) +311 train 7.985363 (lr=1.7479e-04) (hash(x)=29248942) +312 train 7.710568 (lr=1.7479e-04) (hash(x)=25103452) +313 train 7.921133 (lr=1.7478e-04) (hash(x)=25052066) +314 train 7.750198 (lr=1.7478e-04) (hash(x)=24481302) +315 train 7.711704 (lr=1.7478e-04) (hash(x)=23543273) +316 train 7.711774 (lr=1.7477e-04) (hash(x)=25608244) +317 train 7.879584 (lr=1.7477e-04) (hash(x)=27451288) +318 train 7.569566 (lr=1.7477e-04) (hash(x)=22806491) +319 train 7.770554 (lr=1.7476e-04) (hash(x)=25533417) +320 train 7.772245 (lr=1.7476e-04) (hash(x)=24557997) +321 train 7.846378 (lr=1.7475e-04) (hash(x)=24432899) +322 train 8.058401 (lr=1.7475e-04) (hash(x)=27583287) +323 train 7.950891 (lr=1.7474e-04) (hash(x)=25552036) +324 train 7.701803 (lr=1.7474e-04) (hash(x)=24201868) +325 train 8.020961 (lr=1.7474e-04) (hash(x)=28149782) +326 train 7.804487 (lr=1.7473e-04) (hash(x)=25529698) +327 train 7.449324 (lr=1.7473e-04) (hash(x)=20612533) +328 train 7.474945 (lr=1.7472e-04) (hash(x)=20699000) +329 train 7.409338 (lr=1.7472e-04) (hash(x)=19774173) +330 train 7.432703 (lr=1.7472e-04) (hash(x)=21681646) +331 train 7.307397 (lr=1.7471e-04) (hash(x)=20216795) +332 train 8.081515 (lr=1.7471e-04) (hash(x)=27697998) +333 train 7.828749 (lr=1.7470e-04) (hash(x)=25896435) +334 train 7.689296 (lr=1.7470e-04) (hash(x)=21585310) +335 train 7.754688 (lr=1.7469e-04) (hash(x)=24677740) +336 train 7.523381 (lr=1.7469e-04) (hash(x)=22027900) +337 train 7.602470 (lr=1.7468e-04) (hash(x)=21835643) +338 train 7.490216 (lr=1.7468e-04) (hash(x)=20558462) +339 train 7.384494 (lr=1.7467e-04) (hash(x)=16722715) +340 train 7.568264 (lr=1.7467e-04) (hash(x)=20972655) +341 train 8.039072 (lr=1.7466e-04) (hash(x)=26303975) +342 train 7.792998 (lr=1.7466e-04) (hash(x)=22938170) +343 train 7.856098 (lr=1.7466e-04) (hash(x)=25347203) +344 train 7.787610 (lr=1.7465e-04) (hash(x)=27398686) +345 train 7.762537 (lr=1.7465e-04) (hash(x)=25973417) +346 train 7.765556 (lr=1.7464e-04) (hash(x)=26918389) +347 train 7.700412 (lr=1.7464e-04) (hash(x)=24272489) +348 train 7.784546 (lr=1.7463e-04) (hash(x)=25593714) +349 train 7.860828 (lr=1.7463e-04) (hash(x)=29260846) +350 val loss 7.7404 +350 val perplexity 2299.4783 +350 train 7.930069 (lr=1.7462e-04) (hash(x)=27951602) +351 train 8.037191 (lr=1.7462e-04) (hash(x)=28922363) +352 train 7.901097 (lr=1.7461e-04) (hash(x)=27210734) +353 train 7.937207 (lr=1.7461e-04) (hash(x)=26322572) +354 train 7.792641 (lr=1.7460e-04) (hash(x)=27084665) +355 train 7.665458 (lr=1.7460e-04) (hash(x)=25510798) +356 train 7.833991 (lr=1.7459e-04) (hash(x)=24970921) +357 train 7.856867 (lr=1.7458e-04) (hash(x)=24138948) +358 train 7.754318 (lr=1.7458e-04) (hash(x)=24790211) +359 train 7.779957 (lr=1.7457e-04) (hash(x)=25631397) +360 train 7.648029 (lr=1.7457e-04) (hash(x)=23226625) +361 train 7.711850 (lr=1.7456e-04) (hash(x)=24001903) +362 train 7.673266 (lr=1.7456e-04) (hash(x)=24587948) +363 train 7.418134 (lr=1.7455e-04) (hash(x)=21333676) +364 train 7.294660 (lr=1.7455e-04) (hash(x)=23673779) +365 train 8.744910 (lr=1.7454e-04) (hash(x)=30770484) +366 train 7.860017 (lr=1.7454e-04) (hash(x)=26564899) +367 train 7.845342 (lr=1.7453e-04) (hash(x)=26237983) +368 train 7.519323 (lr=1.7452e-04) (hash(x)=23764356) +369 train 7.931804 (lr=1.7452e-04) (hash(x)=26205744) +370 train 7.506726 (lr=1.7451e-04) (hash(x)=19208770) +371 train 7.781342 (lr=1.7451e-04) (hash(x)=25976502) +372 train 7.641385 (lr=1.7450e-04) (hash(x)=23983933) +373 train 7.631490 (lr=1.7450e-04) (hash(x)=24080636) +374 train 7.759300 (lr=1.7449e-04) (hash(x)=24404047) +375 train 7.669866 (lr=1.7448e-04) (hash(x)=24742645) +376 train 7.733222 (lr=1.7448e-04) (hash(x)=24159600) +377 train 7.998694 (lr=1.7447e-04) (hash(x)=28677257) +378 train 7.689475 (lr=1.7447e-04) (hash(x)=25604111) +379 train 7.706505 (lr=1.7446e-04) (hash(x)=27086333) +380 train 7.578667 (lr=1.7445e-04) (hash(x)=25188207) +381 train 7.850991 (lr=1.7445e-04) (hash(x)=27855233) +382 train 7.452619 (lr=1.7444e-04) (hash(x)=19470039) +383 train 7.740345 (lr=1.7444e-04) (hash(x)=26157660) +384 train 7.621964 (lr=1.7443e-04) (hash(x)=25291570) +385 train 7.596429 (lr=1.7442e-04) (hash(x)=25046062) +386 train 7.956384 (lr=1.7442e-04) (hash(x)=27020337) +387 train 7.575864 (lr=1.7441e-04) (hash(x)=23616370) +388 train 7.257782 (lr=1.7440e-04) (hash(x)=19113218) +389 train 7.589835 (lr=1.7440e-04) (hash(x)=24302232) +390 train 7.626503 (lr=1.7439e-04) (hash(x)=22188949) +391 train 7.412755 (lr=1.7439e-04) (hash(x)=22582169) +392 train 7.634757 (lr=1.7438e-04) (hash(x)=24700570) +393 train 7.514993 (lr=1.7437e-04) (hash(x)=22773833) +394 train 7.365992 (lr=1.7437e-04) (hash(x)=21875928) +395 train 7.710503 (lr=1.7436e-04) (hash(x)=26233189) +396 train 7.555509 (lr=1.7435e-04) (hash(x)=24321467) +397 train 7.809241 (lr=1.7435e-04) (hash(x)=26431507) +398 train 7.895669 (lr=1.7434e-04) (hash(x)=28690877) +399 train 7.849988 (lr=1.7433e-04) (hash(x)=26431960) +400 val loss 7.6827 +400 val perplexity 2170.3938 +400 train 7.606523 (lr=1.7433e-04) (hash(x)=24580300) +401 train 7.614560 (lr=1.7432e-04) (hash(x)=25112360) +402 train 7.774988 (lr=1.7431e-04) (hash(x)=27597243) +403 train 8.247518 (lr=1.7431e-04) (hash(x)=30707498) +404 train 7.911833 (lr=1.7430e-04) (hash(x)=28485465) +405 train 7.488530 (lr=1.7429e-04) (hash(x)=22586447) +406 train 7.631022 (lr=1.7429e-04) (hash(x)=23175270) +407 train 7.714269 (lr=1.7428e-04) (hash(x)=25716176) +408 train 7.836156 (lr=1.7427e-04) (hash(x)=26861373) +409 train 7.933876 (lr=1.7426e-04) (hash(x)=25118971) +410 train 7.380278 (lr=1.7426e-04) (hash(x)=19829066) +411 train 7.608719 (lr=1.7425e-04) (hash(x)=26256420) +412 train 7.862065 (lr=1.7424e-04) (hash(x)=27796153) +413 train 7.619585 (lr=1.7424e-04) (hash(x)=22633318) +414 train 7.636585 (lr=1.7423e-04) (hash(x)=22589383) +415 train 8.038772 (lr=1.7422e-04) (hash(x)=28019788) +416 train 7.964368 (lr=1.7421e-04) (hash(x)=28970440) +417 train 7.641969 (lr=1.7421e-04) (hash(x)=27396089) +418 train 7.623160 (lr=1.7420e-04) (hash(x)=21183513) +419 train 7.641370 (lr=1.7419e-04) (hash(x)=23510110) +420 train 7.866565 (lr=1.7419e-04) (hash(x)=28833467) +421 train 7.739654 (lr=1.7418e-04) (hash(x)=23646926) +422 train 7.699613 (lr=1.7417e-04) (hash(x)=24697272) +423 train 7.460079 (lr=1.7416e-04) (hash(x)=20382963) +424 train 7.468967 (lr=1.7416e-04) (hash(x)=23467595) +425 train 7.628604 (lr=1.7415e-04) (hash(x)=24304768) +426 train 7.558877 (lr=1.7414e-04) (hash(x)=21392328) +427 train 7.589240 (lr=1.7413e-04) (hash(x)=25339466) +428 train 7.554646 (lr=1.7412e-04) (hash(x)=22092542) +429 train 7.641617 (lr=1.7412e-04) (hash(x)=22088696) +430 train 7.517190 (lr=1.7411e-04) (hash(x)=22184471) +431 train 7.646923 (lr=1.7410e-04) (hash(x)=24489647) +432 train 7.697415 (lr=1.7409e-04) (hash(x)=26794132) +433 train 7.449661 (lr=1.7409e-04) (hash(x)=22940357) +434 train 7.596870 (lr=1.7408e-04) (hash(x)=23719522) +435 train 7.554264 (lr=1.7407e-04) (hash(x)=22927699) +436 train 7.715514 (lr=1.7406e-04) (hash(x)=26068576) +437 train 7.810506 (lr=1.7405e-04) (hash(x)=27631132) +438 train 7.683877 (lr=1.7405e-04) (hash(x)=26739991) +439 train 7.764221 (lr=1.7404e-04) (hash(x)=25128502) +440 train 7.799438 (lr=1.7403e-04) (hash(x)=25657260) +441 train 7.536346 (lr=1.7402e-04) (hash(x)=23576982) +442 train 7.817509 (lr=1.7401e-04) (hash(x)=27117886) +443 train 7.816141 (lr=1.7401e-04) (hash(x)=25808969) +444 train 7.742898 (lr=1.7400e-04) (hash(x)=24738238) +445 train 7.742898 (lr=1.7399e-04) (hash(x)=23429962) +446 train 7.862072 (lr=1.7398e-04) (hash(x)=25075165) +447 train 7.714202 (lr=1.7397e-04) (hash(x)=25231390) +448 train 7.485040 (lr=1.7396e-04) (hash(x)=22055054) +449 train 7.660170 (lr=1.7396e-04) (hash(x)=25395441) +450 val loss 7.6751 +450 val perplexity 2153.9873 +450 train 7.751298 (lr=1.7395e-04) (hash(x)=25863209) +451 train 7.401909 (lr=1.7394e-04) (hash(x)=21154388) +452 train 7.405069 (lr=1.7393e-04) (hash(x)=21600876) +453 train 7.509288 (lr=1.7392e-04) (hash(x)=24278611) +454 train 7.348924 (lr=1.7391e-04) (hash(x)=23221720) +455 train 7.625268 (lr=1.7391e-04) (hash(x)=22708977) +456 train 8.234636 (lr=1.7390e-04) (hash(x)=23637758) +457 train 7.958269 (lr=1.7389e-04) (hash(x)=28228490) +458 train 7.981285 (lr=1.7388e-04) (hash(x)=28638071) +459 train 7.759894 (lr=1.7387e-04) (hash(x)=27258353) +460 train 7.796529 (lr=1.7386e-04) (hash(x)=26604728) +461 train 7.652893 (lr=1.7385e-04) (hash(x)=23252199) +462 train 7.727846 (lr=1.7385e-04) (hash(x)=26441427) +463 train 7.454460 (lr=1.7384e-04) (hash(x)=24364920) +464 train 7.657610 (lr=1.7383e-04) (hash(x)=25623792) +465 train 7.517468 (lr=1.7382e-04) (hash(x)=23283905) +466 train 7.998416 (lr=1.7381e-04) (hash(x)=26025267) +467 train 7.710394 (lr=1.7380e-04) (hash(x)=27243972) +468 train 8.082953 (lr=1.7379e-04) (hash(x)=30449945) +469 train 7.826736 (lr=1.7378e-04) (hash(x)=28113043) +470 train 7.665568 (lr=1.7377e-04) (hash(x)=25182521) +471 train 7.705608 (lr=1.7376e-04) (hash(x)=24932925) +472 train 7.491448 (lr=1.7376e-04) (hash(x)=20353098) +473 train 7.238029 (lr=1.7375e-04) (hash(x)=19001259) +474 train 7.925653 (lr=1.7374e-04) (hash(x)=27585685) +475 train 7.590480 (lr=1.7373e-04) (hash(x)=26371091) +476 train 7.478018 (lr=1.7372e-04) (hash(x)=24891798) +477 train 7.514482 (lr=1.7371e-04) (hash(x)=24258817) +478 train 7.595482 (lr=1.7370e-04) (hash(x)=24330263) +479 train 7.655056 (lr=1.7369e-04) (hash(x)=26913684) +480 train 7.687671 (lr=1.7368e-04) (hash(x)=26338455) +481 train 8.005083 (lr=1.7367e-04) (hash(x)=27753043) +482 train 7.695072 (lr=1.7366e-04) (hash(x)=26123289) +483 train 7.775134 (lr=1.7365e-04) (hash(x)=29239611) +484 train 7.666428 (lr=1.7364e-04) (hash(x)=26553003) +485 train 7.681695 (lr=1.7363e-04) (hash(x)=22984557) +486 train 7.210671 (lr=1.7362e-04) (hash(x)=16947491) +487 train 7.187346 (lr=1.7361e-04) (hash(x)=18017792) +488 train 7.366931 (lr=1.7361e-04) (hash(x)=19918608) +489 train 7.872978 (lr=1.7360e-04) (hash(x)=23374526) +490 train 7.736130 (lr=1.7359e-04) (hash(x)=25009505) +491 train 7.669062 (lr=1.7358e-04) (hash(x)=27574089) +492 train 7.815389 (lr=1.7357e-04) (hash(x)=24122664) +493 train 7.644863 (lr=1.7356e-04) (hash(x)=26154906) +494 train 7.642568 (lr=1.7355e-04) (hash(x)=25192767) +495 train 7.782142 (lr=1.7354e-04) (hash(x)=28613882) +496 train 7.621475 (lr=1.7353e-04) (hash(x)=23547219) +497 train 7.672811 (lr=1.7352e-04) (hash(x)=25272182) +498 train 7.498312 (lr=1.7351e-04) (hash(x)=24992761) +499 train 7.773884 (lr=1.7350e-04) (hash(x)=26981914) +500 val loss 7.6292 +500 val perplexity 2057.5054 +500 train 7.590665 (lr=1.7349e-04) (hash(x)=22051933) +501 train 7.743190 (lr=1.7348e-04) (hash(x)=24232348) +502 train 7.706734 (lr=1.7347e-04) (hash(x)=23158331) +503 train 7.532314 (lr=1.7346e-04) (hash(x)=22652243) +504 train 7.559126 (lr=1.7345e-04) (hash(x)=23805602) +505 train 7.873782 (lr=1.7344e-04) (hash(x)=25411991) +506 train 7.029175 (lr=1.7343e-04) (hash(x)=18827215) +507 train 6.761673 (lr=1.7342e-04) (hash(x)=15446025) +508 train 7.217239 (lr=1.7341e-04) (hash(x)=20516263) +509 train 7.734291 (lr=1.7340e-04) (hash(x)=27846176) +510 train 7.468335 (lr=1.7338e-04) (hash(x)=23342449) +511 train 7.711679 (lr=1.7337e-04) (hash(x)=27194521) +512 train 7.513147 (lr=1.7336e-04) (hash(x)=23008284) +513 train 8.023833 (lr=1.7335e-04) (hash(x)=29430001) +514 train 7.306133 (lr=1.7334e-04) (hash(x)=22579319) +515 train 7.336780 (lr=1.7333e-04) (hash(x)=25264518) +516 train 7.698594 (lr=1.7332e-04) (hash(x)=25359075) +517 train 7.675915 (lr=1.7331e-04) (hash(x)=25568956) +518 train 7.965427 (lr=1.7330e-04) (hash(x)=32004108) +519 train 7.585410 (lr=1.7329e-04) (hash(x)=24936836) +520 train 7.742934 (lr=1.7328e-04) (hash(x)=27263338) +521 train 7.782831 (lr=1.7327e-04) (hash(x)=27452099) +522 train 7.687560 (lr=1.7326e-04) (hash(x)=25965406) +523 train 7.861892 (lr=1.7325e-04) (hash(x)=28197282) +524 train 7.599555 (lr=1.7324e-04) (hash(x)=22466209) +525 train 7.637883 (lr=1.7323e-04) (hash(x)=22931889) +526 train 7.762926 (lr=1.7321e-04) (hash(x)=26903920) +527 train 7.605119 (lr=1.7320e-04) (hash(x)=24765578) +528 train 7.749185 (lr=1.7319e-04) (hash(x)=27811359) +529 train 7.500327 (lr=1.7318e-04) (hash(x)=25078649) +530 train 7.653389 (lr=1.7317e-04) (hash(x)=25572416) +531 train 7.844255 (lr=1.7316e-04) (hash(x)=27448185) +532 train 7.911660 (lr=1.7315e-04) (hash(x)=25923719) +533 train 7.653197 (lr=1.7314e-04) (hash(x)=24804856) +534 train 7.726358 (lr=1.7313e-04) (hash(x)=23207829) +535 train 7.604220 (lr=1.7311e-04) (hash(x)=23107416) +536 train 7.492002 (lr=1.7310e-04) (hash(x)=26739531) +537 train 7.527800 (lr=1.7309e-04) (hash(x)=24960796) +538 train 7.643587 (lr=1.7308e-04) (hash(x)=24667802) +539 train 7.775574 (lr=1.7307e-04) (hash(x)=26755138) +540 train 7.656999 (lr=1.7306e-04) (hash(x)=25537132) +541 train 7.555719 (lr=1.7305e-04) (hash(x)=24542526) +542 train 7.337930 (lr=1.7304e-04) (hash(x)=21296355) +543 train 7.910770 (lr=1.7302e-04) (hash(x)=29314255) +544 train 7.652048 (lr=1.7301e-04) (hash(x)=26001799) +545 train 7.688942 (lr=1.7300e-04) (hash(x)=27347755) +546 train 7.678664 (lr=1.7299e-04) (hash(x)=25107798) +547 train 7.420536 (lr=1.7298e-04) (hash(x)=22112669) +548 train 7.461105 (lr=1.7297e-04) (hash(x)=21897967) +549 train 7.590547 (lr=1.7295e-04) (hash(x)=25161929) +550 val loss 7.6045 +550 val perplexity 2007.1292 +550 train 7.552210 (lr=1.7294e-04) (hash(x)=27465106) +551 train 7.603122 (lr=1.7293e-04) (hash(x)=24013079) +552 train 7.476396 (lr=1.7292e-04) (hash(x)=23142015) +553 train 7.619457 (lr=1.7291e-04) (hash(x)=26768629) +554 train 7.626319 (lr=1.7290e-04) (hash(x)=26393383) +555 train 7.501526 (lr=1.7288e-04) (hash(x)=22537194) +556 train 7.756095 (lr=1.7287e-04) (hash(x)=24046036) +557 train 7.715929 (lr=1.7286e-04) (hash(x)=24974360) +558 train 7.946237 (lr=1.7285e-04) (hash(x)=28379928) +559 train 7.630135 (lr=1.7284e-04) (hash(x)=25322001) +560 train 7.748892 (lr=1.7282e-04) (hash(x)=26622031) +561 train 7.385933 (lr=1.7281e-04) (hash(x)=20562247) +562 train 7.754488 (lr=1.7280e-04) (hash(x)=27381885) +563 train 7.915915 (lr=1.7279e-04) (hash(x)=27028126) +564 train 7.721741 (lr=1.7278e-04) (hash(x)=28882928) +565 train 7.591710 (lr=1.7276e-04) (hash(x)=25666355) +566 train 7.750383 (lr=1.7275e-04) (hash(x)=24330810) +567 train 7.667186 (lr=1.7274e-04) (hash(x)=26690440) +568 train 7.539073 (lr=1.7273e-04) (hash(x)=22923592) +569 train 7.673538 (lr=1.7271e-04) (hash(x)=27348418) +570 train 7.726388 (lr=1.7270e-04) (hash(x)=28849848) +571 train 7.766823 (lr=1.7269e-04) (hash(x)=26967331) +572 train 7.540265 (lr=1.7268e-04) (hash(x)=22831467) +573 train 7.635026 (lr=1.7266e-04) (hash(x)=24765121) +574 train 7.613614 (lr=1.7265e-04) (hash(x)=24331857) +575 train 7.422508 (lr=1.7264e-04) (hash(x)=22598512) +576 train 7.541670 (lr=1.7263e-04) (hash(x)=25149353) +577 train 7.471202 (lr=1.7261e-04) (hash(x)=23725598) +578 train 7.716736 (lr=1.7260e-04) (hash(x)=26449557) +579 train 7.753842 (lr=1.7259e-04) (hash(x)=24697985) +580 train 7.711708 (lr=1.7258e-04) (hash(x)=26923059) +581 train 7.525840 (lr=1.7256e-04) (hash(x)=25201962) +582 train 7.121490 (lr=1.7255e-04) (hash(x)=20931520) +583 train 7.264955 (lr=1.7254e-04) (hash(x)=18473911) +584 train 7.421797 (lr=1.7253e-04) (hash(x)=21306267) +585 train 7.626076 (lr=1.7251e-04) (hash(x)=25982840) +586 train 7.542549 (lr=1.7250e-04) (hash(x)=25364874) +587 train 7.435397 (lr=1.7249e-04) (hash(x)=23172124) +588 train 7.774071 (lr=1.7247e-04) (hash(x)=27876897) +589 train 8.391635 (lr=1.7246e-04) (hash(x)=34646114) +590 train 8.694720 (lr=1.7245e-04) (hash(x)=35153576) +591 train 7.647054 (lr=1.7244e-04) (hash(x)=22322442) +592 train 7.869254 (lr=1.7242e-04) (hash(x)=27907331) +593 train 7.687452 (lr=1.7241e-04) (hash(x)=26211794) +594 train 7.857393 (lr=1.7240e-04) (hash(x)=29291512) +595 train 8.120015 (lr=1.7238e-04) (hash(x)=29659121) +596 train 7.967923 (lr=1.7237e-04) (hash(x)=29674399) +597 train 7.565293 (lr=1.7236e-04) (hash(x)=23538306) +598 train 7.715385 (lr=1.7234e-04) (hash(x)=21991524) +599 train 7.646545 (lr=1.7233e-04) (hash(x)=26324153) +600 val loss 7.5855 +600 val perplexity 1969.4673 +600 train 7.570690 (lr=1.7232e-04) (hash(x)=23712082) +601 train 7.665134 (lr=1.7230e-04) (hash(x)=24910403) +602 train 7.607604 (lr=1.7229e-04) (hash(x)=26737205) +603 train 7.724202 (lr=1.7228e-04) (hash(x)=26939970) +604 train 7.616143 (lr=1.7226e-04) (hash(x)=27651943) +605 train 7.911752 (lr=1.7225e-04) (hash(x)=27515446) +606 train 7.808201 (lr=1.7224e-04) (hash(x)=26753129) +607 train 7.478519 (lr=1.7222e-04) (hash(x)=23446058) +608 train 7.694103 (lr=1.7221e-04) (hash(x)=27587849) +609 train 7.654418 (lr=1.7220e-04) (hash(x)=25308253) +610 train 7.697901 (lr=1.7218e-04) (hash(x)=26615098) +611 train 7.751485 (lr=1.7217e-04) (hash(x)=29981801) +612 train 7.801786 (lr=1.7215e-04) (hash(x)=29592345) +613 train 7.837966 (lr=1.7214e-04) (hash(x)=23470413) +614 train 7.686771 (lr=1.7213e-04) (hash(x)=24742370) +615 train 7.629974 (lr=1.7211e-04) (hash(x)=24843741) +616 train 7.616684 (lr=1.7210e-04) (hash(x)=25192548) +617 train 7.665692 (lr=1.7209e-04) (hash(x)=27176996) +618 train 7.447793 (lr=1.7207e-04) (hash(x)=23964552) +619 train 7.471257 (lr=1.7206e-04) (hash(x)=22855363) +620 train 7.471652 (lr=1.7204e-04) (hash(x)=26332996) +621 train 7.308353 (lr=1.7203e-04) (hash(x)=22960957) +622 train 7.659335 (lr=1.7202e-04) (hash(x)=22752597) +623 train 7.546922 (lr=1.7200e-04) (hash(x)=23197102) +624 train 8.083297 (lr=1.7199e-04) (hash(x)=27383319) +625 train 7.611967 (lr=1.7197e-04) (hash(x)=26132276) +626 train 7.515472 (lr=1.7196e-04) (hash(x)=19810497) +627 train 7.586175 (lr=1.7194e-04) (hash(x)=25704919) +628 train 7.770135 (lr=1.7193e-04) (hash(x)=27174264) +629 train 7.857109 (lr=1.7192e-04) (hash(x)=22280814) +630 train 8.581650 (lr=1.7190e-04) (hash(x)=24279448) +631 train 8.012835 (lr=1.7189e-04) (hash(x)=23054940) +632 train 8.131896 (lr=1.7187e-04) (hash(x)=23942400) +633 train 8.328246 (lr=1.7186e-04) (hash(x)=24712416) +634 train 7.957413 (lr=1.7184e-04) (hash(x)=24564658) +635 train 7.749388 (lr=1.7183e-04) (hash(x)=24909904) +636 train 7.757536 (lr=1.7182e-04) (hash(x)=23049534) +637 train 7.811825 (lr=1.7180e-04) (hash(x)=24321591) +638 train 7.593428 (lr=1.7179e-04) (hash(x)=26153298) +639 train 7.634542 (lr=1.7177e-04) (hash(x)=27140757) +640 train 7.382504 (lr=1.7176e-04) (hash(x)=25115907) +641 train 7.454508 (lr=1.7174e-04) (hash(x)=26563770) +642 train 7.642798 (lr=1.7173e-04) (hash(x)=28089252) +643 train 7.576675 (lr=1.7171e-04) (hash(x)=25993110) +644 train 7.514632 (lr=1.7170e-04) (hash(x)=25150008) +645 train 7.757527 (lr=1.7168e-04) (hash(x)=28520222) +646 train 7.385512 (lr=1.7167e-04) (hash(x)=21349943) +647 train 7.481320 (lr=1.7165e-04) (hash(x)=25149419) +648 train 7.701583 (lr=1.7164e-04) (hash(x)=25730641) +649 train 7.845759 (lr=1.7162e-04) (hash(x)=26112813) +650 val loss 7.5835 +650 val perplexity 1965.5831 +650 train 7.616491 (lr=1.7161e-04) (hash(x)=25907805) +651 train 7.677904 (lr=1.7159e-04) (hash(x)=27623643) +652 train 7.617195 (lr=1.7158e-04) (hash(x)=26484959) +653 train 7.678992 (lr=1.7156e-04) (hash(x)=29199854) +654 train 7.644851 (lr=1.7155e-04) (hash(x)=28369628) +655 train 7.468862 (lr=1.7153e-04) (hash(x)=24727764) +656 train 7.246382 (lr=1.7152e-04) (hash(x)=22610673) +657 train 7.152176 (lr=1.7150e-04) (hash(x)=22667179) +658 train 6.926712 (lr=1.7149e-04) (hash(x)=18477300) +659 train 7.396597 (lr=1.7147e-04) (hash(x)=23155773) +660 train 7.181561 (lr=1.7146e-04) (hash(x)=19461032) +661 train 7.480533 (lr=1.7144e-04) (hash(x)=23453788) +662 train 7.596875 (lr=1.7143e-04) (hash(x)=24543466) +663 train 7.390470 (lr=1.7141e-04) (hash(x)=21935931) +664 train 7.230340 (lr=1.7140e-04) (hash(x)=19910292) +665 train 7.529412 (lr=1.7138e-04) (hash(x)=24481079) +666 train 7.179627 (lr=1.7137e-04) (hash(x)=18922411) +667 train 7.207328 (lr=1.7135e-04) (hash(x)=20054917) +668 train 7.457289 (lr=1.7133e-04) (hash(x)=24850470) +669 train 7.477885 (lr=1.7132e-04) (hash(x)=25907741) +670 train 7.645493 (lr=1.7130e-04) (hash(x)=26873522) +671 train 7.709450 (lr=1.7129e-04) (hash(x)=27606073) +672 train 7.780024 (lr=1.7127e-04) (hash(x)=26209645) +673 train 7.576046 (lr=1.7126e-04) (hash(x)=25202001) +674 train 7.638560 (lr=1.7124e-04) (hash(x)=25569462) +675 train 7.620046 (lr=1.7122e-04) (hash(x)=26534487) +676 train 7.560248 (lr=1.7121e-04) (hash(x)=26455057) +677 train 7.479454 (lr=1.7119e-04) (hash(x)=24095850) +678 train 7.701039 (lr=1.7118e-04) (hash(x)=25287752) +679 train 7.209142 (lr=1.7116e-04) (hash(x)=22450341) +680 train 7.948421 (lr=1.7115e-04) (hash(x)=29004853) +681 train 7.613501 (lr=1.7113e-04) (hash(x)=27993763) +682 train 7.440854 (lr=1.7111e-04) (hash(x)=26382658) +683 train 7.605091 (lr=1.7110e-04) (hash(x)=25013073) +684 train 7.634939 (lr=1.7108e-04) (hash(x)=30595809) +685 train 7.706549 (lr=1.7107e-04) (hash(x)=30934371) +686 train 8.291282 (lr=1.7105e-04) (hash(x)=33060834) +687 train 7.609924 (lr=1.7103e-04) (hash(x)=25945859) +688 train 7.459781 (lr=1.7102e-04) (hash(x)=23375678) +689 train 7.484091 (lr=1.7100e-04) (hash(x)=25218689) +690 train 7.640195 (lr=1.7098e-04) (hash(x)=28127397) +691 train 7.510850 (lr=1.7097e-04) (hash(x)=24418091) +692 train 7.472142 (lr=1.7095e-04) (hash(x)=22761099) +693 train 7.449001 (lr=1.7094e-04) (hash(x)=24615466) +694 train 7.573950 (lr=1.7092e-04) (hash(x)=24699240) +695 train 7.465300 (lr=1.7090e-04) (hash(x)=21613707) +696 train 7.565304 (lr=1.7089e-04) (hash(x)=24977554) +697 train 7.449106 (lr=1.7087e-04) (hash(x)=24348175) +698 train 7.634198 (lr=1.7085e-04) (hash(x)=25102767) +699 train 7.604398 (lr=1.7084e-04) (hash(x)=26386157) +700 val loss 7.5028 +700 val perplexity 1813.1138 +700 train 7.504271 (lr=1.7082e-04) (hash(x)=26423460) +701 train 7.486885 (lr=1.7080e-04) (hash(x)=25771047) +702 train 7.553000 (lr=1.7079e-04) (hash(x)=26999875) +703 train 7.455225 (lr=1.7077e-04) (hash(x)=24396519) +704 train 7.470165 (lr=1.7075e-04) (hash(x)=22588122) +705 train 7.809997 (lr=1.7074e-04) (hash(x)=25142399) +706 train 7.480245 (lr=1.7072e-04) (hash(x)=20440214) +707 train 7.345809 (lr=1.7070e-04) (hash(x)=23265507) +708 train 7.448934 (lr=1.7069e-04) (hash(x)=24563470) +709 train 7.344946 (lr=1.7067e-04) (hash(x)=22514858) +710 train 7.691774 (lr=1.7065e-04) (hash(x)=26691212) +711 train 7.782299 (lr=1.7064e-04) (hash(x)=29138828) +712 train 7.749134 (lr=1.7062e-04) (hash(x)=28028528) +713 train 7.604854 (lr=1.7060e-04) (hash(x)=20531210) +714 train 7.468532 (lr=1.7059e-04) (hash(x)=25075352) +715 train 7.548395 (lr=1.7057e-04) (hash(x)=24265353) +716 train 7.637886 (lr=1.7055e-04) (hash(x)=24635726) +717 train 7.470478 (lr=1.7053e-04) (hash(x)=24999726) +718 train 7.670167 (lr=1.7052e-04) (hash(x)=27412910) +719 train 7.454857 (lr=1.7050e-04) (hash(x)=24685515) +720 train 7.524707 (lr=1.7048e-04) (hash(x)=23780329) +721 train 7.317017 (lr=1.7047e-04) (hash(x)=25071701) +722 train 7.430956 (lr=1.7045e-04) (hash(x)=23767130) +723 train 7.405002 (lr=1.7043e-04) (hash(x)=24876269) +724 train 7.569158 (lr=1.7041e-04) (hash(x)=26405773) +725 train 7.991605 (lr=1.7040e-04) (hash(x)=31733180) +726 train 7.149426 (lr=1.7038e-04) (hash(x)=21337509) +727 train 7.266210 (lr=1.7036e-04) (hash(x)=22825749) +728 train 7.675918 (lr=1.7034e-04) (hash(x)=28638695) +729 train 7.520520 (lr=1.7033e-04) (hash(x)=26393943) +730 train 7.690063 (lr=1.7031e-04) (hash(x)=27563583) +731 train 7.157005 (lr=1.7029e-04) (hash(x)=21239652) +732 train 7.256210 (lr=1.7027e-04) (hash(x)=23986428) +733 train 7.295372 (lr=1.7026e-04) (hash(x)=24943881) +734 train 7.901634 (lr=1.7024e-04) (hash(x)=29691448) +735 train 7.789102 (lr=1.7022e-04) (hash(x)=28767869) +736 train 7.460247 (lr=1.7020e-04) (hash(x)=23628188) +737 train 7.722951 (lr=1.7019e-04) (hash(x)=29341482) +738 train 7.608926 (lr=1.7017e-04) (hash(x)=30336570) +739 train 7.587518 (lr=1.7015e-04) (hash(x)=25614301) +740 train 7.399121 (lr=1.7013e-04) (hash(x)=24160500) +741 train 7.649428 (lr=1.7011e-04) (hash(x)=26030058) +742 train 7.990937 (lr=1.7010e-04) (hash(x)=29243936) +743 train 7.255569 (lr=1.7008e-04) (hash(x)=21159060) +744 train 7.370750 (lr=1.7006e-04) (hash(x)=23701853) +745 train 7.574025 (lr=1.7004e-04) (hash(x)=24629937) +746 train 7.488417 (lr=1.7002e-04) (hash(x)=25110108) +747 train 7.550615 (lr=1.7001e-04) (hash(x)=26751788) +748 train 7.605670 (lr=1.6999e-04) (hash(x)=26430427) +749 train 7.459891 (lr=1.6997e-04) (hash(x)=26012353) +750 val loss 7.5062 +750 val perplexity 1819.2443 +750 train 7.618661 (lr=1.6995e-04) (hash(x)=22735910) +751 train 7.406206 (lr=1.6993e-04) (hash(x)=25045397) +752 train 7.126010 (lr=1.6992e-04) (hash(x)=21554427) +753 train 7.235245 (lr=1.6990e-04) (hash(x)=23751143) +754 train 7.966995 (lr=1.6988e-04) (hash(x)=28602273) +755 train 8.059062 (lr=1.6986e-04) (hash(x)=29989709) +756 train 7.392491 (lr=1.6984e-04) (hash(x)=22331648) +757 train 7.843289 (lr=1.6982e-04) (hash(x)=31017246) +758 train 7.782758 (lr=1.6981e-04) (hash(x)=29709045) +759 train 7.826093 (lr=1.6979e-04) (hash(x)=25560928) +760 train 7.481869 (lr=1.6977e-04) (hash(x)=25075464) +761 train 7.567995 (lr=1.6975e-04) (hash(x)=27352253) +762 train 7.767975 (lr=1.6973e-04) (hash(x)=28187891) +763 train 7.629108 (lr=1.6971e-04) (hash(x)=26062687) +764 train 7.636301 (lr=1.6970e-04) (hash(x)=27427811) +765 train 7.703266 (lr=1.6968e-04) (hash(x)=27614522) +766 train 7.454701 (lr=1.6966e-04) (hash(x)=26129544) +767 train 8.053670 (lr=1.6964e-04) (hash(x)=28959222) +768 train 7.595616 (lr=1.6962e-04) (hash(x)=26860067) +769 train 7.364763 (lr=1.6960e-04) (hash(x)=25122598) +770 train 7.446823 (lr=1.6958e-04) (hash(x)=25245030) +771 train 7.442594 (lr=1.6956e-04) (hash(x)=25434884) +772 train 7.458787 (lr=1.6955e-04) (hash(x)=27732790) +773 train 7.550734 (lr=1.6953e-04) (hash(x)=27824438) +774 train 7.611646 (lr=1.6951e-04) (hash(x)=27201953) +775 train 7.366907 (lr=1.6949e-04) (hash(x)=21248405) +776 train 7.146640 (lr=1.6947e-04) (hash(x)=22805934) +777 train 7.503961 (lr=1.6945e-04) (hash(x)=26482588) +778 train 7.556195 (lr=1.6943e-04) (hash(x)=24153691) +779 train 7.674963 (lr=1.6941e-04) (hash(x)=25044192) +780 train 7.600915 (lr=1.6939e-04) (hash(x)=25910078) +781 train 7.589005 (lr=1.6937e-04) (hash(x)=28645524) +782 train 7.377233 (lr=1.6936e-04) (hash(x)=24368498) +783 train 7.476176 (lr=1.6934e-04) (hash(x)=25830182) +784 train 7.602439 (lr=1.6932e-04) (hash(x)=29181807) +785 train 7.534583 (lr=1.6930e-04) (hash(x)=25585137) +786 train 7.422924 (lr=1.6928e-04) (hash(x)=24798246) +787 train 7.548898 (lr=1.6926e-04) (hash(x)=26621419) +788 train 7.089635 (lr=1.6924e-04) (hash(x)=21446891) +789 train 7.044606 (lr=1.6922e-04) (hash(x)=22165286) +790 train 7.284376 (lr=1.6920e-04) (hash(x)=23477219) +791 train 7.585629 (lr=1.6918e-04) (hash(x)=25173113) +792 train 7.436124 (lr=1.6916e-04) (hash(x)=25853788) +793 train 7.564908 (lr=1.6914e-04) (hash(x)=27267091) +794 train 7.370657 (lr=1.6912e-04) (hash(x)=23743694) +795 train 7.351192 (lr=1.6910e-04) (hash(x)=24400133) +796 train 7.492054 (lr=1.6908e-04) (hash(x)=23663639) +797 train 7.390868 (lr=1.6906e-04) (hash(x)=23103223) +798 train 7.858745 (lr=1.6904e-04) (hash(x)=28748411) +799 train 7.047395 (lr=1.6903e-04) (hash(x)=23486277) +800 val loss 7.4402 +800 val perplexity 1703.0085 +800 train 7.456628 (lr=1.6901e-04) (hash(x)=25678518) +801 train 7.394464 (lr=1.6899e-04) (hash(x)=23421286) +802 train 7.523833 (lr=1.6897e-04) (hash(x)=26054104) +803 train 7.537870 (lr=1.6895e-04) (hash(x)=25978130) +804 train 7.547666 (lr=1.6893e-04) (hash(x)=26006525) +805 train 7.528543 (lr=1.6891e-04) (hash(x)=25769432) +806 train 7.333286 (lr=1.6889e-04) (hash(x)=22430795) +807 train 7.672630 (lr=1.6887e-04) (hash(x)=28916006) +808 train 7.474395 (lr=1.6885e-04) (hash(x)=25166800) +809 train 7.591422 (lr=1.6883e-04) (hash(x)=24226056) +810 train 7.429743 (lr=1.6881e-04) (hash(x)=25057934) +811 train 8.285167 (lr=1.6879e-04) (hash(x)=33195100) +812 train 7.598077 (lr=1.6877e-04) (hash(x)=26312888) +813 train 7.807603 (lr=1.6875e-04) (hash(x)=27730410) +814 train 7.675714 (lr=1.6873e-04) (hash(x)=27372474) +815 train 7.467877 (lr=1.6871e-04) (hash(x)=25556929) +816 train 7.593077 (lr=1.6869e-04) (hash(x)=26909985) +817 train 7.408102 (lr=1.6867e-04) (hash(x)=25991247) +818 train 7.553258 (lr=1.6865e-04) (hash(x)=27438141) +819 train 7.692410 (lr=1.6863e-04) (hash(x)=29536986) +820 train 7.448097 (lr=1.6860e-04) (hash(x)=24478391) +821 train 7.427952 (lr=1.6858e-04) (hash(x)=26125216) +822 train 7.481461 (lr=1.6856e-04) (hash(x)=26422130) +823 train 7.756953 (lr=1.6854e-04) (hash(x)=29648798) +824 train 7.341103 (lr=1.6852e-04) (hash(x)=21247770) +825 train 7.472427 (lr=1.6850e-04) (hash(x)=23195388) +826 train 7.420586 (lr=1.6848e-04) (hash(x)=25796725) +827 train 7.471542 (lr=1.6846e-04) (hash(x)=23124767) +828 train 7.481410 (lr=1.6844e-04) (hash(x)=25233464) +829 train 7.474864 (lr=1.6842e-04) (hash(x)=25713275) +830 train 7.445520 (lr=1.6840e-04) (hash(x)=25550167) +831 train 7.327528 (lr=1.6838e-04) (hash(x)=24976217) +832 train 7.652036 (lr=1.6836e-04) (hash(x)=28536827) +833 train 7.537745 (lr=1.6834e-04) (hash(x)=27500801) +834 train 7.360593 (lr=1.6832e-04) (hash(x)=25545765) +835 train 7.372346 (lr=1.6830e-04) (hash(x)=23632825) +836 train 7.389682 (lr=1.6828e-04) (hash(x)=25708009) +837 train 7.465456 (lr=1.6825e-04) (hash(x)=24456276) +838 train 7.637081 (lr=1.6823e-04) (hash(x)=29189855) +839 train 7.838640 (lr=1.6821e-04) (hash(x)=31019606) +840 train 7.732792 (lr=1.6819e-04) (hash(x)=26328013) +841 train 7.629203 (lr=1.6817e-04) (hash(x)=25027904) +842 train 7.398161 (lr=1.6815e-04) (hash(x)=23734189) +843 train 7.632477 (lr=1.6813e-04) (hash(x)=28236580) +844 train 7.438712 (lr=1.6811e-04) (hash(x)=26509780) +845 train 7.533272 (lr=1.6809e-04) (hash(x)=25386473) +846 train 7.445456 (lr=1.6807e-04) (hash(x)=24052671) +847 train 7.661762 (lr=1.6804e-04) (hash(x)=28269421) +848 train 7.094215 (lr=1.6802e-04) (hash(x)=22251724) +849 train 7.295473 (lr=1.6800e-04) (hash(x)=24308447) +850 val loss 7.4337 +850 val perplexity 1691.9995 +850 train 7.276260 (lr=1.6798e-04) (hash(x)=24242830) +851 train 7.504854 (lr=1.6796e-04) (hash(x)=25563279) +852 train 7.508223 (lr=1.6794e-04) (hash(x)=26354481) +853 train 7.685848 (lr=1.6792e-04) (hash(x)=26152637) +854 train 7.694124 (lr=1.6790e-04) (hash(x)=28051025) +855 train 7.538227 (lr=1.6787e-04) (hash(x)=24865358) +856 train 7.437582 (lr=1.6785e-04) (hash(x)=24288911) +857 train 7.306118 (lr=1.6783e-04) (hash(x)=22230964) +858 train 7.225446 (lr=1.6781e-04) (hash(x)=21303832) +859 train 7.329225 (lr=1.6779e-04) (hash(x)=22155546) +860 train 7.422482 (lr=1.6777e-04) (hash(x)=25296428) +861 train 7.622443 (lr=1.6774e-04) (hash(x)=29142319) +862 train 7.399178 (lr=1.6772e-04) (hash(x)=25545430) +863 train 7.238618 (lr=1.6770e-04) (hash(x)=26984272) +864 train 7.455322 (lr=1.6768e-04) (hash(x)=25429005) +865 train 7.468640 (lr=1.6766e-04) (hash(x)=27077032) +866 train 7.512381 (lr=1.6764e-04) (hash(x)=26494424) +867 train 7.495189 (lr=1.6761e-04) (hash(x)=23193673) +868 train 7.515610 (lr=1.6759e-04) (hash(x)=25075134) +869 train 7.544042 (lr=1.6757e-04) (hash(x)=27112558) +870 train 7.690286 (lr=1.6755e-04) (hash(x)=27436608) +871 train 7.444406 (lr=1.6753e-04) (hash(x)=24544116) +872 train 7.788448 (lr=1.6751e-04) (hash(x)=31632686) +873 train 7.487518 (lr=1.6748e-04) (hash(x)=25890184) +874 train 7.606574 (lr=1.6746e-04) (hash(x)=22887555) +875 train 7.360123 (lr=1.6744e-04) (hash(x)=24547533) +876 train 7.535503 (lr=1.6742e-04) (hash(x)=26553496) +877 train 7.637180 (lr=1.6740e-04) (hash(x)=27467688) +878 train 7.406638 (lr=1.6737e-04) (hash(x)=24766934) +879 train 7.264151 (lr=1.6735e-04) (hash(x)=22059850) +880 train 7.694665 (lr=1.6733e-04) (hash(x)=22871702) +881 train 7.491835 (lr=1.6731e-04) (hash(x)=23893130) +882 train 7.553699 (lr=1.6728e-04) (hash(x)=25125691) +883 train 7.463985 (lr=1.6726e-04) (hash(x)=25994573) +884 train 7.497080 (lr=1.6724e-04) (hash(x)=26076345) +885 train 7.421423 (lr=1.6722e-04) (hash(x)=26577783) +886 train 7.590969 (lr=1.6719e-04) (hash(x)=27395225) +887 train 7.412277 (lr=1.6717e-04) (hash(x)=23926632) +888 train 7.262119 (lr=1.6715e-04) (hash(x)=21737239) +889 train 7.523038 (lr=1.6713e-04) (hash(x)=23574207) +890 train 7.254060 (lr=1.6711e-04) (hash(x)=24365231) +891 train 7.417316 (lr=1.6708e-04) (hash(x)=27111369) +892 train 7.669003 (lr=1.6706e-04) (hash(x)=27290015) +893 train 7.434046 (lr=1.6704e-04) (hash(x)=23979820) +894 train 7.511974 (lr=1.6701e-04) (hash(x)=26450121) +895 train 7.418861 (lr=1.6699e-04) (hash(x)=27025333) +896 train 7.428174 (lr=1.6697e-04) (hash(x)=23624605) +897 train 7.198270 (lr=1.6695e-04) (hash(x)=22846386) +898 train 7.324648 (lr=1.6692e-04) (hash(x)=22970561) +899 train 7.153699 (lr=1.6690e-04) (hash(x)=16908068) +900 val loss 7.4104 +900 val perplexity 1653.0936 +900 train 7.391977 (lr=1.6688e-04) (hash(x)=24661446) +901 train 7.526794 (lr=1.6686e-04) (hash(x)=25664727) +902 train 7.457315 (lr=1.6683e-04) (hash(x)=25667011) +903 train 7.528759 (lr=1.6681e-04) (hash(x)=29120407) +904 train 7.591407 (lr=1.6679e-04) (hash(x)=23385735) +905 train 7.648175 (lr=1.6676e-04) (hash(x)=25564213) +906 train 7.705678 (lr=1.6674e-04) (hash(x)=25413898) +907 train 7.654289 (lr=1.6672e-04) (hash(x)=27092710) +908 train 7.458135 (lr=1.6670e-04) (hash(x)=25789923) +909 train 7.547719 (lr=1.6667e-04) (hash(x)=28533197) +910 train 7.347461 (lr=1.6665e-04) (hash(x)=22982996) +911 train 7.450638 (lr=1.6663e-04) (hash(x)=23827393) +912 train 7.068848 (lr=1.6660e-04) (hash(x)=21242640) +913 train 7.444733 (lr=1.6658e-04) (hash(x)=24154233) +914 train 7.460280 (lr=1.6656e-04) (hash(x)=24331967) +915 train 7.724884 (lr=1.6653e-04) (hash(x)=32812727) +916 train 7.353579 (lr=1.6651e-04) (hash(x)=23572994) +917 train 7.394855 (lr=1.6649e-04) (hash(x)=26305435) +918 train 7.465688 (lr=1.6646e-04) (hash(x)=26268355) +919 train 7.702760 (lr=1.6644e-04) (hash(x)=27230027) +920 train 7.421075 (lr=1.6642e-04) (hash(x)=23885377) +921 train 7.385822 (lr=1.6639e-04) (hash(x)=23532437) +922 train 7.441507 (lr=1.6637e-04) (hash(x)=25577034) +923 train 7.584579 (lr=1.6635e-04) (hash(x)=25703381) +924 train 7.578584 (lr=1.6632e-04) (hash(x)=27113866) +925 train 7.410996 (lr=1.6630e-04) (hash(x)=26961429) +926 train 7.228590 (lr=1.6628e-04) (hash(x)=21355372) +927 train 7.328952 (lr=1.6625e-04) (hash(x)=24968260) +928 train 7.307260 (lr=1.6623e-04) (hash(x)=25357517) +929 train 7.442552 (lr=1.6620e-04) (hash(x)=24854265) +930 train 7.251236 (lr=1.6618e-04) (hash(x)=21102770) +931 train 7.490656 (lr=1.6616e-04) (hash(x)=25676468) +932 train 7.317986 (lr=1.6613e-04) (hash(x)=22809869) +933 train 7.401534 (lr=1.6611e-04) (hash(x)=25503865) +934 train 7.313524 (lr=1.6609e-04) (hash(x)=24853995) +935 train 7.580982 (lr=1.6606e-04) (hash(x)=27544803) +936 train 7.571377 (lr=1.6604e-04) (hash(x)=25981933) +937 train 7.321687 (lr=1.6601e-04) (hash(x)=24658683) +938 train 7.488365 (lr=1.6599e-04) (hash(x)=23855201) +939 train 7.378026 (lr=1.6597e-04) (hash(x)=24331407) +940 train 7.614972 (lr=1.6594e-04) (hash(x)=29265551) +941 train 7.311106 (lr=1.6592e-04) (hash(x)=21892556) +942 train 7.381755 (lr=1.6589e-04) (hash(x)=27183405) +943 train 7.340268 (lr=1.6587e-04) (hash(x)=26540663) +944 train 7.321720 (lr=1.6585e-04) (hash(x)=25718393) +945 train 7.533424 (lr=1.6582e-04) (hash(x)=26819462) +946 train 7.488293 (lr=1.6580e-04) (hash(x)=27427540) +947 train 7.465200 (lr=1.6577e-04) (hash(x)=25532657) +948 train 7.745911 (lr=1.6575e-04) (hash(x)=27641372) +949 train 7.367515 (lr=1.6573e-04) (hash(x)=26515570) +950 val loss 7.4297 +950 val perplexity 1685.3331 +950 train 7.635022 (lr=1.6570e-04) (hash(x)=26911957) +951 train 7.786602 (lr=1.6568e-04) (hash(x)=25856625) +952 train 7.301848 (lr=1.6565e-04) (hash(x)=25219129) +953 train 7.222931 (lr=1.6563e-04) (hash(x)=25260471) +954 train 7.670156 (lr=1.6560e-04) (hash(x)=29373370) +955 train 7.135919 (lr=1.6558e-04) (hash(x)=23437426) +956 train 7.543376 (lr=1.6555e-04) (hash(x)=23769521) +957 train 7.587812 (lr=1.6553e-04) (hash(x)=25961833) +958 train 7.224538 (lr=1.6551e-04) (hash(x)=23582666) +959 train 7.353281 (lr=1.6548e-04) (hash(x)=23164356) +960 train 7.317770 (lr=1.6546e-04) (hash(x)=24443114) +961 train 7.378426 (lr=1.6543e-04) (hash(x)=25052665) +962 train 7.514469 (lr=1.6541e-04) (hash(x)=27802272) +963 train 7.329125 (lr=1.6538e-04) (hash(x)=25957896) +964 train 7.416162 (lr=1.6536e-04) (hash(x)=26737251) +965 train 7.571111 (lr=1.6533e-04) (hash(x)=24723263) +966 train 7.490062 (lr=1.6531e-04) (hash(x)=24707011) +967 train 7.477394 (lr=1.6528e-04) (hash(x)=25646282) +968 train 7.485884 (lr=1.6526e-04) (hash(x)=27544665) +969 train 7.396613 (lr=1.6523e-04) (hash(x)=25851993) +970 train 7.722042 (lr=1.6521e-04) (hash(x)=29059700) +971 train 7.390087 (lr=1.6518e-04) (hash(x)=21513584) +972 train 7.089977 (lr=1.6516e-04) (hash(x)=23151267) +973 train 7.425648 (lr=1.6513e-04) (hash(x)=26017176) +974 train 7.480681 (lr=1.6511e-04) (hash(x)=26979518) +975 train 7.466490 (lr=1.6508e-04) (hash(x)=23843233) +976 train 7.659674 (lr=1.6506e-04) (hash(x)=24193010) +977 train 7.359391 (lr=1.6503e-04) (hash(x)=21476847) +978 train 7.221791 (lr=1.6501e-04) (hash(x)=21366504) +979 train 7.233772 (lr=1.6498e-04) (hash(x)=23226697) +980 train 7.021259 (lr=1.6496e-04) (hash(x)=19961773) +981 train 6.903261 (lr=1.6493e-04) (hash(x)=19772969) +982 train 7.263675 (lr=1.6491e-04) (hash(x)=23110142) +983 train 7.522234 (lr=1.6488e-04) (hash(x)=24506028) +984 train 7.560934 (lr=1.6486e-04) (hash(x)=25480731) +985 train 7.418973 (lr=1.6483e-04) (hash(x)=21077417) +986 train 7.347414 (lr=1.6481e-04) (hash(x)=23686713) +987 train 7.360385 (lr=1.6478e-04) (hash(x)=26024321) +988 train 7.464611 (lr=1.6476e-04) (hash(x)=27424109) +989 train 7.663765 (lr=1.6473e-04) (hash(x)=27786174) +990 train 7.389594 (lr=1.6471e-04) (hash(x)=25232502) +991 train 7.385541 (lr=1.6468e-04) (hash(x)=22781277) +992 train 7.472127 (lr=1.6465e-04) (hash(x)=26184527) +993 train 7.457071 (lr=1.6463e-04) (hash(x)=24459895) +994 train 7.406919 (lr=1.6460e-04) (hash(x)=25244624) +995 train 7.533245 (lr=1.6458e-04) (hash(x)=24451843) +996 train 7.532261 (lr=1.6455e-04) (hash(x)=22129897) +997 train 7.299985 (lr=1.6453e-04) (hash(x)=21116390) +998 train 7.139305 (lr=1.6450e-04) (hash(x)=20650070) +999 train 7.495744 (lr=1.6448e-04) (hash(x)=24948650) +1000 val loss 7.3967 +1000 val perplexity 1630.6559 +1000 train 7.387193 (lr=1.6445e-04) (hash(x)=25444553) +1001 train 7.366654 (lr=1.6442e-04) (hash(x)=25617781) +1002 train 7.249788 (lr=1.6440e-04) (hash(x)=23862434) +1003 train 7.312129 (lr=1.6437e-04) (hash(x)=25559534) +1004 train 7.512413 (lr=1.6435e-04) (hash(x)=26577585) +1005 train 7.380191 (lr=1.6432e-04) (hash(x)=25546274) +1006 train 7.447994 (lr=1.6429e-04) (hash(x)=26284202) +1007 train 7.472562 (lr=1.6427e-04) (hash(x)=26373991) +1008 train 7.357683 (lr=1.6424e-04) (hash(x)=24612851) +1009 train 7.439560 (lr=1.6422e-04) (hash(x)=26410662) +1010 train 7.469688 (lr=1.6419e-04) (hash(x)=23824841) +1011 train 7.787605 (lr=1.6416e-04) (hash(x)=27756673) +1012 train 7.522087 (lr=1.6414e-04) (hash(x)=25427447) +1013 train 7.514020 (lr=1.6411e-04) (hash(x)=23661686) +1014 train 7.399841 (lr=1.6409e-04) (hash(x)=25129504) +1015 train 7.355077 (lr=1.6406e-04) (hash(x)=23402396) +1016 train 7.598164 (lr=1.6403e-04) (hash(x)=26145557) +1017 train 7.326299 (lr=1.6401e-04) (hash(x)=26547918) +1018 train 7.457886 (lr=1.6398e-04) (hash(x)=26653070) +1019 train 7.454376 (lr=1.6395e-04) (hash(x)=28250354) +1020 train 7.440431 (lr=1.6393e-04) (hash(x)=25437401) +1021 train 7.510159 (lr=1.6390e-04) (hash(x)=25598861) +1022 train 7.318324 (lr=1.6388e-04) (hash(x)=24572587) +1023 train 7.408633 (lr=1.6385e-04) (hash(x)=21562133) +1024 train 7.805688 (lr=1.6382e-04) (hash(x)=27718876) +1025 train 7.305513 (lr=1.6380e-04) (hash(x)=25312391) +1026 train 7.414910 (lr=1.6377e-04) (hash(x)=26579535) +1027 train 7.659260 (lr=1.6374e-04) (hash(x)=27253861) +1028 train 7.556403 (lr=1.6372e-04) (hash(x)=28451867) +1029 train 7.259529 (lr=1.6369e-04) (hash(x)=26795921) +1030 train 7.417929 (lr=1.6366e-04) (hash(x)=26147208) +1031 train 7.462047 (lr=1.6364e-04) (hash(x)=25009210) +1032 train 7.385971 (lr=1.6361e-04) (hash(x)=25213771) +1033 train 7.288133 (lr=1.6358e-04) (hash(x)=26254538) +1034 train 7.326740 (lr=1.6356e-04) (hash(x)=25565614) +1035 train 7.152480 (lr=1.6353e-04) (hash(x)=23052577) +1036 train 7.961533 (lr=1.6350e-04) (hash(x)=29630613) +1037 train 7.230888 (lr=1.6348e-04) (hash(x)=23667224) +1038 train 7.339546 (lr=1.6345e-04) (hash(x)=25740670) +1039 train 7.445198 (lr=1.6342e-04) (hash(x)=27161811) +1040 train 7.571878 (lr=1.6340e-04) (hash(x)=26385663) +1041 train 7.285797 (lr=1.6337e-04) (hash(x)=26313522) +1042 train 7.407652 (lr=1.6334e-04) (hash(x)=26814686) +1043 train 7.514244 (lr=1.6331e-04) (hash(x)=27302459) +1044 train 7.838606 (lr=1.6329e-04) (hash(x)=26758132) +1045 train 7.430371 (lr=1.6326e-04) (hash(x)=26837963) +1046 train 7.223656 (lr=1.6323e-04) (hash(x)=22089547) +1047 train 7.725934 (lr=1.6321e-04) (hash(x)=29515100) +1048 train 7.425559 (lr=1.6318e-04) (hash(x)=25471442) +1049 train 7.400281 (lr=1.6315e-04) (hash(x)=26674478) +1050 val loss 7.3791 +1050 val perplexity 1602.0844 +1050 train 7.351931 (lr=1.6312e-04) (hash(x)=25373386) +1051 train 7.360591 (lr=1.6310e-04) (hash(x)=25318001) +1052 train 7.528632 (lr=1.6307e-04) (hash(x)=27255021) +1053 train 7.426228 (lr=1.6304e-04) (hash(x)=25174043) +1054 train 7.157006 (lr=1.6302e-04) (hash(x)=23857597) +1055 train 7.450856 (lr=1.6299e-04) (hash(x)=25305929) +1056 train 7.494323 (lr=1.6296e-04) (hash(x)=27009246) +1057 train 7.558558 (lr=1.6293e-04) (hash(x)=26175477) +1058 train 7.202619 (lr=1.6291e-04) (hash(x)=22700025) +1059 train 7.371774 (lr=1.6288e-04) (hash(x)=24339043) +1060 train 7.189368 (lr=1.6285e-04) (hash(x)=22139900) +1061 train 7.937978 (lr=1.6282e-04) (hash(x)=25412772) +1062 train 7.411931 (lr=1.6280e-04) (hash(x)=27020849) +1063 train 7.288886 (lr=1.6277e-04) (hash(x)=26808543) +1064 train 7.064786 (lr=1.6274e-04) (hash(x)=23061527) +1065 train 7.335269 (lr=1.6271e-04) (hash(x)=24738650) +1066 train 7.115642 (lr=1.6269e-04) (hash(x)=24036715) +1067 train 7.204399 (lr=1.6266e-04) (hash(x)=25763991) +1068 train 7.528606 (lr=1.6263e-04) (hash(x)=27393753) +1069 train 7.632516 (lr=1.6260e-04) (hash(x)=28182190) +1070 train 7.282097 (lr=1.6257e-04) (hash(x)=23358569) +1071 train 7.478458 (lr=1.6255e-04) (hash(x)=25669509) +1072 train 7.553757 (lr=1.6252e-04) (hash(x)=29139024) +1073 train 7.481774 (lr=1.6249e-04) (hash(x)=25616522) +1074 train 7.333403 (lr=1.6246e-04) (hash(x)=25695789) +1075 train 7.551047 (lr=1.6244e-04) (hash(x)=27676869) +1076 train 7.445690 (lr=1.6241e-04) (hash(x)=25952695) +1077 train 7.452406 (lr=1.6238e-04) (hash(x)=26316170) +1078 train 7.396934 (lr=1.6235e-04) (hash(x)=24081867) +1079 train 7.541876 (lr=1.6232e-04) (hash(x)=28435805) +1080 train 7.412543 (lr=1.6230e-04) (hash(x)=23375063) +1081 train 7.400409 (lr=1.6227e-04) (hash(x)=26869022) +1082 train 7.267751 (lr=1.6224e-04) (hash(x)=25793007) +1083 train 7.194251 (lr=1.6221e-04) (hash(x)=23455211) +1084 train 7.265335 (lr=1.6218e-04) (hash(x)=20441501) +1085 train 7.694765 (lr=1.6215e-04) (hash(x)=29321187) +1086 train 7.853790 (lr=1.6213e-04) (hash(x)=32627505) +1087 train 7.281975 (lr=1.6210e-04) (hash(x)=26482758) +1088 train 7.115514 (lr=1.6207e-04) (hash(x)=21431511) +1089 train 7.427049 (lr=1.6204e-04) (hash(x)=26046639) +1090 train 7.496436 (lr=1.6201e-04) (hash(x)=27464841) +1091 train 7.349338 (lr=1.6198e-04) (hash(x)=27068280) +1092 train 7.209756 (lr=1.6196e-04) (hash(x)=23119133) +1093 train 7.437540 (lr=1.6193e-04) (hash(x)=26782091) +1094 train 7.455720 (lr=1.6190e-04) (hash(x)=26265326) +1095 train 7.418920 (lr=1.6187e-04) (hash(x)=24929929) +1096 train 7.323729 (lr=1.6184e-04) (hash(x)=23158628) +1097 train 7.416749 (lr=1.6181e-04) (hash(x)=25950541) +1098 train 7.189775 (lr=1.6179e-04) (hash(x)=22093912) +1099 train 7.351516 (lr=1.6176e-04) (hash(x)=25373676) +1100 val loss 7.3386 +1100 val perplexity 1538.4806 +1100 train 7.072632 (lr=1.6173e-04) (hash(x)=18986670) +1101 train 7.591695 (lr=1.6170e-04) (hash(x)=27283187) +1102 train 7.335799 (lr=1.6167e-04) (hash(x)=25474743) +1103 train 7.200702 (lr=1.6164e-04) (hash(x)=25043037) +1104 train 7.150907 (lr=1.6161e-04) (hash(x)=23156261) +1105 train 7.585019 (lr=1.6158e-04) (hash(x)=27027534) +1106 train 7.208724 (lr=1.6156e-04) (hash(x)=22733630) +1107 train 7.452558 (lr=1.6153e-04) (hash(x)=27906976) +1108 train 7.385798 (lr=1.6150e-04) (hash(x)=27848655) +1109 train 7.347625 (lr=1.6147e-04) (hash(x)=23889709) +1110 train 8.339077 (lr=1.6144e-04) (hash(x)=33189918) +1111 train 7.950363 (lr=1.6141e-04) (hash(x)=29151257) +1112 train 7.587117 (lr=1.6138e-04) (hash(x)=23881512) +1113 train 7.319090 (lr=1.6135e-04) (hash(x)=21307974) +1114 train 7.312505 (lr=1.6132e-04) (hash(x)=25264524) +1115 train 7.483903 (lr=1.6130e-04) (hash(x)=26405613) +1116 train 7.167427 (lr=1.6127e-04) (hash(x)=21918678) +1117 train 7.238350 (lr=1.6124e-04) (hash(x)=24233887) +1118 train 6.836555 (lr=1.6121e-04) (hash(x)=19490509) +1119 train 7.463530 (lr=1.6118e-04) (hash(x)=26400365) +1120 train 7.700037 (lr=1.6115e-04) (hash(x)=28572086) +1121 train 7.136159 (lr=1.6112e-04) (hash(x)=22293114) +1122 train 7.276592 (lr=1.6109e-04) (hash(x)=26845479) +1123 train 7.147199 (lr=1.6106e-04) (hash(x)=23971905) +1124 train 7.398670 (lr=1.6103e-04) (hash(x)=25639959) +1125 train 7.001608 (lr=1.6100e-04) (hash(x)=20076502) +1126 train 7.393880 (lr=1.6097e-04) (hash(x)=25089255) +1127 train 7.281226 (lr=1.6094e-04) (hash(x)=24098812) +1128 train 7.309778 (lr=1.6092e-04) (hash(x)=23493707) +1129 train 7.536556 (lr=1.6089e-04) (hash(x)=27610410) +1130 train 7.298809 (lr=1.6086e-04) (hash(x)=24540186) +1131 train 7.597886 (lr=1.6083e-04) (hash(x)=29402976) +1132 train 7.196329 (lr=1.6080e-04) (hash(x)=23776025) +1133 train 6.895436 (lr=1.6077e-04) (hash(x)=19032564) +1134 train 7.510370 (lr=1.6074e-04) (hash(x)=26921117) +1135 train 7.086553 (lr=1.6071e-04) (hash(x)=20967666) +1136 train 7.138573 (lr=1.6068e-04) (hash(x)=23394540) +1137 train 7.186077 (lr=1.6065e-04) (hash(x)=22666342) +1138 train 7.386985 (lr=1.6062e-04) (hash(x)=23482498) +1139 train 7.459423 (lr=1.6059e-04) (hash(x)=24287610) +1140 train 7.521519 (lr=1.6056e-04) (hash(x)=24512831) +1141 train 7.749445 (lr=1.6053e-04) (hash(x)=28637634) +1142 train 7.968936 (lr=1.6050e-04) (hash(x)=24107127) +1143 train 7.623067 (lr=1.6047e-04) (hash(x)=28667963) +1144 train 7.512921 (lr=1.6044e-04) (hash(x)=26302492) +1145 train 7.568653 (lr=1.6041e-04) (hash(x)=23621685) +1146 train 7.246742 (lr=1.6038e-04) (hash(x)=23997414) +1147 train 7.373094 (lr=1.6035e-04) (hash(x)=25974316) +1148 train 7.292381 (lr=1.6032e-04) (hash(x)=23464988) +1149 train 7.391063 (lr=1.6029e-04) (hash(x)=24487710) +1150 val loss 7.3646 +1150 val perplexity 1579.0320 +1150 train 7.633968 (lr=1.6026e-04) (hash(x)=29610350) +1151 train 7.730699 (lr=1.6023e-04) (hash(x)=27083417) +1152 train 6.998694 (lr=1.6020e-04) (hash(x)=20666288) +1153 train 7.125401 (lr=1.6017e-04) (hash(x)=22850633) +1154 train 7.345078 (lr=1.6014e-04) (hash(x)=24741872) +1155 train 7.764108 (lr=1.6011e-04) (hash(x)=28605205) +1156 train 7.184031 (lr=1.6008e-04) (hash(x)=22624463) +1157 train 7.405667 (lr=1.6005e-04) (hash(x)=24786468) +1158 train 7.135025 (lr=1.6002e-04) (hash(x)=21365399) +1159 train 7.415128 (lr=1.5999e-04) (hash(x)=23649001) +1160 train 7.435285 (lr=1.5996e-04) (hash(x)=28203982) +1161 train 7.316133 (lr=1.5993e-04) (hash(x)=26473994) +1162 train 6.990098 (lr=1.5990e-04) (hash(x)=19476441) +1163 train 7.290183 (lr=1.5987e-04) (hash(x)=25921700) +1164 train 7.143604 (lr=1.5984e-04) (hash(x)=23064343) +1165 train 7.292191 (lr=1.5981e-04) (hash(x)=24117626) +1166 train 7.238380 (lr=1.5978e-04) (hash(x)=21764556) +1167 train 8.119655 (lr=1.5975e-04) (hash(x)=31338300) +1168 train 7.545616 (lr=1.5972e-04) (hash(x)=27443187) +1169 train 6.948086 (lr=1.5969e-04) (hash(x)=21337692) +1170 train 7.490587 (lr=1.5966e-04) (hash(x)=27845383) +1171 train 7.297555 (lr=1.5963e-04) (hash(x)=23862328) +1172 train 7.504207 (lr=1.5959e-04) (hash(x)=23811014) +1173 train 7.451831 (lr=1.5956e-04) (hash(x)=24380098) +1174 train 7.112328 (lr=1.5953e-04) (hash(x)=22351136) +1175 train 7.436150 (lr=1.5950e-04) (hash(x)=30603174) +1176 train 7.456177 (lr=1.5947e-04) (hash(x)=27924596) +1177 train 7.846539 (lr=1.5944e-04) (hash(x)=30882548) +1178 train 7.244084 (lr=1.5941e-04) (hash(x)=22339464) +1179 train 7.101930 (lr=1.5938e-04) (hash(x)=23603806) +1180 train 7.481613 (lr=1.5935e-04) (hash(x)=24809041) +1181 train 7.277069 (lr=1.5932e-04) (hash(x)=24382442) +1182 train 7.191510 (lr=1.5929e-04) (hash(x)=23134077) +1183 train 7.254590 (lr=1.5926e-04) (hash(x)=24830965) +1184 train 7.333510 (lr=1.5923e-04) (hash(x)=25527259) +1185 train 7.405081 (lr=1.5919e-04) (hash(x)=25547480) +1186 train 7.231034 (lr=1.5916e-04) (hash(x)=24424314) +1187 train 7.650839 (lr=1.5913e-04) (hash(x)=32488729) +1188 train 7.571053 (lr=1.5910e-04) (hash(x)=31168462) +1189 train 7.785546 (lr=1.5907e-04) (hash(x)=31331643) +1190 train 7.489736 (lr=1.5904e-04) (hash(x)=28746633) +1191 train 7.472488 (lr=1.5901e-04) (hash(x)=27269893) +1192 train 7.260554 (lr=1.5898e-04) (hash(x)=23484031) +1193 train 7.252201 (lr=1.5895e-04) (hash(x)=23278725) +1194 train 7.358077 (lr=1.5891e-04) (hash(x)=25440745) +1195 train 7.384694 (lr=1.5888e-04) (hash(x)=25215077) +1196 train 7.459830 (lr=1.5885e-04) (hash(x)=28309266) +1197 train 7.155338 (lr=1.5882e-04) (hash(x)=22442404) +1198 train 7.179025 (lr=1.5879e-04) (hash(x)=20775262) +1199 train 7.264166 (lr=1.5876e-04) (hash(x)=24825041) +1200 val loss 7.3178 +1200 val perplexity 1506.8372 +1200 train 7.448225 (lr=1.5873e-04) (hash(x)=29016896) +1201 train 7.383367 (lr=1.5870e-04) (hash(x)=25590276) +1202 train 7.212790 (lr=1.5866e-04) (hash(x)=22816384) +1203 train 7.414028 (lr=1.5863e-04) (hash(x)=25893804) +1204 train 7.253035 (lr=1.5860e-04) (hash(x)=23983816) +1205 train 7.155618 (lr=1.5857e-04) (hash(x)=22222468) +1206 train 7.195609 (lr=1.5854e-04) (hash(x)=23039141) +1207 train 7.115828 (lr=1.5851e-04) (hash(x)=22724871) +1208 train 7.179703 (lr=1.5847e-04) (hash(x)=25253062) +1209 train 7.211183 (lr=1.5844e-04) (hash(x)=25140744) +1210 train 7.286041 (lr=1.5841e-04) (hash(x)=24717218) +1211 train 7.373634 (lr=1.5838e-04) (hash(x)=27317554) +1212 train 6.989175 (lr=1.5835e-04) (hash(x)=22013236) +1213 train 7.565996 (lr=1.5832e-04) (hash(x)=26692343) +1214 train 7.090186 (lr=1.5828e-04) (hash(x)=19859225) +1215 train 7.020717 (lr=1.5825e-04) (hash(x)=24683717) +1216 train 7.114976 (lr=1.5822e-04) (hash(x)=21932013) +1217 train 7.371843 (lr=1.5819e-04) (hash(x)=26849303) +1218 train 7.437103 (lr=1.5816e-04) (hash(x)=26458000) +1219 train 7.220981 (lr=1.5813e-04) (hash(x)=21584083) +1220 train 7.586666 (lr=1.5809e-04) (hash(x)=23598625) +1221 train 7.298410 (lr=1.5806e-04) (hash(x)=26059939) +1222 train 7.548756 (lr=1.5803e-04) (hash(x)=25481982) +1223 train 7.405670 (lr=1.5800e-04) (hash(x)=26190337) +1224 train 7.566475 (lr=1.5797e-04) (hash(x)=28767755) +1225 train 7.223593 (lr=1.5793e-04) (hash(x)=23663918) +1226 train 7.339757 (lr=1.5790e-04) (hash(x)=21293227) +1227 train 7.335468 (lr=1.5787e-04) (hash(x)=22249019) +1228 train 7.428116 (lr=1.5784e-04) (hash(x)=26886529) +1229 train 7.237994 (lr=1.5781e-04) (hash(x)=25779849) +1230 train 7.362445 (lr=1.5777e-04) (hash(x)=26228964) +1231 train 7.304466 (lr=1.5774e-04) (hash(x)=23086289) +1232 train 7.396204 (lr=1.5771e-04) (hash(x)=23198922) +1233 train 7.398084 (lr=1.5768e-04) (hash(x)=27523941) +1234 train 7.194091 (lr=1.5764e-04) (hash(x)=24293992) +1235 train 7.916892 (lr=1.5761e-04) (hash(x)=28047044) +1236 train 7.393808 (lr=1.5758e-04) (hash(x)=23688671) +1237 train 7.253414 (lr=1.5755e-04) (hash(x)=25125498) +1238 train 7.134528 (lr=1.5752e-04) (hash(x)=21977292) +1239 train 7.251451 (lr=1.5748e-04) (hash(x)=23593875) +1240 train 7.141359 (lr=1.5745e-04) (hash(x)=22659030) +1241 train 7.267606 (lr=1.5742e-04) (hash(x)=25117733) +1242 train 7.313413 (lr=1.5739e-04) (hash(x)=22322808) +1243 train 7.293297 (lr=1.5735e-04) (hash(x)=26059735) +1244 train 7.238138 (lr=1.5732e-04) (hash(x)=22485526) +1245 train 7.151857 (lr=1.5729e-04) (hash(x)=23028679) +1246 train 7.205747 (lr=1.5726e-04) (hash(x)=22906035) +1247 train 7.064780 (lr=1.5722e-04) (hash(x)=22414190) +1248 train 7.386121 (lr=1.5719e-04) (hash(x)=26229624) +1249 train 7.147824 (lr=1.5716e-04) (hash(x)=22223137) +1250 val loss 7.3013 +1250 val perplexity 1482.1614 +1250 train 7.442116 (lr=1.5712e-04) (hash(x)=24911520) +1251 train 7.609742 (lr=1.5709e-04) (hash(x)=24204591) +1252 train 7.145772 (lr=1.5706e-04) (hash(x)=24379601) +1253 train 7.146545 (lr=1.5703e-04) (hash(x)=22922475) +1254 train 7.175485 (lr=1.5699e-04) (hash(x)=23426249) +1255 train 7.446336 (lr=1.5696e-04) (hash(x)=26758114) +1256 train 7.147101 (lr=1.5693e-04) (hash(x)=24027111) +1257 train 7.278448 (lr=1.5690e-04) (hash(x)=25358064) +1258 train 7.173402 (lr=1.5686e-04) (hash(x)=22571285) +1259 train 7.593174 (lr=1.5683e-04) (hash(x)=20084233) +1260 train 7.413831 (lr=1.5680e-04) (hash(x)=18786581) +1261 train 7.300254 (lr=1.5676e-04) (hash(x)=26395104) +1262 train 7.170727 (lr=1.5673e-04) (hash(x)=24212567) +1263 train 6.984296 (lr=1.5670e-04) (hash(x)=21563184) +1264 train 7.269482 (lr=1.5666e-04) (hash(x)=26490150) +1265 train 7.374803 (lr=1.5663e-04) (hash(x)=25207694) +1266 train 7.203279 (lr=1.5660e-04) (hash(x)=23914544) +1267 train 7.186632 (lr=1.5656e-04) (hash(x)=23861489) +1268 train 7.675226 (lr=1.5653e-04) (hash(x)=30714540) +1269 train 7.172559 (lr=1.5650e-04) (hash(x)=23471007) +1270 train 7.146862 (lr=1.5647e-04) (hash(x)=23244293) +1271 train 7.124518 (lr=1.5643e-04) (hash(x)=19218470) +1272 train 7.386475 (lr=1.5640e-04) (hash(x)=26965136) +1273 train 7.138344 (lr=1.5637e-04) (hash(x)=22944035) +1274 train 7.207170 (lr=1.5633e-04) (hash(x)=22002714) +1275 train 7.464637 (lr=1.5630e-04) (hash(x)=28469562) +1276 train 7.506725 (lr=1.5627e-04) (hash(x)=26889992) +1277 train 7.595309 (lr=1.5623e-04) (hash(x)=26452814) +1278 train 7.370560 (lr=1.5620e-04) (hash(x)=28397488) +1279 train 7.473032 (lr=1.5617e-04) (hash(x)=25588469) +1280 train 7.307728 (lr=1.5613e-04) (hash(x)=24833139) +1281 train 7.141214 (lr=1.5610e-04) (hash(x)=24788298) +1282 train 7.435628 (lr=1.5606e-04) (hash(x)=24979383) +1283 train 7.431675 (lr=1.5603e-04) (hash(x)=25236367) +1284 train 7.318077 (lr=1.5600e-04) (hash(x)=22638257) +1285 train 7.094954 (lr=1.5596e-04) (hash(x)=23069067) +1286 train 7.251718 (lr=1.5593e-04) (hash(x)=25133239) +1287 train 7.863077 (lr=1.5590e-04) (hash(x)=30433767) +1288 train 7.929402 (lr=1.5586e-04) (hash(x)=34319079) +1289 train 7.761693 (lr=1.5583e-04) (hash(x)=29268881) +1290 train 7.346176 (lr=1.5580e-04) (hash(x)=24528336) +1291 train 7.523766 (lr=1.5576e-04) (hash(x)=26302626) +1292 train 7.469939 (lr=1.5573e-04) (hash(x)=25479111) +1293 train 7.670720 (lr=1.5569e-04) (hash(x)=24749682) +1294 train 7.295373 (lr=1.5566e-04) (hash(x)=24111393) +1295 train 7.051421 (lr=1.5563e-04) (hash(x)=17851621) +1296 train 7.267999 (lr=1.5559e-04) (hash(x)=26463070) +1297 train 7.310534 (lr=1.5556e-04) (hash(x)=25620741) +1298 train 7.994905 (lr=1.5553e-04) (hash(x)=28225676) +1299 train 7.788484 (lr=1.5549e-04) (hash(x)=27028191) +1300 val loss 7.3329 +1300 val perplexity 1529.7594 +1300 train 7.337159 (lr=1.5546e-04) (hash(x)=29006516) +1301 train 7.526433 (lr=1.5542e-04) (hash(x)=27590299) +1302 train 7.639965 (lr=1.5539e-04) (hash(x)=28678983) +1303 train 7.467281 (lr=1.5536e-04) (hash(x)=25183690) +1304 train 6.983442 (lr=1.5532e-04) (hash(x)=19918097) +1305 train 7.831913 (lr=1.5529e-04) (hash(x)=31114252) +1306 train 7.789459 (lr=1.5525e-04) (hash(x)=30913255) +1307 train 7.369490 (lr=1.5522e-04) (hash(x)=26182243) +1308 train 7.601931 (lr=1.5518e-04) (hash(x)=27420668) +1309 train 7.834111 (lr=1.5515e-04) (hash(x)=30419908) +1310 train 7.744164 (lr=1.5512e-04) (hash(x)=29002281) +1311 train 7.411495 (lr=1.5508e-04) (hash(x)=27040642) +1312 train 7.285323 (lr=1.5505e-04) (hash(x)=26929300) +1313 train 7.364826 (lr=1.5501e-04) (hash(x)=26240761) +1314 train 7.418489 (lr=1.5498e-04) (hash(x)=27161876) +1315 train 7.213614 (lr=1.5494e-04) (hash(x)=24489607) +1316 train 7.678969 (lr=1.5491e-04) (hash(x)=27040115) +1317 train 7.269392 (lr=1.5488e-04) (hash(x)=25012872) +1318 train 6.882874 (lr=1.5484e-04) (hash(x)=20894720) +1319 train 6.969288 (lr=1.5481e-04) (hash(x)=22183303) +1320 train 7.293153 (lr=1.5477e-04) (hash(x)=26291778) +1321 train 7.406949 (lr=1.5474e-04) (hash(x)=27682633) +1322 train 7.153316 (lr=1.5470e-04) (hash(x)=26490892) +1323 train 7.672344 (lr=1.5467e-04) (hash(x)=28844646) +1324 train 7.990402 (lr=1.5463e-04) (hash(x)=29545304) +1325 train 8.114043 (lr=1.5460e-04) (hash(x)=31082070) +1326 train 7.721776 (lr=1.5457e-04) (hash(x)=27486316) +1327 train 7.628705 (lr=1.5453e-04) (hash(x)=27537063) +1328 train 7.376083 (lr=1.5450e-04) (hash(x)=26955557) +1329 train 7.385906 (lr=1.5446e-04) (hash(x)=26125988) +1330 train 7.352911 (lr=1.5443e-04) (hash(x)=22800125) +1331 train 7.518396 (lr=1.5439e-04) (hash(x)=25446686) +1332 train 7.604881 (lr=1.5436e-04) (hash(x)=28743746) +1333 train 7.376309 (lr=1.5432e-04) (hash(x)=19819857) +1334 train 7.059335 (lr=1.5429e-04) (hash(x)=23518628) +1335 train 7.016548 (lr=1.5425e-04) (hash(x)=19492832) +1336 train 7.319496 (lr=1.5422e-04) (hash(x)=24627720) +1337 train 7.219928 (lr=1.5418e-04) (hash(x)=23741214) +1338 train 7.313356 (lr=1.5415e-04) (hash(x)=25837914) +1339 train 7.174649 (lr=1.5411e-04) (hash(x)=25484958) +1340 train 7.172493 (lr=1.5408e-04) (hash(x)=23671284) +1341 train 7.233581 (lr=1.5404e-04) (hash(x)=25525370) +1342 train 7.391696 (lr=1.5401e-04) (hash(x)=26585300) +1343 train 7.431848 (lr=1.5397e-04) (hash(x)=25951629) +1344 train 7.648697 (lr=1.5394e-04) (hash(x)=28743135) +1345 train 7.786083 (lr=1.5390e-04) (hash(x)=28557663) +1346 train 7.151364 (lr=1.5387e-04) (hash(x)=22642751) +1347 train 7.115680 (lr=1.5383e-04) (hash(x)=23462798) +1348 train 7.050096 (lr=1.5380e-04) (hash(x)=24292328) +1349 train 7.393295 (lr=1.5376e-04) (hash(x)=27320280) +1350 val loss 7.3352 +1350 val perplexity 1533.2800 +1350 train 7.535108 (lr=1.5373e-04) (hash(x)=27352812) +1351 train 7.366318 (lr=1.5369e-04) (hash(x)=22408682) +1352 train 7.293193 (lr=1.5366e-04) (hash(x)=23144732) +1353 train 7.114751 (lr=1.5362e-04) (hash(x)=22230799) +1354 train 7.541371 (lr=1.5359e-04) (hash(x)=29747687) +1355 train 7.732825 (lr=1.5355e-04) (hash(x)=31317970) +1356 train 6.873925 (lr=1.5351e-04) (hash(x)=20131758) +1357 train 7.302655 (lr=1.5348e-04) (hash(x)=24020983) +1358 train 7.154573 (lr=1.5344e-04) (hash(x)=23998051) +1359 train 7.272302 (lr=1.5341e-04) (hash(x)=27633457) +1360 train 7.007352 (lr=1.5337e-04) (hash(x)=20155247) +1361 train 7.303558 (lr=1.5334e-04) (hash(x)=23766987) +1362 train 7.171689 (lr=1.5330e-04) (hash(x)=25960383) +1363 train 7.443381 (lr=1.5327e-04) (hash(x)=23729283) +1364 train 7.560018 (lr=1.5323e-04) (hash(x)=27775445) +1365 train 7.392780 (lr=1.5320e-04) (hash(x)=25975834) +1366 train 7.216432 (lr=1.5316e-04) (hash(x)=22765259) +1367 train 7.484306 (lr=1.5312e-04) (hash(x)=27635080) +1368 train 7.243521 (lr=1.5309e-04) (hash(x)=23848542) +1369 train 7.419055 (lr=1.5305e-04) (hash(x)=27181156) +1370 train 7.568095 (lr=1.5302e-04) (hash(x)=28321340) +1371 train 7.265529 (lr=1.5298e-04) (hash(x)=25918780) +1372 train 7.259235 (lr=1.5295e-04) (hash(x)=23338297) +1373 train 7.280173 (lr=1.5291e-04) (hash(x)=22370417) +1374 train 7.278474 (lr=1.5287e-04) (hash(x)=24272668) +1375 train 6.961524 (lr=1.5284e-04) (hash(x)=22287596) +1376 train 7.193790 (lr=1.5280e-04) (hash(x)=25257403) +1377 train 7.095554 (lr=1.5277e-04) (hash(x)=21584419) +1378 train 7.313375 (lr=1.5273e-04) (hash(x)=25318823) +1379 train 7.092103 (lr=1.5269e-04) (hash(x)=22694623) +1380 train 7.216166 (lr=1.5266e-04) (hash(x)=23743406) +1381 train 7.540120 (lr=1.5262e-04) (hash(x)=30820846) +1382 train 8.052444 (lr=1.5259e-04) (hash(x)=34639557) +1383 train 7.935039 (lr=1.5255e-04) (hash(x)=35895440) +1384 train 7.333617 (lr=1.5251e-04) (hash(x)=26304839) +1385 train 7.467938 (lr=1.5248e-04) (hash(x)=27058657) +1386 train 7.395224 (lr=1.5244e-04) (hash(x)=25209529) +1387 train 7.303026 (lr=1.5241e-04) (hash(x)=24298886) +1388 train 7.358049 (lr=1.5237e-04) (hash(x)=26200200) +1389 train 7.298187 (lr=1.5233e-04) (hash(x)=27303061) +1390 train 7.348992 (lr=1.5230e-04) (hash(x)=26531628) +1391 train 7.382965 (lr=1.5226e-04) (hash(x)=25888847) +1392 train 7.551126 (lr=1.5223e-04) (hash(x)=28924067) +1393 train 6.975732 (lr=1.5219e-04) (hash(x)=21267641) +1394 train 7.525554 (lr=1.5215e-04) (hash(x)=29419156) +1395 train 7.776332 (lr=1.5212e-04) (hash(x)=30860646) +1396 train 7.306672 (lr=1.5208e-04) (hash(x)=25744434) +1397 train 7.327614 (lr=1.5204e-04) (hash(x)=26881837) +1398 train 7.281240 (lr=1.5201e-04) (hash(x)=26676176) +1399 train 7.476678 (lr=1.5197e-04) (hash(x)=26518800) +1400 val loss 7.2793 +1400 val perplexity 1450.0110 +1400 train 7.190178 (lr=1.5193e-04) (hash(x)=25043238) +1401 train 7.464552 (lr=1.5190e-04) (hash(x)=25863277) +1402 train 7.144670 (lr=1.5186e-04) (hash(x)=24073623) +1403 train 7.217873 (lr=1.5183e-04) (hash(x)=25385523) +1404 train 7.272659 (lr=1.5179e-04) (hash(x)=24958112) +1405 train 7.145308 (lr=1.5175e-04) (hash(x)=23362519) +1406 train 7.466232 (lr=1.5172e-04) (hash(x)=29262616) +1407 train 7.887386 (lr=1.5168e-04) (hash(x)=37519283) +1408 train 8.107955 (lr=1.5164e-04) (hash(x)=33716930) +1409 train 7.281258 (lr=1.5161e-04) (hash(x)=23392584) +1410 train 7.760787 (lr=1.5157e-04) (hash(x)=22877779) +1411 train 8.122527 (lr=1.5153e-04) (hash(x)=20564397) +1412 train 7.525125 (lr=1.5150e-04) (hash(x)=24366235) +1413 train 7.356494 (lr=1.5146e-04) (hash(x)=27065499) +1414 train 7.213331 (lr=1.5142e-04) (hash(x)=26844114) +1415 train 7.339089 (lr=1.5139e-04) (hash(x)=25141945) +1416 train 7.571267 (lr=1.5135e-04) (hash(x)=28813116) +1417 train 7.342452 (lr=1.5131e-04) (hash(x)=25466598) +1418 train 7.183647 (lr=1.5127e-04) (hash(x)=22800032) +1419 train 7.294796 (lr=1.5124e-04) (hash(x)=22717866) +1420 train 7.827634 (lr=1.5120e-04) (hash(x)=28040763) +1421 train 7.912502 (lr=1.5116e-04) (hash(x)=29648992) +1422 train 7.846652 (lr=1.5113e-04) (hash(x)=31747228) +1423 train 7.319896 (lr=1.5109e-04) (hash(x)=28527939) +1424 train 7.307692 (lr=1.5105e-04) (hash(x)=21563992) +1425 train 7.193414 (lr=1.5102e-04) (hash(x)=25134784) +1426 train 7.394246 (lr=1.5098e-04) (hash(x)=28442823) +1427 train 7.902907 (lr=1.5094e-04) (hash(x)=32757059) +1428 train 7.175413 (lr=1.5090e-04) (hash(x)=24110500) +1429 train 7.209200 (lr=1.5087e-04) (hash(x)=24145729) +1430 train 7.271671 (lr=1.5083e-04) (hash(x)=23541086) +1431 train 7.114433 (lr=1.5079e-04) (hash(x)=21942471) +1432 train 7.215259 (lr=1.5076e-04) (hash(x)=24736836) +1433 train 7.390959 (lr=1.5072e-04) (hash(x)=25325444) +1434 train 7.407048 (lr=1.5068e-04) (hash(x)=25188954) +1435 train 7.986261 (lr=1.5064e-04) (hash(x)=24247339) +1436 train 7.353528 (lr=1.5061e-04) (hash(x)=23773363) +1437 train 7.120374 (lr=1.5057e-04) (hash(x)=24142989) +1438 train 7.097392 (lr=1.5053e-04) (hash(x)=24226952) +1439 train 7.342573 (lr=1.5050e-04) (hash(x)=24955630) +1440 train 7.283896 (lr=1.5046e-04) (hash(x)=24563233) +1441 train 7.375876 (lr=1.5042e-04) (hash(x)=25491335) +1442 train 7.785568 (lr=1.5038e-04) (hash(x)=33253763) +1443 train 7.151388 (lr=1.5035e-04) (hash(x)=21368780) +1444 train 7.218353 (lr=1.5031e-04) (hash(x)=26615500) +1445 train 7.449584 (lr=1.5027e-04) (hash(x)=27146278) +1446 train 7.320756 (lr=1.5023e-04) (hash(x)=25904861) +1447 train 7.144994 (lr=1.5020e-04) (hash(x)=25541230) +1448 train 7.349462 (lr=1.5016e-04) (hash(x)=25434227) +1449 train 7.269311 (lr=1.5012e-04) (hash(x)=25375355) +1450 val loss 7.2552 +1450 val perplexity 1415.4769 +1450 train 7.079390 (lr=1.5008e-04) (hash(x)=21921129) +1451 train 7.086489 (lr=1.5005e-04) (hash(x)=23098806) +1452 train 7.094283 (lr=1.5001e-04) (hash(x)=22000544) +1453 train 7.054965 (lr=1.4997e-04) (hash(x)=22061174) +1454 train 7.163192 (lr=1.4993e-04) (hash(x)=24326286) +1455 train 7.184187 (lr=1.4989e-04) (hash(x)=23501481) +1456 train 7.320199 (lr=1.4986e-04) (hash(x)=26397938) +1457 train 7.300018 (lr=1.4982e-04) (hash(x)=24656430) +1458 train 7.038303 (lr=1.4978e-04) (hash(x)=23494971) +1459 train 7.088500 (lr=1.4974e-04) (hash(x)=23802681) +1460 train 7.078333 (lr=1.4971e-04) (hash(x)=21990153) +1461 train 7.132258 (lr=1.4967e-04) (hash(x)=23496118) +1462 train 7.156801 (lr=1.4963e-04) (hash(x)=24233822) +1463 train 7.436845 (lr=1.4959e-04) (hash(x)=22754988) +1464 train 7.164003 (lr=1.4955e-04) (hash(x)=23116635) +1465 train 6.904428 (lr=1.4952e-04) (hash(x)=21461650) +1466 train 7.039529 (lr=1.4948e-04) (hash(x)=22274473) +1467 train 7.074677 (lr=1.4944e-04) (hash(x)=22183009) +1468 train 7.314081 (lr=1.4940e-04) (hash(x)=24972441) +1469 train 7.131541 (lr=1.4936e-04) (hash(x)=22300616) +1470 train 6.881269 (lr=1.4933e-04) (hash(x)=21443060) +1471 train 7.145296 (lr=1.4929e-04) (hash(x)=23475070) +1472 train 7.069715 (lr=1.4925e-04) (hash(x)=22316810) +1473 train 7.527176 (lr=1.4921e-04) (hash(x)=24508407) +1474 train 7.593291 (lr=1.4917e-04) (hash(x)=24603557) +1475 train 7.163853 (lr=1.4914e-04) (hash(x)=23359061) +1476 train 7.243194 (lr=1.4910e-04) (hash(x)=22950844) +1477 train 7.263689 (lr=1.4906e-04) (hash(x)=22588667) +1478 train 7.367452 (lr=1.4902e-04) (hash(x)=26083526) +1479 train 7.288460 (lr=1.4898e-04) (hash(x)=23609959) +1480 train 7.292361 (lr=1.4894e-04) (hash(x)=24088171) +1481 train 7.289048 (lr=1.4891e-04) (hash(x)=25394852) +1482 train 7.251252 (lr=1.4887e-04) (hash(x)=24503040) +1483 train 6.975101 (lr=1.4883e-04) (hash(x)=22408449) +1484 train 7.232196 (lr=1.4879e-04) (hash(x)=25069325) +1485 train 7.266370 (lr=1.4875e-04) (hash(x)=26947398) +1486 train 6.758662 (lr=1.4871e-04) (hash(x)=17527161) +1487 train 7.143747 (lr=1.4868e-04) (hash(x)=23441847) +1488 train 7.167754 (lr=1.4864e-04) (hash(x)=25592861) +1489 train 7.071529 (lr=1.4860e-04) (hash(x)=23101350) +1490 train 7.053398 (lr=1.4856e-04) (hash(x)=24201380) +1491 train 7.163856 (lr=1.4852e-04) (hash(x)=23676365) +1492 train 7.251531 (lr=1.4848e-04) (hash(x)=26668088) +1493 train 7.372931 (lr=1.4844e-04) (hash(x)=26488811) +1494 train 7.375974 (lr=1.4841e-04) (hash(x)=27248109) +1495 train 7.455024 (lr=1.4837e-04) (hash(x)=23096292) +1496 train 7.314226 (lr=1.4833e-04) (hash(x)=22101981) +1497 train 7.470024 (lr=1.4829e-04) (hash(x)=24512380) +1498 train 7.301931 (lr=1.4825e-04) (hash(x)=25367738) +1499 train 7.265616 (lr=1.4821e-04) (hash(x)=27706294) +1500 val loss 7.2596 +1500 val perplexity 1421.6331 +1500 train 7.409544 (lr=1.4817e-04) (hash(x)=24154026) +1501 train 7.089343 (lr=1.4813e-04) (hash(x)=21892472) +1502 train 7.139742 (lr=1.4810e-04) (hash(x)=23662543) +1503 train 7.199642 (lr=1.4806e-04) (hash(x)=26171093) +1504 train 7.221581 (lr=1.4802e-04) (hash(x)=25974292) +1505 train 7.092992 (lr=1.4798e-04) (hash(x)=23191101) +1506 train 7.358705 (lr=1.4794e-04) (hash(x)=26498861) +1507 train 7.917714 (lr=1.4790e-04) (hash(x)=34946941) +1508 train 7.509454 (lr=1.4786e-04) (hash(x)=25442719) +1509 train 7.327854 (lr=1.4782e-04) (hash(x)=25569942) +1510 train 7.041487 (lr=1.4778e-04) (hash(x)=21265828) +1511 train 6.905364 (lr=1.4775e-04) (hash(x)=20060838) +1512 train 7.099686 (lr=1.4771e-04) (hash(x)=22588251) +1513 train 7.086966 (lr=1.4767e-04) (hash(x)=24581020) +1514 train 7.069127 (lr=1.4763e-04) (hash(x)=21882493) +1515 train 7.071159 (lr=1.4759e-04) (hash(x)=21591702) +1516 train 7.117945 (lr=1.4755e-04) (hash(x)=19813285) +1517 train 7.189862 (lr=1.4751e-04) (hash(x)=21870012) +1518 train 7.172559 (lr=1.4747e-04) (hash(x)=26895498) +1519 train 7.188495 (lr=1.4743e-04) (hash(x)=25451055) +1520 train 7.257711 (lr=1.4739e-04) (hash(x)=25395865) +1521 train 6.742655 (lr=1.4735e-04) (hash(x)=18989695) +1522 train 6.629518 (lr=1.4732e-04) (hash(x)=17040678) +1523 train 6.744956 (lr=1.4728e-04) (hash(x)=18691455) +1524 train 6.810827 (lr=1.4724e-04) (hash(x)=19017167) +1525 train 7.152472 (lr=1.4720e-04) (hash(x)=22406503) +1526 train 7.348174 (lr=1.4716e-04) (hash(x)=23036138) +1527 train 7.183958 (lr=1.4712e-04) (hash(x)=24934792) +1528 train 7.210378 (lr=1.4708e-04) (hash(x)=22843127) +1529 train 7.165117 (lr=1.4704e-04) (hash(x)=24249677) +1530 train 7.036673 (lr=1.4700e-04) (hash(x)=23318555) +1531 train 7.120342 (lr=1.4696e-04) (hash(x)=23864361) +1532 train 6.996155 (lr=1.4692e-04) (hash(x)=20242060) +1533 train 7.139827 (lr=1.4688e-04) (hash(x)=21549554) +1534 train 6.934494 (lr=1.4684e-04) (hash(x)=21642024) +1535 train 7.415451 (lr=1.4680e-04) (hash(x)=25367597) +1536 train 7.598759 (lr=1.4676e-04) (hash(x)=27224144) +1537 train 7.178148 (lr=1.4672e-04) (hash(x)=24409290) +1538 train 7.229758 (lr=1.4669e-04) (hash(x)=24987180) +1539 train 7.130141 (lr=1.4665e-04) (hash(x)=27016702) +1540 train 7.425297 (lr=1.4661e-04) (hash(x)=25819636) +1541 train 7.330272 (lr=1.4657e-04) (hash(x)=25520453) +1542 train 7.092873 (lr=1.4653e-04) (hash(x)=23580496) +1543 train 7.286356 (lr=1.4649e-04) (hash(x)=25022148) +1544 train 7.273058 (lr=1.4645e-04) (hash(x)=25447327) +1545 train 7.264354 (lr=1.4641e-04) (hash(x)=25010319) +1546 train 7.198297 (lr=1.4637e-04) (hash(x)=25511777) +1547 train 7.172736 (lr=1.4633e-04) (hash(x)=24459012) +1548 train 7.220686 (lr=1.4629e-04) (hash(x)=25082785) +1549 train 7.246156 (lr=1.4625e-04) (hash(x)=26528670) +1550 val loss 7.2382 +1550 val perplexity 1391.6455 +1550 train 7.257360 (lr=1.4621e-04) (hash(x)=26684367) +1551 train 7.211895 (lr=1.4617e-04) (hash(x)=25431365) +1552 train 7.189072 (lr=1.4613e-04) (hash(x)=24802747) +1553 train 6.996983 (lr=1.4609e-04) (hash(x)=24229522) +1554 train 7.257213 (lr=1.4605e-04) (hash(x)=24757176) +1555 train 7.380703 (lr=1.4601e-04) (hash(x)=25958785) +1556 train 7.391881 (lr=1.4597e-04) (hash(x)=26810735) +1557 train 6.998268 (lr=1.4593e-04) (hash(x)=22882640) +1558 train 7.497169 (lr=1.4589e-04) (hash(x)=27220057) +1559 train 7.777586 (lr=1.4585e-04) (hash(x)=29307788) +1560 train 7.197903 (lr=1.4581e-04) (hash(x)=25214030) +1561 train 7.030023 (lr=1.4577e-04) (hash(x)=23167825) +1562 train 7.124212 (lr=1.4573e-04) (hash(x)=24658511) +1563 train 7.254726 (lr=1.4569e-04) (hash(x)=24965435) +1564 train 7.018390 (lr=1.4565e-04) (hash(x)=23620579) +1565 train 7.006382 (lr=1.4561e-04) (hash(x)=23772949) +1566 train 7.169366 (lr=1.4557e-04) (hash(x)=23807939) +1567 train 7.390428 (lr=1.4553e-04) (hash(x)=25651929) +1568 train 7.332297 (lr=1.4549e-04) (hash(x)=25549933) +1569 train 7.021163 (lr=1.4545e-04) (hash(x)=23146724) +1570 train 7.129744 (lr=1.4541e-04) (hash(x)=24099275) +1571 train 7.332138 (lr=1.4537e-04) (hash(x)=28451031) +1572 train 7.414527 (lr=1.4533e-04) (hash(x)=25488511) +1573 train 7.185678 (lr=1.4529e-04) (hash(x)=23796771) +1574 train 7.219186 (lr=1.4525e-04) (hash(x)=22642764) +1575 train 7.320749 (lr=1.4521e-04) (hash(x)=26312387) +1576 train 7.099959 (lr=1.4517e-04) (hash(x)=22486223) +1577 train 7.125162 (lr=1.4512e-04) (hash(x)=21257377) +1578 train 7.252236 (lr=1.4508e-04) (hash(x)=24328365) +1579 train 7.342033 (lr=1.4504e-04) (hash(x)=25326650) +1580 train 7.307204 (lr=1.4500e-04) (hash(x)=26484837) +1581 train 7.085496 (lr=1.4496e-04) (hash(x)=24605603) +1582 train 7.175575 (lr=1.4492e-04) (hash(x)=24668537) +1583 train 7.093280 (lr=1.4488e-04) (hash(x)=23804913) +1584 train 7.306127 (lr=1.4484e-04) (hash(x)=23615391) +1585 train 7.306409 (lr=1.4480e-04) (hash(x)=24322926) +1586 train 6.994949 (lr=1.4476e-04) (hash(x)=19753104) +1587 train 7.568569 (lr=1.4472e-04) (hash(x)=25537529) +1588 train 6.942513 (lr=1.4468e-04) (hash(x)=22835476) +1589 train 7.076480 (lr=1.4464e-04) (hash(x)=25707197) +1590 train 7.098063 (lr=1.4460e-04) (hash(x)=24191203) +1591 train 7.346237 (lr=1.4456e-04) (hash(x)=26115519) +1592 train 7.279553 (lr=1.4452e-04) (hash(x)=25781547) +1593 train 7.071204 (lr=1.4448e-04) (hash(x)=24850654) +1594 train 6.966149 (lr=1.4443e-04) (hash(x)=23300928) +1595 train 7.263512 (lr=1.4439e-04) (hash(x)=25494804) +1596 train 7.267597 (lr=1.4435e-04) (hash(x)=28169410) +1597 train 6.970417 (lr=1.4431e-04) (hash(x)=21972022) +1598 train 7.562268 (lr=1.4427e-04) (hash(x)=27687290) +1599 train 7.517670 (lr=1.4423e-04) (hash(x)=23210747) +1600 val loss 7.2347 +1600 val perplexity 1386.7787 +1600 train 7.527618 (lr=1.4419e-04) (hash(x)=20362758) +1601 train 7.322147 (lr=1.4415e-04) (hash(x)=17064773) +1602 train 7.317803 (lr=1.4411e-04) (hash(x)=17173694) +1603 train 7.424255 (lr=1.4407e-04) (hash(x)=15717069) +1604 train 7.503296 (lr=1.4403e-04) (hash(x)=15117973) +1605 train 7.314172 (lr=1.4399e-04) (hash(x)=16189636) +1606 train 7.254157 (lr=1.4394e-04) (hash(x)=16552095) +1607 train 7.128944 (lr=1.4390e-04) (hash(x)=18463712) +1608 train 7.309889 (lr=1.4386e-04) (hash(x)=17572155) +1609 train 7.331039 (lr=1.4382e-04) (hash(x)=19970072) +1610 train 7.377097 (lr=1.4378e-04) (hash(x)=20463871) +1611 train 7.369695 (lr=1.4374e-04) (hash(x)=20705573) +1612 train 7.103568 (lr=1.4370e-04) (hash(x)=24441646) +1613 train 7.254089 (lr=1.4366e-04) (hash(x)=22913147) +1614 train 7.415686 (lr=1.4362e-04) (hash(x)=23081598) +1615 train 7.093077 (lr=1.4357e-04) (hash(x)=23245699) +1616 train 7.139076 (lr=1.4353e-04) (hash(x)=23003072) +1617 train 7.415761 (lr=1.4349e-04) (hash(x)=27121904) +1618 train 7.165211 (lr=1.4345e-04) (hash(x)=25092305) +1619 train 7.200574 (lr=1.4341e-04) (hash(x)=23444521) +1620 train 7.239195 (lr=1.4337e-04) (hash(x)=22130531) +1621 train 6.986836 (lr=1.4333e-04) (hash(x)=20917937) +1622 train 7.125830 (lr=1.4329e-04) (hash(x)=22526838) +1623 train 7.284450 (lr=1.4324e-04) (hash(x)=21770300) +1624 train 8.477878 (lr=1.4320e-04) (hash(x)=22333537) +1625 train 8.501363 (lr=1.4316e-04) (hash(x)=24642519) +1626 train 7.484694 (lr=1.4312e-04) (hash(x)=25199038) +1627 train 7.280428 (lr=1.4308e-04) (hash(x)=23334569) +1628 train 7.147497 (lr=1.4304e-04) (hash(x)=23785360) +1629 train 6.721237 (lr=1.4300e-04) (hash(x)=21796200) +1630 train 6.806113 (lr=1.4295e-04) (hash(x)=22389081) +1631 train 7.164170 (lr=1.4291e-04) (hash(x)=25387532) +1632 train 6.673847 (lr=1.4287e-04) (hash(x)=17247578) +1633 train 7.121597 (lr=1.4283e-04) (hash(x)=22203733) +1634 train 7.276097 (lr=1.4279e-04) (hash(x)=24387455) +1635 train 7.904243 (lr=1.4275e-04) (hash(x)=29466743) +1636 train 7.158227 (lr=1.4270e-04) (hash(x)=25354152) +1637 train 7.199369 (lr=1.4266e-04) (hash(x)=21756102) +1638 train 7.202077 (lr=1.4262e-04) (hash(x)=23544029) +1639 train 7.348789 (lr=1.4258e-04) (hash(x)=27718703) +1640 train 7.331100 (lr=1.4254e-04) (hash(x)=25697138) +1641 train 7.169995 (lr=1.4250e-04) (hash(x)=22978681) +1642 train 7.711208 (lr=1.4245e-04) (hash(x)=29527067) +1643 train 6.801210 (lr=1.4241e-04) (hash(x)=17631973) +1644 train 7.255404 (lr=1.4237e-04) (hash(x)=24860172) +1645 train 7.585113 (lr=1.4233e-04) (hash(x)=27947891) +1646 train 7.207083 (lr=1.4229e-04) (hash(x)=23819556) +1647 train 7.250712 (lr=1.4225e-04) (hash(x)=27661052) +1648 train 7.045279 (lr=1.4220e-04) (hash(x)=23014209) +1649 train 6.976224 (lr=1.4216e-04) (hash(x)=23061452) +1650 val loss 7.2327 +1650 val perplexity 1383.9764 +1650 train 7.102975 (lr=1.4212e-04) (hash(x)=21949051) +1651 train 7.167336 (lr=1.4208e-04) (hash(x)=22244096) +1652 train 7.131713 (lr=1.4204e-04) (hash(x)=25997585) +1653 train 7.223869 (lr=1.4199e-04) (hash(x)=25389713) +1654 train 7.146455 (lr=1.4195e-04) (hash(x)=24390520) +1655 train 7.440315 (lr=1.4191e-04) (hash(x)=26538928) +1656 train 7.372437 (lr=1.4187e-04) (hash(x)=28708088) +1657 train 7.444380 (lr=1.4183e-04) (hash(x)=25685569) +1658 train 6.948607 (lr=1.4178e-04) (hash(x)=22163531) +1659 train 7.144764 (lr=1.4174e-04) (hash(x)=26256802) +1660 train 7.607756 (lr=1.4170e-04) (hash(x)=30016026) +1661 train 7.193587 (lr=1.4166e-04) (hash(x)=24412323) +1662 train 7.227095 (lr=1.4162e-04) (hash(x)=24722307) +1663 train 7.090211 (lr=1.4157e-04) (hash(x)=21772654) +1664 train 7.055702 (lr=1.4153e-04) (hash(x)=24984527) +1665 train 7.210307 (lr=1.4149e-04) (hash(x)=25456825) +1666 train 7.560290 (lr=1.4145e-04) (hash(x)=24383976) +1667 train 7.449451 (lr=1.4141e-04) (hash(x)=25026277) +1668 train 7.370240 (lr=1.4136e-04) (hash(x)=28121715) +1669 train 7.344528 (lr=1.4132e-04) (hash(x)=26855439) +1670 train 7.460767 (lr=1.4128e-04) (hash(x)=33370924) +1671 train 7.285706 (lr=1.4124e-04) (hash(x)=26263254) +1672 train 7.763147 (lr=1.4119e-04) (hash(x)=29958158) +1673 train 7.008060 (lr=1.4115e-04) (hash(x)=21917396) +1674 train 7.171921 (lr=1.4111e-04) (hash(x)=24196295) +1675 train 7.234524 (lr=1.4107e-04) (hash(x)=24726314) +1676 train 7.001846 (lr=1.4102e-04) (hash(x)=22137742) +1677 train 7.125391 (lr=1.4098e-04) (hash(x)=24375100) +1678 train 7.054886 (lr=1.4094e-04) (hash(x)=23965039) +1679 train 7.125299 (lr=1.4090e-04) (hash(x)=23552356) +1680 train 7.117471 (lr=1.4085e-04) (hash(x)=26136969) +1681 train 7.389391 (lr=1.4081e-04) (hash(x)=25343112) +1682 train 7.026872 (lr=1.4077e-04) (hash(x)=22831508) +1683 train 7.367981 (lr=1.4073e-04) (hash(x)=26699819) +1684 train 7.473633 (lr=1.4068e-04) (hash(x)=25435504) +1685 train 7.632508 (lr=1.4064e-04) (hash(x)=25218858) +1686 train 8.249311 (lr=1.4060e-04) (hash(x)=25664448) +1687 train 7.266652 (lr=1.4056e-04) (hash(x)=22707141) +1688 train 7.482156 (lr=1.4051e-04) (hash(x)=28001383) +1689 train 7.727928 (lr=1.4047e-04) (hash(x)=29168269) +1690 train 7.638237 (lr=1.4043e-04) (hash(x)=29637522) +1691 train 7.691123 (lr=1.4039e-04) (hash(x)=25676149) +1692 train 7.063074 (lr=1.4034e-04) (hash(x)=20919831) +1693 train 7.283238 (lr=1.4030e-04) (hash(x)=24324401) +1694 train 7.395297 (lr=1.4026e-04) (hash(x)=26862625) +1695 train 7.787970 (lr=1.4022e-04) (hash(x)=34234481) +1696 train 7.368382 (lr=1.4017e-04) (hash(x)=27415195) +1697 train 7.175175 (lr=1.4013e-04) (hash(x)=24511386) +1698 train 7.287474 (lr=1.4009e-04) (hash(x)=26904299) +1699 train 7.115434 (lr=1.4004e-04) (hash(x)=25401624) +1700 val loss 7.2229 +1700 val perplexity 1370.5248 +1700 train 7.171596 (lr=1.4000e-04) (hash(x)=26498489) +1701 train 7.154315 (lr=1.3996e-04) (hash(x)=22340685) +1702 train 7.269772 (lr=1.3992e-04) (hash(x)=26396757) +1703 train 7.923628 (lr=1.3987e-04) (hash(x)=35008670) +1704 train 7.653439 (lr=1.3983e-04) (hash(x)=31782020) +1705 train 7.523108 (lr=1.3979e-04) (hash(x)=29662286) +1706 train 7.740974 (lr=1.3974e-04) (hash(x)=34215782) +1707 train 7.173633 (lr=1.3970e-04) (hash(x)=25682280) +1708 train 7.343117 (lr=1.3966e-04) (hash(x)=27109048) +1709 train 7.382634 (lr=1.3961e-04) (hash(x)=27686498) +1710 train 7.197780 (lr=1.3957e-04) (hash(x)=24247565) +1711 train 7.229847 (lr=1.3953e-04) (hash(x)=25891543) +1712 train 7.369087 (lr=1.3949e-04) (hash(x)=26436778) +1713 train 7.013275 (lr=1.3944e-04) (hash(x)=22538881) +1714 train 6.960244 (lr=1.3940e-04) (hash(x)=21993512) +1715 train 7.448772 (lr=1.3936e-04) (hash(x)=25962407) +1716 train 7.253677 (lr=1.3931e-04) (hash(x)=24130284) +1717 train 7.110980 (lr=1.3927e-04) (hash(x)=24819073) +1718 train 6.976471 (lr=1.3923e-04) (hash(x)=23496648) +1719 train 7.047193 (lr=1.3918e-04) (hash(x)=21971224) +1720 train 6.938325 (lr=1.3914e-04) (hash(x)=21498081) +1721 train 6.981894 (lr=1.3910e-04) (hash(x)=20951317) +1722 train 7.473367 (lr=1.3905e-04) (hash(x)=28848134) +1723 train 7.504057 (lr=1.3901e-04) (hash(x)=30838142) +1724 train 7.459508 (lr=1.3897e-04) (hash(x)=28844392) +1725 train 7.100942 (lr=1.3892e-04) (hash(x)=23102419) +1726 train 7.164283 (lr=1.3888e-04) (hash(x)=22374479) +1727 train 7.478405 (lr=1.3884e-04) (hash(x)=27312186) +1728 train 7.843576 (lr=1.3879e-04) (hash(x)=34362559) +1729 train 7.719636 (lr=1.3875e-04) (hash(x)=30920030) +1730 train 7.012643 (lr=1.3871e-04) (hash(x)=23684126) +1731 train 7.253380 (lr=1.3866e-04) (hash(x)=23657081) +1732 train 7.473459 (lr=1.3862e-04) (hash(x)=28463299) +1733 train 7.798875 (lr=1.3858e-04) (hash(x)=35351214) +1734 train 7.312026 (lr=1.3853e-04) (hash(x)=28855662) +1735 train 6.803376 (lr=1.3849e-04) (hash(x)=22163749) +1736 train 6.833416 (lr=1.3845e-04) (hash(x)=22024585) +1737 train 7.078853 (lr=1.3840e-04) (hash(x)=24629160) +1738 train 7.171353 (lr=1.3836e-04) (hash(x)=25220941) +1739 train 7.097988 (lr=1.3832e-04) (hash(x)=24829818) +1740 train 7.514937 (lr=1.3827e-04) (hash(x)=28453898) +1741 train 7.507425 (lr=1.3823e-04) (hash(x)=25424550) +1742 train 7.088178 (lr=1.3818e-04) (hash(x)=23437814) +1743 train 7.223357 (lr=1.3814e-04) (hash(x)=25942888) +1744 train 7.176256 (lr=1.3810e-04) (hash(x)=24503801) +1745 train 7.505739 (lr=1.3805e-04) (hash(x)=26418501) +1746 train 7.393577 (lr=1.3801e-04) (hash(x)=27177691) +1747 train 7.065845 (lr=1.3797e-04) (hash(x)=23785671) +1748 train 7.519589 (lr=1.3792e-04) (hash(x)=27362772) +1749 train 7.251195 (lr=1.3788e-04) (hash(x)=25097859) +1750 val loss 7.2298 +1750 val perplexity 1379.9487 +1750 train 7.202635 (lr=1.3784e-04) (hash(x)=24662466) +1751 train 7.112533 (lr=1.3779e-04) (hash(x)=25493916) +1752 train 7.216611 (lr=1.3775e-04) (hash(x)=24655868) +1753 train 7.412010 (lr=1.3770e-04) (hash(x)=19819210) +1754 train 7.070728 (lr=1.3766e-04) (hash(x)=21377155) +1755 train 7.932849 (lr=1.3762e-04) (hash(x)=28618702) +1756 train 7.800925 (lr=1.3757e-04) (hash(x)=27324953) +1757 train 7.536589 (lr=1.3753e-04) (hash(x)=29707907) +1758 train 7.252523 (lr=1.3748e-04) (hash(x)=24485921) +1759 train 7.335941 (lr=1.3744e-04) (hash(x)=24289951) +1760 train 7.031780 (lr=1.3740e-04) (hash(x)=22496716) +1761 train 7.209114 (lr=1.3735e-04) (hash(x)=25147026) +1762 train 7.298314 (lr=1.3731e-04) (hash(x)=26851828) +1763 train 7.273596 (lr=1.3726e-04) (hash(x)=26331486) +1764 train 7.112552 (lr=1.3722e-04) (hash(x)=24383054) +1765 train 7.345064 (lr=1.3718e-04) (hash(x)=25885126) +1766 train 7.319589 (lr=1.3713e-04) (hash(x)=25848470) +1767 train 7.095899 (lr=1.3709e-04) (hash(x)=23648671) +1768 train 7.030211 (lr=1.3704e-04) (hash(x)=23168674) +1769 train 6.878583 (lr=1.3700e-04) (hash(x)=20252079) +1770 train 7.127144 (lr=1.3696e-04) (hash(x)=23914287) +1771 train 7.439570 (lr=1.3691e-04) (hash(x)=27292797) +1772 train 6.515680 (lr=1.3687e-04) (hash(x)=16175151) +1773 train 6.718044 (lr=1.3682e-04) (hash(x)=18317379) +1774 train 7.149910 (lr=1.3678e-04) (hash(x)=24464271) +1775 train 7.099013 (lr=1.3674e-04) (hash(x)=24992055) +1776 train 7.800603 (lr=1.3669e-04) (hash(x)=26032451) +1777 train 7.522977 (lr=1.3665e-04) (hash(x)=24734221) +1778 train 7.490097 (lr=1.3660e-04) (hash(x)=25413430) +1779 train 7.357510 (lr=1.3656e-04) (hash(x)=24398330) +1780 train 7.239010 (lr=1.3651e-04) (hash(x)=24568049) +1781 train 7.062538 (lr=1.3647e-04) (hash(x)=23573984) +1782 train 7.339391 (lr=1.3643e-04) (hash(x)=27338410) +1783 train 7.261046 (lr=1.3638e-04) (hash(x)=26005549) +1784 train 7.090749 (lr=1.3634e-04) (hash(x)=24332331) +1785 train 6.952785 (lr=1.3629e-04) (hash(x)=22583878) +1786 train 7.131565 (lr=1.3625e-04) (hash(x)=24599113) +1787 train 7.627389 (lr=1.3620e-04) (hash(x)=30259737) +1788 train 7.391058 (lr=1.3616e-04) (hash(x)=26504237) +1789 train 7.222547 (lr=1.3611e-04) (hash(x)=25196470) +1790 train 7.148318 (lr=1.3607e-04) (hash(x)=23607871) +1791 train 7.038124 (lr=1.3603e-04) (hash(x)=21046554) +1792 train 7.325368 (lr=1.3598e-04) (hash(x)=27285635) +1793 train 7.327103 (lr=1.3594e-04) (hash(x)=25454371) +1794 train 7.364933 (lr=1.3589e-04) (hash(x)=26486575) +1795 train 6.759193 (lr=1.3585e-04) (hash(x)=18773877) +1796 train 6.950131 (lr=1.3580e-04) (hash(x)=22506761) +1797 train 7.278678 (lr=1.3576e-04) (hash(x)=24645168) +1798 train 7.379448 (lr=1.3571e-04) (hash(x)=25046236) +1799 train 7.455217 (lr=1.3567e-04) (hash(x)=26321539) +1800 val loss 7.2256 +1800 val perplexity 1374.2288 +1800 train 7.139944 (lr=1.3563e-04) (hash(x)=24602494) +1801 train 7.348663 (lr=1.3558e-04) (hash(x)=25722713) +1802 train 7.050003 (lr=1.3554e-04) (hash(x)=23711219) +1803 train 7.203058 (lr=1.3549e-04) (hash(x)=22850804) +1804 train 7.573431 (lr=1.3545e-04) (hash(x)=25829388) +1805 train 7.028386 (lr=1.3540e-04) (hash(x)=22503524) +1806 train 7.325429 (lr=1.3536e-04) (hash(x)=26669453) +1807 train 7.248247 (lr=1.3531e-04) (hash(x)=27807872) +1808 train 7.236740 (lr=1.3527e-04) (hash(x)=23543560) +1809 train 7.388327 (lr=1.3522e-04) (hash(x)=25845590) +1810 train 7.137193 (lr=1.3518e-04) (hash(x)=23026635) +1811 train 7.126706 (lr=1.3513e-04) (hash(x)=25545137) +1812 train 7.609953 (lr=1.3509e-04) (hash(x)=27746841) +1813 train 6.992228 (lr=1.3504e-04) (hash(x)=25471231) +1814 train 7.121476 (lr=1.3500e-04) (hash(x)=24333204) +1815 train 6.959796 (lr=1.3495e-04) (hash(x)=21555364) +1816 train 7.230049 (lr=1.3491e-04) (hash(x)=26317977) +1817 train 7.261989 (lr=1.3486e-04) (hash(x)=24474988) +1818 train 6.901631 (lr=1.3482e-04) (hash(x)=21975953) +1819 train 7.588350 (lr=1.3477e-04) (hash(x)=27243798) +1820 train 7.202996 (lr=1.3473e-04) (hash(x)=25097367) +1821 train 7.059604 (lr=1.3468e-04) (hash(x)=24419085) +1822 train 7.041627 (lr=1.3464e-04) (hash(x)=23058837) +1823 train 7.172251 (lr=1.3459e-04) (hash(x)=26325324) +1824 train 6.891835 (lr=1.3455e-04) (hash(x)=20581023) +1825 train 7.253201 (lr=1.3450e-04) (hash(x)=24822111) +1826 train 7.007009 (lr=1.3446e-04) (hash(x)=24336304) +1827 train 7.181591 (lr=1.3441e-04) (hash(x)=26228728) +1828 train 7.277771 (lr=1.3437e-04) (hash(x)=26445781) +1829 train 7.394415 (lr=1.3432e-04) (hash(x)=24707042) +1830 train 7.659291 (lr=1.3428e-04) (hash(x)=27882744) +1831 train 7.151962 (lr=1.3423e-04) (hash(x)=24956294) +1832 train 6.894830 (lr=1.3419e-04) (hash(x)=20984728) +1833 train 6.972859 (lr=1.3414e-04) (hash(x)=23424737) +1834 train 7.374654 (lr=1.3410e-04) (hash(x)=26207120) +1835 train 7.385252 (lr=1.3405e-04) (hash(x)=25592289) +1836 train 7.077878 (lr=1.3401e-04) (hash(x)=24326649) +1837 train 7.194913 (lr=1.3396e-04) (hash(x)=26826109) +1838 train 7.210364 (lr=1.3392e-04) (hash(x)=24759294) +1839 train 7.237764 (lr=1.3387e-04) (hash(x)=24429389) +1840 train 7.147464 (lr=1.3383e-04) (hash(x)=25537519) +1841 train 7.111665 (lr=1.3378e-04) (hash(x)=24747421) +1842 train 7.045317 (lr=1.3374e-04) (hash(x)=23079065) +1843 train 7.500516 (lr=1.3369e-04) (hash(x)=28733708) +1844 train 7.173015 (lr=1.3364e-04) (hash(x)=23937742) +1845 train 7.531503 (lr=1.3360e-04) (hash(x)=29704803) +1846 train 7.687558 (lr=1.3355e-04) (hash(x)=34617155) +1847 train 7.362559 (lr=1.3351e-04) (hash(x)=27929846) +1848 train 7.705171 (lr=1.3346e-04) (hash(x)=28280878) +1849 train 6.670125 (lr=1.3342e-04) (hash(x)=18961171) +1850 val loss 7.2101 +1850 val perplexity 1352.9697 +1850 train 7.300223 (lr=1.3337e-04) (hash(x)=27146015) +1851 train 7.087097 (lr=1.3333e-04) (hash(x)=22417476) +1852 train 7.243867 (lr=1.3328e-04) (hash(x)=24583152) +1853 train 7.277690 (lr=1.3324e-04) (hash(x)=26364120) +1854 train 7.432983 (lr=1.3319e-04) (hash(x)=25946767) +1855 train 7.279851 (lr=1.3315e-04) (hash(x)=25282897) +1856 train 7.227619 (lr=1.3310e-04) (hash(x)=25154557) +1857 train 6.876026 (lr=1.3305e-04) (hash(x)=22082503) +1858 train 6.967098 (lr=1.3301e-04) (hash(x)=23974606) +1859 train 7.097215 (lr=1.3296e-04) (hash(x)=22278062) +1860 train 7.057922 (lr=1.3292e-04) (hash(x)=19509639) +1861 train 7.328331 (lr=1.3287e-04) (hash(x)=24271468) +1862 train 6.870406 (lr=1.3283e-04) (hash(x)=21943809) +1863 train 7.148587 (lr=1.3278e-04) (hash(x)=26802508) +1864 train 7.784807 (lr=1.3273e-04) (hash(x)=34178409) +1865 train 7.898849 (lr=1.3269e-04) (hash(x)=33468379) +1866 train 7.022884 (lr=1.3264e-04) (hash(x)=22109262) +1867 train 6.736211 (lr=1.3260e-04) (hash(x)=22094832) +1868 train 7.066391 (lr=1.3255e-04) (hash(x)=24016953) +1869 train 7.356413 (lr=1.3251e-04) (hash(x)=26759850) +1870 train 7.137595 (lr=1.3246e-04) (hash(x)=23570779) +1871 train 7.632535 (lr=1.3241e-04) (hash(x)=28390416) +1872 train 7.642961 (lr=1.3237e-04) (hash(x)=26215770) +1873 train 7.493005 (lr=1.3232e-04) (hash(x)=22727956) +1874 train 7.284837 (lr=1.3228e-04) (hash(x)=21304587) +1875 train 7.586081 (lr=1.3223e-04) (hash(x)=26379331) +1876 train 7.673052 (lr=1.3219e-04) (hash(x)=25252419) +1877 train 7.496334 (lr=1.3214e-04) (hash(x)=25048158) +1878 train 7.428970 (lr=1.3209e-04) (hash(x)=23588991) +1879 train 7.441842 (lr=1.3205e-04) (hash(x)=26292451) +1880 train 7.305914 (lr=1.3200e-04) (hash(x)=23617086) +1881 train 7.183995 (lr=1.3196e-04) (hash(x)=23336031) +1882 train 7.130594 (lr=1.3191e-04) (hash(x)=19198742) +1883 train 7.877135 (lr=1.3186e-04) (hash(x)=26301866) +1884 train 7.781803 (lr=1.3182e-04) (hash(x)=30114703) +1885 train 7.328207 (lr=1.3177e-04) (hash(x)=26687040) +1886 train 7.152738 (lr=1.3173e-04) (hash(x)=25810717) +1887 train 6.955141 (lr=1.3168e-04) (hash(x)=22915344) +1888 train 7.334555 (lr=1.3163e-04) (hash(x)=27046189) +1889 train 6.916052 (lr=1.3159e-04) (hash(x)=19831900) +1890 train 7.315692 (lr=1.3154e-04) (hash(x)=27786987) +1891 train 7.185688 (lr=1.3150e-04) (hash(x)=25448318) +1892 train 7.218239 (lr=1.3145e-04) (hash(x)=25166953) +1893 train 7.187833 (lr=1.3140e-04) (hash(x)=24993116) +1894 train 7.251340 (lr=1.3136e-04) (hash(x)=25748002) +1895 train 7.484659 (lr=1.3131e-04) (hash(x)=24744383) +1896 train 7.209352 (lr=1.3127e-04) (hash(x)=25560120) +1897 train 7.026508 (lr=1.3122e-04) (hash(x)=23731849) +1898 train 7.013347 (lr=1.3117e-04) (hash(x)=24115851) +1899 train 7.056390 (lr=1.3113e-04) (hash(x)=22835201) +1900 val loss 7.1924 +1900 val perplexity 1329.2357 +1900 train 6.795841 (lr=1.3108e-04) (hash(x)=21927896) +1901 train 7.262439 (lr=1.3103e-04) (hash(x)=24652361) +1902 train 7.435998 (lr=1.3099e-04) (hash(x)=27332405) +1903 train 7.217870 (lr=1.3094e-04) (hash(x)=26284678) +1904 train 7.162474 (lr=1.3090e-04) (hash(x)=23441305) +1905 train 7.242784 (lr=1.3085e-04) (hash(x)=27522881) +1906 train 7.313230 (lr=1.3080e-04) (hash(x)=25521191) +1907 train 7.086790 (lr=1.3076e-04) (hash(x)=24745936) +1908 train 6.958604 (lr=1.3071e-04) (hash(x)=21653364) +1909 train 7.024893 (lr=1.3066e-04) (hash(x)=21973969) +1910 train 7.018456 (lr=1.3062e-04) (hash(x)=24318192) +1911 train 6.973849 (lr=1.3057e-04) (hash(x)=21654269) +1912 train 7.026785 (lr=1.3052e-04) (hash(x)=24142904) +1913 train 6.936176 (lr=1.3048e-04) (hash(x)=21708739) +1914 train 7.178764 (lr=1.3043e-04) (hash(x)=22937923) +1915 train 7.752532 (lr=1.3039e-04) (hash(x)=32387999) +1916 train 7.939316 (lr=1.3034e-04) (hash(x)=28958671) +1917 train 7.984092 (lr=1.3029e-04) (hash(x)=32662682) +1918 train 7.874176 (lr=1.3025e-04) (hash(x)=31364539) +1919 train 7.962125 (lr=1.3020e-04) (hash(x)=29466268) +1920 train 7.934254 (lr=1.3015e-04) (hash(x)=31407564) +1921 train 7.762949 (lr=1.3011e-04) (hash(x)=28372973) +1922 train 7.902223 (lr=1.3006e-04) (hash(x)=28620993) +1923 train 7.944328 (lr=1.3001e-04) (hash(x)=30736727) +1924 train 7.857098 (lr=1.2997e-04) (hash(x)=30370374) +1925 train 7.789908 (lr=1.2992e-04) (hash(x)=29935562) +1926 train 7.799755 (lr=1.2987e-04) (hash(x)=30528627) +1927 train 7.823196 (lr=1.2983e-04) (hash(x)=32616762) +1928 train 7.676139 (lr=1.2978e-04) (hash(x)=29150044) +1929 train 7.846957 (lr=1.2973e-04) (hash(x)=32861403) +1930 train 7.752257 (lr=1.2969e-04) (hash(x)=31053918) +1931 train 7.677280 (lr=1.2964e-04) (hash(x)=29358578) +1932 train 7.761977 (lr=1.2959e-04) (hash(x)=31521292) +1933 train 7.745698 (lr=1.2955e-04) (hash(x)=31218966) +1934 train 7.764627 (lr=1.2950e-04) (hash(x)=31811872) +1935 train 7.933795 (lr=1.2945e-04) (hash(x)=32201138) +1936 train 7.655651 (lr=1.2941e-04) (hash(x)=28631348) +1937 train 7.723119 (lr=1.2936e-04) (hash(x)=30545133) +1938 train 7.767137 (lr=1.2931e-04) (hash(x)=32136080) +1939 train 7.838194 (lr=1.2927e-04) (hash(x)=30041621) +1940 train 7.632572 (lr=1.2922e-04) (hash(x)=30537181) +1941 train 7.651428 (lr=1.2917e-04) (hash(x)=30371023) +1942 train 7.763472 (lr=1.2913e-04) (hash(x)=30734634) +1943 train 7.728037 (lr=1.2908e-04) (hash(x)=33683468) +1944 train 7.772049 (lr=1.2903e-04) (hash(x)=30472451) +1945 train 7.582921 (lr=1.2899e-04) (hash(x)=29809830) +1946 train 7.381126 (lr=1.2894e-04) (hash(x)=26077593) +1947 train 7.391232 (lr=1.2889e-04) (hash(x)=26837755) +1948 train 7.333454 (lr=1.2884e-04) (hash(x)=23910920) +1949 train 7.335709 (lr=1.2880e-04) (hash(x)=26084089) +1950 val loss 7.2868 +1950 val perplexity 1460.8408 +1950 train 7.505495 (lr=1.2875e-04) (hash(x)=26963533) +1951 train 7.365032 (lr=1.2870e-04) (hash(x)=27498125) +1952 train 7.520912 (lr=1.2866e-04) (hash(x)=29512508) +1953 train 7.759078 (lr=1.2861e-04) (hash(x)=34478395) +1954 train 7.431064 (lr=1.2856e-04) (hash(x)=25357046) +1955 train 7.213615 (lr=1.2852e-04) (hash(x)=22372507) +1956 train 7.167297 (lr=1.2847e-04) (hash(x)=24501779) +1957 train 7.248073 (lr=1.2842e-04) (hash(x)=25638879) +1958 train 7.093545 (lr=1.2837e-04) (hash(x)=24243109) +1959 train 7.047056 (lr=1.2833e-04) (hash(x)=25164318) +1960 train 7.242770 (lr=1.2828e-04) (hash(x)=24139533) +1961 train 7.217906 (lr=1.2823e-04) (hash(x)=27271900) +1962 train 7.056436 (lr=1.2819e-04) (hash(x)=24869232) +1963 train 7.267892 (lr=1.2814e-04) (hash(x)=26562947) +1964 train 7.153735 (lr=1.2809e-04) (hash(x)=26477326) +1965 train 7.257887 (lr=1.2804e-04) (hash(x)=24917192) +1966 train 7.009139 (lr=1.2800e-04) (hash(x)=23110147) +1967 train 7.123291 (lr=1.2795e-04) (hash(x)=25690221) +1968 train 7.613416 (lr=1.2790e-04) (hash(x)=26999273) +1969 train 7.229627 (lr=1.2786e-04) (hash(x)=24807841) +1970 train 7.119017 (lr=1.2781e-04) (hash(x)=23918831) +1971 train 7.037689 (lr=1.2776e-04) (hash(x)=21947305) +1972 train 7.126740 (lr=1.2771e-04) (hash(x)=22874486) +1973 train 7.010978 (lr=1.2767e-04) (hash(x)=22195089) +1974 train 7.159554 (lr=1.2762e-04) (hash(x)=25345359) +1975 train 7.341095 (lr=1.2757e-04) (hash(x)=29031550) +1976 train 7.272713 (lr=1.2753e-04) (hash(x)=29947423) +1977 train 7.451923 (lr=1.2748e-04) (hash(x)=29395823) +1978 train 7.246927 (lr=1.2743e-04) (hash(x)=26968216) +1979 train 7.270454 (lr=1.2738e-04) (hash(x)=26551589) +1980 train 7.239296 (lr=1.2734e-04) (hash(x)=25657210) +1981 train 7.200113 (lr=1.2729e-04) (hash(x)=23689487) +1982 train 7.291115 (lr=1.2724e-04) (hash(x)=25744240) +1983 train 7.273978 (lr=1.2719e-04) (hash(x)=24094093) +1984 train 6.967029 (lr=1.2715e-04) (hash(x)=21724872) +1985 train 7.061882 (lr=1.2710e-04) (hash(x)=24106453) +1986 train 7.127153 (lr=1.2705e-04) (hash(x)=25004577) +1987 train 7.110184 (lr=1.2700e-04) (hash(x)=23639076) +1988 train 7.425650 (lr=1.2696e-04) (hash(x)=29408797) +1989 train 7.034615 (lr=1.2691e-04) (hash(x)=25107314) +1990 train 9.562436 (lr=1.2686e-04) (hash(x)=49896019) +1991 train 10.941291 (lr=1.2681e-04) (hash(x)=61455960) +1992 train 10.671782 (lr=1.2677e-04) (hash(x)=63788199) +1993 train 10.603959 (lr=1.2672e-04) (hash(x)=63899424) +1994 train 10.275154 (lr=1.2667e-04) (hash(x)=66412689) +1995 train 9.858528 (lr=1.2662e-04) (hash(x)=65636572) +1996 train 9.904015 (lr=1.2658e-04) (hash(x)=69649789) +1997 train 9.617710 (lr=1.2653e-04) (hash(x)=71578682) +1998 train 8.954453 (lr=1.2648e-04) (hash(x)=58341730) +1999 train 8.954882 (lr=1.2643e-04) (hash(x)=61104710) +2000 val loss 8.1082 +2000 val perplexity 3321.4355 +2000 train 8.664612 (lr=1.2639e-04) (hash(x)=52865322) +2001 train 8.317512 (lr=1.2634e-04) (hash(x)=23633693) +2002 train 7.971401 (lr=1.2629e-04) (hash(x)=25297571) +2003 train 8.165484 (lr=1.2624e-04) (hash(x)=24123821) +2004 train 7.270192 (lr=1.2620e-04) (hash(x)=20161517) +2005 train 7.114407 (lr=1.2615e-04) (hash(x)=19919984) +2006 train 7.035583 (lr=1.2610e-04) (hash(x)=18626507) +2007 train 7.185970 (lr=1.2605e-04) (hash(x)=20881126) +2008 train 7.346191 (lr=1.2600e-04) (hash(x)=26261448) +2009 train 7.512371 (lr=1.2596e-04) (hash(x)=27528050) +2010 train 7.534325 (lr=1.2591e-04) (hash(x)=26692097) +2011 train 7.252133 (lr=1.2586e-04) (hash(x)=23209969) +2012 train 7.238327 (lr=1.2581e-04) (hash(x)=26083446) +2013 train 7.535777 (lr=1.2577e-04) (hash(x)=28426467) +2014 train 7.333952 (lr=1.2572e-04) (hash(x)=26158154) +2015 train 7.474695 (lr=1.2567e-04) (hash(x)=26920243) +2016 train 7.149426 (lr=1.2562e-04) (hash(x)=21365321) +2017 train 7.231088 (lr=1.2557e-04) (hash(x)=25730699) +2018 train 7.323392 (lr=1.2553e-04) (hash(x)=25177106) +2019 train 7.179190 (lr=1.2548e-04) (hash(x)=26127756) +2020 train 6.685746 (lr=1.2543e-04) (hash(x)=19770037) +2021 train 7.194377 (lr=1.2538e-04) (hash(x)=26479346) +2022 train 7.192195 (lr=1.2534e-04) (hash(x)=25967643) +2023 train 7.119737 (lr=1.2529e-04) (hash(x)=21970343) +2024 train 7.364023 (lr=1.2524e-04) (hash(x)=26449648) +2025 train 7.280899 (lr=1.2519e-04) (hash(x)=24874094) +2026 train 6.887901 (lr=1.2514e-04) (hash(x)=21399697) +2027 train 7.145041 (lr=1.2510e-04) (hash(x)=24097897) +2028 train 7.195076 (lr=1.2505e-04) (hash(x)=24453548) +2029 train 7.305523 (lr=1.2500e-04) (hash(x)=26692093) +2030 train 7.121979 (lr=1.2495e-04) (hash(x)=27217002) +2031 train 7.529012 (lr=1.2490e-04) (hash(x)=31676352) +2032 train 7.183279 (lr=1.2486e-04) (hash(x)=23396350) +2033 train 7.204298 (lr=1.2481e-04) (hash(x)=26245173) +2034 train 7.214088 (lr=1.2476e-04) (hash(x)=24821033) +2035 train 7.276561 (lr=1.2471e-04) (hash(x)=23908053) +2036 train 6.989641 (lr=1.2466e-04) (hash(x)=23469373) +2037 train 7.055687 (lr=1.2462e-04) (hash(x)=24102198) +2038 train 7.115652 (lr=1.2457e-04) (hash(x)=24712135) +2039 train 7.372444 (lr=1.2452e-04) (hash(x)=25600562) +2040 train 7.288224 (lr=1.2447e-04) (hash(x)=23193393) +2041 train 7.263266 (lr=1.2442e-04) (hash(x)=24776954) +2042 train 7.394853 (lr=1.2438e-04) (hash(x)=28066546) +2043 train 6.984076 (lr=1.2433e-04) (hash(x)=23549168) +2044 train 7.009393 (lr=1.2428e-04) (hash(x)=22681487) +2045 train 7.236278 (lr=1.2423e-04) (hash(x)=26663184) +2046 train 7.137058 (lr=1.2418e-04) (hash(x)=23320809) +2047 train 7.036510 (lr=1.2413e-04) (hash(x)=22022924) +2048 train 7.397393 (lr=1.2409e-04) (hash(x)=27960930) +2049 train 7.162697 (lr=1.2404e-04) (hash(x)=24899178) +2050 val loss 7.1864 +2050 val perplexity 1321.3623 +2050 train 7.075012 (lr=1.2399e-04) (hash(x)=24450711) +2051 train 7.014728 (lr=1.2394e-04) (hash(x)=23294980) +2052 train 6.926003 (lr=1.2389e-04) (hash(x)=23243665) +2053 train 6.747998 (lr=1.2384e-04) (hash(x)=21004461) +2054 train 7.145402 (lr=1.2380e-04) (hash(x)=24493583) +2055 train 7.053000 (lr=1.2375e-04) (hash(x)=22777085) +2056 train 7.000822 (lr=1.2370e-04) (hash(x)=25169889) +2057 train 7.652785 (lr=1.2365e-04) (hash(x)=28395880) +2058 train 7.564177 (lr=1.2360e-04) (hash(x)=29603726) +2059 train 7.258667 (lr=1.2356e-04) (hash(x)=26271115) +2060 train 7.203855 (lr=1.2351e-04) (hash(x)=25616212) +2061 train 7.303323 (lr=1.2346e-04) (hash(x)=26398325) +2062 train 6.964115 (lr=1.2341e-04) (hash(x)=23836586) +2063 train 6.845136 (lr=1.2336e-04) (hash(x)=21727744) +2064 train 7.140051 (lr=1.2331e-04) (hash(x)=25183195) +2065 train 7.274280 (lr=1.2326e-04) (hash(x)=27108132) +2066 train 6.935452 (lr=1.2322e-04) (hash(x)=20987812) +2067 train 7.302111 (lr=1.2317e-04) (hash(x)=22729318) +2068 train 7.085506 (lr=1.2312e-04) (hash(x)=23129709) +2069 train 7.664187 (lr=1.2307e-04) (hash(x)=32820084) +2070 train 7.707558 (lr=1.2302e-04) (hash(x)=33763489) +2071 train 7.138307 (lr=1.2297e-04) (hash(x)=20701998) +2072 train 7.345096 (lr=1.2293e-04) (hash(x)=27765988) +2073 train 7.088323 (lr=1.2288e-04) (hash(x)=24157446) +2074 train 7.026555 (lr=1.2283e-04) (hash(x)=22014978) +2075 train 7.546835 (lr=1.2278e-04) (hash(x)=27928398) +2076 train 7.378767 (lr=1.2273e-04) (hash(x)=27880142) +2077 train 7.734351 (lr=1.2268e-04) (hash(x)=34991795) +2078 train 7.256163 (lr=1.2263e-04) (hash(x)=25944128) +2079 train 6.943766 (lr=1.2259e-04) (hash(x)=20863982) +2080 train 7.414781 (lr=1.2254e-04) (hash(x)=28036097) +2081 train 7.443410 (lr=1.2249e-04) (hash(x)=25813615) +2082 train 6.839360 (lr=1.2244e-04) (hash(x)=22862316) +2083 train 6.934859 (lr=1.2239e-04) (hash(x)=22827054) +2084 train 7.015913 (lr=1.2234e-04) (hash(x)=23996531) +2085 train 7.144403 (lr=1.2229e-04) (hash(x)=25756087) +2086 train 7.183532 (lr=1.2225e-04) (hash(x)=23165889) +2087 train 7.374521 (lr=1.2220e-04) (hash(x)=25084926) +2088 train 7.214917 (lr=1.2215e-04) (hash(x)=26063862) +2089 train 7.251738 (lr=1.2210e-04) (hash(x)=27843638) +2090 train 7.532813 (lr=1.2205e-04) (hash(x)=27375554) +2091 train 7.299141 (lr=1.2200e-04) (hash(x)=25540961) +2092 train 7.006586 (lr=1.2195e-04) (hash(x)=22933785) +2093 train 7.189813 (lr=1.2190e-04) (hash(x)=23996956) +2094 train 6.876276 (lr=1.2186e-04) (hash(x)=22915854) +2095 train 7.164136 (lr=1.2181e-04) (hash(x)=24412897) +2096 train 7.199939 (lr=1.2176e-04) (hash(x)=25152336) +2097 train 7.532398 (lr=1.2171e-04) (hash(x)=29525589) +2098 train 7.361145 (lr=1.2166e-04) (hash(x)=26435656) +2099 train 7.222747 (lr=1.2161e-04) (hash(x)=26269869) +2100 val loss 7.1663 +2100 val perplexity 1295.0148 +2100 train 6.995104 (lr=1.2156e-04) (hash(x)=23856783) +2101 train 7.258359 (lr=1.2151e-04) (hash(x)=26039611) +2102 train 6.992233 (lr=1.2147e-04) (hash(x)=25048861) +2103 train 7.149225 (lr=1.2142e-04) (hash(x)=25434913) +2104 train 7.277534 (lr=1.2137e-04) (hash(x)=24203891) +2105 train 7.169728 (lr=1.2132e-04) (hash(x)=26016998) +2106 train 7.256017 (lr=1.2127e-04) (hash(x)=23986767) +2107 train 7.189711 (lr=1.2122e-04) (hash(x)=25157653) +2108 train 7.359025 (lr=1.2117e-04) (hash(x)=30193751) +2109 train 7.181992 (lr=1.2112e-04) (hash(x)=22630574) +2110 train 7.027831 (lr=1.2107e-04) (hash(x)=23475467) +2111 train 7.309285 (lr=1.2103e-04) (hash(x)=26302544) +2112 train 7.125993 (lr=1.2098e-04) (hash(x)=21276592) +2113 train 7.380962 (lr=1.2093e-04) (hash(x)=27566393) +2114 train 7.092500 (lr=1.2088e-04) (hash(x)=25028015) +2115 train 6.872937 (lr=1.2083e-04) (hash(x)=22010703) +2116 train 7.224542 (lr=1.2078e-04) (hash(x)=23711709) +2117 train 7.260895 (lr=1.2073e-04) (hash(x)=26105026) +2118 train 7.728166 (lr=1.2068e-04) (hash(x)=34433894) +2119 train 7.783975 (lr=1.2063e-04) (hash(x)=34976197) +2120 train 7.234260 (lr=1.2059e-04) (hash(x)=27690727) +2121 train 7.058824 (lr=1.2054e-04) (hash(x)=24368234) +2122 train 7.033279 (lr=1.2049e-04) (hash(x)=25095726) +2123 train 7.261145 (lr=1.2044e-04) (hash(x)=28248301) +2124 train 6.944487 (lr=1.2039e-04) (hash(x)=23322302) +2125 train 7.427849 (lr=1.2034e-04) (hash(x)=26416200) +2126 train 7.090233 (lr=1.2029e-04) (hash(x)=26577567) +2127 train 7.138910 (lr=1.2024e-04) (hash(x)=23870805) +2128 train 7.053777 (lr=1.2019e-04) (hash(x)=25440544) +2129 train 7.183734 (lr=1.2014e-04) (hash(x)=25795021) +2130 train 6.987785 (lr=1.2009e-04) (hash(x)=20896402) +2131 train 7.070447 (lr=1.2005e-04) (hash(x)=24457252) +2132 train 7.165120 (lr=1.2000e-04) (hash(x)=25926760) +2133 train 7.017775 (lr=1.1995e-04) (hash(x)=23503725) +2134 train 7.608032 (lr=1.1990e-04) (hash(x)=28728828) +2135 train 7.089996 (lr=1.1985e-04) (hash(x)=25041103) +2136 train 7.110245 (lr=1.1980e-04) (hash(x)=22863770) +2137 train 6.950591 (lr=1.1975e-04) (hash(x)=23037755) +2138 train 7.209898 (lr=1.1970e-04) (hash(x)=25848413) +2139 train 7.241037 (lr=1.1965e-04) (hash(x)=25998487) +2140 train 7.073767 (lr=1.1960e-04) (hash(x)=22754440) +2141 train 7.365823 (lr=1.1955e-04) (hash(x)=27705382) +2142 train 7.400772 (lr=1.1950e-04) (hash(x)=27629095) +2143 train 7.248607 (lr=1.1945e-04) (hash(x)=26041745) +2144 train 7.003661 (lr=1.1941e-04) (hash(x)=21909712) +2145 train 7.174825 (lr=1.1936e-04) (hash(x)=24353905) +2146 train 7.130042 (lr=1.1931e-04) (hash(x)=24482587) +2147 train 7.212151 (lr=1.1926e-04) (hash(x)=27249810) +2148 train 7.379567 (lr=1.1921e-04) (hash(x)=26709938) +2149 train 6.991316 (lr=1.1916e-04) (hash(x)=23831457) +2150 val loss 7.1288 +2150 val perplexity 1247.3678 +2150 train 7.398417 (lr=1.1911e-04) (hash(x)=29776243) +2151 train 6.875792 (lr=1.1906e-04) (hash(x)=24068619) +2152 train 7.057687 (lr=1.1901e-04) (hash(x)=22208671) +2153 train 7.236943 (lr=1.1896e-04) (hash(x)=26680905) +2154 train 7.115276 (lr=1.1891e-04) (hash(x)=23567808) +2155 train 7.367845 (lr=1.1886e-04) (hash(x)=26359528) +2156 train 7.169439 (lr=1.1881e-04) (hash(x)=23787652) +2157 train 7.464867 (lr=1.1876e-04) (hash(x)=28347177) +2158 train 7.131497 (lr=1.1872e-04) (hash(x)=25266519) +2159 train 7.047608 (lr=1.1867e-04) (hash(x)=25441262) +2160 train 6.962095 (lr=1.1862e-04) (hash(x)=23959943) +2161 train 7.230023 (lr=1.1857e-04) (hash(x)=27888093) +2162 train 7.124601 (lr=1.1852e-04) (hash(x)=25547833) +2163 train 7.055371 (lr=1.1847e-04) (hash(x)=24413659) +2164 train 8.603147 (lr=1.1842e-04) (hash(x)=34397626) +2165 train 6.978024 (lr=1.1837e-04) (hash(x)=21159323) +2166 train 7.167279 (lr=1.1832e-04) (hash(x)=25360269) +2167 train 7.238690 (lr=1.1827e-04) (hash(x)=29181867) +2168 train 7.055978 (lr=1.1822e-04) (hash(x)=22501613) +2169 train 7.134708 (lr=1.1817e-04) (hash(x)=26469077) +2170 train 7.090793 (lr=1.1812e-04) (hash(x)=26665118) +2171 train 7.770927 (lr=1.1807e-04) (hash(x)=31551575) +2172 train 7.044282 (lr=1.1802e-04) (hash(x)=24803935) +2173 train 6.921672 (lr=1.1797e-04) (hash(x)=20896465) +2174 train 7.371375 (lr=1.1792e-04) (hash(x)=25702284) +2175 train 7.381319 (lr=1.1787e-04) (hash(x)=27093757) +2176 train 7.155960 (lr=1.1782e-04) (hash(x)=26024255) +2177 train 7.303250 (lr=1.1777e-04) (hash(x)=26443521) +2178 train 7.219388 (lr=1.1773e-04) (hash(x)=25478467) +2179 train 7.103130 (lr=1.1768e-04) (hash(x)=23624298) +2180 train 7.207465 (lr=1.1763e-04) (hash(x)=27304178) +2181 train 6.940717 (lr=1.1758e-04) (hash(x)=23016570) +2182 train 6.957013 (lr=1.1753e-04) (hash(x)=21073756) +2183 train 7.022153 (lr=1.1748e-04) (hash(x)=25150275) +2184 train 6.799738 (lr=1.1743e-04) (hash(x)=21004187) +2185 train 7.094775 (lr=1.1738e-04) (hash(x)=25876062) +2186 train 7.014618 (lr=1.1733e-04) (hash(x)=24221275) +2187 train 7.319928 (lr=1.1728e-04) (hash(x)=26239886) +2188 train 7.011585 (lr=1.1723e-04) (hash(x)=23299261) +2189 train 7.477020 (lr=1.1718e-04) (hash(x)=31024703) +2190 train 7.609372 (lr=1.1713e-04) (hash(x)=30084774) +2191 train 7.915937 (lr=1.1708e-04) (hash(x)=33457102) +2192 train 7.050688 (lr=1.1703e-04) (hash(x)=22423723) +2193 train 7.083801 (lr=1.1698e-04) (hash(x)=21989055) +2194 train 7.089728 (lr=1.1693e-04) (hash(x)=23286499) +2195 train 7.023372 (lr=1.1688e-04) (hash(x)=17499738) +2196 train 7.040054 (lr=1.1683e-04) (hash(x)=25329557) +2197 train 6.947763 (lr=1.1678e-04) (hash(x)=24195578) +2198 train 7.270235 (lr=1.1673e-04) (hash(x)=26646383) +2199 train 7.173996 (lr=1.1668e-04) (hash(x)=25755322) +2200 val loss 7.1210 +2200 val perplexity 1237.6914 +2200 train 7.197544 (lr=1.1663e-04) (hash(x)=27592223) +2201 train 7.405149 (lr=1.1658e-04) (hash(x)=26164625) +2202 train 7.225702 (lr=1.1653e-04) (hash(x)=21856341) +2203 train 7.068192 (lr=1.1648e-04) (hash(x)=23722795) +2204 train 7.166686 (lr=1.1643e-04) (hash(x)=25409645) +2205 train 7.089561 (lr=1.1638e-04) (hash(x)=23415339) +2206 train 7.060962 (lr=1.1633e-04) (hash(x)=24147928) +2207 train 6.972564 (lr=1.1628e-04) (hash(x)=23630794) +2208 train 7.071013 (lr=1.1623e-04) (hash(x)=27361452) +2209 train 7.110269 (lr=1.1618e-04) (hash(x)=25632158) +2210 train 6.947960 (lr=1.1613e-04) (hash(x)=21159789) +2211 train 7.102717 (lr=1.1608e-04) (hash(x)=23374168) +2212 train 7.113782 (lr=1.1603e-04) (hash(x)=24844739) +2213 train 7.058904 (lr=1.1598e-04) (hash(x)=23461285) +2214 train 7.089536 (lr=1.1593e-04) (hash(x)=27958481) +2215 train 6.981340 (lr=1.1588e-04) (hash(x)=25167987) +2216 train 7.179862 (lr=1.1583e-04) (hash(x)=22873204) +2217 train 7.812197 (lr=1.1578e-04) (hash(x)=31038116) +2218 train 7.221897 (lr=1.1573e-04) (hash(x)=28883155) +2219 train 7.138785 (lr=1.1568e-04) (hash(x)=30941010) +2220 train 7.096837 (lr=1.1563e-04) (hash(x)=24947521) +2221 train 7.113147 (lr=1.1558e-04) (hash(x)=22703293) +2222 train 7.055782 (lr=1.1553e-04) (hash(x)=23976007) +2223 train 6.996181 (lr=1.1548e-04) (hash(x)=24043224) +2224 train 6.926343 (lr=1.1543e-04) (hash(x)=23981093) +2225 train 7.135509 (lr=1.1538e-04) (hash(x)=26445994) +2226 train 7.382738 (lr=1.1533e-04) (hash(x)=27252393) +2227 train 7.388333 (lr=1.1528e-04) (hash(x)=29736627) +2228 train 7.301010 (lr=1.1523e-04) (hash(x)=24698933) +2229 train 6.930367 (lr=1.1518e-04) (hash(x)=24357840) +2230 train 7.062430 (lr=1.1513e-04) (hash(x)=25384498) +2231 train 7.267227 (lr=1.1508e-04) (hash(x)=24665411) +2232 train 7.095343 (lr=1.1503e-04) (hash(x)=24646352) +2233 train 7.082706 (lr=1.1498e-04) (hash(x)=25670741) +2234 train 7.126546 (lr=1.1493e-04) (hash(x)=26648242) +2235 train 7.431221 (lr=1.1488e-04) (hash(x)=27916043) +2236 train 7.105758 (lr=1.1483e-04) (hash(x)=25963100) +2237 train 7.176370 (lr=1.1478e-04) (hash(x)=27357379) +2238 train 6.967458 (lr=1.1473e-04) (hash(x)=21852360) +2239 train 6.878014 (lr=1.1468e-04) (hash(x)=17321657) +2240 train 6.850743 (lr=1.1463e-04) (hash(x)=18446645) +2241 train 6.621093 (lr=1.1458e-04) (hash(x)=17550988) +2242 train 7.117435 (lr=1.1453e-04) (hash(x)=27052347) +2243 train 6.937897 (lr=1.1448e-04) (hash(x)=23829833) +2244 train 7.181499 (lr=1.1443e-04) (hash(x)=27267264) +2245 train 7.439857 (lr=1.1438e-04) (hash(x)=24673611) +2246 train 7.369609 (lr=1.1433e-04) (hash(x)=25248507) +2247 train 7.650921 (lr=1.1428e-04) (hash(x)=27932591) +2248 train 7.467889 (lr=1.1423e-04) (hash(x)=26078877) +2249 train 7.516407 (lr=1.1418e-04) (hash(x)=26067367) +2250 val loss 7.1202 +2250 val perplexity 1236.6495 +2250 train 7.493057 (lr=1.1413e-04) (hash(x)=29143527) +2251 train 7.487740 (lr=1.1408e-04) (hash(x)=28206079) +2252 train 8.075753 (lr=1.1403e-04) (hash(x)=28894494) +2253 train 7.511520 (lr=1.1398e-04) (hash(x)=27977422) +2254 train 7.186319 (lr=1.1393e-04) (hash(x)=26446420) +2255 train 7.348236 (lr=1.1388e-04) (hash(x)=29447954) +2256 train 7.176373 (lr=1.1383e-04) (hash(x)=22181789) +2257 train 7.160720 (lr=1.1378e-04) (hash(x)=24976337) +2258 train 7.071693 (lr=1.1373e-04) (hash(x)=23277532) +2259 train 7.248175 (lr=1.1368e-04) (hash(x)=25935364) +2260 train 7.439528 (lr=1.1363e-04) (hash(x)=26988889) +2261 train 7.162052 (lr=1.1358e-04) (hash(x)=26887303) +2262 train 7.138790 (lr=1.1353e-04) (hash(x)=25021426) +2263 train 7.065670 (lr=1.1348e-04) (hash(x)=24621816) +2264 train 6.932611 (lr=1.1343e-04) (hash(x)=22132007) +2265 train 6.847266 (lr=1.1338e-04) (hash(x)=22648602) +2266 train 7.215424 (lr=1.1333e-04) (hash(x)=23132242) +2267 train 7.236318 (lr=1.1328e-04) (hash(x)=24070405) +2268 train 6.794704 (lr=1.1323e-04) (hash(x)=21412906) +2269 train 7.535532 (lr=1.1318e-04) (hash(x)=27547292) +2270 train 7.271435 (lr=1.1313e-04) (hash(x)=27740500) +2271 train 6.985265 (lr=1.1308e-04) (hash(x)=24682294) +2272 train 7.450733 (lr=1.1303e-04) (hash(x)=27969424) +2273 train 7.136070 (lr=1.1298e-04) (hash(x)=22172182) +2274 train 7.123863 (lr=1.1293e-04) (hash(x)=26485905) +2275 train 6.998128 (lr=1.1288e-04) (hash(x)=24050209) +2276 train 7.169535 (lr=1.1282e-04) (hash(x)=28802650) +2277 train 6.919501 (lr=1.1277e-04) (hash(x)=23644616) +2278 train 7.096149 (lr=1.1272e-04) (hash(x)=25409768) +2279 train 7.283679 (lr=1.1267e-04) (hash(x)=28057095) +2280 train 7.713985 (lr=1.1262e-04) (hash(x)=31689723) +2281 train 6.910736 (lr=1.1257e-04) (hash(x)=22252427) +2282 train 7.185542 (lr=1.1252e-04) (hash(x)=24142092) +2283 train 7.118595 (lr=1.1247e-04) (hash(x)=22523232) +2284 train 7.290862 (lr=1.1242e-04) (hash(x)=26017294) +2285 train 7.144022 (lr=1.1237e-04) (hash(x)=25025388) +2286 train 6.909698 (lr=1.1232e-04) (hash(x)=23819479) +2287 train 7.091933 (lr=1.1227e-04) (hash(x)=24547536) +2288 train 6.880793 (lr=1.1222e-04) (hash(x)=22622789) +2289 train 6.850891 (lr=1.1217e-04) (hash(x)=23874051) +2290 train 7.235469 (lr=1.1212e-04) (hash(x)=25015641) +2291 train 7.076654 (lr=1.1207e-04) (hash(x)=24978712) +2292 train 7.164300 (lr=1.1202e-04) (hash(x)=25311986) +2293 train 6.935513 (lr=1.1197e-04) (hash(x)=24298295) +2294 train 7.047333 (lr=1.1192e-04) (hash(x)=26481527) +2295 train 6.706625 (lr=1.1187e-04) (hash(x)=18987545) +2296 train 6.957227 (lr=1.1182e-04) (hash(x)=24617990) +2297 train 7.001710 (lr=1.1176e-04) (hash(x)=23903200) +2298 train 7.348461 (lr=1.1171e-04) (hash(x)=26278697) +2299 train 7.093422 (lr=1.1166e-04) (hash(x)=24092784) +2300 val loss 7.0971 +2300 val perplexity 1208.4031 +2300 train 7.040658 (lr=1.1161e-04) (hash(x)=22894919) +2301 train 7.073419 (lr=1.1156e-04) (hash(x)=24253964) +2302 train 7.038204 (lr=1.1151e-04) (hash(x)=23750610) +2303 train 7.071838 (lr=1.1146e-04) (hash(x)=26745063) +2304 train 6.894549 (lr=1.1141e-04) (hash(x)=21407001) +2305 train 7.297554 (lr=1.1136e-04) (hash(x)=26680082) +2306 train 7.194049 (lr=1.1131e-04) (hash(x)=26722122) +2307 train 7.024025 (lr=1.1126e-04) (hash(x)=22539112) +2308 train 6.749485 (lr=1.1121e-04) (hash(x)=19927356) +2309 train 6.903705 (lr=1.1116e-04) (hash(x)=21431267) +2310 train 6.828185 (lr=1.1111e-04) (hash(x)=21073487) +2311 train 6.846675 (lr=1.1106e-04) (hash(x)=21447406) +2312 train 6.839444 (lr=1.1101e-04) (hash(x)=22667253) +2313 train 6.807533 (lr=1.1096e-04) (hash(x)=20849089) +2314 train 6.780899 (lr=1.1091e-04) (hash(x)=19168351) +2315 train 6.806485 (lr=1.1085e-04) (hash(x)=21082139) +2316 train 6.807202 (lr=1.1080e-04) (hash(x)=21493530) +2317 train 6.737267 (lr=1.1075e-04) (hash(x)=19506447) +2318 train 6.907871 (lr=1.1070e-04) (hash(x)=23128797) +2319 train 7.013445 (lr=1.1065e-04) (hash(x)=24650655) +2320 train 6.742830 (lr=1.1060e-04) (hash(x)=21833080) +2321 train 7.327652 (lr=1.1055e-04) (hash(x)=26355512) +2322 train 7.489439 (lr=1.1050e-04) (hash(x)=26746363) +2323 train 6.899905 (lr=1.1045e-04) (hash(x)=22130721) +2324 train 7.292229 (lr=1.1040e-04) (hash(x)=28301752) +2325 train 7.156539 (lr=1.1035e-04) (hash(x)=26444359) +2326 train 7.528728 (lr=1.1030e-04) (hash(x)=24836130) +2327 train 7.949455 (lr=1.1025e-04) (hash(x)=26519976) +2328 train 9.459323 (lr=1.1020e-04) (hash(x)=35558906) +2329 train 7.531723 (lr=1.1014e-04) (hash(x)=30877729) +2330 train 7.362033 (lr=1.1009e-04) (hash(x)=28028485) +2331 train 7.510506 (lr=1.1004e-04) (hash(x)=25582440) +2332 train 7.861465 (lr=1.0999e-04) (hash(x)=29402491) +2333 train 7.202336 (lr=1.0994e-04) (hash(x)=25200284) +2334 train 7.180917 (lr=1.0989e-04) (hash(x)=26288480) +2335 train 6.896741 (lr=1.0984e-04) (hash(x)=20106514) +2336 train 6.982515 (lr=1.0979e-04) (hash(x)=22522123) +2337 train 6.963033 (lr=1.0974e-04) (hash(x)=23362041) +2338 train 7.127336 (lr=1.0969e-04) (hash(x)=26003099) +2339 train 7.159607 (lr=1.0964e-04) (hash(x)=25695510) +2340 train 7.131079 (lr=1.0959e-04) (hash(x)=27225904) +2341 train 6.832953 (lr=1.0954e-04) (hash(x)=21573008) +2342 train 7.373450 (lr=1.0948e-04) (hash(x)=21386628) +2343 train 7.138770 (lr=1.0943e-04) (hash(x)=20117808) +2344 train 7.300498 (lr=1.0938e-04) (hash(x)=21592790) +2345 train 7.170145 (lr=1.0933e-04) (hash(x)=19909192) +2346 train 7.267289 (lr=1.0928e-04) (hash(x)=22529262) +2347 train 7.251617 (lr=1.0923e-04) (hash(x)=24501900) +2348 train 7.060014 (lr=1.0918e-04) (hash(x)=25912171) +2349 train 7.192098 (lr=1.0913e-04) (hash(x)=25606665) +2350 val loss 7.1621 +2350 val perplexity 1289.5742 +2350 train 7.085845 (lr=1.0908e-04) (hash(x)=24487351) +2351 train 7.380007 (lr=1.0903e-04) (hash(x)=25510334) +2352 train 7.252944 (lr=1.0898e-04) (hash(x)=25357989) +2353 train 6.867908 (lr=1.0893e-04) (hash(x)=24656801) +2354 train 6.936265 (lr=1.0887e-04) (hash(x)=23312772) +2355 train 6.765882 (lr=1.0882e-04) (hash(x)=22099158) +2356 train 6.856295 (lr=1.0877e-04) (hash(x)=26507898) +2357 train 7.196308 (lr=1.0872e-04) (hash(x)=28351614) +2358 train 7.205841 (lr=1.0867e-04) (hash(x)=27489567) +2359 train 7.186885 (lr=1.0862e-04) (hash(x)=25749120) +2360 train 7.530904 (lr=1.0857e-04) (hash(x)=31711338) +2361 train 7.632341 (lr=1.0852e-04) (hash(x)=29645018) +2362 train 7.604261 (lr=1.0847e-04) (hash(x)=29713268) +2363 train 6.821105 (lr=1.0842e-04) (hash(x)=21720691) +2364 train 6.925874 (lr=1.0837e-04) (hash(x)=24316633) +2365 train 6.838554 (lr=1.0831e-04) (hash(x)=21597124) +2366 train 6.918574 (lr=1.0826e-04) (hash(x)=22520345) +2367 train 6.917400 (lr=1.0821e-04) (hash(x)=24357241) +2368 train 7.033244 (lr=1.0816e-04) (hash(x)=24085450) +2369 train 6.972855 (lr=1.0811e-04) (hash(x)=25136495) +2370 train 7.517776 (lr=1.0806e-04) (hash(x)=26073986) +2371 train 7.353758 (lr=1.0801e-04) (hash(x)=28911272) +2372 train 7.178276 (lr=1.0796e-04) (hash(x)=26667356) +2373 train 6.997464 (lr=1.0791e-04) (hash(x)=25225894) +2374 train 7.034945 (lr=1.0786e-04) (hash(x)=24404081) +2375 train 7.130293 (lr=1.0781e-04) (hash(x)=25584945) +2376 train 6.953538 (lr=1.0775e-04) (hash(x)=23831571) +2377 train 6.929798 (lr=1.0770e-04) (hash(x)=23521916) +2378 train 6.985038 (lr=1.0765e-04) (hash(x)=25318634) +2379 train 6.833395 (lr=1.0760e-04) (hash(x)=21847287) +2380 train 7.233537 (lr=1.0755e-04) (hash(x)=23877060) +2381 train 7.002081 (lr=1.0750e-04) (hash(x)=24069020) +2382 train 6.771136 (lr=1.0745e-04) (hash(x)=21724290) +2383 train 7.072685 (lr=1.0740e-04) (hash(x)=25198897) +2384 train 6.917481 (lr=1.0735e-04) (hash(x)=24109958) +2385 train 6.746269 (lr=1.0729e-04) (hash(x)=20122390) +2386 train 7.047054 (lr=1.0724e-04) (hash(x)=24062305) +2387 train 6.823797 (lr=1.0719e-04) (hash(x)=22436833) +2388 train 7.123312 (lr=1.0714e-04) (hash(x)=26013214) +2389 train 7.561423 (lr=1.0709e-04) (hash(x)=27691436) +2390 train 7.636407 (lr=1.0704e-04) (hash(x)=30802878) +2391 train 6.796062 (lr=1.0699e-04) (hash(x)=23475891) +2392 train 6.776907 (lr=1.0694e-04) (hash(x)=23118133) +2393 train 6.652825 (lr=1.0689e-04) (hash(x)=21469159) +2394 train 7.076959 (lr=1.0684e-04) (hash(x)=26444484) +2395 train 6.941983 (lr=1.0678e-04) (hash(x)=25083992) +2396 train 7.297260 (lr=1.0673e-04) (hash(x)=23461229) +2397 train 7.129922 (lr=1.0668e-04) (hash(x)=20441653) +2398 train 7.266745 (lr=1.0663e-04) (hash(x)=28024211) +2399 train 7.061489 (lr=1.0658e-04) (hash(x)=23644804) +2400 val loss 7.0996 +2400 val perplexity 1211.5018 +2400 train 6.866131 (lr=1.0653e-04) (hash(x)=26685301) +2401 train 6.695928 (lr=1.0648e-04) (hash(x)=20820913) +2402 train 6.891950 (lr=1.0643e-04) (hash(x)=22178190) +2403 train 7.555011 (lr=1.0638e-04) (hash(x)=31377168) +2404 train 7.749181 (lr=1.0632e-04) (hash(x)=33795307) +2405 train 7.872043 (lr=1.0627e-04) (hash(x)=34450341) +2406 train 7.007439 (lr=1.0622e-04) (hash(x)=25834183) +2407 train 7.241863 (lr=1.0617e-04) (hash(x)=25629584) +2408 train 6.967971 (lr=1.0612e-04) (hash(x)=25080123) +2409 train 6.823477 (lr=1.0607e-04) (hash(x)=21975628) +2410 train 7.451122 (lr=1.0602e-04) (hash(x)=27430197) +2411 train 7.576024 (lr=1.0597e-04) (hash(x)=29285135) +2412 train 7.279236 (lr=1.0592e-04) (hash(x)=24640105) +2413 train 7.401529 (lr=1.0586e-04) (hash(x)=29628864) +2414 train 7.649707 (lr=1.0581e-04) (hash(x)=30096444) +2415 train 7.423462 (lr=1.0576e-04) (hash(x)=29797280) +2416 train 6.791560 (lr=1.0571e-04) (hash(x)=22686143) +2417 train 7.431798 (lr=1.0566e-04) (hash(x)=28346842) +2418 train 7.414529 (lr=1.0561e-04) (hash(x)=28167937) +2419 train 7.639775 (lr=1.0556e-04) (hash(x)=33122326) +2420 train 7.695371 (lr=1.0551e-04) (hash(x)=33044913) +2421 train 7.490546 (lr=1.0545e-04) (hash(x)=31250981) +2422 train 7.693878 (lr=1.0540e-04) (hash(x)=29827111) +2423 train 7.586786 (lr=1.0535e-04) (hash(x)=30026394) +2424 train 7.650307 (lr=1.0530e-04) (hash(x)=26998238) +2425 train 7.598945 (lr=1.0525e-04) (hash(x)=24850684) +2426 train 7.924122 (lr=1.0520e-04) (hash(x)=36659853) +2427 train 7.814201 (lr=1.0515e-04) (hash(x)=34353164) +2428 train 7.051156 (lr=1.0510e-04) (hash(x)=23630644) +2429 train 7.033995 (lr=1.0505e-04) (hash(x)=24528186) +2430 train 6.893421 (lr=1.0499e-04) (hash(x)=22665222) +2431 train 7.072841 (lr=1.0494e-04) (hash(x)=26594177) +2432 train 7.453317 (lr=1.0489e-04) (hash(x)=29300546) +2433 train 6.810925 (lr=1.0484e-04) (hash(x)=21331715) +2434 train 7.127500 (lr=1.0479e-04) (hash(x)=26290885) +2435 train 7.056018 (lr=1.0474e-04) (hash(x)=25554738) +2436 train 7.335802 (lr=1.0469e-04) (hash(x)=26744311) +2437 train 7.278793 (lr=1.0464e-04) (hash(x)=26872344) +2438 train 7.366186 (lr=1.0458e-04) (hash(x)=27636081) +2439 train 7.126044 (lr=1.0453e-04) (hash(x)=23766256) +2440 train 7.212218 (lr=1.0448e-04) (hash(x)=24434438) +2441 train 7.015493 (lr=1.0443e-04) (hash(x)=22992618) +2442 train 6.859272 (lr=1.0438e-04) (hash(x)=22393467) +2443 train 7.157192 (lr=1.0433e-04) (hash(x)=26853444) +2444 train 7.058929 (lr=1.0428e-04) (hash(x)=25101020) +2445 train 6.936559 (lr=1.0423e-04) (hash(x)=24705456) +2446 train 7.300861 (lr=1.0417e-04) (hash(x)=26798611) +2447 train 6.928377 (lr=1.0412e-04) (hash(x)=24250150) +2448 train 7.002667 (lr=1.0407e-04) (hash(x)=24494331) +2449 train 7.033144 (lr=1.0402e-04) (hash(x)=27579257) +2450 val loss 7.0908 +2450 val perplexity 1200.8518 +2450 train 6.789952 (lr=1.0397e-04) (hash(x)=22377407) +2451 train 7.107633 (lr=1.0392e-04) (hash(x)=26289588) +2452 train 7.023820 (lr=1.0387e-04) (hash(x)=25871900) +2453 train 6.888841 (lr=1.0381e-04) (hash(x)=23437197) +2454 train 7.203754 (lr=1.0376e-04) (hash(x)=23557786) +2455 train 7.069810 (lr=1.0371e-04) (hash(x)=26108817) +2456 train 6.974941 (lr=1.0366e-04) (hash(x)=26440482) +2457 train 6.994641 (lr=1.0361e-04) (hash(x)=24583191) +2458 train 7.014629 (lr=1.0356e-04) (hash(x)=23756440) +2459 train 6.869069 (lr=1.0351e-04) (hash(x)=23814987) +2460 train 7.289239 (lr=1.0346e-04) (hash(x)=28508433) +2461 train 6.903244 (lr=1.0340e-04) (hash(x)=25692442) +2462 train 6.860966 (lr=1.0335e-04) (hash(x)=24699197) +2463 train 6.526548 (lr=1.0330e-04) (hash(x)=18582688) +2464 train 6.912909 (lr=1.0325e-04) (hash(x)=23266625) +2465 train 7.257096 (lr=1.0320e-04) (hash(x)=26565489) +2466 train 6.714916 (lr=1.0315e-04) (hash(x)=21686599) +2467 train 6.998694 (lr=1.0310e-04) (hash(x)=25558792) +2468 train 6.769664 (lr=1.0305e-04) (hash(x)=25110035) +2469 train 7.170947 (lr=1.0299e-04) (hash(x)=26263661) +2470 train 6.867715 (lr=1.0294e-04) (hash(x)=22282189) +2471 train 6.857160 (lr=1.0289e-04) (hash(x)=23272705) +2472 train 6.986919 (lr=1.0284e-04) (hash(x)=25300067) +2473 train 7.184438 (lr=1.0279e-04) (hash(x)=26802369) +2474 train 6.867556 (lr=1.0274e-04) (hash(x)=24646471) +2475 train 6.819782 (lr=1.0269e-04) (hash(x)=24709241) +2476 train 6.927803 (lr=1.0263e-04) (hash(x)=26747197) +2477 train 6.992201 (lr=1.0258e-04) (hash(x)=25201108) +2478 train 7.105743 (lr=1.0253e-04) (hash(x)=24962427) +2479 train 6.907937 (lr=1.0248e-04) (hash(x)=24793412) +2480 train 7.030728 (lr=1.0243e-04) (hash(x)=24452301) +2481 train 7.005591 (lr=1.0238e-04) (hash(x)=25177251) +2482 train 6.903771 (lr=1.0233e-04) (hash(x)=25801499) +2483 train 7.080588 (lr=1.0227e-04) (hash(x)=27256707) +2484 train 7.378307 (lr=1.0222e-04) (hash(x)=25303237) +2485 train 6.944518 (lr=1.0217e-04) (hash(x)=21641481) +2486 train 6.882612 (lr=1.0212e-04) (hash(x)=23818831) +2487 train 6.662552 (lr=1.0207e-04) (hash(x)=19280989) +2488 train 7.063883 (lr=1.0202e-04) (hash(x)=24075167) +2489 train 7.038526 (lr=1.0197e-04) (hash(x)=26651546) +2490 train 6.996483 (lr=1.0191e-04) (hash(x)=25367186) +2491 train 6.961235 (lr=1.0186e-04) (hash(x)=26508642) +2492 train 7.074408 (lr=1.0181e-04) (hash(x)=25294182) +2493 train 6.913908 (lr=1.0176e-04) (hash(x)=23916886) +2494 train 6.836350 (lr=1.0171e-04) (hash(x)=21189910) +2495 train 6.931221 (lr=1.0166e-04) (hash(x)=22751150) +2496 train 7.357186 (lr=1.0161e-04) (hash(x)=26608502) +2497 train 7.742055 (lr=1.0155e-04) (hash(x)=25372010) +2498 train 6.964520 (lr=1.0150e-04) (hash(x)=22006251) +2499 train 6.922758 (lr=1.0145e-04) (hash(x)=23880160) +2500 val loss 7.0629 +2500 val perplexity 1167.8331 +2500 train 6.855840 (lr=1.0140e-04) (hash(x)=23225337) +2501 train 7.038391 (lr=1.0135e-04) (hash(x)=24932950) +2502 train 6.747205 (lr=1.0130e-04) (hash(x)=20022340) +2503 train 7.150856 (lr=1.0125e-04) (hash(x)=23537942) +2504 train 7.052712 (lr=1.0119e-04) (hash(x)=24884288) +2505 train 6.668532 (lr=1.0114e-04) (hash(x)=21296580) +2506 train 6.922048 (lr=1.0109e-04) (hash(x)=23001455) +2507 train 7.233597 (lr=1.0104e-04) (hash(x)=26975313) +2508 train 7.241160 (lr=1.0099e-04) (hash(x)=26029962) +2509 train 6.898946 (lr=1.0094e-04) (hash(x)=24302204) +2510 train 6.633322 (lr=1.0089e-04) (hash(x)=22997203) +2511 train 6.758659 (lr=1.0083e-04) (hash(x)=23748375) +2512 train 7.010509 (lr=1.0078e-04) (hash(x)=24453191) +2513 train 6.682086 (lr=1.0073e-04) (hash(x)=22026776) +2514 train 6.768941 (lr=1.0068e-04) (hash(x)=19934168) +2515 train 7.098673 (lr=1.0063e-04) (hash(x)=25541754) +2516 train 7.462517 (lr=1.0058e-04) (hash(x)=26604471) +2517 train 7.455731 (lr=1.0053e-04) (hash(x)=27900386) +2518 train 7.410210 (lr=1.0047e-04) (hash(x)=26403431) +2519 train 7.429483 (lr=1.0042e-04) (hash(x)=27413825) +2520 train 7.499312 (lr=1.0037e-04) (hash(x)=28332637) +2521 train 7.301729 (lr=1.0032e-04) (hash(x)=27223027) +2522 train 7.287279 (lr=1.0027e-04) (hash(x)=23843387) +2523 train 7.231874 (lr=1.0022e-04) (hash(x)=27075951) +2524 train 7.340244 (lr=1.0017e-04) (hash(x)=29300154) +2525 train 7.080967 (lr=1.0011e-04) (hash(x)=28100582) +2526 train 7.231954 (lr=1.0006e-04) (hash(x)=28051084) +2527 train 6.893175 (lr=1.0001e-04) (hash(x)=21682445) +2528 train 7.118740 (lr=9.9960e-05) (hash(x)=24062589) +2529 train 7.305021 (lr=9.9908e-05) (hash(x)=29616079) +2530 train 7.209516 (lr=9.9857e-05) (hash(x)=25170523) +2531 train 6.772041 (lr=9.9805e-05) (hash(x)=23361504) +2532 train 7.008194 (lr=9.9754e-05) (hash(x)=24444462) +2533 train 7.007323 (lr=9.9702e-05) (hash(x)=24035993) +2534 train 6.958823 (lr=9.9651e-05) (hash(x)=24696651) +2535 train 6.965162 (lr=9.9599e-05) (hash(x)=22040184) +2536 train 6.878072 (lr=9.9548e-05) (hash(x)=27400103) +2537 train 7.220253 (lr=9.9496e-05) (hash(x)=27383080) +2538 train 6.991440 (lr=9.9445e-05) (hash(x)=24212212) +2539 train 6.842075 (lr=9.9393e-05) (hash(x)=23727731) +2540 train 7.017539 (lr=9.9342e-05) (hash(x)=24149487) +2541 train 6.776837 (lr=9.9290e-05) (hash(x)=23794649) +2542 train 6.961843 (lr=9.9239e-05) (hash(x)=26147774) +2543 train 7.069711 (lr=9.9187e-05) (hash(x)=24463229) +2544 train 7.160890 (lr=9.9136e-05) (hash(x)=26361238) +2545 train 6.774475 (lr=9.9084e-05) (hash(x)=18891545) +2546 train 7.381800 (lr=9.9033e-05) (hash(x)=30380438) +2547 train 7.602135 (lr=9.8981e-05) (hash(x)=32663792) +2548 train 6.964838 (lr=9.8930e-05) (hash(x)=25175499) +2549 train 7.218709 (lr=9.8878e-05) (hash(x)=26702407) +2550 val loss 7.0744 +2550 val perplexity 1181.3530 +2550 train 6.981876 (lr=9.8827e-05) (hash(x)=24578061) +2551 train 7.019083 (lr=9.8775e-05) (hash(x)=24091954) +2552 train 7.021454 (lr=9.8724e-05) (hash(x)=23041778) +2553 train 6.797612 (lr=9.8672e-05) (hash(x)=23686239) +2554 train 6.910463 (lr=9.8621e-05) (hash(x)=22745355) +2555 train 6.991321 (lr=9.8569e-05) (hash(x)=23599013) +2556 train 6.871175 (lr=9.8518e-05) (hash(x)=26033088) +2557 train 6.978382 (lr=9.8466e-05) (hash(x)=21634218) +2558 train 6.862081 (lr=9.8414e-05) (hash(x)=20985281) +2559 train 7.164453 (lr=9.8363e-05) (hash(x)=26670219) +2560 train 6.920759 (lr=9.8311e-05) (hash(x)=26499936) +2561 train 7.001311 (lr=9.8260e-05) (hash(x)=23547908) +2562 train 6.889867 (lr=9.8208e-05) (hash(x)=22306373) +2563 train 7.035316 (lr=9.8157e-05) (hash(x)=24380893) +2564 train 6.913175 (lr=9.8105e-05) (hash(x)=23726190) +2565 train 6.990210 (lr=9.8054e-05) (hash(x)=26967512) +2566 train 7.053531 (lr=9.8002e-05) (hash(x)=23414576) +2567 train 7.317380 (lr=9.7951e-05) (hash(x)=25558986) +2568 train 7.151882 (lr=9.7899e-05) (hash(x)=27057505) +2569 train 7.134542 (lr=9.7848e-05) (hash(x)=26048135) +2570 train 7.109226 (lr=9.7796e-05) (hash(x)=26991032) +2571 train 7.164163 (lr=9.7745e-05) (hash(x)=25729492) +2572 train 6.648682 (lr=9.7693e-05) (hash(x)=20611723) +2573 train 6.830585 (lr=9.7642e-05) (hash(x)=24563606) +2574 train 6.921739 (lr=9.7590e-05) (hash(x)=23330043) +2575 train 6.902926 (lr=9.7538e-05) (hash(x)=19218943) +2576 train 7.270324 (lr=9.7487e-05) (hash(x)=20985122) +2577 train 6.895148 (lr=9.7435e-05) (hash(x)=24133609) +2578 train 7.227249 (lr=9.7384e-05) (hash(x)=28368610) +2579 train 6.913442 (lr=9.7332e-05) (hash(x)=23952206) +2580 train 6.852751 (lr=9.7281e-05) (hash(x)=23068957) +2581 train 6.980247 (lr=9.7229e-05) (hash(x)=25365277) +2582 train 7.310165 (lr=9.7178e-05) (hash(x)=24721184) +2583 train 7.038297 (lr=9.7126e-05) (hash(x)=24551402) +2584 train 6.709333 (lr=9.7075e-05) (hash(x)=20469327) +2585 train 7.159882 (lr=9.7023e-05) (hash(x)=24966478) +2586 train 6.875873 (lr=9.6972e-05) (hash(x)=18626184) +2587 train 6.893636 (lr=9.6920e-05) (hash(x)=24007642) +2588 train 6.839958 (lr=9.6868e-05) (hash(x)=23521875) +2589 train 7.090329 (lr=9.6817e-05) (hash(x)=25204207) +2590 train 6.850131 (lr=9.6765e-05) (hash(x)=25449801) +2591 train 7.076412 (lr=9.6714e-05) (hash(x)=25229281) +2592 train 6.908577 (lr=9.6662e-05) (hash(x)=23202696) +2593 train 6.776979 (lr=9.6611e-05) (hash(x)=22435944) +2594 train 6.842861 (lr=9.6559e-05) (hash(x)=20787439) +2595 train 6.294328 (lr=9.6508e-05) (hash(x)=18214283) +2596 train 6.547222 (lr=9.6456e-05) (hash(x)=20851477) +2597 train 6.529191 (lr=9.6405e-05) (hash(x)=20609675) +2598 train 6.657707 (lr=9.6353e-05) (hash(x)=20061218) +2599 train 6.721231 (lr=9.6302e-05) (hash(x)=21251127) +2600 val loss 7.0424 +2600 val perplexity 1144.1476 +2600 train 7.235226 (lr=9.6250e-05) (hash(x)=30948038) +2601 train 7.446356 (lr=9.6198e-05) (hash(x)=32279160) +2602 train 7.121643 (lr=9.6147e-05) (hash(x)=26607151) +2603 train 7.008049 (lr=9.6095e-05) (hash(x)=25097619) +2604 train 6.561621 (lr=9.6044e-05) (hash(x)=20892421) +2605 train 6.737102 (lr=9.5992e-05) (hash(x)=22212821) +2606 train 7.076064 (lr=9.5941e-05) (hash(x)=24720588) +2607 train 7.068634 (lr=9.5889e-05) (hash(x)=25800857) +2608 train 6.850365 (lr=9.5838e-05) (hash(x)=22901279) +2609 train 6.740447 (lr=9.5786e-05) (hash(x)=20921910) +2610 train 6.998358 (lr=9.5735e-05) (hash(x)=24846267) +2611 train 6.859607 (lr=9.5683e-05) (hash(x)=22918428) +2612 train 6.813886 (lr=9.5632e-05) (hash(x)=22805901) +2613 train 6.959507 (lr=9.5580e-05) (hash(x)=24345816) +2614 train 6.824925 (lr=9.5528e-05) (hash(x)=22962012) +2615 train 7.110302 (lr=9.5477e-05) (hash(x)=25836189) +2616 train 7.141264 (lr=9.5425e-05) (hash(x)=27922916) +2617 train 6.833754 (lr=9.5374e-05) (hash(x)=21697866) +2618 train 6.854562 (lr=9.5322e-05) (hash(x)=24283369) +2619 train 6.737924 (lr=9.5271e-05) (hash(x)=24504567) +2620 train 6.849158 (lr=9.5219e-05) (hash(x)=25557725) +2621 train 6.896092 (lr=9.5168e-05) (hash(x)=23135849) +2622 train 6.872879 (lr=9.5116e-05) (hash(x)=22888908) +2623 train 7.077089 (lr=9.5065e-05) (hash(x)=25999255) +2624 train 6.920072 (lr=9.5013e-05) (hash(x)=24446851) +2625 train 6.617473 (lr=9.4962e-05) (hash(x)=21137520) +2626 train 6.951722 (lr=9.4910e-05) (hash(x)=26245754) +2627 train 7.338588 (lr=9.4858e-05) (hash(x)=27308968) +2628 train 7.084594 (lr=9.4807e-05) (hash(x)=23961169) +2629 train 7.007692 (lr=9.4755e-05) (hash(x)=25924731) +2630 train 7.054982 (lr=9.4704e-05) (hash(x)=25782315) +2631 train 7.077680 (lr=9.4652e-05) (hash(x)=20149394) +2632 train 7.182241 (lr=9.4601e-05) (hash(x)=23801981) +2633 train 6.941782 (lr=9.4549e-05) (hash(x)=23830286) +2634 train 6.877419 (lr=9.4498e-05) (hash(x)=25325236) +2635 train 6.872406 (lr=9.4446e-05) (hash(x)=24498556) +2636 train 6.832939 (lr=9.4395e-05) (hash(x)=23693078) +2637 train 7.021748 (lr=9.4343e-05) (hash(x)=25484922) +2638 train 6.691226 (lr=9.4292e-05) (hash(x)=22645025) +2639 train 6.678830 (lr=9.4240e-05) (hash(x)=21999338) +2640 train 6.951094 (lr=9.4189e-05) (hash(x)=21758019) +2641 train 6.864727 (lr=9.4137e-05) (hash(x)=24064168) +2642 train 6.900023 (lr=9.4086e-05) (hash(x)=26847292) +2643 train 6.752564 (lr=9.4034e-05) (hash(x)=23280568) +2644 train 6.757165 (lr=9.3982e-05) (hash(x)=21749161) +2645 train 7.445436 (lr=9.3931e-05) (hash(x)=30082352) +2646 train 7.260282 (lr=9.3879e-05) (hash(x)=28334297) +2647 train 7.423587 (lr=9.3828e-05) (hash(x)=27611302) +2648 train 7.799814 (lr=9.3776e-05) (hash(x)=31007436) +2649 train 6.660974 (lr=9.3725e-05) (hash(x)=22356183) +2650 val loss 7.0546 +2650 val perplexity 1158.1777 +2650 train 6.753658 (lr=9.3673e-05) (hash(x)=23071731) +2651 train 6.762289 (lr=9.3622e-05) (hash(x)=23982308) +2652 train 7.120603 (lr=9.3570e-05) (hash(x)=25673823) +2653 train 6.863933 (lr=9.3519e-05) (hash(x)=22973788) +2654 train 7.072919 (lr=9.3467e-05) (hash(x)=25386647) +2655 train 6.762117 (lr=9.3416e-05) (hash(x)=22778356) +2656 train 7.021230 (lr=9.3364e-05) (hash(x)=26669130) +2657 train 6.706600 (lr=9.3313e-05) (hash(x)=23542930) +2658 train 6.826568 (lr=9.3261e-05) (hash(x)=23307871) +2659 train 6.819393 (lr=9.3210e-05) (hash(x)=23467046) +2660 train 6.987218 (lr=9.3158e-05) (hash(x)=24728872) +2661 train 7.612241 (lr=9.3107e-05) (hash(x)=29719902) +2662 train 6.894469 (lr=9.3055e-05) (hash(x)=25114165) +2663 train 6.815865 (lr=9.3004e-05) (hash(x)=24195959) +2664 train 7.047452 (lr=9.2952e-05) (hash(x)=26938509) +2665 train 7.229732 (lr=9.2901e-05) (hash(x)=27168434) +2666 train 7.376734 (lr=9.2849e-05) (hash(x)=27488221) +2667 train 8.001590 (lr=9.2798e-05) (hash(x)=32710438) +2668 train 7.157660 (lr=9.2746e-05) (hash(x)=25073185) +2669 train 7.172925 (lr=9.2695e-05) (hash(x)=26951664) +2670 train 7.355852 (lr=9.2643e-05) (hash(x)=24886228) +2671 train 6.724875 (lr=9.2592e-05) (hash(x)=19127465) +2672 train 7.053759 (lr=9.2540e-05) (hash(x)=27134917) +2673 train 6.984301 (lr=9.2489e-05) (hash(x)=25673955) +2674 train 7.469795 (lr=9.2437e-05) (hash(x)=27111776) +2675 train 7.483125 (lr=9.2386e-05) (hash(x)=28962580) +2676 train 6.940949 (lr=9.2334e-05) (hash(x)=25593381) +2677 train 7.018903 (lr=9.2283e-05) (hash(x)=25238916) +2678 train 6.897678 (lr=9.2231e-05) (hash(x)=27453574) +2679 train 6.887170 (lr=9.2180e-05) (hash(x)=22426274) +2680 train 6.860542 (lr=9.2129e-05) (hash(x)=22974780) +2681 train 6.949782 (lr=9.2077e-05) (hash(x)=24668644) +2682 train 6.960538 (lr=9.2026e-05) (hash(x)=26182084) +2683 train 7.158153 (lr=9.1974e-05) (hash(x)=25606512) +2684 train 6.942038 (lr=9.1923e-05) (hash(x)=24885252) +2685 train 6.772027 (lr=9.1871e-05) (hash(x)=21290254) +2686 train 6.678739 (lr=9.1820e-05) (hash(x)=21367078) +2687 train 6.882175 (lr=9.1768e-05) (hash(x)=23785205) +2688 train 6.791492 (lr=9.1717e-05) (hash(x)=24640056) +2689 train 7.241463 (lr=9.1665e-05) (hash(x)=27083886) +2690 train 6.913746 (lr=9.1614e-05) (hash(x)=23603571) +2691 train 7.064287 (lr=9.1562e-05) (hash(x)=24779414) +2692 train 6.669206 (lr=9.1511e-05) (hash(x)=22200693) +2693 train 7.037221 (lr=9.1460e-05) (hash(x)=26907868) +2694 train 7.387016 (lr=9.1408e-05) (hash(x)=32034827) +2695 train 7.266781 (lr=9.1357e-05) (hash(x)=28505676) +2696 train 6.842959 (lr=9.1305e-05) (hash(x)=23805750) +2697 train 7.196982 (lr=9.1254e-05) (hash(x)=29804750) +2698 train 7.513614 (lr=9.1202e-05) (hash(x)=28443583) +2699 train 7.371768 (lr=9.1151e-05) (hash(x)=29156288) +2700 val loss 7.0492 +2700 val perplexity 1151.8940 +2700 train 7.030667 (lr=9.1100e-05) (hash(x)=25895743) +2701 train 6.676667 (lr=9.1048e-05) (hash(x)=21173795) +2702 train 6.560352 (lr=9.0997e-05) (hash(x)=20790866) +2703 train 7.192363 (lr=9.0945e-05) (hash(x)=27706477) +2704 train 7.294408 (lr=9.0894e-05) (hash(x)=30358985) +2705 train 6.884857 (lr=9.0842e-05) (hash(x)=23548492) +2706 train 7.004297 (lr=9.0791e-05) (hash(x)=25879696) +2707 train 6.862975 (lr=9.0740e-05) (hash(x)=23711800) +2708 train 7.422128 (lr=9.0688e-05) (hash(x)=28763123) +2709 train 7.041805 (lr=9.0637e-05) (hash(x)=23327642) +2710 train 7.099484 (lr=9.0585e-05) (hash(x)=25634166) +2711 train 6.982551 (lr=9.0534e-05) (hash(x)=28684175) +2712 train 7.107619 (lr=9.0482e-05) (hash(x)=23996278) +2713 train 6.692694 (lr=9.0431e-05) (hash(x)=21795980) +2714 train 7.026743 (lr=9.0380e-05) (hash(x)=24840769) +2715 train 6.987751 (lr=9.0328e-05) (hash(x)=25225466) +2716 train 7.272102 (lr=9.0277e-05) (hash(x)=27500471) +2717 train 6.935478 (lr=9.0226e-05) (hash(x)=24703036) +2718 train 7.104482 (lr=9.0174e-05) (hash(x)=24294293) +2719 train 7.034584 (lr=9.0123e-05) (hash(x)=28003600) +2720 train 6.749675 (lr=9.0071e-05) (hash(x)=22822962) +2721 train 6.628162 (lr=9.0020e-05) (hash(x)=24189246) +2722 train 6.767362 (lr=8.9969e-05) (hash(x)=22608951) +2723 train 7.490951 (lr=8.9917e-05) (hash(x)=27989890) +2724 train 7.163837 (lr=8.9866e-05) (hash(x)=24175838) +2725 train 7.016553 (lr=8.9814e-05) (hash(x)=24781792) +2726 train 6.797054 (lr=8.9763e-05) (hash(x)=23413276) +2727 train 7.264644 (lr=8.9712e-05) (hash(x)=27586845) +2728 train 7.011148 (lr=8.9660e-05) (hash(x)=27336264) +2729 train 7.131293 (lr=8.9609e-05) (hash(x)=26808464) +2730 train 6.888600 (lr=8.9558e-05) (hash(x)=22312009) +2731 train 6.970131 (lr=8.9506e-05) (hash(x)=22373927) +2732 train 6.851515 (lr=8.9455e-05) (hash(x)=23428834) +2733 train 6.907625 (lr=8.9404e-05) (hash(x)=25304441) +2734 train 6.954953 (lr=8.9352e-05) (hash(x)=24798164) +2735 train 6.738002 (lr=8.9301e-05) (hash(x)=21176405) +2736 train 6.834878 (lr=8.9250e-05) (hash(x)=22343075) +2737 train 6.919292 (lr=8.9198e-05) (hash(x)=23825332) +2738 train 6.975772 (lr=8.9147e-05) (hash(x)=24191865) +2739 train 6.799628 (lr=8.9096e-05) (hash(x)=23806052) +2740 train 6.817761 (lr=8.9044e-05) (hash(x)=21764591) +2741 train 6.968564 (lr=8.8993e-05) (hash(x)=25548695) +2742 train 7.228071 (lr=8.8942e-05) (hash(x)=26847535) +2743 train 6.888519 (lr=8.8890e-05) (hash(x)=25888433) +2744 train 6.872122 (lr=8.8839e-05) (hash(x)=24327454) +2745 train 6.751068 (lr=8.8788e-05) (hash(x)=22543301) +2746 train 7.192050 (lr=8.8736e-05) (hash(x)=24593022) +2747 train 7.900829 (lr=8.8685e-05) (hash(x)=27797727) +2748 train 7.274578 (lr=8.8634e-05) (hash(x)=28067682) +2749 train 6.872028 (lr=8.8582e-05) (hash(x)=25278538) +2750 val loss 7.0523 +2750 val perplexity 1155.5701 +2750 train 6.805706 (lr=8.8531e-05) (hash(x)=23875731) +2751 train 7.019908 (lr=8.8480e-05) (hash(x)=27916982) +2752 train 6.983228 (lr=8.8429e-05) (hash(x)=25726799) +2753 train 6.771355 (lr=8.8377e-05) (hash(x)=25227141) +2754 train 7.129304 (lr=8.8326e-05) (hash(x)=27679212) +2755 train 6.719382 (lr=8.8275e-05) (hash(x)=24621793) +2756 train 6.699593 (lr=8.8223e-05) (hash(x)=21962296) +2757 train 7.084196 (lr=8.8172e-05) (hash(x)=24899679) +2758 train 6.750377 (lr=8.8121e-05) (hash(x)=21452158) +2759 train 6.857551 (lr=8.8070e-05) (hash(x)=24334708) +2760 train 7.110089 (lr=8.8018e-05) (hash(x)=25523041) +2761 train 7.242205 (lr=8.7967e-05) (hash(x)=30389813) +2762 train 6.771088 (lr=8.7916e-05) (hash(x)=22426014) +2763 train 6.875633 (lr=8.7865e-05) (hash(x)=24419143) +2764 train 6.933246 (lr=8.7813e-05) (hash(x)=24850536) +2765 train 7.013118 (lr=8.7762e-05) (hash(x)=24181393) +2766 train 6.477016 (lr=8.7711e-05) (hash(x)=18882503) +2767 train 7.014371 (lr=8.7660e-05) (hash(x)=25617709) +2768 train 6.915090 (lr=8.7608e-05) (hash(x)=24076662) +2769 train 6.848786 (lr=8.7557e-05) (hash(x)=21656802) +2770 train 6.781439 (lr=8.7506e-05) (hash(x)=21014265) +2771 train 6.928917 (lr=8.7455e-05) (hash(x)=24556034) +2772 train 6.659492 (lr=8.7404e-05) (hash(x)=22046665) +2773 train 6.992423 (lr=8.7352e-05) (hash(x)=26761579) +2774 train 8.413177 (lr=8.7301e-05) (hash(x)=41414315) +2775 train 6.898349 (lr=8.7250e-05) (hash(x)=25152362) +2776 train 7.093412 (lr=8.7199e-05) (hash(x)=25567641) +2777 train 6.995754 (lr=8.7148e-05) (hash(x)=25427935) +2778 train 7.092000 (lr=8.7096e-05) (hash(x)=25824457) +2779 train 6.960628 (lr=8.7045e-05) (hash(x)=24326376) +2780 train 7.028047 (lr=8.6994e-05) (hash(x)=27447230) +2781 train 6.839067 (lr=8.6943e-05) (hash(x)=24003710) +2782 train 6.758281 (lr=8.6892e-05) (hash(x)=24157390) +2783 train 6.881407 (lr=8.6840e-05) (hash(x)=24276512) +2784 train 6.720352 (lr=8.6789e-05) (hash(x)=21503752) +2785 train 6.660437 (lr=8.6738e-05) (hash(x)=20031488) +2786 train 6.668082 (lr=8.6687e-05) (hash(x)=21788715) +2787 train 6.872644 (lr=8.6636e-05) (hash(x)=24344695) +2788 train 6.919835 (lr=8.6585e-05) (hash(x)=22927763) +2789 train 6.799027 (lr=8.6533e-05) (hash(x)=23710755) +2790 train 7.069730 (lr=8.6482e-05) (hash(x)=26924620) +2791 train 7.390865 (lr=8.6431e-05) (hash(x)=26776133) +2792 train 6.812822 (lr=8.6380e-05) (hash(x)=19936770) +2793 train 6.986314 (lr=8.6329e-05) (hash(x)=25440959) +2794 train 6.901677 (lr=8.6278e-05) (hash(x)=25146097) +2795 train 6.720444 (lr=8.6227e-05) (hash(x)=21847282) +2796 train 6.916646 (lr=8.6176e-05) (hash(x)=25639784) +2797 train 6.687352 (lr=8.6124e-05) (hash(x)=21199921) +2798 train 6.881638 (lr=8.6073e-05) (hash(x)=22360806) +2799 train 6.393846 (lr=8.6022e-05) (hash(x)=20254159) +2800 val loss 7.0258 +2800 val perplexity 1125.3247 +2800 train 6.580608 (lr=8.5971e-05) (hash(x)=23348345) +2801 train 7.137886 (lr=8.5920e-05) (hash(x)=24908033) +2802 train 6.854863 (lr=8.5869e-05) (hash(x)=23350309) +2803 train 6.920856 (lr=8.5818e-05) (hash(x)=25044762) +2804 train 6.818204 (lr=8.5767e-05) (hash(x)=24071026) +2805 train 6.606088 (lr=8.5716e-05) (hash(x)=22169363) +2806 train 6.914648 (lr=8.5665e-05) (hash(x)=23757564) +2807 train 7.374099 (lr=8.5613e-05) (hash(x)=27873855) +2808 train 7.103696 (lr=8.5562e-05) (hash(x)=26577893) +2809 train 7.151579 (lr=8.5511e-05) (hash(x)=27001634) +2810 train 6.943118 (lr=8.5460e-05) (hash(x)=24796541) +2811 train 6.810224 (lr=8.5409e-05) (hash(x)=22575615) +2812 train 6.937664 (lr=8.5358e-05) (hash(x)=25876475) +2813 train 6.945934 (lr=8.5307e-05) (hash(x)=24765155) +2814 train 6.856375 (lr=8.5256e-05) (hash(x)=25785699) +2815 train 7.085687 (lr=8.5205e-05) (hash(x)=25113614) +2816 train 6.912235 (lr=8.5154e-05) (hash(x)=24415748) +2817 train 7.036218 (lr=8.5103e-05) (hash(x)=25140622) +2818 train 6.953426 (lr=8.5052e-05) (hash(x)=24845866) +2819 train 7.397821 (lr=8.5001e-05) (hash(x)=28062905) +2820 train 6.906925 (lr=8.4950e-05) (hash(x)=22041086) +2821 train 7.057568 (lr=8.4899e-05) (hash(x)=24957184) +2822 train 6.935727 (lr=8.4848e-05) (hash(x)=24360380) +2823 train 7.107787 (lr=8.4797e-05) (hash(x)=26192886) +2824 train 6.944501 (lr=8.4746e-05) (hash(x)=25001858) +2825 train 6.910816 (lr=8.4695e-05) (hash(x)=24721193) +2826 train 6.996217 (lr=8.4644e-05) (hash(x)=26186227) +2827 train 6.931142 (lr=8.4593e-05) (hash(x)=25770338) +2828 train 7.020776 (lr=8.4542e-05) (hash(x)=25920767) +2829 train 6.935483 (lr=8.4491e-05) (hash(x)=25060684) +2830 train 6.588660 (lr=8.4440e-05) (hash(x)=22933946) +2831 train 6.792430 (lr=8.4389e-05) (hash(x)=24614912) +2832 train 6.505306 (lr=8.4338e-05) (hash(x)=19955522) +2833 train 6.552739 (lr=8.4287e-05) (hash(x)=21111215) +2834 train 7.460799 (lr=8.4236e-05) (hash(x)=28817924) +2835 train 7.010896 (lr=8.4185e-05) (hash(x)=26934071) +2836 train 6.935467 (lr=8.4134e-05) (hash(x)=24768851) +2837 train 6.889069 (lr=8.4084e-05) (hash(x)=25706447) +2838 train 6.667769 (lr=8.4033e-05) (hash(x)=19579834) +2839 train 6.927854 (lr=8.3982e-05) (hash(x)=25397093) +2840 train 7.345102 (lr=8.3931e-05) (hash(x)=27902141) +2841 train 7.004067 (lr=8.3880e-05) (hash(x)=25383069) +2842 train 6.769089 (lr=8.3829e-05) (hash(x)=22007373) +2843 train 6.861946 (lr=8.3778e-05) (hash(x)=25925963) +2844 train 6.907314 (lr=8.3727e-05) (hash(x)=25711128) +2845 train 6.660764 (lr=8.3676e-05) (hash(x)=21881216) +2846 train 6.837032 (lr=8.3625e-05) (hash(x)=20277075) +2847 train 6.896729 (lr=8.3575e-05) (hash(x)=19811802) +2848 train 6.766769 (lr=8.3524e-05) (hash(x)=23878906) +2849 train 7.015074 (lr=8.3473e-05) (hash(x)=25034966) +2850 val loss 7.0108 +2850 val perplexity 1108.5583 +2850 train 7.035387 (lr=8.3422e-05) (hash(x)=24359507) +2851 train 6.807156 (lr=8.3371e-05) (hash(x)=23248423) +2852 train 6.767419 (lr=8.3320e-05) (hash(x)=21782773) +2853 train 6.943712 (lr=8.3269e-05) (hash(x)=23804418) +2854 train 6.999252 (lr=8.3219e-05) (hash(x)=22525078) +2855 train 6.984258 (lr=8.3168e-05) (hash(x)=25579655) +2856 train 7.064804 (lr=8.3117e-05) (hash(x)=27048876) +2857 train 7.198110 (lr=8.3066e-05) (hash(x)=26468479) +2858 train 6.871454 (lr=8.3015e-05) (hash(x)=23854933) +2859 train 7.281395 (lr=8.2965e-05) (hash(x)=25537603) +2860 train 6.686565 (lr=8.2914e-05) (hash(x)=20979252) +2861 train 7.231477 (lr=8.2863e-05) (hash(x)=26504374) +2862 train 7.025659 (lr=8.2812e-05) (hash(x)=27561842) +2863 train 7.046295 (lr=8.2761e-05) (hash(x)=26096514) +2864 train 7.083885 (lr=8.2711e-05) (hash(x)=25926899) +2865 train 7.099131 (lr=8.2660e-05) (hash(x)=26058348) +2866 train 7.057396 (lr=8.2609e-05) (hash(x)=29802259) +2867 train 6.998508 (lr=8.2558e-05) (hash(x)=24132888) +2868 train 6.689407 (lr=8.2508e-05) (hash(x)=23369410) +2869 train 6.840897 (lr=8.2457e-05) (hash(x)=25387506) +2870 train 7.046193 (lr=8.2406e-05) (hash(x)=27375344) +2871 train 6.801297 (lr=8.2355e-05) (hash(x)=22589633) +2872 train 6.976071 (lr=8.2305e-05) (hash(x)=23250237) +2873 train 6.848424 (lr=8.2254e-05) (hash(x)=25511322) +2874 train 6.481688 (lr=8.2203e-05) (hash(x)=18356418) +2875 train 6.962309 (lr=8.2152e-05) (hash(x)=27781566) +2876 train 6.848701 (lr=8.2102e-05) (hash(x)=24878173) +2877 train 7.308976 (lr=8.2051e-05) (hash(x)=30018637) +2878 train 7.151006 (lr=8.2000e-05) (hash(x)=27168416) +2879 train 7.129665 (lr=8.1950e-05) (hash(x)=26757147) +2880 train 7.172122 (lr=8.1899e-05) (hash(x)=26637081) +2881 train 7.020332 (lr=8.1848e-05) (hash(x)=24795024) +2882 train 7.288018 (lr=8.1798e-05) (hash(x)=29787745) +2883 train 7.146400 (lr=8.1747e-05) (hash(x)=26649864) +2884 train 6.975151 (lr=8.1696e-05) (hash(x)=27306612) +2885 train 7.050130 (lr=8.1646e-05) (hash(x)=27568311) +2886 train 7.080367 (lr=8.1595e-05) (hash(x)=27440150) +2887 train 6.802064 (lr=8.1544e-05) (hash(x)=24963730) +2888 train 6.853481 (lr=8.1494e-05) (hash(x)=23619807) +2889 train 7.341805 (lr=8.1443e-05) (hash(x)=29447356) +2890 train 6.816885 (lr=8.1392e-05) (hash(x)=25144675) +2891 train 6.722229 (lr=8.1342e-05) (hash(x)=25249959) +2892 train 6.785065 (lr=8.1291e-05) (hash(x)=26608712) +2893 train 6.796838 (lr=8.1241e-05) (hash(x)=26333258) +2894 train 6.645080 (lr=8.1190e-05) (hash(x)=20682182) +2895 train 7.039697 (lr=8.1139e-05) (hash(x)=27703124) +2896 train 6.872433 (lr=8.1089e-05) (hash(x)=23228180) +2897 train 6.742588 (lr=8.1038e-05) (hash(x)=25252411) +2898 train 6.702431 (lr=8.0988e-05) (hash(x)=22879178) +2899 train 7.052791 (lr=8.0937e-05) (hash(x)=26459082) +2900 val loss 7.0201 +2900 val perplexity 1118.8965 +2900 train 6.835831 (lr=8.0887e-05) (hash(x)=24569501) +2901 train 6.581685 (lr=8.0836e-05) (hash(x)=19803884) +2902 train 6.633043 (lr=8.0786e-05) (hash(x)=18799747) +2903 train 6.966812 (lr=8.0735e-05) (hash(x)=24781713) +2904 train 7.139426 (lr=8.0684e-05) (hash(x)=25016590) +2905 train 7.313200 (lr=8.0634e-05) (hash(x)=29006906) +2906 train 7.059744 (lr=8.0583e-05) (hash(x)=24069959) +2907 train 7.220505 (lr=8.0533e-05) (hash(x)=26597693) +2908 train 6.816994 (lr=8.0482e-05) (hash(x)=25014146) +2909 train 7.033288 (lr=8.0432e-05) (hash(x)=24943747) +2910 train 6.969265 (lr=8.0381e-05) (hash(x)=27847542) +2911 train 6.891059 (lr=8.0331e-05) (hash(x)=24720476) +2912 train 6.738854 (lr=8.0281e-05) (hash(x)=24388804) +2913 train 6.868114 (lr=8.0230e-05) (hash(x)=23567535) +2914 train 7.185052 (lr=8.0180e-05) (hash(x)=29673625) +2915 train 6.896758 (lr=8.0129e-05) (hash(x)=23691295) +2916 train 7.239989 (lr=8.0079e-05) (hash(x)=26572819) +2917 train 6.874945 (lr=8.0028e-05) (hash(x)=23237812) +2918 train 7.188771 (lr=7.9978e-05) (hash(x)=26531016) +2919 train 6.670689 (lr=7.9927e-05) (hash(x)=23481301) +2920 train 6.983457 (lr=7.9877e-05) (hash(x)=24839184) +2921 train 6.822216 (lr=7.9827e-05) (hash(x)=23327755) +2922 train 7.133273 (lr=7.9776e-05) (hash(x)=26347114) +2923 train 6.748609 (lr=7.9726e-05) (hash(x)=23295676) +2924 train 6.805417 (lr=7.9675e-05) (hash(x)=24557178) +2925 train 6.885303 (lr=7.9625e-05) (hash(x)=26067788) +2926 train 6.842871 (lr=7.9575e-05) (hash(x)=25694982) +2927 train 6.940145 (lr=7.9524e-05) (hash(x)=25641033) +2928 train 6.973026 (lr=7.9474e-05) (hash(x)=24906422) +2929 train 7.176134 (lr=7.9424e-05) (hash(x)=27803515) +2930 train 7.136788 (lr=7.9373e-05) (hash(x)=26208803) +2931 train 6.567378 (lr=7.9323e-05) (hash(x)=22441379) +2932 train 6.885569 (lr=7.9272e-05) (hash(x)=24741626) +2933 train 6.773774 (lr=7.9222e-05) (hash(x)=24595257) +2934 train 6.796254 (lr=7.9172e-05) (hash(x)=23939167) +2935 train 7.097914 (lr=7.9122e-05) (hash(x)=27369437) +2936 train 6.726705 (lr=7.9071e-05) (hash(x)=21409783) +2937 train 7.011394 (lr=7.9021e-05) (hash(x)=25923735) +2938 train 6.991069 (lr=7.8971e-05) (hash(x)=29559511) +2939 train 6.882654 (lr=7.8920e-05) (hash(x)=24482272) +2940 train 6.853082 (lr=7.8870e-05) (hash(x)=24767658) +2941 train 7.057157 (lr=7.8820e-05) (hash(x)=26425020) +2942 train 7.429273 (lr=7.8770e-05) (hash(x)=27444868) +2943 train 6.863396 (lr=7.8719e-05) (hash(x)=24760900) +2944 train 6.880623 (lr=7.8669e-05) (hash(x)=25605407) +2945 train 6.749480 (lr=7.8619e-05) (hash(x)=22886951) +2946 train 7.098404 (lr=7.8569e-05) (hash(x)=26112205) +2947 train 6.915840 (lr=7.8518e-05) (hash(x)=23919156) +2948 train 6.869895 (lr=7.8468e-05) (hash(x)=23729312) +2949 train 7.129529 (lr=7.8418e-05) (hash(x)=30440878) +2950 val loss 6.9911 +2950 val perplexity 1086.9220 +2950 train 6.617352 (lr=7.8368e-05) (hash(x)=20004041) +2951 train 6.538577 (lr=7.8318e-05) (hash(x)=21692546) +2952 train 6.636996 (lr=7.8267e-05) (hash(x)=23021681) +2953 train 7.007796 (lr=7.8217e-05) (hash(x)=26663597) +2954 train 6.893516 (lr=7.8167e-05) (hash(x)=23727385) +2955 train 6.848169 (lr=7.8117e-05) (hash(x)=27692087) +2956 train 6.908054 (lr=7.8067e-05) (hash(x)=24003378) +2957 train 7.571167 (lr=7.8017e-05) (hash(x)=29534673) +2958 train 6.773067 (lr=7.7966e-05) (hash(x)=22875068) +2959 train 6.748396 (lr=7.7916e-05) (hash(x)=22720391) +2960 train 6.560318 (lr=7.7866e-05) (hash(x)=17997400) +2961 train 6.771810 (lr=7.7816e-05) (hash(x)=22853822) +2962 train 6.821781 (lr=7.7766e-05) (hash(x)=25238004) +2963 train 6.926317 (lr=7.7716e-05) (hash(x)=26146560) +2964 train 7.107852 (lr=7.7666e-05) (hash(x)=21894867) +2965 train 7.030219 (lr=7.7616e-05) (hash(x)=23001150) +2966 train 6.756018 (lr=7.7566e-05) (hash(x)=23392923) +2967 train 6.830000 (lr=7.7516e-05) (hash(x)=24376979) +2968 train 6.806616 (lr=7.7465e-05) (hash(x)=23781449) +2969 train 6.968484 (lr=7.7415e-05) (hash(x)=25315495) +2970 train 7.117059 (lr=7.7365e-05) (hash(x)=27165470) +2971 train 6.916799 (lr=7.7315e-05) (hash(x)=22917712) +2972 train 7.236751 (lr=7.7265e-05) (hash(x)=27928456) +2973 train 6.679420 (lr=7.7215e-05) (hash(x)=19890855) +2974 train 6.615514 (lr=7.7165e-05) (hash(x)=21318134) +2975 train 6.749727 (lr=7.7115e-05) (hash(x)=22244509) +2976 train 6.691394 (lr=7.7065e-05) (hash(x)=21293137) +2977 train 6.755253 (lr=7.7015e-05) (hash(x)=23465789) +2978 train 6.742574 (lr=7.6965e-05) (hash(x)=21169753) +2979 train 7.127779 (lr=7.6915e-05) (hash(x)=25243385) +2980 train 7.177092 (lr=7.6865e-05) (hash(x)=27465812) +2981 train 6.864111 (lr=7.6815e-05) (hash(x)=24615492) +2982 train 6.813709 (lr=7.6766e-05) (hash(x)=23081307) +2983 train 6.606929 (lr=7.6716e-05) (hash(x)=21831960) +2984 train 6.729398 (lr=7.6666e-05) (hash(x)=23242850) +2985 train 6.833621 (lr=7.6616e-05) (hash(x)=24308188) +2986 train 7.018365 (lr=7.6566e-05) (hash(x)=28541601) +2987 train 6.905643 (lr=7.6516e-05) (hash(x)=24842373) +2988 train 6.634270 (lr=7.6466e-05) (hash(x)=21967126) +2989 train 6.832938 (lr=7.6416e-05) (hash(x)=22951616) +2990 train 6.964893 (lr=7.6366e-05) (hash(x)=24325714) +2991 train 6.734102 (lr=7.6316e-05) (hash(x)=24921535) +2992 train 6.996751 (lr=7.6267e-05) (hash(x)=25937112) +2993 train 6.631054 (lr=7.6217e-05) (hash(x)=20716218) +2994 train 6.953061 (lr=7.6167e-05) (hash(x)=25450724) +2995 train 6.909795 (lr=7.6117e-05) (hash(x)=24344615) +2996 train 6.683432 (lr=7.6067e-05) (hash(x)=20299058) +2997 train 6.854691 (lr=7.6017e-05) (hash(x)=23859426) +2998 train 6.825602 (lr=7.5968e-05) (hash(x)=23094397) +2999 train 7.123569 (lr=7.5918e-05) (hash(x)=25381251) +3000 val loss 7.0045 +3000 val perplexity 1101.5333 +3000 train 6.909330 (lr=7.5868e-05) (hash(x)=23586527) +3001 train 6.787376 (lr=7.5818e-05) (hash(x)=24220410) +3002 train 6.622882 (lr=7.5768e-05) (hash(x)=20597347) +3003 train 6.747865 (lr=7.5719e-05) (hash(x)=22887303) +3004 train 7.082275 (lr=7.5669e-05) (hash(x)=25869462) +3005 train 6.774522 (lr=7.5619e-05) (hash(x)=22098530) +3006 train 7.078367 (lr=7.5569e-05) (hash(x)=26246291) +3007 train 7.037583 (lr=7.5520e-05) (hash(x)=25687352) +3008 train 6.775048 (lr=7.5470e-05) (hash(x)=25425646) +3009 train 6.956143 (lr=7.5420e-05) (hash(x)=26021124) +3010 train 6.980675 (lr=7.5371e-05) (hash(x)=25392057) +3011 train 7.084544 (lr=7.5321e-05) (hash(x)=27791412) +3012 train 6.888234 (lr=7.5271e-05) (hash(x)=23181098) +3013 train 6.886527 (lr=7.5222e-05) (hash(x)=25521889) +3014 train 6.709221 (lr=7.5172e-05) (hash(x)=21685795) +3015 train 6.871192 (lr=7.5122e-05) (hash(x)=25221654) +3016 train 7.030579 (lr=7.5073e-05) (hash(x)=24888744) +3017 train 6.950064 (lr=7.5023e-05) (hash(x)=24200150) +3018 train 6.879749 (lr=7.4973e-05) (hash(x)=26943942) +3019 train 6.826482 (lr=7.4924e-05) (hash(x)=23243731) +3020 train 6.695484 (lr=7.4874e-05) (hash(x)=21068284) +3021 train 6.842945 (lr=7.4824e-05) (hash(x)=23876902) +3022 train 7.026747 (lr=7.4775e-05) (hash(x)=25337639) +3023 train 6.927525 (lr=7.4725e-05) (hash(x)=24469863) +3024 train 7.336689 (lr=7.4676e-05) (hash(x)=27850876) +3025 train 7.243522 (lr=7.4626e-05) (hash(x)=20515778) +3026 train 7.002084 (lr=7.4577e-05) (hash(x)=29019173) +3027 train 6.612644 (lr=7.4527e-05) (hash(x)=22484936) +3028 train 6.790689 (lr=7.4478e-05) (hash(x)=24639400) +3029 train 6.982985 (lr=7.4428e-05) (hash(x)=26835174) +3030 train 7.096414 (lr=7.4378e-05) (hash(x)=29843763) +3031 train 6.803298 (lr=7.4329e-05) (hash(x)=25291413) +3032 train 6.723235 (lr=7.4279e-05) (hash(x)=24590244) +3033 train 7.015836 (lr=7.4230e-05) (hash(x)=28880142) +3034 train 6.722392 (lr=7.4180e-05) (hash(x)=23372199) +3035 train 6.714650 (lr=7.4131e-05) (hash(x)=23952225) +3036 train 6.851591 (lr=7.4082e-05) (hash(x)=24589186) +3037 train 6.838117 (lr=7.4032e-05) (hash(x)=23260323) +3038 train 6.984058 (lr=7.3983e-05) (hash(x)=25824498) +3039 train 6.945809 (lr=7.3933e-05) (hash(x)=25744274) +3040 train 6.889784 (lr=7.3884e-05) (hash(x)=21610247) +3041 train 7.024806 (lr=7.3834e-05) (hash(x)=25079786) +3042 train 6.642825 (lr=7.3785e-05) (hash(x)=23219195) +3043 train 6.553426 (lr=7.3736e-05) (hash(x)=22616739) +3044 train 6.880579 (lr=7.3686e-05) (hash(x)=24908480) +3045 train 6.754032 (lr=7.3637e-05) (hash(x)=22293489) +3046 train 6.739192 (lr=7.3587e-05) (hash(x)=23557651) +3047 train 6.801211 (lr=7.3538e-05) (hash(x)=24246963) +3048 train 6.926782 (lr=7.3489e-05) (hash(x)=24490083) +3049 train 6.895084 (lr=7.3439e-05) (hash(x)=22372895) +3050 val loss 6.9713 +3050 val perplexity 1065.6550 +3050 train 6.611146 (lr=7.3390e-05) (hash(x)=21759470) +3051 train 6.527889 (lr=7.3341e-05) (hash(x)=19407094) +3052 train 6.921742 (lr=7.3291e-05) (hash(x)=23957047) +3053 train 7.029835 (lr=7.3242e-05) (hash(x)=24719318) +3054 train 6.811192 (lr=7.3193e-05) (hash(x)=20719314) +3055 train 6.759030 (lr=7.3144e-05) (hash(x)=19724058) +3056 train 6.519582 (lr=7.3094e-05) (hash(x)=14407266) +3057 train 6.367445 (lr=7.3045e-05) (hash(x)=12468292) +3058 train 6.677091 (lr=7.2996e-05) (hash(x)=16098279) +3059 train 6.776329 (lr=7.2947e-05) (hash(x)=18836491) +3060 train 6.618752 (lr=7.2897e-05) (hash(x)=19132277) +3061 train 6.775600 (lr=7.2848e-05) (hash(x)=22814208) +3062 train 6.802906 (lr=7.2799e-05) (hash(x)=24838508) +3063 train 6.715274 (lr=7.2750e-05) (hash(x)=20705649) +3064 train 7.665613 (lr=7.2701e-05) (hash(x)=29416914) +3065 train 7.195251 (lr=7.2651e-05) (hash(x)=25972430) +3066 train 6.562171 (lr=7.2602e-05) (hash(x)=23705805) +3067 train 6.627826 (lr=7.2553e-05) (hash(x)=21325875) +3068 train 6.856089 (lr=7.2504e-05) (hash(x)=23526506) +3069 train 7.351917 (lr=7.2455e-05) (hash(x)=27282337) +3070 train 7.188288 (lr=7.2406e-05) (hash(x)=27968043) +3071 train 6.957800 (lr=7.2357e-05) (hash(x)=24938685) +3072 train 7.166903 (lr=7.2307e-05) (hash(x)=26942737) +3073 train 7.039800 (lr=7.2258e-05) (hash(x)=23506879) +3074 train 6.727058 (lr=7.2209e-05) (hash(x)=23589913) +3075 train 6.934800 (lr=7.2160e-05) (hash(x)=25152403) +3076 train 7.088725 (lr=7.2111e-05) (hash(x)=23425868) +3077 train 7.236238 (lr=7.2062e-05) (hash(x)=23966181) +3078 train 7.327002 (lr=7.2013e-05) (hash(x)=27312570) +3079 train 6.902525 (lr=7.1964e-05) (hash(x)=21707000) +3080 train 6.817893 (lr=7.1915e-05) (hash(x)=25600427) +3081 train 6.954405 (lr=7.1866e-05) (hash(x)=24270631) +3082 train 7.036107 (lr=7.1817e-05) (hash(x)=25199537) +3083 train 6.318712 (lr=7.1768e-05) (hash(x)=17952018) +3084 train 6.427156 (lr=7.1719e-05) (hash(x)=18733143) +3085 train 7.064868 (lr=7.1670e-05) (hash(x)=26946100) +3086 train 6.902754 (lr=7.1621e-05) (hash(x)=25547515) +3087 train 6.872291 (lr=7.1572e-05) (hash(x)=24948980) +3088 train 8.072706 (lr=7.1523e-05) (hash(x)=35461645) +3089 train 7.090270 (lr=7.1474e-05) (hash(x)=28330877) +3090 train 7.029012 (lr=7.1425e-05) (hash(x)=27687861) +3091 train 7.144858 (lr=7.1376e-05) (hash(x)=28012110) +3092 train 6.976890 (lr=7.1327e-05) (hash(x)=24684480) +3093 train 6.970152 (lr=7.1279e-05) (hash(x)=26225786) +3094 train 6.625325 (lr=7.1230e-05) (hash(x)=23098156) +3095 train 7.203928 (lr=7.1181e-05) (hash(x)=30773958) +3096 train 7.530106 (lr=7.1132e-05) (hash(x)=28640406) +3097 train 7.456500 (lr=7.1083e-05) (hash(x)=28201086) +3098 train 7.762473 (lr=7.1034e-05) (hash(x)=35002344) +3099 train 7.291790 (lr=7.0985e-05) (hash(x)=29481068) +3100 val loss 6.9699 +3100 val perplexity 1064.1150 +3100 train 6.862111 (lr=7.0937e-05) (hash(x)=26374528) +3101 train 6.803409 (lr=7.0888e-05) (hash(x)=24153602) +3102 train 6.860218 (lr=7.0839e-05) (hash(x)=25478746) +3103 train 7.185140 (lr=7.0790e-05) (hash(x)=26769046) +3104 train 6.756393 (lr=7.0742e-05) (hash(x)=21841970) +3105 train 7.080129 (lr=7.0693e-05) (hash(x)=27693052) +3106 train 6.518754 (lr=7.0644e-05) (hash(x)=20689448) +3107 train 6.885692 (lr=7.0595e-05) (hash(x)=26755048) +3108 train 6.955716 (lr=7.0547e-05) (hash(x)=24431904) +3109 train 6.792508 (lr=7.0498e-05) (hash(x)=21009792) +3110 train 6.894330 (lr=7.0449e-05) (hash(x)=21909003) +3111 train 6.950596 (lr=7.0400e-05) (hash(x)=18849656) +3112 train 7.021787 (lr=7.0352e-05) (hash(x)=22223376) +3113 train 7.307311 (lr=7.0303e-05) (hash(x)=25652491) +3114 train 7.207497 (lr=7.0254e-05) (hash(x)=23521434) +3115 train 7.260736 (lr=7.0206e-05) (hash(x)=25449800) +3116 train 7.557388 (lr=7.0157e-05) (hash(x)=27655847) +3117 train 7.612424 (lr=7.0109e-05) (hash(x)=29878248) +3118 train 7.655592 (lr=7.0060e-05) (hash(x)=30444094) +3119 train 7.325796 (lr=7.0011e-05) (hash(x)=24624950) +3120 train 6.642021 (lr=6.9963e-05) (hash(x)=20798511) +3121 train 7.069824 (lr=6.9914e-05) (hash(x)=26581679) +3122 train 6.946641 (lr=6.9866e-05) (hash(x)=25333422) +3123 train 7.019887 (lr=6.9817e-05) (hash(x)=26174069) +3124 train 7.108293 (lr=6.9768e-05) (hash(x)=25219475) +3125 train 6.992405 (lr=6.9720e-05) (hash(x)=20919061) +3126 train 6.933656 (lr=6.9671e-05) (hash(x)=23828688) +3127 train 7.429634 (lr=6.9623e-05) (hash(x)=27299605) +3128 train 6.760711 (lr=6.9574e-05) (hash(x)=23797514) +3129 train 7.049410 (lr=6.9526e-05) (hash(x)=23601883) +3130 train 7.215332 (lr=6.9477e-05) (hash(x)=31003964) +3131 train 6.957524 (lr=6.9429e-05) (hash(x)=24777273) +3132 train 6.830570 (lr=6.9381e-05) (hash(x)=25403249) +3133 train 7.080384 (lr=6.9332e-05) (hash(x)=28913150) +3134 train 6.975938 (lr=6.9284e-05) (hash(x)=26541508) +3135 train 6.968021 (lr=6.9235e-05) (hash(x)=24113445) +3136 train 6.709189 (lr=6.9187e-05) (hash(x)=25464565) +3137 train 7.006946 (lr=6.9138e-05) (hash(x)=26581432) +3138 train 6.846040 (lr=6.9090e-05) (hash(x)=23074513) +3139 train 6.710161 (lr=6.9042e-05) (hash(x)=23970384) +3140 train 6.975200 (lr=6.8993e-05) (hash(x)=26694495) +3141 train 6.961933 (lr=6.8945e-05) (hash(x)=26883445) +3142 train 7.108763 (lr=6.8897e-05) (hash(x)=28632211) +3143 train 7.563463 (lr=6.8848e-05) (hash(x)=32644465) +3144 train 7.258441 (lr=6.8800e-05) (hash(x)=27490443) +3145 train 6.829456 (lr=6.8752e-05) (hash(x)=23814853) +3146 train 7.240881 (lr=6.8703e-05) (hash(x)=29664236) +3147 train 7.554377 (lr=6.8655e-05) (hash(x)=29951548) +3148 train 7.291046 (lr=6.8607e-05) (hash(x)=28426503) +3149 train 6.671187 (lr=6.8559e-05) (hash(x)=23727657) +3150 val loss 6.9750 +3150 val perplexity 1069.5087 +3150 train 6.835080 (lr=6.8510e-05) (hash(x)=21430659) +3151 train 6.940782 (lr=6.8462e-05) (hash(x)=25829219) +3152 train 7.058386 (lr=6.8414e-05) (hash(x)=29735208) +3153 train 7.105672 (lr=6.8366e-05) (hash(x)=28173447) +3154 train 6.795256 (lr=6.8317e-05) (hash(x)=22909641) +3155 train 6.945840 (lr=6.8269e-05) (hash(x)=20556094) +3156 train 6.690282 (lr=6.8221e-05) (hash(x)=24013769) +3157 train 6.700607 (lr=6.8173e-05) (hash(x)=22525971) +3158 train 6.793033 (lr=6.8125e-05) (hash(x)=25492728) +3159 train 6.860646 (lr=6.8077e-05) (hash(x)=25194550) +3160 train 6.949533 (lr=6.8029e-05) (hash(x)=25610603) +3161 train 6.939870 (lr=6.7980e-05) (hash(x)=23848640) +3162 train 6.713568 (lr=6.7932e-05) (hash(x)=24082226) +3163 train 7.153998 (lr=6.7884e-05) (hash(x)=28482186) +3164 train 7.025539 (lr=6.7836e-05) (hash(x)=27542978) +3165 train 6.787388 (lr=6.7788e-05) (hash(x)=22540954) +3166 train 6.933972 (lr=6.7740e-05) (hash(x)=26103641) +3167 train 6.894773 (lr=6.7692e-05) (hash(x)=25941804) +3168 train 6.932087 (lr=6.7644e-05) (hash(x)=25965921) +3169 train 7.127128 (lr=6.7596e-05) (hash(x)=25631269) +3170 train 6.750134 (lr=6.7548e-05) (hash(x)=23471525) +3171 train 7.005857 (lr=6.7500e-05) (hash(x)=27049208) +3172 train 6.998909 (lr=6.7452e-05) (hash(x)=27074992) +3173 train 6.907677 (lr=6.7404e-05) (hash(x)=25712617) +3174 train 6.862287 (lr=6.7356e-05) (hash(x)=25884917) +3175 train 6.903133 (lr=6.7308e-05) (hash(x)=24075727) +3176 train 6.764287 (lr=6.7260e-05) (hash(x)=23681759) +3177 train 7.053956 (lr=6.7212e-05) (hash(x)=25786577) +3178 train 7.028774 (lr=6.7164e-05) (hash(x)=27307614) +3179 train 7.058043 (lr=6.7116e-05) (hash(x)=25082806) +3180 train 7.000577 (lr=6.7069e-05) (hash(x)=26098308) +3181 train 6.812013 (lr=6.7021e-05) (hash(x)=24080140) +3182 train 7.026271 (lr=6.6973e-05) (hash(x)=26399395) +3183 train 7.055923 (lr=6.6925e-05) (hash(x)=23104539) +3184 train 6.719506 (lr=6.6877e-05) (hash(x)=23356930) +3185 train 6.961069 (lr=6.6829e-05) (hash(x)=27972420) +3186 train 6.631247 (lr=6.6782e-05) (hash(x)=21338924) +3187 train 7.108430 (lr=6.6734e-05) (hash(x)=25351113) +3188 train 7.020116 (lr=6.6686e-05) (hash(x)=26019439) +3189 train 7.092979 (lr=6.6638e-05) (hash(x)=30149312) +3190 train 6.726524 (lr=6.6591e-05) (hash(x)=23028152) +3191 train 7.142691 (lr=6.6543e-05) (hash(x)=23018983) +3192 train 6.744797 (lr=6.6495e-05) (hash(x)=23190787) +3193 train 7.169956 (lr=6.6447e-05) (hash(x)=27798543) +3194 train 6.959194 (lr=6.6400e-05) (hash(x)=25193663) +3195 train 6.758553 (lr=6.6352e-05) (hash(x)=25302106) +3196 train 6.921306 (lr=6.6304e-05) (hash(x)=24325364) +3197 train 6.936995 (lr=6.6257e-05) (hash(x)=25399101) +3198 train 6.776213 (lr=6.6209e-05) (hash(x)=23606439) +3199 train 6.850709 (lr=6.6161e-05) (hash(x)=24422929) +3200 val loss 6.9516 +3200 val perplexity 1044.8496 +3200 train 7.010690 (lr=6.6114e-05) (hash(x)=24760381) +3201 train 6.626883 (lr=6.6066e-05) (hash(x)=23278576) +3202 train 6.904172 (lr=6.6018e-05) (hash(x)=24897511) +3203 train 7.243408 (lr=6.5971e-05) (hash(x)=29052117) +3204 train 6.895093 (lr=6.5923e-05) (hash(x)=25772923) +3205 train 7.070468 (lr=6.5876e-05) (hash(x)=25885977) +3206 train 6.861331 (lr=6.5828e-05) (hash(x)=21985272) +3207 train 6.769063 (lr=6.5781e-05) (hash(x)=23389696) +3208 train 6.687192 (lr=6.5733e-05) (hash(x)=25299042) +3209 train 7.031387 (lr=6.5686e-05) (hash(x)=23703987) +3210 train 6.857678 (lr=6.5638e-05) (hash(x)=23362342) +3211 train 6.950337 (lr=6.5591e-05) (hash(x)=23962503) +3212 train 6.801613 (lr=6.5543e-05) (hash(x)=21216023) +3213 train 6.908116 (lr=6.5496e-05) (hash(x)=25841931) +3214 train 6.756931 (lr=6.5448e-05) (hash(x)=23631428) +3215 train 7.151029 (lr=6.5401e-05) (hash(x)=29102969) +3216 train 6.907567 (lr=6.5353e-05) (hash(x)=25782766) +3217 train 7.172443 (lr=6.5306e-05) (hash(x)=28825867) +3218 train 7.136841 (lr=6.5259e-05) (hash(x)=24609499) +3219 train 7.033115 (lr=6.5211e-05) (hash(x)=24948166) +3220 train 7.150601 (lr=6.5164e-05) (hash(x)=26919841) +3221 train 6.953964 (lr=6.5117e-05) (hash(x)=27236198) +3222 train 6.732513 (lr=6.5069e-05) (hash(x)=24029305) +3223 train 7.332021 (lr=6.5022e-05) (hash(x)=28359859) +3224 train 7.085290 (lr=6.4975e-05) (hash(x)=24886008) +3225 train 6.907720 (lr=6.4927e-05) (hash(x)=27159867) +3226 train 7.209095 (lr=6.4880e-05) (hash(x)=20672023) +3227 train 6.849389 (lr=6.4833e-05) (hash(x)=22360298) +3228 train 7.296331 (lr=6.4786e-05) (hash(x)=27478658) +3229 train 7.089754 (lr=6.4738e-05) (hash(x)=26575886) +3230 train 7.296713 (lr=6.4691e-05) (hash(x)=26890615) +3231 train 6.879463 (lr=6.4644e-05) (hash(x)=24630955) +3232 train 7.188436 (lr=6.4597e-05) (hash(x)=27016054) +3233 train 7.358588 (lr=6.4549e-05) (hash(x)=28444407) +3234 train 6.769901 (lr=6.4502e-05) (hash(x)=24053336) +3235 train 7.077795 (lr=6.4455e-05) (hash(x)=26897402) +3236 train 7.223245 (lr=6.4408e-05) (hash(x)=29451214) +3237 train 6.982449 (lr=6.4361e-05) (hash(x)=27268677) +3238 train 7.184033 (lr=6.4314e-05) (hash(x)=27494000) +3239 train 6.759958 (lr=6.4267e-05) (hash(x)=22969113) +3240 train 6.747613 (lr=6.4219e-05) (hash(x)=21944576) +3241 train 6.937845 (lr=6.4172e-05) (hash(x)=21671079) +3242 train 6.833542 (lr=6.4125e-05) (hash(x)=23912980) +3243 train 6.814462 (lr=6.4078e-05) (hash(x)=25205781) +3244 train 6.799835 (lr=6.4031e-05) (hash(x)=25654244) +3245 train 6.737499 (lr=6.3984e-05) (hash(x)=23335929) +3246 train 7.131110 (lr=6.3937e-05) (hash(x)=27953926) +3247 train 6.916532 (lr=6.3890e-05) (hash(x)=27004415) +3248 train 6.554161 (lr=6.3843e-05) (hash(x)=20471566) +3249 train 6.804153 (lr=6.3796e-05) (hash(x)=25797941) +3250 val loss 6.9455 +3250 val perplexity 1038.4878 +3250 train 6.675243 (lr=6.3749e-05) (hash(x)=21787064) +3251 train 6.697276 (lr=6.3702e-05) (hash(x)=22974875) +3252 train 6.965354 (lr=6.3655e-05) (hash(x)=28431267) +3253 train 6.853536 (lr=6.3609e-05) (hash(x)=25584910) +3254 train 6.658128 (lr=6.3562e-05) (hash(x)=23888922) +3255 train 6.868762 (lr=6.3515e-05) (hash(x)=22265063) +3256 train 6.442418 (lr=6.3468e-05) (hash(x)=21926624) +3257 train 6.779758 (lr=6.3421e-05) (hash(x)=23073191) +3258 train 6.753833 (lr=6.3374e-05) (hash(x)=24409183) +3259 train 6.850575 (lr=6.3327e-05) (hash(x)=23312114) +3260 train 6.727112 (lr=6.3281e-05) (hash(x)=21001289) +3261 train 6.969602 (lr=6.3234e-05) (hash(x)=25514824) +3262 train 6.719578 (lr=6.3187e-05) (hash(x)=22526800) +3263 train 7.145920 (lr=6.3140e-05) (hash(x)=26905990) +3264 train 6.812085 (lr=6.3093e-05) (hash(x)=24469631) +3265 train 6.683994 (lr=6.3047e-05) (hash(x)=21149081) +3266 train 6.848545 (lr=6.3000e-05) (hash(x)=24696215) +3267 train 7.148021 (lr=6.2953e-05) (hash(x)=27089280) +3268 train 6.719892 (lr=6.2907e-05) (hash(x)=23100446) +3269 train 6.977715 (lr=6.2860e-05) (hash(x)=25061229) +3270 train 6.873664 (lr=6.2813e-05) (hash(x)=24337543) +3271 train 6.916550 (lr=6.2767e-05) (hash(x)=24047679) +3272 train 7.008436 (lr=6.2720e-05) (hash(x)=27616773) +3273 train 6.908716 (lr=6.2673e-05) (hash(x)=25315110) +3274 train 6.973115 (lr=6.2627e-05) (hash(x)=28354645) +3275 train 6.818166 (lr=6.2580e-05) (hash(x)=25034684) +3276 train 6.862257 (lr=6.2533e-05) (hash(x)=23550342) +3277 train 7.612191 (lr=6.2487e-05) (hash(x)=28661487) +3278 train 7.116397 (lr=6.2440e-05) (hash(x)=24724622) +3279 train 7.029098 (lr=6.2394e-05) (hash(x)=26905582) +3280 train 7.123268 (lr=6.2347e-05) (hash(x)=26838818) +3281 train 6.824170 (lr=6.2301e-05) (hash(x)=23949017) +3282 train 6.326439 (lr=6.2254e-05) (hash(x)=18846300) +3283 train 6.689134 (lr=6.2208e-05) (hash(x)=21406950) +3284 train 6.512292 (lr=6.2161e-05) (hash(x)=21157696) +3285 train 6.638773 (lr=6.2115e-05) (hash(x)=21440152) +3286 train 6.823941 (lr=6.2068e-05) (hash(x)=26749182) +3287 train 7.041782 (lr=6.2022e-05) (hash(x)=29018970) +3288 train 6.965236 (lr=6.1976e-05) (hash(x)=27577517) +3289 train 6.631529 (lr=6.1929e-05) (hash(x)=19190537) +3290 train 6.652944 (lr=6.1883e-05) (hash(x)=21957991) +3291 train 6.699684 (lr=6.1836e-05) (hash(x)=20853530) +3292 train 6.607270 (lr=6.1790e-05) (hash(x)=22291731) +3293 train 6.844143 (lr=6.1744e-05) (hash(x)=23786853) +3294 train 6.948232 (lr=6.1697e-05) (hash(x)=25740147) +3295 train 7.079788 (lr=6.1651e-05) (hash(x)=24503315) +3296 train 6.796639 (lr=6.1605e-05) (hash(x)=22541728) +3297 train 7.107314 (lr=6.1559e-05) (hash(x)=27067328) +3298 train 6.745680 (lr=6.1512e-05) (hash(x)=22600715) +3299 train 6.780099 (lr=6.1466e-05) (hash(x)=23080074) +3300 val loss 6.9457 +3300 val perplexity 1038.6884 +3300 train 6.555989 (lr=6.1420e-05) (hash(x)=22097758) +3301 train 6.729404 (lr=6.1374e-05) (hash(x)=24105430) +3302 train 6.614711 (lr=6.1327e-05) (hash(x)=23343775) +3303 train 6.883775 (lr=6.1281e-05) (hash(x)=22607537) +3304 train 6.941864 (lr=6.1235e-05) (hash(x)=26501182) +3305 train 7.206123 (lr=6.1189e-05) (hash(x)=26063650) +3306 train 6.806335 (lr=6.1143e-05) (hash(x)=23486602) +3307 train 7.768999 (lr=6.1097e-05) (hash(x)=32179773) +3308 train 11.273172 (lr=6.1050e-05) (hash(x)=66155855) +3309 train 8.302658 (lr=6.1004e-05) (hash(x)=37724427) +3310 train 7.353237 (lr=6.0958e-05) (hash(x)=28861610) +3311 train 7.289868 (lr=6.0912e-05) (hash(x)=26690225) +3312 train 6.800321 (lr=6.0866e-05) (hash(x)=24136450) +3313 train 7.028333 (lr=6.0820e-05) (hash(x)=23702010) +3314 train 7.257812 (lr=6.0774e-05) (hash(x)=28761762) +3315 train 6.556831 (lr=6.0728e-05) (hash(x)=22109609) +3316 train 6.959670 (lr=6.0682e-05) (hash(x)=25168631) +3317 train 6.890611 (lr=6.0636e-05) (hash(x)=24503786) +3318 train 6.886694 (lr=6.0590e-05) (hash(x)=23698606) +3319 train 6.961238 (lr=6.0544e-05) (hash(x)=24226255) +3320 train 7.473519 (lr=6.0498e-05) (hash(x)=31110577) +3321 train 6.874765 (lr=6.0452e-05) (hash(x)=24752754) +3322 train 6.735727 (lr=6.0406e-05) (hash(x)=21135610) +3323 train 6.688985 (lr=6.0361e-05) (hash(x)=23013573) +3324 train 6.407887 (lr=6.0315e-05) (hash(x)=20289715) +3325 train 6.693317 (lr=6.0269e-05) (hash(x)=22700287) +3326 train 6.769084 (lr=6.0223e-05) (hash(x)=21320362) +3327 train 6.939937 (lr=6.0177e-05) (hash(x)=23622702) +3328 train 7.165973 (lr=6.0131e-05) (hash(x)=27435461) +3329 train 6.933644 (lr=6.0086e-05) (hash(x)=25435452) +3330 train 6.935992 (lr=6.0040e-05) (hash(x)=27952557) +3331 train 6.592511 (lr=5.9994e-05) (hash(x)=21517429) +3332 train 6.716946 (lr=5.9948e-05) (hash(x)=24288985) +3333 train 6.898689 (lr=5.9903e-05) (hash(x)=23374788) +3334 train 6.674020 (lr=5.9857e-05) (hash(x)=22042499) +3335 train 6.977423 (lr=5.9811e-05) (hash(x)=23910425) +3336 train 7.277790 (lr=5.9765e-05) (hash(x)=28118508) +3337 train 7.033176 (lr=5.9720e-05) (hash(x)=26737440) +3338 train 6.806504 (lr=5.9674e-05) (hash(x)=24472271) +3339 train 6.764511 (lr=5.9628e-05) (hash(x)=24407484) +3340 train 7.356912 (lr=5.9583e-05) (hash(x)=27908937) +3341 train 7.459172 (lr=5.9537e-05) (hash(x)=29038937) +3342 train 7.216639 (lr=5.9492e-05) (hash(x)=24802580) +3343 train 7.204131 (lr=5.9446e-05) (hash(x)=27213318) +3344 train 7.299863 (lr=5.9401e-05) (hash(x)=28693458) +3345 train 6.513282 (lr=5.9355e-05) (hash(x)=20332324) +3346 train 6.955509 (lr=5.9309e-05) (hash(x)=26726007) +3347 train 6.856748 (lr=5.9264e-05) (hash(x)=25524191) +3348 train 6.943234 (lr=5.9218e-05) (hash(x)=25553293) +3349 train 6.870175 (lr=5.9173e-05) (hash(x)=25614848) +3350 val loss 6.9564 +3350 val perplexity 1049.8462 +3350 train 6.969777 (lr=5.9128e-05) (hash(x)=25747903) +3351 train 6.937963 (lr=5.9082e-05) (hash(x)=26701577) +3352 train 6.657826 (lr=5.9037e-05) (hash(x)=21964135) +3353 train 6.800012 (lr=5.8991e-05) (hash(x)=24461007) +3354 train 6.832136 (lr=5.8946e-05) (hash(x)=25818495) +3355 train 6.678519 (lr=5.8900e-05) (hash(x)=22091266) +3356 train 6.667264 (lr=5.8855e-05) (hash(x)=24476213) +3357 train 7.066464 (lr=5.8810e-05) (hash(x)=24500423) +3358 train 6.794815 (lr=5.8764e-05) (hash(x)=21754841) +3359 train 7.131439 (lr=5.8719e-05) (hash(x)=26216794) +3360 train 6.580904 (lr=5.8674e-05) (hash(x)=24267249) +3361 train 6.951766 (lr=5.8628e-05) (hash(x)=23143515) +3362 train 6.820532 (lr=5.8583e-05) (hash(x)=24120302) +3363 train 7.044966 (lr=5.8538e-05) (hash(x)=20817340) +3364 train 6.950226 (lr=5.8493e-05) (hash(x)=22285847) +3365 train 7.245946 (lr=5.8447e-05) (hash(x)=28151597) +3366 train 7.606422 (lr=5.8402e-05) (hash(x)=31593285) +3367 train 7.262344 (lr=5.8357e-05) (hash(x)=27579623) +3368 train 6.912749 (lr=5.8312e-05) (hash(x)=24995988) +3369 train 6.520549 (lr=5.8267e-05) (hash(x)=22166810) +3370 train 6.843183 (lr=5.8222e-05) (hash(x)=23948298) +3371 train 6.721944 (lr=5.8176e-05) (hash(x)=21532187) +3372 train 6.793892 (lr=5.8131e-05) (hash(x)=23571652) +3373 train 7.203857 (lr=5.8086e-05) (hash(x)=26911513) +3374 train 7.135462 (lr=5.8041e-05) (hash(x)=24011329) +3375 train 7.320616 (lr=5.7996e-05) (hash(x)=26086198) +3376 train 6.871767 (lr=5.7951e-05) (hash(x)=22844402) +3377 train 6.810362 (lr=5.7906e-05) (hash(x)=21817762) +3378 train 6.857077 (lr=5.7861e-05) (hash(x)=23903232) +3379 train 6.854022 (lr=5.7816e-05) (hash(x)=23911729) +3380 train 6.837252 (lr=5.7771e-05) (hash(x)=24485288) +3381 train 7.022882 (lr=5.7726e-05) (hash(x)=27955492) +3382 train 6.740823 (lr=5.7681e-05) (hash(x)=25884586) +3383 train 6.964380 (lr=5.7636e-05) (hash(x)=24863441) +3384 train 7.258396 (lr=5.7591e-05) (hash(x)=22045992) +3385 train 7.325626 (lr=5.7546e-05) (hash(x)=29174796) +3386 train 7.607278 (lr=5.7502e-05) (hash(x)=32589942) +3387 train 7.219906 (lr=5.7457e-05) (hash(x)=28856978) +3388 train 6.679092 (lr=5.7412e-05) (hash(x)=21667904) +3389 train 6.680204 (lr=5.7367e-05) (hash(x)=23431801) +3390 train 6.484954 (lr=5.7322e-05) (hash(x)=20877285) +3391 train 6.762793 (lr=5.7277e-05) (hash(x)=25236385) +3392 train 7.065376 (lr=5.7233e-05) (hash(x)=25373071) +3393 train 7.200453 (lr=5.7188e-05) (hash(x)=25713464) +3394 train 7.130432 (lr=5.7143e-05) (hash(x)=25713475) +3395 train 6.977625 (lr=5.7098e-05) (hash(x)=24278687) +3396 train 7.119829 (lr=5.7054e-05) (hash(x)=27491349) +3397 train 7.030473 (lr=5.7009e-05) (hash(x)=24513692) +3398 train 7.134828 (lr=5.6964e-05) (hash(x)=26853415) +3399 train 7.189727 (lr=5.6920e-05) (hash(x)=25330803) +3400 val loss 6.9348 +3400 val perplexity 1027.3767 +3400 train 7.160875 (lr=5.6875e-05) (hash(x)=26578066) +3401 train 7.165541 (lr=5.6830e-05) (hash(x)=26811522) +3402 train 6.852936 (lr=5.6786e-05) (hash(x)=25611092) +3403 train 6.633321 (lr=5.6741e-05) (hash(x)=21568545) +3404 train 6.671486 (lr=5.6697e-05) (hash(x)=22756484) +3405 train 6.925548 (lr=5.6652e-05) (hash(x)=27927608) +3406 train 6.979741 (lr=5.6607e-05) (hash(x)=27497018) +3407 train 6.792542 (lr=5.6563e-05) (hash(x)=22508532) +3408 train 7.245780 (lr=5.6518e-05) (hash(x)=26673287) +3409 train 6.855945 (lr=5.6474e-05) (hash(x)=23675869) +3410 train 6.811191 (lr=5.6429e-05) (hash(x)=25496948) +3411 train 6.804498 (lr=5.6385e-05) (hash(x)=24850662) +3412 train 7.061012 (lr=5.6341e-05) (hash(x)=29790167) +3413 train 6.686859 (lr=5.6296e-05) (hash(x)=24193434) +3414 train 7.127925 (lr=5.6252e-05) (hash(x)=25310919) +3415 train 6.719337 (lr=5.6207e-05) (hash(x)=21799261) +3416 train 7.059566 (lr=5.6163e-05) (hash(x)=26620074) +3417 train 7.000246 (lr=5.6119e-05) (hash(x)=26719309) +3418 train 7.366043 (lr=5.6074e-05) (hash(x)=23190530) +3419 train 6.957561 (lr=5.6030e-05) (hash(x)=24884891) +3420 train 6.955208 (lr=5.5986e-05) (hash(x)=25545849) +3421 train 6.910017 (lr=5.5941e-05) (hash(x)=26021405) +3422 train 6.855814 (lr=5.5897e-05) (hash(x)=23887343) +3423 train 6.946106 (lr=5.5853e-05) (hash(x)=26311168) +3424 train 6.585390 (lr=5.5809e-05) (hash(x)=21051541) +3425 train 6.976114 (lr=5.5764e-05) (hash(x)=23553179) +3426 train 6.853446 (lr=5.5720e-05) (hash(x)=24345540) +3427 train 7.310127 (lr=5.5676e-05) (hash(x)=27549895) +3428 train 6.615856 (lr=5.5632e-05) (hash(x)=22559753) +3429 train 6.594594 (lr=5.5588e-05) (hash(x)=21647642) +3430 train 6.487521 (lr=5.5544e-05) (hash(x)=20130901) +3431 train 6.598724 (lr=5.5499e-05) (hash(x)=20977430) +3432 train 6.647725 (lr=5.5455e-05) (hash(x)=21356429) +3433 train 6.637048 (lr=5.5411e-05) (hash(x)=23494380) +3434 train 6.890620 (lr=5.5367e-05) (hash(x)=23805501) +3435 train 6.846646 (lr=5.5323e-05) (hash(x)=23448855) +3436 train 7.198660 (lr=5.5279e-05) (hash(x)=26000319) +3437 train 6.636712 (lr=5.5235e-05) (hash(x)=21760032) +3438 train 6.811616 (lr=5.5191e-05) (hash(x)=24424886) +3439 train 7.218151 (lr=5.5147e-05) (hash(x)=26941617) +3440 train 7.247195 (lr=5.5103e-05) (hash(x)=26798528) +3441 train 7.253095 (lr=5.5059e-05) (hash(x)=27464193) +3442 train 7.177139 (lr=5.5015e-05) (hash(x)=25649118) +3443 train 7.154488 (lr=5.4971e-05) (hash(x)=26953192) +3444 train 6.991067 (lr=5.4928e-05) (hash(x)=22224958) +3445 train 6.811161 (lr=5.4884e-05) (hash(x)=24044587) +3446 train 7.246463 (lr=5.4840e-05) (hash(x)=29584466) +3447 train 7.671993 (lr=5.4796e-05) (hash(x)=30008957) +3448 train 7.479039 (lr=5.4752e-05) (hash(x)=26059290) +3449 train 6.446845 (lr=5.4708e-05) (hash(x)=19733965) +3450 val loss 6.9416 +3450 val perplexity 1034.4091 +3450 train 6.988662 (lr=5.4665e-05) (hash(x)=23960200) +3451 train 7.183358 (lr=5.4621e-05) (hash(x)=27069893) +3452 train 6.791683 (lr=5.4577e-05) (hash(x)=23947772) +3453 train 6.850320 (lr=5.4533e-05) (hash(x)=22707406) +3454 train 7.071092 (lr=5.4490e-05) (hash(x)=27832550) +3455 train 6.920452 (lr=5.4446e-05) (hash(x)=27125962) +3456 train 6.794563 (lr=5.4402e-05) (hash(x)=24510254) +3457 train 6.604444 (lr=5.4359e-05) (hash(x)=23545652) +3458 train 6.669182 (lr=5.4315e-05) (hash(x)=23554751) +3459 train 6.788518 (lr=5.4271e-05) (hash(x)=23341415) +3460 train 6.994516 (lr=5.4228e-05) (hash(x)=21784583) +3461 train 6.759340 (lr=5.4184e-05) (hash(x)=22214769) +3462 train 6.831899 (lr=5.4141e-05) (hash(x)=24206922) +3463 train 6.918060 (lr=5.4097e-05) (hash(x)=25888358) +3464 train 6.743138 (lr=5.4054e-05) (hash(x)=22689666) +3465 train 6.880685 (lr=5.4010e-05) (hash(x)=24918697) +3466 train 7.141829 (lr=5.3967e-05) (hash(x)=28237214) +3467 train 7.250368 (lr=5.3923e-05) (hash(x)=26761645) +3468 train 6.916312 (lr=5.3880e-05) (hash(x)=26979307) +3469 train 6.820612 (lr=5.3836e-05) (hash(x)=23553754) +3470 train 6.969753 (lr=5.3793e-05) (hash(x)=25256849) +3471 train 6.817578 (lr=5.3749e-05) (hash(x)=21725719) +3472 train 6.945953 (lr=5.3706e-05) (hash(x)=24897801) +3473 train 6.873648 (lr=5.3663e-05) (hash(x)=26175307) +3474 train 6.663467 (lr=5.3619e-05) (hash(x)=23309218) +3475 train 6.723794 (lr=5.3576e-05) (hash(x)=25746493) +3476 train 7.051494 (lr=5.3533e-05) (hash(x)=27169613) +3477 train 6.790697 (lr=5.3489e-05) (hash(x)=22937341) +3478 train 6.901680 (lr=5.3446e-05) (hash(x)=24250636) +3479 train 6.715382 (lr=5.3403e-05) (hash(x)=21669704) +3480 train 6.718998 (lr=5.3360e-05) (hash(x)=24431839) +3481 train 6.753015 (lr=5.3316e-05) (hash(x)=22763387) +3482 train 6.751956 (lr=5.3273e-05) (hash(x)=20489446) +3483 train 6.726984 (lr=5.3230e-05) (hash(x)=21167493) +3484 train 6.711812 (lr=5.3187e-05) (hash(x)=23465087) +3485 train 6.911060 (lr=5.3144e-05) (hash(x)=26175023) +3486 train 6.996813 (lr=5.3101e-05) (hash(x)=24986207) +3487 train 6.599138 (lr=5.3058e-05) (hash(x)=23166993) +3488 train 6.898590 (lr=5.3014e-05) (hash(x)=25281216) +3489 train 6.639743 (lr=5.2971e-05) (hash(x)=21824285) +3490 train 6.679765 (lr=5.2928e-05) (hash(x)=22352750) +3491 train 6.956882 (lr=5.2885e-05) (hash(x)=23947208) +3492 train 7.011903 (lr=5.2842e-05) (hash(x)=26257363) +3493 train 6.854857 (lr=5.2799e-05) (hash(x)=25103214) +3494 train 6.912284 (lr=5.2756e-05) (hash(x)=25267583) +3495 train 6.958719 (lr=5.2713e-05) (hash(x)=26235974) +3496 train 7.176886 (lr=5.2670e-05) (hash(x)=26430769) +3497 train 7.573516 (lr=5.2627e-05) (hash(x)=28282027) +3498 train 7.373355 (lr=5.2585e-05) (hash(x)=28386462) +3499 train 7.053270 (lr=5.2542e-05) (hash(x)=29822604) +3500 val loss 6.9284 +3500 val perplexity 1020.8360 +3500 train 6.964994 (lr=5.2499e-05) (hash(x)=29225386) +3501 train 6.844374 (lr=5.2456e-05) (hash(x)=25249294) +3502 train 6.578019 (lr=5.2413e-05) (hash(x)=20020741) +3503 train 6.741693 (lr=5.2370e-05) (hash(x)=25426430) +3504 train 6.747417 (lr=5.2328e-05) (hash(x)=25720411) +3505 train 6.777835 (lr=5.2285e-05) (hash(x)=25602639) +3506 train 6.872841 (lr=5.2242e-05) (hash(x)=26724388) +3507 train 6.800946 (lr=5.2199e-05) (hash(x)=26043735) +3508 train 6.715390 (lr=5.2157e-05) (hash(x)=24955163) +3509 train 6.722688 (lr=5.2114e-05) (hash(x)=20936107) +3510 train 6.730183 (lr=5.2071e-05) (hash(x)=20317378) +3511 train 6.770567 (lr=5.2029e-05) (hash(x)=22966314) +3512 train 7.076623 (lr=5.1986e-05) (hash(x)=25870930) +3513 train 6.890501 (lr=5.1943e-05) (hash(x)=24656635) +3514 train 7.168521 (lr=5.1901e-05) (hash(x)=28576810) +3515 train 7.084714 (lr=5.1858e-05) (hash(x)=27944619) +3516 train 6.875206 (lr=5.1816e-05) (hash(x)=27421509) +3517 train 6.622154 (lr=5.1773e-05) (hash(x)=20844620) +3518 train 6.851198 (lr=5.1731e-05) (hash(x)=28569406) +3519 train 6.753862 (lr=5.1688e-05) (hash(x)=23448505) +3520 train 6.966929 (lr=5.1646e-05) (hash(x)=24852577) +3521 train 6.787287 (lr=5.1603e-05) (hash(x)=23963103) +3522 train 6.686344 (lr=5.1561e-05) (hash(x)=24816516) +3523 train 6.899437 (lr=5.1518e-05) (hash(x)=24205942) +3524 train 6.451637 (lr=5.1476e-05) (hash(x)=20988660) +3525 train 6.532243 (lr=5.1433e-05) (hash(x)=21631366) +3526 train 6.765723 (lr=5.1391e-05) (hash(x)=23499370) +3527 train 6.895891 (lr=5.1349e-05) (hash(x)=26330693) +3528 train 6.526759 (lr=5.1306e-05) (hash(x)=23937176) +3529 train 6.816631 (lr=5.1264e-05) (hash(x)=27345885) +3530 train 6.522233 (lr=5.1222e-05) (hash(x)=21104610) +3531 train 6.927766 (lr=5.1179e-05) (hash(x)=24844466) +3532 train 6.234476 (lr=5.1137e-05) (hash(x)=21055483) +3533 train 6.609892 (lr=5.1095e-05) (hash(x)=23229414) +3534 train 6.928941 (lr=5.1053e-05) (hash(x)=26676920) +3535 train 6.888046 (lr=5.1011e-05) (hash(x)=29550596) +3536 train 6.649889 (lr=5.0968e-05) (hash(x)=22231942) +3537 train 6.834854 (lr=5.0926e-05) (hash(x)=25843852) +3538 train 6.995361 (lr=5.0884e-05) (hash(x)=27110533) +3539 train 6.458017 (lr=5.0842e-05) (hash(x)=20506540) +3540 train 6.627005 (lr=5.0800e-05) (hash(x)=21599346) +3541 train 6.865598 (lr=5.0758e-05) (hash(x)=26395519) +3542 train 6.808821 (lr=5.0716e-05) (hash(x)=25892512) +3543 train 6.867964 (lr=5.0674e-05) (hash(x)=22124892) +3544 train 6.762145 (lr=5.0632e-05) (hash(x)=21882567) +3545 train 6.805260 (lr=5.0590e-05) (hash(x)=24316212) +3546 train 6.725446 (lr=5.0548e-05) (hash(x)=24296310) +3547 train 6.818314 (lr=5.0506e-05) (hash(x)=24867036) +3548 train 6.817760 (lr=5.0464e-05) (hash(x)=23351896) +3549 train 6.779060 (lr=5.0422e-05) (hash(x)=21576408) +3550 val loss 6.9220 +3550 val perplexity 1014.3055 +3550 train 6.954858 (lr=5.0380e-05) (hash(x)=26377338) +3551 train 6.730671 (lr=5.0338e-05) (hash(x)=25607640) +3552 train 7.052454 (lr=5.0296e-05) (hash(x)=27619776) +3553 train 6.584586 (lr=5.0254e-05) (hash(x)=23454533) +3554 train 6.750808 (lr=5.0212e-05) (hash(x)=22542519) +3555 train 6.823187 (lr=5.0171e-05) (hash(x)=26176930) +3556 train 6.637849 (lr=5.0129e-05) (hash(x)=22815181) +3557 train 6.639349 (lr=5.0087e-05) (hash(x)=21821757) +3558 train 6.684540 (lr=5.0045e-05) (hash(x)=23988293) +3559 train 6.600428 (lr=5.0004e-05) (hash(x)=23795894) +3560 train 6.545197 (lr=4.9962e-05) (hash(x)=22898969) +3561 train 6.542564 (lr=4.9920e-05) (hash(x)=21510825) +3562 train 6.470284 (lr=4.9879e-05) (hash(x)=22499317) +3563 train 6.521801 (lr=4.9837e-05) (hash(x)=23756298) +3564 train 6.556154 (lr=4.9795e-05) (hash(x)=23964512) +3565 train 6.612128 (lr=4.9754e-05) (hash(x)=23262803) +3566 train 6.817944 (lr=4.9712e-05) (hash(x)=23347279) +3567 train 6.709943 (lr=4.9671e-05) (hash(x)=24165449) +3568 train 6.855806 (lr=4.9629e-05) (hash(x)=25503946) +3569 train 6.817132 (lr=4.9587e-05) (hash(x)=26532839) +3570 train 6.468466 (lr=4.9546e-05) (hash(x)=21889816) +3571 train 6.775684 (lr=4.9504e-05) (hash(x)=26643739) +3572 train 6.988927 (lr=4.9463e-05) (hash(x)=26826130) +3573 train 6.991425 (lr=4.9422e-05) (hash(x)=25810624) +3574 train 6.868832 (lr=4.9380e-05) (hash(x)=23080331) +3575 train 6.981857 (lr=4.9339e-05) (hash(x)=24697756) +3576 train 6.851587 (lr=4.9297e-05) (hash(x)=25158900) +3577 train 6.995860 (lr=4.9256e-05) (hash(x)=25793633) +3578 train 6.537029 (lr=4.9215e-05) (hash(x)=21468493) +3579 train 6.933549 (lr=4.9173e-05) (hash(x)=24431101) +3580 train 6.718296 (lr=4.9132e-05) (hash(x)=27314357) +3581 train 6.960288 (lr=4.9091e-05) (hash(x)=26286249) +3582 train 7.156480 (lr=4.9049e-05) (hash(x)=25954856) +3583 train 7.056367 (lr=4.9008e-05) (hash(x)=27218899) +3584 train 6.866228 (lr=4.8967e-05) (hash(x)=24249114) +3585 train 6.731576 (lr=4.8926e-05) (hash(x)=23659934) +3586 train 6.729885 (lr=4.8885e-05) (hash(x)=25995600) +3587 train 6.722527 (lr=4.8843e-05) (hash(x)=29462219) +3588 train 6.829985 (lr=4.8802e-05) (hash(x)=23346714) +3589 train 6.976491 (lr=4.8761e-05) (hash(x)=27168432) +3590 train 6.761092 (lr=4.8720e-05) (hash(x)=23954240) +3591 train 6.731843 (lr=4.8679e-05) (hash(x)=24748522) +3592 train 6.923409 (lr=4.8638e-05) (hash(x)=24887007) +3593 train 6.683370 (lr=4.8597e-05) (hash(x)=25539383) +3594 train 6.604494 (lr=4.8556e-05) (hash(x)=20104613) +3595 train 7.148720 (lr=4.8515e-05) (hash(x)=24843486) +3596 train 7.148406 (lr=4.8474e-05) (hash(x)=24357864) +3597 train 6.822994 (lr=4.8433e-05) (hash(x)=23873745) +3598 train 6.941689 (lr=4.8392e-05) (hash(x)=25142829) +3599 train 7.023768 (lr=4.8351e-05) (hash(x)=24965317) +3600 val loss 6.9134 +3600 val perplexity 1005.6201 +3600 train 6.470205 (lr=4.8310e-05) (hash(x)=18505205) +3601 train 6.509544 (lr=4.8269e-05) (hash(x)=23632877) +3602 train 6.770299 (lr=4.8228e-05) (hash(x)=23704554) +3603 train 6.938591 (lr=4.8187e-05) (hash(x)=26584754) +3604 train 6.539038 (lr=4.8147e-05) (hash(x)=20667709) +3605 train 6.417882 (lr=4.8106e-05) (hash(x)=20573248) +3606 train 6.580158 (lr=4.8065e-05) (hash(x)=23998997) +3607 train 6.757572 (lr=4.8024e-05) (hash(x)=22031210) +3608 train 6.779081 (lr=4.7984e-05) (hash(x)=24124536) +3609 train 6.724651 (lr=4.7943e-05) (hash(x)=22650144) +3610 train 6.790544 (lr=4.7902e-05) (hash(x)=23796998) +3611 train 6.841908 (lr=4.7861e-05) (hash(x)=24860582) +3612 train 6.339604 (lr=4.7821e-05) (hash(x)=20591300) +3613 train 6.773711 (lr=4.7780e-05) (hash(x)=23447130) +3614 train 6.798345 (lr=4.7740e-05) (hash(x)=26237963) +3615 train 6.903835 (lr=4.7699e-05) (hash(x)=25877990) +3616 train 6.686193 (lr=4.7658e-05) (hash(x)=24808003) +3617 train 6.898405 (lr=4.7618e-05) (hash(x)=24103543) +3618 train 6.814860 (lr=4.7577e-05) (hash(x)=24877184) +3619 train 6.855191 (lr=4.7537e-05) (hash(x)=24970646) +3620 train 6.865898 (lr=4.7496e-05) (hash(x)=25764524) +3621 train 7.019080 (lr=4.7456e-05) (hash(x)=25313591) +3622 train 6.860963 (lr=4.7415e-05) (hash(x)=23260940) +3623 train 6.798985 (lr=4.7375e-05) (hash(x)=24382381) +3624 train 6.716474 (lr=4.7335e-05) (hash(x)=24618902) +3625 train 6.909110 (lr=4.7294e-05) (hash(x)=25074871) +3626 train 6.620758 (lr=4.7254e-05) (hash(x)=24472251) +3627 train 6.782846 (lr=4.7214e-05) (hash(x)=25221746) +3628 train 6.869153 (lr=4.7173e-05) (hash(x)=27448790) +3629 train 6.844543 (lr=4.7133e-05) (hash(x)=25221431) +3630 train 6.374962 (lr=4.7093e-05) (hash(x)=22034366) +3631 train 6.979202 (lr=4.7052e-05) (hash(x)=24551999) +3632 train 6.647773 (lr=4.7012e-05) (hash(x)=24330217) +3633 train 6.810013 (lr=4.6972e-05) (hash(x)=22792380) +3634 train 6.565918 (lr=4.6932e-05) (hash(x)=22393767) +3635 train 6.876889 (lr=4.6892e-05) (hash(x)=28151378) +3636 train 6.909078 (lr=4.6851e-05) (hash(x)=26999341) +3637 train 6.902439 (lr=4.6811e-05) (hash(x)=27251870) +3638 train 6.902814 (lr=4.6771e-05) (hash(x)=23439462) +3639 train 6.948017 (lr=4.6731e-05) (hash(x)=25765516) +3640 train 6.837874 (lr=4.6691e-05) (hash(x)=24720171) +3641 train 7.034154 (lr=4.6651e-05) (hash(x)=23927187) +3642 train 6.816963 (lr=4.6611e-05) (hash(x)=23879561) +3643 train 6.919305 (lr=4.6571e-05) (hash(x)=25630696) +3644 train 6.467154 (lr=4.6531e-05) (hash(x)=22030016) +3645 train 6.964450 (lr=4.6491e-05) (hash(x)=28781600) +3646 train 6.961038 (lr=4.6451e-05) (hash(x)=26668019) +3647 train 7.030889 (lr=4.6411e-05) (hash(x)=25204247) +3648 train 7.206046 (lr=4.6371e-05) (hash(x)=31261394) +3649 train 7.027603 (lr=4.6331e-05) (hash(x)=26193103) +3650 val loss 6.9130 +3650 val perplexity 1005.2332 +3650 train 6.818627 (lr=4.6292e-05) (hash(x)=23872456) +3651 train 6.727789 (lr=4.6252e-05) (hash(x)=26326447) +3652 train 6.709917 (lr=4.6212e-05) (hash(x)=26449631) +3653 train 7.021634 (lr=4.6172e-05) (hash(x)=26373461) +3654 train 6.867322 (lr=4.6132e-05) (hash(x)=24882768) +3655 train 6.912727 (lr=4.6093e-05) (hash(x)=26321813) +3656 train 6.972717 (lr=4.6053e-05) (hash(x)=27056428) +3657 train 6.944974 (lr=4.6013e-05) (hash(x)=24583976) +3658 train 6.631669 (lr=4.5973e-05) (hash(x)=22259624) +3659 train 6.755797 (lr=4.5934e-05) (hash(x)=25400396) +3660 train 6.623776 (lr=4.5894e-05) (hash(x)=21095507) +3661 train 6.875817 (lr=4.5855e-05) (hash(x)=27231042) +3662 train 6.692311 (lr=4.5815e-05) (hash(x)=27292771) +3663 train 7.020390 (lr=4.5775e-05) (hash(x)=25528323) +3664 train 6.842432 (lr=4.5736e-05) (hash(x)=24374502) +3665 train 6.627223 (lr=4.5696e-05) (hash(x)=22463800) +3666 train 6.935321 (lr=4.5657e-05) (hash(x)=25413960) +3667 train 6.852039 (lr=4.5617e-05) (hash(x)=24035353) +3668 train 6.761319 (lr=4.5578e-05) (hash(x)=24815852) +3669 train 6.663284 (lr=4.5538e-05) (hash(x)=22995856) +3670 train 6.955818 (lr=4.5499e-05) (hash(x)=28128238) +3671 train 6.935407 (lr=4.5460e-05) (hash(x)=25114729) +3672 train 6.657240 (lr=4.5420e-05) (hash(x)=19337726) +3673 train 7.149887 (lr=4.5381e-05) (hash(x)=26674420) +3674 train 6.598382 (lr=4.5342e-05) (hash(x)=22553270) +3675 train 6.455402 (lr=4.5302e-05) (hash(x)=21634962) +3676 train 6.644903 (lr=4.5263e-05) (hash(x)=23362669) +3677 train 6.839841 (lr=4.5224e-05) (hash(x)=24781824) +3678 train 6.317278 (lr=4.5184e-05) (hash(x)=17909688) +3679 train 7.492203 (lr=4.5145e-05) (hash(x)=31341964) +3680 train 7.102956 (lr=4.5106e-05) (hash(x)=29071335) +3681 train 6.523331 (lr=4.5067e-05) (hash(x)=19486640) +3682 train 6.692101 (lr=4.5028e-05) (hash(x)=24301133) +3683 train 6.895547 (lr=4.4988e-05) (hash(x)=29172813) +3684 train 7.422718 (lr=4.4949e-05) (hash(x)=31501337) +3685 train 7.019812 (lr=4.4910e-05) (hash(x)=27377840) +3686 train 6.798430 (lr=4.4871e-05) (hash(x)=24499761) +3687 train 6.823456 (lr=4.4832e-05) (hash(x)=26326024) +3688 train 6.764062 (lr=4.4793e-05) (hash(x)=23179996) +3689 train 6.433959 (lr=4.4754e-05) (hash(x)=20963675) +3690 train 6.751756 (lr=4.4715e-05) (hash(x)=26650521) +3691 train 6.434819 (lr=4.4676e-05) (hash(x)=20140071) +3692 train 6.465065 (lr=4.4637e-05) (hash(x)=21734340) +3693 train 6.807580 (lr=4.4598e-05) (hash(x)=23848422) +3694 train 6.835564 (lr=4.4559e-05) (hash(x)=27499953) +3695 train 7.078125 (lr=4.4521e-05) (hash(x)=27273311) +3696 train 7.028077 (lr=4.4482e-05) (hash(x)=25741091) +3697 train 6.740757 (lr=4.4443e-05) (hash(x)=22010794) +3698 train 6.844248 (lr=4.4404e-05) (hash(x)=24616138) +3699 train 7.237691 (lr=4.4365e-05) (hash(x)=31276487) +3700 val loss 6.9140 +3700 val perplexity 1006.2835 +3700 train 6.874299 (lr=4.4327e-05) (hash(x)=24042922) +3701 train 6.640704 (lr=4.4288e-05) (hash(x)=21985431) +3702 train 6.492976 (lr=4.4249e-05) (hash(x)=21336316) +3703 train 6.326650 (lr=4.4210e-05) (hash(x)=17819313) +3704 train 6.980400 (lr=4.4172e-05) (hash(x)=27033851) +3705 train 7.011501 (lr=4.4133e-05) (hash(x)=27260043) +3706 train 7.100539 (lr=4.4094e-05) (hash(x)=26847649) +3707 train 6.993849 (lr=4.4056e-05) (hash(x)=25843618) +3708 train 6.968867 (lr=4.4017e-05) (hash(x)=25828009) +3709 train 7.042763 (lr=4.3979e-05) (hash(x)=24960960) +3710 train 7.106724 (lr=4.3940e-05) (hash(x)=24852741) +3711 train 6.568175 (lr=4.3902e-05) (hash(x)=23769243) +3712 train 6.779731 (lr=4.3863e-05) (hash(x)=27110690) +3713 train 6.797914 (lr=4.3825e-05) (hash(x)=22817285) +3714 train 6.453543 (lr=4.3786e-05) (hash(x)=19618355) +3715 train 7.053226 (lr=4.3748e-05) (hash(x)=28731298) +3716 train 6.784948 (lr=4.3709e-05) (hash(x)=23091196) +3717 train 7.368845 (lr=4.3671e-05) (hash(x)=28825233) +3718 train 6.899004 (lr=4.3633e-05) (hash(x)=25778506) +3719 train 6.833716 (lr=4.3594e-05) (hash(x)=23788738) +3720 train 6.087805 (lr=4.3556e-05) (hash(x)=16684794) +3721 train 6.681551 (lr=4.3518e-05) (hash(x)=24755102) +3722 train 6.979467 (lr=4.3479e-05) (hash(x)=26839238) +3723 train 7.020378 (lr=4.3441e-05) (hash(x)=26599031) +3724 train 6.869339 (lr=4.3403e-05) (hash(x)=25945650) +3725 train 7.043253 (lr=4.3365e-05) (hash(x)=27434751) +3726 train 6.789423 (lr=4.3327e-05) (hash(x)=24814591) +3727 train 6.777029 (lr=4.3288e-05) (hash(x)=24818744) +3728 train 6.839920 (lr=4.3250e-05) (hash(x)=25649817) +3729 train 6.733263 (lr=4.3212e-05) (hash(x)=24987021) +3730 train 6.685966 (lr=4.3174e-05) (hash(x)=24667779) +3731 train 6.676974 (lr=4.3136e-05) (hash(x)=23053871) +3732 train 6.315533 (lr=4.3098e-05) (hash(x)=19264856) +3733 train 6.990650 (lr=4.3060e-05) (hash(x)=23718117) +3734 train 6.634696 (lr=4.3022e-05) (hash(x)=21904779) +3735 train 6.848686 (lr=4.2984e-05) (hash(x)=23472795) +3736 train 7.098633 (lr=4.2946e-05) (hash(x)=24650440) +3737 train 7.171913 (lr=4.2908e-05) (hash(x)=25243911) +3738 train 7.564798 (lr=4.2870e-05) (hash(x)=30423616) +3739 train 7.551946 (lr=4.2832e-05) (hash(x)=29748225) +3740 train 6.968785 (lr=4.2794e-05) (hash(x)=25180684) +3741 train 6.982929 (lr=4.2757e-05) (hash(x)=25619065) +3742 train 7.311972 (lr=4.2719e-05) (hash(x)=31847002) +3743 train 6.867106 (lr=4.2681e-05) (hash(x)=24991832) +3744 train 6.801587 (lr=4.2643e-05) (hash(x)=23836263) +3745 train 6.709761 (lr=4.2605e-05) (hash(x)=24651902) +3746 train 7.260786 (lr=4.2568e-05) (hash(x)=22936538) +3747 train 7.245897 (lr=4.2530e-05) (hash(x)=23681545) +3748 train 6.610517 (lr=4.2492e-05) (hash(x)=21140825) +3749 train 6.817780 (lr=4.2455e-05) (hash(x)=24932453) +3750 val loss 6.9154 +3750 val perplexity 1007.7034 +3750 train 7.026044 (lr=4.2417e-05) (hash(x)=25919062) +3751 train 6.802402 (lr=4.2379e-05) (hash(x)=22424066) +3752 train 6.844432 (lr=4.2342e-05) (hash(x)=23542210) +3753 train 6.691444 (lr=4.2304e-05) (hash(x)=22113561) +3754 train 6.593921 (lr=4.2267e-05) (hash(x)=24892794) +3755 train 7.102296 (lr=4.2229e-05) (hash(x)=25262748) +3756 train 6.874303 (lr=4.2192e-05) (hash(x)=24477975) +3757 train 6.664425 (lr=4.2154e-05) (hash(x)=24681189) +3758 train 6.688190 (lr=4.2117e-05) (hash(x)=24052603) +3759 train 6.900231 (lr=4.2079e-05) (hash(x)=26474878) +3760 train 7.486144 (lr=4.2042e-05) (hash(x)=28228836) +3761 train 7.003723 (lr=4.2005e-05) (hash(x)=23832522) +3762 train 6.997826 (lr=4.1967e-05) (hash(x)=24416789) +3763 train 6.717594 (lr=4.1930e-05) (hash(x)=23930593) +3764 train 6.775208 (lr=4.1893e-05) (hash(x)=23895092) +3765 train 6.724019 (lr=4.1855e-05) (hash(x)=26865287) +3766 train 6.743690 (lr=4.1818e-05) (hash(x)=21330722) +3767 train 6.782231 (lr=4.1781e-05) (hash(x)=22704349) +3768 train 6.991741 (lr=4.1744e-05) (hash(x)=27740886) +3769 train 6.947910 (lr=4.1707e-05) (hash(x)=24935936) +3770 train 6.830818 (lr=4.1669e-05) (hash(x)=23497487) +3771 train 6.999860 (lr=4.1632e-05) (hash(x)=24801048) +3772 train 6.759007 (lr=4.1595e-05) (hash(x)=25490486) +3773 train 6.772388 (lr=4.1558e-05) (hash(x)=21166466) +3774 train 6.964996 (lr=4.1521e-05) (hash(x)=23225244) +3775 train 6.730405 (lr=4.1484e-05) (hash(x)=22293673) +3776 train 7.088698 (lr=4.1447e-05) (hash(x)=25700016) +3777 train 6.573430 (lr=4.1410e-05) (hash(x)=22370207) +3778 train 6.943368 (lr=4.1373e-05) (hash(x)=25224849) +3779 train 6.820161 (lr=4.1336e-05) (hash(x)=23311934) +3780 train 6.538391 (lr=4.1299e-05) (hash(x)=19627124) +3781 train 7.024850 (lr=4.1262e-05) (hash(x)=27132838) +3782 train 7.047288 (lr=4.1225e-05) (hash(x)=27242104) +3783 train 6.532173 (lr=4.1188e-05) (hash(x)=21785487) +3784 train 6.865051 (lr=4.1152e-05) (hash(x)=25798262) +3785 train 6.781072 (lr=4.1115e-05) (hash(x)=24806937) +3786 train 6.578357 (lr=4.1078e-05) (hash(x)=24098756) +3787 train 6.607670 (lr=4.1041e-05) (hash(x)=22981456) +3788 train 7.060722 (lr=4.1004e-05) (hash(x)=22441908) +3789 train 6.921943 (lr=4.0968e-05) (hash(x)=25867804) +3790 train 6.873672 (lr=4.0931e-05) (hash(x)=22835586) +3791 train 7.044709 (lr=4.0894e-05) (hash(x)=25251063) +3792 train 6.942983 (lr=4.0858e-05) (hash(x)=27059729) +3793 train 6.870433 (lr=4.0821e-05) (hash(x)=23819311) +3794 train 6.566869 (lr=4.0784e-05) (hash(x)=21345757) +3795 train 6.823369 (lr=4.0748e-05) (hash(x)=25796422) +3796 train 6.498137 (lr=4.0711e-05) (hash(x)=21414971) +3797 train 6.816213 (lr=4.0675e-05) (hash(x)=26120920) +3798 train 6.717169 (lr=4.0638e-05) (hash(x)=22008247) +3799 train 6.804931 (lr=4.0602e-05) (hash(x)=22722211) +3800 val loss 6.9073 +3800 val perplexity 999.5267 +3800 train 6.541434 (lr=4.0565e-05) (hash(x)=24484513) +3801 train 6.891666 (lr=4.0529e-05) (hash(x)=24463866) +3802 train 6.904186 (lr=4.0492e-05) (hash(x)=26470775) +3803 train 6.915276 (lr=4.0456e-05) (hash(x)=24296755) +3804 train 6.909041 (lr=4.0420e-05) (hash(x)=24381309) +3805 train 7.091249 (lr=4.0383e-05) (hash(x)=26781262) +3806 train 6.579919 (lr=4.0347e-05) (hash(x)=23563137) +3807 train 6.827985 (lr=4.0311e-05) (hash(x)=24522269) +3808 train 6.600151 (lr=4.0275e-05) (hash(x)=22871995) +3809 train 6.950928 (lr=4.0238e-05) (hash(x)=24751946) +3810 train 6.759264 (lr=4.0202e-05) (hash(x)=19879741) +3811 train 6.842937 (lr=4.0166e-05) (hash(x)=25617184) +3812 train 6.495866 (lr=4.0130e-05) (hash(x)=21776722) +3813 train 6.621160 (lr=4.0094e-05) (hash(x)=22663402) +3814 train 7.010683 (lr=4.0057e-05) (hash(x)=26072046) +3815 train 6.653041 (lr=4.0021e-05) (hash(x)=23329475) +3816 train 6.730078 (lr=3.9985e-05) (hash(x)=25519031) +3817 train 6.697043 (lr=3.9949e-05) (hash(x)=22846270) +3818 train 6.674518 (lr=3.9913e-05) (hash(x)=20299429) +3819 train 7.141498 (lr=3.9877e-05) (hash(x)=30652062) +3820 train 6.424750 (lr=3.9841e-05) (hash(x)=19824665) +3821 train 7.065759 (lr=3.9805e-05) (hash(x)=26698904) +3822 train 6.860784 (lr=3.9769e-05) (hash(x)=27612163) +3823 train 6.668616 (lr=3.9733e-05) (hash(x)=24735165) +3824 train 6.408151 (lr=3.9698e-05) (hash(x)=19965890) +3825 train 6.544472 (lr=3.9662e-05) (hash(x)=23518594) +3826 train 6.578018 (lr=3.9626e-05) (hash(x)=22388460) +3827 train 6.653639 (lr=3.9590e-05) (hash(x)=23795686) +3828 train 6.529286 (lr=3.9554e-05) (hash(x)=24470150) +3829 train 6.210554 (lr=3.9519e-05) (hash(x)=19483392) +3830 train 6.688910 (lr=3.9483e-05) (hash(x)=23304516) +3831 train 7.026149 (lr=3.9447e-05) (hash(x)=27002892) +3832 train 6.735130 (lr=3.9411e-05) (hash(x)=22114813) +3833 train 6.912308 (lr=3.9376e-05) (hash(x)=26221916) +3834 train 6.394979 (lr=3.9340e-05) (hash(x)=27261960) +3835 train 6.709470 (lr=3.9304e-05) (hash(x)=21189101) +3836 train 6.379937 (lr=3.9269e-05) (hash(x)=20638173) +3837 train 6.822933 (lr=3.9233e-05) (hash(x)=25497439) +3838 train 6.283241 (lr=3.9198e-05) (hash(x)=20460499) +3839 train 6.758191 (lr=3.9162e-05) (hash(x)=23499349) +3840 train 7.627409 (lr=3.9127e-05) (hash(x)=22671939) +3841 train 7.576720 (lr=3.9091e-05) (hash(x)=26809295) +3842 train 6.848341 (lr=3.9056e-05) (hash(x)=28094504) +3843 train 6.819110 (lr=3.9020e-05) (hash(x)=26807896) +3844 train 6.913040 (lr=3.8985e-05) (hash(x)=24749334) +3845 train 6.801123 (lr=3.8950e-05) (hash(x)=25031330) +3846 train 6.701328 (lr=3.8914e-05) (hash(x)=23008126) +3847 train 6.695072 (lr=3.8879e-05) (hash(x)=22461589) +3848 train 6.896999 (lr=3.8844e-05) (hash(x)=24959391) +3849 train 6.858173 (lr=3.8808e-05) (hash(x)=24239512) +3850 val loss 6.8980 +3850 val perplexity 990.2532 +3850 train 6.678646 (lr=3.8773e-05) (hash(x)=24760422) +3851 train 7.189079 (lr=3.8738e-05) (hash(x)=26904123) +3852 train 6.307419 (lr=3.8703e-05) (hash(x)=17986444) +3853 train 6.666389 (lr=3.8668e-05) (hash(x)=21618533) +3854 train 6.709580 (lr=3.8632e-05) (hash(x)=27107027) +3855 train 6.995900 (lr=3.8597e-05) (hash(x)=26415040) +3856 train 7.560163 (lr=3.8562e-05) (hash(x)=28682703) +3857 train 6.719826 (lr=3.8527e-05) (hash(x)=22824767) +3858 train 6.857234 (lr=3.8492e-05) (hash(x)=24540450) +3859 train 6.832207 (lr=3.8457e-05) (hash(x)=24463181) +3860 train 6.754776 (lr=3.8422e-05) (hash(x)=22832558) +3861 train 6.953284 (lr=3.8387e-05) (hash(x)=26582384) +3862 train 7.643433 (lr=3.8352e-05) (hash(x)=32327364) +3863 train 6.988721 (lr=3.8317e-05) (hash(x)=26349465) +3864 train 6.682745 (lr=3.8282e-05) (hash(x)=23079414) +3865 train 6.747746 (lr=3.8247e-05) (hash(x)=23464639) +3866 train 6.613739 (lr=3.8213e-05) (hash(x)=21406620) +3867 train 6.426009 (lr=3.8178e-05) (hash(x)=21205988) +3868 train 6.493584 (lr=3.8143e-05) (hash(x)=22742634) +3869 train 6.516138 (lr=3.8108e-05) (hash(x)=24868938) +3870 train 6.942536 (lr=3.8073e-05) (hash(x)=28095283) +3871 train 6.631032 (lr=3.8039e-05) (hash(x)=21596677) +3872 train 6.859248 (lr=3.8004e-05) (hash(x)=26884381) +3873 train 6.931905 (lr=3.7969e-05) (hash(x)=26410272) +3874 train 6.713377 (lr=3.7935e-05) (hash(x)=22915785) +3875 train 6.737991 (lr=3.7900e-05) (hash(x)=23575666) +3876 train 6.661017 (lr=3.7865e-05) (hash(x)=25313223) +3877 train 6.126415 (lr=3.7831e-05) (hash(x)=16319719) +3878 train 6.794595 (lr=3.7796e-05) (hash(x)=23227579) +3879 train 6.693275 (lr=3.7762e-05) (hash(x)=24117012) +3880 train 6.775121 (lr=3.7727e-05) (hash(x)=24681517) +3881 train 6.718994 (lr=3.7693e-05) (hash(x)=23186527) +3882 train 6.696471 (lr=3.7658e-05) (hash(x)=23472784) +3883 train 6.640598 (lr=3.7624e-05) (hash(x)=26013014) +3884 train 6.902093 (lr=3.7590e-05) (hash(x)=25952206) +3885 train 7.054468 (lr=3.7555e-05) (hash(x)=23897834) +3886 train 6.751627 (lr=3.7521e-05) (hash(x)=26350364) +3887 train 6.797497 (lr=3.7487e-05) (hash(x)=24105761) +3888 train 6.945719 (lr=3.7452e-05) (hash(x)=22801707) +3889 train 6.693770 (lr=3.7418e-05) (hash(x)=21821937) +3890 train 6.658220 (lr=3.7384e-05) (hash(x)=24264640) +3891 train 6.599084 (lr=3.7349e-05) (hash(x)=20369133) +3892 train 6.609910 (lr=3.7315e-05) (hash(x)=24313506) +3893 train 6.602056 (lr=3.7281e-05) (hash(x)=22104086) +3894 train 6.831174 (lr=3.7247e-05) (hash(x)=25312602) +3895 train 6.872856 (lr=3.7213e-05) (hash(x)=25725049) +3896 train 6.767476 (lr=3.7179e-05) (hash(x)=22981231) +3897 train 6.596347 (lr=3.7145e-05) (hash(x)=18021467) +3898 train 6.564484 (lr=3.7111e-05) (hash(x)=17960254) +3899 train 6.728171 (lr=3.7077e-05) (hash(x)=19808118) +3900 val loss 6.8975 +3900 val perplexity 989.7750 +3900 train 6.463081 (lr=3.7043e-05) (hash(x)=21022829) +3901 train 6.650966 (lr=3.7009e-05) (hash(x)=22434663) +3902 train 6.396706 (lr=3.6975e-05) (hash(x)=20208091) +3903 train 6.524733 (lr=3.6941e-05) (hash(x)=22892776) +3904 train 6.654483 (lr=3.6907e-05) (hash(x)=21554367) +3905 train 6.790940 (lr=3.6873e-05) (hash(x)=23704875) +3906 train 6.759229 (lr=3.6839e-05) (hash(x)=21690340) +3907 train 6.706762 (lr=3.6805e-05) (hash(x)=23736780) +3908 train 6.562206 (lr=3.6772e-05) (hash(x)=21060920) +3909 train 6.504331 (lr=3.6738e-05) (hash(x)=20091559) +3910 train 6.762136 (lr=3.6704e-05) (hash(x)=22147974) +3911 train 6.715361 (lr=3.6670e-05) (hash(x)=21630383) +3912 train 6.990121 (lr=3.6637e-05) (hash(x)=28339385) +3913 train 6.766277 (lr=3.6603e-05) (hash(x)=25355505) +3914 train 6.608740 (lr=3.6569e-05) (hash(x)=20843914) +3915 train 7.121387 (lr=3.6536e-05) (hash(x)=25397467) +3916 train 6.846413 (lr=3.6502e-05) (hash(x)=23587501) +3917 train 6.388564 (lr=3.6469e-05) (hash(x)=19036533) +3918 train 6.557099 (lr=3.6435e-05) (hash(x)=29749389) +3919 train 6.486229 (lr=3.6402e-05) (hash(x)=24727094) +3920 train 6.528986 (lr=3.6368e-05) (hash(x)=22723450) +3921 train 6.727931 (lr=3.6335e-05) (hash(x)=24424680) +3922 train 6.846408 (lr=3.6301e-05) (hash(x)=25817917) +3923 train 6.638229 (lr=3.6268e-05) (hash(x)=23951182) +3924 train 6.677992 (lr=3.6234e-05) (hash(x)=21177944) +3925 train 6.501514 (lr=3.6201e-05) (hash(x)=23533768) +3926 train 6.745697 (lr=3.6168e-05) (hash(x)=24263615) +3927 train 6.547125 (lr=3.6134e-05) (hash(x)=22835000) +3928 train 6.761014 (lr=3.6101e-05) (hash(x)=26076156) +3929 train 6.775788 (lr=3.6068e-05) (hash(x)=25171508) +3930 train 6.778692 (lr=3.6035e-05) (hash(x)=22021396) +3931 train 7.045052 (lr=3.6001e-05) (hash(x)=28767849) +3932 train 6.953866 (lr=3.5968e-05) (hash(x)=29497606) +3933 train 6.600929 (lr=3.5935e-05) (hash(x)=22723124) +3934 train 6.887221 (lr=3.5902e-05) (hash(x)=27106616) +3935 train 6.741925 (lr=3.5869e-05) (hash(x)=22839049) +3936 train 6.782143 (lr=3.5836e-05) (hash(x)=25101923) +3937 train 6.748991 (lr=3.5803e-05) (hash(x)=25945975) +3938 train 6.880750 (lr=3.5770e-05) (hash(x)=25382013) +3939 train 6.388464 (lr=3.5737e-05) (hash(x)=19930900) +3940 train 6.558933 (lr=3.5704e-05) (hash(x)=22202373) +3941 train 6.771702 (lr=3.5671e-05) (hash(x)=24592992) +3942 train 6.643730 (lr=3.5638e-05) (hash(x)=25002271) +3943 train 6.546396 (lr=3.5605e-05) (hash(x)=20654136) +3944 train 6.596195 (lr=3.5572e-05) (hash(x)=20061590) +3945 train 6.462345 (lr=3.5539e-05) (hash(x)=21441361) +3946 train 6.722219 (lr=3.5506e-05) (hash(x)=20055468) +3947 train 7.498007 (lr=3.5474e-05) (hash(x)=28495621) +3948 train 6.846237 (lr=3.5441e-05) (hash(x)=25959236) +3949 train 7.161261 (lr=3.5408e-05) (hash(x)=26750193) +3950 val loss 6.9006 +3950 val perplexity 992.8569 +3950 train 6.997890 (lr=3.5375e-05) (hash(x)=25882605) +3951 train 7.083330 (lr=3.5343e-05) (hash(x)=26776000) +3952 train 6.650035 (lr=3.5310e-05) (hash(x)=24155107) +3953 train 6.760826 (lr=3.5277e-05) (hash(x)=23441845) +3954 train 6.670654 (lr=3.5245e-05) (hash(x)=22860915) +3955 train 6.439163 (lr=3.5212e-05) (hash(x)=21584429) +3956 train 6.028228 (lr=3.5180e-05) (hash(x)=16535556) +3957 train 6.145103 (lr=3.5147e-05) (hash(x)=17946180) +3958 train 6.683519 (lr=3.5115e-05) (hash(x)=25367610) +3959 train 6.563596 (lr=3.5082e-05) (hash(x)=22560658) +3960 train 6.857762 (lr=3.5050e-05) (hash(x)=23809585) +3961 train 7.101147 (lr=3.5017e-05) (hash(x)=20438213) +3962 train 7.472517 (lr=3.4985e-05) (hash(x)=30520037) +3963 train 7.095532 (lr=3.4953e-05) (hash(x)=25276565) +3964 train 6.810911 (lr=3.4920e-05) (hash(x)=26796532) +3965 train 6.585492 (lr=3.4888e-05) (hash(x)=22850475) +3966 train 7.144847 (lr=3.4856e-05) (hash(x)=25983698) +3967 train 7.026293 (lr=3.4823e-05) (hash(x)=25995933) +3968 train 7.185269 (lr=3.4791e-05) (hash(x)=25319339) +3969 train 6.787590 (lr=3.4759e-05) (hash(x)=25066892) +3970 train 7.017344 (lr=3.4727e-05) (hash(x)=26931819) +3971 train 7.027260 (lr=3.4695e-05) (hash(x)=24163910) +3972 train 6.870145 (lr=3.4662e-05) (hash(x)=25359634) +3973 train 6.737701 (lr=3.4630e-05) (hash(x)=24323444) +3974 train 6.928976 (lr=3.4598e-05) (hash(x)=26529231) +3975 train 6.928905 (lr=3.4566e-05) (hash(x)=24635394) +3976 train 7.212471 (lr=3.4534e-05) (hash(x)=24783093) +3977 train 7.333831 (lr=3.4502e-05) (hash(x)=26710509) +3978 train 6.762607 (lr=3.4470e-05) (hash(x)=25396630) +3979 train 6.667480 (lr=3.4438e-05) (hash(x)=22556381) +3980 train 6.975674 (lr=3.4406e-05) (hash(x)=26912161) +3981 train 6.515207 (lr=3.4374e-05) (hash(x)=22268078) +3982 train 7.596296 (lr=3.4343e-05) (hash(x)=30430328) +3983 train 7.233380 (lr=3.4311e-05) (hash(x)=27537228) +3984 train 6.590198 (lr=3.4279e-05) (hash(x)=24468603) +3985 train 6.940199 (lr=3.4247e-05) (hash(x)=27006663) +3986 train 7.212766 (lr=3.4215e-05) (hash(x)=27014728) +3987 train 6.596451 (lr=3.4184e-05) (hash(x)=20883633) +3988 train 6.699689 (lr=3.4152e-05) (hash(x)=23361791) +3989 train 6.869370 (lr=3.4120e-05) (hash(x)=26775925) +3990 train 7.391487 (lr=3.4089e-05) (hash(x)=30648934) +3991 train 6.917289 (lr=3.4057e-05) (hash(x)=26496730) +3992 train 6.699697 (lr=3.4025e-05) (hash(x)=25942897) +3993 train 6.755058 (lr=3.3994e-05) (hash(x)=24887111) +3994 train 6.628035 (lr=3.3962e-05) (hash(x)=22908550) +3995 train 6.320226 (lr=3.3931e-05) (hash(x)=20342150) +3996 train 6.652631 (lr=3.3899e-05) (hash(x)=22261760) +3997 train 6.703210 (lr=3.3868e-05) (hash(x)=22731641) +3998 train 6.575751 (lr=3.3836e-05) (hash(x)=20669749) +3999 train 6.531224 (lr=3.3805e-05) (hash(x)=16533310) +4000 val loss 6.8931 +4000 val perplexity 985.4786 +4000 train 6.704611 (lr=3.3773e-05) (hash(x)=23661341) +4001 train 6.709897 (lr=3.3742e-05) (hash(x)=24644301) +4002 train 6.538026 (lr=3.3711e-05) (hash(x)=22938438) +4003 train 6.632095 (lr=3.3679e-05) (hash(x)=24315862) +4004 train 6.830893 (lr=3.3648e-05) (hash(x)=25169315) +4005 train 6.842971 (lr=3.3617e-05) (hash(x)=24752796) +4006 train 6.770696 (lr=3.3586e-05) (hash(x)=23103706) +4007 train 6.905498 (lr=3.3554e-05) (hash(x)=24881176) +4008 train 6.739798 (lr=3.3523e-05) (hash(x)=23971947) +4009 train 7.069972 (lr=3.3492e-05) (hash(x)=27741054) +4010 train 7.478254 (lr=3.3461e-05) (hash(x)=30956251) +4011 train 6.835320 (lr=3.3430e-05) (hash(x)=23649686) +4012 train 6.666200 (lr=3.3399e-05) (hash(x)=23344798) +4013 train 7.321987 (lr=3.3368e-05) (hash(x)=29529498) +4014 train 6.798433 (lr=3.3337e-05) (hash(x)=24688359) +4015 train 6.765795 (lr=3.3306e-05) (hash(x)=25593613) +4016 train 6.894493 (lr=3.3275e-05) (hash(x)=25674488) +4017 train 6.312147 (lr=3.3244e-05) (hash(x)=21345346) +4018 train 6.658943 (lr=3.3213e-05) (hash(x)=21978324) +4019 train 6.710938 (lr=3.3182e-05) (hash(x)=23669244) +4020 train 6.566146 (lr=3.3151e-05) (hash(x)=22479613) +4021 train 6.555429 (lr=3.3120e-05) (hash(x)=22855256) +4022 train 6.942874 (lr=3.3090e-05) (hash(x)=19759826) +4023 train 6.866990 (lr=3.3059e-05) (hash(x)=22886646) +4024 train 6.824827 (lr=3.3028e-05) (hash(x)=25553008) +4025 train 6.676443 (lr=3.2997e-05) (hash(x)=25487028) +4026 train 7.243703 (lr=3.2967e-05) (hash(x)=26799246) +4027 train 7.561057 (lr=3.2936e-05) (hash(x)=30728540) +4028 train 7.005745 (lr=3.2905e-05) (hash(x)=23966676) +4029 train 6.687280 (lr=3.2875e-05) (hash(x)=22118783) +4030 train 6.814980 (lr=3.2844e-05) (hash(x)=24744703) +4031 train 6.794789 (lr=3.2814e-05) (hash(x)=21407676) +4032 train 6.740234 (lr=3.2783e-05) (hash(x)=20623349) +4033 train 6.517343 (lr=3.2753e-05) (hash(x)=24723788) +4034 train 6.879096 (lr=3.2722e-05) (hash(x)=25030709) +4035 train 6.905511 (lr=3.2692e-05) (hash(x)=26326164) +4036 train 6.741724 (lr=3.2661e-05) (hash(x)=23754475) +4037 train 7.390110 (lr=3.2631e-05) (hash(x)=30112933) +4038 train 7.140865 (lr=3.2601e-05) (hash(x)=27474299) +4039 train 6.588475 (lr=3.2570e-05) (hash(x)=21720304) +4040 train 7.006709 (lr=3.2540e-05) (hash(x)=25142674) +4041 train 7.295213 (lr=3.2510e-05) (hash(x)=25284552) +4042 train 7.178388 (lr=3.2479e-05) (hash(x)=24554942) +4043 train 6.913712 (lr=3.2449e-05) (hash(x)=23773870) +4044 train 6.634113 (lr=3.2419e-05) (hash(x)=23896338) +4045 train 7.477289 (lr=3.2389e-05) (hash(x)=34984911) +4046 train 6.706333 (lr=3.2359e-05) (hash(x)=23854263) +4047 train 6.999016 (lr=3.2329e-05) (hash(x)=27263416) +4048 train 6.681479 (lr=3.2298e-05) (hash(x)=24989642) +4049 train 6.723650 (lr=3.2268e-05) (hash(x)=24492055) +4050 val loss 6.8952 +4050 val perplexity 987.4877 +4050 train 6.625104 (lr=3.2238e-05) (hash(x)=21579916) +4051 train 6.840927 (lr=3.2208e-05) (hash(x)=25274710) +4052 train 6.767310 (lr=3.2178e-05) (hash(x)=24701947) +4053 train 6.751800 (lr=3.2148e-05) (hash(x)=25477340) +4054 train 6.664388 (lr=3.2118e-05) (hash(x)=23774195) +4055 train 6.921768 (lr=3.2089e-05) (hash(x)=25840801) +4056 train 7.076913 (lr=3.2059e-05) (hash(x)=27972529) +4057 train 6.871007 (lr=3.2029e-05) (hash(x)=26952458) +4058 train 6.353218 (lr=3.1999e-05) (hash(x)=22683653) +4059 train 6.430875 (lr=3.1969e-05) (hash(x)=20984129) +4060 train 6.616565 (lr=3.1939e-05) (hash(x)=22816482) +4061 train 6.921360 (lr=3.1910e-05) (hash(x)=24285302) +4062 train 7.330631 (lr=3.1880e-05) (hash(x)=31517950) +4063 train 7.475160 (lr=3.1850e-05) (hash(x)=31424568) +4064 train 7.141225 (lr=3.1821e-05) (hash(x)=29497876) +4065 train 7.106895 (lr=3.1791e-05) (hash(x)=27277376) +4066 train 6.859807 (lr=3.1761e-05) (hash(x)=26832588) +4067 train 6.690247 (lr=3.1732e-05) (hash(x)=25149712) +4068 train 6.699085 (lr=3.1702e-05) (hash(x)=23728457) +4069 train 6.578011 (lr=3.1673e-05) (hash(x)=25265136) +4070 train 7.123682 (lr=3.1643e-05) (hash(x)=25241681) +4071 train 6.835152 (lr=3.1614e-05) (hash(x)=23403065) +4072 train 6.758152 (lr=3.1584e-05) (hash(x)=25808207) +4073 train 6.702881 (lr=3.1555e-05) (hash(x)=23904844) +4074 train 6.350358 (lr=3.1526e-05) (hash(x)=18865309) +4075 train 6.849595 (lr=3.1496e-05) (hash(x)=23531744) +4076 train 6.843568 (lr=3.1467e-05) (hash(x)=25784275) +4077 train 6.602116 (lr=3.1438e-05) (hash(x)=22417529) +4078 train 6.579498 (lr=3.1409e-05) (hash(x)=23095491) +4079 train 6.750638 (lr=3.1379e-05) (hash(x)=22656033) +4080 train 6.742249 (lr=3.1350e-05) (hash(x)=25865435) +4081 train 6.876459 (lr=3.1321e-05) (hash(x)=25699377) +4082 train 6.852190 (lr=3.1292e-05) (hash(x)=20854084) +4083 train 6.411652 (lr=3.1263e-05) (hash(x)=18950799) +4084 train 6.636545 (lr=3.1234e-05) (hash(x)=22633739) +4085 train 7.548560 (lr=3.1204e-05) (hash(x)=34054446) +4086 train 7.055092 (lr=3.1175e-05) (hash(x)=27599387) +4087 train 6.883729 (lr=3.1146e-05) (hash(x)=26869295) +4088 train 6.822455 (lr=3.1117e-05) (hash(x)=24075139) +4089 train 7.286432 (lr=3.1088e-05) (hash(x)=29784110) +4090 train 7.574097 (lr=3.1060e-05) (hash(x)=34273918) +4091 train 8.006599 (lr=3.1031e-05) (hash(x)=34472685) +4092 train 7.316485 (lr=3.1002e-05) (hash(x)=30113791) +4093 train 6.568294 (lr=3.0973e-05) (hash(x)=22366381) +4094 train 6.819587 (lr=3.0944e-05) (hash(x)=24922935) +4095 train 7.034043 (lr=3.0915e-05) (hash(x)=25504151) +4096 train 6.951800 (lr=3.0887e-05) (hash(x)=24517375) +4097 train 7.686265 (lr=3.0858e-05) (hash(x)=25871651) +4098 train 6.698869 (lr=3.0829e-05) (hash(x)=23480225) +4099 train 6.548758 (lr=3.0800e-05) (hash(x)=22559978) +4100 val loss 6.8951 +4100 val perplexity 987.4604 +4100 train 7.002875 (lr=3.0772e-05) (hash(x)=25795272) +4101 train 6.957516 (lr=3.0743e-05) (hash(x)=25440399) +4102 train 6.599799 (lr=3.0715e-05) (hash(x)=21581806) +4103 train 6.651503 (lr=3.0686e-05) (hash(x)=25781518) +4104 train 6.777705 (lr=3.0657e-05) (hash(x)=24682372) +4105 train 6.631793 (lr=3.0629e-05) (hash(x)=22440094) +4106 train 6.788860 (lr=3.0600e-05) (hash(x)=23661032) +4107 train 7.022300 (lr=3.0572e-05) (hash(x)=26966012) +4108 train 7.084597 (lr=3.0544e-05) (hash(x)=26232227) +4109 train 6.730193 (lr=3.0515e-05) (hash(x)=24110656) +4110 train 6.994766 (lr=3.0487e-05) (hash(x)=25938621) +4111 train 6.811040 (lr=3.0458e-05) (hash(x)=26432850) +4112 train 6.815111 (lr=3.0430e-05) (hash(x)=25387672) +4113 train 6.564571 (lr=3.0402e-05) (hash(x)=22740017) +4114 train 6.962827 (lr=3.0374e-05) (hash(x)=26384190) +4115 train 6.647817 (lr=3.0345e-05) (hash(x)=24725583) +4116 train 6.808736 (lr=3.0317e-05) (hash(x)=23986700) +4117 train 6.789610 (lr=3.0289e-05) (hash(x)=18529900) +4118 train 6.851551 (lr=3.0261e-05) (hash(x)=22236257) +4119 train 6.428178 (lr=3.0233e-05) (hash(x)=20155894) +4120 train 6.229617 (lr=3.0205e-05) (hash(x)=17423813) +4121 train 6.182607 (lr=3.0177e-05) (hash(x)=18905183) +4122 train 6.571210 (lr=3.0149e-05) (hash(x)=22534398) +4123 train 7.291256 (lr=3.0121e-05) (hash(x)=25247868) +4124 train 6.796432 (lr=3.0093e-05) (hash(x)=23994188) +4125 train 6.668655 (lr=3.0065e-05) (hash(x)=22929754) +4126 train 6.518054 (lr=3.0037e-05) (hash(x)=22485897) +4127 train 6.591773 (lr=3.0009e-05) (hash(x)=22270169) +4128 train 6.549529 (lr=2.9981e-05) (hash(x)=23638027) +4129 train 6.872931 (lr=2.9953e-05) (hash(x)=23821210) +4130 train 6.775836 (lr=2.9925e-05) (hash(x)=25021512) +4131 train 6.810155 (lr=2.9898e-05) (hash(x)=25240141) +4132 train 6.766983 (lr=2.9870e-05) (hash(x)=22833160) +4133 train 6.699699 (lr=2.9842e-05) (hash(x)=22909944) +4134 train 6.969867 (lr=2.9814e-05) (hash(x)=26163558) +4135 train 6.679244 (lr=2.9787e-05) (hash(x)=22108461) +4136 train 6.664731 (lr=2.9759e-05) (hash(x)=22549232) +4137 train 6.867044 (lr=2.9732e-05) (hash(x)=24701302) +4138 train 6.959600 (lr=2.9704e-05) (hash(x)=25206013) +4139 train 6.888027 (lr=2.9676e-05) (hash(x)=27896130) +4140 train 6.622514 (lr=2.9649e-05) (hash(x)=24106243) +4141 train 7.278246 (lr=2.9621e-05) (hash(x)=27158651) +4142 train 6.766888 (lr=2.9594e-05) (hash(x)=23841147) +4143 train 6.702794 (lr=2.9567e-05) (hash(x)=24802848) +4144 train 7.039080 (lr=2.9539e-05) (hash(x)=24911295) +4145 train 6.829791 (lr=2.9512e-05) (hash(x)=26473900) +4146 train 6.875476 (lr=2.9484e-05) (hash(x)=26785092) +4147 train 7.160844 (lr=2.9457e-05) (hash(x)=30188532) +4148 train 6.715473 (lr=2.9430e-05) (hash(x)=25010649) +4149 train 6.677655 (lr=2.9403e-05) (hash(x)=22409016) +4150 val loss 6.8887 +4150 val perplexity 981.1205 +4150 train 7.464789 (lr=2.9375e-05) (hash(x)=31675024) +4151 train 6.760646 (lr=2.9348e-05) (hash(x)=25086604) +4152 train 6.762389 (lr=2.9321e-05) (hash(x)=24429343) +4153 train 6.937891 (lr=2.9294e-05) (hash(x)=25014232) +4154 train 6.818936 (lr=2.9267e-05) (hash(x)=25366275) +4155 train 7.329737 (lr=2.9240e-05) (hash(x)=24031473) +4156 train 6.784442 (lr=2.9213e-05) (hash(x)=26651059) +4157 train 6.891052 (lr=2.9186e-05) (hash(x)=26069721) +4158 train 7.081160 (lr=2.9159e-05) (hash(x)=28114382) +4159 train 7.083481 (lr=2.9132e-05) (hash(x)=26983186) +4160 train 6.378991 (lr=2.9105e-05) (hash(x)=21944670) +4161 train 7.163633 (lr=2.9078e-05) (hash(x)=28155702) +4162 train 6.588771 (lr=2.9051e-05) (hash(x)=24765002) +4163 train 6.846442 (lr=2.9024e-05) (hash(x)=26492636) +4164 train 6.804710 (lr=2.8997e-05) (hash(x)=24063705) +4165 train 7.091170 (lr=2.8970e-05) (hash(x)=27079573) +4166 train 6.731233 (lr=2.8944e-05) (hash(x)=24912201) +4167 train 6.877913 (lr=2.8917e-05) (hash(x)=27208507) +4168 train 6.772585 (lr=2.8890e-05) (hash(x)=25824320) +4169 train 7.341262 (lr=2.8863e-05) (hash(x)=29641677) +4170 train 7.024601 (lr=2.8837e-05) (hash(x)=26275614) +4171 train 6.851286 (lr=2.8810e-05) (hash(x)=25227725) +4172 train 6.937306 (lr=2.8783e-05) (hash(x)=27417375) +4173 train 7.132277 (lr=2.8757e-05) (hash(x)=25581973) +4174 train 7.337979 (lr=2.8730e-05) (hash(x)=30360417) +4175 train 6.672531 (lr=2.8704e-05) (hash(x)=23862845) +4176 train 6.745258 (lr=2.8677e-05) (hash(x)=25415130) +4177 train 6.767834 (lr=2.8651e-05) (hash(x)=23111123) +4178 train 6.710436 (lr=2.8625e-05) (hash(x)=24022804) +4179 train 6.732069 (lr=2.8598e-05) (hash(x)=25148490) +4180 train 6.922449 (lr=2.8572e-05) (hash(x)=22792092) +4181 train 7.077606 (lr=2.8545e-05) (hash(x)=24779698) +4182 train 6.945142 (lr=2.8519e-05) (hash(x)=24870844) +4183 train 6.624658 (lr=2.8493e-05) (hash(x)=22664494) +4184 train 6.684522 (lr=2.8467e-05) (hash(x)=22599729) +4185 train 6.945723 (lr=2.8440e-05) (hash(x)=24707078) +4186 train 6.664680 (lr=2.8414e-05) (hash(x)=23823945) +4187 train 6.357392 (lr=2.8388e-05) (hash(x)=22219856) +4188 train 7.135705 (lr=2.8362e-05) (hash(x)=27061401) +4189 train 6.802678 (lr=2.8336e-05) (hash(x)=23398766) +4190 train 6.937697 (lr=2.8310e-05) (hash(x)=27916730) +4191 train 6.832770 (lr=2.8284e-05) (hash(x)=24092927) +4192 train 6.847847 (lr=2.8258e-05) (hash(x)=24723657) +4193 train 6.877130 (lr=2.8232e-05) (hash(x)=24676155) +4194 train 6.728097 (lr=2.8206e-05) (hash(x)=23455369) +4195 train 6.678876 (lr=2.8180e-05) (hash(x)=21999890) +4196 train 6.595695 (lr=2.8154e-05) (hash(x)=23385567) +4197 train 6.853539 (lr=2.8128e-05) (hash(x)=25120814) +4198 train 6.538571 (lr=2.8102e-05) (hash(x)=21308113) +4199 train 6.848165 (lr=2.8076e-05) (hash(x)=27213812) +4200 val loss 6.8890 +4200 val perplexity 981.4387 +4200 train 6.410205 (lr=2.8050e-05) (hash(x)=19675382) +4201 train 6.738058 (lr=2.8025e-05) (hash(x)=23882161) +4202 train 6.690750 (lr=2.7999e-05) (hash(x)=24338567) +4203 train 6.996390 (lr=2.7973e-05) (hash(x)=27649723) +4204 train 6.831218 (lr=2.7948e-05) (hash(x)=27563514) +4205 train 6.778459 (lr=2.7922e-05) (hash(x)=23128552) +4206 train 6.689908 (lr=2.7896e-05) (hash(x)=26203283) +4207 train 6.743276 (lr=2.7871e-05) (hash(x)=23929955) +4208 train 6.396828 (lr=2.7845e-05) (hash(x)=20978691) +4209 train 6.737297 (lr=2.7820e-05) (hash(x)=21875178) +4210 train 6.818733 (lr=2.7794e-05) (hash(x)=23563293) +4211 train 7.008678 (lr=2.7769e-05) (hash(x)=25538503) +4212 train 7.029752 (lr=2.7743e-05) (hash(x)=24171014) +4213 train 6.862943 (lr=2.7718e-05) (hash(x)=22306665) +4214 train 6.759972 (lr=2.7693e-05) (hash(x)=26082318) +4215 train 6.490427 (lr=2.7667e-05) (hash(x)=23025790) +4216 train 6.688460 (lr=2.7642e-05) (hash(x)=21146597) +4217 train 7.006819 (lr=2.7617e-05) (hash(x)=27470230) +4218 train 6.705226 (lr=2.7591e-05) (hash(x)=22691005) +4219 train 6.488266 (lr=2.7566e-05) (hash(x)=21550313) +4220 train 6.616849 (lr=2.7541e-05) (hash(x)=20618443) +4221 train 6.719763 (lr=2.7516e-05) (hash(x)=25260787) +4222 train 6.782259 (lr=2.7491e-05) (hash(x)=25249873) +4223 train 6.342081 (lr=2.7466e-05) (hash(x)=20452272) +4224 train 6.700685 (lr=2.7440e-05) (hash(x)=25649764) +4225 train 6.593815 (lr=2.7415e-05) (hash(x)=19589460) +4226 train 6.986748 (lr=2.7390e-05) (hash(x)=26477595) +4227 train 7.176155 (lr=2.7365e-05) (hash(x)=27585442) +4228 train 7.030519 (lr=2.7340e-05) (hash(x)=25821343) +4229 train 6.904854 (lr=2.7315e-05) (hash(x)=24549919) +4230 train 6.798511 (lr=2.7291e-05) (hash(x)=26124522) +4231 train 7.155755 (lr=2.7266e-05) (hash(x)=26473464) +4232 train 7.093967 (lr=2.7241e-05) (hash(x)=28883028) +4233 train 7.061152 (lr=2.7216e-05) (hash(x)=29611296) +4234 train 6.944502 (lr=2.7191e-05) (hash(x)=29059941) +4235 train 6.809503 (lr=2.7166e-05) (hash(x)=26368203) +4236 train 6.847707 (lr=2.7142e-05) (hash(x)=27021360) +4237 train 6.727356 (lr=2.7117e-05) (hash(x)=26135379) +4238 train 6.542399 (lr=2.7092e-05) (hash(x)=25862549) +4239 train 6.979514 (lr=2.7068e-05) (hash(x)=28276603) +4240 train 6.528776 (lr=2.7043e-05) (hash(x)=22170090) +4241 train 6.884288 (lr=2.7019e-05) (hash(x)=22625589) +4242 train 6.906765 (lr=2.6994e-05) (hash(x)=25751475) +4243 train 6.817679 (lr=2.6970e-05) (hash(x)=25836838) +4244 train 6.752515 (lr=2.6945e-05) (hash(x)=23938214) +4245 train 6.685399 (lr=2.6921e-05) (hash(x)=22759365) +4246 train 6.652998 (lr=2.6896e-05) (hash(x)=24964628) +4247 train 6.356693 (lr=2.6872e-05) (hash(x)=21480367) +4248 train 6.858916 (lr=2.6847e-05) (hash(x)=25974694) +4249 train 7.222829 (lr=2.6823e-05) (hash(x)=29830546) +4250 val loss 6.8859 +4250 val perplexity 978.4210 +4250 train 6.894647 (lr=2.6799e-05) (hash(x)=26283200) +4251 train 6.965534 (lr=2.6774e-05) (hash(x)=25605672) +4252 train 6.587060 (lr=2.6750e-05) (hash(x)=21439107) +4253 train 6.504822 (lr=2.6726e-05) (hash(x)=22626883) +4254 train 6.902378 (lr=2.6702e-05) (hash(x)=25627150) +4255 train 7.061313 (lr=2.6678e-05) (hash(x)=24658642) +4256 train 7.110702 (lr=2.6653e-05) (hash(x)=29755505) +4257 train 6.857160 (lr=2.6629e-05) (hash(x)=22750846) +4258 train 6.805950 (lr=2.6605e-05) (hash(x)=21892651) +4259 train 6.867141 (lr=2.6581e-05) (hash(x)=22487960) +4260 train 6.926965 (lr=2.6557e-05) (hash(x)=24059869) +4261 train 6.696211 (lr=2.6533e-05) (hash(x)=21090180) +4262 train 6.796253 (lr=2.6509e-05) (hash(x)=22716452) +4263 train 7.001836 (lr=2.6485e-05) (hash(x)=26854801) +4264 train 6.786858 (lr=2.6461e-05) (hash(x)=23815428) +4265 train 6.595539 (lr=2.6438e-05) (hash(x)=23368704) +4266 train 6.683600 (lr=2.6414e-05) (hash(x)=24301098) +4267 train 6.896335 (lr=2.6390e-05) (hash(x)=25025039) +4268 train 6.651246 (lr=2.6366e-05) (hash(x)=25425736) +4269 train 6.857399 (lr=2.6342e-05) (hash(x)=27439380) +4270 train 6.282257 (lr=2.6319e-05) (hash(x)=18682756) +4271 train 6.466825 (lr=2.6295e-05) (hash(x)=17862226) +4272 train 7.042469 (lr=2.6271e-05) (hash(x)=29946491) +4273 train 6.305553 (lr=2.6248e-05) (hash(x)=21392062) +4274 train 6.877512 (lr=2.6224e-05) (hash(x)=25195556) +4275 train 6.871633 (lr=2.6201e-05) (hash(x)=26682036) +4276 train 6.750804 (lr=2.6177e-05) (hash(x)=21235260) +4277 train 6.575766 (lr=2.6154e-05) (hash(x)=22118984) +4278 train 6.613853 (lr=2.6130e-05) (hash(x)=24094510) +4279 train 7.148835 (lr=2.6107e-05) (hash(x)=28519182) +4280 train 6.806067 (lr=2.6083e-05) (hash(x)=26652859) +4281 train 6.723567 (lr=2.6060e-05) (hash(x)=24463139) +4282 train 6.674957 (lr=2.6036e-05) (hash(x)=23281870) +4283 train 6.903635 (lr=2.6013e-05) (hash(x)=29181174) +4284 train 6.587060 (lr=2.5990e-05) (hash(x)=24797417) +4285 train 6.981544 (lr=2.5967e-05) (hash(x)=29026537) +4286 train 6.757161 (lr=2.5943e-05) (hash(x)=23045165) +4287 train 6.686438 (lr=2.5920e-05) (hash(x)=25193694) +4288 train 6.741624 (lr=2.5897e-05) (hash(x)=23475407) +4289 train 6.871963 (lr=2.5874e-05) (hash(x)=24875410) +4290 train 6.760067 (lr=2.5851e-05) (hash(x)=26328101) +4291 train 7.072490 (lr=2.5828e-05) (hash(x)=26273661) +4292 train 6.792946 (lr=2.5805e-05) (hash(x)=23271891) +4293 train 6.768750 (lr=2.5782e-05) (hash(x)=23300732) +4294 train 6.857564 (lr=2.5759e-05) (hash(x)=24243693) +4295 train 6.931240 (lr=2.5736e-05) (hash(x)=25642620) +4296 train 6.912519 (lr=2.5713e-05) (hash(x)=27730411) +4297 train 6.689636 (lr=2.5690e-05) (hash(x)=25485335) +4298 train 6.573671 (lr=2.5667e-05) (hash(x)=25268789) +4299 train 7.002513 (lr=2.5644e-05) (hash(x)=28917143) +4300 val loss 6.8866 +4300 val perplexity 979.1108 +4300 train 7.170503 (lr=2.5621e-05) (hash(x)=28987991) +4301 train 6.902322 (lr=2.5598e-05) (hash(x)=25989151) +4302 train 6.806311 (lr=2.5576e-05) (hash(x)=25658195) +4303 train 6.734891 (lr=2.5553e-05) (hash(x)=25765909) +4304 train 6.764465 (lr=2.5530e-05) (hash(x)=25704261) +4305 train 6.783464 (lr=2.5508e-05) (hash(x)=24438198) +4306 train 6.591087 (lr=2.5485e-05) (hash(x)=22871710) +4307 train 6.432083 (lr=2.5462e-05) (hash(x)=20160896) +4308 train 6.970313 (lr=2.5440e-05) (hash(x)=24218641) +4309 train 6.408470 (lr=2.5417e-05) (hash(x)=22073751) +4310 train 6.752674 (lr=2.5395e-05) (hash(x)=26434959) +4311 train 6.457527 (lr=2.5372e-05) (hash(x)=20750531) +4312 train 6.569357 (lr=2.5350e-05) (hash(x)=22232293) +4313 train 6.857037 (lr=2.5327e-05) (hash(x)=27324521) +4314 train 6.526181 (lr=2.5305e-05) (hash(x)=22217862) +4315 train 6.948444 (lr=2.5283e-05) (hash(x)=25741958) +4316 train 6.741991 (lr=2.5260e-05) (hash(x)=22738456) +4317 train 6.786305 (lr=2.5238e-05) (hash(x)=25387302) +4318 train 6.760733 (lr=2.5216e-05) (hash(x)=24669014) +4319 train 6.867548 (lr=2.5194e-05) (hash(x)=24917098) +4320 train 6.802016 (lr=2.5171e-05) (hash(x)=26698227) +4321 train 6.609337 (lr=2.5149e-05) (hash(x)=23518293) +4322 train 6.517593 (lr=2.5127e-05) (hash(x)=23643971) +4323 train 6.764904 (lr=2.5105e-05) (hash(x)=25659505) +4324 train 6.519952 (lr=2.5083e-05) (hash(x)=22697720) +4325 train 7.054576 (lr=2.5061e-05) (hash(x)=25082178) +4326 train 6.559257 (lr=2.5039e-05) (hash(x)=24166546) +4327 train 6.732448 (lr=2.5017e-05) (hash(x)=24499766) +4328 train 6.829726 (lr=2.4995e-05) (hash(x)=24338607) +4329 train 6.651296 (lr=2.4973e-05) (hash(x)=23225420) +4330 train 6.798383 (lr=2.4951e-05) (hash(x)=25907032) +4331 train 6.613815 (lr=2.4929e-05) (hash(x)=24634979) +4332 train 6.711908 (lr=2.4907e-05) (hash(x)=22161377) +4333 train 6.860256 (lr=2.4886e-05) (hash(x)=22559939) +4334 train 6.603379 (lr=2.4864e-05) (hash(x)=20840022) +4335 train 6.917793 (lr=2.4842e-05) (hash(x)=25067358) +4336 train 6.543382 (lr=2.4820e-05) (hash(x)=23432626) +4337 train 6.723249 (lr=2.4799e-05) (hash(x)=23820385) +4338 train 7.478791 (lr=2.4777e-05) (hash(x)=31594930) +4339 train 6.929819 (lr=2.4755e-05) (hash(x)=27138750) +4340 train 7.175144 (lr=2.4734e-05) (hash(x)=30031341) +4341 train 6.654572 (lr=2.4712e-05) (hash(x)=24602807) +4342 train 6.430533 (lr=2.4691e-05) (hash(x)=21584976) +4343 train 6.904682 (lr=2.4669e-05) (hash(x)=27479796) +4344 train 6.570119 (lr=2.4648e-05) (hash(x)=22746241) +4345 train 6.737620 (lr=2.4626e-05) (hash(x)=19728452) +4346 train 6.526744 (lr=2.4605e-05) (hash(x)=24502020) +4347 train 7.014987 (lr=2.4583e-05) (hash(x)=28225954) +4348 train 6.614040 (lr=2.4562e-05) (hash(x)=23893447) +4349 train 6.983837 (lr=2.4541e-05) (hash(x)=25654586) +4350 val loss 6.8721 +4350 val perplexity 964.9401 +4350 train 6.809719 (lr=2.4519e-05) (hash(x)=23856469) +4351 train 6.736071 (lr=2.4498e-05) (hash(x)=23136080) +4352 train 6.859502 (lr=2.4477e-05) (hash(x)=26532918) +4353 train 6.763969 (lr=2.4456e-05) (hash(x)=25461947) +4354 train 6.763426 (lr=2.4435e-05) (hash(x)=26590231) +4355 train 6.475096 (lr=2.4413e-05) (hash(x)=21441985) +4356 train 6.789182 (lr=2.4392e-05) (hash(x)=26507941) +4357 train 7.113550 (lr=2.4371e-05) (hash(x)=26245238) +4358 train 6.863144 (lr=2.4350e-05) (hash(x)=24879059) +4359 train 7.115354 (lr=2.4329e-05) (hash(x)=29810074) +4360 train 6.502719 (lr=2.4308e-05) (hash(x)=24258069) +4361 train 6.644287 (lr=2.4287e-05) (hash(x)=25229360) +4362 train 6.859499 (lr=2.4266e-05) (hash(x)=25440206) +4363 train 6.732378 (lr=2.4246e-05) (hash(x)=23222125) +4364 train 6.535866 (lr=2.4225e-05) (hash(x)=23353186) +4365 train 6.795887 (lr=2.4204e-05) (hash(x)=26995240) +4366 train 6.733279 (lr=2.4183e-05) (hash(x)=24135899) +4367 train 6.747497 (lr=2.4162e-05) (hash(x)=24765539) +4368 train 6.784398 (lr=2.4142e-05) (hash(x)=26051004) +4369 train 6.527706 (lr=2.4121e-05) (hash(x)=22559142) +4370 train 6.457703 (lr=2.4100e-05) (hash(x)=20364388) +4371 train 6.989655 (lr=2.4080e-05) (hash(x)=25938817) +4372 train 7.009412 (lr=2.4059e-05) (hash(x)=26060945) +4373 train 6.927637 (lr=2.4038e-05) (hash(x)=27866714) +4374 train 6.820764 (lr=2.4018e-05) (hash(x)=27104972) +4375 train 6.520058 (lr=2.3997e-05) (hash(x)=22216309) +4376 train 6.547294 (lr=2.3977e-05) (hash(x)=20781533) +4377 train 6.488054 (lr=2.3956e-05) (hash(x)=18784350) +4378 train 6.584607 (lr=2.3936e-05) (hash(x)=21102897) +4379 train 6.866512 (lr=2.3916e-05) (hash(x)=25647489) +4380 train 6.687770 (lr=2.3895e-05) (hash(x)=24486462) +4381 train 6.945220 (lr=2.3875e-05) (hash(x)=26539114) +4382 train 6.623604 (lr=2.3855e-05) (hash(x)=20026045) +4383 train 6.982934 (lr=2.3834e-05) (hash(x)=20613861) +4384 train 6.577603 (lr=2.3814e-05) (hash(x)=20676237) +4385 train 6.788648 (lr=2.3794e-05) (hash(x)=24893163) +4386 train 6.323720 (lr=2.3774e-05) (hash(x)=17299395) +4387 train 6.489086 (lr=2.3754e-05) (hash(x)=19580191) +4388 train 6.719058 (lr=2.3733e-05) (hash(x)=25588218) +4389 train 6.823461 (lr=2.3713e-05) (hash(x)=26433063) +4390 train 6.961775 (lr=2.3693e-05) (hash(x)=24917693) +4391 train 6.584199 (lr=2.3673e-05) (hash(x)=23462447) +4392 train 6.799689 (lr=2.3653e-05) (hash(x)=27185416) +4393 train 6.991074 (lr=2.3633e-05) (hash(x)=24109010) +4394 train 6.717517 (lr=2.3613e-05) (hash(x)=21486000) +4395 train 6.599308 (lr=2.3593e-05) (hash(x)=22230006) +4396 train 7.033691 (lr=2.3574e-05) (hash(x)=26092311) +4397 train 6.762044 (lr=2.3554e-05) (hash(x)=24112426) +4398 train 6.567722 (lr=2.3534e-05) (hash(x)=21881373) +4399 train 6.689046 (lr=2.3514e-05) (hash(x)=26739455) +4400 val loss 6.8776 +4400 val perplexity 970.3404 +4400 train 6.571119 (lr=2.3494e-05) (hash(x)=22873602) +4401 train 6.670599 (lr=2.3475e-05) (hash(x)=26748712) +4402 train 6.877281 (lr=2.3455e-05) (hash(x)=26306618) +4403 train 7.054536 (lr=2.3435e-05) (hash(x)=26898808) +4404 train 6.766754 (lr=2.3416e-05) (hash(x)=25067751) +4405 train 6.799676 (lr=2.3396e-05) (hash(x)=25397145) +4406 train 6.953964 (lr=2.3377e-05) (hash(x)=24796962) +4407 train 6.750146 (lr=2.3357e-05) (hash(x)=23222996) +4408 train 6.731348 (lr=2.3338e-05) (hash(x)=24820189) +4409 train 7.152068 (lr=2.3318e-05) (hash(x)=27669038) +4410 train 6.722940 (lr=2.3299e-05) (hash(x)=24283976) +4411 train 6.918985 (lr=2.3279e-05) (hash(x)=25018789) +4412 train 6.846900 (lr=2.3260e-05) (hash(x)=26247064) +4413 train 6.920617 (lr=2.3241e-05) (hash(x)=22942904) +4414 train 6.744469 (lr=2.3221e-05) (hash(x)=23918746) +4415 train 6.851825 (lr=2.3202e-05) (hash(x)=26489285) +4416 train 5.829161 (lr=2.3183e-05) (hash(x)=14942495) +4417 train 6.655881 (lr=2.3164e-05) (hash(x)=23908505) +4418 train 6.894411 (lr=2.3145e-05) (hash(x)=25854036) +4419 train 6.751424 (lr=2.3125e-05) (hash(x)=27522868) +4420 train 6.658719 (lr=2.3106e-05) (hash(x)=26549205) +4421 train 6.522742 (lr=2.3087e-05) (hash(x)=24565522) +4422 train 6.899838 (lr=2.3068e-05) (hash(x)=23919123) +4423 train 6.718152 (lr=2.3049e-05) (hash(x)=25185942) +4424 train 6.732327 (lr=2.3030e-05) (hash(x)=24818969) +4425 train 6.858784 (lr=2.3011e-05) (hash(x)=26750372) +4426 train 6.820395 (lr=2.2992e-05) (hash(x)=25621536) +4427 train 7.307607 (lr=2.2973e-05) (hash(x)=28037060) +4428 train 7.252057 (lr=2.2954e-05) (hash(x)=30829517) +4429 train 6.835028 (lr=2.2936e-05) (hash(x)=28728766) +4430 train 6.826877 (lr=2.2917e-05) (hash(x)=25936895) +4431 train 6.999509 (lr=2.2898e-05) (hash(x)=27476158) +4432 train 6.696663 (lr=2.2879e-05) (hash(x)=23297921) +4433 train 6.640248 (lr=2.2861e-05) (hash(x)=23201299) +4434 train 6.587667 (lr=2.2842e-05) (hash(x)=22681766) +4435 train 6.613910 (lr=2.2823e-05) (hash(x)=23217512) +4436 train 7.079469 (lr=2.2805e-05) (hash(x)=29322443) +4437 train 6.655345 (lr=2.2786e-05) (hash(x)=23502072) +4438 train 6.760931 (lr=2.2768e-05) (hash(x)=28873527) +4439 train 6.787485 (lr=2.2749e-05) (hash(x)=23653175) +4440 train 6.605890 (lr=2.2731e-05) (hash(x)=21635879) +4441 train 6.621479 (lr=2.2712e-05) (hash(x)=22201854) +4442 train 6.537676 (lr=2.2694e-05) (hash(x)=23101164) +4443 train 6.979733 (lr=2.2675e-05) (hash(x)=25475122) +4444 train 6.696896 (lr=2.2657e-05) (hash(x)=25124825) +4445 train 6.871330 (lr=2.2639e-05) (hash(x)=26883852) +4446 train 6.647952 (lr=2.2620e-05) (hash(x)=24731829) +4447 train 6.600984 (lr=2.2602e-05) (hash(x)=22405076) +4448 train 6.784742 (lr=2.2584e-05) (hash(x)=27633869) +4449 train 6.829639 (lr=2.2566e-05) (hash(x)=25162594) +4450 val loss 6.8693 +4450 val perplexity 962.2590 +4450 train 6.861753 (lr=2.2547e-05) (hash(x)=26438149) +4451 train 6.882202 (lr=2.2529e-05) (hash(x)=26748800) +4452 train 6.595447 (lr=2.2511e-05) (hash(x)=22971620) +4453 train 6.754899 (lr=2.2493e-05) (hash(x)=25886430) +4454 train 6.480513 (lr=2.2475e-05) (hash(x)=21084137) +4455 train 6.722002 (lr=2.2457e-05) (hash(x)=25673545) +4456 train 7.347829 (lr=2.2439e-05) (hash(x)=29389002) +4457 train 6.470656 (lr=2.2421e-05) (hash(x)=21676076) +4458 train 6.527013 (lr=2.2403e-05) (hash(x)=22616647) +4459 train 6.931713 (lr=2.2385e-05) (hash(x)=22771197) +4460 train 6.849561 (lr=2.2367e-05) (hash(x)=26393514) +4461 train 7.072440 (lr=2.2350e-05) (hash(x)=24996433) +4462 train 6.678548 (lr=2.2332e-05) (hash(x)=19594028) +4463 train 6.855194 (lr=2.2314e-05) (hash(x)=22675428) +4464 train 6.867237 (lr=2.2296e-05) (hash(x)=26566551) +4465 train 6.853595 (lr=2.2279e-05) (hash(x)=22469290) +4466 train 7.326225 (lr=2.2261e-05) (hash(x)=29821654) +4467 train 6.827315 (lr=2.2243e-05) (hash(x)=26305388) +4468 train 6.695396 (lr=2.2226e-05) (hash(x)=21998506) +4469 train 7.131748 (lr=2.2208e-05) (hash(x)=23953315) +4470 train 6.690087 (lr=2.2191e-05) (hash(x)=23985456) +4471 train 7.166594 (lr=2.2173e-05) (hash(x)=28168456) +4472 train 6.778458 (lr=2.2156e-05) (hash(x)=25126411) +4473 train 6.584102 (lr=2.2138e-05) (hash(x)=24619336) +4474 train 6.748307 (lr=2.2121e-05) (hash(x)=24467798) +4475 train 7.672887 (lr=2.2103e-05) (hash(x)=31673254) +4476 train 7.384232 (lr=2.2086e-05) (hash(x)=29929610) +4477 train 7.157316 (lr=2.2069e-05) (hash(x)=29412572) +4478 train 7.277013 (lr=2.2051e-05) (hash(x)=31910006) +4479 train 6.922807 (lr=2.2034e-05) (hash(x)=26072586) +4480 train 6.864363 (lr=2.2017e-05) (hash(x)=25782825) +4481 train 6.710647 (lr=2.2000e-05) (hash(x)=21131363) +4482 train 6.811800 (lr=2.1983e-05) (hash(x)=25071223) +4483 train 7.425877 (lr=2.1966e-05) (hash(x)=32249577) +4484 train 6.665681 (lr=2.1948e-05) (hash(x)=24752808) +4485 train 6.705457 (lr=2.1931e-05) (hash(x)=24970539) +4486 train 6.628154 (lr=2.1914e-05) (hash(x)=24191005) +4487 train 6.873999 (lr=2.1897e-05) (hash(x)=24974331) +4488 train 7.004392 (lr=2.1880e-05) (hash(x)=27043409) +4489 train 6.656440 (lr=2.1863e-05) (hash(x)=11320385) +4490 train 6.696743 (lr=2.1847e-05) (hash(x)=11919565) +4491 train 6.705492 (lr=2.1830e-05) (hash(x)=10404694) +4492 train 6.741930 (lr=2.1813e-05) (hash(x)=12393159) +4493 train 6.655879 (lr=2.1796e-05) (hash(x)=11843609) +4494 train 6.658169 (lr=2.1779e-05) (hash(x)=12632729) +4495 train 6.708669 (lr=2.1762e-05) (hash(x)=21951984) +4496 train 7.473439 (lr=2.1746e-05) (hash(x)=19411544) +4497 train 7.424373 (lr=2.1729e-05) (hash(x)=21000228) +4498 train 6.977210 (lr=2.1712e-05) (hash(x)=26018207) +4499 train 6.988954 (lr=2.1696e-05) (hash(x)=24659058) +4500 val loss 6.8750 +4500 val perplexity 967.7338 +4500 train 7.172386 (lr=2.1679e-05) (hash(x)=27919597) +4501 train 6.730968 (lr=2.1663e-05) (hash(x)=26232596) +4502 train 6.907197 (lr=2.1646e-05) (hash(x)=26248912) +4503 train 6.719063 (lr=2.1630e-05) (hash(x)=25403751) +4504 train 6.646373 (lr=2.1613e-05) (hash(x)=21096637) +4505 train 6.747220 (lr=2.1597e-05) (hash(x)=26560941) +4506 train 6.812090 (lr=2.1580e-05) (hash(x)=24942406) +4507 train 6.884159 (lr=2.1564e-05) (hash(x)=24405748) +4508 train 6.761856 (lr=2.1548e-05) (hash(x)=22975455) +4509 train 6.705237 (lr=2.1531e-05) (hash(x)=26358820) +4510 train 6.726135 (lr=2.1515e-05) (hash(x)=24211938) +4511 train 6.922943 (lr=2.1499e-05) (hash(x)=26396012) +4512 train 6.543233 (lr=2.1483e-05) (hash(x)=22534410) +4513 train 6.679688 (lr=2.1467e-05) (hash(x)=23855025) +4514 train 6.567801 (lr=2.1450e-05) (hash(x)=22722345) +4515 train 6.543881 (lr=2.1434e-05) (hash(x)=22779251) +4516 train 6.878362 (lr=2.1418e-05) (hash(x)=23973078) +4517 train 6.683354 (lr=2.1402e-05) (hash(x)=19886228) +4518 train 6.812244 (lr=2.1386e-05) (hash(x)=23849694) +4519 train 7.200603 (lr=2.1370e-05) (hash(x)=24827190) +4520 train 6.763060 (lr=2.1354e-05) (hash(x)=25111498) +4521 train 7.549054 (lr=2.1338e-05) (hash(x)=29752556) +4522 train 7.000812 (lr=2.1323e-05) (hash(x)=25606805) +4523 train 6.819913 (lr=2.1307e-05) (hash(x)=22209714) +4524 train 6.507175 (lr=2.1291e-05) (hash(x)=24991834) +4525 train 6.797069 (lr=2.1275e-05) (hash(x)=27808158) +4526 train 6.767845 (lr=2.1259e-05) (hash(x)=23041199) +4527 train 6.779760 (lr=2.1244e-05) (hash(x)=24847458) +4528 train 6.721032 (lr=2.1228e-05) (hash(x)=25091787) +4529 train 7.718216 (lr=2.1212e-05) (hash(x)=29745551) +4530 train 6.405295 (lr=2.1197e-05) (hash(x)=20447167) +4531 train 6.669603 (lr=2.1181e-05) (hash(x)=20720911) +4532 train 6.824388 (lr=2.1165e-05) (hash(x)=24803353) +4533 train 6.898160 (lr=2.1150e-05) (hash(x)=23780724) +4534 train 6.914755 (lr=2.1134e-05) (hash(x)=23423120) +4535 train 6.548781 (lr=2.1119e-05) (hash(x)=22159088) +4536 train 6.747463 (lr=2.1104e-05) (hash(x)=25820304) +4537 train 6.540157 (lr=2.1088e-05) (hash(x)=22813612) +4538 train 6.884897 (lr=2.1073e-05) (hash(x)=27827979) +4539 train 6.885158 (lr=2.1057e-05) (hash(x)=25737179) +4540 train 7.110309 (lr=2.1042e-05) (hash(x)=23401504) +4541 train 6.724220 (lr=2.1027e-05) (hash(x)=25071988) +4542 train 6.786217 (lr=2.1012e-05) (hash(x)=22844541) +4543 train 6.531958 (lr=2.0996e-05) (hash(x)=22140034) +4544 train 6.815818 (lr=2.0981e-05) (hash(x)=26522091) +4545 train 6.833099 (lr=2.0966e-05) (hash(x)=24099725) +4546 train 6.410257 (lr=2.0951e-05) (hash(x)=19127182) +4547 train 6.538867 (lr=2.0936e-05) (hash(x)=18992693) +4548 train 7.568063 (lr=2.0921e-05) (hash(x)=26723015) +4549 train 7.319198 (lr=2.0906e-05) (hash(x)=30389969) +4550 val loss 6.8715 +4550 val perplexity 964.3923 +4550 train 6.640594 (lr=2.0891e-05) (hash(x)=24065654) +4551 train 6.411170 (lr=2.0876e-05) (hash(x)=19044797) +4552 train 6.920929 (lr=2.0861e-05) (hash(x)=24919665) +4553 train 6.952950 (lr=2.0846e-05) (hash(x)=22780968) +4554 train 6.689249 (lr=2.0831e-05) (hash(x)=24549699) +4555 train 6.543057 (lr=2.0817e-05) (hash(x)=21374811) +4556 train 6.667618 (lr=2.0802e-05) (hash(x)=25225950) +4557 train 6.807100 (lr=2.0787e-05) (hash(x)=25691882) +4558 train 6.707149 (lr=2.0772e-05) (hash(x)=24685235) +4559 train 6.525768 (lr=2.0758e-05) (hash(x)=23932794) +4560 train 7.157791 (lr=2.0743e-05) (hash(x)=28152043) +4561 train 6.625257 (lr=2.0728e-05) (hash(x)=23417051) +4562 train 6.702904 (lr=2.0714e-05) (hash(x)=26250211) +4563 train 6.991426 (lr=2.0699e-05) (hash(x)=25428813) +4564 train 7.081673 (lr=2.0685e-05) (hash(x)=27477379) +4565 train 6.871616 (lr=2.0670e-05) (hash(x)=23015212) +4566 train 6.574852 (lr=2.0656e-05) (hash(x)=22837608) +4567 train 6.683371 (lr=2.0641e-05) (hash(x)=25256890) +4568 train 6.563649 (lr=2.0627e-05) (hash(x)=22742827) +4569 train 7.012980 (lr=2.0613e-05) (hash(x)=30167922) +4570 train 6.675362 (lr=2.0598e-05) (hash(x)=24540265) +4571 train 7.024487 (lr=2.0584e-05) (hash(x)=26752941) +4572 train 6.840831 (lr=2.0570e-05) (hash(x)=25094026) +4573 train 7.522995 (lr=2.0555e-05) (hash(x)=28508785) +4574 train 6.941650 (lr=2.0541e-05) (hash(x)=26501871) +4575 train 6.700075 (lr=2.0527e-05) (hash(x)=24161711) +4576 train 6.630472 (lr=2.0513e-05) (hash(x)=24313695) +4577 train 7.066020 (lr=2.0499e-05) (hash(x)=28248933) +4578 train 7.225666 (lr=2.0485e-05) (hash(x)=28445722) +4579 train 6.797353 (lr=2.0471e-05) (hash(x)=24589015) +4580 train 7.013742 (lr=2.0457e-05) (hash(x)=26192193) +4581 train 6.601051 (lr=2.0443e-05) (hash(x)=25131316) +4582 train 6.713483 (lr=2.0429e-05) (hash(x)=26631504) +4583 train 6.528053 (lr=2.0415e-05) (hash(x)=22036817) +4584 train 7.166656 (lr=2.0401e-05) (hash(x)=28361254) +4585 train 6.818867 (lr=2.0387e-05) (hash(x)=24828340) +4586 train 6.457961 (lr=2.0373e-05) (hash(x)=24067304) +4587 train 6.232293 (lr=2.0360e-05) (hash(x)=20733289) +4588 train 6.155338 (lr=2.0346e-05) (hash(x)=19526622) +4589 train 6.569516 (lr=2.0332e-05) (hash(x)=22148688) +4590 train 6.834720 (lr=2.0318e-05) (hash(x)=24141800) +4591 train 6.879106 (lr=2.0305e-05) (hash(x)=26663208) +4592 train 6.507044 (lr=2.0291e-05) (hash(x)=22536305) +4593 train 6.825207 (lr=2.0278e-05) (hash(x)=23608185) +4594 train 6.627852 (lr=2.0264e-05) (hash(x)=23348495) +4595 train 6.797820 (lr=2.0250e-05) (hash(x)=25409759) +4596 train 6.804558 (lr=2.0237e-05) (hash(x)=25572131) +4597 train 6.769125 (lr=2.0224e-05) (hash(x)=21782039) +4598 train 6.734493 (lr=2.0210e-05) (hash(x)=24643923) +4599 train 6.684459 (lr=2.0197e-05) (hash(x)=24072213) +4600 val loss 6.8712 +4600 val perplexity 964.1017 +4600 train 6.654805 (lr=2.0183e-05) (hash(x)=23925612) +4601 train 6.708200 (lr=2.0170e-05) (hash(x)=23315415) +4602 train 6.729585 (lr=2.0157e-05) (hash(x)=21793800) +4603 train 6.642457 (lr=2.0143e-05) (hash(x)=24921200) +4604 train 6.916425 (lr=2.0130e-05) (hash(x)=27226113) +4605 train 6.729945 (lr=2.0117e-05) (hash(x)=22920960) +4606 train 6.657600 (lr=2.0104e-05) (hash(x)=21947750) +4607 train 6.713051 (lr=2.0091e-05) (hash(x)=22766044) +4608 train 7.143655 (lr=2.0078e-05) (hash(x)=28237005) +4609 train 6.539455 (lr=2.0065e-05) (hash(x)=24922621) +4610 train 6.799097 (lr=2.0052e-05) (hash(x)=24899830) +4611 train 7.124277 (lr=2.0039e-05) (hash(x)=32920298) +4612 train 6.631721 (lr=2.0026e-05) (hash(x)=25083835) +4613 train 6.701656 (lr=2.0013e-05) (hash(x)=22863054) +4614 train 6.683258 (lr=2.0000e-05) (hash(x)=24841464) +4615 train 6.934246 (lr=1.9987e-05) (hash(x)=27871153) +4616 train 6.891883 (lr=1.9974e-05) (hash(x)=28025163) +4617 train 6.604390 (lr=1.9961e-05) (hash(x)=24659561) +4618 train 6.765518 (lr=1.9949e-05) (hash(x)=25067194) +4619 train 6.748781 (lr=1.9936e-05) (hash(x)=22731460) +4620 train 6.740057 (lr=1.9923e-05) (hash(x)=20445873) +4621 train 6.761292 (lr=1.9910e-05) (hash(x)=26033948) +4622 train 6.634154 (lr=1.9898e-05) (hash(x)=22473213) +4623 train 7.256247 (lr=1.9885e-05) (hash(x)=24037280) +4624 train 7.709720 (lr=1.9873e-05) (hash(x)=25624131) +4625 train 7.315317 (lr=1.9860e-05) (hash(x)=26799867) +4626 train 6.806224 (lr=1.9848e-05) (hash(x)=27187602) +4627 train 6.743580 (lr=1.9835e-05) (hash(x)=23277695) +4628 train 6.753790 (lr=1.9823e-05) (hash(x)=24748234) +4629 train 6.867402 (lr=1.9810e-05) (hash(x)=26103104) +4630 train 6.777814 (lr=1.9798e-05) (hash(x)=24327389) +4631 train 6.898202 (lr=1.9785e-05) (hash(x)=24121850) +4632 train 6.743097 (lr=1.9773e-05) (hash(x)=23714590) +4633 train 6.782179 (lr=1.9761e-05) (hash(x)=22379412) +4634 train 7.029058 (lr=1.9749e-05) (hash(x)=24454713) +4635 train 6.683530 (lr=1.9736e-05) (hash(x)=22966977) +4636 train 6.703299 (lr=1.9724e-05) (hash(x)=23764884) +4637 train 6.558157 (lr=1.9712e-05) (hash(x)=23827429) +4638 train 6.779560 (lr=1.9700e-05) (hash(x)=24088592) +4639 train 6.738483 (lr=1.9688e-05) (hash(x)=24380031) +4640 train 6.856184 (lr=1.9676e-05) (hash(x)=26065050) +4641 train 6.726950 (lr=1.9664e-05) (hash(x)=24442902) +4642 train 6.355424 (lr=1.9652e-05) (hash(x)=18548782) +4643 train 6.866253 (lr=1.9640e-05) (hash(x)=26957303) +4644 train 6.851644 (lr=1.9628e-05) (hash(x)=25032727) +4645 train 6.707086 (lr=1.9616e-05) (hash(x)=27224706) +4646 train 6.854754 (lr=1.9604e-05) (hash(x)=27508476) +4647 train 6.582642 (lr=1.9592e-05) (hash(x)=23055215) +4648 train 6.710373 (lr=1.9581e-05) (hash(x)=24496194) +4649 train 8.021329 (lr=1.9569e-05) (hash(x)=13982941) +4650 val loss 6.8676 +4650 val perplexity 960.6013 +4650 train 7.203649 (lr=1.9557e-05) (hash(x)=16721547) +4651 train 6.730865 (lr=1.9546e-05) (hash(x)=22929154) +4652 train 6.643094 (lr=1.9534e-05) (hash(x)=23323994) +4653 train 7.028355 (lr=1.9522e-05) (hash(x)=24877951) +4654 train 6.890497 (lr=1.9511e-05) (hash(x)=24096183) +4655 train 6.681752 (lr=1.9499e-05) (hash(x)=25329724) +4656 train 6.629042 (lr=1.9488e-05) (hash(x)=23877337) +4657 train 6.273477 (lr=1.9476e-05) (hash(x)=20923083) +4658 train 6.605800 (lr=1.9465e-05) (hash(x)=23807996) +4659 train 6.712348 (lr=1.9453e-05) (hash(x)=24370475) +4660 train 7.077855 (lr=1.9442e-05) (hash(x)=28202255) +4661 train 6.797891 (lr=1.9430e-05) (hash(x)=26142119) +4662 train 6.598009 (lr=1.9419e-05) (hash(x)=21387743) +4663 train 6.741683 (lr=1.9408e-05) (hash(x)=25662408) +4664 train 6.759553 (lr=1.9397e-05) (hash(x)=23962815) +4665 train 6.723354 (lr=1.9385e-05) (hash(x)=23987677) +4666 train 7.025465 (lr=1.9374e-05) (hash(x)=26554284) +4667 train 7.051884 (lr=1.9363e-05) (hash(x)=25991817) +4668 train 6.753574 (lr=1.9352e-05) (hash(x)=24256966) +4669 train 6.530626 (lr=1.9341e-05) (hash(x)=22187158) +4670 train 6.811315 (lr=1.9330e-05) (hash(x)=26295320) +4671 train 6.841646 (lr=1.9319e-05) (hash(x)=26346814) +4672 train 7.096401 (lr=1.9308e-05) (hash(x)=26594196) +4673 train 6.873532 (lr=1.9297e-05) (hash(x)=24322101) +4674 train 6.986640 (lr=1.9286e-05) (hash(x)=27274566) +4675 train 6.802240 (lr=1.9275e-05) (hash(x)=24505725) +4676 train 6.912678 (lr=1.9264e-05) (hash(x)=26167371) +4677 train 7.049534 (lr=1.9253e-05) (hash(x)=28062311) +4678 train 6.732069 (lr=1.9242e-05) (hash(x)=23476009) +4679 train 6.862985 (lr=1.9232e-05) (hash(x)=25283256) +4680 train 6.580097 (lr=1.9221e-05) (hash(x)=22033246) +4681 train 6.620810 (lr=1.9210e-05) (hash(x)=22716214) +4682 train 6.747859 (lr=1.9200e-05) (hash(x)=25672672) +4683 train 6.647457 (lr=1.9189e-05) (hash(x)=22979072) +4684 train 6.852188 (lr=1.9178e-05) (hash(x)=27439204) +4685 train 6.740368 (lr=1.9168e-05) (hash(x)=24857737) +4686 train 7.061380 (lr=1.9157e-05) (hash(x)=29615897) +4687 train 6.552560 (lr=1.9147e-05) (hash(x)=24021771) +4688 train 6.746587 (lr=1.9136e-05) (hash(x)=27410807) +4689 train 6.563284 (lr=1.9126e-05) (hash(x)=22850411) +4690 train 6.840758 (lr=1.9115e-05) (hash(x)=24949696) +4691 train 6.643905 (lr=1.9105e-05) (hash(x)=22956381) +4692 train 7.122231 (lr=1.9095e-05) (hash(x)=28193458) +4693 train 6.703644 (lr=1.9084e-05) (hash(x)=25596844) +4694 train 6.638340 (lr=1.9074e-05) (hash(x)=22101377) +4695 train 6.559303 (lr=1.9064e-05) (hash(x)=23576840) +4696 train 6.560678 (lr=1.9054e-05) (hash(x)=21849758) +4697 train 6.758486 (lr=1.9043e-05) (hash(x)=26431349) +4698 train 6.854388 (lr=1.9033e-05) (hash(x)=22960758) +4699 train 6.783379 (lr=1.9023e-05) (hash(x)=23243097) +4700 val loss 6.8657 +4700 val perplexity 958.8211 +4700 train 6.649982 (lr=1.9013e-05) (hash(x)=23715370) +4701 train 7.295115 (lr=1.9003e-05) (hash(x)=30678293) +4702 train 7.369474 (lr=1.8993e-05) (hash(x)=32481620) +4703 train 6.941051 (lr=1.8983e-05) (hash(x)=26414858) +4704 train 6.812434 (lr=1.8973e-05) (hash(x)=24768691) +4705 train 6.461930 (lr=1.8963e-05) (hash(x)=21627762) +4706 train 6.600749 (lr=1.8953e-05) (hash(x)=21024917) +4707 train 6.527980 (lr=1.8944e-05) (hash(x)=23570951) +4708 train 6.663105 (lr=1.8934e-05) (hash(x)=23729185) +4709 train 7.052941 (lr=1.8924e-05) (hash(x)=25933754) +4710 train 6.465300 (lr=1.8914e-05) (hash(x)=23091014) +4711 train 6.584089 (lr=1.8905e-05) (hash(x)=20099261) +4712 train 6.725585 (lr=1.8895e-05) (hash(x)=26807297) +4713 train 6.626420 (lr=1.8885e-05) (hash(x)=25332115) +4714 train 6.614858 (lr=1.8876e-05) (hash(x)=23247605) +4715 train 6.519762 (lr=1.8866e-05) (hash(x)=23786549) +4716 train 6.615671 (lr=1.8857e-05) (hash(x)=23981166) +4717 train 6.763098 (lr=1.8847e-05) (hash(x)=25967754) +4718 train 6.647775 (lr=1.8838e-05) (hash(x)=23659116) +4719 train 6.679504 (lr=1.8828e-05) (hash(x)=22453718) +4720 train 6.653776 (lr=1.8819e-05) (hash(x)=22597951) +4721 train 6.841361 (lr=1.8809e-05) (hash(x)=25284885) +4722 train 6.814415 (lr=1.8800e-05) (hash(x)=24748569) +4723 train 6.418743 (lr=1.8791e-05) (hash(x)=19448608) +4724 train 6.769655 (lr=1.8781e-05) (hash(x)=24888040) +4725 train 6.605466 (lr=1.8772e-05) (hash(x)=23203503) +4726 train 6.375670 (lr=1.8763e-05) (hash(x)=20387787) +4727 train 6.473207 (lr=1.8754e-05) (hash(x)=22529445) +4728 train 6.769678 (lr=1.8745e-05) (hash(x)=22455471) +4729 train 6.750879 (lr=1.8735e-05) (hash(x)=25661132) +4730 train 6.734619 (lr=1.8726e-05) (hash(x)=24997711) +4731 train 6.879546 (lr=1.8717e-05) (hash(x)=22575521) +4732 train 6.639046 (lr=1.8708e-05) (hash(x)=22640285) +4733 train 6.503881 (lr=1.8699e-05) (hash(x)=18637357) +4734 train 6.633078 (lr=1.8690e-05) (hash(x)=22845826) +4735 train 6.850954 (lr=1.8682e-05) (hash(x)=24484543) +4736 train 6.690231 (lr=1.8673e-05) (hash(x)=23352320) +4737 train 6.507486 (lr=1.8664e-05) (hash(x)=21544758) +4738 train 6.249679 (lr=1.8655e-05) (hash(x)=18292136) +4739 train 6.972015 (lr=1.8646e-05) (hash(x)=24893614) +4740 train 6.805821 (lr=1.8637e-05) (hash(x)=28103443) +4741 train 6.611372 (lr=1.8629e-05) (hash(x)=22233356) +4742 train 6.471807 (lr=1.8620e-05) (hash(x)=21133541) +4743 train 6.744525 (lr=1.8611e-05) (hash(x)=24043998) +4744 train 7.036078 (lr=1.8603e-05) (hash(x)=24801185) +4745 train 6.806386 (lr=1.8594e-05) (hash(x)=23858358) +4746 train 6.824765 (lr=1.8586e-05) (hash(x)=23926989) +4747 train 6.920671 (lr=1.8577e-05) (hash(x)=24813708) +4748 train 6.692020 (lr=1.8569e-05) (hash(x)=26339467) +4749 train 6.557486 (lr=1.8560e-05) (hash(x)=21850656) +4750 val loss 6.8674 +4750 val perplexity 960.4163 +4750 train 6.548925 (lr=1.8552e-05) (hash(x)=21475802) +4751 train 6.719928 (lr=1.8543e-05) (hash(x)=24301906) +4752 train 6.580870 (lr=1.8535e-05) (hash(x)=22748495) +4753 train 6.751115 (lr=1.8527e-05) (hash(x)=25649256) +4754 train 6.654036 (lr=1.8519e-05) (hash(x)=23934346) +4755 train 6.776674 (lr=1.8510e-05) (hash(x)=26332892) +4756 train 6.619913 (lr=1.8502e-05) (hash(x)=23279389) +4757 train 6.689407 (lr=1.8494e-05) (hash(x)=23146858) +4758 train 7.067613 (lr=1.8486e-05) (hash(x)=26892932) +4759 train 6.583162 (lr=1.8478e-05) (hash(x)=26328881) +4760 train 6.676076 (lr=1.8470e-05) (hash(x)=24394655) +4761 train 6.689046 (lr=1.8461e-05) (hash(x)=22122308) +4762 train 6.851139 (lr=1.8453e-05) (hash(x)=24200369) +4763 train 6.938946 (lr=1.8446e-05) (hash(x)=26841776) +4764 train 6.870819 (lr=1.8438e-05) (hash(x)=27196641) +4765 train 6.630584 (lr=1.8430e-05) (hash(x)=24912822) +4766 train 6.892261 (lr=1.8422e-05) (hash(x)=25946055) +4767 train 6.487081 (lr=1.8414e-05) (hash(x)=23101508) +4768 train 6.640067 (lr=1.8406e-05) (hash(x)=24287798) +4769 train 6.747902 (lr=1.8398e-05) (hash(x)=22798964) +4770 train 6.669160 (lr=1.8391e-05) (hash(x)=24164479) +4771 train 6.733989 (lr=1.8383e-05) (hash(x)=24946464) +4772 train 6.882961 (lr=1.8375e-05) (hash(x)=25154423) +4773 train 6.541963 (lr=1.8368e-05) (hash(x)=23173476) +4774 train 6.833361 (lr=1.8360e-05) (hash(x)=25373559) +4775 train 6.800446 (lr=1.8352e-05) (hash(x)=23527176) +4776 train 6.683774 (lr=1.8345e-05) (hash(x)=24865403) +4777 train 6.655376 (lr=1.8337e-05) (hash(x)=24451067) +4778 train 7.282863 (lr=1.8330e-05) (hash(x)=28187162) +4779 train 7.463428 (lr=1.8322e-05) (hash(x)=31163350) +4780 train 7.754320 (lr=1.8315e-05) (hash(x)=33563280) +4781 train 7.846790 (lr=1.8308e-05) (hash(x)=34939183) +4782 train 7.301214 (lr=1.8300e-05) (hash(x)=30263543) +4783 train 6.621620 (lr=1.8293e-05) (hash(x)=22705673) +4784 train 6.477541 (lr=1.8286e-05) (hash(x)=21415023) +4785 train 6.735619 (lr=1.8278e-05) (hash(x)=26079097) +4786 train 7.079022 (lr=1.8271e-05) (hash(x)=25503836) +4787 train 6.905981 (lr=1.8264e-05) (hash(x)=24705721) +4788 train 6.799414 (lr=1.8257e-05) (hash(x)=24384657) +4789 train 6.669618 (lr=1.8250e-05) (hash(x)=22550579) +4790 train 6.719832 (lr=1.8243e-05) (hash(x)=22452164) +4791 train 7.023449 (lr=1.8236e-05) (hash(x)=28664796) +4792 train 7.380501 (lr=1.8229e-05) (hash(x)=26139280) +4793 train 7.051075 (lr=1.8222e-05) (hash(x)=23862341) +4794 train 6.603147 (lr=1.8215e-05) (hash(x)=23784757) +4795 train 6.460844 (lr=1.8208e-05) (hash(x)=22659441) +4796 train 7.207775 (lr=1.8201e-05) (hash(x)=29744216) +4797 train 7.160123 (lr=1.8194e-05) (hash(x)=25822591) +4798 train 6.537170 (lr=1.8187e-05) (hash(x)=22370895) +4799 train 7.011456 (lr=1.8180e-05) (hash(x)=27102890) +4800 val loss 6.8658 +4800 val perplexity 958.8870 +4800 train 7.056954 (lr=1.8174e-05) (hash(x)=27014625) +4801 train 6.798198 (lr=1.8167e-05) (hash(x)=25755963) +4802 train 6.995137 (lr=1.8160e-05) (hash(x)=29675278) +4803 train 7.223261 (lr=1.8154e-05) (hash(x)=26660930) +4804 train 7.135617 (lr=1.8147e-05) (hash(x)=24557060) +4805 train 7.289427 (lr=1.8140e-05) (hash(x)=24622741) +4806 train 7.331226 (lr=1.8134e-05) (hash(x)=23952601) +4807 train 6.889182 (lr=1.8127e-05) (hash(x)=26787259) +4808 train 7.123333 (lr=1.8121e-05) (hash(x)=28919605) +4809 train 7.438262 (lr=1.8115e-05) (hash(x)=37061654) +4810 train 7.215797 (lr=1.8108e-05) (hash(x)=30379739) +4811 train 6.999845 (lr=1.8102e-05) (hash(x)=26097180) +4812 train 7.179447 (lr=1.8095e-05) (hash(x)=26327092) +4813 train 6.894281 (lr=1.8089e-05) (hash(x)=23258030) +4814 train 6.999429 (lr=1.8083e-05) (hash(x)=25582015) +4815 train 6.669625 (lr=1.8077e-05) (hash(x)=23396088) +4816 train 6.631316 (lr=1.8070e-05) (hash(x)=21904146) +4817 train 6.861490 (lr=1.8064e-05) (hash(x)=26281676) +4818 train 6.596069 (lr=1.8058e-05) (hash(x)=23140470) +4819 train 6.943889 (lr=1.8052e-05) (hash(x)=24611098) +4820 train 6.764410 (lr=1.8046e-05) (hash(x)=23832642) +4821 train 6.954610 (lr=1.8040e-05) (hash(x)=21439671) +4822 train 6.787479 (lr=1.8034e-05) (hash(x)=25128845) +4823 train 6.769070 (lr=1.8028e-05) (hash(x)=24911831) +4824 train 6.886997 (lr=1.8022e-05) (hash(x)=26051723) +4825 train 6.905843 (lr=1.8016e-05) (hash(x)=26479565) +4826 train 7.014032 (lr=1.8010e-05) (hash(x)=26228987) +4827 train 6.880816 (lr=1.8004e-05) (hash(x)=25131300) +4828 train 6.604707 (lr=1.7998e-05) (hash(x)=19921978) +4829 train 6.604507 (lr=1.7993e-05) (hash(x)=23173449) +4830 train 6.957776 (lr=1.7987e-05) (hash(x)=24791832) +4831 train 6.692473 (lr=1.7981e-05) (hash(x)=23453491) +4832 train 6.808731 (lr=1.7976e-05) (hash(x)=22564139) +4833 train 6.654746 (lr=1.7970e-05) (hash(x)=21659918) +4834 train 6.788120 (lr=1.7964e-05) (hash(x)=22956076) +4835 train 6.873708 (lr=1.7959e-05) (hash(x)=22237612) +4836 train 7.002861 (lr=1.7953e-05) (hash(x)=24736427) +4837 train 7.095549 (lr=1.7948e-05) (hash(x)=24939751) +4838 train 6.910909 (lr=1.7942e-05) (hash(x)=25059298) +4839 train 6.830338 (lr=1.7937e-05) (hash(x)=23453396) +4840 train 6.328024 (lr=1.7931e-05) (hash(x)=17919338) +4841 train 6.873860 (lr=1.7926e-05) (hash(x)=23428815) +4842 train 7.115964 (lr=1.7921e-05) (hash(x)=27042659) +4843 train 7.210310 (lr=1.7915e-05) (hash(x)=25161278) +4844 train 6.996619 (lr=1.7910e-05) (hash(x)=24113253) +4845 train 7.102759 (lr=1.7905e-05) (hash(x)=26139263) +4846 train 7.140669 (lr=1.7900e-05) (hash(x)=27787006) +4847 train 6.872943 (lr=1.7895e-05) (hash(x)=23869612) +4848 train 6.998209 (lr=1.7889e-05) (hash(x)=26092193) +4849 train 7.014174 (lr=1.7884e-05) (hash(x)=29351182) +4850 val loss 6.8568 +4850 val perplexity 950.3181 +4850 train 7.189230 (lr=1.7879e-05) (hash(x)=28773463) +4851 train 7.129888 (lr=1.7874e-05) (hash(x)=28207741) +4852 train 6.660071 (lr=1.7869e-05) (hash(x)=23280878) +4853 train 7.128517 (lr=1.7864e-05) (hash(x)=26742336) +4854 train 6.894071 (lr=1.7859e-05) (hash(x)=23543321) +4855 train 7.313221 (lr=1.7854e-05) (hash(x)=26581590) +4856 train 6.760025 (lr=1.7849e-05) (hash(x)=22728668) +4857 train 6.555032 (lr=1.7845e-05) (hash(x)=19854534) +4858 train 7.004663 (lr=1.7840e-05) (hash(x)=26612813) +4859 train 7.124903 (lr=1.7835e-05) (hash(x)=25827863) +4860 train 6.782835 (lr=1.7830e-05) (hash(x)=24574997) +4861 train 6.960684 (lr=1.7826e-05) (hash(x)=26187830) +4862 train 6.906730 (lr=1.7821e-05) (hash(x)=25105823) +4863 train 6.978349 (lr=1.7816e-05) (hash(x)=28056342) +4864 train 6.857328 (lr=1.7812e-05) (hash(x)=21885801) +4865 train 7.032880 (lr=1.7807e-05) (hash(x)=25659043) +4866 train 7.001457 (lr=1.7803e-05) (hash(x)=23852824) +4867 train 6.805715 (lr=1.7798e-05) (hash(x)=23965470) +4868 train 6.814636 (lr=1.7794e-05) (hash(x)=25035012) +4869 train 6.999059 (lr=1.7789e-05) (hash(x)=26639165) +4870 train 6.994965 (lr=1.7785e-05) (hash(x)=29205362) +4871 train 6.831811 (lr=1.7781e-05) (hash(x)=25900866) +4872 train 6.867117 (lr=1.7776e-05) (hash(x)=25636242) +4873 train 6.943078 (lr=1.7772e-05) (hash(x)=25430698) +4874 train 6.923645 (lr=1.7768e-05) (hash(x)=27629981) +4875 train 6.909965 (lr=1.7763e-05) (hash(x)=27682625) +4876 train 7.181478 (lr=1.7759e-05) (hash(x)=27549409) +4877 train 6.854262 (lr=1.7755e-05) (hash(x)=24661627) +4878 train 6.961199 (lr=1.7751e-05) (hash(x)=25196542) +4879 train 6.828572 (lr=1.7747e-05) (hash(x)=24549177) +4880 train 6.786792 (lr=1.7743e-05) (hash(x)=23740600) +4881 train 6.680032 (lr=1.7739e-05) (hash(x)=21460850) +4882 train 6.960546 (lr=1.7735e-05) (hash(x)=27101400) +4883 train 6.995830 (lr=1.7731e-05) (hash(x)=24193076) +4884 train 6.888493 (lr=1.7727e-05) (hash(x)=24582947) +4885 train 6.858354 (lr=1.7723e-05) (hash(x)=25133839) +4886 train 6.835056 (lr=1.7719e-05) (hash(x)=24759454) +4887 train 6.872731 (lr=1.7715e-05) (hash(x)=28239583) +4888 train 7.192745 (lr=1.7711e-05) (hash(x)=29594489) +4889 train 6.890363 (lr=1.7708e-05) (hash(x)=23833431) +4890 train 6.851476 (lr=1.7704e-05) (hash(x)=23139411) +4891 train 6.819656 (lr=1.7700e-05) (hash(x)=20885864) +4892 train 7.160034 (lr=1.7697e-05) (hash(x)=26217418) +4893 train 6.937436 (lr=1.7693e-05) (hash(x)=27321870) +4894 train 6.448091 (lr=1.7689e-05) (hash(x)=19912955) +4895 train 6.778284 (lr=1.7686e-05) (hash(x)=23223554) +4896 train 6.943902 (lr=1.7682e-05) (hash(x)=25667219) +4897 train 7.200344 (lr=1.7679e-05) (hash(x)=28007972) +4898 train 6.999490 (lr=1.7675e-05) (hash(x)=27748764) +4899 train 6.924522 (lr=1.7672e-05) (hash(x)=27425770) +4900 val loss 6.8540 +4900 val perplexity 947.6627 +4900 train 7.077585 (lr=1.7669e-05) (hash(x)=28394020) +4901 train 6.916797 (lr=1.7665e-05) (hash(x)=24080235) +4902 train 6.750403 (lr=1.7662e-05) (hash(x)=23309527) +4903 train 6.758956 (lr=1.7659e-05) (hash(x)=24793480) +4904 train 6.996812 (lr=1.7655e-05) (hash(x)=25344456) +4905 train 6.903560 (lr=1.7652e-05) (hash(x)=24590670) +4906 train 6.850603 (lr=1.7649e-05) (hash(x)=26937171) +4907 train 6.977675 (lr=1.7646e-05) (hash(x)=26949097) +4908 train 6.682796 (lr=1.7643e-05) (hash(x)=22443915) +4909 train 6.776030 (lr=1.7640e-05) (hash(x)=23814995) +4910 train 6.831769 (lr=1.7637e-05) (hash(x)=26135871) +4911 train 6.663278 (lr=1.7634e-05) (hash(x)=25415570) +4912 train 7.014316 (lr=1.7631e-05) (hash(x)=26756326) +4913 train 6.835277 (lr=1.7628e-05) (hash(x)=22920200) +4914 train 6.886926 (lr=1.7625e-05) (hash(x)=26710977) +4915 train 6.830363 (lr=1.7622e-05) (hash(x)=24985634) +4916 train 6.940105 (lr=1.7619e-05) (hash(x)=26004335) +4917 train 6.864182 (lr=1.7616e-05) (hash(x)=25637457) +4918 train 7.099922 (lr=1.7613e-05) (hash(x)=26645180) +4919 train 6.949733 (lr=1.7611e-05) (hash(x)=24425760) +4920 train 7.203304 (lr=1.7608e-05) (hash(x)=28223544) +4921 train 6.867339 (lr=1.7605e-05) (hash(x)=25538618) +4922 train 7.078314 (lr=1.7603e-05) (hash(x)=26984784) +4923 train 7.159619 (lr=1.7600e-05) (hash(x)=29154578) +4924 train 6.828113 (lr=1.7597e-05) (hash(x)=25308123) +4925 train 7.171484 (lr=1.7595e-05) (hash(x)=27939259) +4926 train 6.769840 (lr=1.7592e-05) (hash(x)=21984545) +4927 train 6.780930 (lr=1.7590e-05) (hash(x)=23707134) +4928 train 6.850050 (lr=1.7587e-05) (hash(x)=27201034) +4929 train 7.183071 (lr=1.7585e-05) (hash(x)=31623877) +4930 train 6.898935 (lr=1.7583e-05) (hash(x)=22162782) +4931 train 6.815515 (lr=1.7580e-05) (hash(x)=20049335) +4932 train 6.723375 (lr=1.7578e-05) (hash(x)=25594665) +4933 train 6.821468 (lr=1.7576e-05) (hash(x)=25265312) +4934 train 6.935918 (lr=1.7573e-05) (hash(x)=27094896) +4935 train 7.301876 (lr=1.7571e-05) (hash(x)=28321697) +4936 train 6.798506 (lr=1.7569e-05) (hash(x)=25006013) +4937 train 7.019775 (lr=1.7567e-05) (hash(x)=24596431) +4938 train 7.044205 (lr=1.7565e-05) (hash(x)=25150510) +4939 train 6.518428 (lr=1.7563e-05) (hash(x)=21497535) +4940 train 6.836492 (lr=1.7561e-05) (hash(x)=25094669) +4941 train 6.689918 (lr=1.7559e-05) (hash(x)=24024557) +4942 train 7.013366 (lr=1.7557e-05) (hash(x)=24370776) +4943 train 6.887035 (lr=1.7555e-05) (hash(x)=23434031) +4944 train 6.830760 (lr=1.7553e-05) (hash(x)=24383517) +4945 train 6.853674 (lr=1.7551e-05) (hash(x)=25858759) +4946 train 6.441849 (lr=1.7549e-05) (hash(x)=20409561) +4947 train 7.155850 (lr=1.7547e-05) (hash(x)=27469117) +4948 train 6.695686 (lr=1.7546e-05) (hash(x)=22086623) +4949 train 6.998756 (lr=1.7544e-05) (hash(x)=25759281) +4950 val loss 6.8476 +4950 val perplexity 941.6286 +4950 train 6.917680 (lr=1.7542e-05) (hash(x)=27130117) +4951 train 6.776254 (lr=1.7540e-05) (hash(x)=27003481) +4952 train 7.098798 (lr=1.7539e-05) (hash(x)=26725937) +4953 train 6.829429 (lr=1.7537e-05) (hash(x)=22691119) +4954 train 6.928755 (lr=1.7536e-05) (hash(x)=17272898) +4955 train 6.732567 (lr=1.7534e-05) (hash(x)=17850370) +4956 train 6.708738 (lr=1.7533e-05) (hash(x)=18729639) +4957 train 6.912189 (lr=1.7531e-05) (hash(x)=25327160) +4958 train 7.038198 (lr=1.7530e-05) (hash(x)=28709044) +4959 train 6.599286 (lr=1.7528e-05) (hash(x)=22236893) +4960 train 6.572000 (lr=1.7527e-05) (hash(x)=21729251) +4961 train 6.675761 (lr=1.7526e-05) (hash(x)=23852346) +4962 train 6.923357 (lr=1.7524e-05) (hash(x)=23974368) +4963 train 6.850718 (lr=1.7523e-05) (hash(x)=25764691) +4964 train 7.228931 (lr=1.7522e-05) (hash(x)=28341865) +4965 train 6.710148 (lr=1.7521e-05) (hash(x)=23856238) +4966 train 6.977136 (lr=1.7519e-05) (hash(x)=24568904) +4967 train 6.880764 (lr=1.7518e-05) (hash(x)=26857458) +4968 train 6.716918 (lr=1.7517e-05) (hash(x)=20507972) +4969 train 6.928884 (lr=1.7516e-05) (hash(x)=23139455) +4970 train 6.747704 (lr=1.7515e-05) (hash(x)=24853703) +4971 train 6.798585 (lr=1.7514e-05) (hash(x)=25654849) +4972 train 6.631575 (lr=1.7513e-05) (hash(x)=22963710) +4973 train 7.014744 (lr=1.7512e-05) (hash(x)=25652110) +4974 train 6.950275 (lr=1.7511e-05) (hash(x)=24085957) +4975 train 7.173336 (lr=1.7511e-05) (hash(x)=26413122) +4976 train 7.325288 (lr=1.7510e-05) (hash(x)=26989387) +4977 train 6.979928 (lr=1.7509e-05) (hash(x)=22784033) +4978 train 7.346239 (lr=1.7508e-05) (hash(x)=26694945) +4979 train 7.276747 (lr=1.7507e-05) (hash(x)=24507726) +4980 train 7.351413 (lr=1.7507e-05) (hash(x)=26490335) +4981 train 7.272418 (lr=1.7506e-05) (hash(x)=25624751) +4982 train 7.209583 (lr=1.7505e-05) (hash(x)=27846204) +4983 train 7.076420 (lr=1.7505e-05) (hash(x)=27696537) +4984 train 6.970578 (lr=1.7504e-05) (hash(x)=28915842) +4985 train 7.024146 (lr=1.7504e-05) (hash(x)=28274576) +4986 train 7.030910 (lr=1.7503e-05) (hash(x)=28923892) +4987 train 6.636160 (lr=1.7503e-05) (hash(x)=21602520) +4988 train 6.572734 (lr=1.7502e-05) (hash(x)=21061011) +4989 train 7.071750 (lr=1.7502e-05) (hash(x)=28060542) +4990 train 6.863745 (lr=1.7502e-05) (hash(x)=24838134) +4991 train 6.811313 (lr=1.7501e-05) (hash(x)=21950234) +4992 train 7.090426 (lr=1.7501e-05) (hash(x)=27192740) +4993 train 7.049943 (lr=1.7501e-05) (hash(x)=26770105) +4994 train 6.701662 (lr=1.7501e-05) (hash(x)=23721261) +4995 train 6.783868 (lr=1.7500e-05) (hash(x)=26064895) +4996 train 6.971525 (lr=1.7500e-05) (hash(x)=25651075) +4997 train 6.828383 (lr=1.7500e-05) (hash(x)=25029447) +4998 train 6.979232 (lr=1.7500e-05) (hash(x)=26088225) +4999 val loss 6.8481 +4999 val perplexity 942.0786 +4999 train 6.887456 (lr=1.7500e-05) (hash(x)=24051952) diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/model_02500.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/model_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..34ae90f4351a6fc925c6ef2a311671dcd4c82be2 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/model_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a7570a945466aabde12025fb8dfcd9b796dd3e2e51890329e3fa3eb72b51e76 +size 38587970 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/model_04999.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/model_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..bb0b6e28928a864901d1fff890523cb45a6c4cfe --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/model_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8142462dc3b9b330636bc72945bd70bf8a161f48cc13f6943cd9f11e1b218b8b +size 38587970 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/optimizer_02500.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/optimizer_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..72f7f220946858fffe03d6fe5161fd7aa7e7dfd8 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/optimizer_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:938e4f91794f0f255cd401c60167b96750cf1c47b92ed00f0b52da29a383a8d5 +size 70895430 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/optimizer_04999.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/optimizer_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..ca9bee96fe77f622018de402234f0fff0939e366 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200_seed1339/optimizer_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e0c5c32c2ac3624c06b530d32622310af02d78a2344acf24ac3bb5330add948 +size 70895430