diff --git a/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/args.json b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/args.json new file mode 100644 index 0000000000000000000000000000000000000000..6cb9146cbd6258c069bc0349cc1afc841521546a --- /dev/null +++ b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/args.json @@ -0,0 +1 @@ +{"hellaswag": true, "attention_kind": "selective", "log_dir": "proxy_model_sweep_2/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200", "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": 1337, "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": 0.0001, "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/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/dataloader_02500.pt b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/dataloader_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bc253f8fc6225637fb651d7b45bcde02b1c9ff0 --- /dev/null +++ b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/dataloader_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5f86eba64e08aa3145708d463ef689ecaee47ebe0a97035e6e0aeb59f377344 +size 964 diff --git a/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/dataloader_04999.pt b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/dataloader_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..0618c479f1dc6588bdd52311cf3417cbd843ddd9 --- /dev/null +++ b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/dataloader_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431842dc67f0d83e5eb85cf9c36fd024e295001fe78f3ba5deeae77865394feb +size 964 diff --git a/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/log2.txt b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/log2.txt new file mode 100644 index 0000000000000000000000000000000000000000..5f2eab16492bd3d5c4b8963c87262d3e1e0e6b7d --- /dev/null +++ b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/log2.txt @@ -0,0 +1,5203 @@ +max_steps: 5000 +0 val loss 11.7537 +0 val perplexity 127229.2734 +0 train 11.717543 (lr=5.0000e-07) (hash(x)=22886834) +1 train 11.791148 (lr=1.0000e-06) (hash(x)=26375038) +2 train 11.774296 (lr=1.5000e-06) (hash(x)=30598777) +3 train 11.767374 (lr=2.0000e-06) (hash(x)=27234506) +4 train 11.694025 (lr=2.5000e-06) (hash(x)=27767880) +5 train 11.717905 (lr=3.0000e-06) (hash(x)=23702020) +6 train 11.689738 (lr=3.5000e-06) (hash(x)=31986844) +7 train 11.718233 (lr=4.0000e-06) (hash(x)=20782690) +8 train 11.705768 (lr=4.5000e-06) (hash(x)=25201599) +9 train 11.674097 (lr=5.0000e-06) (hash(x)=23094976) +10 train 11.696157 (lr=5.5000e-06) (hash(x)=23841096) +11 train 11.706876 (lr=6.0000e-06) (hash(x)=26532095) +12 train 11.664809 (lr=6.5000e-06) (hash(x)=24432298) +13 train 11.622833 (lr=7.0000e-06) (hash(x)=27151649) +14 train 11.563034 (lr=7.5000e-06) (hash(x)=24596846) +15 train 11.587021 (lr=8.0000e-06) (hash(x)=23890908) +16 train 11.514373 (lr=8.5000e-06) (hash(x)=28913955) +17 train 11.510559 (lr=9.0000e-06) (hash(x)=25588236) +18 train 11.510505 (lr=9.5000e-06) (hash(x)=23770034) +19 train 11.497057 (lr=1.0000e-05) (hash(x)=24011372) +20 train 11.414654 (lr=1.0500e-05) (hash(x)=25441898) +21 train 11.429493 (lr=1.1000e-05) (hash(x)=28375581) +22 train 11.391650 (lr=1.1500e-05) (hash(x)=24046679) +23 train 11.333480 (lr=1.2000e-05) (hash(x)=24611628) +24 train 11.313580 (lr=1.2500e-05) (hash(x)=26169030) +25 train 11.275523 (lr=1.3000e-05) (hash(x)=30298407) +26 train 11.224258 (lr=1.3500e-05) (hash(x)=23711112) +27 train 11.159025 (lr=1.4000e-05) (hash(x)=19245352) +28 train 11.132742 (lr=1.4500e-05) (hash(x)=21529136) +29 train 11.082305 (lr=1.5000e-05) (hash(x)=28936608) +30 train 11.003980 (lr=1.5500e-05) (hash(x)=24339013) +31 train 10.928147 (lr=1.6000e-05) (hash(x)=25767553) +32 train 10.973014 (lr=1.6500e-05) (hash(x)=26439905) +33 train 10.914645 (lr=1.7000e-05) (hash(x)=31093473) +34 train 10.910687 (lr=1.7500e-05) (hash(x)=25450374) +35 train 10.886195 (lr=1.8000e-05) (hash(x)=24809873) +36 train 10.924857 (lr=1.8500e-05) (hash(x)=23253252) +37 train 10.880988 (lr=1.9000e-05) (hash(x)=27852919) +38 train 10.806103 (lr=1.9500e-05) (hash(x)=23327497) +39 train 10.743582 (lr=2.0000e-05) (hash(x)=22512166) +40 train 10.733600 (lr=2.0500e-05) (hash(x)=22859419) +41 train 10.748346 (lr=2.1000e-05) (hash(x)=27620338) +42 train 10.657208 (lr=2.1500e-05) (hash(x)=26397837) +43 train 10.590596 (lr=2.2000e-05) (hash(x)=28092148) +44 train 10.583491 (lr=2.2500e-05) (hash(x)=24662703) +45 train 10.619946 (lr=2.3000e-05) (hash(x)=27938767) +46 train 10.612073 (lr=2.3500e-05) (hash(x)=26037988) +47 train 10.542515 (lr=2.4000e-05) (hash(x)=24732833) +48 train 10.488375 (lr=2.4500e-05) (hash(x)=25259526) +49 train 10.495667 (lr=2.5000e-05) (hash(x)=23200230) +50 val loss 10.4426 +50 val perplexity 34288.7188 +50 train 10.452418 (lr=2.5500e-05) (hash(x)=26721357) +51 train 10.380390 (lr=2.6000e-05) (hash(x)=22694718) +52 train 10.411171 (lr=2.6500e-05) (hash(x)=28066766) +53 train 10.397777 (lr=2.7000e-05) (hash(x)=23125151) +54 train 10.306638 (lr=2.7500e-05) (hash(x)=27193725) +55 train 10.280418 (lr=2.8000e-05) (hash(x)=25129410) +56 train 10.408997 (lr=2.8500e-05) (hash(x)=24263988) +57 train 10.321315 (lr=2.9000e-05) (hash(x)=23059154) +58 train 10.285110 (lr=2.9500e-05) (hash(x)=26063864) +59 train 10.406013 (lr=3.0000e-05) (hash(x)=27858570) +60 train 10.310256 (lr=3.0500e-05) (hash(x)=23874620) +61 train 10.259917 (lr=3.1000e-05) (hash(x)=22402617) +62 train 10.272315 (lr=3.1500e-05) (hash(x)=23600822) +63 train 10.089684 (lr=3.2000e-05) (hash(x)=26582391) +64 train 10.057032 (lr=3.2500e-05) (hash(x)=23225283) +65 train 10.068942 (lr=3.3000e-05) (hash(x)=26075451) +66 train 10.223747 (lr=3.3500e-05) (hash(x)=24723419) +67 train 10.225207 (lr=3.4000e-05) (hash(x)=27279806) +68 train 10.040860 (lr=3.4500e-05) (hash(x)=25870391) +69 train 10.120662 (lr=3.5000e-05) (hash(x)=26188136) +70 train 10.079686 (lr=3.5500e-05) (hash(x)=30373443) +71 train 10.173802 (lr=3.6000e-05) (hash(x)=26472336) +72 train 9.995460 (lr=3.6500e-05) (hash(x)=26651572) +73 train 9.997302 (lr=3.7000e-05) (hash(x)=26376212) +74 train 10.079582 (lr=3.7500e-05) (hash(x)=26733350) +75 train 10.044250 (lr=3.8000e-05) (hash(x)=28301589) +76 train 9.981005 (lr=3.8500e-05) (hash(x)=27599559) +77 train 9.968283 (lr=3.9000e-05) (hash(x)=28035221) +78 train 10.077829 (lr=3.9500e-05) (hash(x)=25016783) +79 train 10.065589 (lr=4.0000e-05) (hash(x)=27654289) +80 train 10.083023 (lr=4.0500e-05) (hash(x)=24597558) +81 train 10.009830 (lr=4.1000e-05) (hash(x)=21560904) +82 train 9.975218 (lr=4.1500e-05) (hash(x)=21983837) +83 train 9.961377 (lr=4.2000e-05) (hash(x)=24995715) +84 train 10.011349 (lr=4.2500e-05) (hash(x)=29876413) +85 train 9.971313 (lr=4.3000e-05) (hash(x)=23792508) +86 train 9.879027 (lr=4.3500e-05) (hash(x)=25509120) +87 train 9.896153 (lr=4.4000e-05) (hash(x)=26559876) +88 train 9.935773 (lr=4.4500e-05) (hash(x)=23569647) +89 train 9.882335 (lr=4.5000e-05) (hash(x)=25758852) +90 train 9.777249 (lr=4.5500e-05) (hash(x)=25706298) +91 train 9.733275 (lr=4.6000e-05) (hash(x)=28364895) +92 train 9.840235 (lr=4.6500e-05) (hash(x)=25304663) +93 train 9.814618 (lr=4.7000e-05) (hash(x)=25269299) +94 train 9.978966 (lr=4.7500e-05) (hash(x)=25870566) +95 train 9.808481 (lr=4.8000e-05) (hash(x)=21770329) +96 train 9.935964 (lr=4.8500e-05) (hash(x)=27595900) +97 train 9.959178 (lr=4.9000e-05) (hash(x)=24785397) +98 train 9.750016 (lr=4.9500e-05) (hash(x)=21521480) +99 train 9.751403 (lr=5.0000e-05) (hash(x)=24628606) +100 val loss 9.7768 +100 val perplexity 17620.7188 +100 train 9.818863 (lr=5.0500e-05) (hash(x)=24670150) +101 train 9.748668 (lr=5.1000e-05) (hash(x)=23181910) +102 train 9.755307 (lr=5.1500e-05) (hash(x)=22714991) +103 train 9.866544 (lr=5.2000e-05) (hash(x)=22723459) +104 train 9.767305 (lr=5.2500e-05) (hash(x)=21524316) +105 train 9.731975 (lr=5.3000e-05) (hash(x)=25506632) +106 train 9.568256 (lr=5.3500e-05) (hash(x)=21675672) +107 train 9.659647 (lr=5.4000e-05) (hash(x)=22897919) +108 train 9.709656 (lr=5.4500e-05) (hash(x)=23321631) +109 train 9.694289 (lr=5.5000e-05) (hash(x)=26546719) +110 train 10.225426 (lr=5.5500e-05) (hash(x)=31962348) +111 train 9.668236 (lr=5.6000e-05) (hash(x)=30338342) +112 train 9.586009 (lr=5.6500e-05) (hash(x)=23724471) +113 train 9.659467 (lr=5.7000e-05) (hash(x)=29175888) +114 train 9.718089 (lr=5.7500e-05) (hash(x)=23256716) +115 train 9.626838 (lr=5.8000e-05) (hash(x)=27063280) +116 train 9.583290 (lr=5.8500e-05) (hash(x)=31057659) +117 train 9.628167 (lr=5.9000e-05) (hash(x)=32915097) +118 train 9.615371 (lr=5.9500e-05) (hash(x)=28842717) +119 train 9.535438 (lr=6.0000e-05) (hash(x)=25678059) +120 train 9.524816 (lr=6.0500e-05) (hash(x)=21593510) +121 train 9.388110 (lr=6.1000e-05) (hash(x)=20083773) +122 train 9.626368 (lr=6.1500e-05) (hash(x)=23002820) +123 train 9.456954 (lr=6.2000e-05) (hash(x)=21853028) +124 train 9.441917 (lr=6.2500e-05) (hash(x)=26985625) +125 train 9.438922 (lr=6.3000e-05) (hash(x)=21808483) +126 train 9.525559 (lr=6.3500e-05) (hash(x)=28873251) +127 train 9.485570 (lr=6.4000e-05) (hash(x)=26109335) +128 train 9.504525 (lr=6.4500e-05) (hash(x)=26334674) +129 train 9.533132 (lr=6.5000e-05) (hash(x)=24916754) +130 train 9.445696 (lr=6.5500e-05) (hash(x)=25449624) +131 train 9.541610 (lr=6.6000e-05) (hash(x)=25334848) +132 train 9.488467 (lr=6.6500e-05) (hash(x)=27484863) +133 train 9.320836 (lr=6.7000e-05) (hash(x)=24917705) +134 train 9.267656 (lr=6.7500e-05) (hash(x)=25143449) +135 train 9.309358 (lr=6.8000e-05) (hash(x)=25044885) +136 train 9.360680 (lr=6.8500e-05) (hash(x)=27821028) +137 train 9.389270 (lr=6.9000e-05) (hash(x)=28747022) +138 train 9.382277 (lr=6.9500e-05) (hash(x)=27182888) +139 train 9.266914 (lr=7.0000e-05) (hash(x)=23678349) +140 train 9.369065 (lr=7.0500e-05) (hash(x)=23593235) +141 train 9.414867 (lr=7.1000e-05) (hash(x)=28529813) +142 train 9.554746 (lr=7.1500e-05) (hash(x)=32074661) +143 train 9.300135 (lr=7.2000e-05) (hash(x)=28870690) +144 train 9.345124 (lr=7.2500e-05) (hash(x)=27307705) +145 train 9.287250 (lr=7.3000e-05) (hash(x)=25044834) +146 train 9.304664 (lr=7.3500e-05) (hash(x)=23712023) +147 train 9.511298 (lr=7.4000e-05) (hash(x)=32982615) +148 train 9.373015 (lr=7.4500e-05) (hash(x)=30113660) +149 train 9.222826 (lr=7.5000e-05) (hash(x)=20970960) +150 val loss 9.1922 +150 val perplexity 9820.2480 +150 train 9.244207 (lr=7.5500e-05) (hash(x)=23132684) +151 train 10.105093 (lr=7.6000e-05) (hash(x)=35279941) +152 train 9.628279 (lr=7.6500e-05) (hash(x)=31227444) +153 train 9.128272 (lr=7.7000e-05) (hash(x)=25529472) +154 train 9.128903 (lr=7.7500e-05) (hash(x)=24350409) +155 train 9.395986 (lr=7.8000e-05) (hash(x)=26400041) +156 train 9.190023 (lr=7.8500e-05) (hash(x)=25262621) +157 train 9.204473 (lr=7.9000e-05) (hash(x)=24656138) +158 train 9.228887 (lr=7.9500e-05) (hash(x)=26803414) +159 train 9.174343 (lr=8.0000e-05) (hash(x)=25015923) +160 train 9.013201 (lr=8.0500e-05) (hash(x)=23581172) +161 train 9.032209 (lr=8.1000e-05) (hash(x)=22924885) +162 train 9.037453 (lr=8.1500e-05) (hash(x)=23414296) +163 train 9.260027 (lr=8.2000e-05) (hash(x)=24853586) +164 train 9.272435 (lr=8.2500e-05) (hash(x)=25000130) +165 train 9.126460 (lr=8.3000e-05) (hash(x)=27004780) +166 train 9.097142 (lr=8.3500e-05) (hash(x)=26148573) +167 train 9.056226 (lr=8.4000e-05) (hash(x)=26740855) +168 train 8.793766 (lr=8.4500e-05) (hash(x)=20965419) +169 train 8.875299 (lr=8.5000e-05) (hash(x)=23950114) +170 train 8.799952 (lr=8.5500e-05) (hash(x)=24951982) +171 train 8.932489 (lr=8.6000e-05) (hash(x)=24584116) +172 train 8.955546 (lr=8.6500e-05) (hash(x)=24378759) +173 train 8.815804 (lr=8.7000e-05) (hash(x)=25718516) +174 train 8.967551 (lr=8.7500e-05) (hash(x)=28424396) +175 train 8.797860 (lr=8.8000e-05) (hash(x)=22262151) +176 train 8.997576 (lr=8.8500e-05) (hash(x)=26438412) +177 train 8.806168 (lr=8.9000e-05) (hash(x)=23025303) +178 train 8.803565 (lr=8.9500e-05) (hash(x)=24190770) +179 train 8.808853 (lr=9.0000e-05) (hash(x)=26627860) +180 train 8.870173 (lr=9.0500e-05) (hash(x)=23663439) +181 train 8.651610 (lr=9.1000e-05) (hash(x)=23700532) +182 train 8.780563 (lr=9.1500e-05) (hash(x)=23075676) +183 train 8.844901 (lr=9.2000e-05) (hash(x)=26621834) +184 train 8.796781 (lr=9.2500e-05) (hash(x)=29426269) +185 train 8.628044 (lr=9.3000e-05) (hash(x)=21821465) +186 train 8.730048 (lr=9.3500e-05) (hash(x)=26506130) +187 train 8.930550 (lr=9.4000e-05) (hash(x)=26930630) +188 train 8.681235 (lr=9.4500e-05) (hash(x)=22993793) +189 train 8.600999 (lr=9.5000e-05) (hash(x)=19557946) +190 train 8.775767 (lr=9.5500e-05) (hash(x)=23572891) +191 train 8.601241 (lr=9.6000e-05) (hash(x)=23234741) +192 train 8.628249 (lr=9.6500e-05) (hash(x)=25547951) +193 train 8.584600 (lr=9.7000e-05) (hash(x)=26713563) +194 train 8.688560 (lr=9.7500e-05) (hash(x)=25913622) +195 train 8.789580 (lr=9.8000e-05) (hash(x)=28102443) +196 train 8.586296 (lr=9.8500e-05) (hash(x)=23093351) +197 train 9.069463 (lr=9.9000e-05) (hash(x)=31689122) +198 train 8.968048 (lr=9.9500e-05) (hash(x)=32252517) +199 train 8.599006 (lr=1.0000e-04) (hash(x)=25470563) +200 val loss 8.5836 +200 val perplexity 5343.3174 +200 train 8.674526 (lr=1.0000e-04) (hash(x)=25597614) +201 train 8.661656 (lr=1.0000e-04) (hash(x)=23757479) +202 train 8.528800 (lr=1.0000e-04) (hash(x)=25140048) +203 train 8.621612 (lr=1.0000e-04) (hash(x)=28282861) +204 train 8.563056 (lr=1.0000e-04) (hash(x)=24754885) +205 train 8.639158 (lr=1.0000e-04) (hash(x)=26731964) +206 train 8.664908 (lr=1.0000e-04) (hash(x)=26660561) +207 train 8.464404 (lr=1.0000e-04) (hash(x)=21799102) +208 train 8.576723 (lr=9.9999e-05) (hash(x)=27025986) +209 train 8.424191 (lr=9.9999e-05) (hash(x)=24672077) +210 train 8.492984 (lr=9.9999e-05) (hash(x)=25322984) +211 train 8.354903 (lr=9.9999e-05) (hash(x)=23471769) +212 train 8.151738 (lr=9.9999e-05) (hash(x)=20766491) +213 train 8.577545 (lr=9.9998e-05) (hash(x)=24058931) +214 train 8.379951 (lr=9.9998e-05) (hash(x)=23872843) +215 train 8.388368 (lr=9.9998e-05) (hash(x)=23275479) +216 train 8.485564 (lr=9.9998e-05) (hash(x)=24914695) +217 train 8.335305 (lr=9.9997e-05) (hash(x)=24364396) +218 train 8.384751 (lr=9.9997e-05) (hash(x)=27986474) +219 train 8.361603 (lr=9.9997e-05) (hash(x)=24473581) +220 train 8.358359 (lr=9.9996e-05) (hash(x)=22974689) +221 train 8.399707 (lr=9.9996e-05) (hash(x)=23774644) +222 train 8.389674 (lr=9.9995e-05) (hash(x)=23245327) +223 train 8.175067 (lr=9.9995e-05) (hash(x)=22091862) +224 train 8.188159 (lr=9.9994e-05) (hash(x)=24362839) +225 train 8.258307 (lr=9.9994e-05) (hash(x)=25482303) +226 train 8.350518 (lr=9.9993e-05) (hash(x)=24911853) +227 train 8.267423 (lr=9.9993e-05) (hash(x)=26018202) +228 train 8.120996 (lr=9.9992e-05) (hash(x)=26124495) +229 train 8.138924 (lr=9.9992e-05) (hash(x)=24560096) +230 train 8.199431 (lr=9.9991e-05) (hash(x)=24695331) +231 train 8.105962 (lr=9.9991e-05) (hash(x)=17430373) +232 train 8.048963 (lr=9.9990e-05) (hash(x)=21813345) +233 train 7.622435 (lr=9.9990e-05) (hash(x)=20098681) +234 train 7.932193 (lr=9.9989e-05) (hash(x)=25095928) +235 train 8.062198 (lr=9.9988e-05) (hash(x)=24078083) +236 train 8.012694 (lr=9.9988e-05) (hash(x)=22901505) +237 train 8.139340 (lr=9.9987e-05) (hash(x)=26595592) +238 train 8.100632 (lr=9.9986e-05) (hash(x)=27663196) +239 train 7.904012 (lr=9.9985e-05) (hash(x)=22954861) +240 train 8.293597 (lr=9.9985e-05) (hash(x)=30159234) +241 train 8.162087 (lr=9.9984e-05) (hash(x)=29294271) +242 train 8.103084 (lr=9.9983e-05) (hash(x)=23728322) +243 train 8.152059 (lr=9.9982e-05) (hash(x)=28695016) +244 train 8.265421 (lr=9.9981e-05) (hash(x)=26702728) +245 train 8.060061 (lr=9.9980e-05) (hash(x)=27100115) +246 train 7.988558 (lr=9.9980e-05) (hash(x)=25082752) +247 train 8.321895 (lr=9.9979e-05) (hash(x)=26671799) +248 train 8.083918 (lr=9.9978e-05) (hash(x)=23718946) +249 train 8.228238 (lr=9.9977e-05) (hash(x)=28137394) +250 val loss 8.0163 +250 val perplexity 3029.9001 +250 train 8.290059 (lr=9.9976e-05) (hash(x)=23893495) +251 train 8.071246 (lr=9.9975e-05) (hash(x)=23166092) +252 train 8.039131 (lr=9.9974e-05) (hash(x)=25907665) +253 train 7.949707 (lr=9.9973e-05) (hash(x)=25885986) +254 train 8.050296 (lr=9.9972e-05) (hash(x)=25262712) +255 train 8.012464 (lr=9.9971e-05) (hash(x)=26924723) +256 train 8.164421 (lr=9.9970e-05) (hash(x)=28744736) +257 train 7.936325 (lr=9.9969e-05) (hash(x)=26140590) +258 train 8.129687 (lr=9.9968e-05) (hash(x)=25780449) +259 train 7.953636 (lr=9.9966e-05) (hash(x)=25138659) +260 train 8.193129 (lr=9.9965e-05) (hash(x)=27244046) +261 train 8.082969 (lr=9.9964e-05) (hash(x)=27224685) +262 train 8.318938 (lr=9.9963e-05) (hash(x)=28274477) +263 train 7.909862 (lr=9.9962e-05) (hash(x)=23557495) +264 train 7.981049 (lr=9.9961e-05) (hash(x)=24680596) +265 train 7.938049 (lr=9.9959e-05) (hash(x)=23928957) +266 train 7.878102 (lr=9.9958e-05) (hash(x)=23761390) +267 train 7.881931 (lr=9.9957e-05) (hash(x)=25288123) +268 train 8.082782 (lr=9.9955e-05) (hash(x)=28705502) +269 train 7.769020 (lr=9.9954e-05) (hash(x)=23246294) +270 train 7.840169 (lr=9.9953e-05) (hash(x)=28639079) +271 train 7.746507 (lr=9.9951e-05) (hash(x)=27804380) +272 train 7.955101 (lr=9.9950e-05) (hash(x)=24172235) +273 train 7.977670 (lr=9.9949e-05) (hash(x)=23089140) +274 train 8.167956 (lr=9.9947e-05) (hash(x)=27163701) +275 train 8.223762 (lr=9.9946e-05) (hash(x)=26993263) +276 train 7.990491 (lr=9.9944e-05) (hash(x)=28224233) +277 train 8.216460 (lr=9.9943e-05) (hash(x)=27397203) +278 train 8.191266 (lr=9.9941e-05) (hash(x)=27923882) +279 train 8.005309 (lr=9.9940e-05) (hash(x)=26654908) +280 train 7.966596 (lr=9.9938e-05) (hash(x)=24213147) +281 train 7.714232 (lr=9.9937e-05) (hash(x)=21965022) +282 train 7.885773 (lr=9.9935e-05) (hash(x)=25465685) +283 train 8.035399 (lr=9.9934e-05) (hash(x)=27347722) +284 train 8.031413 (lr=9.9932e-05) (hash(x)=26732050) +285 train 8.191075 (lr=9.9930e-05) (hash(x)=28314127) +286 train 7.759979 (lr=9.9929e-05) (hash(x)=21471186) +287 train 7.777987 (lr=9.9927e-05) (hash(x)=23627518) +288 train 7.767568 (lr=9.9925e-05) (hash(x)=20870353) +289 train 7.861176 (lr=9.9924e-05) (hash(x)=25024764) +290 train 7.668922 (lr=9.9922e-05) (hash(x)=20683822) +291 train 7.948330 (lr=9.9920e-05) (hash(x)=21768671) +292 train 7.946980 (lr=9.9918e-05) (hash(x)=25557309) +293 train 8.054116 (lr=9.9917e-05) (hash(x)=25076667) +294 train 7.788653 (lr=9.9915e-05) (hash(x)=23765822) +295 train 7.745824 (lr=9.9913e-05) (hash(x)=21889990) +296 train 7.922730 (lr=9.9911e-05) (hash(x)=26339893) +297 train 7.623785 (lr=9.9909e-05) (hash(x)=20932794) +298 train 7.751045 (lr=9.9907e-05) (hash(x)=21750070) +299 train 7.934078 (lr=9.9906e-05) (hash(x)=23665838) +300 val loss 7.8557 +300 val perplexity 2580.4341 +300 train 8.626081 (lr=9.9904e-05) (hash(x)=32888061) +301 train 8.390717 (lr=9.9902e-05) (hash(x)=30223582) +302 train 8.143650 (lr=9.9900e-05) (hash(x)=26908418) +303 train 7.533394 (lr=9.9898e-05) (hash(x)=22528001) +304 train 8.048970 (lr=9.9896e-05) (hash(x)=27452187) +305 train 7.875854 (lr=9.9894e-05) (hash(x)=25181641) +306 train 7.926123 (lr=9.9892e-05) (hash(x)=25546593) +307 train 7.961288 (lr=9.9890e-05) (hash(x)=22487328) +308 train 8.064745 (lr=9.9888e-05) (hash(x)=27804274) +309 train 8.126706 (lr=9.9886e-05) (hash(x)=26544630) +310 train 8.262713 (lr=9.9883e-05) (hash(x)=27738934) +311 train 8.031315 (lr=9.9881e-05) (hash(x)=29248942) +312 train 7.813045 (lr=9.9879e-05) (hash(x)=25103452) +313 train 8.017257 (lr=9.9877e-05) (hash(x)=25052066) +314 train 7.844212 (lr=9.9875e-05) (hash(x)=24481302) +315 train 7.820708 (lr=9.9873e-05) (hash(x)=23543273) +316 train 7.813313 (lr=9.9870e-05) (hash(x)=25608244) +317 train 7.986979 (lr=9.9868e-05) (hash(x)=27451288) +318 train 7.667023 (lr=9.9866e-05) (hash(x)=22806491) +319 train 7.834596 (lr=9.9864e-05) (hash(x)=25533417) +320 train 7.839604 (lr=9.9861e-05) (hash(x)=24557997) +321 train 7.892155 (lr=9.9859e-05) (hash(x)=24432899) +322 train 8.094562 (lr=9.9857e-05) (hash(x)=27583287) +323 train 8.001032 (lr=9.9854e-05) (hash(x)=25552036) +324 train 7.779908 (lr=9.9852e-05) (hash(x)=24201868) +325 train 8.047614 (lr=9.9849e-05) (hash(x)=28149782) +326 train 7.865846 (lr=9.9847e-05) (hash(x)=25529698) +327 train 7.565611 (lr=9.9845e-05) (hash(x)=20612533) +328 train 7.613857 (lr=9.9842e-05) (hash(x)=20699000) +329 train 7.579123 (lr=9.9840e-05) (hash(x)=19774173) +330 train 7.634419 (lr=9.9837e-05) (hash(x)=21681646) +331 train 7.513054 (lr=9.9835e-05) (hash(x)=20216795) +332 train 8.066974 (lr=9.9832e-05) (hash(x)=27697998) +333 train 7.901691 (lr=9.9830e-05) (hash(x)=25896435) +334 train 7.753703 (lr=9.9827e-05) (hash(x)=21585310) +335 train 7.811893 (lr=9.9824e-05) (hash(x)=24677740) +336 train 7.645640 (lr=9.9822e-05) (hash(x)=22027900) +337 train 7.678463 (lr=9.9819e-05) (hash(x)=21835643) +338 train 7.580638 (lr=9.9817e-05) (hash(x)=20558462) +339 train 7.530559 (lr=9.9814e-05) (hash(x)=16722715) +340 train 7.635645 (lr=9.9811e-05) (hash(x)=20972655) +341 train 8.040879 (lr=9.9809e-05) (hash(x)=26303975) +342 train 7.798607 (lr=9.9806e-05) (hash(x)=22938170) +343 train 7.842052 (lr=9.9803e-05) (hash(x)=25347203) +344 train 7.846238 (lr=9.9800e-05) (hash(x)=27398686) +345 train 7.809822 (lr=9.9798e-05) (hash(x)=25973417) +346 train 7.817956 (lr=9.9795e-05) (hash(x)=26918389) +347 train 7.787659 (lr=9.9792e-05) (hash(x)=24272489) +348 train 7.792881 (lr=9.9789e-05) (hash(x)=25593714) +349 train 7.900801 (lr=9.9786e-05) (hash(x)=29260846) +350 val loss 7.7963 +350 val perplexity 2431.6636 +350 train 7.993730 (lr=9.9783e-05) (hash(x)=27951602) +351 train 8.077891 (lr=9.9780e-05) (hash(x)=28922363) +352 train 7.953830 (lr=9.9778e-05) (hash(x)=27210734) +353 train 7.945892 (lr=9.9775e-05) (hash(x)=26322572) +354 train 7.878439 (lr=9.9772e-05) (hash(x)=27084665) +355 train 7.768027 (lr=9.9769e-05) (hash(x)=25510798) +356 train 7.855779 (lr=9.9766e-05) (hash(x)=24970921) +357 train 7.889483 (lr=9.9763e-05) (hash(x)=24138948) +358 train 7.813313 (lr=9.9760e-05) (hash(x)=24790211) +359 train 7.841788 (lr=9.9757e-05) (hash(x)=25631397) +360 train 7.729650 (lr=9.9753e-05) (hash(x)=23226625) +361 train 7.764099 (lr=9.9750e-05) (hash(x)=24001903) +362 train 7.760417 (lr=9.9747e-05) (hash(x)=24587948) +363 train 7.483226 (lr=9.9744e-05) (hash(x)=21333676) +364 train 7.389046 (lr=9.9741e-05) (hash(x)=23673779) +365 train 8.697715 (lr=9.9738e-05) (hash(x)=30770484) +366 train 7.894783 (lr=9.9735e-05) (hash(x)=26564899) +367 train 7.888393 (lr=9.9731e-05) (hash(x)=26237983) +368 train 7.625299 (lr=9.9728e-05) (hash(x)=23764356) +369 train 7.954674 (lr=9.9725e-05) (hash(x)=26205744) +370 train 7.626493 (lr=9.9722e-05) (hash(x)=19208770) +371 train 7.855874 (lr=9.9718e-05) (hash(x)=25976502) +372 train 7.714458 (lr=9.9715e-05) (hash(x)=23983933) +373 train 7.703249 (lr=9.9712e-05) (hash(x)=24080636) +374 train 7.824359 (lr=9.9709e-05) (hash(x)=24404047) +375 train 7.784371 (lr=9.9705e-05) (hash(x)=24742645) +376 train 7.792115 (lr=9.9702e-05) (hash(x)=24159600) +377 train 8.050934 (lr=9.9698e-05) (hash(x)=28677257) +378 train 7.806250 (lr=9.9695e-05) (hash(x)=25604111) +379 train 7.741827 (lr=9.9692e-05) (hash(x)=27086333) +380 train 7.724776 (lr=9.9688e-05) (hash(x)=25188207) +381 train 7.897764 (lr=9.9685e-05) (hash(x)=27855233) +382 train 7.490703 (lr=9.9681e-05) (hash(x)=19470039) +383 train 7.808545 (lr=9.9678e-05) (hash(x)=26157660) +384 train 7.754638 (lr=9.9674e-05) (hash(x)=25291570) +385 train 7.694666 (lr=9.9671e-05) (hash(x)=25046062) +386 train 8.013748 (lr=9.9667e-05) (hash(x)=27020337) +387 train 7.656032 (lr=9.9663e-05) (hash(x)=23616370) +388 train 7.361691 (lr=9.9660e-05) (hash(x)=19113218) +389 train 7.694899 (lr=9.9656e-05) (hash(x)=24302232) +390 train 7.698671 (lr=9.9653e-05) (hash(x)=22188949) +391 train 7.518701 (lr=9.9649e-05) (hash(x)=22582169) +392 train 7.718729 (lr=9.9645e-05) (hash(x)=24700570) +393 train 7.629510 (lr=9.9641e-05) (hash(x)=22773833) +394 train 7.483158 (lr=9.9638e-05) (hash(x)=21875928) +395 train 7.761631 (lr=9.9634e-05) (hash(x)=26233189) +396 train 7.610033 (lr=9.9630e-05) (hash(x)=24321467) +397 train 7.866858 (lr=9.9626e-05) (hash(x)=26431507) +398 train 7.972069 (lr=9.9623e-05) (hash(x)=28690877) +399 train 7.900959 (lr=9.9619e-05) (hash(x)=26431960) +400 val loss 7.7751 +400 val perplexity 2380.6489 +400 train 7.728631 (lr=9.9615e-05) (hash(x)=24580300) +401 train 7.758382 (lr=9.9611e-05) (hash(x)=25112360) +402 train 7.828086 (lr=9.9607e-05) (hash(x)=27597243) +403 train 8.246428 (lr=9.9603e-05) (hash(x)=30707498) +404 train 7.921945 (lr=9.9599e-05) (hash(x)=28485465) +405 train 7.607574 (lr=9.9596e-05) (hash(x)=22586447) +406 train 7.724748 (lr=9.9592e-05) (hash(x)=23175270) +407 train 7.813931 (lr=9.9588e-05) (hash(x)=25716176) +408 train 7.912572 (lr=9.9584e-05) (hash(x)=26861373) +409 train 8.001615 (lr=9.9580e-05) (hash(x)=25118971) +410 train 7.512779 (lr=9.9576e-05) (hash(x)=19829066) +411 train 7.689018 (lr=9.9572e-05) (hash(x)=26256420) +412 train 7.916815 (lr=9.9568e-05) (hash(x)=27796153) +413 train 7.662607 (lr=9.9563e-05) (hash(x)=22633318) +414 train 7.706013 (lr=9.9559e-05) (hash(x)=22589383) +415 train 8.091255 (lr=9.9555e-05) (hash(x)=28019788) +416 train 8.036534 (lr=9.9551e-05) (hash(x)=28970440) +417 train 7.691381 (lr=9.9547e-05) (hash(x)=27396089) +418 train 7.682308 (lr=9.9543e-05) (hash(x)=21183513) +419 train 7.707077 (lr=9.9539e-05) (hash(x)=23510110) +420 train 7.935289 (lr=9.9534e-05) (hash(x)=28833467) +421 train 7.780090 (lr=9.9530e-05) (hash(x)=23646926) +422 train 7.737181 (lr=9.9526e-05) (hash(x)=24697272) +423 train 7.519940 (lr=9.9522e-05) (hash(x)=20382963) +424 train 7.555287 (lr=9.9517e-05) (hash(x)=23467595) +425 train 7.740663 (lr=9.9513e-05) (hash(x)=24304768) +426 train 7.670421 (lr=9.9509e-05) (hash(x)=21392328) +427 train 7.716104 (lr=9.9504e-05) (hash(x)=25339466) +428 train 7.607124 (lr=9.9500e-05) (hash(x)=22092542) +429 train 7.732859 (lr=9.9496e-05) (hash(x)=22088696) +430 train 7.640871 (lr=9.9491e-05) (hash(x)=22184471) +431 train 7.742539 (lr=9.9487e-05) (hash(x)=24489647) +432 train 7.784955 (lr=9.9482e-05) (hash(x)=26794132) +433 train 7.563036 (lr=9.9478e-05) (hash(x)=22940357) +434 train 7.758945 (lr=9.9473e-05) (hash(x)=23719522) +435 train 7.618813 (lr=9.9469e-05) (hash(x)=22927699) +436 train 7.782980 (lr=9.9464e-05) (hash(x)=26068576) +437 train 7.881954 (lr=9.9460e-05) (hash(x)=27631132) +438 train 7.750226 (lr=9.9455e-05) (hash(x)=26739991) +439 train 7.819572 (lr=9.9451e-05) (hash(x)=25128502) +440 train 7.872389 (lr=9.9446e-05) (hash(x)=25657260) +441 train 7.645148 (lr=9.9441e-05) (hash(x)=23576982) +442 train 7.884838 (lr=9.9437e-05) (hash(x)=27117886) +443 train 7.821048 (lr=9.9432e-05) (hash(x)=25808969) +444 train 7.773300 (lr=9.9427e-05) (hash(x)=24738238) +445 train 7.762508 (lr=9.9423e-05) (hash(x)=23429962) +446 train 7.873083 (lr=9.9418e-05) (hash(x)=25075165) +447 train 7.751924 (lr=9.9413e-05) (hash(x)=25231390) +448 train 7.526475 (lr=9.9409e-05) (hash(x)=22055054) +449 train 7.748540 (lr=9.9404e-05) (hash(x)=25395441) +450 val loss 7.7488 +450 val perplexity 2318.8862 +450 train 7.804873 (lr=9.9399e-05) (hash(x)=25863209) +451 train 7.499594 (lr=9.9394e-05) (hash(x)=21154388) +452 train 7.459474 (lr=9.9389e-05) (hash(x)=21600876) +453 train 7.605766 (lr=9.9384e-05) (hash(x)=24278611) +454 train 7.494721 (lr=9.9380e-05) (hash(x)=23221720) +455 train 7.663011 (lr=9.9375e-05) (hash(x)=22708977) +456 train 8.213643 (lr=9.9370e-05) (hash(x)=23637758) +457 train 7.981488 (lr=9.9365e-05) (hash(x)=28228490) +458 train 8.003145 (lr=9.9360e-05) (hash(x)=28638071) +459 train 7.852913 (lr=9.9355e-05) (hash(x)=27258353) +460 train 7.863774 (lr=9.9350e-05) (hash(x)=26604728) +461 train 7.748739 (lr=9.9345e-05) (hash(x)=23252199) +462 train 7.847767 (lr=9.9340e-05) (hash(x)=26441427) +463 train 7.576848 (lr=9.9335e-05) (hash(x)=24364920) +464 train 7.742551 (lr=9.9330e-05) (hash(x)=25623792) +465 train 7.631734 (lr=9.9325e-05) (hash(x)=23283905) +466 train 8.034983 (lr=9.9320e-05) (hash(x)=26025267) +467 train 7.843510 (lr=9.9315e-05) (hash(x)=27243972) +468 train 8.186464 (lr=9.9310e-05) (hash(x)=30449945) +469 train 7.910814 (lr=9.9304e-05) (hash(x)=28113043) +470 train 7.713929 (lr=9.9299e-05) (hash(x)=25182521) +471 train 7.770517 (lr=9.9294e-05) (hash(x)=24932925) +472 train 7.615549 (lr=9.9289e-05) (hash(x)=20353098) +473 train 7.502066 (lr=9.9284e-05) (hash(x)=19001259) +474 train 8.036162 (lr=9.9278e-05) (hash(x)=27585685) +475 train 7.760082 (lr=9.9273e-05) (hash(x)=26371091) +476 train 7.598426 (lr=9.9268e-05) (hash(x)=24891798) +477 train 7.645143 (lr=9.9262e-05) (hash(x)=24258817) +478 train 7.735620 (lr=9.9257e-05) (hash(x)=24330263) +479 train 7.788456 (lr=9.9252e-05) (hash(x)=26913684) +480 train 7.777271 (lr=9.9246e-05) (hash(x)=26338455) +481 train 8.030086 (lr=9.9241e-05) (hash(x)=27753043) +482 train 7.752409 (lr=9.9236e-05) (hash(x)=26123289) +483 train 7.866055 (lr=9.9230e-05) (hash(x)=29239611) +484 train 7.765050 (lr=9.9225e-05) (hash(x)=26553003) +485 train 7.736943 (lr=9.9219e-05) (hash(x)=22984557) +486 train 7.278147 (lr=9.9214e-05) (hash(x)=16947491) +487 train 7.323411 (lr=9.9208e-05) (hash(x)=18017792) +488 train 7.488973 (lr=9.9203e-05) (hash(x)=19918608) +489 train 7.944309 (lr=9.9197e-05) (hash(x)=23374526) +490 train 7.810419 (lr=9.9192e-05) (hash(x)=25009505) +491 train 7.782021 (lr=9.9186e-05) (hash(x)=27574089) +492 train 7.868452 (lr=9.9181e-05) (hash(x)=24122664) +493 train 7.752498 (lr=9.9175e-05) (hash(x)=26154906) +494 train 7.714033 (lr=9.9169e-05) (hash(x)=25192767) +495 train 7.848149 (lr=9.9164e-05) (hash(x)=28613882) +496 train 7.720334 (lr=9.9158e-05) (hash(x)=23547219) +497 train 7.738115 (lr=9.9152e-05) (hash(x)=25272182) +498 train 7.618700 (lr=9.9147e-05) (hash(x)=24992761) +499 train 7.884619 (lr=9.9141e-05) (hash(x)=26981914) +500 val loss 7.7439 +500 val perplexity 2307.4766 +500 train 7.677109 (lr=9.9135e-05) (hash(x)=22051933) +501 train 7.815614 (lr=9.9130e-05) (hash(x)=24232348) +502 train 7.816216 (lr=9.9124e-05) (hash(x)=23158331) +503 train 7.634670 (lr=9.9118e-05) (hash(x)=22652243) +504 train 7.704566 (lr=9.9112e-05) (hash(x)=23805602) +505 train 7.972635 (lr=9.9106e-05) (hash(x)=25411991) +506 train 7.238259 (lr=9.9101e-05) (hash(x)=18827215) +507 train 6.928096 (lr=9.9095e-05) (hash(x)=15446025) +508 train 7.300294 (lr=9.9089e-05) (hash(x)=20516263) +509 train 7.891028 (lr=9.9083e-05) (hash(x)=27846176) +510 train 7.605103 (lr=9.9077e-05) (hash(x)=23342449) +511 train 7.825378 (lr=9.9071e-05) (hash(x)=27194521) +512 train 7.621549 (lr=9.9065e-05) (hash(x)=23008284) +513 train 8.063850 (lr=9.9059e-05) (hash(x)=29430001) +514 train 7.433350 (lr=9.9053e-05) (hash(x)=22579319) +515 train 7.477325 (lr=9.9047e-05) (hash(x)=25264518) +516 train 7.801746 (lr=9.9041e-05) (hash(x)=25359075) +517 train 7.756578 (lr=9.9035e-05) (hash(x)=25568956) +518 train 8.090651 (lr=9.9029e-05) (hash(x)=32004108) +519 train 7.712171 (lr=9.9023e-05) (hash(x)=24936836) +520 train 7.885605 (lr=9.9017e-05) (hash(x)=27263338) +521 train 7.875789 (lr=9.9011e-05) (hash(x)=27452099) +522 train 7.793939 (lr=9.9004e-05) (hash(x)=25965406) +523 train 7.973755 (lr=9.8998e-05) (hash(x)=28197282) +524 train 7.706869 (lr=9.8992e-05) (hash(x)=22466209) +525 train 7.742816 (lr=9.8986e-05) (hash(x)=22931889) +526 train 7.854855 (lr=9.8980e-05) (hash(x)=26903920) +527 train 7.732115 (lr=9.8973e-05) (hash(x)=24765578) +528 train 7.878274 (lr=9.8967e-05) (hash(x)=27811359) +529 train 7.660901 (lr=9.8961e-05) (hash(x)=25078649) +530 train 7.834573 (lr=9.8954e-05) (hash(x)=25572416) +531 train 7.918024 (lr=9.8948e-05) (hash(x)=27448185) +532 train 7.979871 (lr=9.8942e-05) (hash(x)=25923719) +533 train 7.779222 (lr=9.8935e-05) (hash(x)=24804856) +534 train 7.863863 (lr=9.8929e-05) (hash(x)=23207829) +535 train 7.782910 (lr=9.8923e-05) (hash(x)=23107416) +536 train 7.697355 (lr=9.8916e-05) (hash(x)=26739531) +537 train 7.684310 (lr=9.8910e-05) (hash(x)=24960796) +538 train 7.785207 (lr=9.8903e-05) (hash(x)=24667802) +539 train 7.895954 (lr=9.8897e-05) (hash(x)=26755138) +540 train 7.775555 (lr=9.8890e-05) (hash(x)=25537132) +541 train 7.689426 (lr=9.8884e-05) (hash(x)=24542526) +542 train 7.499730 (lr=9.8877e-05) (hash(x)=21296355) +543 train 8.013835 (lr=9.8871e-05) (hash(x)=29314255) +544 train 7.742314 (lr=9.8864e-05) (hash(x)=26001799) +545 train 7.812541 (lr=9.8858e-05) (hash(x)=27347755) +546 train 7.773796 (lr=9.8851e-05) (hash(x)=25107798) +547 train 7.599113 (lr=9.8844e-05) (hash(x)=22112669) +548 train 7.606183 (lr=9.8838e-05) (hash(x)=21897967) +549 train 7.732434 (lr=9.8831e-05) (hash(x)=25161929) +550 val loss 7.7465 +550 val perplexity 2313.5173 +550 train 7.669617 (lr=9.8824e-05) (hash(x)=27465106) +551 train 7.749249 (lr=9.8818e-05) (hash(x)=24013079) +552 train 7.648317 (lr=9.8811e-05) (hash(x)=23142015) +553 train 7.757488 (lr=9.8804e-05) (hash(x)=26768629) +554 train 7.774316 (lr=9.8798e-05) (hash(x)=26393383) +555 train 7.534172 (lr=9.8791e-05) (hash(x)=22537194) +556 train 7.804461 (lr=9.8784e-05) (hash(x)=24046036) +557 train 7.748639 (lr=9.8777e-05) (hash(x)=24974360) +558 train 7.987827 (lr=9.8770e-05) (hash(x)=28379928) +559 train 7.752639 (lr=9.8764e-05) (hash(x)=25322001) +560 train 7.849225 (lr=9.8757e-05) (hash(x)=26622031) +561 train 7.523070 (lr=9.8750e-05) (hash(x)=20562247) +562 train 7.891835 (lr=9.8743e-05) (hash(x)=27381885) +563 train 8.043578 (lr=9.8736e-05) (hash(x)=27028126) +564 train 7.821640 (lr=9.8729e-05) (hash(x)=28882928) +565 train 7.781976 (lr=9.8722e-05) (hash(x)=25666355) +566 train 7.862701 (lr=9.8715e-05) (hash(x)=24330810) +567 train 7.814674 (lr=9.8708e-05) (hash(x)=26690440) +568 train 7.674043 (lr=9.8701e-05) (hash(x)=22923592) +569 train 7.810895 (lr=9.8694e-05) (hash(x)=27348418) +570 train 7.865865 (lr=9.8687e-05) (hash(x)=28849848) +571 train 7.895148 (lr=9.8680e-05) (hash(x)=26967331) +572 train 7.615647 (lr=9.8673e-05) (hash(x)=22831467) +573 train 7.729290 (lr=9.8666e-05) (hash(x)=24765121) +574 train 7.705600 (lr=9.8659e-05) (hash(x)=24331857) +575 train 7.547235 (lr=9.8651e-05) (hash(x)=22598512) +576 train 7.699470 (lr=9.8644e-05) (hash(x)=25149353) +577 train 7.580893 (lr=9.8637e-05) (hash(x)=23725598) +578 train 7.820389 (lr=9.8630e-05) (hash(x)=26449557) +579 train 7.848804 (lr=9.8623e-05) (hash(x)=24697985) +580 train 7.844222 (lr=9.8615e-05) (hash(x)=26923059) +581 train 7.687314 (lr=9.8608e-05) (hash(x)=25201962) +582 train 7.318205 (lr=9.8601e-05) (hash(x)=20931520) +583 train 7.381827 (lr=9.8594e-05) (hash(x)=18473911) +584 train 7.525074 (lr=9.8586e-05) (hash(x)=21306267) +585 train 7.809242 (lr=9.8579e-05) (hash(x)=25982840) +586 train 7.688092 (lr=9.8572e-05) (hash(x)=25364874) +587 train 7.591451 (lr=9.8564e-05) (hash(x)=23172124) +588 train 7.884545 (lr=9.8557e-05) (hash(x)=27876897) +589 train 8.499048 (lr=9.8549e-05) (hash(x)=34646114) +590 train 8.835678 (lr=9.8542e-05) (hash(x)=35153576) +591 train 7.694362 (lr=9.8535e-05) (hash(x)=22322442) +592 train 7.918718 (lr=9.8527e-05) (hash(x)=27907331) +593 train 7.863945 (lr=9.8520e-05) (hash(x)=26211794) +594 train 8.086212 (lr=9.8512e-05) (hash(x)=29291512) +595 train 8.276333 (lr=9.8505e-05) (hash(x)=29659121) +596 train 8.060725 (lr=9.8497e-05) (hash(x)=29674399) +597 train 7.773380 (lr=9.8489e-05) (hash(x)=23538306) +598 train 7.872892 (lr=9.8482e-05) (hash(x)=21991524) +599 train 7.770621 (lr=9.8474e-05) (hash(x)=26324153) +600 val loss 7.7475 +600 val perplexity 2315.8496 +600 train 7.752910 (lr=9.8467e-05) (hash(x)=23712082) +601 train 7.768864 (lr=9.8459e-05) (hash(x)=24910403) +602 train 7.743946 (lr=9.8451e-05) (hash(x)=26737205) +603 train 7.868119 (lr=9.8444e-05) (hash(x)=26939970) +604 train 7.757974 (lr=9.8436e-05) (hash(x)=27651943) +605 train 8.078232 (lr=9.8428e-05) (hash(x)=27515446) +606 train 7.961208 (lr=9.8421e-05) (hash(x)=26753129) +607 train 7.622949 (lr=9.8413e-05) (hash(x)=23446058) +608 train 7.894987 (lr=9.8405e-05) (hash(x)=27587849) +609 train 7.801679 (lr=9.8397e-05) (hash(x)=25308253) +610 train 7.841344 (lr=9.8390e-05) (hash(x)=26615098) +611 train 7.917737 (lr=9.8382e-05) (hash(x)=29981801) +612 train 7.965541 (lr=9.8374e-05) (hash(x)=29592345) +613 train 8.007228 (lr=9.8366e-05) (hash(x)=23470413) +614 train 7.875785 (lr=9.8358e-05) (hash(x)=24742370) +615 train 7.881253 (lr=9.8350e-05) (hash(x)=24843741) +616 train 7.787037 (lr=9.8342e-05) (hash(x)=25192548) +617 train 7.870148 (lr=9.8334e-05) (hash(x)=27176996) +618 train 7.697362 (lr=9.8326e-05) (hash(x)=23964552) +619 train 7.713278 (lr=9.8318e-05) (hash(x)=22855363) +620 train 7.724720 (lr=9.8310e-05) (hash(x)=26332996) +621 train 7.539825 (lr=9.8302e-05) (hash(x)=22960957) +622 train 7.839091 (lr=9.8294e-05) (hash(x)=22752597) +623 train 7.740685 (lr=9.8286e-05) (hash(x)=23197102) +624 train 8.179171 (lr=9.8278e-05) (hash(x)=27383319) +625 train 7.787714 (lr=9.8270e-05) (hash(x)=26132276) +626 train 7.643514 (lr=9.8262e-05) (hash(x)=19810497) +627 train 7.713253 (lr=9.8254e-05) (hash(x)=25704919) +628 train 7.858028 (lr=9.8246e-05) (hash(x)=27174264) +629 train 7.971109 (lr=9.8238e-05) (hash(x)=22280814) +630 train 8.719095 (lr=9.8230e-05) (hash(x)=24279448) +631 train 8.171974 (lr=9.8221e-05) (hash(x)=23054940) +632 train 8.280000 (lr=9.8213e-05) (hash(x)=23942400) +633 train 8.539346 (lr=9.8205e-05) (hash(x)=24712416) +634 train 8.115908 (lr=9.8197e-05) (hash(x)=24564658) +635 train 7.842930 (lr=9.8188e-05) (hash(x)=24909904) +636 train 7.851747 (lr=9.8180e-05) (hash(x)=23049534) +637 train 7.904913 (lr=9.8172e-05) (hash(x)=24321591) +638 train 7.740619 (lr=9.8164e-05) (hash(x)=26153298) +639 train 7.770329 (lr=9.8155e-05) (hash(x)=27140757) +640 train 7.564924 (lr=9.8147e-05) (hash(x)=25115907) +641 train 7.640377 (lr=9.8139e-05) (hash(x)=26563770) +642 train 7.780909 (lr=9.8130e-05) (hash(x)=28089252) +643 train 7.720172 (lr=9.8122e-05) (hash(x)=25993110) +644 train 7.693466 (lr=9.8113e-05) (hash(x)=25150008) +645 train 7.861884 (lr=9.8105e-05) (hash(x)=28520222) +646 train 7.528358 (lr=9.8096e-05) (hash(x)=21349943) +647 train 7.619948 (lr=9.8088e-05) (hash(x)=25149419) +648 train 7.810609 (lr=9.8079e-05) (hash(x)=25730641) +649 train 7.962170 (lr=9.8071e-05) (hash(x)=26112813) +650 val loss 7.7242 +650 val perplexity 2262.3972 +650 train 7.786140 (lr=9.8062e-05) (hash(x)=25907805) +651 train 7.814849 (lr=9.8054e-05) (hash(x)=27623643) +652 train 7.775393 (lr=9.8045e-05) (hash(x)=26484959) +653 train 7.854787 (lr=9.8037e-05) (hash(x)=29199854) +654 train 7.854855 (lr=9.8028e-05) (hash(x)=28369628) +655 train 7.668689 (lr=9.8019e-05) (hash(x)=24727764) +656 train 7.367423 (lr=9.8011e-05) (hash(x)=22610673) +657 train 7.309201 (lr=9.8002e-05) (hash(x)=22667179) +658 train 7.097827 (lr=9.7993e-05) (hash(x)=18477300) +659 train 7.557555 (lr=9.7985e-05) (hash(x)=23155773) +660 train 7.344257 (lr=9.7976e-05) (hash(x)=19461032) +661 train 7.637123 (lr=9.7967e-05) (hash(x)=23453788) +662 train 7.734077 (lr=9.7958e-05) (hash(x)=24543466) +663 train 7.543086 (lr=9.7950e-05) (hash(x)=21935931) +664 train 7.389060 (lr=9.7941e-05) (hash(x)=19910292) +665 train 7.645732 (lr=9.7932e-05) (hash(x)=24481079) +666 train 7.348190 (lr=9.7923e-05) (hash(x)=18922411) +667 train 7.388016 (lr=9.7914e-05) (hash(x)=20054917) +668 train 7.618326 (lr=9.7905e-05) (hash(x)=24850470) +669 train 7.664933 (lr=9.7897e-05) (hash(x)=25907741) +670 train 7.813211 (lr=9.7888e-05) (hash(x)=26873522) +671 train 7.835485 (lr=9.7879e-05) (hash(x)=27606073) +672 train 7.953900 (lr=9.7870e-05) (hash(x)=26209645) +673 train 7.783077 (lr=9.7861e-05) (hash(x)=25202001) +674 train 7.842935 (lr=9.7852e-05) (hash(x)=25569462) +675 train 7.827940 (lr=9.7843e-05) (hash(x)=26534487) +676 train 7.765630 (lr=9.7834e-05) (hash(x)=26455057) +677 train 7.656991 (lr=9.7825e-05) (hash(x)=24095850) +678 train 7.911496 (lr=9.7816e-05) (hash(x)=25287752) +679 train 7.372158 (lr=9.7807e-05) (hash(x)=22450341) +680 train 8.124528 (lr=9.7798e-05) (hash(x)=29004853) +681 train 7.825069 (lr=9.7788e-05) (hash(x)=27993763) +682 train 7.666725 (lr=9.7779e-05) (hash(x)=26382658) +683 train 7.781044 (lr=9.7770e-05) (hash(x)=25013073) +684 train 7.853429 (lr=9.7761e-05) (hash(x)=30595809) +685 train 7.930470 (lr=9.7752e-05) (hash(x)=30934371) +686 train 8.451807 (lr=9.7743e-05) (hash(x)=33060834) +687 train 7.787563 (lr=9.7733e-05) (hash(x)=25945859) +688 train 7.632839 (lr=9.7724e-05) (hash(x)=23375678) +689 train 7.683624 (lr=9.7715e-05) (hash(x)=25218689) +690 train 7.779258 (lr=9.7706e-05) (hash(x)=28127397) +691 train 7.713147 (lr=9.7696e-05) (hash(x)=24418091) +692 train 7.582967 (lr=9.7687e-05) (hash(x)=22761099) +693 train 7.644634 (lr=9.7678e-05) (hash(x)=24615466) +694 train 7.764627 (lr=9.7668e-05) (hash(x)=24699240) +695 train 7.668275 (lr=9.7659e-05) (hash(x)=21613707) +696 train 7.717183 (lr=9.7650e-05) (hash(x)=24977554) +697 train 7.635185 (lr=9.7640e-05) (hash(x)=24348175) +698 train 7.802435 (lr=9.7631e-05) (hash(x)=25102767) +699 train 7.774536 (lr=9.7621e-05) (hash(x)=26386157) +700 val loss 7.6797 +700 val perplexity 2164.0281 +700 train 7.701099 (lr=9.7612e-05) (hash(x)=26423460) +701 train 7.654764 (lr=9.7602e-05) (hash(x)=25771047) +702 train 7.758335 (lr=9.7593e-05) (hash(x)=26999875) +703 train 7.634614 (lr=9.7583e-05) (hash(x)=24396519) +704 train 7.683030 (lr=9.7574e-05) (hash(x)=22588122) +705 train 7.985619 (lr=9.7564e-05) (hash(x)=25142399) +706 train 7.699346 (lr=9.7555e-05) (hash(x)=20440214) +707 train 7.552512 (lr=9.7545e-05) (hash(x)=23265507) +708 train 7.679708 (lr=9.7536e-05) (hash(x)=24563470) +709 train 7.558553 (lr=9.7526e-05) (hash(x)=22514858) +710 train 7.898207 (lr=9.7516e-05) (hash(x)=26691212) +711 train 7.987007 (lr=9.7507e-05) (hash(x)=29138828) +712 train 7.947612 (lr=9.7497e-05) (hash(x)=28028528) +713 train 7.786697 (lr=9.7487e-05) (hash(x)=20531210) +714 train 7.635825 (lr=9.7478e-05) (hash(x)=25075352) +715 train 7.766264 (lr=9.7468e-05) (hash(x)=24265353) +716 train 7.839868 (lr=9.7458e-05) (hash(x)=24635726) +717 train 7.688402 (lr=9.7448e-05) (hash(x)=24999726) +718 train 7.880919 (lr=9.7438e-05) (hash(x)=27412910) +719 train 7.658783 (lr=9.7429e-05) (hash(x)=24685515) +720 train 7.746465 (lr=9.7419e-05) (hash(x)=23780329) +721 train 7.534795 (lr=9.7409e-05) (hash(x)=25071701) +722 train 7.678514 (lr=9.7399e-05) (hash(x)=23767130) +723 train 7.667732 (lr=9.7389e-05) (hash(x)=24876269) +724 train 7.767432 (lr=9.7379e-05) (hash(x)=26405773) +725 train 8.159888 (lr=9.7369e-05) (hash(x)=31733180) +726 train 7.383862 (lr=9.7360e-05) (hash(x)=21337509) +727 train 7.523326 (lr=9.7350e-05) (hash(x)=22825749) +728 train 7.857671 (lr=9.7340e-05) (hash(x)=28638695) +729 train 7.702179 (lr=9.7330e-05) (hash(x)=26393943) +730 train 7.910509 (lr=9.7320e-05) (hash(x)=27563583) +731 train 7.397211 (lr=9.7310e-05) (hash(x)=21239652) +732 train 7.532898 (lr=9.7300e-05) (hash(x)=23986428) +733 train 7.513837 (lr=9.7290e-05) (hash(x)=24943881) +734 train 8.011764 (lr=9.7279e-05) (hash(x)=29691448) +735 train 7.968709 (lr=9.7269e-05) (hash(x)=28767869) +736 train 7.674783 (lr=9.7259e-05) (hash(x)=23628188) +737 train 7.946720 (lr=9.7249e-05) (hash(x)=29341482) +738 train 7.843012 (lr=9.7239e-05) (hash(x)=30336570) +739 train 7.816359 (lr=9.7229e-05) (hash(x)=25614301) +740 train 7.649014 (lr=9.7219e-05) (hash(x)=24160500) +741 train 7.866886 (lr=9.7208e-05) (hash(x)=26030058) +742 train 8.170291 (lr=9.7198e-05) (hash(x)=29243936) +743 train 7.524190 (lr=9.7188e-05) (hash(x)=21159060) +744 train 7.589813 (lr=9.7178e-05) (hash(x)=23701853) +745 train 7.719594 (lr=9.7167e-05) (hash(x)=24629937) +746 train 7.667924 (lr=9.7157e-05) (hash(x)=25110108) +747 train 7.716519 (lr=9.7147e-05) (hash(x)=26751788) +748 train 7.772907 (lr=9.7136e-05) (hash(x)=26430427) +749 train 7.615331 (lr=9.7126e-05) (hash(x)=26012353) +750 val loss 7.6588 +750 val perplexity 2119.2505 +750 train 7.772005 (lr=9.7116e-05) (hash(x)=22735910) +751 train 7.566054 (lr=9.7105e-05) (hash(x)=25045397) +752 train 7.290556 (lr=9.7095e-05) (hash(x)=21554427) +753 train 7.454259 (lr=9.7085e-05) (hash(x)=23751143) +754 train 8.180555 (lr=9.7074e-05) (hash(x)=28602273) +755 train 8.192451 (lr=9.7064e-05) (hash(x)=29989709) +756 train 7.589859 (lr=9.7053e-05) (hash(x)=22331648) +757 train 8.037612 (lr=9.7043e-05) (hash(x)=31017246) +758 train 7.960075 (lr=9.7032e-05) (hash(x)=29709045) +759 train 8.006764 (lr=9.7022e-05) (hash(x)=25560928) +760 train 7.708201 (lr=9.7011e-05) (hash(x)=25075464) +761 train 7.762511 (lr=9.7001e-05) (hash(x)=27352253) +762 train 7.993021 (lr=9.6990e-05) (hash(x)=28187891) +763 train 7.836254 (lr=9.6979e-05) (hash(x)=26062687) +764 train 7.855246 (lr=9.6969e-05) (hash(x)=27427811) +765 train 7.886703 (lr=9.6958e-05) (hash(x)=27614522) +766 train 7.673180 (lr=9.6947e-05) (hash(x)=26129544) +767 train 8.264147 (lr=9.6937e-05) (hash(x)=28959222) +768 train 7.751735 (lr=9.6926e-05) (hash(x)=26860067) +769 train 7.560666 (lr=9.6915e-05) (hash(x)=25122598) +770 train 7.655239 (lr=9.6905e-05) (hash(x)=25245030) +771 train 7.689519 (lr=9.6894e-05) (hash(x)=25434884) +772 train 7.712990 (lr=9.6883e-05) (hash(x)=27732790) +773 train 7.772213 (lr=9.6872e-05) (hash(x)=27824438) +774 train 7.822304 (lr=9.6862e-05) (hash(x)=27201953) +775 train 7.555831 (lr=9.6851e-05) (hash(x)=21248405) +776 train 7.396427 (lr=9.6840e-05) (hash(x)=22805934) +777 train 7.733068 (lr=9.6829e-05) (hash(x)=26482588) +778 train 7.766984 (lr=9.6818e-05) (hash(x)=24153691) +779 train 7.938623 (lr=9.6807e-05) (hash(x)=25044192) +780 train 7.826402 (lr=9.6796e-05) (hash(x)=25910078) +781 train 7.797885 (lr=9.6786e-05) (hash(x)=28645524) +782 train 7.609600 (lr=9.6775e-05) (hash(x)=24368498) +783 train 7.685874 (lr=9.6764e-05) (hash(x)=25830182) +784 train 7.807868 (lr=9.6753e-05) (hash(x)=29181807) +785 train 7.729765 (lr=9.6742e-05) (hash(x)=25585137) +786 train 7.652174 (lr=9.6731e-05) (hash(x)=24798246) +787 train 7.764668 (lr=9.6720e-05) (hash(x)=26621419) +788 train 7.328049 (lr=9.6709e-05) (hash(x)=21446891) +789 train 7.283100 (lr=9.6697e-05) (hash(x)=22165286) +790 train 7.500456 (lr=9.6686e-05) (hash(x)=23477219) +791 train 7.771136 (lr=9.6675e-05) (hash(x)=25173113) +792 train 7.639176 (lr=9.6664e-05) (hash(x)=25853788) +793 train 7.727561 (lr=9.6653e-05) (hash(x)=27267091) +794 train 7.575316 (lr=9.6642e-05) (hash(x)=23743694) +795 train 7.552075 (lr=9.6631e-05) (hash(x)=24400133) +796 train 7.680225 (lr=9.6620e-05) (hash(x)=23663639) +797 train 7.545484 (lr=9.6608e-05) (hash(x)=23103223) +798 train 8.059119 (lr=9.6597e-05) (hash(x)=28748411) +799 train 7.274641 (lr=9.6586e-05) (hash(x)=23486277) +800 val loss 7.6456 +800 val perplexity 2091.5034 +800 train 7.609250 (lr=9.6575e-05) (hash(x)=25678518) +801 train 7.571640 (lr=9.6563e-05) (hash(x)=23421286) +802 train 7.720001 (lr=9.6552e-05) (hash(x)=26054104) +803 train 7.716413 (lr=9.6541e-05) (hash(x)=25978130) +804 train 7.740596 (lr=9.6529e-05) (hash(x)=26006525) +805 train 7.696387 (lr=9.6518e-05) (hash(x)=25769432) +806 train 7.522447 (lr=9.6507e-05) (hash(x)=22430795) +807 train 7.884042 (lr=9.6495e-05) (hash(x)=28916006) +808 train 7.721826 (lr=9.6484e-05) (hash(x)=25166800) +809 train 7.847145 (lr=9.6472e-05) (hash(x)=24226056) +810 train 7.690549 (lr=9.6461e-05) (hash(x)=25057934) +811 train 8.458320 (lr=9.6450e-05) (hash(x)=33195100) +812 train 7.837795 (lr=9.6438e-05) (hash(x)=26312888) +813 train 8.003098 (lr=9.6427e-05) (hash(x)=27730410) +814 train 7.868997 (lr=9.6415e-05) (hash(x)=27372474) +815 train 7.655834 (lr=9.6404e-05) (hash(x)=25556929) +816 train 7.774901 (lr=9.6392e-05) (hash(x)=26909985) +817 train 7.579738 (lr=9.6380e-05) (hash(x)=25991247) +818 train 7.775042 (lr=9.6369e-05) (hash(x)=27438141) +819 train 7.900272 (lr=9.6357e-05) (hash(x)=29536986) +820 train 7.645302 (lr=9.6346e-05) (hash(x)=24478391) +821 train 7.666008 (lr=9.6334e-05) (hash(x)=26125216) +822 train 7.731503 (lr=9.6322e-05) (hash(x)=26422130) +823 train 7.828330 (lr=9.6311e-05) (hash(x)=29648798) +824 train 7.577850 (lr=9.6299e-05) (hash(x)=21247770) +825 train 7.709621 (lr=9.6287e-05) (hash(x)=23195388) +826 train 7.662941 (lr=9.6276e-05) (hash(x)=25796725) +827 train 7.664857 (lr=9.6264e-05) (hash(x)=23124767) +828 train 7.681262 (lr=9.6252e-05) (hash(x)=25233464) +829 train 7.674352 (lr=9.6240e-05) (hash(x)=25713275) +830 train 7.653254 (lr=9.6228e-05) (hash(x)=25550167) +831 train 7.569873 (lr=9.6217e-05) (hash(x)=24976217) +832 train 7.844654 (lr=9.6205e-05) (hash(x)=28536827) +833 train 7.726701 (lr=9.6193e-05) (hash(x)=27500801) +834 train 7.584366 (lr=9.6181e-05) (hash(x)=25545765) +835 train 7.603620 (lr=9.6169e-05) (hash(x)=23632825) +836 train 7.619943 (lr=9.6157e-05) (hash(x)=25708009) +837 train 7.632808 (lr=9.6145e-05) (hash(x)=24456276) +838 train 7.794542 (lr=9.6133e-05) (hash(x)=29189855) +839 train 7.996647 (lr=9.6122e-05) (hash(x)=31019606) +840 train 7.899827 (lr=9.6110e-05) (hash(x)=26328013) +841 train 7.832706 (lr=9.6098e-05) (hash(x)=25027904) +842 train 7.574049 (lr=9.6086e-05) (hash(x)=23734189) +843 train 7.811978 (lr=9.6074e-05) (hash(x)=28236580) +844 train 7.665820 (lr=9.6061e-05) (hash(x)=26509780) +845 train 7.705869 (lr=9.6049e-05) (hash(x)=25386473) +846 train 7.679700 (lr=9.6037e-05) (hash(x)=24052671) +847 train 7.835336 (lr=9.6025e-05) (hash(x)=28269421) +848 train 7.298905 (lr=9.6013e-05) (hash(x)=22251724) +849 train 7.523511 (lr=9.6001e-05) (hash(x)=24308447) +850 val loss 7.6262 +850 val perplexity 2051.2124 +850 train 7.482263 (lr=9.5989e-05) (hash(x)=24242830) +851 train 7.655927 (lr=9.5977e-05) (hash(x)=25563279) +852 train 7.708108 (lr=9.5965e-05) (hash(x)=26354481) +853 train 7.845835 (lr=9.5952e-05) (hash(x)=26152637) +854 train 7.848653 (lr=9.5940e-05) (hash(x)=28051025) +855 train 7.690929 (lr=9.5928e-05) (hash(x)=24865358) +856 train 7.586415 (lr=9.5916e-05) (hash(x)=24288911) +857 train 7.502471 (lr=9.5903e-05) (hash(x)=22230964) +858 train 7.386088 (lr=9.5891e-05) (hash(x)=21303832) +859 train 7.528646 (lr=9.5879e-05) (hash(x)=22155546) +860 train 7.626129 (lr=9.5866e-05) (hash(x)=25296428) +861 train 7.787820 (lr=9.5854e-05) (hash(x)=29142319) +862 train 7.613499 (lr=9.5842e-05) (hash(x)=25545430) +863 train 7.457430 (lr=9.5829e-05) (hash(x)=26984272) +864 train 7.643788 (lr=9.5817e-05) (hash(x)=25429005) +865 train 7.669521 (lr=9.5805e-05) (hash(x)=27077032) +866 train 7.697694 (lr=9.5792e-05) (hash(x)=26494424) +867 train 7.665582 (lr=9.5780e-05) (hash(x)=23193673) +868 train 7.729189 (lr=9.5767e-05) (hash(x)=25075134) +869 train 7.732307 (lr=9.5755e-05) (hash(x)=27112558) +870 train 7.855672 (lr=9.5742e-05) (hash(x)=27436608) +871 train 7.584032 (lr=9.5730e-05) (hash(x)=24544116) +872 train 7.944889 (lr=9.5717e-05) (hash(x)=31632686) +873 train 7.611336 (lr=9.5705e-05) (hash(x)=25890184) +874 train 7.730201 (lr=9.5692e-05) (hash(x)=22887555) +875 train 7.580858 (lr=9.5680e-05) (hash(x)=24547533) +876 train 7.727063 (lr=9.5667e-05) (hash(x)=26553496) +877 train 7.784742 (lr=9.5654e-05) (hash(x)=27467688) +878 train 7.585792 (lr=9.5642e-05) (hash(x)=24766934) +879 train 7.468731 (lr=9.5629e-05) (hash(x)=22059850) +880 train 7.850780 (lr=9.5616e-05) (hash(x)=22871702) +881 train 7.664211 (lr=9.5604e-05) (hash(x)=23893130) +882 train 7.715257 (lr=9.5591e-05) (hash(x)=25125691) +883 train 7.661165 (lr=9.5578e-05) (hash(x)=25994573) +884 train 7.656132 (lr=9.5565e-05) (hash(x)=26076345) +885 train 7.618903 (lr=9.5553e-05) (hash(x)=26577783) +886 train 7.740520 (lr=9.5540e-05) (hash(x)=27395225) +887 train 7.561760 (lr=9.5527e-05) (hash(x)=23926632) +888 train 7.400877 (lr=9.5514e-05) (hash(x)=21737239) +889 train 7.684419 (lr=9.5502e-05) (hash(x)=23574207) +890 train 7.376943 (lr=9.5489e-05) (hash(x)=24365231) +891 train 7.574795 (lr=9.5476e-05) (hash(x)=27111369) +892 train 7.828601 (lr=9.5463e-05) (hash(x)=27290015) +893 train 7.632066 (lr=9.5450e-05) (hash(x)=23979820) +894 train 7.720632 (lr=9.5437e-05) (hash(x)=26450121) +895 train 7.620336 (lr=9.5424e-05) (hash(x)=27025333) +896 train 7.663381 (lr=9.5411e-05) (hash(x)=23624605) +897 train 7.453915 (lr=9.5398e-05) (hash(x)=22846386) +898 train 7.556504 (lr=9.5385e-05) (hash(x)=22970561) +899 train 7.408277 (lr=9.5372e-05) (hash(x)=16908068) +900 val loss 7.6055 +900 val perplexity 2009.2234 +900 train 7.574020 (lr=9.5359e-05) (hash(x)=24661446) +901 train 7.678688 (lr=9.5346e-05) (hash(x)=25664727) +902 train 7.634378 (lr=9.5333e-05) (hash(x)=25667011) +903 train 7.687885 (lr=9.5320e-05) (hash(x)=29120407) +904 train 7.741706 (lr=9.5307e-05) (hash(x)=23385735) +905 train 7.771673 (lr=9.5294e-05) (hash(x)=25564213) +906 train 7.786844 (lr=9.5281e-05) (hash(x)=25413898) +907 train 7.752594 (lr=9.5268e-05) (hash(x)=27092710) +908 train 7.556826 (lr=9.5255e-05) (hash(x)=25789923) +909 train 7.637554 (lr=9.5241e-05) (hash(x)=28533197) +910 train 7.479904 (lr=9.5228e-05) (hash(x)=22982996) +911 train 7.609290 (lr=9.5215e-05) (hash(x)=23827393) +912 train 7.318192 (lr=9.5202e-05) (hash(x)=21242640) +913 train 7.659963 (lr=9.5188e-05) (hash(x)=24154233) +914 train 7.647649 (lr=9.5175e-05) (hash(x)=24331967) +915 train 7.871466 (lr=9.5162e-05) (hash(x)=32812727) +916 train 7.565320 (lr=9.5149e-05) (hash(x)=23572994) +917 train 7.571517 (lr=9.5135e-05) (hash(x)=26305435) +918 train 7.645743 (lr=9.5122e-05) (hash(x)=26268355) +919 train 7.803890 (lr=9.5109e-05) (hash(x)=27230027) +920 train 7.594276 (lr=9.5095e-05) (hash(x)=23885377) +921 train 7.531516 (lr=9.5082e-05) (hash(x)=23532437) +922 train 7.627121 (lr=9.5069e-05) (hash(x)=25577034) +923 train 7.746913 (lr=9.5055e-05) (hash(x)=25703381) +924 train 7.725035 (lr=9.5042e-05) (hash(x)=27113866) +925 train 7.556348 (lr=9.5028e-05) (hash(x)=26961429) +926 train 7.398965 (lr=9.5015e-05) (hash(x)=21355372) +927 train 7.479282 (lr=9.5001e-05) (hash(x)=24968260) +928 train 7.483374 (lr=9.4988e-05) (hash(x)=25357517) +929 train 7.628192 (lr=9.4974e-05) (hash(x)=24854265) +930 train 7.372659 (lr=9.4961e-05) (hash(x)=21102770) +931 train 7.712151 (lr=9.4947e-05) (hash(x)=25676468) +932 train 7.531806 (lr=9.4934e-05) (hash(x)=22809869) +933 train 7.588851 (lr=9.4920e-05) (hash(x)=25503865) +934 train 7.494019 (lr=9.4906e-05) (hash(x)=24853995) +935 train 7.718419 (lr=9.4893e-05) (hash(x)=27544803) +936 train 7.712807 (lr=9.4879e-05) (hash(x)=25981933) +937 train 7.483336 (lr=9.4866e-05) (hash(x)=24658683) +938 train 7.650724 (lr=9.4852e-05) (hash(x)=23855201) +939 train 7.579767 (lr=9.4838e-05) (hash(x)=24331407) +940 train 7.788236 (lr=9.4824e-05) (hash(x)=29265551) +941 train 7.502376 (lr=9.4811e-05) (hash(x)=21892556) +942 train 7.550581 (lr=9.4797e-05) (hash(x)=27183405) +943 train 7.505895 (lr=9.4783e-05) (hash(x)=26540663) +944 train 7.456562 (lr=9.4769e-05) (hash(x)=25718393) +945 train 7.631005 (lr=9.4756e-05) (hash(x)=26819462) +946 train 7.633646 (lr=9.4742e-05) (hash(x)=27427540) +947 train 7.579056 (lr=9.4728e-05) (hash(x)=25532657) +948 train 7.827742 (lr=9.4714e-05) (hash(x)=27641372) +949 train 7.502323 (lr=9.4700e-05) (hash(x)=26515570) +950 val loss 7.5794 +950 val perplexity 1957.4841 +950 train 7.792461 (lr=9.4686e-05) (hash(x)=26911957) +951 train 7.887889 (lr=9.4673e-05) (hash(x)=25856625) +952 train 7.441124 (lr=9.4659e-05) (hash(x)=25219129) +953 train 7.408433 (lr=9.4645e-05) (hash(x)=25260471) +954 train 7.801564 (lr=9.4631e-05) (hash(x)=29373370) +955 train 7.339977 (lr=9.4617e-05) (hash(x)=23437426) +956 train 7.702676 (lr=9.4603e-05) (hash(x)=23769521) +957 train 7.721569 (lr=9.4589e-05) (hash(x)=25961833) +958 train 7.444047 (lr=9.4575e-05) (hash(x)=23582666) +959 train 7.533696 (lr=9.4561e-05) (hash(x)=23164356) +960 train 7.467818 (lr=9.4547e-05) (hash(x)=24443114) +961 train 7.574922 (lr=9.4533e-05) (hash(x)=25052665) +962 train 7.680786 (lr=9.4519e-05) (hash(x)=27802272) +963 train 7.538483 (lr=9.4505e-05) (hash(x)=25957896) +964 train 7.565891 (lr=9.4490e-05) (hash(x)=26737251) +965 train 7.707680 (lr=9.4476e-05) (hash(x)=24723263) +966 train 7.648175 (lr=9.4462e-05) (hash(x)=24707011) +967 train 7.636089 (lr=9.4448e-05) (hash(x)=25646282) +968 train 7.638423 (lr=9.4434e-05) (hash(x)=27544665) +969 train 7.568131 (lr=9.4420e-05) (hash(x)=25851993) +970 train 7.853735 (lr=9.4405e-05) (hash(x)=29059700) +971 train 7.562181 (lr=9.4391e-05) (hash(x)=21513584) +972 train 7.302324 (lr=9.4377e-05) (hash(x)=23151267) +973 train 7.620585 (lr=9.4363e-05) (hash(x)=26017176) +974 train 7.660547 (lr=9.4348e-05) (hash(x)=26979518) +975 train 7.655492 (lr=9.4334e-05) (hash(x)=23843233) +976 train 7.796519 (lr=9.4320e-05) (hash(x)=24193010) +977 train 7.570941 (lr=9.4305e-05) (hash(x)=21476847) +978 train 7.428411 (lr=9.4291e-05) (hash(x)=21366504) +979 train 7.439783 (lr=9.4277e-05) (hash(x)=23226697) +980 train 7.188049 (lr=9.4262e-05) (hash(x)=19961773) +981 train 7.115675 (lr=9.4248e-05) (hash(x)=19772969) +982 train 7.443807 (lr=9.4234e-05) (hash(x)=23110142) +983 train 7.693380 (lr=9.4219e-05) (hash(x)=24506028) +984 train 7.688756 (lr=9.4205e-05) (hash(x)=25480731) +985 train 7.509168 (lr=9.4190e-05) (hash(x)=21077417) +986 train 7.505541 (lr=9.4176e-05) (hash(x)=23686713) +987 train 7.539226 (lr=9.4161e-05) (hash(x)=26024321) +988 train 7.621897 (lr=9.4147e-05) (hash(x)=27424109) +989 train 7.727331 (lr=9.4132e-05) (hash(x)=27786174) +990 train 7.605325 (lr=9.4118e-05) (hash(x)=25232502) +991 train 7.610675 (lr=9.4103e-05) (hash(x)=22781277) +992 train 7.701828 (lr=9.4088e-05) (hash(x)=26184527) +993 train 7.648715 (lr=9.4074e-05) (hash(x)=24459895) +994 train 7.577343 (lr=9.4059e-05) (hash(x)=25244624) +995 train 7.698280 (lr=9.4045e-05) (hash(x)=24451843) +996 train 7.717098 (lr=9.4030e-05) (hash(x)=22129897) +997 train 7.504028 (lr=9.4015e-05) (hash(x)=21116390) +998 train 7.328356 (lr=9.4001e-05) (hash(x)=20650070) +999 train 7.653084 (lr=9.3986e-05) (hash(x)=24948650) +1000 val loss 7.5607 +1000 val perplexity 1921.1880 +1000 train 7.558179 (lr=9.3971e-05) (hash(x)=25444553) +1001 train 7.525141 (lr=9.3956e-05) (hash(x)=25617781) +1002 train 7.430688 (lr=9.3942e-05) (hash(x)=23862434) +1003 train 7.454074 (lr=9.3927e-05) (hash(x)=25559534) +1004 train 7.690261 (lr=9.3912e-05) (hash(x)=26577585) +1005 train 7.552997 (lr=9.3897e-05) (hash(x)=25546274) +1006 train 7.576579 (lr=9.3882e-05) (hash(x)=26284202) +1007 train 7.627608 (lr=9.3868e-05) (hash(x)=26373991) +1008 train 7.527191 (lr=9.3853e-05) (hash(x)=24612851) +1009 train 7.610004 (lr=9.3838e-05) (hash(x)=26410662) +1010 train 7.659445 (lr=9.3823e-05) (hash(x)=23824841) +1011 train 7.955840 (lr=9.3808e-05) (hash(x)=27756673) +1012 train 7.674811 (lr=9.3793e-05) (hash(x)=25427447) +1013 train 7.698648 (lr=9.3778e-05) (hash(x)=23661686) +1014 train 7.592491 (lr=9.3763e-05) (hash(x)=25129504) +1015 train 7.553594 (lr=9.3748e-05) (hash(x)=23402396) +1016 train 7.780065 (lr=9.3733e-05) (hash(x)=26145557) +1017 train 7.523108 (lr=9.3718e-05) (hash(x)=26547918) +1018 train 7.652981 (lr=9.3703e-05) (hash(x)=26653070) +1019 train 7.645828 (lr=9.3688e-05) (hash(x)=28250354) +1020 train 7.612958 (lr=9.3673e-05) (hash(x)=25437401) +1021 train 7.677971 (lr=9.3658e-05) (hash(x)=25598861) +1022 train 7.505057 (lr=9.3643e-05) (hash(x)=24572587) +1023 train 7.489716 (lr=9.3628e-05) (hash(x)=21562133) +1024 train 7.920770 (lr=9.3613e-05) (hash(x)=27718876) +1025 train 7.505865 (lr=9.3598e-05) (hash(x)=25312391) +1026 train 7.596338 (lr=9.3583e-05) (hash(x)=26579535) +1027 train 7.836936 (lr=9.3567e-05) (hash(x)=27253861) +1028 train 7.719052 (lr=9.3552e-05) (hash(x)=28451867) +1029 train 7.470731 (lr=9.3537e-05) (hash(x)=26795921) +1030 train 7.602629 (lr=9.3522e-05) (hash(x)=26147208) +1031 train 7.629373 (lr=9.3507e-05) (hash(x)=25009210) +1032 train 7.559729 (lr=9.3491e-05) (hash(x)=25213771) +1033 train 7.506413 (lr=9.3476e-05) (hash(x)=26254538) +1034 train 7.553938 (lr=9.3461e-05) (hash(x)=25565614) +1035 train 7.360831 (lr=9.3446e-05) (hash(x)=23052577) +1036 train 8.122029 (lr=9.3430e-05) (hash(x)=29630613) +1037 train 7.402580 (lr=9.3415e-05) (hash(x)=23667224) +1038 train 7.552306 (lr=9.3400e-05) (hash(x)=25740670) +1039 train 7.635067 (lr=9.3384e-05) (hash(x)=27161811) +1040 train 7.766672 (lr=9.3369e-05) (hash(x)=26385663) +1041 train 7.385004 (lr=9.3353e-05) (hash(x)=26313522) +1042 train 7.488634 (lr=9.3338e-05) (hash(x)=26814686) +1043 train 7.685110 (lr=9.3323e-05) (hash(x)=27302459) +1044 train 7.987646 (lr=9.3307e-05) (hash(x)=26758132) +1045 train 7.615773 (lr=9.3292e-05) (hash(x)=26837963) +1046 train 7.409013 (lr=9.3276e-05) (hash(x)=22089547) +1047 train 7.860301 (lr=9.3261e-05) (hash(x)=29515100) +1048 train 7.614453 (lr=9.3245e-05) (hash(x)=25471442) +1049 train 7.553246 (lr=9.3230e-05) (hash(x)=26674478) +1050 val loss 7.5707 +1050 val perplexity 1940.4790 +1050 train 7.529601 (lr=9.3214e-05) (hash(x)=25373386) +1051 train 7.556325 (lr=9.3199e-05) (hash(x)=25318001) +1052 train 7.702899 (lr=9.3183e-05) (hash(x)=27255021) +1053 train 7.632065 (lr=9.3167e-05) (hash(x)=25174043) +1054 train 7.384738 (lr=9.3152e-05) (hash(x)=23857597) +1055 train 7.657314 (lr=9.3136e-05) (hash(x)=25305929) +1056 train 7.686002 (lr=9.3120e-05) (hash(x)=27009246) +1057 train 7.716791 (lr=9.3105e-05) (hash(x)=26175477) +1058 train 7.385377 (lr=9.3089e-05) (hash(x)=22700025) +1059 train 7.503308 (lr=9.3073e-05) (hash(x)=24339043) +1060 train 7.343609 (lr=9.3058e-05) (hash(x)=22139900) +1061 train 8.184896 (lr=9.3042e-05) (hash(x)=25412772) +1062 train 7.623433 (lr=9.3026e-05) (hash(x)=27020849) +1063 train 7.515852 (lr=9.3011e-05) (hash(x)=26808543) +1064 train 7.315138 (lr=9.2995e-05) (hash(x)=23061527) +1065 train 7.549204 (lr=9.2979e-05) (hash(x)=24738650) +1066 train 7.385074 (lr=9.2963e-05) (hash(x)=24036715) +1067 train 7.441844 (lr=9.2947e-05) (hash(x)=25763991) +1068 train 7.703162 (lr=9.2932e-05) (hash(x)=27393753) +1069 train 7.795969 (lr=9.2916e-05) (hash(x)=28182190) +1070 train 7.465557 (lr=9.2900e-05) (hash(x)=23358569) +1071 train 7.646346 (lr=9.2884e-05) (hash(x)=25669509) +1072 train 7.731937 (lr=9.2868e-05) (hash(x)=29139024) +1073 train 7.675262 (lr=9.2852e-05) (hash(x)=25616522) +1074 train 7.494331 (lr=9.2836e-05) (hash(x)=25695789) +1075 train 7.713814 (lr=9.2820e-05) (hash(x)=27676869) +1076 train 7.592940 (lr=9.2804e-05) (hash(x)=25952695) +1077 train 7.608580 (lr=9.2788e-05) (hash(x)=26316170) +1078 train 7.497690 (lr=9.2772e-05) (hash(x)=24081867) +1079 train 7.651706 (lr=9.2756e-05) (hash(x)=28435805) +1080 train 7.570873 (lr=9.2740e-05) (hash(x)=23375063) +1081 train 7.603826 (lr=9.2724e-05) (hash(x)=26869022) +1082 train 7.479872 (lr=9.2708e-05) (hash(x)=25793007) +1083 train 7.406568 (lr=9.2692e-05) (hash(x)=23455211) +1084 train 7.453598 (lr=9.2676e-05) (hash(x)=20441501) +1085 train 7.830307 (lr=9.2660e-05) (hash(x)=29321187) +1086 train 7.993745 (lr=9.2644e-05) (hash(x)=32627505) +1087 train 7.461217 (lr=9.2627e-05) (hash(x)=26482758) +1088 train 7.327737 (lr=9.2611e-05) (hash(x)=21431511) +1089 train 7.564361 (lr=9.2595e-05) (hash(x)=26046639) +1090 train 7.657875 (lr=9.2579e-05) (hash(x)=27464841) +1091 train 7.519824 (lr=9.2563e-05) (hash(x)=27068280) +1092 train 7.400468 (lr=9.2547e-05) (hash(x)=23119133) +1093 train 7.607563 (lr=9.2530e-05) (hash(x)=26782091) +1094 train 7.616701 (lr=9.2514e-05) (hash(x)=26265326) +1095 train 7.610729 (lr=9.2498e-05) (hash(x)=24929929) +1096 train 7.527037 (lr=9.2481e-05) (hash(x)=23158628) +1097 train 7.572069 (lr=9.2465e-05) (hash(x)=25950541) +1098 train 7.394171 (lr=9.2449e-05) (hash(x)=22093912) +1099 train 7.557044 (lr=9.2432e-05) (hash(x)=25373676) +1100 val loss 7.5238 +1100 val perplexity 1851.5244 +1100 train 7.295323 (lr=9.2416e-05) (hash(x)=18986670) +1101 train 7.778243 (lr=9.2400e-05) (hash(x)=27283187) +1102 train 7.521855 (lr=9.2383e-05) (hash(x)=25474743) +1103 train 7.390871 (lr=9.2367e-05) (hash(x)=25043037) +1104 train 7.344062 (lr=9.2351e-05) (hash(x)=23156261) +1105 train 7.780495 (lr=9.2334e-05) (hash(x)=27027534) +1106 train 7.377420 (lr=9.2318e-05) (hash(x)=22733630) +1107 train 7.636552 (lr=9.2301e-05) (hash(x)=27906976) +1108 train 7.584538 (lr=9.2285e-05) (hash(x)=27848655) +1109 train 7.509862 (lr=9.2268e-05) (hash(x)=23889709) +1110 train 8.494962 (lr=9.2252e-05) (hash(x)=33189918) +1111 train 8.062297 (lr=9.2235e-05) (hash(x)=29151257) +1112 train 7.769610 (lr=9.2219e-05) (hash(x)=23881512) +1113 train 7.499758 (lr=9.2202e-05) (hash(x)=21307974) +1114 train 7.536093 (lr=9.2185e-05) (hash(x)=25264524) +1115 train 7.679715 (lr=9.2169e-05) (hash(x)=26405613) +1116 train 7.352970 (lr=9.2152e-05) (hash(x)=21918678) +1117 train 7.410726 (lr=9.2136e-05) (hash(x)=24233887) +1118 train 7.068607 (lr=9.2119e-05) (hash(x)=19490509) +1119 train 7.651881 (lr=9.2102e-05) (hash(x)=26400365) +1120 train 7.844104 (lr=9.2086e-05) (hash(x)=28572086) +1121 train 7.361107 (lr=9.2069e-05) (hash(x)=22293114) +1122 train 7.495931 (lr=9.2052e-05) (hash(x)=26845479) +1123 train 7.370531 (lr=9.2036e-05) (hash(x)=23971905) +1124 train 7.587895 (lr=9.2019e-05) (hash(x)=25639959) +1125 train 7.215895 (lr=9.2002e-05) (hash(x)=20076502) +1126 train 7.565506 (lr=9.1985e-05) (hash(x)=25089255) +1127 train 7.475942 (lr=9.1969e-05) (hash(x)=24098812) +1128 train 7.489673 (lr=9.1952e-05) (hash(x)=23493707) +1129 train 7.716963 (lr=9.1935e-05) (hash(x)=27610410) +1130 train 7.496765 (lr=9.1918e-05) (hash(x)=24540186) +1131 train 7.726737 (lr=9.1901e-05) (hash(x)=29402976) +1132 train 7.389707 (lr=9.1884e-05) (hash(x)=23776025) +1133 train 7.175653 (lr=9.1867e-05) (hash(x)=19032564) +1134 train 7.696732 (lr=9.1851e-05) (hash(x)=26921117) +1135 train 7.296449 (lr=9.1834e-05) (hash(x)=20967666) +1136 train 7.354138 (lr=9.1817e-05) (hash(x)=23394540) +1137 train 7.362871 (lr=9.1800e-05) (hash(x)=22666342) +1138 train 7.500402 (lr=9.1783e-05) (hash(x)=23482498) +1139 train 7.580133 (lr=9.1766e-05) (hash(x)=24287610) +1140 train 7.658752 (lr=9.1749e-05) (hash(x)=24512831) +1141 train 7.904619 (lr=9.1732e-05) (hash(x)=28637634) +1142 train 8.107552 (lr=9.1715e-05) (hash(x)=24107127) +1143 train 7.782131 (lr=9.1698e-05) (hash(x)=28667963) +1144 train 7.648643 (lr=9.1681e-05) (hash(x)=26302492) +1145 train 7.655035 (lr=9.1664e-05) (hash(x)=23621685) +1146 train 7.392579 (lr=9.1647e-05) (hash(x)=23997414) +1147 train 7.506348 (lr=9.1629e-05) (hash(x)=25974316) +1148 train 7.469901 (lr=9.1612e-05) (hash(x)=23464988) +1149 train 7.536716 (lr=9.1595e-05) (hash(x)=24487710) +1150 val loss 7.5339 +1150 val perplexity 1870.3149 +1150 train 7.755232 (lr=9.1578e-05) (hash(x)=29610350) +1151 train 7.831023 (lr=9.1561e-05) (hash(x)=27083417) +1152 train 7.207921 (lr=9.1544e-05) (hash(x)=20666288) +1153 train 7.306133 (lr=9.1527e-05) (hash(x)=22850633) +1154 train 7.495575 (lr=9.1509e-05) (hash(x)=24741872) +1155 train 7.849510 (lr=9.1492e-05) (hash(x)=28605205) +1156 train 7.341031 (lr=9.1475e-05) (hash(x)=22624463) +1157 train 7.548891 (lr=9.1458e-05) (hash(x)=24786468) +1158 train 7.304167 (lr=9.1440e-05) (hash(x)=21365399) +1159 train 7.495845 (lr=9.1423e-05) (hash(x)=23649001) +1160 train 7.553916 (lr=9.1406e-05) (hash(x)=28203982) +1161 train 7.463458 (lr=9.1388e-05) (hash(x)=26473994) +1162 train 7.140790 (lr=9.1371e-05) (hash(x)=19476441) +1163 train 7.408739 (lr=9.1354e-05) (hash(x)=25921700) +1164 train 7.289115 (lr=9.1336e-05) (hash(x)=23064343) +1165 train 7.448032 (lr=9.1319e-05) (hash(x)=24117626) +1166 train 7.364417 (lr=9.1302e-05) (hash(x)=21764556) +1167 train 8.203400 (lr=9.1284e-05) (hash(x)=31338300) +1168 train 7.669779 (lr=9.1267e-05) (hash(x)=27443187) +1169 train 7.163606 (lr=9.1249e-05) (hash(x)=21337692) +1170 train 7.599271 (lr=9.1232e-05) (hash(x)=27845383) +1171 train 7.445019 (lr=9.1214e-05) (hash(x)=23862328) +1172 train 7.632945 (lr=9.1197e-05) (hash(x)=23811014) +1173 train 7.572186 (lr=9.1179e-05) (hash(x)=24380098) +1174 train 7.301361 (lr=9.1162e-05) (hash(x)=22351136) +1175 train 7.572604 (lr=9.1144e-05) (hash(x)=30603174) +1176 train 7.596747 (lr=9.1127e-05) (hash(x)=27924596) +1177 train 7.948407 (lr=9.1109e-05) (hash(x)=30882548) +1178 train 7.413599 (lr=9.1092e-05) (hash(x)=22339464) +1179 train 7.279783 (lr=9.1074e-05) (hash(x)=23603806) +1180 train 7.643811 (lr=9.1056e-05) (hash(x)=24809041) +1181 train 7.429119 (lr=9.1039e-05) (hash(x)=24382442) +1182 train 7.393371 (lr=9.1021e-05) (hash(x)=23134077) +1183 train 7.403084 (lr=9.1003e-05) (hash(x)=24830965) +1184 train 7.505212 (lr=9.0986e-05) (hash(x)=25527259) +1185 train 7.567395 (lr=9.0968e-05) (hash(x)=25547480) +1186 train 7.393365 (lr=9.0950e-05) (hash(x)=24424314) +1187 train 7.793381 (lr=9.0933e-05) (hash(x)=32488729) +1188 train 7.734123 (lr=9.0915e-05) (hash(x)=31168462) +1189 train 7.914559 (lr=9.0897e-05) (hash(x)=31331643) +1190 train 7.634789 (lr=9.0879e-05) (hash(x)=28746633) +1191 train 7.619796 (lr=9.0862e-05) (hash(x)=27269893) +1192 train 7.431469 (lr=9.0844e-05) (hash(x)=23484031) +1193 train 7.446782 (lr=9.0826e-05) (hash(x)=23278725) +1194 train 7.549463 (lr=9.0808e-05) (hash(x)=25440745) +1195 train 7.558908 (lr=9.0790e-05) (hash(x)=25215077) +1196 train 7.576012 (lr=9.0772e-05) (hash(x)=28309266) +1197 train 7.386093 (lr=9.0755e-05) (hash(x)=22442404) +1198 train 7.376715 (lr=9.0737e-05) (hash(x)=20775262) +1199 train 7.432323 (lr=9.0719e-05) (hash(x)=24825041) +1200 val loss 7.4984 +1200 val perplexity 1805.2202 +1200 train 7.620444 (lr=9.0701e-05) (hash(x)=29016896) +1201 train 7.548433 (lr=9.0683e-05) (hash(x)=25590276) +1202 train 7.427860 (lr=9.0665e-05) (hash(x)=22816384) +1203 train 7.564336 (lr=9.0647e-05) (hash(x)=25893804) +1204 train 7.448357 (lr=9.0629e-05) (hash(x)=23983816) +1205 train 7.334667 (lr=9.0611e-05) (hash(x)=22222468) +1206 train 7.421144 (lr=9.0593e-05) (hash(x)=23039141) +1207 train 7.322713 (lr=9.0575e-05) (hash(x)=22724871) +1208 train 7.376744 (lr=9.0557e-05) (hash(x)=25253062) +1209 train 7.372352 (lr=9.0539e-05) (hash(x)=25140744) +1210 train 7.461755 (lr=9.0521e-05) (hash(x)=24717218) +1211 train 7.542711 (lr=9.0503e-05) (hash(x)=27317554) +1212 train 7.213936 (lr=9.0485e-05) (hash(x)=22013236) +1213 train 7.771966 (lr=9.0467e-05) (hash(x)=26692343) +1214 train 7.323499 (lr=9.0448e-05) (hash(x)=19859225) +1215 train 7.243451 (lr=9.0430e-05) (hash(x)=24683717) +1216 train 7.315441 (lr=9.0412e-05) (hash(x)=21932013) +1217 train 7.529681 (lr=9.0394e-05) (hash(x)=26849303) +1218 train 7.612915 (lr=9.0376e-05) (hash(x)=26458000) +1219 train 7.394868 (lr=9.0357e-05) (hash(x)=21584083) +1220 train 7.742769 (lr=9.0339e-05) (hash(x)=23598625) +1221 train 7.476626 (lr=9.0321e-05) (hash(x)=26059939) +1222 train 7.717343 (lr=9.0303e-05) (hash(x)=25481982) +1223 train 7.575685 (lr=9.0284e-05) (hash(x)=26190337) +1224 train 7.767078 (lr=9.0266e-05) (hash(x)=28767755) +1225 train 7.426524 (lr=9.0248e-05) (hash(x)=23663918) +1226 train 7.559912 (lr=9.0230e-05) (hash(x)=21293227) +1227 train 7.548059 (lr=9.0211e-05) (hash(x)=22249019) +1228 train 7.628417 (lr=9.0193e-05) (hash(x)=26886529) +1229 train 7.461914 (lr=9.0175e-05) (hash(x)=25779849) +1230 train 7.545537 (lr=9.0156e-05) (hash(x)=26228964) +1231 train 7.483455 (lr=9.0138e-05) (hash(x)=23086289) +1232 train 7.613971 (lr=9.0119e-05) (hash(x)=23198922) +1233 train 7.573383 (lr=9.0101e-05) (hash(x)=27523941) +1234 train 7.387291 (lr=9.0083e-05) (hash(x)=24293992) +1235 train 8.129328 (lr=9.0064e-05) (hash(x)=28047044) +1236 train 7.593424 (lr=9.0046e-05) (hash(x)=23688671) +1237 train 7.416161 (lr=9.0027e-05) (hash(x)=25125498) +1238 train 7.339520 (lr=9.0009e-05) (hash(x)=21977292) +1239 train 7.431721 (lr=8.9990e-05) (hash(x)=23593875) +1240 train 7.388382 (lr=8.9972e-05) (hash(x)=22659030) +1241 train 7.462129 (lr=8.9953e-05) (hash(x)=25117733) +1242 train 7.428633 (lr=8.9934e-05) (hash(x)=22322808) +1243 train 7.477368 (lr=8.9916e-05) (hash(x)=26059735) +1244 train 7.409832 (lr=8.9897e-05) (hash(x)=22485526) +1245 train 7.334839 (lr=8.9879e-05) (hash(x)=23028679) +1246 train 7.344614 (lr=8.9860e-05) (hash(x)=22906035) +1247 train 7.275671 (lr=8.9841e-05) (hash(x)=22414190) +1248 train 7.541482 (lr=8.9823e-05) (hash(x)=26229624) +1249 train 7.326276 (lr=8.9804e-05) (hash(x)=22223137) +1250 val loss 7.4821 +1250 val perplexity 1775.9436 +1250 train 7.588226 (lr=8.9785e-05) (hash(x)=24911520) +1251 train 7.705436 (lr=8.9767e-05) (hash(x)=24204591) +1252 train 7.338848 (lr=8.9748e-05) (hash(x)=24379601) +1253 train 7.324895 (lr=8.9729e-05) (hash(x)=22922475) +1254 train 7.376085 (lr=8.9711e-05) (hash(x)=23426249) +1255 train 7.612946 (lr=8.9692e-05) (hash(x)=26758114) +1256 train 7.284721 (lr=8.9673e-05) (hash(x)=24027111) +1257 train 7.451291 (lr=8.9654e-05) (hash(x)=25358064) +1258 train 7.342072 (lr=8.9636e-05) (hash(x)=22571285) +1259 train 7.747643 (lr=8.9617e-05) (hash(x)=20084233) +1260 train 7.554463 (lr=8.9598e-05) (hash(x)=18786581) +1261 train 7.491148 (lr=8.9579e-05) (hash(x)=26395104) +1262 train 7.379024 (lr=8.9560e-05) (hash(x)=24212567) +1263 train 7.202823 (lr=8.9541e-05) (hash(x)=21563184) +1264 train 7.472843 (lr=8.9522e-05) (hash(x)=26490150) +1265 train 7.577176 (lr=8.9504e-05) (hash(x)=25207694) +1266 train 7.383245 (lr=8.9485e-05) (hash(x)=23914544) +1267 train 7.407594 (lr=8.9466e-05) (hash(x)=23861489) +1268 train 7.861157 (lr=8.9447e-05) (hash(x)=30714540) +1269 train 7.373550 (lr=8.9428e-05) (hash(x)=23471007) +1270 train 7.371806 (lr=8.9409e-05) (hash(x)=23244293) +1271 train 7.271282 (lr=8.9390e-05) (hash(x)=19218470) +1272 train 7.584294 (lr=8.9371e-05) (hash(x)=26965136) +1273 train 7.375560 (lr=8.9352e-05) (hash(x)=22944035) +1274 train 7.431174 (lr=8.9333e-05) (hash(x)=22002714) +1275 train 7.686217 (lr=8.9314e-05) (hash(x)=28469562) +1276 train 7.721536 (lr=8.9295e-05) (hash(x)=26889992) +1277 train 7.780008 (lr=8.9276e-05) (hash(x)=26452814) +1278 train 7.567596 (lr=8.9256e-05) (hash(x)=28397488) +1279 train 7.632340 (lr=8.9237e-05) (hash(x)=25588469) +1280 train 7.508586 (lr=8.9218e-05) (hash(x)=24833139) +1281 train 7.391318 (lr=8.9199e-05) (hash(x)=24788298) +1282 train 7.589585 (lr=8.9180e-05) (hash(x)=24979383) +1283 train 7.596637 (lr=8.9161e-05) (hash(x)=25236367) +1284 train 7.492453 (lr=8.9142e-05) (hash(x)=22638257) +1285 train 7.281238 (lr=8.9122e-05) (hash(x)=23069067) +1286 train 7.452467 (lr=8.9103e-05) (hash(x)=25133239) +1287 train 8.001796 (lr=8.9084e-05) (hash(x)=30433767) +1288 train 8.051967 (lr=8.9065e-05) (hash(x)=34319079) +1289 train 7.915737 (lr=8.9046e-05) (hash(x)=29268881) +1290 train 7.514818 (lr=8.9026e-05) (hash(x)=24528336) +1291 train 7.683116 (lr=8.9007e-05) (hash(x)=26302626) +1292 train 7.668601 (lr=8.8988e-05) (hash(x)=25479111) +1293 train 7.802569 (lr=8.8968e-05) (hash(x)=24749682) +1294 train 7.438343 (lr=8.8949e-05) (hash(x)=24111393) +1295 train 7.167775 (lr=8.8930e-05) (hash(x)=17851621) +1296 train 7.441631 (lr=8.8910e-05) (hash(x)=26463070) +1297 train 7.482723 (lr=8.8891e-05) (hash(x)=25620741) +1298 train 8.110367 (lr=8.8872e-05) (hash(x)=28225676) +1299 train 7.911397 (lr=8.8852e-05) (hash(x)=27028191) +1300 val loss 7.5004 +1300 val perplexity 1808.7538 +1300 train 7.562824 (lr=8.8833e-05) (hash(x)=29006516) +1301 train 7.687393 (lr=8.8813e-05) (hash(x)=27590299) +1302 train 7.826881 (lr=8.8794e-05) (hash(x)=28678983) +1303 train 7.674335 (lr=8.8774e-05) (hash(x)=25183690) +1304 train 7.198757 (lr=8.8755e-05) (hash(x)=19918097) +1305 train 8.005996 (lr=8.8736e-05) (hash(x)=31114252) +1306 train 7.990795 (lr=8.8716e-05) (hash(x)=30913255) +1307 train 7.541443 (lr=8.8697e-05) (hash(x)=26182243) +1308 train 7.764823 (lr=8.8677e-05) (hash(x)=27420668) +1309 train 8.004107 (lr=8.8657e-05) (hash(x)=30419908) +1310 train 7.873722 (lr=8.8638e-05) (hash(x)=29002281) +1311 train 7.589754 (lr=8.8618e-05) (hash(x)=27040642) +1312 train 7.477207 (lr=8.8599e-05) (hash(x)=26929300) +1313 train 7.566266 (lr=8.8579e-05) (hash(x)=26240761) +1314 train 7.601010 (lr=8.8560e-05) (hash(x)=27161876) +1315 train 7.423627 (lr=8.8540e-05) (hash(x)=24489607) +1316 train 7.828207 (lr=8.8520e-05) (hash(x)=27040115) +1317 train 7.493042 (lr=8.8501e-05) (hash(x)=25012872) +1318 train 7.171190 (lr=8.8481e-05) (hash(x)=20894720) +1319 train 7.266117 (lr=8.8461e-05) (hash(x)=22183303) +1320 train 7.525944 (lr=8.8442e-05) (hash(x)=26291778) +1321 train 7.609241 (lr=8.8422e-05) (hash(x)=27682633) +1322 train 7.377609 (lr=8.8402e-05) (hash(x)=26490892) +1323 train 7.830138 (lr=8.8382e-05) (hash(x)=28844646) +1324 train 8.159600 (lr=8.8363e-05) (hash(x)=29545304) +1325 train 8.253781 (lr=8.8343e-05) (hash(x)=31082070) +1326 train 7.850395 (lr=8.8323e-05) (hash(x)=27486316) +1327 train 7.810335 (lr=8.8303e-05) (hash(x)=27537063) +1328 train 7.633194 (lr=8.8283e-05) (hash(x)=26955557) +1329 train 7.652132 (lr=8.8264e-05) (hash(x)=26125988) +1330 train 7.638851 (lr=8.8244e-05) (hash(x)=22800125) +1331 train 7.768598 (lr=8.8224e-05) (hash(x)=25446686) +1332 train 7.864256 (lr=8.8204e-05) (hash(x)=28743746) +1333 train 7.626868 (lr=8.8184e-05) (hash(x)=19819857) +1334 train 7.347402 (lr=8.8164e-05) (hash(x)=23518628) +1335 train 7.284332 (lr=8.8144e-05) (hash(x)=19492832) +1336 train 7.518838 (lr=8.8124e-05) (hash(x)=24627720) +1337 train 7.391307 (lr=8.8104e-05) (hash(x)=23741214) +1338 train 7.477391 (lr=8.8084e-05) (hash(x)=25837914) +1339 train 7.392856 (lr=8.8064e-05) (hash(x)=25484958) +1340 train 7.363356 (lr=8.8045e-05) (hash(x)=23671284) +1341 train 7.497285 (lr=8.8025e-05) (hash(x)=25525370) +1342 train 7.573437 (lr=8.8004e-05) (hash(x)=26585300) +1343 train 7.626306 (lr=8.7984e-05) (hash(x)=25951629) +1344 train 7.819092 (lr=8.7964e-05) (hash(x)=28743135) +1345 train 7.972946 (lr=8.7944e-05) (hash(x)=28557663) +1346 train 7.317842 (lr=8.7924e-05) (hash(x)=22642751) +1347 train 7.254521 (lr=8.7904e-05) (hash(x)=23462798) +1348 train 7.145559 (lr=8.7884e-05) (hash(x)=24292328) +1349 train 7.502313 (lr=8.7864e-05) (hash(x)=27320280) +1350 val loss 7.4929 +1350 val perplexity 1795.2797 +1350 train 7.657524 (lr=8.7844e-05) (hash(x)=27352812) +1351 train 7.523433 (lr=8.7824e-05) (hash(x)=22408682) +1352 train 7.458742 (lr=8.7804e-05) (hash(x)=23144732) +1353 train 7.309787 (lr=8.7783e-05) (hash(x)=22230799) +1354 train 7.674279 (lr=8.7763e-05) (hash(x)=29747687) +1355 train 7.872722 (lr=8.7743e-05) (hash(x)=31317970) +1356 train 7.126400 (lr=8.7723e-05) (hash(x)=20131758) +1357 train 7.510678 (lr=8.7703e-05) (hash(x)=24020983) +1358 train 7.374164 (lr=8.7682e-05) (hash(x)=23998051) +1359 train 7.440895 (lr=8.7662e-05) (hash(x)=27633457) +1360 train 7.188716 (lr=8.7642e-05) (hash(x)=20155247) +1361 train 7.420837 (lr=8.7622e-05) (hash(x)=23766987) +1362 train 7.330685 (lr=8.7601e-05) (hash(x)=25960383) +1363 train 7.615689 (lr=8.7581e-05) (hash(x)=23729283) +1364 train 7.748448 (lr=8.7561e-05) (hash(x)=27775445) +1365 train 7.588597 (lr=8.7540e-05) (hash(x)=25975834) +1366 train 7.369789 (lr=8.7520e-05) (hash(x)=22765259) +1367 train 7.658144 (lr=8.7500e-05) (hash(x)=27635080) +1368 train 7.426579 (lr=8.7479e-05) (hash(x)=23848542) +1369 train 7.564298 (lr=8.7459e-05) (hash(x)=27181156) +1370 train 7.706552 (lr=8.7438e-05) (hash(x)=28321340) +1371 train 7.426431 (lr=8.7418e-05) (hash(x)=25918780) +1372 train 7.427619 (lr=8.7398e-05) (hash(x)=23338297) +1373 train 7.487586 (lr=8.7377e-05) (hash(x)=22370417) +1374 train 7.464633 (lr=8.7357e-05) (hash(x)=24272668) +1375 train 7.179981 (lr=8.7336e-05) (hash(x)=22287596) +1376 train 7.383783 (lr=8.7316e-05) (hash(x)=25257403) +1377 train 7.320114 (lr=8.7295e-05) (hash(x)=21584419) +1378 train 7.472328 (lr=8.7275e-05) (hash(x)=25318823) +1379 train 7.272464 (lr=8.7254e-05) (hash(x)=22694623) +1380 train 7.406021 (lr=8.7234e-05) (hash(x)=23743406) +1381 train 7.644372 (lr=8.7213e-05) (hash(x)=30820846) +1382 train 8.152699 (lr=8.7192e-05) (hash(x)=34639557) +1383 train 8.035156 (lr=8.7172e-05) (hash(x)=35895440) +1384 train 7.469388 (lr=8.7151e-05) (hash(x)=26304839) +1385 train 7.611621 (lr=8.7131e-05) (hash(x)=27058657) +1386 train 7.521425 (lr=8.7110e-05) (hash(x)=25209529) +1387 train 7.417232 (lr=8.7089e-05) (hash(x)=24298886) +1388 train 7.542579 (lr=8.7069e-05) (hash(x)=26200200) +1389 train 7.448978 (lr=8.7048e-05) (hash(x)=27303061) +1390 train 7.534799 (lr=8.7027e-05) (hash(x)=26531628) +1391 train 7.544376 (lr=8.7007e-05) (hash(x)=25888847) +1392 train 7.677736 (lr=8.6986e-05) (hash(x)=28924067) +1393 train 7.167787 (lr=8.6965e-05) (hash(x)=21267641) +1394 train 7.693576 (lr=8.6945e-05) (hash(x)=29419156) +1395 train 7.949173 (lr=8.6924e-05) (hash(x)=30860646) +1396 train 7.493675 (lr=8.6903e-05) (hash(x)=25744434) +1397 train 7.496407 (lr=8.6882e-05) (hash(x)=26881837) +1398 train 7.471373 (lr=8.6861e-05) (hash(x)=26676176) +1399 train 7.680252 (lr=8.6841e-05) (hash(x)=26518800) +1400 val loss 7.4779 +1400 val perplexity 1768.5475 +1400 train 7.406942 (lr=8.6820e-05) (hash(x)=25043238) +1401 train 7.679151 (lr=8.6799e-05) (hash(x)=25863277) +1402 train 7.315744 (lr=8.6778e-05) (hash(x)=24073623) +1403 train 7.398768 (lr=8.6757e-05) (hash(x)=25385523) +1404 train 7.481390 (lr=8.6736e-05) (hash(x)=24958112) +1405 train 7.363178 (lr=8.6716e-05) (hash(x)=23362519) +1406 train 7.651063 (lr=8.6695e-05) (hash(x)=29262616) +1407 train 8.041824 (lr=8.6674e-05) (hash(x)=37519283) +1408 train 8.302029 (lr=8.6653e-05) (hash(x)=33716930) +1409 train 7.510316 (lr=8.6632e-05) (hash(x)=23392584) +1410 train 7.890495 (lr=8.6611e-05) (hash(x)=22877779) +1411 train 8.175915 (lr=8.6590e-05) (hash(x)=20564397) +1412 train 7.678229 (lr=8.6569e-05) (hash(x)=24366235) +1413 train 7.614723 (lr=8.6548e-05) (hash(x)=27065499) +1414 train 7.448431 (lr=8.6527e-05) (hash(x)=26844114) +1415 train 7.580675 (lr=8.6506e-05) (hash(x)=25141945) +1416 train 7.761178 (lr=8.6485e-05) (hash(x)=28813116) +1417 train 7.553171 (lr=8.6464e-05) (hash(x)=25466598) +1418 train 7.443981 (lr=8.6443e-05) (hash(x)=22800032) +1419 train 7.513879 (lr=8.6422e-05) (hash(x)=22717866) +1420 train 7.982430 (lr=8.6401e-05) (hash(x)=28040763) +1421 train 8.093472 (lr=8.6379e-05) (hash(x)=29648992) +1422 train 8.005381 (lr=8.6358e-05) (hash(x)=31747228) +1423 train 7.478645 (lr=8.6337e-05) (hash(x)=28527939) +1424 train 7.441044 (lr=8.6316e-05) (hash(x)=21563992) +1425 train 7.338328 (lr=8.6295e-05) (hash(x)=25134784) +1426 train 7.530267 (lr=8.6274e-05) (hash(x)=28442823) +1427 train 8.114864 (lr=8.6253e-05) (hash(x)=32757059) +1428 train 7.316907 (lr=8.6231e-05) (hash(x)=24110500) +1429 train 7.394138 (lr=8.6210e-05) (hash(x)=24145729) +1430 train 7.487275 (lr=8.6189e-05) (hash(x)=23541086) +1431 train 7.347667 (lr=8.6168e-05) (hash(x)=21942471) +1432 train 7.436012 (lr=8.6146e-05) (hash(x)=24736836) +1433 train 7.569325 (lr=8.6125e-05) (hash(x)=25325444) +1434 train 7.565547 (lr=8.6104e-05) (hash(x)=25188954) +1435 train 8.072635 (lr=8.6083e-05) (hash(x)=24247339) +1436 train 7.567680 (lr=8.6061e-05) (hash(x)=23773363) +1437 train 7.320451 (lr=8.6040e-05) (hash(x)=24142989) +1438 train 7.293697 (lr=8.6019e-05) (hash(x)=24226952) +1439 train 7.522785 (lr=8.5997e-05) (hash(x)=24955630) +1440 train 7.484088 (lr=8.5976e-05) (hash(x)=24563233) +1441 train 7.588741 (lr=8.5955e-05) (hash(x)=25491335) +1442 train 7.866867 (lr=8.5933e-05) (hash(x)=33253763) +1443 train 7.360505 (lr=8.5912e-05) (hash(x)=21368780) +1444 train 7.394946 (lr=8.5890e-05) (hash(x)=26615500) +1445 train 7.622545 (lr=8.5869e-05) (hash(x)=27146278) +1446 train 7.480767 (lr=8.5848e-05) (hash(x)=25904861) +1447 train 7.347823 (lr=8.5826e-05) (hash(x)=25541230) +1448 train 7.498975 (lr=8.5805e-05) (hash(x)=25434227) +1449 train 7.480849 (lr=8.5783e-05) (hash(x)=25375355) +1450 val loss 7.4546 +1450 val perplexity 1727.8188 +1450 train 7.293513 (lr=8.5762e-05) (hash(x)=21921129) +1451 train 7.290968 (lr=8.5740e-05) (hash(x)=23098806) +1452 train 7.311298 (lr=8.5719e-05) (hash(x)=22000544) +1453 train 7.209388 (lr=8.5697e-05) (hash(x)=22061174) +1454 train 7.319004 (lr=8.5676e-05) (hash(x)=24326286) +1455 train 7.371556 (lr=8.5654e-05) (hash(x)=23501481) +1456 train 7.567047 (lr=8.5632e-05) (hash(x)=26397938) +1457 train 7.491324 (lr=8.5611e-05) (hash(x)=24656430) +1458 train 7.254005 (lr=8.5589e-05) (hash(x)=23494971) +1459 train 7.262798 (lr=8.5568e-05) (hash(x)=23802681) +1460 train 7.283868 (lr=8.5546e-05) (hash(x)=21990153) +1461 train 7.340654 (lr=8.5524e-05) (hash(x)=23496118) +1462 train 7.330861 (lr=8.5503e-05) (hash(x)=24233822) +1463 train 7.662525 (lr=8.5481e-05) (hash(x)=22754988) +1464 train 7.369340 (lr=8.5459e-05) (hash(x)=23116635) +1465 train 7.122736 (lr=8.5438e-05) (hash(x)=21461650) +1466 train 7.238974 (lr=8.5416e-05) (hash(x)=22274473) +1467 train 7.288820 (lr=8.5394e-05) (hash(x)=22183009) +1468 train 7.497007 (lr=8.5373e-05) (hash(x)=24972441) +1469 train 7.317658 (lr=8.5351e-05) (hash(x)=22300616) +1470 train 7.100246 (lr=8.5329e-05) (hash(x)=21443060) +1471 train 7.313563 (lr=8.5307e-05) (hash(x)=23475070) +1472 train 7.268262 (lr=8.5286e-05) (hash(x)=22316810) +1473 train 7.676486 (lr=8.5264e-05) (hash(x)=24508407) +1474 train 7.662473 (lr=8.5242e-05) (hash(x)=24603557) +1475 train 7.343811 (lr=8.5220e-05) (hash(x)=23359061) +1476 train 7.397048 (lr=8.5198e-05) (hash(x)=22950844) +1477 train 7.445221 (lr=8.5176e-05) (hash(x)=22588667) +1478 train 7.546518 (lr=8.5155e-05) (hash(x)=26083526) +1479 train 7.475607 (lr=8.5133e-05) (hash(x)=23609959) +1480 train 7.506227 (lr=8.5111e-05) (hash(x)=24088171) +1481 train 7.483855 (lr=8.5089e-05) (hash(x)=25394852) +1482 train 7.422825 (lr=8.5067e-05) (hash(x)=24503040) +1483 train 7.185295 (lr=8.5045e-05) (hash(x)=22408449) +1484 train 7.424895 (lr=8.5023e-05) (hash(x)=25069325) +1485 train 7.454614 (lr=8.5001e-05) (hash(x)=26947398) +1486 train 6.904400 (lr=8.4979e-05) (hash(x)=17527161) +1487 train 7.342773 (lr=8.4957e-05) (hash(x)=23441847) +1488 train 7.363519 (lr=8.4935e-05) (hash(x)=25592861) +1489 train 7.278503 (lr=8.4913e-05) (hash(x)=23101350) +1490 train 7.242131 (lr=8.4891e-05) (hash(x)=24201380) +1491 train 7.355363 (lr=8.4869e-05) (hash(x)=23676365) +1492 train 7.455443 (lr=8.4847e-05) (hash(x)=26668088) +1493 train 7.581244 (lr=8.4825e-05) (hash(x)=26488811) +1494 train 7.547104 (lr=8.4803e-05) (hash(x)=27248109) +1495 train 7.567159 (lr=8.4781e-05) (hash(x)=23096292) +1496 train 7.498595 (lr=8.4759e-05) (hash(x)=22101981) +1497 train 7.652998 (lr=8.4737e-05) (hash(x)=24512380) +1498 train 7.459951 (lr=8.4715e-05) (hash(x)=25367738) +1499 train 7.478229 (lr=8.4693e-05) (hash(x)=27706294) +1500 val loss 7.4497 +1500 val perplexity 1719.4258 +1500 train 7.575786 (lr=8.4671e-05) (hash(x)=24154026) +1501 train 7.302785 (lr=8.4648e-05) (hash(x)=21892472) +1502 train 7.370102 (lr=8.4626e-05) (hash(x)=23662543) +1503 train 7.427538 (lr=8.4604e-05) (hash(x)=26171093) +1504 train 7.428116 (lr=8.4582e-05) (hash(x)=25974292) +1505 train 7.311324 (lr=8.4560e-05) (hash(x)=23191101) +1506 train 7.531612 (lr=8.4537e-05) (hash(x)=26498861) +1507 train 8.033237 (lr=8.4515e-05) (hash(x)=34946941) +1508 train 7.659924 (lr=8.4493e-05) (hash(x)=25442719) +1509 train 7.500165 (lr=8.4471e-05) (hash(x)=25569942) +1510 train 7.243385 (lr=8.4448e-05) (hash(x)=21265828) +1511 train 7.141631 (lr=8.4426e-05) (hash(x)=20060838) +1512 train 7.290610 (lr=8.4404e-05) (hash(x)=22588251) +1513 train 7.289864 (lr=8.4382e-05) (hash(x)=24581020) +1514 train 7.290906 (lr=8.4359e-05) (hash(x)=21882493) +1515 train 7.241589 (lr=8.4337e-05) (hash(x)=21591702) +1516 train 7.267448 (lr=8.4315e-05) (hash(x)=19813285) +1517 train 7.357244 (lr=8.4292e-05) (hash(x)=21870012) +1518 train 7.380553 (lr=8.4270e-05) (hash(x)=26895498) +1519 train 7.397521 (lr=8.4248e-05) (hash(x)=25451055) +1520 train 7.467579 (lr=8.4225e-05) (hash(x)=25395865) +1521 train 6.906722 (lr=8.4203e-05) (hash(x)=18989695) +1522 train 6.760650 (lr=8.4180e-05) (hash(x)=17040678) +1523 train 6.894502 (lr=8.4158e-05) (hash(x)=18691455) +1524 train 7.022522 (lr=8.4135e-05) (hash(x)=19017167) +1525 train 7.341568 (lr=8.4113e-05) (hash(x)=22406503) +1526 train 7.496724 (lr=8.4091e-05) (hash(x)=23036138) +1527 train 7.357131 (lr=8.4068e-05) (hash(x)=24934792) +1528 train 7.389096 (lr=8.4046e-05) (hash(x)=22843127) +1529 train 7.316824 (lr=8.4023e-05) (hash(x)=24249677) +1530 train 7.194917 (lr=8.4001e-05) (hash(x)=23318555) +1531 train 7.248104 (lr=8.3978e-05) (hash(x)=23864361) +1532 train 7.154395 (lr=8.3956e-05) (hash(x)=20242060) +1533 train 7.303594 (lr=8.3933e-05) (hash(x)=21549554) +1534 train 7.132853 (lr=8.3910e-05) (hash(x)=21642024) +1535 train 7.605480 (lr=8.3888e-05) (hash(x)=25367597) +1536 train 7.770660 (lr=8.3865e-05) (hash(x)=27224144) +1537 train 7.339244 (lr=8.3843e-05) (hash(x)=24409290) +1538 train 7.405628 (lr=8.3820e-05) (hash(x)=24987180) +1539 train 7.348588 (lr=8.3797e-05) (hash(x)=27016702) +1540 train 7.550661 (lr=8.3775e-05) (hash(x)=25819636) +1541 train 7.492980 (lr=8.3752e-05) (hash(x)=25520453) +1542 train 7.264626 (lr=8.3729e-05) (hash(x)=23580496) +1543 train 7.488274 (lr=8.3707e-05) (hash(x)=25022148) +1544 train 7.477872 (lr=8.3684e-05) (hash(x)=25447327) +1545 train 7.473244 (lr=8.3661e-05) (hash(x)=25010319) +1546 train 7.380149 (lr=8.3639e-05) (hash(x)=25511777) +1547 train 7.355400 (lr=8.3616e-05) (hash(x)=24459012) +1548 train 7.404420 (lr=8.3593e-05) (hash(x)=25082785) +1549 train 7.490077 (lr=8.3570e-05) (hash(x)=26528670) +1550 val loss 7.4205 +1550 val perplexity 1669.9403 +1550 train 7.407942 (lr=8.3548e-05) (hash(x)=26684367) +1551 train 7.384481 (lr=8.3525e-05) (hash(x)=25431365) +1552 train 7.375795 (lr=8.3502e-05) (hash(x)=24802747) +1553 train 7.195179 (lr=8.3479e-05) (hash(x)=24229522) +1554 train 7.408119 (lr=8.3457e-05) (hash(x)=24757176) +1555 train 7.542372 (lr=8.3434e-05) (hash(x)=25958785) +1556 train 7.547225 (lr=8.3411e-05) (hash(x)=26810735) +1557 train 7.206272 (lr=8.3388e-05) (hash(x)=22882640) +1558 train 7.639746 (lr=8.3365e-05) (hash(x)=27220057) +1559 train 7.903757 (lr=8.3342e-05) (hash(x)=29307788) +1560 train 7.393426 (lr=8.3319e-05) (hash(x)=25214030) +1561 train 7.244678 (lr=8.3297e-05) (hash(x)=23167825) +1562 train 7.296377 (lr=8.3274e-05) (hash(x)=24658511) +1563 train 7.440595 (lr=8.3251e-05) (hash(x)=24965435) +1564 train 7.199853 (lr=8.3228e-05) (hash(x)=23620579) +1565 train 7.201491 (lr=8.3205e-05) (hash(x)=23772949) +1566 train 7.381175 (lr=8.3182e-05) (hash(x)=23807939) +1567 train 7.564943 (lr=8.3159e-05) (hash(x)=25651929) +1568 train 7.501093 (lr=8.3136e-05) (hash(x)=25549933) +1569 train 7.212087 (lr=8.3113e-05) (hash(x)=23146724) +1570 train 7.309038 (lr=8.3090e-05) (hash(x)=24099275) +1571 train 7.531780 (lr=8.3067e-05) (hash(x)=28451031) +1572 train 7.556322 (lr=8.3044e-05) (hash(x)=25488511) +1573 train 7.340907 (lr=8.3021e-05) (hash(x)=23796771) +1574 train 7.414082 (lr=8.2998e-05) (hash(x)=22642764) +1575 train 7.499119 (lr=8.2975e-05) (hash(x)=26312387) +1576 train 7.311882 (lr=8.2952e-05) (hash(x)=22486223) +1577 train 7.307395 (lr=8.2929e-05) (hash(x)=21257377) +1578 train 7.451889 (lr=8.2905e-05) (hash(x)=24328365) +1579 train 7.535576 (lr=8.2882e-05) (hash(x)=25326650) +1580 train 7.487628 (lr=8.2859e-05) (hash(x)=26484837) +1581 train 7.293094 (lr=8.2836e-05) (hash(x)=24605603) +1582 train 7.381313 (lr=8.2813e-05) (hash(x)=24668537) +1583 train 7.281059 (lr=8.2790e-05) (hash(x)=23804913) +1584 train 7.531216 (lr=8.2767e-05) (hash(x)=23615391) +1585 train 7.503478 (lr=8.2743e-05) (hash(x)=24322926) +1586 train 7.295772 (lr=8.2720e-05) (hash(x)=19753104) +1587 train 7.727454 (lr=8.2697e-05) (hash(x)=25537529) +1588 train 7.189266 (lr=8.2674e-05) (hash(x)=22835476) +1589 train 7.312458 (lr=8.2651e-05) (hash(x)=25707197) +1590 train 7.304048 (lr=8.2627e-05) (hash(x)=24191203) +1591 train 7.566562 (lr=8.2604e-05) (hash(x)=26115519) +1592 train 7.434022 (lr=8.2581e-05) (hash(x)=25781547) +1593 train 7.269275 (lr=8.2558e-05) (hash(x)=24850654) +1594 train 7.195733 (lr=8.2534e-05) (hash(x)=23300928) +1595 train 7.422292 (lr=8.2511e-05) (hash(x)=25494804) +1596 train 7.438097 (lr=8.2488e-05) (hash(x)=28169410) +1597 train 7.188785 (lr=8.2464e-05) (hash(x)=21972022) +1598 train 7.717287 (lr=8.2441e-05) (hash(x)=27687290) +1599 train 7.601554 (lr=8.2418e-05) (hash(x)=23210747) +1600 val loss 7.4134 +1600 val perplexity 1658.0583 +1600 train 7.580705 (lr=8.2394e-05) (hash(x)=20362758) +1601 train 7.410956 (lr=8.2371e-05) (hash(x)=17064773) +1602 train 7.427640 (lr=8.2348e-05) (hash(x)=17173694) +1603 train 7.490749 (lr=8.2324e-05) (hash(x)=15717069) +1604 train 7.607529 (lr=8.2301e-05) (hash(x)=15117973) +1605 train 7.419469 (lr=8.2277e-05) (hash(x)=16189636) +1606 train 7.358716 (lr=8.2254e-05) (hash(x)=16552095) +1607 train 7.215996 (lr=8.2230e-05) (hash(x)=18463712) +1608 train 7.415286 (lr=8.2207e-05) (hash(x)=17572155) +1609 train 7.385947 (lr=8.2183e-05) (hash(x)=19970072) +1610 train 7.389784 (lr=8.2160e-05) (hash(x)=20463871) +1611 train 7.480476 (lr=8.2137e-05) (hash(x)=20705573) +1612 train 7.276389 (lr=8.2113e-05) (hash(x)=24441646) +1613 train 7.410474 (lr=8.2090e-05) (hash(x)=22913147) +1614 train 7.579034 (lr=8.2066e-05) (hash(x)=23081598) +1615 train 7.294931 (lr=8.2042e-05) (hash(x)=23245699) +1616 train 7.308812 (lr=8.2019e-05) (hash(x)=23003072) +1617 train 7.597538 (lr=8.1995e-05) (hash(x)=27121904) +1618 train 7.323784 (lr=8.1972e-05) (hash(x)=25092305) +1619 train 7.392274 (lr=8.1948e-05) (hash(x)=23444521) +1620 train 7.405376 (lr=8.1925e-05) (hash(x)=22130531) +1621 train 7.173090 (lr=8.1901e-05) (hash(x)=20917937) +1622 train 7.317397 (lr=8.1877e-05) (hash(x)=22526838) +1623 train 7.420631 (lr=8.1854e-05) (hash(x)=21770300) +1624 train 8.520942 (lr=8.1830e-05) (hash(x)=22333537) +1625 train 8.516612 (lr=8.1806e-05) (hash(x)=24642519) +1626 train 7.661308 (lr=8.1783e-05) (hash(x)=25199038) +1627 train 7.481368 (lr=8.1759e-05) (hash(x)=23334569) +1628 train 7.354071 (lr=8.1735e-05) (hash(x)=23785360) +1629 train 7.018459 (lr=8.1712e-05) (hash(x)=21796200) +1630 train 7.111472 (lr=8.1688e-05) (hash(x)=22389081) +1631 train 7.402736 (lr=8.1664e-05) (hash(x)=25387532) +1632 train 7.006423 (lr=8.1641e-05) (hash(x)=17247578) +1633 train 7.387505 (lr=8.1617e-05) (hash(x)=22203733) +1634 train 7.552587 (lr=8.1593e-05) (hash(x)=24387455) +1635 train 7.981741 (lr=8.1569e-05) (hash(x)=29466743) +1636 train 7.385553 (lr=8.1546e-05) (hash(x)=25354152) +1637 train 7.436981 (lr=8.1522e-05) (hash(x)=21756102) +1638 train 7.397049 (lr=8.1498e-05) (hash(x)=23544029) +1639 train 7.517251 (lr=8.1474e-05) (hash(x)=27718703) +1640 train 7.498566 (lr=8.1450e-05) (hash(x)=25697138) +1641 train 7.326415 (lr=8.1427e-05) (hash(x)=22978681) +1642 train 7.894705 (lr=8.1403e-05) (hash(x)=29527067) +1643 train 6.989457 (lr=8.1379e-05) (hash(x)=17631973) +1644 train 7.365158 (lr=8.1355e-05) (hash(x)=24860172) +1645 train 7.718862 (lr=8.1331e-05) (hash(x)=27947891) +1646 train 7.416622 (lr=8.1307e-05) (hash(x)=23819556) +1647 train 7.461150 (lr=8.1283e-05) (hash(x)=27661052) +1648 train 7.255884 (lr=8.1259e-05) (hash(x)=23014209) +1649 train 7.186330 (lr=8.1235e-05) (hash(x)=23061452) +1650 val loss 7.4177 +1650 val perplexity 1665.2417 +1650 train 7.271852 (lr=8.1211e-05) (hash(x)=21949051) +1651 train 7.339942 (lr=8.1188e-05) (hash(x)=22244096) +1652 train 7.327539 (lr=8.1164e-05) (hash(x)=25997585) +1653 train 7.409492 (lr=8.1140e-05) (hash(x)=25389713) +1654 train 7.326575 (lr=8.1116e-05) (hash(x)=24390520) +1655 train 7.535323 (lr=8.1092e-05) (hash(x)=26538928) +1656 train 7.472581 (lr=8.1068e-05) (hash(x)=28708088) +1657 train 7.588590 (lr=8.1044e-05) (hash(x)=25685569) +1658 train 7.177274 (lr=8.1020e-05) (hash(x)=22163531) +1659 train 7.338222 (lr=8.0996e-05) (hash(x)=26256802) +1660 train 7.767662 (lr=8.0972e-05) (hash(x)=30016026) +1661 train 7.360260 (lr=8.0947e-05) (hash(x)=24412323) +1662 train 7.396743 (lr=8.0923e-05) (hash(x)=24722307) +1663 train 7.263336 (lr=8.0899e-05) (hash(x)=21772654) +1664 train 7.234113 (lr=8.0875e-05) (hash(x)=24984527) +1665 train 7.375216 (lr=8.0851e-05) (hash(x)=25456825) +1666 train 7.728891 (lr=8.0827e-05) (hash(x)=24383976) +1667 train 7.619377 (lr=8.0803e-05) (hash(x)=25026277) +1668 train 7.496841 (lr=8.0779e-05) (hash(x)=28121715) +1669 train 7.512100 (lr=8.0755e-05) (hash(x)=26855439) +1670 train 7.606505 (lr=8.0730e-05) (hash(x)=33370924) +1671 train 7.467250 (lr=8.0706e-05) (hash(x)=26263254) +1672 train 7.942585 (lr=8.0682e-05) (hash(x)=29958158) +1673 train 7.221619 (lr=8.0658e-05) (hash(x)=21917396) +1674 train 7.378360 (lr=8.0634e-05) (hash(x)=24196295) +1675 train 7.400902 (lr=8.0610e-05) (hash(x)=24726314) +1676 train 7.218528 (lr=8.0585e-05) (hash(x)=22137742) +1677 train 7.317780 (lr=8.0561e-05) (hash(x)=24375100) +1678 train 7.301944 (lr=8.0537e-05) (hash(x)=23965039) +1679 train 7.339649 (lr=8.0513e-05) (hash(x)=23552356) +1680 train 7.320940 (lr=8.0488e-05) (hash(x)=26136969) +1681 train 7.519227 (lr=8.0464e-05) (hash(x)=25343112) +1682 train 7.221225 (lr=8.0440e-05) (hash(x)=22831508) +1683 train 7.490463 (lr=8.0415e-05) (hash(x)=26699819) +1684 train 7.612087 (lr=8.0391e-05) (hash(x)=25435504) +1685 train 7.760126 (lr=8.0367e-05) (hash(x)=25218858) +1686 train 8.371573 (lr=8.0342e-05) (hash(x)=25664448) +1687 train 7.431502 (lr=8.0318e-05) (hash(x)=22707141) +1688 train 7.614961 (lr=8.0294e-05) (hash(x)=28001383) +1689 train 7.852661 (lr=8.0269e-05) (hash(x)=29168269) +1690 train 7.826295 (lr=8.0245e-05) (hash(x)=29637522) +1691 train 7.817075 (lr=8.0221e-05) (hash(x)=25676149) +1692 train 7.261047 (lr=8.0196e-05) (hash(x)=20919831) +1693 train 7.423781 (lr=8.0172e-05) (hash(x)=24324401) +1694 train 7.506384 (lr=8.0147e-05) (hash(x)=26862625) +1695 train 7.921072 (lr=8.0123e-05) (hash(x)=34234481) +1696 train 7.507249 (lr=8.0099e-05) (hash(x)=27415195) +1697 train 7.311703 (lr=8.0074e-05) (hash(x)=24511386) +1698 train 7.457128 (lr=8.0050e-05) (hash(x)=26904299) +1699 train 7.322994 (lr=8.0025e-05) (hash(x)=25401624) +1700 val loss 7.4168 +1700 val perplexity 1663.7075 +1700 train 7.377234 (lr=8.0001e-05) (hash(x)=26498489) +1701 train 7.356296 (lr=7.9976e-05) (hash(x)=22340685) +1702 train 7.460903 (lr=7.9952e-05) (hash(x)=26396757) +1703 train 8.058539 (lr=7.9927e-05) (hash(x)=35008670) +1704 train 7.829288 (lr=7.9903e-05) (hash(x)=31782020) +1705 train 7.684465 (lr=7.9878e-05) (hash(x)=29662286) +1706 train 7.884261 (lr=7.9854e-05) (hash(x)=34215782) +1707 train 7.340155 (lr=7.9829e-05) (hash(x)=25682280) +1708 train 7.543502 (lr=7.9804e-05) (hash(x)=27109048) +1709 train 7.598724 (lr=7.9780e-05) (hash(x)=27686498) +1710 train 7.435388 (lr=7.9755e-05) (hash(x)=24247565) +1711 train 7.460526 (lr=7.9731e-05) (hash(x)=25891543) +1712 train 7.547961 (lr=7.9706e-05) (hash(x)=26436778) +1713 train 7.226340 (lr=7.9681e-05) (hash(x)=22538881) +1714 train 7.180665 (lr=7.9657e-05) (hash(x)=21993512) +1715 train 7.634172 (lr=7.9632e-05) (hash(x)=25962407) +1716 train 7.458717 (lr=7.9607e-05) (hash(x)=24130284) +1717 train 7.282018 (lr=7.9583e-05) (hash(x)=24819073) +1718 train 7.202960 (lr=7.9558e-05) (hash(x)=23496648) +1719 train 7.249197 (lr=7.9533e-05) (hash(x)=21971224) +1720 train 7.127276 (lr=7.9509e-05) (hash(x)=21498081) +1721 train 7.173683 (lr=7.9484e-05) (hash(x)=20951317) +1722 train 7.728227 (lr=7.9459e-05) (hash(x)=28848134) +1723 train 7.753543 (lr=7.9435e-05) (hash(x)=30838142) +1724 train 7.708217 (lr=7.9410e-05) (hash(x)=28844392) +1725 train 7.322315 (lr=7.9385e-05) (hash(x)=23102419) +1726 train 7.362976 (lr=7.9360e-05) (hash(x)=22374479) +1727 train 7.627951 (lr=7.9336e-05) (hash(x)=27312186) +1728 train 8.014775 (lr=7.9311e-05) (hash(x)=34362559) +1729 train 7.882504 (lr=7.9286e-05) (hash(x)=30920030) +1730 train 7.172666 (lr=7.9261e-05) (hash(x)=23684126) +1731 train 7.428177 (lr=7.9236e-05) (hash(x)=23657081) +1732 train 7.668635 (lr=7.9212e-05) (hash(x)=28463299) +1733 train 7.958034 (lr=7.9187e-05) (hash(x)=35351214) +1734 train 7.489228 (lr=7.9162e-05) (hash(x)=28855662) +1735 train 7.009999 (lr=7.9137e-05) (hash(x)=22163749) +1736 train 7.041547 (lr=7.9112e-05) (hash(x)=22024585) +1737 train 7.261356 (lr=7.9087e-05) (hash(x)=24629160) +1738 train 7.324649 (lr=7.9062e-05) (hash(x)=25220941) +1739 train 7.265762 (lr=7.9038e-05) (hash(x)=24829818) +1740 train 7.619984 (lr=7.9013e-05) (hash(x)=28453898) +1741 train 7.657526 (lr=7.8988e-05) (hash(x)=25424550) +1742 train 7.320747 (lr=7.8963e-05) (hash(x)=23437814) +1743 train 7.409170 (lr=7.8938e-05) (hash(x)=25942888) +1744 train 7.379616 (lr=7.8913e-05) (hash(x)=24503801) +1745 train 7.673671 (lr=7.8888e-05) (hash(x)=26418501) +1746 train 7.551375 (lr=7.8863e-05) (hash(x)=27177691) +1747 train 7.270834 (lr=7.8838e-05) (hash(x)=23785671) +1748 train 7.685880 (lr=7.8813e-05) (hash(x)=27362772) +1749 train 7.447214 (lr=7.8788e-05) (hash(x)=25097859) +1750 val loss 7.4276 +1750 val perplexity 1681.7743 +1750 train 7.403180 (lr=7.8763e-05) (hash(x)=24662466) +1751 train 7.327254 (lr=7.8738e-05) (hash(x)=25493916) +1752 train 7.435394 (lr=7.8713e-05) (hash(x)=24655868) +1753 train 7.661208 (lr=7.8688e-05) (hash(x)=19819210) +1754 train 7.290498 (lr=7.8663e-05) (hash(x)=21377155) +1755 train 8.108066 (lr=7.8638e-05) (hash(x)=28618702) +1756 train 8.024882 (lr=7.8613e-05) (hash(x)=27324953) +1757 train 7.687793 (lr=7.8588e-05) (hash(x)=29707907) +1758 train 7.454464 (lr=7.8563e-05) (hash(x)=24485921) +1759 train 7.557559 (lr=7.8538e-05) (hash(x)=24289951) +1760 train 7.270947 (lr=7.8512e-05) (hash(x)=22496716) +1761 train 7.403629 (lr=7.8487e-05) (hash(x)=25147026) +1762 train 7.499116 (lr=7.8462e-05) (hash(x)=26851828) +1763 train 7.452975 (lr=7.8437e-05) (hash(x)=26331486) +1764 train 7.292915 (lr=7.8412e-05) (hash(x)=24383054) +1765 train 7.561025 (lr=7.8387e-05) (hash(x)=25885126) +1766 train 7.470851 (lr=7.8362e-05) (hash(x)=25848470) +1767 train 7.307134 (lr=7.8336e-05) (hash(x)=23648671) +1768 train 7.274804 (lr=7.8311e-05) (hash(x)=23168674) +1769 train 7.125011 (lr=7.8286e-05) (hash(x)=20252079) +1770 train 7.342415 (lr=7.8261e-05) (hash(x)=23914287) +1771 train 7.620416 (lr=7.8236e-05) (hash(x)=27292797) +1772 train 6.863697 (lr=7.8210e-05) (hash(x)=16175151) +1773 train 6.984117 (lr=7.8185e-05) (hash(x)=18317379) +1774 train 7.357522 (lr=7.8160e-05) (hash(x)=24464271) +1775 train 7.298680 (lr=7.8135e-05) (hash(x)=24992055) +1776 train 7.979851 (lr=7.8109e-05) (hash(x)=26032451) +1777 train 7.711338 (lr=7.8084e-05) (hash(x)=24734221) +1778 train 7.699853 (lr=7.8059e-05) (hash(x)=25413430) +1779 train 7.561271 (lr=7.8033e-05) (hash(x)=24398330) +1780 train 7.403827 (lr=7.8008e-05) (hash(x)=24568049) +1781 train 7.286310 (lr=7.7983e-05) (hash(x)=23573984) +1782 train 7.498843 (lr=7.7958e-05) (hash(x)=27338410) +1783 train 7.470617 (lr=7.7932e-05) (hash(x)=26005549) +1784 train 7.326871 (lr=7.7907e-05) (hash(x)=24332331) +1785 train 7.211593 (lr=7.7882e-05) (hash(x)=22583878) +1786 train 7.356583 (lr=7.7856e-05) (hash(x)=24599113) +1787 train 7.766499 (lr=7.7831e-05) (hash(x)=30259737) +1788 train 7.547497 (lr=7.7805e-05) (hash(x)=26504237) +1789 train 7.431557 (lr=7.7780e-05) (hash(x)=25196470) +1790 train 7.343987 (lr=7.7755e-05) (hash(x)=23607871) +1791 train 7.243556 (lr=7.7729e-05) (hash(x)=21046554) +1792 train 7.494962 (lr=7.7704e-05) (hash(x)=27285635) +1793 train 7.464397 (lr=7.7678e-05) (hash(x)=25454371) +1794 train 7.512895 (lr=7.7653e-05) (hash(x)=26486575) +1795 train 6.998218 (lr=7.7627e-05) (hash(x)=18773877) +1796 train 7.131040 (lr=7.7602e-05) (hash(x)=22506761) +1797 train 7.436620 (lr=7.7576e-05) (hash(x)=24645168) +1798 train 7.500215 (lr=7.7551e-05) (hash(x)=25046236) +1799 train 7.562080 (lr=7.7526e-05) (hash(x)=26321539) +1800 val loss 7.3969 +1800 val perplexity 1630.9171 +1800 train 7.325395 (lr=7.7500e-05) (hash(x)=24602494) +1801 train 7.538409 (lr=7.7474e-05) (hash(x)=25722713) +1802 train 7.248719 (lr=7.7449e-05) (hash(x)=23711219) +1803 train 7.381755 (lr=7.7423e-05) (hash(x)=22850804) +1804 train 7.673640 (lr=7.7398e-05) (hash(x)=25829388) +1805 train 7.230181 (lr=7.7372e-05) (hash(x)=22503524) +1806 train 7.519132 (lr=7.7347e-05) (hash(x)=26669453) +1807 train 7.430868 (lr=7.7321e-05) (hash(x)=27807872) +1808 train 7.467777 (lr=7.7296e-05) (hash(x)=23543560) +1809 train 7.575658 (lr=7.7270e-05) (hash(x)=25845590) +1810 train 7.388931 (lr=7.7244e-05) (hash(x)=23026635) +1811 train 7.316125 (lr=7.7219e-05) (hash(x)=25545137) +1812 train 7.832513 (lr=7.7193e-05) (hash(x)=27746841) +1813 train 7.206037 (lr=7.7168e-05) (hash(x)=25471231) +1814 train 7.352433 (lr=7.7142e-05) (hash(x)=24333204) +1815 train 7.219606 (lr=7.7116e-05) (hash(x)=21555364) +1816 train 7.415167 (lr=7.7091e-05) (hash(x)=26317977) +1817 train 7.487892 (lr=7.7065e-05) (hash(x)=24474988) +1818 train 7.156200 (lr=7.7039e-05) (hash(x)=21975953) +1819 train 7.729491 (lr=7.7014e-05) (hash(x)=27243798) +1820 train 7.360482 (lr=7.6988e-05) (hash(x)=25097367) +1821 train 7.285423 (lr=7.6962e-05) (hash(x)=24419085) +1822 train 7.244354 (lr=7.6937e-05) (hash(x)=23058837) +1823 train 7.400100 (lr=7.6911e-05) (hash(x)=26325324) +1824 train 7.143346 (lr=7.6885e-05) (hash(x)=20581023) +1825 train 7.441812 (lr=7.6859e-05) (hash(x)=24822111) +1826 train 7.211830 (lr=7.6834e-05) (hash(x)=24336304) +1827 train 7.370343 (lr=7.6808e-05) (hash(x)=26228728) +1828 train 7.449831 (lr=7.6782e-05) (hash(x)=26445781) +1829 train 7.527048 (lr=7.6756e-05) (hash(x)=24707042) +1830 train 7.819948 (lr=7.6731e-05) (hash(x)=27882744) +1831 train 7.357953 (lr=7.6705e-05) (hash(x)=24956294) +1832 train 7.156406 (lr=7.6679e-05) (hash(x)=20984728) +1833 train 7.172290 (lr=7.6653e-05) (hash(x)=23424737) +1834 train 7.567694 (lr=7.6627e-05) (hash(x)=26207120) +1835 train 7.578979 (lr=7.6601e-05) (hash(x)=25592289) +1836 train 7.269718 (lr=7.6576e-05) (hash(x)=24326649) +1837 train 7.422615 (lr=7.6550e-05) (hash(x)=26826109) +1838 train 7.384429 (lr=7.6524e-05) (hash(x)=24759294) +1839 train 7.367612 (lr=7.6498e-05) (hash(x)=24429389) +1840 train 7.313692 (lr=7.6472e-05) (hash(x)=25537519) +1841 train 7.319896 (lr=7.6446e-05) (hash(x)=24747421) +1842 train 7.224752 (lr=7.6420e-05) (hash(x)=23079065) +1843 train 7.605228 (lr=7.6394e-05) (hash(x)=28733708) +1844 train 7.355839 (lr=7.6369e-05) (hash(x)=23937742) +1845 train 7.648876 (lr=7.6343e-05) (hash(x)=29704803) +1846 train 7.809319 (lr=7.6317e-05) (hash(x)=34617155) +1847 train 7.533841 (lr=7.6291e-05) (hash(x)=27929846) +1848 train 7.886939 (lr=7.6265e-05) (hash(x)=28280878) +1849 train 6.936866 (lr=7.6239e-05) (hash(x)=18961171) +1850 val loss 7.4106 +1850 val perplexity 1653.3403 +1850 train 7.515425 (lr=7.6213e-05) (hash(x)=27146015) +1851 train 7.277046 (lr=7.6187e-05) (hash(x)=22417476) +1852 train 7.437815 (lr=7.6161e-05) (hash(x)=24583152) +1853 train 7.488023 (lr=7.6135e-05) (hash(x)=26364120) +1854 train 7.635784 (lr=7.6109e-05) (hash(x)=25946767) +1855 train 7.467056 (lr=7.6083e-05) (hash(x)=25282897) +1856 train 7.420310 (lr=7.6057e-05) (hash(x)=25154557) +1857 train 7.130376 (lr=7.6031e-05) (hash(x)=22082503) +1858 train 7.202943 (lr=7.6005e-05) (hash(x)=23974606) +1859 train 7.337186 (lr=7.5979e-05) (hash(x)=22278062) +1860 train 7.228487 (lr=7.5953e-05) (hash(x)=19509639) +1861 train 7.506558 (lr=7.5927e-05) (hash(x)=24271468) +1862 train 7.147316 (lr=7.5901e-05) (hash(x)=21943809) +1863 train 7.353185 (lr=7.5874e-05) (hash(x)=26802508) +1864 train 7.929266 (lr=7.5848e-05) (hash(x)=34178409) +1865 train 8.085721 (lr=7.5822e-05) (hash(x)=33468379) +1866 train 7.210468 (lr=7.5796e-05) (hash(x)=22109262) +1867 train 6.944704 (lr=7.5770e-05) (hash(x)=22094832) +1868 train 7.204996 (lr=7.5744e-05) (hash(x)=24016953) +1869 train 7.502548 (lr=7.5718e-05) (hash(x)=26759850) +1870 train 7.318489 (lr=7.5692e-05) (hash(x)=23570779) +1871 train 7.762761 (lr=7.5665e-05) (hash(x)=28390416) +1872 train 7.753612 (lr=7.5639e-05) (hash(x)=26215770) +1873 train 7.640705 (lr=7.5613e-05) (hash(x)=22727956) +1874 train 7.442585 (lr=7.5587e-05) (hash(x)=21304587) +1875 train 7.745538 (lr=7.5561e-05) (hash(x)=26379331) +1876 train 7.815949 (lr=7.5534e-05) (hash(x)=25252419) +1877 train 7.710059 (lr=7.5508e-05) (hash(x)=25048158) +1878 train 7.648780 (lr=7.5482e-05) (hash(x)=23588991) +1879 train 7.650725 (lr=7.5456e-05) (hash(x)=26292451) +1880 train 7.550568 (lr=7.5430e-05) (hash(x)=23617086) +1881 train 7.413182 (lr=7.5403e-05) (hash(x)=23336031) +1882 train 7.371873 (lr=7.5377e-05) (hash(x)=19198742) +1883 train 8.000254 (lr=7.5351e-05) (hash(x)=26301866) +1884 train 7.987742 (lr=7.5325e-05) (hash(x)=30114703) +1885 train 7.510330 (lr=7.5298e-05) (hash(x)=26687040) +1886 train 7.333753 (lr=7.5272e-05) (hash(x)=25810717) +1887 train 7.184506 (lr=7.5246e-05) (hash(x)=22915344) +1888 train 7.554443 (lr=7.5219e-05) (hash(x)=27046189) +1889 train 7.113553 (lr=7.5193e-05) (hash(x)=19831900) +1890 train 7.514762 (lr=7.5167e-05) (hash(x)=27786987) +1891 train 7.392644 (lr=7.5140e-05) (hash(x)=25448318) +1892 train 7.392615 (lr=7.5114e-05) (hash(x)=25166953) +1893 train 7.373025 (lr=7.5088e-05) (hash(x)=24993116) +1894 train 7.458057 (lr=7.5061e-05) (hash(x)=25748002) +1895 train 7.663741 (lr=7.5035e-05) (hash(x)=24744383) +1896 train 7.397337 (lr=7.5009e-05) (hash(x)=25560120) +1897 train 7.230226 (lr=7.4982e-05) (hash(x)=23731849) +1898 train 7.243111 (lr=7.4956e-05) (hash(x)=24115851) +1899 train 7.257451 (lr=7.4929e-05) (hash(x)=22835201) +1900 val loss 7.4104 +1900 val perplexity 1653.0061 +1900 train 7.078705 (lr=7.4903e-05) (hash(x)=21927896) +1901 train 7.462975 (lr=7.4877e-05) (hash(x)=24652361) +1902 train 7.600458 (lr=7.4850e-05) (hash(x)=27332405) +1903 train 7.433250 (lr=7.4824e-05) (hash(x)=26284678) +1904 train 7.391943 (lr=7.4797e-05) (hash(x)=23441305) +1905 train 7.480125 (lr=7.4771e-05) (hash(x)=27522881) +1906 train 7.538419 (lr=7.4744e-05) (hash(x)=25521191) +1907 train 7.311906 (lr=7.4718e-05) (hash(x)=24745936) +1908 train 7.221130 (lr=7.4691e-05) (hash(x)=21653364) +1909 train 7.265538 (lr=7.4665e-05) (hash(x)=21973969) +1910 train 7.252509 (lr=7.4638e-05) (hash(x)=24318192) +1911 train 7.193466 (lr=7.4612e-05) (hash(x)=21654269) +1912 train 7.253296 (lr=7.4585e-05) (hash(x)=24142904) +1913 train 7.192461 (lr=7.4559e-05) (hash(x)=21708739) +1914 train 7.381726 (lr=7.4532e-05) (hash(x)=22937923) +1915 train 7.956892 (lr=7.4506e-05) (hash(x)=32387999) +1916 train 8.132834 (lr=7.4479e-05) (hash(x)=28958671) +1917 train 8.216915 (lr=7.4453e-05) (hash(x)=32662682) +1918 train 8.105025 (lr=7.4426e-05) (hash(x)=31364539) +1919 train 8.176633 (lr=7.4400e-05) (hash(x)=29466268) +1920 train 8.153466 (lr=7.4373e-05) (hash(x)=31407564) +1921 train 7.974712 (lr=7.4346e-05) (hash(x)=28372973) +1922 train 8.062938 (lr=7.4320e-05) (hash(x)=28620993) +1923 train 8.112796 (lr=7.4293e-05) (hash(x)=30736727) +1924 train 8.052246 (lr=7.4267e-05) (hash(x)=30370374) +1925 train 8.025405 (lr=7.4240e-05) (hash(x)=29935562) +1926 train 8.015068 (lr=7.4213e-05) (hash(x)=30528627) +1927 train 8.069846 (lr=7.4187e-05) (hash(x)=32616762) +1928 train 7.920131 (lr=7.4160e-05) (hash(x)=29150044) +1929 train 8.090812 (lr=7.4133e-05) (hash(x)=32861403) +1930 train 8.009574 (lr=7.4107e-05) (hash(x)=31053918) +1931 train 7.951589 (lr=7.4080e-05) (hash(x)=29358578) +1932 train 8.001826 (lr=7.4053e-05) (hash(x)=31521292) +1933 train 7.943472 (lr=7.4027e-05) (hash(x)=31218966) +1934 train 7.952846 (lr=7.4000e-05) (hash(x)=31811872) +1935 train 8.146747 (lr=7.3973e-05) (hash(x)=32201138) +1936 train 7.870992 (lr=7.3947e-05) (hash(x)=28631348) +1937 train 7.968262 (lr=7.3920e-05) (hash(x)=30545133) +1938 train 8.038999 (lr=7.3893e-05) (hash(x)=32136080) +1939 train 8.149827 (lr=7.3866e-05) (hash(x)=30041621) +1940 train 7.876837 (lr=7.3840e-05) (hash(x)=30537181) +1941 train 7.909687 (lr=7.3813e-05) (hash(x)=30371023) +1942 train 8.064418 (lr=7.3786e-05) (hash(x)=30734634) +1943 train 7.990982 (lr=7.3759e-05) (hash(x)=33683468) +1944 train 8.014204 (lr=7.3733e-05) (hash(x)=30472451) +1945 train 7.868238 (lr=7.3706e-05) (hash(x)=29809830) +1946 train 7.553423 (lr=7.3679e-05) (hash(x)=26077593) +1947 train 7.554437 (lr=7.3652e-05) (hash(x)=26837755) +1948 train 7.525189 (lr=7.3625e-05) (hash(x)=23910920) +1949 train 7.525575 (lr=7.3599e-05) (hash(x)=26084089) +1950 val loss 7.5078 +1950 val perplexity 1822.1135 +1950 train 7.688653 (lr=7.3572e-05) (hash(x)=26963533) +1951 train 7.533641 (lr=7.3545e-05) (hash(x)=27498125) +1952 train 7.712630 (lr=7.3518e-05) (hash(x)=29512508) +1953 train 7.977885 (lr=7.3491e-05) (hash(x)=34478395) +1954 train 7.591170 (lr=7.3464e-05) (hash(x)=25357046) +1955 train 7.425119 (lr=7.3438e-05) (hash(x)=22372507) +1956 train 7.384172 (lr=7.3411e-05) (hash(x)=24501779) +1957 train 7.463665 (lr=7.3384e-05) (hash(x)=25638879) +1958 train 7.293460 (lr=7.3357e-05) (hash(x)=24243109) +1959 train 7.225823 (lr=7.3330e-05) (hash(x)=25164318) +1960 train 7.434216 (lr=7.3303e-05) (hash(x)=24139533) +1961 train 7.447136 (lr=7.3276e-05) (hash(x)=27271900) +1962 train 7.301296 (lr=7.3249e-05) (hash(x)=24869232) +1963 train 7.490280 (lr=7.3222e-05) (hash(x)=26562947) +1964 train 7.359089 (lr=7.3195e-05) (hash(x)=26477326) +1965 train 7.434015 (lr=7.3169e-05) (hash(x)=24917192) +1966 train 7.227565 (lr=7.3142e-05) (hash(x)=23110147) +1967 train 7.356107 (lr=7.3115e-05) (hash(x)=25690221) +1968 train 7.795756 (lr=7.3088e-05) (hash(x)=26999273) +1969 train 7.446951 (lr=7.3061e-05) (hash(x)=24807841) +1970 train 7.325645 (lr=7.3034e-05) (hash(x)=23918831) +1971 train 7.255313 (lr=7.3007e-05) (hash(x)=21947305) +1972 train 7.326285 (lr=7.2980e-05) (hash(x)=22874486) +1973 train 7.298260 (lr=7.2953e-05) (hash(x)=22195089) +1974 train 7.384624 (lr=7.2926e-05) (hash(x)=25345359) +1975 train 7.514126 (lr=7.2899e-05) (hash(x)=29031550) +1976 train 7.481432 (lr=7.2872e-05) (hash(x)=29947423) +1977 train 7.624204 (lr=7.2845e-05) (hash(x)=29395823) +1978 train 7.463021 (lr=7.2818e-05) (hash(x)=26968216) +1979 train 7.493421 (lr=7.2791e-05) (hash(x)=26551589) +1980 train 7.452576 (lr=7.2763e-05) (hash(x)=25657210) +1981 train 7.403625 (lr=7.2736e-05) (hash(x)=23689487) +1982 train 7.521020 (lr=7.2709e-05) (hash(x)=25744240) +1983 train 7.490091 (lr=7.2682e-05) (hash(x)=24094093) +1984 train 7.201150 (lr=7.2655e-05) (hash(x)=21724872) +1985 train 7.224582 (lr=7.2628e-05) (hash(x)=24106453) +1986 train 7.285701 (lr=7.2601e-05) (hash(x)=25004577) +1987 train 7.335849 (lr=7.2574e-05) (hash(x)=23639076) +1988 train 7.633564 (lr=7.2547e-05) (hash(x)=29408797) +1989 train 7.281562 (lr=7.2520e-05) (hash(x)=25107314) +1990 train 9.921767 (lr=7.2492e-05) (hash(x)=49896019) +1991 train 11.458948 (lr=7.2465e-05) (hash(x)=61455960) +1992 train 11.336151 (lr=7.2438e-05) (hash(x)=63788199) +1993 train 11.473420 (lr=7.2411e-05) (hash(x)=63899424) +1994 train 11.156628 (lr=7.2384e-05) (hash(x)=66412689) +1995 train 10.783494 (lr=7.2357e-05) (hash(x)=65636572) +1996 train 10.975460 (lr=7.2330e-05) (hash(x)=69649789) +1997 train 10.726192 (lr=7.2302e-05) (hash(x)=71578682) +1998 train 9.733302 (lr=7.2275e-05) (hash(x)=58341730) +1999 train 9.705507 (lr=7.2248e-05) (hash(x)=61104710) +2000 val loss 7.8895 +2000 val perplexity 2669.1909 +2000 train 9.137214 (lr=7.2221e-05) (hash(x)=52865322) +2001 train 7.930107 (lr=7.2194e-05) (hash(x)=23633693) +2002 train 7.872548 (lr=7.2166e-05) (hash(x)=25297571) +2003 train 8.125849 (lr=7.2139e-05) (hash(x)=24123821) +2004 train 7.709621 (lr=7.2112e-05) (hash(x)=20161517) +2005 train 7.729897 (lr=7.2085e-05) (hash(x)=19919984) +2006 train 7.713218 (lr=7.2057e-05) (hash(x)=18626507) +2007 train 7.931180 (lr=7.2030e-05) (hash(x)=20881126) +2008 train 8.124745 (lr=7.2003e-05) (hash(x)=26261448) +2009 train 8.158652 (lr=7.1976e-05) (hash(x)=27528050) +2010 train 8.245661 (lr=7.1948e-05) (hash(x)=26692097) +2011 train 7.948402 (lr=7.1921e-05) (hash(x)=23209969) +2012 train 7.935871 (lr=7.1894e-05) (hash(x)=26083446) +2013 train 8.061312 (lr=7.1866e-05) (hash(x)=28426467) +2014 train 7.927114 (lr=7.1839e-05) (hash(x)=26158154) +2015 train 7.914685 (lr=7.1812e-05) (hash(x)=26920243) +2016 train 7.600462 (lr=7.1784e-05) (hash(x)=21365321) +2017 train 7.682968 (lr=7.1757e-05) (hash(x)=25730699) +2018 train 7.700447 (lr=7.1730e-05) (hash(x)=25177106) +2019 train 7.614825 (lr=7.1702e-05) (hash(x)=26127756) +2020 train 7.169022 (lr=7.1675e-05) (hash(x)=19770037) +2021 train 7.611279 (lr=7.1648e-05) (hash(x)=26479346) +2022 train 7.594403 (lr=7.1620e-05) (hash(x)=25967643) +2023 train 7.507532 (lr=7.1593e-05) (hash(x)=21970343) +2024 train 7.700414 (lr=7.1566e-05) (hash(x)=26449648) +2025 train 7.674234 (lr=7.1538e-05) (hash(x)=24874094) +2026 train 7.302056 (lr=7.1511e-05) (hash(x)=21399697) +2027 train 7.495318 (lr=7.1483e-05) (hash(x)=24097897) +2028 train 7.537164 (lr=7.1456e-05) (hash(x)=24453548) +2029 train 7.627000 (lr=7.1429e-05) (hash(x)=26692093) +2030 train 7.479730 (lr=7.1401e-05) (hash(x)=27217002) +2031 train 7.853931 (lr=7.1374e-05) (hash(x)=31676352) +2032 train 7.512065 (lr=7.1346e-05) (hash(x)=23396350) +2033 train 7.586199 (lr=7.1319e-05) (hash(x)=26245173) +2034 train 7.582504 (lr=7.1291e-05) (hash(x)=24821033) +2035 train 7.598387 (lr=7.1264e-05) (hash(x)=23908053) +2036 train 7.374969 (lr=7.1236e-05) (hash(x)=23469373) +2037 train 7.435905 (lr=7.1209e-05) (hash(x)=24102198) +2038 train 7.432377 (lr=7.1182e-05) (hash(x)=24712135) +2039 train 7.699411 (lr=7.1154e-05) (hash(x)=25600562) +2040 train 7.612355 (lr=7.1127e-05) (hash(x)=23193393) +2041 train 7.620882 (lr=7.1099e-05) (hash(x)=24776954) +2042 train 7.762058 (lr=7.1072e-05) (hash(x)=28066546) +2043 train 7.347878 (lr=7.1044e-05) (hash(x)=23549168) +2044 train 7.398865 (lr=7.1017e-05) (hash(x)=22681487) +2045 train 7.590604 (lr=7.0989e-05) (hash(x)=26663184) +2046 train 7.511789 (lr=7.0961e-05) (hash(x)=23320809) +2047 train 7.414745 (lr=7.0934e-05) (hash(x)=22022924) +2048 train 7.734169 (lr=7.0906e-05) (hash(x)=27960930) +2049 train 7.528861 (lr=7.0879e-05) (hash(x)=24899178) +2050 val loss 7.5454 +2050 val perplexity 1892.0503 +2050 train 7.458789 (lr=7.0851e-05) (hash(x)=24450711) +2051 train 7.362485 (lr=7.0824e-05) (hash(x)=23294980) +2052 train 7.317688 (lr=7.0796e-05) (hash(x)=23243665) +2053 train 7.125148 (lr=7.0769e-05) (hash(x)=21004461) +2054 train 7.501003 (lr=7.0741e-05) (hash(x)=24493583) +2055 train 7.387524 (lr=7.0713e-05) (hash(x)=22777085) +2056 train 7.367586 (lr=7.0686e-05) (hash(x)=25169889) +2057 train 7.982567 (lr=7.0658e-05) (hash(x)=28395880) +2058 train 7.868866 (lr=7.0631e-05) (hash(x)=29603726) +2059 train 7.564701 (lr=7.0603e-05) (hash(x)=26271115) +2060 train 7.550610 (lr=7.0575e-05) (hash(x)=25616212) +2061 train 7.649696 (lr=7.0548e-05) (hash(x)=26398325) +2062 train 7.379322 (lr=7.0520e-05) (hash(x)=23836586) +2063 train 7.254695 (lr=7.0492e-05) (hash(x)=21727744) +2064 train 7.474371 (lr=7.0465e-05) (hash(x)=25183195) +2065 train 7.627191 (lr=7.0437e-05) (hash(x)=27108132) +2066 train 7.281436 (lr=7.0409e-05) (hash(x)=20987812) +2067 train 7.590227 (lr=7.0382e-05) (hash(x)=22729318) +2068 train 7.427046 (lr=7.0354e-05) (hash(x)=23129709) +2069 train 7.938098 (lr=7.0326e-05) (hash(x)=32820084) +2070 train 7.978308 (lr=7.0299e-05) (hash(x)=33763489) +2071 train 7.425861 (lr=7.0271e-05) (hash(x)=20701998) +2072 train 7.668451 (lr=7.0243e-05) (hash(x)=27765988) +2073 train 7.418332 (lr=7.0215e-05) (hash(x)=24157446) +2074 train 7.330895 (lr=7.0188e-05) (hash(x)=22014978) +2075 train 7.814953 (lr=7.0160e-05) (hash(x)=27928398) +2076 train 7.679217 (lr=7.0132e-05) (hash(x)=27880142) +2077 train 7.981419 (lr=7.0105e-05) (hash(x)=34991795) +2078 train 7.570991 (lr=7.0077e-05) (hash(x)=25944128) +2079 train 7.276928 (lr=7.0049e-05) (hash(x)=20863982) +2080 train 7.678383 (lr=7.0021e-05) (hash(x)=28036097) +2081 train 7.726758 (lr=6.9994e-05) (hash(x)=25813615) +2082 train 7.154210 (lr=6.9966e-05) (hash(x)=22862316) +2083 train 7.234128 (lr=6.9938e-05) (hash(x)=22827054) +2084 train 7.309952 (lr=6.9910e-05) (hash(x)=23996531) +2085 train 7.425836 (lr=6.9882e-05) (hash(x)=25756087) +2086 train 7.464035 (lr=6.9855e-05) (hash(x)=23165889) +2087 train 7.626601 (lr=6.9827e-05) (hash(x)=25084926) +2088 train 7.435947 (lr=6.9799e-05) (hash(x)=26063862) +2089 train 7.513147 (lr=6.9771e-05) (hash(x)=27843638) +2090 train 7.780769 (lr=6.9743e-05) (hash(x)=27375554) +2091 train 7.516301 (lr=6.9716e-05) (hash(x)=25540961) +2092 train 7.298000 (lr=6.9688e-05) (hash(x)=22933785) +2093 train 7.465823 (lr=6.9660e-05) (hash(x)=23996956) +2094 train 7.151511 (lr=6.9632e-05) (hash(x)=22915854) +2095 train 7.407806 (lr=6.9604e-05) (hash(x)=24412897) +2096 train 7.444150 (lr=6.9576e-05) (hash(x)=25152336) +2097 train 7.759216 (lr=6.9548e-05) (hash(x)=29525589) +2098 train 7.569783 (lr=6.9521e-05) (hash(x)=26435656) +2099 train 7.452833 (lr=6.9493e-05) (hash(x)=26269869) +2100 val loss 7.4035 +2100 val perplexity 1641.7213 +2100 train 7.214059 (lr=6.9465e-05) (hash(x)=23856783) +2101 train 7.496129 (lr=6.9437e-05) (hash(x)=26039611) +2102 train 7.227283 (lr=6.9409e-05) (hash(x)=25048861) +2103 train 7.379979 (lr=6.9381e-05) (hash(x)=25434913) +2104 train 7.525540 (lr=6.9353e-05) (hash(x)=24203891) +2105 train 7.431954 (lr=6.9325e-05) (hash(x)=26016998) +2106 train 7.486635 (lr=6.9297e-05) (hash(x)=23986767) +2107 train 7.418678 (lr=6.9269e-05) (hash(x)=25157653) +2108 train 7.558234 (lr=6.9241e-05) (hash(x)=30193751) +2109 train 7.401525 (lr=6.9214e-05) (hash(x)=22630574) +2110 train 7.300399 (lr=6.9186e-05) (hash(x)=23475467) +2111 train 7.572607 (lr=6.9158e-05) (hash(x)=26302544) +2112 train 7.365524 (lr=6.9130e-05) (hash(x)=21276592) +2113 train 7.607825 (lr=6.9102e-05) (hash(x)=27566393) +2114 train 7.330783 (lr=6.9074e-05) (hash(x)=25028015) +2115 train 7.144746 (lr=6.9046e-05) (hash(x)=22010703) +2116 train 7.446876 (lr=6.9018e-05) (hash(x)=23711709) +2117 train 7.485370 (lr=6.8990e-05) (hash(x)=26105026) +2118 train 7.919989 (lr=6.8962e-05) (hash(x)=34433894) +2119 train 7.975127 (lr=6.8934e-05) (hash(x)=34976197) +2120 train 7.486873 (lr=6.8906e-05) (hash(x)=27690727) +2121 train 7.315488 (lr=6.8878e-05) (hash(x)=24368234) +2122 train 7.312982 (lr=6.8850e-05) (hash(x)=25095726) +2123 train 7.511717 (lr=6.8822e-05) (hash(x)=28248301) +2124 train 7.224530 (lr=6.8794e-05) (hash(x)=23322302) +2125 train 7.683571 (lr=6.8766e-05) (hash(x)=26416200) +2126 train 7.382143 (lr=6.8738e-05) (hash(x)=26577567) +2127 train 7.399791 (lr=6.8710e-05) (hash(x)=23870805) +2128 train 7.346454 (lr=6.8681e-05) (hash(x)=25440544) +2129 train 7.488043 (lr=6.8653e-05) (hash(x)=25795021) +2130 train 7.321902 (lr=6.8625e-05) (hash(x)=20896402) +2131 train 7.318401 (lr=6.8597e-05) (hash(x)=24457252) +2132 train 7.455615 (lr=6.8569e-05) (hash(x)=25926760) +2133 train 7.302074 (lr=6.8541e-05) (hash(x)=23503725) +2134 train 7.864351 (lr=6.8513e-05) (hash(x)=28728828) +2135 train 7.386191 (lr=6.8485e-05) (hash(x)=25041103) +2136 train 7.398715 (lr=6.8457e-05) (hash(x)=22863770) +2137 train 7.253308 (lr=6.8429e-05) (hash(x)=23037755) +2138 train 7.475159 (lr=6.8401e-05) (hash(x)=25848413) +2139 train 7.531835 (lr=6.8372e-05) (hash(x)=25998487) +2140 train 7.391769 (lr=6.8344e-05) (hash(x)=22754440) +2141 train 7.644990 (lr=6.8316e-05) (hash(x)=27705382) +2142 train 7.662917 (lr=6.8288e-05) (hash(x)=27629095) +2143 train 7.506051 (lr=6.8260e-05) (hash(x)=26041745) +2144 train 7.316436 (lr=6.8232e-05) (hash(x)=21909712) +2145 train 7.477670 (lr=6.8204e-05) (hash(x)=24353905) +2146 train 7.417520 (lr=6.8176e-05) (hash(x)=24482587) +2147 train 7.512314 (lr=6.8147e-05) (hash(x)=27249810) +2148 train 7.670751 (lr=6.8119e-05) (hash(x)=26709938) +2149 train 7.320272 (lr=6.8091e-05) (hash(x)=23831457) +2150 val loss 7.4291 +2150 val perplexity 1684.3289 +2150 train 7.673570 (lr=6.8063e-05) (hash(x)=29776243) +2151 train 7.187873 (lr=6.8035e-05) (hash(x)=24068619) +2152 train 7.387456 (lr=6.8006e-05) (hash(x)=22208671) +2153 train 7.545961 (lr=6.7978e-05) (hash(x)=26680905) +2154 train 7.389132 (lr=6.7950e-05) (hash(x)=23567808) +2155 train 7.616122 (lr=6.7922e-05) (hash(x)=26359528) +2156 train 7.437459 (lr=6.7894e-05) (hash(x)=23787652) +2157 train 7.730381 (lr=6.7865e-05) (hash(x)=28347177) +2158 train 7.386163 (lr=6.7837e-05) (hash(x)=25266519) +2159 train 7.288136 (lr=6.7809e-05) (hash(x)=25441262) +2160 train 7.255972 (lr=6.7781e-05) (hash(x)=23959943) +2161 train 7.493693 (lr=6.7752e-05) (hash(x)=27888093) +2162 train 7.400236 (lr=6.7724e-05) (hash(x)=25547833) +2163 train 7.339013 (lr=6.7696e-05) (hash(x)=24413659) +2164 train 8.855608 (lr=6.7668e-05) (hash(x)=34397626) +2165 train 7.290115 (lr=6.7639e-05) (hash(x)=21159323) +2166 train 7.460950 (lr=6.7611e-05) (hash(x)=25360269) +2167 train 7.524681 (lr=6.7583e-05) (hash(x)=29181867) +2168 train 7.343953 (lr=6.7555e-05) (hash(x)=22501613) +2169 train 7.442438 (lr=6.7526e-05) (hash(x)=26469077) +2170 train 7.392007 (lr=6.7498e-05) (hash(x)=26665118) +2171 train 8.040509 (lr=6.7470e-05) (hash(x)=31551575) +2172 train 7.351474 (lr=6.7441e-05) (hash(x)=24803935) +2173 train 7.242291 (lr=6.7413e-05) (hash(x)=20896465) +2174 train 7.753693 (lr=6.7385e-05) (hash(x)=25702284) +2175 train 7.693785 (lr=6.7356e-05) (hash(x)=27093757) +2176 train 7.479699 (lr=6.7328e-05) (hash(x)=26024255) +2177 train 7.604610 (lr=6.7300e-05) (hash(x)=26443521) +2178 train 7.536502 (lr=6.7272e-05) (hash(x)=25478467) +2179 train 7.393929 (lr=6.7243e-05) (hash(x)=23624298) +2180 train 7.474151 (lr=6.7215e-05) (hash(x)=27304178) +2181 train 7.222245 (lr=6.7186e-05) (hash(x)=23016570) +2182 train 7.169329 (lr=6.7158e-05) (hash(x)=21073756) +2183 train 7.324128 (lr=6.7130e-05) (hash(x)=25150275) +2184 train 7.105211 (lr=6.7101e-05) (hash(x)=21004187) +2185 train 7.350910 (lr=6.7073e-05) (hash(x)=25876062) +2186 train 7.292341 (lr=6.7045e-05) (hash(x)=24221275) +2187 train 7.606780 (lr=6.7016e-05) (hash(x)=26239886) +2188 train 7.289304 (lr=6.6988e-05) (hash(x)=23299261) +2189 train 7.758327 (lr=6.6959e-05) (hash(x)=31024703) +2190 train 7.858157 (lr=6.6931e-05) (hash(x)=30084774) +2191 train 8.195720 (lr=6.6903e-05) (hash(x)=33457102) +2192 train 7.326437 (lr=6.6874e-05) (hash(x)=22423723) +2193 train 7.320102 (lr=6.6846e-05) (hash(x)=21989055) +2194 train 7.355392 (lr=6.6817e-05) (hash(x)=23286499) +2195 train 7.285322 (lr=6.6789e-05) (hash(x)=17499738) +2196 train 7.363481 (lr=6.6761e-05) (hash(x)=25329557) +2197 train 7.247552 (lr=6.6732e-05) (hash(x)=24195578) +2198 train 7.494475 (lr=6.6704e-05) (hash(x)=26646383) +2199 train 7.360439 (lr=6.6675e-05) (hash(x)=25755322) +2200 val loss 7.3831 +2200 val perplexity 1608.6078 +2200 train 7.432649 (lr=6.6647e-05) (hash(x)=27592223) +2201 train 7.613643 (lr=6.6618e-05) (hash(x)=26164625) +2202 train 7.455805 (lr=6.6590e-05) (hash(x)=21856341) +2203 train 7.340684 (lr=6.6561e-05) (hash(x)=23722795) +2204 train 7.414586 (lr=6.6533e-05) (hash(x)=25409645) +2205 train 7.358551 (lr=6.6505e-05) (hash(x)=23415339) +2206 train 7.334785 (lr=6.6476e-05) (hash(x)=24147928) +2207 train 7.240528 (lr=6.6448e-05) (hash(x)=23630794) +2208 train 7.343484 (lr=6.6419e-05) (hash(x)=27361452) +2209 train 7.365655 (lr=6.6391e-05) (hash(x)=25632158) +2210 train 7.203681 (lr=6.6362e-05) (hash(x)=21159789) +2211 train 7.318504 (lr=6.6334e-05) (hash(x)=23374168) +2212 train 7.378926 (lr=6.6305e-05) (hash(x)=24844739) +2213 train 7.295161 (lr=6.6277e-05) (hash(x)=23461285) +2214 train 7.342472 (lr=6.6248e-05) (hash(x)=27958481) +2215 train 7.272435 (lr=6.6220e-05) (hash(x)=25167987) +2216 train 7.438210 (lr=6.6191e-05) (hash(x)=22873204) +2217 train 8.064265 (lr=6.6163e-05) (hash(x)=31038116) +2218 train 7.474613 (lr=6.6134e-05) (hash(x)=28883155) +2219 train 7.398502 (lr=6.6105e-05) (hash(x)=30941010) +2220 train 7.402516 (lr=6.6077e-05) (hash(x)=24947521) +2221 train 7.436206 (lr=6.6048e-05) (hash(x)=22703293) +2222 train 7.359938 (lr=6.6020e-05) (hash(x)=23976007) +2223 train 7.271332 (lr=6.5991e-05) (hash(x)=24043224) +2224 train 7.215761 (lr=6.5963e-05) (hash(x)=23981093) +2225 train 7.394746 (lr=6.5934e-05) (hash(x)=26445994) +2226 train 7.690964 (lr=6.5906e-05) (hash(x)=27252393) +2227 train 7.644478 (lr=6.5877e-05) (hash(x)=29736627) +2228 train 7.594713 (lr=6.5848e-05) (hash(x)=24698933) +2229 train 7.249879 (lr=6.5820e-05) (hash(x)=24357840) +2230 train 7.386963 (lr=6.5791e-05) (hash(x)=25384498) +2231 train 7.547955 (lr=6.5763e-05) (hash(x)=24665411) +2232 train 7.395818 (lr=6.5734e-05) (hash(x)=24646352) +2233 train 7.388283 (lr=6.5705e-05) (hash(x)=25670741) +2234 train 7.447453 (lr=6.5677e-05) (hash(x)=26648242) +2235 train 7.669882 (lr=6.5648e-05) (hash(x)=27916043) +2236 train 7.435269 (lr=6.5620e-05) (hash(x)=25963100) +2237 train 7.511296 (lr=6.5591e-05) (hash(x)=27357379) +2238 train 7.307805 (lr=6.5562e-05) (hash(x)=21852360) +2239 train 7.191928 (lr=6.5534e-05) (hash(x)=17321657) +2240 train 7.187386 (lr=6.5505e-05) (hash(x)=18446645) +2241 train 6.994118 (lr=6.5476e-05) (hash(x)=17550988) +2242 train 7.382514 (lr=6.5448e-05) (hash(x)=27052347) +2243 train 7.239145 (lr=6.5419e-05) (hash(x)=23829833) +2244 train 7.474399 (lr=6.5390e-05) (hash(x)=27267264) +2245 train 7.719350 (lr=6.5362e-05) (hash(x)=24673611) +2246 train 7.580342 (lr=6.5333e-05) (hash(x)=25248507) +2247 train 7.830274 (lr=6.5304e-05) (hash(x)=27932591) +2248 train 7.685134 (lr=6.5276e-05) (hash(x)=26078877) +2249 train 7.738717 (lr=6.5247e-05) (hash(x)=26067367) +2250 val loss 7.4096 +2250 val perplexity 1651.7211 +2250 train 7.793739 (lr=6.5218e-05) (hash(x)=29143527) +2251 train 7.805459 (lr=6.5190e-05) (hash(x)=28206079) +2252 train 8.415320 (lr=6.5161e-05) (hash(x)=28894494) +2253 train 7.791904 (lr=6.5132e-05) (hash(x)=27977422) +2254 train 7.418730 (lr=6.5104e-05) (hash(x)=26446420) +2255 train 7.686765 (lr=6.5075e-05) (hash(x)=29447954) +2256 train 7.450847 (lr=6.5046e-05) (hash(x)=22181789) +2257 train 7.462616 (lr=6.5018e-05) (hash(x)=24976337) +2258 train 7.415416 (lr=6.4989e-05) (hash(x)=23277532) +2259 train 7.541521 (lr=6.4960e-05) (hash(x)=25935364) +2260 train 7.618942 (lr=6.4931e-05) (hash(x)=26988889) +2261 train 7.438663 (lr=6.4903e-05) (hash(x)=26887303) +2262 train 7.394279 (lr=6.4874e-05) (hash(x)=25021426) +2263 train 7.306453 (lr=6.4845e-05) (hash(x)=24621816) +2264 train 7.214792 (lr=6.4816e-05) (hash(x)=22132007) +2265 train 7.149776 (lr=6.4788e-05) (hash(x)=22648602) +2266 train 7.454079 (lr=6.4759e-05) (hash(x)=23132242) +2267 train 7.488904 (lr=6.4730e-05) (hash(x)=24070405) +2268 train 7.094957 (lr=6.4701e-05) (hash(x)=21412906) +2269 train 7.787141 (lr=6.4673e-05) (hash(x)=27547292) +2270 train 7.539707 (lr=6.4644e-05) (hash(x)=27740500) +2271 train 7.273145 (lr=6.4615e-05) (hash(x)=24682294) +2272 train 7.721769 (lr=6.4586e-05) (hash(x)=27969424) +2273 train 7.406244 (lr=6.4558e-05) (hash(x)=22172182) +2274 train 7.401733 (lr=6.4529e-05) (hash(x)=26485905) +2275 train 7.264786 (lr=6.4500e-05) (hash(x)=24050209) +2276 train 7.422550 (lr=6.4471e-05) (hash(x)=28802650) +2277 train 7.224575 (lr=6.4442e-05) (hash(x)=23644616) +2278 train 7.383304 (lr=6.4414e-05) (hash(x)=25409768) +2279 train 7.563138 (lr=6.4385e-05) (hash(x)=28057095) +2280 train 7.976818 (lr=6.4356e-05) (hash(x)=31689723) +2281 train 7.189786 (lr=6.4327e-05) (hash(x)=22252427) +2282 train 7.445633 (lr=6.4298e-05) (hash(x)=24142092) +2283 train 7.378568 (lr=6.4270e-05) (hash(x)=22523232) +2284 train 7.540256 (lr=6.4241e-05) (hash(x)=26017294) +2285 train 7.412307 (lr=6.4212e-05) (hash(x)=25025388) +2286 train 7.218381 (lr=6.4183e-05) (hash(x)=23819479) +2287 train 7.365240 (lr=6.4154e-05) (hash(x)=24547536) +2288 train 7.145947 (lr=6.4125e-05) (hash(x)=22622789) +2289 train 7.138055 (lr=6.4097e-05) (hash(x)=23874051) +2290 train 7.445759 (lr=6.4068e-05) (hash(x)=25015641) +2291 train 7.371028 (lr=6.4039e-05) (hash(x)=24978712) +2292 train 7.443379 (lr=6.4010e-05) (hash(x)=25311986) +2293 train 7.199098 (lr=6.3981e-05) (hash(x)=24298295) +2294 train 7.319970 (lr=6.3952e-05) (hash(x)=26481527) +2295 train 7.055648 (lr=6.3923e-05) (hash(x)=18987545) +2296 train 7.251954 (lr=6.3895e-05) (hash(x)=24617990) +2297 train 7.271871 (lr=6.3866e-05) (hash(x)=23903200) +2298 train 7.584883 (lr=6.3837e-05) (hash(x)=26278697) +2299 train 7.358535 (lr=6.3808e-05) (hash(x)=24092784) +2300 val loss 7.3707 +2300 val perplexity 1588.6976 +2300 train 7.320579 (lr=6.3779e-05) (hash(x)=22894919) +2301 train 7.386736 (lr=6.3750e-05) (hash(x)=24253964) +2302 train 7.314235 (lr=6.3721e-05) (hash(x)=23750610) +2303 train 7.349697 (lr=6.3692e-05) (hash(x)=26745063) +2304 train 7.146497 (lr=6.3663e-05) (hash(x)=21407001) +2305 train 7.532796 (lr=6.3635e-05) (hash(x)=26680082) +2306 train 7.428951 (lr=6.3606e-05) (hash(x)=26722122) +2307 train 7.282853 (lr=6.3577e-05) (hash(x)=22539112) +2308 train 7.051393 (lr=6.3548e-05) (hash(x)=19927356) +2309 train 7.195471 (lr=6.3519e-05) (hash(x)=21431267) +2310 train 7.128865 (lr=6.3490e-05) (hash(x)=21073487) +2311 train 7.155914 (lr=6.3461e-05) (hash(x)=21447406) +2312 train 7.154523 (lr=6.3432e-05) (hash(x)=22667253) +2313 train 7.130226 (lr=6.3403e-05) (hash(x)=20849089) +2314 train 7.140160 (lr=6.3374e-05) (hash(x)=19168351) +2315 train 7.159378 (lr=6.3345e-05) (hash(x)=21082139) +2316 train 7.125011 (lr=6.3316e-05) (hash(x)=21493530) +2317 train 7.080222 (lr=6.3287e-05) (hash(x)=19506447) +2318 train 7.201966 (lr=6.3259e-05) (hash(x)=23128797) +2319 train 7.248107 (lr=6.3230e-05) (hash(x)=24650655) +2320 train 7.051160 (lr=6.3201e-05) (hash(x)=21833080) +2321 train 7.576496 (lr=6.3172e-05) (hash(x)=26355512) +2322 train 7.717639 (lr=6.3143e-05) (hash(x)=26746363) +2323 train 7.189575 (lr=6.3114e-05) (hash(x)=22130721) +2324 train 7.552524 (lr=6.3085e-05) (hash(x)=28301752) +2325 train 7.393242 (lr=6.3056e-05) (hash(x)=26444359) +2326 train 7.734894 (lr=6.3027e-05) (hash(x)=24836130) +2327 train 8.156684 (lr=6.2998e-05) (hash(x)=26519976) +2328 train 9.696072 (lr=6.2969e-05) (hash(x)=35558906) +2329 train 7.819241 (lr=6.2940e-05) (hash(x)=30877729) +2330 train 7.601140 (lr=6.2911e-05) (hash(x)=28028485) +2331 train 7.740665 (lr=6.2882e-05) (hash(x)=25582440) +2332 train 8.116214 (lr=6.2853e-05) (hash(x)=29402491) +2333 train 7.409257 (lr=6.2824e-05) (hash(x)=25200284) +2334 train 7.460115 (lr=6.2795e-05) (hash(x)=26288480) +2335 train 7.226735 (lr=6.2766e-05) (hash(x)=20106514) +2336 train 7.208194 (lr=6.2737e-05) (hash(x)=22522123) +2337 train 7.250950 (lr=6.2708e-05) (hash(x)=23362041) +2338 train 7.345647 (lr=6.2679e-05) (hash(x)=26003099) +2339 train 7.335033 (lr=6.2650e-05) (hash(x)=25695510) +2340 train 7.343344 (lr=6.2621e-05) (hash(x)=27225904) +2341 train 7.121616 (lr=6.2592e-05) (hash(x)=21573008) +2342 train 7.524814 (lr=6.2563e-05) (hash(x)=21386628) +2343 train 7.316766 (lr=6.2534e-05) (hash(x)=20117808) +2344 train 7.463954 (lr=6.2505e-05) (hash(x)=21592790) +2345 train 7.373927 (lr=6.2476e-05) (hash(x)=19909192) +2346 train 7.454240 (lr=6.2447e-05) (hash(x)=22529262) +2347 train 7.524382 (lr=6.2417e-05) (hash(x)=24501900) +2348 train 7.291490 (lr=6.2388e-05) (hash(x)=25912171) +2349 train 7.403684 (lr=6.2359e-05) (hash(x)=25606665) +2350 val loss 7.3772 +2350 val perplexity 1599.0620 +2350 train 7.341349 (lr=6.2330e-05) (hash(x)=24487351) +2351 train 7.566792 (lr=6.2301e-05) (hash(x)=25510334) +2352 train 7.472572 (lr=6.2272e-05) (hash(x)=25357989) +2353 train 7.096241 (lr=6.2243e-05) (hash(x)=24656801) +2354 train 7.198749 (lr=6.2214e-05) (hash(x)=23312772) +2355 train 7.070610 (lr=6.2185e-05) (hash(x)=22099158) +2356 train 7.120533 (lr=6.2156e-05) (hash(x)=26507898) +2357 train 7.444738 (lr=6.2127e-05) (hash(x)=28351614) +2358 train 7.472775 (lr=6.2098e-05) (hash(x)=27489567) +2359 train 7.455833 (lr=6.2069e-05) (hash(x)=25749120) +2360 train 7.801441 (lr=6.2040e-05) (hash(x)=31711338) +2361 train 7.900759 (lr=6.2010e-05) (hash(x)=29645018) +2362 train 7.923193 (lr=6.1981e-05) (hash(x)=29713268) +2363 train 7.091573 (lr=6.1952e-05) (hash(x)=21720691) +2364 train 7.215450 (lr=6.1923e-05) (hash(x)=24316633) +2365 train 7.151794 (lr=6.1894e-05) (hash(x)=21597124) +2366 train 7.194368 (lr=6.1865e-05) (hash(x)=22520345) +2367 train 7.199522 (lr=6.1836e-05) (hash(x)=24357241) +2368 train 7.336904 (lr=6.1807e-05) (hash(x)=24085450) +2369 train 7.263498 (lr=6.1778e-05) (hash(x)=25136495) +2370 train 7.717093 (lr=6.1749e-05) (hash(x)=26073986) +2371 train 7.683250 (lr=6.1719e-05) (hash(x)=28911272) +2372 train 7.425050 (lr=6.1690e-05) (hash(x)=26667356) +2373 train 7.262192 (lr=6.1661e-05) (hash(x)=25225894) +2374 train 7.293796 (lr=6.1632e-05) (hash(x)=24404081) +2375 train 7.373603 (lr=6.1603e-05) (hash(x)=25584945) +2376 train 7.207318 (lr=6.1574e-05) (hash(x)=23831571) +2377 train 7.236287 (lr=6.1545e-05) (hash(x)=23521916) +2378 train 7.258869 (lr=6.1515e-05) (hash(x)=25318634) +2379 train 7.097867 (lr=6.1486e-05) (hash(x)=21847287) +2380 train 7.493997 (lr=6.1457e-05) (hash(x)=23877060) +2381 train 7.277055 (lr=6.1428e-05) (hash(x)=24069020) +2382 train 7.072619 (lr=6.1399e-05) (hash(x)=21724290) +2383 train 7.317764 (lr=6.1370e-05) (hash(x)=25198897) +2384 train 7.192906 (lr=6.1341e-05) (hash(x)=24109958) +2385 train 7.053838 (lr=6.1311e-05) (hash(x)=20122390) +2386 train 7.364433 (lr=6.1282e-05) (hash(x)=24062305) +2387 train 7.118276 (lr=6.1253e-05) (hash(x)=22436833) +2388 train 7.418575 (lr=6.1224e-05) (hash(x)=26013214) +2389 train 7.743938 (lr=6.1195e-05) (hash(x)=27691436) +2390 train 7.891489 (lr=6.1166e-05) (hash(x)=30802878) +2391 train 7.067360 (lr=6.1136e-05) (hash(x)=23475891) +2392 train 7.074794 (lr=6.1107e-05) (hash(x)=23118133) +2393 train 6.984413 (lr=6.1078e-05) (hash(x)=21469159) +2394 train 7.348535 (lr=6.1049e-05) (hash(x)=26444484) +2395 train 7.200738 (lr=6.1020e-05) (hash(x)=25083992) +2396 train 7.601744 (lr=6.0990e-05) (hash(x)=23461229) +2397 train 7.439319 (lr=6.0961e-05) (hash(x)=20441653) +2398 train 7.496942 (lr=6.0932e-05) (hash(x)=28024211) +2399 train 7.354591 (lr=6.0903e-05) (hash(x)=23644804) +2400 val loss 7.3585 +2400 val perplexity 1569.4034 +2400 train 7.167804 (lr=6.0874e-05) (hash(x)=26685301) +2401 train 7.002786 (lr=6.0844e-05) (hash(x)=20820913) +2402 train 7.180539 (lr=6.0815e-05) (hash(x)=22178190) +2403 train 7.788939 (lr=6.0786e-05) (hash(x)=31377168) +2404 train 7.969972 (lr=6.0757e-05) (hash(x)=33795307) +2405 train 8.134722 (lr=6.0728e-05) (hash(x)=34450341) +2406 train 7.316260 (lr=6.0698e-05) (hash(x)=25834183) +2407 train 7.528852 (lr=6.0669e-05) (hash(x)=25629584) +2408 train 7.313785 (lr=6.0640e-05) (hash(x)=25080123) +2409 train 7.180015 (lr=6.0611e-05) (hash(x)=21975628) +2410 train 7.732230 (lr=6.0582e-05) (hash(x)=27430197) +2411 train 7.910317 (lr=6.0552e-05) (hash(x)=29285135) +2412 train 7.668327 (lr=6.0523e-05) (hash(x)=24640105) +2413 train 7.672191 (lr=6.0494e-05) (hash(x)=29628864) +2414 train 7.841314 (lr=6.0465e-05) (hash(x)=30096444) +2415 train 7.727530 (lr=6.0435e-05) (hash(x)=29797280) +2416 train 7.093266 (lr=6.0406e-05) (hash(x)=22686143) +2417 train 7.672148 (lr=6.0377e-05) (hash(x)=28346842) +2418 train 7.648798 (lr=6.0348e-05) (hash(x)=28167937) +2419 train 7.875957 (lr=6.0318e-05) (hash(x)=33122326) +2420 train 7.904889 (lr=6.0289e-05) (hash(x)=33044913) +2421 train 7.724910 (lr=6.0260e-05) (hash(x)=31250981) +2422 train 7.963220 (lr=6.0231e-05) (hash(x)=29827111) +2423 train 7.875791 (lr=6.0201e-05) (hash(x)=30026394) +2424 train 8.064844 (lr=6.0172e-05) (hash(x)=26998238) +2425 train 8.066844 (lr=6.0143e-05) (hash(x)=24850684) +2426 train 8.162618 (lr=6.0114e-05) (hash(x)=36659853) +2427 train 8.106685 (lr=6.0084e-05) (hash(x)=34353164) +2428 train 7.449216 (lr=6.0055e-05) (hash(x)=23630644) +2429 train 7.315761 (lr=6.0026e-05) (hash(x)=24528186) +2430 train 7.210274 (lr=5.9997e-05) (hash(x)=22665222) +2431 train 7.344448 (lr=5.9967e-05) (hash(x)=26594177) +2432 train 7.713892 (lr=5.9938e-05) (hash(x)=29300546) +2433 train 7.170033 (lr=5.9909e-05) (hash(x)=21331715) +2434 train 7.416790 (lr=5.9879e-05) (hash(x)=26290885) +2435 train 7.341986 (lr=5.9850e-05) (hash(x)=25554738) +2436 train 7.589548 (lr=5.9821e-05) (hash(x)=26744311) +2437 train 7.535085 (lr=5.9792e-05) (hash(x)=26872344) +2438 train 7.566888 (lr=5.9762e-05) (hash(x)=27636081) +2439 train 7.387322 (lr=5.9733e-05) (hash(x)=23766256) +2440 train 7.514888 (lr=5.9704e-05) (hash(x)=24434438) +2441 train 7.274297 (lr=5.9674e-05) (hash(x)=22992618) +2442 train 7.157644 (lr=5.9645e-05) (hash(x)=22393467) +2443 train 7.441916 (lr=5.9616e-05) (hash(x)=26853444) +2444 train 7.354985 (lr=5.9587e-05) (hash(x)=25101020) +2445 train 7.279753 (lr=5.9557e-05) (hash(x)=24705456) +2446 train 7.558359 (lr=5.9528e-05) (hash(x)=26798611) +2447 train 7.213109 (lr=5.9499e-05) (hash(x)=24250150) +2448 train 7.295018 (lr=5.9469e-05) (hash(x)=24494331) +2449 train 7.308960 (lr=5.9440e-05) (hash(x)=27579257) +2450 val loss 7.3520 +2450 val perplexity 1559.3444 +2450 train 7.109311 (lr=5.9411e-05) (hash(x)=22377407) +2451 train 7.392530 (lr=5.9381e-05) (hash(x)=26289588) +2452 train 7.310822 (lr=5.9352e-05) (hash(x)=25871900) +2453 train 7.198655 (lr=5.9323e-05) (hash(x)=23437197) +2454 train 7.475731 (lr=5.9294e-05) (hash(x)=23557786) +2455 train 7.343980 (lr=5.9264e-05) (hash(x)=26108817) +2456 train 7.308820 (lr=5.9235e-05) (hash(x)=26440482) +2457 train 7.311571 (lr=5.9206e-05) (hash(x)=24583191) +2458 train 7.295736 (lr=5.9176e-05) (hash(x)=23756440) +2459 train 7.196327 (lr=5.9147e-05) (hash(x)=23814987) +2460 train 7.548543 (lr=5.9118e-05) (hash(x)=28508433) +2461 train 7.220433 (lr=5.9088e-05) (hash(x)=25692442) +2462 train 7.214851 (lr=5.9059e-05) (hash(x)=24699197) +2463 train 6.911469 (lr=5.9030e-05) (hash(x)=18582688) +2464 train 7.225690 (lr=5.9000e-05) (hash(x)=23266625) +2465 train 7.530269 (lr=5.8971e-05) (hash(x)=26565489) +2466 train 7.051958 (lr=5.8942e-05) (hash(x)=21686599) +2467 train 7.318019 (lr=5.8912e-05) (hash(x)=25558792) +2468 train 7.110492 (lr=5.8883e-05) (hash(x)=25110035) +2469 train 7.461235 (lr=5.8854e-05) (hash(x)=26263661) +2470 train 7.203532 (lr=5.8824e-05) (hash(x)=22282189) +2471 train 7.162306 (lr=5.8795e-05) (hash(x)=23272705) +2472 train 7.275609 (lr=5.8766e-05) (hash(x)=25300067) +2473 train 7.474448 (lr=5.8736e-05) (hash(x)=26802369) +2474 train 7.152376 (lr=5.8707e-05) (hash(x)=24646471) +2475 train 7.144839 (lr=5.8677e-05) (hash(x)=24709241) +2476 train 7.221771 (lr=5.8648e-05) (hash(x)=26747197) +2477 train 7.280963 (lr=5.8619e-05) (hash(x)=25201108) +2478 train 7.380435 (lr=5.8589e-05) (hash(x)=24962427) +2479 train 7.218111 (lr=5.8560e-05) (hash(x)=24793412) +2480 train 7.279108 (lr=5.8531e-05) (hash(x)=24452301) +2481 train 7.301357 (lr=5.8501e-05) (hash(x)=25177251) +2482 train 7.198413 (lr=5.8472e-05) (hash(x)=25801499) +2483 train 7.402544 (lr=5.8443e-05) (hash(x)=27256707) +2484 train 7.651717 (lr=5.8413e-05) (hash(x)=25303237) +2485 train 7.243488 (lr=5.8384e-05) (hash(x)=21641481) +2486 train 7.221061 (lr=5.8354e-05) (hash(x)=23818831) +2487 train 6.994219 (lr=5.8325e-05) (hash(x)=19280989) +2488 train 7.334148 (lr=5.8296e-05) (hash(x)=24075167) +2489 train 7.360981 (lr=5.8266e-05) (hash(x)=26651546) +2490 train 7.291838 (lr=5.8237e-05) (hash(x)=25367186) +2491 train 7.243894 (lr=5.8208e-05) (hash(x)=26508642) +2492 train 7.328351 (lr=5.8178e-05) (hash(x)=25294182) +2493 train 7.240640 (lr=5.8149e-05) (hash(x)=23916886) +2494 train 7.119045 (lr=5.8119e-05) (hash(x)=21189910) +2495 train 7.206516 (lr=5.8090e-05) (hash(x)=22751150) +2496 train 7.592556 (lr=5.8061e-05) (hash(x)=26608502) +2497 train 7.982599 (lr=5.8031e-05) (hash(x)=25372010) +2498 train 7.275246 (lr=5.8002e-05) (hash(x)=22006251) +2499 train 7.225408 (lr=5.7973e-05) (hash(x)=23880160) +2500 val loss 7.3627 +2500 val perplexity 1576.1133 +2500 train 7.175320 (lr=5.7943e-05) (hash(x)=23225337) +2501 train 7.323326 (lr=5.7914e-05) (hash(x)=24932950) +2502 train 7.079038 (lr=5.7884e-05) (hash(x)=20022340) +2503 train 7.456829 (lr=5.7855e-05) (hash(x)=23537942) +2504 train 7.337195 (lr=5.7826e-05) (hash(x)=24884288) +2505 train 7.019737 (lr=5.7796e-05) (hash(x)=21296580) +2506 train 7.230985 (lr=5.7767e-05) (hash(x)=23001455) +2507 train 7.524774 (lr=5.7737e-05) (hash(x)=26975313) +2508 train 7.510713 (lr=5.7708e-05) (hash(x)=26029962) +2509 train 7.218516 (lr=5.7679e-05) (hash(x)=24302204) +2510 train 6.953238 (lr=5.7649e-05) (hash(x)=22997203) +2511 train 7.099550 (lr=5.7620e-05) (hash(x)=23748375) +2512 train 7.284031 (lr=5.7590e-05) (hash(x)=24453191) +2513 train 6.982556 (lr=5.7561e-05) (hash(x)=22026776) +2514 train 7.108831 (lr=5.7532e-05) (hash(x)=19934168) +2515 train 7.382019 (lr=5.7502e-05) (hash(x)=25541754) +2516 train 7.704679 (lr=5.7473e-05) (hash(x)=26604471) +2517 train 7.695575 (lr=5.7443e-05) (hash(x)=27900386) +2518 train 7.623473 (lr=5.7414e-05) (hash(x)=26403431) +2519 train 7.652719 (lr=5.7385e-05) (hash(x)=27413825) +2520 train 7.737082 (lr=5.7355e-05) (hash(x)=28332637) +2521 train 7.550247 (lr=5.7326e-05) (hash(x)=27223027) +2522 train 7.554977 (lr=5.7296e-05) (hash(x)=23843387) +2523 train 7.560004 (lr=5.7267e-05) (hash(x)=27075951) +2524 train 7.741774 (lr=5.7237e-05) (hash(x)=29300154) +2525 train 7.395977 (lr=5.7208e-05) (hash(x)=28100582) +2526 train 7.476713 (lr=5.7179e-05) (hash(x)=28051084) +2527 train 7.198694 (lr=5.7149e-05) (hash(x)=21682445) +2528 train 7.388038 (lr=5.7120e-05) (hash(x)=24062589) +2529 train 7.581800 (lr=5.7090e-05) (hash(x)=29616079) +2530 train 7.486112 (lr=5.7061e-05) (hash(x)=25170523) +2531 train 7.099017 (lr=5.7032e-05) (hash(x)=23361504) +2532 train 7.272026 (lr=5.7002e-05) (hash(x)=24444462) +2533 train 7.298943 (lr=5.6973e-05) (hash(x)=24035993) +2534 train 7.262784 (lr=5.6943e-05) (hash(x)=24696651) +2535 train 7.254650 (lr=5.6914e-05) (hash(x)=22040184) +2536 train 7.172775 (lr=5.6884e-05) (hash(x)=27400103) +2537 train 7.492019 (lr=5.6855e-05) (hash(x)=27383080) +2538 train 7.297838 (lr=5.6826e-05) (hash(x)=24212212) +2539 train 7.176251 (lr=5.6796e-05) (hash(x)=23727731) +2540 train 7.301162 (lr=5.6767e-05) (hash(x)=24149487) +2541 train 7.065120 (lr=5.6737e-05) (hash(x)=23794649) +2542 train 7.269997 (lr=5.6708e-05) (hash(x)=26147774) +2543 train 7.425128 (lr=5.6678e-05) (hash(x)=24463229) +2544 train 7.428159 (lr=5.6649e-05) (hash(x)=26361238) +2545 train 7.111249 (lr=5.6620e-05) (hash(x)=18891545) +2546 train 7.621414 (lr=5.6590e-05) (hash(x)=30380438) +2547 train 7.857845 (lr=5.6561e-05) (hash(x)=32663792) +2548 train 7.288755 (lr=5.6531e-05) (hash(x)=25175499) +2549 train 7.446157 (lr=5.6502e-05) (hash(x)=26702407) +2550 val loss 7.3445 +2550 val perplexity 1547.6212 +2550 train 7.274071 (lr=5.6472e-05) (hash(x)=24578061) +2551 train 7.263312 (lr=5.6443e-05) (hash(x)=24091954) +2552 train 7.319641 (lr=5.6413e-05) (hash(x)=23041778) +2553 train 7.081047 (lr=5.6384e-05) (hash(x)=23686239) +2554 train 7.211385 (lr=5.6355e-05) (hash(x)=22745355) +2555 train 7.280243 (lr=5.6325e-05) (hash(x)=23599013) +2556 train 7.187982 (lr=5.6296e-05) (hash(x)=26033088) +2557 train 7.252450 (lr=5.6266e-05) (hash(x)=21634218) +2558 train 7.184023 (lr=5.6237e-05) (hash(x)=20985281) +2559 train 7.429420 (lr=5.6207e-05) (hash(x)=26670219) +2560 train 7.204785 (lr=5.6178e-05) (hash(x)=26499936) +2561 train 7.314107 (lr=5.6149e-05) (hash(x)=23547908) +2562 train 7.152805 (lr=5.6119e-05) (hash(x)=22306373) +2563 train 7.271047 (lr=5.6090e-05) (hash(x)=24380893) +2564 train 7.223689 (lr=5.6060e-05) (hash(x)=23726190) +2565 train 7.245555 (lr=5.6031e-05) (hash(x)=26967512) +2566 train 7.345840 (lr=5.6001e-05) (hash(x)=23414576) +2567 train 7.536186 (lr=5.5972e-05) (hash(x)=25558986) +2568 train 7.438119 (lr=5.5942e-05) (hash(x)=27057505) +2569 train 7.430492 (lr=5.5913e-05) (hash(x)=26048135) +2570 train 7.385779 (lr=5.5884e-05) (hash(x)=26991032) +2571 train 7.417774 (lr=5.5854e-05) (hash(x)=25729492) +2572 train 7.036258 (lr=5.5825e-05) (hash(x)=20611723) +2573 train 7.105304 (lr=5.5795e-05) (hash(x)=24563606) +2574 train 7.190872 (lr=5.5766e-05) (hash(x)=23330043) +2575 train 7.218630 (lr=5.5736e-05) (hash(x)=19218943) +2576 train 7.550228 (lr=5.5707e-05) (hash(x)=20985122) +2577 train 7.208459 (lr=5.5677e-05) (hash(x)=24133609) +2578 train 7.524933 (lr=5.5648e-05) (hash(x)=28368610) +2579 train 7.224768 (lr=5.5618e-05) (hash(x)=23952206) +2580 train 7.154535 (lr=5.5589e-05) (hash(x)=23068957) +2581 train 7.248578 (lr=5.5560e-05) (hash(x)=25365277) +2582 train 7.602788 (lr=5.5530e-05) (hash(x)=24721184) +2583 train 7.312303 (lr=5.5501e-05) (hash(x)=24551402) +2584 train 7.031414 (lr=5.5471e-05) (hash(x)=20469327) +2585 train 7.446261 (lr=5.5442e-05) (hash(x)=24966478) +2586 train 7.205168 (lr=5.5412e-05) (hash(x)=18626184) +2587 train 7.210016 (lr=5.5383e-05) (hash(x)=24007642) +2588 train 7.161241 (lr=5.5353e-05) (hash(x)=23521875) +2589 train 7.387840 (lr=5.5324e-05) (hash(x)=25204207) +2590 train 7.162518 (lr=5.5295e-05) (hash(x)=25449801) +2591 train 7.361732 (lr=5.5265e-05) (hash(x)=25229281) +2592 train 7.202153 (lr=5.5236e-05) (hash(x)=23202696) +2593 train 7.087167 (lr=5.5206e-05) (hash(x)=22435944) +2594 train 7.092510 (lr=5.5177e-05) (hash(x)=20787439) +2595 train 6.674074 (lr=5.5147e-05) (hash(x)=18214283) +2596 train 6.874825 (lr=5.5118e-05) (hash(x)=20851477) +2597 train 6.857329 (lr=5.5088e-05) (hash(x)=20609675) +2598 train 6.985332 (lr=5.5059e-05) (hash(x)=20061218) +2599 train 7.032012 (lr=5.5029e-05) (hash(x)=21251127) +2600 val loss 7.3347 +2600 val perplexity 1532.6193 +2600 train 7.533613 (lr=5.5000e-05) (hash(x)=30948038) +2601 train 7.791287 (lr=5.4971e-05) (hash(x)=32279160) +2602 train 7.418382 (lr=5.4941e-05) (hash(x)=26607151) +2603 train 7.304367 (lr=5.4912e-05) (hash(x)=25097619) +2604 train 6.872011 (lr=5.4882e-05) (hash(x)=20892421) +2605 train 7.063298 (lr=5.4853e-05) (hash(x)=22212821) +2606 train 7.381574 (lr=5.4823e-05) (hash(x)=24720588) +2607 train 7.375499 (lr=5.4794e-05) (hash(x)=25800857) +2608 train 7.169837 (lr=5.4764e-05) (hash(x)=22901279) +2609 train 7.059238 (lr=5.4735e-05) (hash(x)=20921910) +2610 train 7.290086 (lr=5.4705e-05) (hash(x)=24846267) +2611 train 7.153946 (lr=5.4676e-05) (hash(x)=22918428) +2612 train 7.134293 (lr=5.4647e-05) (hash(x)=22805901) +2613 train 7.299657 (lr=5.4617e-05) (hash(x)=24345816) +2614 train 7.149353 (lr=5.4588e-05) (hash(x)=22962012) +2615 train 7.419786 (lr=5.4558e-05) (hash(x)=25836189) +2616 train 7.423200 (lr=5.4529e-05) (hash(x)=27922916) +2617 train 7.177486 (lr=5.4499e-05) (hash(x)=21697866) +2618 train 7.159400 (lr=5.4470e-05) (hash(x)=24283369) +2619 train 7.072507 (lr=5.4440e-05) (hash(x)=24504567) +2620 train 7.186447 (lr=5.4411e-05) (hash(x)=25557725) +2621 train 7.242863 (lr=5.4382e-05) (hash(x)=23135849) +2622 train 7.166189 (lr=5.4352e-05) (hash(x)=22888908) +2623 train 7.350320 (lr=5.4323e-05) (hash(x)=25999255) +2624 train 7.219135 (lr=5.4293e-05) (hash(x)=24446851) +2625 train 6.974392 (lr=5.4264e-05) (hash(x)=21137520) +2626 train 7.287389 (lr=5.4234e-05) (hash(x)=26245754) +2627 train 7.579677 (lr=5.4205e-05) (hash(x)=27308968) +2628 train 7.330669 (lr=5.4175e-05) (hash(x)=23961169) +2629 train 7.302693 (lr=5.4146e-05) (hash(x)=25924731) +2630 train 7.368779 (lr=5.4116e-05) (hash(x)=25782315) +2631 train 7.394910 (lr=5.4087e-05) (hash(x)=20149394) +2632 train 7.459026 (lr=5.4058e-05) (hash(x)=23801981) +2633 train 7.269629 (lr=5.4028e-05) (hash(x)=23830286) +2634 train 7.191109 (lr=5.3999e-05) (hash(x)=25325236) +2635 train 7.214069 (lr=5.3969e-05) (hash(x)=24498556) +2636 train 7.182202 (lr=5.3940e-05) (hash(x)=23693078) +2637 train 7.351404 (lr=5.3910e-05) (hash(x)=25484922) +2638 train 7.031906 (lr=5.3881e-05) (hash(x)=22645025) +2639 train 6.976915 (lr=5.3851e-05) (hash(x)=21999338) +2640 train 7.213445 (lr=5.3822e-05) (hash(x)=21758019) +2641 train 7.162343 (lr=5.3793e-05) (hash(x)=24064168) +2642 train 7.197914 (lr=5.3763e-05) (hash(x)=26847292) +2643 train 7.086104 (lr=5.3734e-05) (hash(x)=23280568) +2644 train 7.062374 (lr=5.3704e-05) (hash(x)=21749161) +2645 train 7.716487 (lr=5.3675e-05) (hash(x)=30082352) +2646 train 7.566802 (lr=5.3645e-05) (hash(x)=28334297) +2647 train 7.704314 (lr=5.3616e-05) (hash(x)=27611302) +2648 train 8.152580 (lr=5.3587e-05) (hash(x)=31007436) +2649 train 7.001828 (lr=5.3557e-05) (hash(x)=22356183) +2650 val loss 7.3373 +2650 val perplexity 1536.5795 +2650 train 7.066448 (lr=5.3528e-05) (hash(x)=23071731) +2651 train 7.066854 (lr=5.3498e-05) (hash(x)=23982308) +2652 train 7.403479 (lr=5.3469e-05) (hash(x)=25673823) +2653 train 7.171665 (lr=5.3439e-05) (hash(x)=22973788) +2654 train 7.344702 (lr=5.3410e-05) (hash(x)=25386647) +2655 train 7.115299 (lr=5.3380e-05) (hash(x)=22778356) +2656 train 7.339192 (lr=5.3351e-05) (hash(x)=26669130) +2657 train 7.051778 (lr=5.3322e-05) (hash(x)=23542930) +2658 train 7.183263 (lr=5.3292e-05) (hash(x)=23307871) +2659 train 7.136843 (lr=5.3263e-05) (hash(x)=23467046) +2660 train 7.296025 (lr=5.3233e-05) (hash(x)=24728872) +2661 train 7.907941 (lr=5.3204e-05) (hash(x)=29719902) +2662 train 7.209068 (lr=5.3174e-05) (hash(x)=25114165) +2663 train 7.118519 (lr=5.3145e-05) (hash(x)=24195959) +2664 train 7.318449 (lr=5.3116e-05) (hash(x)=26938509) +2665 train 7.513397 (lr=5.3086e-05) (hash(x)=27168434) +2666 train 7.645387 (lr=5.3057e-05) (hash(x)=27488221) +2667 train 8.462729 (lr=5.3027e-05) (hash(x)=32710438) +2668 train 7.438625 (lr=5.2998e-05) (hash(x)=25073185) +2669 train 7.439869 (lr=5.2968e-05) (hash(x)=26951664) +2670 train 7.578035 (lr=5.2939e-05) (hash(x)=24886228) +2671 train 7.080110 (lr=5.2910e-05) (hash(x)=19127465) +2672 train 7.345986 (lr=5.2880e-05) (hash(x)=27134917) +2673 train 7.311088 (lr=5.2851e-05) (hash(x)=25673955) +2674 train 7.809062 (lr=5.2821e-05) (hash(x)=27111776) +2675 train 7.768851 (lr=5.2792e-05) (hash(x)=28962580) +2676 train 7.285261 (lr=5.2763e-05) (hash(x)=25593381) +2677 train 7.335710 (lr=5.2733e-05) (hash(x)=25238916) +2678 train 7.232298 (lr=5.2704e-05) (hash(x)=27453574) +2679 train 7.192081 (lr=5.2674e-05) (hash(x)=22426274) +2680 train 7.219081 (lr=5.2645e-05) (hash(x)=22974780) +2681 train 7.226925 (lr=5.2615e-05) (hash(x)=24668644) +2682 train 7.237484 (lr=5.2586e-05) (hash(x)=26182084) +2683 train 7.458327 (lr=5.2557e-05) (hash(x)=25606512) +2684 train 7.261054 (lr=5.2527e-05) (hash(x)=24885252) +2685 train 7.069341 (lr=5.2498e-05) (hash(x)=21290254) +2686 train 7.006832 (lr=5.2468e-05) (hash(x)=21367078) +2687 train 7.199103 (lr=5.2439e-05) (hash(x)=23785205) +2688 train 7.079500 (lr=5.2410e-05) (hash(x)=24640056) +2689 train 7.521057 (lr=5.2380e-05) (hash(x)=27083886) +2690 train 7.234679 (lr=5.2351e-05) (hash(x)=23603571) +2691 train 7.301355 (lr=5.2321e-05) (hash(x)=24779414) +2692 train 7.018394 (lr=5.2292e-05) (hash(x)=22200693) +2693 train 7.326562 (lr=5.2263e-05) (hash(x)=26907868) +2694 train 7.684368 (lr=5.2233e-05) (hash(x)=32034827) +2695 train 7.558665 (lr=5.2204e-05) (hash(x)=28505676) +2696 train 7.170404 (lr=5.2174e-05) (hash(x)=23805750) +2697 train 7.473287 (lr=5.2145e-05) (hash(x)=29804750) +2698 train 7.746840 (lr=5.2116e-05) (hash(x)=28443583) +2699 train 7.694058 (lr=5.2086e-05) (hash(x)=29156288) +2700 val loss 7.3364 +2700 val perplexity 1535.1090 +2700 train 7.412717 (lr=5.2057e-05) (hash(x)=25895743) +2701 train 6.990408 (lr=5.2027e-05) (hash(x)=21173795) +2702 train 6.911435 (lr=5.1998e-05) (hash(x)=20790866) +2703 train 7.470433 (lr=5.1969e-05) (hash(x)=27706477) +2704 train 7.594637 (lr=5.1939e-05) (hash(x)=30358985) +2705 train 7.138741 (lr=5.1910e-05) (hash(x)=23548492) +2706 train 7.280753 (lr=5.1881e-05) (hash(x)=25879696) +2707 train 7.167577 (lr=5.1851e-05) (hash(x)=23711800) +2708 train 7.676529 (lr=5.1822e-05) (hash(x)=28763123) +2709 train 7.342824 (lr=5.1792e-05) (hash(x)=23327642) +2710 train 7.374287 (lr=5.1763e-05) (hash(x)=25634166) +2711 train 7.283693 (lr=5.1734e-05) (hash(x)=28684175) +2712 train 7.399293 (lr=5.1704e-05) (hash(x)=23996278) +2713 train 6.989049 (lr=5.1675e-05) (hash(x)=21795980) +2714 train 7.338191 (lr=5.1646e-05) (hash(x)=24840769) +2715 train 7.263078 (lr=5.1616e-05) (hash(x)=25225466) +2716 train 7.565772 (lr=5.1587e-05) (hash(x)=27500471) +2717 train 7.237922 (lr=5.1557e-05) (hash(x)=24703036) +2718 train 7.384323 (lr=5.1528e-05) (hash(x)=24294293) +2719 train 7.359820 (lr=5.1499e-05) (hash(x)=28003600) +2720 train 7.083063 (lr=5.1469e-05) (hash(x)=22822962) +2721 train 6.993946 (lr=5.1440e-05) (hash(x)=24189246) +2722 train 7.097726 (lr=5.1411e-05) (hash(x)=22608951) +2723 train 7.806340 (lr=5.1381e-05) (hash(x)=27989890) +2724 train 7.452957 (lr=5.1352e-05) (hash(x)=24175838) +2725 train 7.298019 (lr=5.1323e-05) (hash(x)=24781792) +2726 train 7.120986 (lr=5.1293e-05) (hash(x)=23413276) +2727 train 7.549554 (lr=5.1264e-05) (hash(x)=27586845) +2728 train 7.364994 (lr=5.1234e-05) (hash(x)=27336264) +2729 train 7.433378 (lr=5.1205e-05) (hash(x)=26808464) +2730 train 7.198753 (lr=5.1176e-05) (hash(x)=22312009) +2731 train 7.247110 (lr=5.1146e-05) (hash(x)=22373927) +2732 train 7.206516 (lr=5.1117e-05) (hash(x)=23428834) +2733 train 7.229299 (lr=5.1088e-05) (hash(x)=25304441) +2734 train 7.230420 (lr=5.1058e-05) (hash(x)=24798164) +2735 train 7.058170 (lr=5.1029e-05) (hash(x)=21176405) +2736 train 7.142491 (lr=5.1000e-05) (hash(x)=22343075) +2737 train 7.211609 (lr=5.0970e-05) (hash(x)=23825332) +2738 train 7.236432 (lr=5.0941e-05) (hash(x)=24191865) +2739 train 7.051704 (lr=5.0912e-05) (hash(x)=23806052) +2740 train 7.110625 (lr=5.0882e-05) (hash(x)=21764591) +2741 train 7.251066 (lr=5.0853e-05) (hash(x)=25548695) +2742 train 7.471662 (lr=5.0824e-05) (hash(x)=26847535) +2743 train 7.175809 (lr=5.0794e-05) (hash(x)=25888433) +2744 train 7.152771 (lr=5.0765e-05) (hash(x)=24327454) +2745 train 7.040082 (lr=5.0736e-05) (hash(x)=22543301) +2746 train 7.466095 (lr=5.0706e-05) (hash(x)=24593022) +2747 train 8.078624 (lr=5.0677e-05) (hash(x)=27797727) +2748 train 7.530402 (lr=5.0648e-05) (hash(x)=28067682) +2749 train 7.175803 (lr=5.0619e-05) (hash(x)=25278538) +2750 val loss 7.3345 +2750 val perplexity 1532.2889 +2750 train 7.121686 (lr=5.0589e-05) (hash(x)=23875731) +2751 train 7.324822 (lr=5.0560e-05) (hash(x)=27916982) +2752 train 7.298048 (lr=5.0531e-05) (hash(x)=25726799) +2753 train 7.119039 (lr=5.0501e-05) (hash(x)=25227141) +2754 train 7.410728 (lr=5.0472e-05) (hash(x)=27679212) +2755 train 7.116774 (lr=5.0443e-05) (hash(x)=24621793) +2756 train 7.026241 (lr=5.0413e-05) (hash(x)=21962296) +2757 train 7.341152 (lr=5.0384e-05) (hash(x)=24899679) +2758 train 7.062627 (lr=5.0355e-05) (hash(x)=21452158) +2759 train 7.177049 (lr=5.0326e-05) (hash(x)=24334708) +2760 train 7.429447 (lr=5.0296e-05) (hash(x)=25523041) +2761 train 7.541074 (lr=5.0267e-05) (hash(x)=30389813) +2762 train 7.087142 (lr=5.0238e-05) (hash(x)=22426014) +2763 train 7.167123 (lr=5.0208e-05) (hash(x)=24419143) +2764 train 7.252107 (lr=5.0179e-05) (hash(x)=24850536) +2765 train 7.319881 (lr=5.0150e-05) (hash(x)=24181393) +2766 train 6.853857 (lr=5.0121e-05) (hash(x)=18882503) +2767 train 7.318271 (lr=5.0091e-05) (hash(x)=25617709) +2768 train 7.264529 (lr=5.0062e-05) (hash(x)=24076662) +2769 train 7.192127 (lr=5.0033e-05) (hash(x)=21656802) +2770 train 7.133041 (lr=5.0003e-05) (hash(x)=21014265) +2771 train 7.266133 (lr=4.9974e-05) (hash(x)=24556034) +2772 train 7.032043 (lr=4.9945e-05) (hash(x)=22046665) +2773 train 7.296694 (lr=4.9916e-05) (hash(x)=26761579) +2774 train 8.709860 (lr=4.9886e-05) (hash(x)=41414315) +2775 train 7.198826 (lr=4.9857e-05) (hash(x)=25152362) +2776 train 7.402594 (lr=4.9828e-05) (hash(x)=25567641) +2777 train 7.319295 (lr=4.9799e-05) (hash(x)=25427935) +2778 train 7.400853 (lr=4.9769e-05) (hash(x)=25824457) +2779 train 7.310801 (lr=4.9740e-05) (hash(x)=24326376) +2780 train 7.351306 (lr=4.9711e-05) (hash(x)=27447230) +2781 train 7.227319 (lr=4.9682e-05) (hash(x)=24003710) +2782 train 7.122805 (lr=4.9652e-05) (hash(x)=24157390) +2783 train 7.222364 (lr=4.9623e-05) (hash(x)=24276512) +2784 train 7.052912 (lr=4.9594e-05) (hash(x)=21503752) +2785 train 6.955575 (lr=4.9565e-05) (hash(x)=20031488) +2786 train 7.050358 (lr=4.9535e-05) (hash(x)=21788715) +2787 train 7.206815 (lr=4.9506e-05) (hash(x)=24344695) +2788 train 7.242774 (lr=4.9477e-05) (hash(x)=22927763) +2789 train 7.115476 (lr=4.9448e-05) (hash(x)=23710755) +2790 train 7.361351 (lr=4.9418e-05) (hash(x)=26924620) +2791 train 7.665054 (lr=4.9389e-05) (hash(x)=26776133) +2792 train 7.110201 (lr=4.9360e-05) (hash(x)=19936770) +2793 train 7.277504 (lr=4.9331e-05) (hash(x)=25440959) +2794 train 7.236137 (lr=4.9302e-05) (hash(x)=25146097) +2795 train 7.028958 (lr=4.9272e-05) (hash(x)=21847282) +2796 train 7.232625 (lr=4.9243e-05) (hash(x)=25639784) +2797 train 7.045059 (lr=4.9214e-05) (hash(x)=21199921) +2798 train 7.225367 (lr=4.9185e-05) (hash(x)=22360806) +2799 train 6.680149 (lr=4.9156e-05) (hash(x)=20254159) +2800 val loss 7.3255 +2800 val perplexity 1518.5540 +2800 train 6.824565 (lr=4.9126e-05) (hash(x)=23348345) +2801 train 7.427626 (lr=4.9097e-05) (hash(x)=24908033) +2802 train 7.171834 (lr=4.9068e-05) (hash(x)=23350309) +2803 train 7.261899 (lr=4.9039e-05) (hash(x)=25044762) +2804 train 7.124521 (lr=4.9010e-05) (hash(x)=24071026) +2805 train 6.937493 (lr=4.8980e-05) (hash(x)=22169363) +2806 train 7.205905 (lr=4.8951e-05) (hash(x)=23757564) +2807 train 7.638570 (lr=4.8922e-05) (hash(x)=27873855) +2808 train 7.408920 (lr=4.8893e-05) (hash(x)=26577893) +2809 train 7.450810 (lr=4.8864e-05) (hash(x)=27001634) +2810 train 7.239531 (lr=4.8834e-05) (hash(x)=24796541) +2811 train 7.120615 (lr=4.8805e-05) (hash(x)=22575615) +2812 train 7.241846 (lr=4.8776e-05) (hash(x)=25876475) +2813 train 7.237237 (lr=4.8747e-05) (hash(x)=24765155) +2814 train 7.192205 (lr=4.8718e-05) (hash(x)=25785699) +2815 train 7.352929 (lr=4.8689e-05) (hash(x)=25113614) +2816 train 7.248258 (lr=4.8659e-05) (hash(x)=24415748) +2817 train 7.374227 (lr=4.8630e-05) (hash(x)=25140622) +2818 train 7.233031 (lr=4.8601e-05) (hash(x)=24845866) +2819 train 7.670344 (lr=4.8572e-05) (hash(x)=28062905) +2820 train 7.199675 (lr=4.8543e-05) (hash(x)=22041086) +2821 train 7.317238 (lr=4.8514e-05) (hash(x)=24957184) +2822 train 7.255701 (lr=4.8485e-05) (hash(x)=24360380) +2823 train 7.386106 (lr=4.8455e-05) (hash(x)=26192886) +2824 train 7.257364 (lr=4.8426e-05) (hash(x)=25001858) +2825 train 7.212101 (lr=4.8397e-05) (hash(x)=24721193) +2826 train 7.278675 (lr=4.8368e-05) (hash(x)=26186227) +2827 train 7.250520 (lr=4.8339e-05) (hash(x)=25770338) +2828 train 7.310730 (lr=4.8310e-05) (hash(x)=25920767) +2829 train 7.241342 (lr=4.8281e-05) (hash(x)=25060684) +2830 train 6.945348 (lr=4.8251e-05) (hash(x)=22933946) +2831 train 7.097369 (lr=4.8222e-05) (hash(x)=24614912) +2832 train 6.854627 (lr=4.8193e-05) (hash(x)=19955522) +2833 train 6.905454 (lr=4.8164e-05) (hash(x)=21111215) +2834 train 7.784486 (lr=4.8135e-05) (hash(x)=28817924) +2835 train 7.324445 (lr=4.8106e-05) (hash(x)=26934071) +2836 train 7.250919 (lr=4.8077e-05) (hash(x)=24768851) +2837 train 7.211243 (lr=4.8048e-05) (hash(x)=25706447) +2838 train 7.031476 (lr=4.8019e-05) (hash(x)=19579834) +2839 train 7.253378 (lr=4.7990e-05) (hash(x)=25397093) +2840 train 7.723607 (lr=4.7960e-05) (hash(x)=27902141) +2841 train 7.302728 (lr=4.7931e-05) (hash(x)=25383069) +2842 train 7.131284 (lr=4.7902e-05) (hash(x)=22007373) +2843 train 7.207843 (lr=4.7873e-05) (hash(x)=25925963) +2844 train 7.272063 (lr=4.7844e-05) (hash(x)=25711128) +2845 train 7.022730 (lr=4.7815e-05) (hash(x)=21881216) +2846 train 7.177112 (lr=4.7786e-05) (hash(x)=20277075) +2847 train 7.231056 (lr=4.7757e-05) (hash(x)=19811802) +2848 train 7.117745 (lr=4.7728e-05) (hash(x)=23878906) +2849 train 7.342428 (lr=4.7699e-05) (hash(x)=25034966) +2850 val loss 7.3198 +2850 val perplexity 1509.8348 +2850 train 7.352124 (lr=4.7670e-05) (hash(x)=24359507) +2851 train 7.114750 (lr=4.7641e-05) (hash(x)=23248423) +2852 train 7.122468 (lr=4.7612e-05) (hash(x)=21782773) +2853 train 7.264654 (lr=4.7583e-05) (hash(x)=23804418) +2854 train 7.302848 (lr=4.7553e-05) (hash(x)=22525078) +2855 train 7.273076 (lr=4.7524e-05) (hash(x)=25579655) +2856 train 7.402965 (lr=4.7495e-05) (hash(x)=27048876) +2857 train 7.560220 (lr=4.7466e-05) (hash(x)=26468479) +2858 train 7.211446 (lr=4.7437e-05) (hash(x)=23854933) +2859 train 7.538556 (lr=4.7408e-05) (hash(x)=25537603) +2860 train 6.996162 (lr=4.7379e-05) (hash(x)=20979252) +2861 train 7.555917 (lr=4.7350e-05) (hash(x)=26504374) +2862 train 7.363110 (lr=4.7321e-05) (hash(x)=27561842) +2863 train 7.333464 (lr=4.7292e-05) (hash(x)=26096514) +2864 train 7.364452 (lr=4.7263e-05) (hash(x)=25926899) +2865 train 7.384094 (lr=4.7234e-05) (hash(x)=26058348) +2866 train 7.441120 (lr=4.7205e-05) (hash(x)=29802259) +2867 train 7.297967 (lr=4.7176e-05) (hash(x)=24132888) +2868 train 7.038587 (lr=4.7147e-05) (hash(x)=23369410) +2869 train 7.204766 (lr=4.7118e-05) (hash(x)=25387506) +2870 train 7.356116 (lr=4.7089e-05) (hash(x)=27375344) +2871 train 7.115211 (lr=4.7060e-05) (hash(x)=22589633) +2872 train 7.273728 (lr=4.7031e-05) (hash(x)=23250237) +2873 train 7.171365 (lr=4.7002e-05) (hash(x)=25511322) +2874 train 6.846585 (lr=4.6973e-05) (hash(x)=18356418) +2875 train 7.263504 (lr=4.6944e-05) (hash(x)=27781566) +2876 train 7.116947 (lr=4.6915e-05) (hash(x)=24878173) +2877 train 7.629753 (lr=4.6886e-05) (hash(x)=30018637) +2878 train 7.459528 (lr=4.6857e-05) (hash(x)=27168416) +2879 train 7.473234 (lr=4.6828e-05) (hash(x)=26757147) +2880 train 7.472131 (lr=4.6799e-05) (hash(x)=26637081) +2881 train 7.314606 (lr=4.6770e-05) (hash(x)=24795024) +2882 train 7.595755 (lr=4.6741e-05) (hash(x)=29787745) +2883 train 7.449039 (lr=4.6713e-05) (hash(x)=26649864) +2884 train 7.273410 (lr=4.6684e-05) (hash(x)=27306612) +2885 train 7.365255 (lr=4.6655e-05) (hash(x)=27568311) +2886 train 7.408184 (lr=4.6626e-05) (hash(x)=27440150) +2887 train 7.135801 (lr=4.6597e-05) (hash(x)=24963730) +2888 train 7.143126 (lr=4.6568e-05) (hash(x)=23619807) +2889 train 7.658548 (lr=4.6539e-05) (hash(x)=29447356) +2890 train 7.124897 (lr=4.6510e-05) (hash(x)=25144675) +2891 train 7.080283 (lr=4.6481e-05) (hash(x)=25249959) +2892 train 7.130851 (lr=4.6452e-05) (hash(x)=26608712) +2893 train 7.137230 (lr=4.6423e-05) (hash(x)=26333258) +2894 train 6.928567 (lr=4.6394e-05) (hash(x)=20682182) +2895 train 7.363138 (lr=4.6365e-05) (hash(x)=27703124) +2896 train 7.150838 (lr=4.6337e-05) (hash(x)=23228180) +2897 train 7.026752 (lr=4.6308e-05) (hash(x)=25252411) +2898 train 7.020576 (lr=4.6279e-05) (hash(x)=22879178) +2899 train 7.303586 (lr=4.6250e-05) (hash(x)=26459082) +2900 val loss 7.3151 +2900 val perplexity 1502.8546 +2900 train 7.154560 (lr=4.6221e-05) (hash(x)=24569501) +2901 train 6.953430 (lr=4.6192e-05) (hash(x)=19803884) +2902 train 6.984598 (lr=4.6163e-05) (hash(x)=18799747) +2903 train 7.287380 (lr=4.6134e-05) (hash(x)=24781713) +2904 train 7.415933 (lr=4.6105e-05) (hash(x)=25016590) +2905 train 7.623482 (lr=4.6077e-05) (hash(x)=29006906) +2906 train 7.362875 (lr=4.6048e-05) (hash(x)=24069959) +2907 train 7.516979 (lr=4.6019e-05) (hash(x)=26597693) +2908 train 7.137006 (lr=4.5990e-05) (hash(x)=25014146) +2909 train 7.341924 (lr=4.5961e-05) (hash(x)=24943747) +2910 train 7.264249 (lr=4.5932e-05) (hash(x)=27847542) +2911 train 7.202640 (lr=4.5903e-05) (hash(x)=24720476) +2912 train 7.071958 (lr=4.5875e-05) (hash(x)=24388804) +2913 train 7.199536 (lr=4.5846e-05) (hash(x)=23567535) +2914 train 7.505574 (lr=4.5817e-05) (hash(x)=29673625) +2915 train 7.226314 (lr=4.5788e-05) (hash(x)=23691295) +2916 train 7.594347 (lr=4.5759e-05) (hash(x)=26572819) +2917 train 7.270073 (lr=4.5730e-05) (hash(x)=23237812) +2918 train 7.528328 (lr=4.5702e-05) (hash(x)=26531016) +2919 train 7.041008 (lr=4.5673e-05) (hash(x)=23481301) +2920 train 7.320837 (lr=4.5644e-05) (hash(x)=24839184) +2921 train 7.183839 (lr=4.5615e-05) (hash(x)=23327755) +2922 train 7.416695 (lr=4.5586e-05) (hash(x)=26347114) +2923 train 7.079137 (lr=4.5558e-05) (hash(x)=23295676) +2924 train 7.153876 (lr=4.5529e-05) (hash(x)=24557178) +2925 train 7.218227 (lr=4.5500e-05) (hash(x)=26067788) +2926 train 7.164728 (lr=4.5471e-05) (hash(x)=25694982) +2927 train 7.253955 (lr=4.5442e-05) (hash(x)=25641033) +2928 train 7.284192 (lr=4.5414e-05) (hash(x)=24906422) +2929 train 7.462956 (lr=4.5385e-05) (hash(x)=27803515) +2930 train 7.433431 (lr=4.5356e-05) (hash(x)=26208803) +2931 train 6.919310 (lr=4.5327e-05) (hash(x)=22441379) +2932 train 7.217947 (lr=4.5299e-05) (hash(x)=24741626) +2933 train 7.077733 (lr=4.5270e-05) (hash(x)=24595257) +2934 train 7.142920 (lr=4.5241e-05) (hash(x)=23939167) +2935 train 7.411452 (lr=4.5212e-05) (hash(x)=27369437) +2936 train 7.080792 (lr=4.5184e-05) (hash(x)=21409783) +2937 train 7.343723 (lr=4.5155e-05) (hash(x)=25923735) +2938 train 7.344265 (lr=4.5126e-05) (hash(x)=29559511) +2939 train 7.202981 (lr=4.5097e-05) (hash(x)=24482272) +2940 train 7.217554 (lr=4.5069e-05) (hash(x)=24767658) +2941 train 7.371255 (lr=4.5040e-05) (hash(x)=26425020) +2942 train 7.721246 (lr=4.5011e-05) (hash(x)=27444868) +2943 train 7.164596 (lr=4.4982e-05) (hash(x)=24760900) +2944 train 7.224323 (lr=4.4954e-05) (hash(x)=25605407) +2945 train 7.122156 (lr=4.4925e-05) (hash(x)=22886951) +2946 train 7.442699 (lr=4.4896e-05) (hash(x)=26112205) +2947 train 7.261830 (lr=4.4868e-05) (hash(x)=23919156) +2948 train 7.218698 (lr=4.4839e-05) (hash(x)=23729312) +2949 train 7.505236 (lr=4.4810e-05) (hash(x)=30440878) +2950 val loss 7.3139 +2950 val perplexity 1501.0463 +2950 train 6.952800 (lr=4.4782e-05) (hash(x)=20004041) +2951 train 6.949013 (lr=4.4753e-05) (hash(x)=21692546) +2952 train 6.992400 (lr=4.4724e-05) (hash(x)=23021681) +2953 train 7.349823 (lr=4.4696e-05) (hash(x)=26663597) +2954 train 7.199914 (lr=4.4667e-05) (hash(x)=23727385) +2955 train 7.200075 (lr=4.4638e-05) (hash(x)=27692087) +2956 train 7.231278 (lr=4.4610e-05) (hash(x)=24003378) +2957 train 7.880797 (lr=4.4581e-05) (hash(x)=29534673) +2958 train 7.123781 (lr=4.4552e-05) (hash(x)=22875068) +2959 train 7.103206 (lr=4.4524e-05) (hash(x)=22720391) +2960 train 6.915534 (lr=4.4495e-05) (hash(x)=17997400) +2961 train 7.098499 (lr=4.4466e-05) (hash(x)=22853822) +2962 train 7.166670 (lr=4.4438e-05) (hash(x)=25238004) +2963 train 7.321134 (lr=4.4409e-05) (hash(x)=26146560) +2964 train 7.437609 (lr=4.4380e-05) (hash(x)=21894867) +2965 train 7.416379 (lr=4.4352e-05) (hash(x)=23001150) +2966 train 7.097058 (lr=4.4323e-05) (hash(x)=23392923) +2967 train 7.157240 (lr=4.4295e-05) (hash(x)=24376979) +2968 train 7.145074 (lr=4.4266e-05) (hash(x)=23781449) +2969 train 7.300775 (lr=4.4237e-05) (hash(x)=25315495) +2970 train 7.415687 (lr=4.4209e-05) (hash(x)=27165470) +2971 train 7.236299 (lr=4.4180e-05) (hash(x)=22917712) +2972 train 7.620883 (lr=4.4152e-05) (hash(x)=27928456) +2973 train 6.969656 (lr=4.4123e-05) (hash(x)=19890855) +2974 train 6.944773 (lr=4.4094e-05) (hash(x)=21318134) +2975 train 7.098761 (lr=4.4066e-05) (hash(x)=22244509) +2976 train 7.031218 (lr=4.4037e-05) (hash(x)=21293137) +2977 train 7.129697 (lr=4.4009e-05) (hash(x)=23465789) +2978 train 7.110592 (lr=4.3980e-05) (hash(x)=21169753) +2979 train 7.440605 (lr=4.3952e-05) (hash(x)=25243385) +2980 train 7.499303 (lr=4.3923e-05) (hash(x)=27465812) +2981 train 7.193048 (lr=4.3895e-05) (hash(x)=24615492) +2982 train 7.117795 (lr=4.3866e-05) (hash(x)=23081307) +2983 train 6.926740 (lr=4.3837e-05) (hash(x)=21831960) +2984 train 7.075343 (lr=4.3809e-05) (hash(x)=23242850) +2985 train 7.148460 (lr=4.3780e-05) (hash(x)=24308188) +2986 train 7.325967 (lr=4.3752e-05) (hash(x)=28541601) +2987 train 7.218338 (lr=4.3723e-05) (hash(x)=24842373) +2988 train 6.943732 (lr=4.3695e-05) (hash(x)=21967126) +2989 train 7.143953 (lr=4.3666e-05) (hash(x)=22951616) +2990 train 7.269799 (lr=4.3638e-05) (hash(x)=24325714) +2991 train 7.065985 (lr=4.3609e-05) (hash(x)=24921535) +2992 train 7.292367 (lr=4.3581e-05) (hash(x)=25937112) +2993 train 7.000023 (lr=4.3552e-05) (hash(x)=20716218) +2994 train 7.263947 (lr=4.3524e-05) (hash(x)=25450724) +2995 train 7.234276 (lr=4.3495e-05) (hash(x)=24344615) +2996 train 6.941790 (lr=4.3467e-05) (hash(x)=20299058) +2997 train 7.175077 (lr=4.3439e-05) (hash(x)=23859426) +2998 train 7.159955 (lr=4.3410e-05) (hash(x)=23094397) +2999 train 7.486581 (lr=4.3382e-05) (hash(x)=25381251) +3000 val loss 7.3038 +3000 val perplexity 1485.9167 +3000 train 7.214624 (lr=4.3353e-05) (hash(x)=23586527) +3001 train 7.117177 (lr=4.3325e-05) (hash(x)=24220410) +3002 train 6.989014 (lr=4.3296e-05) (hash(x)=20597347) +3003 train 7.072722 (lr=4.3268e-05) (hash(x)=22887303) +3004 train 7.340112 (lr=4.3239e-05) (hash(x)=25869462) +3005 train 7.087224 (lr=4.3211e-05) (hash(x)=22098530) +3006 train 7.378331 (lr=4.3183e-05) (hash(x)=26246291) +3007 train 7.329854 (lr=4.3154e-05) (hash(x)=25687352) +3008 train 7.069179 (lr=4.3126e-05) (hash(x)=25425646) +3009 train 7.268817 (lr=4.3097e-05) (hash(x)=26021124) +3010 train 7.291849 (lr=4.3069e-05) (hash(x)=25392057) +3011 train 7.381213 (lr=4.3041e-05) (hash(x)=27791412) +3012 train 7.186845 (lr=4.3012e-05) (hash(x)=23181098) +3013 train 7.219715 (lr=4.2984e-05) (hash(x)=25521889) +3014 train 7.041337 (lr=4.2955e-05) (hash(x)=21685795) +3015 train 7.199733 (lr=4.2927e-05) (hash(x)=25221654) +3016 train 7.370148 (lr=4.2899e-05) (hash(x)=24888744) +3017 train 7.254753 (lr=4.2870e-05) (hash(x)=24200150) +3018 train 7.208360 (lr=4.2842e-05) (hash(x)=26943942) +3019 train 7.182079 (lr=4.2814e-05) (hash(x)=23243731) +3020 train 7.032955 (lr=4.2785e-05) (hash(x)=21068284) +3021 train 7.206770 (lr=4.2757e-05) (hash(x)=23876902) +3022 train 7.330835 (lr=4.2728e-05) (hash(x)=25337639) +3023 train 7.260438 (lr=4.2700e-05) (hash(x)=24469863) +3024 train 7.738248 (lr=4.2672e-05) (hash(x)=27850876) +3025 train 7.527371 (lr=4.2644e-05) (hash(x)=20515778) +3026 train 7.303688 (lr=4.2615e-05) (hash(x)=29019173) +3027 train 6.982231 (lr=4.2587e-05) (hash(x)=22484936) +3028 train 7.157965 (lr=4.2559e-05) (hash(x)=24639400) +3029 train 7.306113 (lr=4.2530e-05) (hash(x)=26835174) +3030 train 7.425995 (lr=4.2502e-05) (hash(x)=29843763) +3031 train 7.155858 (lr=4.2474e-05) (hash(x)=25291413) +3032 train 7.104713 (lr=4.2445e-05) (hash(x)=24590244) +3033 train 7.348638 (lr=4.2417e-05) (hash(x)=28880142) +3034 train 7.082291 (lr=4.2389e-05) (hash(x)=23372199) +3035 train 7.067873 (lr=4.2361e-05) (hash(x)=23952225) +3036 train 7.224333 (lr=4.2332e-05) (hash(x)=24589186) +3037 train 7.210041 (lr=4.2304e-05) (hash(x)=23260323) +3038 train 7.346794 (lr=4.2276e-05) (hash(x)=25824498) +3039 train 7.257109 (lr=4.2248e-05) (hash(x)=25744274) +3040 train 7.261623 (lr=4.2219e-05) (hash(x)=21610247) +3041 train 7.367082 (lr=4.2191e-05) (hash(x)=25079786) +3042 train 6.990570 (lr=4.2163e-05) (hash(x)=23219195) +3043 train 6.946577 (lr=4.2135e-05) (hash(x)=22616739) +3044 train 7.234272 (lr=4.2106e-05) (hash(x)=24908480) +3045 train 7.070831 (lr=4.2078e-05) (hash(x)=22293489) +3046 train 7.112133 (lr=4.2050e-05) (hash(x)=23557651) +3047 train 7.159425 (lr=4.2022e-05) (hash(x)=24246963) +3048 train 7.260234 (lr=4.1994e-05) (hash(x)=24490083) +3049 train 7.266962 (lr=4.1965e-05) (hash(x)=22372895) +3050 val loss 7.3119 +3050 val perplexity 1498.0031 +3050 train 6.985235 (lr=4.1937e-05) (hash(x)=21759470) +3051 train 6.904051 (lr=4.1909e-05) (hash(x)=19407094) +3052 train 7.246074 (lr=4.1881e-05) (hash(x)=23957047) +3053 train 7.342361 (lr=4.1853e-05) (hash(x)=24719318) +3054 train 7.142002 (lr=4.1824e-05) (hash(x)=20719314) +3055 train 7.092992 (lr=4.1796e-05) (hash(x)=19724058) +3056 train 6.965175 (lr=4.1768e-05) (hash(x)=14407266) +3057 train 6.845867 (lr=4.1740e-05) (hash(x)=12468292) +3058 train 7.072976 (lr=4.1712e-05) (hash(x)=16098279) +3059 train 7.135832 (lr=4.1684e-05) (hash(x)=18836491) +3060 train 6.979392 (lr=4.1656e-05) (hash(x)=19132277) +3061 train 7.132857 (lr=4.1628e-05) (hash(x)=22814208) +3062 train 7.163373 (lr=4.1599e-05) (hash(x)=24838508) +3063 train 7.056452 (lr=4.1571e-05) (hash(x)=20705649) +3064 train 8.044838 (lr=4.1543e-05) (hash(x)=29416914) +3065 train 7.523171 (lr=4.1515e-05) (hash(x)=25972430) +3066 train 6.875882 (lr=4.1487e-05) (hash(x)=23705805) +3067 train 6.970534 (lr=4.1459e-05) (hash(x)=21325875) +3068 train 7.179073 (lr=4.1431e-05) (hash(x)=23526506) +3069 train 7.668737 (lr=4.1403e-05) (hash(x)=27282337) +3070 train 7.502665 (lr=4.1375e-05) (hash(x)=27968043) +3071 train 7.308984 (lr=4.1347e-05) (hash(x)=24938685) +3072 train 7.519260 (lr=4.1319e-05) (hash(x)=26942737) +3073 train 7.407292 (lr=4.1290e-05) (hash(x)=23506879) +3074 train 7.090761 (lr=4.1262e-05) (hash(x)=23589913) +3075 train 7.270621 (lr=4.1234e-05) (hash(x)=25152403) +3076 train 7.388647 (lr=4.1206e-05) (hash(x)=23425868) +3077 train 7.590557 (lr=4.1178e-05) (hash(x)=23966181) +3078 train 7.628561 (lr=4.1150e-05) (hash(x)=27312570) +3079 train 7.235442 (lr=4.1122e-05) (hash(x)=21707000) +3080 train 7.155818 (lr=4.1094e-05) (hash(x)=25600427) +3081 train 7.277230 (lr=4.1066e-05) (hash(x)=24270631) +3082 train 7.421895 (lr=4.1038e-05) (hash(x)=25199537) +3083 train 6.614623 (lr=4.1010e-05) (hash(x)=17952018) +3084 train 6.773090 (lr=4.0982e-05) (hash(x)=18733143) +3085 train 7.417519 (lr=4.0954e-05) (hash(x)=26946100) +3086 train 7.242366 (lr=4.0926e-05) (hash(x)=25547515) +3087 train 7.205678 (lr=4.0898e-05) (hash(x)=24948980) +3088 train 8.479877 (lr=4.0870e-05) (hash(x)=35461645) +3089 train 7.436716 (lr=4.0842e-05) (hash(x)=28330877) +3090 train 7.327089 (lr=4.0814e-05) (hash(x)=27687861) +3091 train 7.479769 (lr=4.0786e-05) (hash(x)=28012110) +3092 train 7.329267 (lr=4.0759e-05) (hash(x)=24684480) +3093 train 7.319864 (lr=4.0731e-05) (hash(x)=26225786) +3094 train 6.974519 (lr=4.0703e-05) (hash(x)=23098156) +3095 train 7.541593 (lr=4.0675e-05) (hash(x)=30773958) +3096 train 7.839276 (lr=4.0647e-05) (hash(x)=28640406) +3097 train 7.769947 (lr=4.0619e-05) (hash(x)=28201086) +3098 train 8.182805 (lr=4.0591e-05) (hash(x)=35002344) +3099 train 7.666515 (lr=4.0563e-05) (hash(x)=29481068) +3100 val loss 7.3134 +3100 val perplexity 1500.2584 +3100 train 7.217837 (lr=4.0535e-05) (hash(x)=26374528) +3101 train 7.152023 (lr=4.0507e-05) (hash(x)=24153602) +3102 train 7.232337 (lr=4.0479e-05) (hash(x)=25478746) +3103 train 7.509212 (lr=4.0452e-05) (hash(x)=26769046) +3104 train 7.110539 (lr=4.0424e-05) (hash(x)=21841970) +3105 train 7.384933 (lr=4.0396e-05) (hash(x)=27693052) +3106 train 6.887121 (lr=4.0368e-05) (hash(x)=20689448) +3107 train 7.230586 (lr=4.0340e-05) (hash(x)=26755048) +3108 train 7.271994 (lr=4.0312e-05) (hash(x)=24431904) +3109 train 7.139643 (lr=4.0284e-05) (hash(x)=21009792) +3110 train 7.211774 (lr=4.0257e-05) (hash(x)=21909003) +3111 train 7.281325 (lr=4.0229e-05) (hash(x)=18849656) +3112 train 7.381369 (lr=4.0201e-05) (hash(x)=22223376) +3113 train 7.640775 (lr=4.0173e-05) (hash(x)=25652491) +3114 train 7.543965 (lr=4.0145e-05) (hash(x)=23521434) +3115 train 7.591535 (lr=4.0118e-05) (hash(x)=25449800) +3116 train 7.988182 (lr=4.0090e-05) (hash(x)=27655847) +3117 train 8.037548 (lr=4.0062e-05) (hash(x)=29878248) +3118 train 8.074717 (lr=4.0034e-05) (hash(x)=30444094) +3119 train 7.663070 (lr=4.0006e-05) (hash(x)=24624950) +3120 train 7.027951 (lr=3.9979e-05) (hash(x)=20798511) +3121 train 7.366142 (lr=3.9951e-05) (hash(x)=26581679) +3122 train 7.285432 (lr=3.9923e-05) (hash(x)=25333422) +3123 train 7.322648 (lr=3.9895e-05) (hash(x)=26174069) +3124 train 7.393023 (lr=3.9868e-05) (hash(x)=25219475) +3125 train 7.324622 (lr=3.9840e-05) (hash(x)=20919061) +3126 train 7.239666 (lr=3.9812e-05) (hash(x)=23828688) +3127 train 7.768711 (lr=3.9785e-05) (hash(x)=27299605) +3128 train 7.103973 (lr=3.9757e-05) (hash(x)=23797514) +3129 train 7.342157 (lr=3.9729e-05) (hash(x)=23601883) +3130 train 7.581515 (lr=3.9701e-05) (hash(x)=31003964) +3131 train 7.288376 (lr=3.9674e-05) (hash(x)=24777273) +3132 train 7.178196 (lr=3.9646e-05) (hash(x)=25403249) +3133 train 7.372739 (lr=3.9618e-05) (hash(x)=28913150) +3134 train 7.353873 (lr=3.9591e-05) (hash(x)=26541508) +3135 train 7.311655 (lr=3.9563e-05) (hash(x)=24113445) +3136 train 7.098188 (lr=3.9535e-05) (hash(x)=25464565) +3137 train 7.361370 (lr=3.9508e-05) (hash(x)=26581432) +3138 train 7.201590 (lr=3.9480e-05) (hash(x)=23074513) +3139 train 7.056259 (lr=3.9452e-05) (hash(x)=23970384) +3140 train 7.299781 (lr=3.9425e-05) (hash(x)=26694495) +3141 train 7.258164 (lr=3.9397e-05) (hash(x)=26883445) +3142 train 7.398782 (lr=3.9369e-05) (hash(x)=28632211) +3143 train 7.837822 (lr=3.9342e-05) (hash(x)=32644465) +3144 train 7.575583 (lr=3.9314e-05) (hash(x)=27490443) +3145 train 7.129695 (lr=3.9287e-05) (hash(x)=23814853) +3146 train 7.634032 (lr=3.9259e-05) (hash(x)=29664236) +3147 train 7.874290 (lr=3.9231e-05) (hash(x)=29951548) +3148 train 7.672510 (lr=3.9204e-05) (hash(x)=28426503) +3149 train 7.042558 (lr=3.9176e-05) (hash(x)=23727657) +3150 val loss 7.3114 +3150 val perplexity 1497.2489 +3150 train 7.187227 (lr=3.9149e-05) (hash(x)=21430659) +3151 train 7.244945 (lr=3.9121e-05) (hash(x)=25829219) +3152 train 7.430505 (lr=3.9094e-05) (hash(x)=29735208) +3153 train 7.445520 (lr=3.9066e-05) (hash(x)=28173447) +3154 train 7.128049 (lr=3.9039e-05) (hash(x)=22909641) +3155 train 7.330530 (lr=3.9011e-05) (hash(x)=20556094) +3156 train 7.053868 (lr=3.8983e-05) (hash(x)=24013769) +3157 train 7.073137 (lr=3.8956e-05) (hash(x)=22525971) +3158 train 7.137987 (lr=3.8928e-05) (hash(x)=25492728) +3159 train 7.186077 (lr=3.8901e-05) (hash(x)=25194550) +3160 train 7.323500 (lr=3.8873e-05) (hash(x)=25610603) +3161 train 7.283505 (lr=3.8846e-05) (hash(x)=23848640) +3162 train 7.107884 (lr=3.8818e-05) (hash(x)=24082226) +3163 train 7.477473 (lr=3.8791e-05) (hash(x)=28482186) +3164 train 7.374053 (lr=3.8764e-05) (hash(x)=27542978) +3165 train 7.133229 (lr=3.8736e-05) (hash(x)=22540954) +3166 train 7.248230 (lr=3.8709e-05) (hash(x)=26103641) +3167 train 7.245139 (lr=3.8681e-05) (hash(x)=25941804) +3168 train 7.261822 (lr=3.8654e-05) (hash(x)=25965921) +3169 train 7.507526 (lr=3.8626e-05) (hash(x)=25631269) +3170 train 7.072639 (lr=3.8599e-05) (hash(x)=23471525) +3171 train 7.323097 (lr=3.8571e-05) (hash(x)=27049208) +3172 train 7.344841 (lr=3.8544e-05) (hash(x)=27074992) +3173 train 7.261893 (lr=3.8517e-05) (hash(x)=25712617) +3174 train 7.233289 (lr=3.8489e-05) (hash(x)=25884917) +3175 train 7.250674 (lr=3.8462e-05) (hash(x)=24075727) +3176 train 7.131979 (lr=3.8434e-05) (hash(x)=23681759) +3177 train 7.420442 (lr=3.8407e-05) (hash(x)=25786577) +3178 train 7.408154 (lr=3.8380e-05) (hash(x)=27307614) +3179 train 7.439061 (lr=3.8352e-05) (hash(x)=25082806) +3180 train 7.428758 (lr=3.8325e-05) (hash(x)=26098308) +3181 train 7.176293 (lr=3.8298e-05) (hash(x)=24080140) +3182 train 7.374971 (lr=3.8270e-05) (hash(x)=26399395) +3183 train 7.454953 (lr=3.8243e-05) (hash(x)=23104539) +3184 train 7.089612 (lr=3.8216e-05) (hash(x)=23356930) +3185 train 7.316880 (lr=3.8188e-05) (hash(x)=27972420) +3186 train 7.002807 (lr=3.8161e-05) (hash(x)=21338924) +3187 train 7.412212 (lr=3.8134e-05) (hash(x)=25351113) +3188 train 7.347341 (lr=3.8106e-05) (hash(x)=26019439) +3189 train 7.399082 (lr=3.8079e-05) (hash(x)=30149312) +3190 train 7.094406 (lr=3.8052e-05) (hash(x)=23028152) +3191 train 7.466507 (lr=3.8024e-05) (hash(x)=23018983) +3192 train 7.129637 (lr=3.7997e-05) (hash(x)=23190787) +3193 train 7.519339 (lr=3.7970e-05) (hash(x)=27798543) +3194 train 7.310327 (lr=3.7943e-05) (hash(x)=25193663) +3195 train 7.098179 (lr=3.7915e-05) (hash(x)=25302106) +3196 train 7.220839 (lr=3.7888e-05) (hash(x)=24325364) +3197 train 7.262838 (lr=3.7861e-05) (hash(x)=25399101) +3198 train 7.108005 (lr=3.7834e-05) (hash(x)=23606439) +3199 train 7.157710 (lr=3.7806e-05) (hash(x)=24422929) +3200 val loss 7.2892 +3200 val perplexity 1464.3433 +3200 train 7.300329 (lr=3.7779e-05) (hash(x)=24760381) +3201 train 7.024259 (lr=3.7752e-05) (hash(x)=23278576) +3202 train 7.227977 (lr=3.7725e-05) (hash(x)=24897511) +3203 train 7.522926 (lr=3.7698e-05) (hash(x)=29052117) +3204 train 7.282268 (lr=3.7670e-05) (hash(x)=25772923) +3205 train 7.414823 (lr=3.7643e-05) (hash(x)=25885977) +3206 train 7.211408 (lr=3.7616e-05) (hash(x)=21985272) +3207 train 7.140839 (lr=3.7589e-05) (hash(x)=23389696) +3208 train 7.054515 (lr=3.7562e-05) (hash(x)=25299042) +3209 train 7.289825 (lr=3.7535e-05) (hash(x)=23703987) +3210 train 7.186859 (lr=3.7508e-05) (hash(x)=23362342) +3211 train 7.261674 (lr=3.7480e-05) (hash(x)=23962503) +3212 train 7.187416 (lr=3.7453e-05) (hash(x)=21216023) +3213 train 7.250856 (lr=3.7426e-05) (hash(x)=25841931) +3214 train 7.104683 (lr=3.7399e-05) (hash(x)=23631428) +3215 train 7.533267 (lr=3.7372e-05) (hash(x)=29102969) +3216 train 7.263937 (lr=3.7345e-05) (hash(x)=25782766) +3217 train 7.508817 (lr=3.7318e-05) (hash(x)=28825867) +3218 train 7.476713 (lr=3.7291e-05) (hash(x)=24609499) +3219 train 7.387482 (lr=3.7264e-05) (hash(x)=24948166) +3220 train 7.434741 (lr=3.7237e-05) (hash(x)=26919841) +3221 train 7.309513 (lr=3.7209e-05) (hash(x)=27236198) +3222 train 7.076083 (lr=3.7182e-05) (hash(x)=24029305) +3223 train 7.640678 (lr=3.7155e-05) (hash(x)=28359859) +3224 train 7.439217 (lr=3.7128e-05) (hash(x)=24886008) +3225 train 7.263954 (lr=3.7101e-05) (hash(x)=27159867) +3226 train 7.547276 (lr=3.7074e-05) (hash(x)=20672023) +3227 train 7.214265 (lr=3.7047e-05) (hash(x)=22360298) +3228 train 7.637065 (lr=3.7020e-05) (hash(x)=27478658) +3229 train 7.434270 (lr=3.6993e-05) (hash(x)=26575886) +3230 train 7.621831 (lr=3.6966e-05) (hash(x)=26890615) +3231 train 7.253577 (lr=3.6939e-05) (hash(x)=24630955) +3232 train 7.518926 (lr=3.6912e-05) (hash(x)=27016054) +3233 train 7.726894 (lr=3.6885e-05) (hash(x)=28444407) +3234 train 7.131767 (lr=3.6858e-05) (hash(x)=24053336) +3235 train 7.436161 (lr=3.6831e-05) (hash(x)=26897402) +3236 train 7.601967 (lr=3.6805e-05) (hash(x)=29451214) +3237 train 7.364683 (lr=3.6778e-05) (hash(x)=27268677) +3238 train 7.472024 (lr=3.6751e-05) (hash(x)=27494000) +3239 train 7.154754 (lr=3.6724e-05) (hash(x)=22969113) +3240 train 7.115766 (lr=3.6697e-05) (hash(x)=21944576) +3241 train 7.318929 (lr=3.6670e-05) (hash(x)=21671079) +3242 train 7.208345 (lr=3.6643e-05) (hash(x)=23912980) +3243 train 7.178249 (lr=3.6616e-05) (hash(x)=25205781) +3244 train 7.160678 (lr=3.6589e-05) (hash(x)=25654244) +3245 train 7.090703 (lr=3.6562e-05) (hash(x)=23335929) +3246 train 7.482316 (lr=3.6536e-05) (hash(x)=27953926) +3247 train 7.253487 (lr=3.6509e-05) (hash(x)=27004415) +3248 train 6.948010 (lr=3.6482e-05) (hash(x)=20471566) +3249 train 7.181863 (lr=3.6455e-05) (hash(x)=25797941) +3250 val loss 7.2860 +3250 val perplexity 1459.7637 +3250 train 7.065357 (lr=3.6428e-05) (hash(x)=21787064) +3251 train 7.054930 (lr=3.6401e-05) (hash(x)=22974875) +3252 train 7.307163 (lr=3.6375e-05) (hash(x)=28431267) +3253 train 7.201665 (lr=3.6348e-05) (hash(x)=25584910) +3254 train 7.031229 (lr=3.6321e-05) (hash(x)=23888922) +3255 train 7.219573 (lr=3.6294e-05) (hash(x)=22265063) +3256 train 6.847531 (lr=3.6267e-05) (hash(x)=21926624) +3257 train 7.146996 (lr=3.6241e-05) (hash(x)=23073191) +3258 train 7.131055 (lr=3.6214e-05) (hash(x)=24409183) +3259 train 7.218989 (lr=3.6187e-05) (hash(x)=23312114) +3260 train 7.125167 (lr=3.6160e-05) (hash(x)=21001289) +3261 train 7.295450 (lr=3.6134e-05) (hash(x)=25514824) +3262 train 7.092391 (lr=3.6107e-05) (hash(x)=22526800) +3263 train 7.484335 (lr=3.6080e-05) (hash(x)=26905990) +3264 train 7.185835 (lr=3.6053e-05) (hash(x)=24469631) +3265 train 7.023385 (lr=3.6027e-05) (hash(x)=21149081) +3266 train 7.205122 (lr=3.6000e-05) (hash(x)=24696215) +3267 train 7.568378 (lr=3.5973e-05) (hash(x)=27089280) +3268 train 7.078718 (lr=3.5947e-05) (hash(x)=23100446) +3269 train 7.361164 (lr=3.5920e-05) (hash(x)=25061229) +3270 train 7.209053 (lr=3.5893e-05) (hash(x)=24337543) +3271 train 7.284817 (lr=3.5867e-05) (hash(x)=24047679) +3272 train 7.336080 (lr=3.5840e-05) (hash(x)=27616773) +3273 train 7.240280 (lr=3.5813e-05) (hash(x)=25315110) +3274 train 7.324628 (lr=3.5787e-05) (hash(x)=28354645) +3275 train 7.156651 (lr=3.5760e-05) (hash(x)=25034684) +3276 train 7.204113 (lr=3.5733e-05) (hash(x)=23550342) +3277 train 7.855283 (lr=3.5707e-05) (hash(x)=28661487) +3278 train 7.477972 (lr=3.5680e-05) (hash(x)=24724622) +3279 train 7.378666 (lr=3.5654e-05) (hash(x)=26905582) +3280 train 7.477433 (lr=3.5627e-05) (hash(x)=26838818) +3281 train 7.192913 (lr=3.5600e-05) (hash(x)=23949017) +3282 train 6.729698 (lr=3.5574e-05) (hash(x)=18846300) +3283 train 7.087392 (lr=3.5547e-05) (hash(x)=21406950) +3284 train 6.904218 (lr=3.5521e-05) (hash(x)=21157696) +3285 train 7.017906 (lr=3.5494e-05) (hash(x)=21440152) +3286 train 7.193555 (lr=3.5468e-05) (hash(x)=26749182) +3287 train 7.352565 (lr=3.5441e-05) (hash(x)=29018970) +3288 train 7.315976 (lr=3.5415e-05) (hash(x)=27577517) +3289 train 6.961244 (lr=3.5388e-05) (hash(x)=19190537) +3290 train 7.004144 (lr=3.5362e-05) (hash(x)=21957991) +3291 train 7.029243 (lr=3.5335e-05) (hash(x)=20853530) +3292 train 6.946768 (lr=3.5309e-05) (hash(x)=22291731) +3293 train 7.136297 (lr=3.5282e-05) (hash(x)=23786853) +3294 train 7.302043 (lr=3.5256e-05) (hash(x)=25740147) +3295 train 7.373680 (lr=3.5229e-05) (hash(x)=24503315) +3296 train 7.117462 (lr=3.5203e-05) (hash(x)=22541728) +3297 train 7.449216 (lr=3.5176e-05) (hash(x)=27067328) +3298 train 7.114469 (lr=3.5150e-05) (hash(x)=22600715) +3299 train 7.130618 (lr=3.5123e-05) (hash(x)=23080074) +3300 val loss 7.2882 +3300 val perplexity 1462.9990 +3300 train 6.949951 (lr=3.5097e-05) (hash(x)=22097758) +3301 train 7.070705 (lr=3.5071e-05) (hash(x)=24105430) +3302 train 6.992860 (lr=3.5044e-05) (hash(x)=23343775) +3303 train 7.240813 (lr=3.5018e-05) (hash(x)=22607537) +3304 train 7.298077 (lr=3.4991e-05) (hash(x)=26501182) +3305 train 7.586641 (lr=3.4965e-05) (hash(x)=26063650) +3306 train 7.169569 (lr=3.4939e-05) (hash(x)=23486602) +3307 train 8.105039 (lr=3.4912e-05) (hash(x)=32179773) +3308 train 11.191283 (lr=3.4886e-05) (hash(x)=66155855) +3309 train 8.582365 (lr=3.4860e-05) (hash(x)=37724427) +3310 train 7.641433 (lr=3.4833e-05) (hash(x)=28861610) +3311 train 7.602120 (lr=3.4807e-05) (hash(x)=26690225) +3312 train 7.164061 (lr=3.4781e-05) (hash(x)=24136450) +3313 train 7.344255 (lr=3.4754e-05) (hash(x)=23702010) +3314 train 7.560262 (lr=3.4728e-05) (hash(x)=28761762) +3315 train 6.928417 (lr=3.4702e-05) (hash(x)=22109609) +3316 train 7.294727 (lr=3.4675e-05) (hash(x)=25168631) +3317 train 7.175420 (lr=3.4649e-05) (hash(x)=24503786) +3318 train 7.166044 (lr=3.4623e-05) (hash(x)=23698606) +3319 train 7.238608 (lr=3.4597e-05) (hash(x)=24226255) +3320 train 7.800744 (lr=3.4570e-05) (hash(x)=31110577) +3321 train 7.218703 (lr=3.4544e-05) (hash(x)=24752754) +3322 train 7.060254 (lr=3.4518e-05) (hash(x)=21135610) +3323 train 7.017804 (lr=3.4492e-05) (hash(x)=23013573) +3324 train 6.768904 (lr=3.4466e-05) (hash(x)=20289715) +3325 train 7.047975 (lr=3.4439e-05) (hash(x)=22700287) +3326 train 7.106929 (lr=3.4413e-05) (hash(x)=21320362) +3327 train 7.244455 (lr=3.4387e-05) (hash(x)=23622702) +3328 train 7.531855 (lr=3.4361e-05) (hash(x)=27435461) +3329 train 7.279477 (lr=3.4335e-05) (hash(x)=25435452) +3330 train 7.245135 (lr=3.4308e-05) (hash(x)=27952557) +3331 train 6.933546 (lr=3.4282e-05) (hash(x)=21517429) +3332 train 7.068462 (lr=3.4256e-05) (hash(x)=24288985) +3333 train 7.240575 (lr=3.4230e-05) (hash(x)=23374788) +3334 train 7.068707 (lr=3.4204e-05) (hash(x)=22042499) +3335 train 7.302106 (lr=3.4178e-05) (hash(x)=23910425) +3336 train 7.604633 (lr=3.4152e-05) (hash(x)=28118508) +3337 train 7.376407 (lr=3.4126e-05) (hash(x)=26737440) +3338 train 7.179760 (lr=3.4099e-05) (hash(x)=24472271) +3339 train 7.103487 (lr=3.4073e-05) (hash(x)=24407484) +3340 train 7.664506 (lr=3.4047e-05) (hash(x)=27908937) +3341 train 7.775636 (lr=3.4021e-05) (hash(x)=29038937) +3342 train 7.560928 (lr=3.3995e-05) (hash(x)=24802580) +3343 train 7.531517 (lr=3.3969e-05) (hash(x)=27213318) +3344 train 7.557042 (lr=3.3943e-05) (hash(x)=28693458) +3345 train 6.916960 (lr=3.3917e-05) (hash(x)=20332324) +3346 train 7.279916 (lr=3.3891e-05) (hash(x)=26726007) +3347 train 7.197578 (lr=3.3865e-05) (hash(x)=25524191) +3348 train 7.277654 (lr=3.3839e-05) (hash(x)=25553293) +3349 train 7.219860 (lr=3.3813e-05) (hash(x)=25614848) +3350 val loss 7.2834 +3350 val perplexity 1455.9257 +3350 train 7.294765 (lr=3.3787e-05) (hash(x)=25747903) +3351 train 7.285137 (lr=3.3761e-05) (hash(x)=26701577) +3352 train 7.027245 (lr=3.3735e-05) (hash(x)=21964135) +3353 train 7.159939 (lr=3.3709e-05) (hash(x)=24461007) +3354 train 7.191726 (lr=3.3683e-05) (hash(x)=25818495) +3355 train 7.001172 (lr=3.3657e-05) (hash(x)=22091266) +3356 train 7.009459 (lr=3.3631e-05) (hash(x)=24476213) +3357 train 7.371677 (lr=3.3606e-05) (hash(x)=24500423) +3358 train 7.152522 (lr=3.3580e-05) (hash(x)=21754841) +3359 train 7.462189 (lr=3.3554e-05) (hash(x)=26216794) +3360 train 6.952119 (lr=3.3528e-05) (hash(x)=24267249) +3361 train 7.291106 (lr=3.3502e-05) (hash(x)=23143515) +3362 train 7.178563 (lr=3.3476e-05) (hash(x)=24120302) +3363 train 7.333332 (lr=3.3450e-05) (hash(x)=20817340) +3364 train 7.301036 (lr=3.3424e-05) (hash(x)=22285847) +3365 train 7.595589 (lr=3.3399e-05) (hash(x)=28151597) +3366 train 8.012629 (lr=3.3373e-05) (hash(x)=31593285) +3367 train 7.684323 (lr=3.3347e-05) (hash(x)=27579623) +3368 train 7.287810 (lr=3.3321e-05) (hash(x)=24995988) +3369 train 6.898845 (lr=3.3295e-05) (hash(x)=22166810) +3370 train 7.165616 (lr=3.3269e-05) (hash(x)=23948298) +3371 train 7.062979 (lr=3.3244e-05) (hash(x)=21532187) +3372 train 7.157211 (lr=3.3218e-05) (hash(x)=23571652) +3373 train 7.543157 (lr=3.3192e-05) (hash(x)=26911513) +3374 train 7.457295 (lr=3.3166e-05) (hash(x)=24011329) +3375 train 7.649423 (lr=3.3141e-05) (hash(x)=26086198) +3376 train 7.245555 (lr=3.3115e-05) (hash(x)=22844402) +3377 train 7.202417 (lr=3.3089e-05) (hash(x)=21817762) +3378 train 7.259338 (lr=3.3063e-05) (hash(x)=23903232) +3379 train 7.201717 (lr=3.3038e-05) (hash(x)=23911729) +3380 train 7.178975 (lr=3.3012e-05) (hash(x)=24485288) +3381 train 7.365491 (lr=3.2986e-05) (hash(x)=27955492) +3382 train 7.100110 (lr=3.2961e-05) (hash(x)=25884586) +3383 train 7.298726 (lr=3.2935e-05) (hash(x)=24863441) +3384 train 7.565051 (lr=3.2909e-05) (hash(x)=22045992) +3385 train 7.677527 (lr=3.2884e-05) (hash(x)=29174796) +3386 train 7.969975 (lr=3.2858e-05) (hash(x)=32589942) +3387 train 7.585396 (lr=3.2832e-05) (hash(x)=28856978) +3388 train 7.046310 (lr=3.2807e-05) (hash(x)=21667904) +3389 train 7.038227 (lr=3.2781e-05) (hash(x)=23431801) +3390 train 6.877365 (lr=3.2756e-05) (hash(x)=20877285) +3391 train 7.116765 (lr=3.2730e-05) (hash(x)=25236385) +3392 train 7.332780 (lr=3.2704e-05) (hash(x)=25373071) +3393 train 7.466510 (lr=3.2679e-05) (hash(x)=25713464) +3394 train 7.455084 (lr=3.2653e-05) (hash(x)=25713475) +3395 train 7.306343 (lr=3.2628e-05) (hash(x)=24278687) +3396 train 7.441572 (lr=3.2602e-05) (hash(x)=27491349) +3397 train 7.327236 (lr=3.2577e-05) (hash(x)=24513692) +3398 train 7.434364 (lr=3.2551e-05) (hash(x)=26853415) +3399 train 7.494700 (lr=3.2526e-05) (hash(x)=25330803) +3400 val loss 7.2870 +3400 val perplexity 1461.1334 +3400 train 7.445577 (lr=3.2500e-05) (hash(x)=26578066) +3401 train 7.496194 (lr=3.2474e-05) (hash(x)=26811522) +3402 train 7.226558 (lr=3.2449e-05) (hash(x)=25611092) +3403 train 7.017652 (lr=3.2424e-05) (hash(x)=21568545) +3404 train 7.046621 (lr=3.2398e-05) (hash(x)=22756484) +3405 train 7.332584 (lr=3.2373e-05) (hash(x)=27927608) +3406 train 7.365638 (lr=3.2347e-05) (hash(x)=27497018) +3407 train 7.158040 (lr=3.2322e-05) (hash(x)=22508532) +3408 train 7.579128 (lr=3.2296e-05) (hash(x)=26673287) +3409 train 7.230328 (lr=3.2271e-05) (hash(x)=23675869) +3410 train 7.153571 (lr=3.2245e-05) (hash(x)=25496948) +3411 train 7.151897 (lr=3.2220e-05) (hash(x)=24850662) +3412 train 7.386037 (lr=3.2195e-05) (hash(x)=29790167) +3413 train 7.026656 (lr=3.2169e-05) (hash(x)=24193434) +3414 train 7.432335 (lr=3.2144e-05) (hash(x)=25310919) +3415 train 7.150276 (lr=3.2118e-05) (hash(x)=21799261) +3416 train 7.370380 (lr=3.2093e-05) (hash(x)=26620074) +3417 train 7.322507 (lr=3.2068e-05) (hash(x)=26719309) +3418 train 7.792458 (lr=3.2042e-05) (hash(x)=23190530) +3419 train 7.285765 (lr=3.2017e-05) (hash(x)=24884891) +3420 train 7.266771 (lr=3.1992e-05) (hash(x)=25545849) +3421 train 7.255655 (lr=3.1967e-05) (hash(x)=26021405) +3422 train 7.208421 (lr=3.1941e-05) (hash(x)=23887343) +3423 train 7.266614 (lr=3.1916e-05) (hash(x)=26311168) +3424 train 6.966907 (lr=3.1891e-05) (hash(x)=21051541) +3425 train 7.328690 (lr=3.1865e-05) (hash(x)=23553179) +3426 train 7.197370 (lr=3.1840e-05) (hash(x)=24345540) +3427 train 7.649268 (lr=3.1815e-05) (hash(x)=27549895) +3428 train 7.001039 (lr=3.1790e-05) (hash(x)=22559753) +3429 train 6.962399 (lr=3.1764e-05) (hash(x)=21647642) +3430 train 6.863794 (lr=3.1739e-05) (hash(x)=20130901) +3431 train 7.017929 (lr=3.1714e-05) (hash(x)=20977430) +3432 train 7.028333 (lr=3.1689e-05) (hash(x)=21356429) +3433 train 6.991014 (lr=3.1664e-05) (hash(x)=23494380) +3434 train 7.231336 (lr=3.1638e-05) (hash(x)=23805501) +3435 train 7.188951 (lr=3.1613e-05) (hash(x)=23448855) +3436 train 7.543741 (lr=3.1588e-05) (hash(x)=26000319) +3437 train 7.068601 (lr=3.1563e-05) (hash(x)=21760032) +3438 train 7.153378 (lr=3.1538e-05) (hash(x)=24424886) +3439 train 7.532276 (lr=3.1513e-05) (hash(x)=26941617) +3440 train 7.531097 (lr=3.1488e-05) (hash(x)=26798528) +3441 train 7.561490 (lr=3.1462e-05) (hash(x)=27464193) +3442 train 7.474552 (lr=3.1437e-05) (hash(x)=25649118) +3443 train 7.543752 (lr=3.1412e-05) (hash(x)=26953192) +3444 train 7.359256 (lr=3.1387e-05) (hash(x)=22224958) +3445 train 7.164491 (lr=3.1362e-05) (hash(x)=24044587) +3446 train 7.586357 (lr=3.1337e-05) (hash(x)=29584466) +3447 train 7.936237 (lr=3.1312e-05) (hash(x)=30008957) +3448 train 7.925615 (lr=3.1287e-05) (hash(x)=26059290) +3449 train 6.845743 (lr=3.1262e-05) (hash(x)=19733965) +3450 val loss 7.2992 +3450 val perplexity 1479.1226 +3450 train 7.336537 (lr=3.1237e-05) (hash(x)=23960200) +3451 train 7.515291 (lr=3.1212e-05) (hash(x)=27069893) +3452 train 7.156527 (lr=3.1187e-05) (hash(x)=23947772) +3453 train 7.233603 (lr=3.1162e-05) (hash(x)=22707406) +3454 train 7.389619 (lr=3.1137e-05) (hash(x)=27832550) +3455 train 7.287213 (lr=3.1112e-05) (hash(x)=27125962) +3456 train 7.158811 (lr=3.1087e-05) (hash(x)=24510254) +3457 train 6.952010 (lr=3.1062e-05) (hash(x)=23545652) +3458 train 7.047264 (lr=3.1037e-05) (hash(x)=23554751) +3459 train 7.149616 (lr=3.1012e-05) (hash(x)=23341415) +3460 train 7.313583 (lr=3.0987e-05) (hash(x)=21784583) +3461 train 7.101665 (lr=3.0962e-05) (hash(x)=22214769) +3462 train 7.148751 (lr=3.0938e-05) (hash(x)=24206922) +3463 train 7.311936 (lr=3.0913e-05) (hash(x)=25888358) +3464 train 7.107082 (lr=3.0888e-05) (hash(x)=22689666) +3465 train 7.237466 (lr=3.0863e-05) (hash(x)=24918697) +3466 train 7.546819 (lr=3.0838e-05) (hash(x)=28237214) +3467 train 7.604826 (lr=3.0813e-05) (hash(x)=26761645) +3468 train 7.254467 (lr=3.0788e-05) (hash(x)=26979307) +3469 train 7.142123 (lr=3.0764e-05) (hash(x)=23553754) +3470 train 7.313599 (lr=3.0739e-05) (hash(x)=25256849) +3471 train 7.197996 (lr=3.0714e-05) (hash(x)=21725719) +3472 train 7.292244 (lr=3.0689e-05) (hash(x)=24897801) +3473 train 7.178743 (lr=3.0664e-05) (hash(x)=26175307) +3474 train 7.019121 (lr=3.0640e-05) (hash(x)=23309218) +3475 train 7.133958 (lr=3.0615e-05) (hash(x)=25746493) +3476 train 7.412576 (lr=3.0590e-05) (hash(x)=27169613) +3477 train 7.131692 (lr=3.0565e-05) (hash(x)=22937341) +3478 train 7.241011 (lr=3.0541e-05) (hash(x)=24250636) +3479 train 7.067482 (lr=3.0516e-05) (hash(x)=21669704) +3480 train 7.069672 (lr=3.0491e-05) (hash(x)=24431839) +3481 train 7.105145 (lr=3.0467e-05) (hash(x)=22763387) +3482 train 7.085555 (lr=3.0442e-05) (hash(x)=20489446) +3483 train 7.034396 (lr=3.0417e-05) (hash(x)=21167493) +3484 train 7.032174 (lr=3.0393e-05) (hash(x)=23465087) +3485 train 7.280733 (lr=3.0368e-05) (hash(x)=26175023) +3486 train 7.381639 (lr=3.0343e-05) (hash(x)=24986207) +3487 train 6.977190 (lr=3.0319e-05) (hash(x)=23166993) +3488 train 7.203434 (lr=3.0294e-05) (hash(x)=25281216) +3489 train 7.027025 (lr=3.0269e-05) (hash(x)=21824285) +3490 train 7.073400 (lr=3.0245e-05) (hash(x)=22352750) +3491 train 7.299675 (lr=3.0220e-05) (hash(x)=23947208) +3492 train 7.349679 (lr=3.0196e-05) (hash(x)=26257363) +3493 train 7.192984 (lr=3.0171e-05) (hash(x)=25103214) +3494 train 7.232059 (lr=3.0146e-05) (hash(x)=25267583) +3495 train 7.300799 (lr=3.0122e-05) (hash(x)=26235974) +3496 train 7.499693 (lr=3.0097e-05) (hash(x)=26430769) +3497 train 7.918096 (lr=3.0073e-05) (hash(x)=28282027) +3498 train 7.830985 (lr=3.0048e-05) (hash(x)=28386462) +3499 train 7.399060 (lr=3.0024e-05) (hash(x)=29822604) +3500 val loss 7.2769 +3500 val perplexity 1446.4325 +3500 train 7.319355 (lr=2.9999e-05) (hash(x)=29225386) +3501 train 7.192918 (lr=2.9975e-05) (hash(x)=25249294) +3502 train 6.961766 (lr=2.9950e-05) (hash(x)=20020741) +3503 train 7.148475 (lr=2.9926e-05) (hash(x)=25426430) +3504 train 7.085713 (lr=2.9901e-05) (hash(x)=25720411) +3505 train 7.121936 (lr=2.9877e-05) (hash(x)=25602639) +3506 train 7.219014 (lr=2.9853e-05) (hash(x)=26724388) +3507 train 7.144784 (lr=2.9828e-05) (hash(x)=26043735) +3508 train 7.094469 (lr=2.9804e-05) (hash(x)=24955163) +3509 train 7.107381 (lr=2.9779e-05) (hash(x)=20936107) +3510 train 7.082379 (lr=2.9755e-05) (hash(x)=20317378) +3511 train 7.078000 (lr=2.9731e-05) (hash(x)=22966314) +3512 train 7.433356 (lr=2.9706e-05) (hash(x)=25870930) +3513 train 7.233343 (lr=2.9682e-05) (hash(x)=24656635) +3514 train 7.505353 (lr=2.9658e-05) (hash(x)=28576810) +3515 train 7.427908 (lr=2.9633e-05) (hash(x)=27944619) +3516 train 7.290582 (lr=2.9609e-05) (hash(x)=27421509) +3517 train 7.043478 (lr=2.9585e-05) (hash(x)=20844620) +3518 train 7.207141 (lr=2.9560e-05) (hash(x)=28569406) +3519 train 7.087395 (lr=2.9536e-05) (hash(x)=23448505) +3520 train 7.265561 (lr=2.9512e-05) (hash(x)=24852577) +3521 train 7.178320 (lr=2.9487e-05) (hash(x)=23963103) +3522 train 7.053415 (lr=2.9463e-05) (hash(x)=24816516) +3523 train 7.240435 (lr=2.9439e-05) (hash(x)=24205942) +3524 train 6.834880 (lr=2.9415e-05) (hash(x)=20988660) +3525 train 6.933896 (lr=2.9390e-05) (hash(x)=21631366) +3526 train 7.135091 (lr=2.9366e-05) (hash(x)=23499370) +3527 train 7.255733 (lr=2.9342e-05) (hash(x)=26330693) +3528 train 6.898633 (lr=2.9318e-05) (hash(x)=23937176) +3529 train 7.190175 (lr=2.9294e-05) (hash(x)=27345885) +3530 train 6.897037 (lr=2.9270e-05) (hash(x)=21104610) +3531 train 7.269547 (lr=2.9245e-05) (hash(x)=24844466) +3532 train 6.620180 (lr=2.9221e-05) (hash(x)=21055483) +3533 train 6.970966 (lr=2.9197e-05) (hash(x)=23229414) +3534 train 7.262718 (lr=2.9173e-05) (hash(x)=26676920) +3535 train 7.237074 (lr=2.9149e-05) (hash(x)=29550596) +3536 train 6.991380 (lr=2.9125e-05) (hash(x)=22231942) +3537 train 7.162532 (lr=2.9101e-05) (hash(x)=25843852) +3538 train 7.335758 (lr=2.9077e-05) (hash(x)=27110533) +3539 train 6.898044 (lr=2.9053e-05) (hash(x)=20506540) +3540 train 6.999603 (lr=2.9028e-05) (hash(x)=21599346) +3541 train 7.222530 (lr=2.9004e-05) (hash(x)=26395519) +3542 train 7.166037 (lr=2.8980e-05) (hash(x)=25892512) +3543 train 7.218479 (lr=2.8956e-05) (hash(x)=22124892) +3544 train 7.081568 (lr=2.8932e-05) (hash(x)=21882567) +3545 train 7.172189 (lr=2.8908e-05) (hash(x)=24316212) +3546 train 7.113675 (lr=2.8884e-05) (hash(x)=24296310) +3547 train 7.215546 (lr=2.8860e-05) (hash(x)=24867036) +3548 train 7.200561 (lr=2.8836e-05) (hash(x)=23351896) +3549 train 7.143201 (lr=2.8812e-05) (hash(x)=21576408) +3550 val loss 7.2722 +3550 val perplexity 1439.7529 +3550 train 7.297269 (lr=2.8789e-05) (hash(x)=26377338) +3551 train 7.102701 (lr=2.8765e-05) (hash(x)=25607640) +3552 train 7.428174 (lr=2.8741e-05) (hash(x)=27619776) +3553 train 6.950134 (lr=2.8717e-05) (hash(x)=23454533) +3554 train 7.136574 (lr=2.8693e-05) (hash(x)=22542519) +3555 train 7.179964 (lr=2.8669e-05) (hash(x)=26176930) +3556 train 6.958450 (lr=2.8645e-05) (hash(x)=22815181) +3557 train 6.963901 (lr=2.8621e-05) (hash(x)=21821757) +3558 train 7.000998 (lr=2.8597e-05) (hash(x)=23988293) +3559 train 6.914305 (lr=2.8573e-05) (hash(x)=23795894) +3560 train 6.878391 (lr=2.8550e-05) (hash(x)=22898969) +3561 train 6.878652 (lr=2.8526e-05) (hash(x)=21510825) +3562 train 6.804225 (lr=2.8502e-05) (hash(x)=22499317) +3563 train 6.840782 (lr=2.8478e-05) (hash(x)=23756298) +3564 train 6.905316 (lr=2.8454e-05) (hash(x)=23964512) +3565 train 6.987062 (lr=2.8431e-05) (hash(x)=23262803) +3566 train 7.187460 (lr=2.8407e-05) (hash(x)=23347279) +3567 train 7.097675 (lr=2.8383e-05) (hash(x)=24165449) +3568 train 7.220905 (lr=2.8359e-05) (hash(x)=25503946) +3569 train 7.204903 (lr=2.8336e-05) (hash(x)=26532839) +3570 train 6.835692 (lr=2.8312e-05) (hash(x)=21889816) +3571 train 7.126985 (lr=2.8288e-05) (hash(x)=26643739) +3572 train 7.339061 (lr=2.8265e-05) (hash(x)=26826130) +3573 train 7.343292 (lr=2.8241e-05) (hash(x)=25810624) +3574 train 7.203614 (lr=2.8217e-05) (hash(x)=23080331) +3575 train 7.349844 (lr=2.8194e-05) (hash(x)=24697756) +3576 train 7.195995 (lr=2.8170e-05) (hash(x)=25158900) +3577 train 7.320331 (lr=2.8146e-05) (hash(x)=25793633) +3578 train 6.924356 (lr=2.8123e-05) (hash(x)=21468493) +3579 train 7.200334 (lr=2.8099e-05) (hash(x)=24431101) +3580 train 7.107620 (lr=2.8075e-05) (hash(x)=27314357) +3581 train 7.314916 (lr=2.8052e-05) (hash(x)=26286249) +3582 train 7.601991 (lr=2.8028e-05) (hash(x)=25954856) +3583 train 7.491263 (lr=2.8005e-05) (hash(x)=27218899) +3584 train 7.253973 (lr=2.7981e-05) (hash(x)=24249114) +3585 train 7.127439 (lr=2.7958e-05) (hash(x)=23659934) +3586 train 7.111472 (lr=2.7934e-05) (hash(x)=25995600) +3587 train 7.090261 (lr=2.7910e-05) (hash(x)=29462219) +3588 train 7.224585 (lr=2.7887e-05) (hash(x)=23346714) +3589 train 7.346446 (lr=2.7863e-05) (hash(x)=27168432) +3590 train 7.126941 (lr=2.7840e-05) (hash(x)=23954240) +3591 train 7.094627 (lr=2.7817e-05) (hash(x)=24748522) +3592 train 7.269965 (lr=2.7793e-05) (hash(x)=24887007) +3593 train 7.052481 (lr=2.7770e-05) (hash(x)=25539383) +3594 train 6.979141 (lr=2.7746e-05) (hash(x)=20104613) +3595 train 7.461546 (lr=2.7723e-05) (hash(x)=24843486) +3596 train 7.473848 (lr=2.7699e-05) (hash(x)=24357864) +3597 train 7.163681 (lr=2.7676e-05) (hash(x)=23873745) +3598 train 7.349608 (lr=2.7652e-05) (hash(x)=25142829) +3599 train 7.374944 (lr=2.7629e-05) (hash(x)=24965317) +3600 val loss 7.2712 +3600 val perplexity 1438.2057 +3600 train 6.869157 (lr=2.7606e-05) (hash(x)=18505205) +3601 train 6.946785 (lr=2.7582e-05) (hash(x)=23632877) +3602 train 7.134324 (lr=2.7559e-05) (hash(x)=23704554) +3603 train 7.281237 (lr=2.7536e-05) (hash(x)=26584754) +3604 train 6.915731 (lr=2.7512e-05) (hash(x)=20667709) +3605 train 6.812530 (lr=2.7489e-05) (hash(x)=20573248) +3606 train 6.928447 (lr=2.7466e-05) (hash(x)=23998997) +3607 train 7.133442 (lr=2.7442e-05) (hash(x)=22031210) +3608 train 7.202966 (lr=2.7419e-05) (hash(x)=24124536) +3609 train 7.113441 (lr=2.7396e-05) (hash(x)=22650144) +3610 train 7.164196 (lr=2.7373e-05) (hash(x)=23796998) +3611 train 7.228293 (lr=2.7349e-05) (hash(x)=24860582) +3612 train 6.783326 (lr=2.7326e-05) (hash(x)=20591300) +3613 train 7.167436 (lr=2.7303e-05) (hash(x)=23447130) +3614 train 7.170043 (lr=2.7280e-05) (hash(x)=26237963) +3615 train 7.261659 (lr=2.7257e-05) (hash(x)=25877990) +3616 train 7.088329 (lr=2.7233e-05) (hash(x)=24808003) +3617 train 7.265840 (lr=2.7210e-05) (hash(x)=24103543) +3618 train 7.175282 (lr=2.7187e-05) (hash(x)=24877184) +3619 train 7.287346 (lr=2.7164e-05) (hash(x)=24970646) +3620 train 7.206178 (lr=2.7141e-05) (hash(x)=25764524) +3621 train 7.356564 (lr=2.7118e-05) (hash(x)=25313591) +3622 train 7.238751 (lr=2.7095e-05) (hash(x)=23260940) +3623 train 7.150598 (lr=2.7071e-05) (hash(x)=24382381) +3624 train 7.127674 (lr=2.7048e-05) (hash(x)=24618902) +3625 train 7.281014 (lr=2.7025e-05) (hash(x)=25074871) +3626 train 6.986037 (lr=2.7002e-05) (hash(x)=24472251) +3627 train 7.111738 (lr=2.6979e-05) (hash(x)=25221746) +3628 train 7.212598 (lr=2.6956e-05) (hash(x)=27448790) +3629 train 7.185960 (lr=2.6933e-05) (hash(x)=25221431) +3630 train 6.805218 (lr=2.6910e-05) (hash(x)=22034366) +3631 train 7.336376 (lr=2.6887e-05) (hash(x)=24551999) +3632 train 7.054515 (lr=2.6864e-05) (hash(x)=24330217) +3633 train 7.150680 (lr=2.6841e-05) (hash(x)=22792380) +3634 train 6.977755 (lr=2.6818e-05) (hash(x)=22393767) +3635 train 7.297270 (lr=2.6795e-05) (hash(x)=28151378) +3636 train 7.306850 (lr=2.6772e-05) (hash(x)=26999341) +3637 train 7.288976 (lr=2.6749e-05) (hash(x)=27251870) +3638 train 7.237766 (lr=2.6726e-05) (hash(x)=23439462) +3639 train 7.389588 (lr=2.6703e-05) (hash(x)=25765516) +3640 train 7.171916 (lr=2.6681e-05) (hash(x)=24720171) +3641 train 7.395160 (lr=2.6658e-05) (hash(x)=23927187) +3642 train 7.151522 (lr=2.6635e-05) (hash(x)=23879561) +3643 train 7.286510 (lr=2.6612e-05) (hash(x)=25630696) +3644 train 6.920162 (lr=2.6589e-05) (hash(x)=22030016) +3645 train 7.369038 (lr=2.6566e-05) (hash(x)=28781600) +3646 train 7.327190 (lr=2.6543e-05) (hash(x)=26668019) +3647 train 7.355859 (lr=2.6521e-05) (hash(x)=25204247) +3648 train 7.626610 (lr=2.6498e-05) (hash(x)=31261394) +3649 train 7.399213 (lr=2.6475e-05) (hash(x)=26193103) +3650 val loss 7.2770 +3650 val perplexity 1446.6511 +3650 train 7.216286 (lr=2.6452e-05) (hash(x)=23872456) +3651 train 7.098091 (lr=2.6430e-05) (hash(x)=26326447) +3652 train 7.114798 (lr=2.6407e-05) (hash(x)=26449631) +3653 train 7.368749 (lr=2.6384e-05) (hash(x)=26373461) +3654 train 7.235602 (lr=2.6361e-05) (hash(x)=24882768) +3655 train 7.312269 (lr=2.6339e-05) (hash(x)=26321813) +3656 train 7.328528 (lr=2.6316e-05) (hash(x)=27056428) +3657 train 7.299886 (lr=2.6293e-05) (hash(x)=24583976) +3658 train 6.972292 (lr=2.6271e-05) (hash(x)=22259624) +3659 train 7.167568 (lr=2.6248e-05) (hash(x)=25400396) +3660 train 7.009230 (lr=2.6225e-05) (hash(x)=21095507) +3661 train 7.255487 (lr=2.6203e-05) (hash(x)=27231042) +3662 train 7.032941 (lr=2.6180e-05) (hash(x)=27292771) +3663 train 7.502797 (lr=2.6157e-05) (hash(x)=25528323) +3664 train 7.209529 (lr=2.6135e-05) (hash(x)=24374502) +3665 train 7.013028 (lr=2.6112e-05) (hash(x)=22463800) +3666 train 7.327943 (lr=2.6090e-05) (hash(x)=25413960) +3667 train 7.215233 (lr=2.6067e-05) (hash(x)=24035353) +3668 train 7.150247 (lr=2.6044e-05) (hash(x)=24815852) +3669 train 7.017223 (lr=2.6022e-05) (hash(x)=22995856) +3670 train 7.293122 (lr=2.5999e-05) (hash(x)=28128238) +3671 train 7.311614 (lr=2.5977e-05) (hash(x)=25114729) +3672 train 7.043405 (lr=2.5954e-05) (hash(x)=19337726) +3673 train 7.509674 (lr=2.5932e-05) (hash(x)=26674420) +3674 train 6.995795 (lr=2.5909e-05) (hash(x)=22553270) +3675 train 6.822765 (lr=2.5887e-05) (hash(x)=21634962) +3676 train 7.040730 (lr=2.5865e-05) (hash(x)=23362669) +3677 train 7.193027 (lr=2.5842e-05) (hash(x)=24781824) +3678 train 6.754646 (lr=2.5820e-05) (hash(x)=17909688) +3679 train 8.022571 (lr=2.5797e-05) (hash(x)=31341964) +3680 train 7.476932 (lr=2.5775e-05) (hash(x)=29071335) +3681 train 6.856703 (lr=2.5752e-05) (hash(x)=19486640) +3682 train 7.047691 (lr=2.5730e-05) (hash(x)=24301133) +3683 train 7.231914 (lr=2.5708e-05) (hash(x)=29172813) +3684 train 7.731028 (lr=2.5685e-05) (hash(x)=31501337) +3685 train 7.364964 (lr=2.5663e-05) (hash(x)=27377840) +3686 train 7.162892 (lr=2.5641e-05) (hash(x)=24499761) +3687 train 7.162609 (lr=2.5618e-05) (hash(x)=26326024) +3688 train 7.124295 (lr=2.5596e-05) (hash(x)=23179996) +3689 train 6.828955 (lr=2.5574e-05) (hash(x)=20963675) +3690 train 7.112991 (lr=2.5552e-05) (hash(x)=26650521) +3691 train 6.810411 (lr=2.5529e-05) (hash(x)=20140071) +3692 train 6.862097 (lr=2.5507e-05) (hash(x)=21734340) +3693 train 7.153169 (lr=2.5485e-05) (hash(x)=23848422) +3694 train 7.235937 (lr=2.5463e-05) (hash(x)=27499953) +3695 train 7.446592 (lr=2.5440e-05) (hash(x)=27273311) +3696 train 7.375061 (lr=2.5418e-05) (hash(x)=25741091) +3697 train 7.090008 (lr=2.5396e-05) (hash(x)=22010794) +3698 train 7.202114 (lr=2.5374e-05) (hash(x)=24616138) +3699 train 7.526897 (lr=2.5352e-05) (hash(x)=31276487) +3700 val loss 7.2686 +3700 val perplexity 1434.5619 +3700 train 7.228763 (lr=2.5329e-05) (hash(x)=24042922) +3701 train 6.990170 (lr=2.5307e-05) (hash(x)=21985431) +3702 train 6.849536 (lr=2.5285e-05) (hash(x)=21336316) +3703 train 6.695387 (lr=2.5263e-05) (hash(x)=17819313) +3704 train 7.329816 (lr=2.5241e-05) (hash(x)=27033851) +3705 train 7.337076 (lr=2.5219e-05) (hash(x)=27260043) +3706 train 7.412085 (lr=2.5197e-05) (hash(x)=26847649) +3707 train 7.369420 (lr=2.5175e-05) (hash(x)=25843618) +3708 train 7.347515 (lr=2.5153e-05) (hash(x)=25828009) +3709 train 7.414192 (lr=2.5131e-05) (hash(x)=24960960) +3710 train 7.485973 (lr=2.5109e-05) (hash(x)=24852741) +3711 train 6.925084 (lr=2.5087e-05) (hash(x)=23769243) +3712 train 7.154541 (lr=2.5065e-05) (hash(x)=27110690) +3713 train 7.179393 (lr=2.5043e-05) (hash(x)=22817285) +3714 train 6.847891 (lr=2.5021e-05) (hash(x)=19618355) +3715 train 7.444620 (lr=2.4999e-05) (hash(x)=28731298) +3716 train 7.164339 (lr=2.4977e-05) (hash(x)=23091196) +3717 train 7.698608 (lr=2.4955e-05) (hash(x)=28825233) +3718 train 7.234155 (lr=2.4933e-05) (hash(x)=25778506) +3719 train 7.206594 (lr=2.4911e-05) (hash(x)=23788738) +3720 train 6.580095 (lr=2.4889e-05) (hash(x)=16684794) +3721 train 7.051033 (lr=2.4867e-05) (hash(x)=24755102) +3722 train 7.368907 (lr=2.4845e-05) (hash(x)=26839238) +3723 train 7.381262 (lr=2.4824e-05) (hash(x)=26599031) +3724 train 7.243936 (lr=2.4802e-05) (hash(x)=25945650) +3725 train 7.424077 (lr=2.4780e-05) (hash(x)=27434751) +3726 train 7.176313 (lr=2.4758e-05) (hash(x)=24814591) +3727 train 7.137760 (lr=2.4736e-05) (hash(x)=24818744) +3728 train 7.210231 (lr=2.4714e-05) (hash(x)=25649817) +3729 train 7.090579 (lr=2.4693e-05) (hash(x)=24987021) +3730 train 7.069279 (lr=2.4671e-05) (hash(x)=24667779) +3731 train 7.026303 (lr=2.4649e-05) (hash(x)=23053871) +3732 train 6.755768 (lr=2.4627e-05) (hash(x)=19264856) +3733 train 7.324741 (lr=2.4606e-05) (hash(x)=23718117) +3734 train 7.045462 (lr=2.4584e-05) (hash(x)=21904779) +3735 train 7.237618 (lr=2.4562e-05) (hash(x)=23472795) +3736 train 7.436453 (lr=2.4541e-05) (hash(x)=24650440) +3737 train 7.527051 (lr=2.4519e-05) (hash(x)=25243911) +3738 train 7.898980 (lr=2.4497e-05) (hash(x)=30423616) +3739 train 7.913135 (lr=2.4476e-05) (hash(x)=29748225) +3740 train 7.312219 (lr=2.4454e-05) (hash(x)=25180684) +3741 train 7.330641 (lr=2.4432e-05) (hash(x)=25619065) +3742 train 7.708967 (lr=2.4411e-05) (hash(x)=31847002) +3743 train 7.253120 (lr=2.4389e-05) (hash(x)=24991832) +3744 train 7.198473 (lr=2.4368e-05) (hash(x)=23836263) +3745 train 7.085007 (lr=2.4346e-05) (hash(x)=24651902) +3746 train 7.594311 (lr=2.4324e-05) (hash(x)=22936538) +3747 train 7.596478 (lr=2.4303e-05) (hash(x)=23681545) +3748 train 7.036049 (lr=2.4281e-05) (hash(x)=21140825) +3749 train 7.198567 (lr=2.4260e-05) (hash(x)=24932453) +3750 val loss 7.2665 +3750 val perplexity 1431.5880 +3750 train 7.348564 (lr=2.4238e-05) (hash(x)=25919062) +3751 train 7.135525 (lr=2.4217e-05) (hash(x)=22424066) +3752 train 7.188993 (lr=2.4195e-05) (hash(x)=23542210) +3753 train 7.077817 (lr=2.4174e-05) (hash(x)=22113561) +3754 train 6.961366 (lr=2.4152e-05) (hash(x)=24892794) +3755 train 7.450841 (lr=2.4131e-05) (hash(x)=25262748) +3756 train 7.233292 (lr=2.4110e-05) (hash(x)=24477975) +3757 train 7.024306 (lr=2.4088e-05) (hash(x)=24681189) +3758 train 7.044612 (lr=2.4067e-05) (hash(x)=24052603) +3759 train 7.274812 (lr=2.4045e-05) (hash(x)=26474878) +3760 train 7.823971 (lr=2.4024e-05) (hash(x)=28228836) +3761 train 7.360085 (lr=2.4003e-05) (hash(x)=23832522) +3762 train 7.301764 (lr=2.3981e-05) (hash(x)=24416789) +3763 train 7.076125 (lr=2.3960e-05) (hash(x)=23930593) +3764 train 7.128445 (lr=2.3939e-05) (hash(x)=23895092) +3765 train 7.087198 (lr=2.3917e-05) (hash(x)=26865287) +3766 train 7.121910 (lr=2.3896e-05) (hash(x)=21330722) +3767 train 7.210057 (lr=2.3875e-05) (hash(x)=22704349) +3768 train 7.310537 (lr=2.3854e-05) (hash(x)=27740886) +3769 train 7.281418 (lr=2.3832e-05) (hash(x)=24935936) +3770 train 7.154755 (lr=2.3811e-05) (hash(x)=23497487) +3771 train 7.353899 (lr=2.3790e-05) (hash(x)=24801048) +3772 train 7.111990 (lr=2.3769e-05) (hash(x)=25490486) +3773 train 7.130460 (lr=2.3747e-05) (hash(x)=21166466) +3774 train 7.344331 (lr=2.3726e-05) (hash(x)=23225244) +3775 train 7.127609 (lr=2.3705e-05) (hash(x)=22293673) +3776 train 7.422481 (lr=2.3684e-05) (hash(x)=25700016) +3777 train 6.987212 (lr=2.3663e-05) (hash(x)=22370207) +3778 train 7.289276 (lr=2.3642e-05) (hash(x)=25224849) +3779 train 7.222337 (lr=2.3621e-05) (hash(x)=23311934) +3780 train 6.973030 (lr=2.3599e-05) (hash(x)=19627124) +3781 train 7.563354 (lr=2.3578e-05) (hash(x)=27132838) +3782 train 7.390973 (lr=2.3557e-05) (hash(x)=27242104) +3783 train 6.927184 (lr=2.3536e-05) (hash(x)=21785487) +3784 train 7.216373 (lr=2.3515e-05) (hash(x)=25798262) +3785 train 7.137174 (lr=2.3494e-05) (hash(x)=24806937) +3786 train 6.961446 (lr=2.3473e-05) (hash(x)=24098756) +3787 train 6.979872 (lr=2.3452e-05) (hash(x)=22981456) +3788 train 7.437376 (lr=2.3431e-05) (hash(x)=22441908) +3789 train 7.329002 (lr=2.3410e-05) (hash(x)=25867804) +3790 train 7.227690 (lr=2.3389e-05) (hash(x)=22835586) +3791 train 7.466232 (lr=2.3368e-05) (hash(x)=25251063) +3792 train 7.262079 (lr=2.3347e-05) (hash(x)=27059729) +3793 train 7.235185 (lr=2.3326e-05) (hash(x)=23819311) +3794 train 6.969786 (lr=2.3305e-05) (hash(x)=21345757) +3795 train 7.179044 (lr=2.3284e-05) (hash(x)=25796422) +3796 train 6.907613 (lr=2.3264e-05) (hash(x)=21414971) +3797 train 7.180908 (lr=2.3243e-05) (hash(x)=26120920) +3798 train 7.106952 (lr=2.3222e-05) (hash(x)=22008247) +3799 train 7.182267 (lr=2.3201e-05) (hash(x)=22722211) +3800 val loss 7.2624 +3800 val perplexity 1425.6776 +3800 train 6.943440 (lr=2.3180e-05) (hash(x)=24484513) +3801 train 7.281896 (lr=2.3159e-05) (hash(x)=24463866) +3802 train 7.244328 (lr=2.3139e-05) (hash(x)=26470775) +3803 train 7.266863 (lr=2.3118e-05) (hash(x)=24296755) +3804 train 7.259927 (lr=2.3097e-05) (hash(x)=24381309) +3805 train 7.448349 (lr=2.3076e-05) (hash(x)=26781262) +3806 train 6.997243 (lr=2.3055e-05) (hash(x)=23563137) +3807 train 7.189026 (lr=2.3035e-05) (hash(x)=24522269) +3808 train 6.970183 (lr=2.3014e-05) (hash(x)=22871995) +3809 train 7.309185 (lr=2.2993e-05) (hash(x)=24751946) +3810 train 7.135849 (lr=2.2973e-05) (hash(x)=19879741) +3811 train 7.193130 (lr=2.2952e-05) (hash(x)=25617184) +3812 train 6.920973 (lr=2.2931e-05) (hash(x)=21776722) +3813 train 6.996922 (lr=2.2911e-05) (hash(x)=22663402) +3814 train 7.348056 (lr=2.2890e-05) (hash(x)=26072046) +3815 train 7.042468 (lr=2.2869e-05) (hash(x)=23329475) +3816 train 7.112793 (lr=2.2849e-05) (hash(x)=25519031) +3817 train 7.082181 (lr=2.2828e-05) (hash(x)=22846270) +3818 train 7.081096 (lr=2.2808e-05) (hash(x)=20299429) +3819 train 7.534329 (lr=2.2787e-05) (hash(x)=30652062) +3820 train 6.877959 (lr=2.2766e-05) (hash(x)=19824665) +3821 train 7.419551 (lr=2.2746e-05) (hash(x)=26698904) +3822 train 7.236088 (lr=2.2725e-05) (hash(x)=27612163) +3823 train 7.039444 (lr=2.2705e-05) (hash(x)=24735165) +3824 train 6.820638 (lr=2.2684e-05) (hash(x)=19965890) +3825 train 6.974228 (lr=2.2664e-05) (hash(x)=23518594) +3826 train 6.951990 (lr=2.2643e-05) (hash(x)=22388460) +3827 train 7.029045 (lr=2.2623e-05) (hash(x)=23795686) +3828 train 6.950104 (lr=2.2602e-05) (hash(x)=24470150) +3829 train 6.604763 (lr=2.2582e-05) (hash(x)=19483392) +3830 train 7.070208 (lr=2.2562e-05) (hash(x)=23304516) +3831 train 7.373921 (lr=2.2541e-05) (hash(x)=27002892) +3832 train 7.093163 (lr=2.2521e-05) (hash(x)=22114813) +3833 train 7.241803 (lr=2.2500e-05) (hash(x)=26221916) +3834 train 6.846887 (lr=2.2480e-05) (hash(x)=27261960) +3835 train 7.082551 (lr=2.2460e-05) (hash(x)=21189101) +3836 train 6.780862 (lr=2.2439e-05) (hash(x)=20638173) +3837 train 7.210579 (lr=2.2419e-05) (hash(x)=25497439) +3838 train 6.695731 (lr=2.2399e-05) (hash(x)=20460499) +3839 train 7.114877 (lr=2.2378e-05) (hash(x)=23499349) +3840 train 7.965875 (lr=2.2358e-05) (hash(x)=22671939) +3841 train 8.042960 (lr=2.2338e-05) (hash(x)=26809295) +3842 train 7.232137 (lr=2.2318e-05) (hash(x)=28094504) +3843 train 7.198338 (lr=2.2297e-05) (hash(x)=26807896) +3844 train 7.302151 (lr=2.2277e-05) (hash(x)=24749334) +3845 train 7.204523 (lr=2.2257e-05) (hash(x)=25031330) +3846 train 7.104920 (lr=2.2237e-05) (hash(x)=23008126) +3847 train 7.059170 (lr=2.2217e-05) (hash(x)=22461589) +3848 train 7.349740 (lr=2.2196e-05) (hash(x)=24959391) +3849 train 7.236189 (lr=2.2176e-05) (hash(x)=24239512) +3850 val loss 7.2685 +3850 val perplexity 1434.3615 +3850 train 7.081157 (lr=2.2156e-05) (hash(x)=24760422) +3851 train 7.520923 (lr=2.2136e-05) (hash(x)=26904123) +3852 train 6.688895 (lr=2.2116e-05) (hash(x)=17986444) +3853 train 7.054346 (lr=2.2096e-05) (hash(x)=21618533) +3854 train 7.098383 (lr=2.2076e-05) (hash(x)=27107027) +3855 train 7.360414 (lr=2.2056e-05) (hash(x)=26415040) +3856 train 7.909233 (lr=2.2036e-05) (hash(x)=28682703) +3857 train 7.037393 (lr=2.2016e-05) (hash(x)=22824767) +3858 train 7.218159 (lr=2.1996e-05) (hash(x)=24540450) +3859 train 7.192351 (lr=2.1975e-05) (hash(x)=24463181) +3860 train 7.086183 (lr=2.1955e-05) (hash(x)=22832558) +3861 train 7.328854 (lr=2.1936e-05) (hash(x)=26582384) +3862 train 7.993146 (lr=2.1916e-05) (hash(x)=32327364) +3863 train 7.341266 (lr=2.1896e-05) (hash(x)=26349465) +3864 train 7.094948 (lr=2.1876e-05) (hash(x)=23079414) +3865 train 7.123573 (lr=2.1856e-05) (hash(x)=23464639) +3866 train 6.959785 (lr=2.1836e-05) (hash(x)=21406620) +3867 train 6.798053 (lr=2.1816e-05) (hash(x)=21205988) +3868 train 6.869220 (lr=2.1796e-05) (hash(x)=22742634) +3869 train 6.959396 (lr=2.1776e-05) (hash(x)=24868938) +3870 train 7.310965 (lr=2.1756e-05) (hash(x)=28095283) +3871 train 7.037083 (lr=2.1736e-05) (hash(x)=21596677) +3872 train 7.230830 (lr=2.1717e-05) (hash(x)=26884381) +3873 train 7.308460 (lr=2.1697e-05) (hash(x)=26410272) +3874 train 7.079074 (lr=2.1677e-05) (hash(x)=22915785) +3875 train 7.080569 (lr=2.1657e-05) (hash(x)=23575666) +3876 train 7.051015 (lr=2.1637e-05) (hash(x)=25313223) +3877 train 6.517197 (lr=2.1618e-05) (hash(x)=16319719) +3878 train 7.150082 (lr=2.1598e-05) (hash(x)=23227579) +3879 train 7.091311 (lr=2.1578e-05) (hash(x)=24117012) +3880 train 7.142775 (lr=2.1558e-05) (hash(x)=24681517) +3881 train 7.061980 (lr=2.1539e-05) (hash(x)=23186527) +3882 train 7.065598 (lr=2.1519e-05) (hash(x)=23472784) +3883 train 7.102006 (lr=2.1499e-05) (hash(x)=26013014) +3884 train 7.267644 (lr=2.1480e-05) (hash(x)=25952206) +3885 train 7.374770 (lr=2.1460e-05) (hash(x)=23897834) +3886 train 7.131230 (lr=2.1440e-05) (hash(x)=26350364) +3887 train 7.147134 (lr=2.1421e-05) (hash(x)=24105761) +3888 train 7.216236 (lr=2.1401e-05) (hash(x)=22801707) +3889 train 7.083305 (lr=2.1382e-05) (hash(x)=21821937) +3890 train 7.041765 (lr=2.1362e-05) (hash(x)=24264640) +3891 train 6.994444 (lr=2.1343e-05) (hash(x)=20369133) +3892 train 6.969075 (lr=2.1323e-05) (hash(x)=24313506) +3893 train 6.994904 (lr=2.1303e-05) (hash(x)=22104086) +3894 train 7.194833 (lr=2.1284e-05) (hash(x)=25312602) +3895 train 7.280859 (lr=2.1264e-05) (hash(x)=25725049) +3896 train 7.091753 (lr=2.1245e-05) (hash(x)=22981231) +3897 train 6.958412 (lr=2.1226e-05) (hash(x)=18021467) +3898 train 6.924529 (lr=2.1206e-05) (hash(x)=17960254) +3899 train 7.092745 (lr=2.1187e-05) (hash(x)=19808118) +3900 val loss 7.2581 +3900 val perplexity 1419.5082 +3900 train 6.866737 (lr=2.1167e-05) (hash(x)=21022829) +3901 train 7.022851 (lr=2.1148e-05) (hash(x)=22434663) +3902 train 6.809032 (lr=2.1128e-05) (hash(x)=20208091) +3903 train 6.939160 (lr=2.1109e-05) (hash(x)=22892776) +3904 train 7.037018 (lr=2.1090e-05) (hash(x)=21554367) +3905 train 7.174757 (lr=2.1070e-05) (hash(x)=23704875) +3906 train 7.178391 (lr=2.1051e-05) (hash(x)=21690340) +3907 train 7.095500 (lr=2.1032e-05) (hash(x)=23736780) +3908 train 6.961048 (lr=2.1012e-05) (hash(x)=21060920) +3909 train 6.914685 (lr=2.0993e-05) (hash(x)=20091559) +3910 train 7.177839 (lr=2.0974e-05) (hash(x)=22147974) +3911 train 7.114203 (lr=2.0954e-05) (hash(x)=21630383) +3912 train 7.369138 (lr=2.0935e-05) (hash(x)=28339385) +3913 train 7.127946 (lr=2.0916e-05) (hash(x)=25355505) +3914 train 7.028788 (lr=2.0897e-05) (hash(x)=20843914) +3915 train 7.542100 (lr=2.0878e-05) (hash(x)=25397467) +3916 train 7.183890 (lr=2.0858e-05) (hash(x)=23587501) +3917 train 6.812485 (lr=2.0839e-05) (hash(x)=19036533) +3918 train 7.021364 (lr=2.0820e-05) (hash(x)=29749389) +3919 train 6.912797 (lr=2.0801e-05) (hash(x)=24727094) +3920 train 6.926858 (lr=2.0782e-05) (hash(x)=22723450) +3921 train 7.109632 (lr=2.0763e-05) (hash(x)=24424680) +3922 train 7.252950 (lr=2.0744e-05) (hash(x)=25817917) +3923 train 7.044363 (lr=2.0724e-05) (hash(x)=23951182) +3924 train 7.079704 (lr=2.0705e-05) (hash(x)=21177944) +3925 train 6.904030 (lr=2.0686e-05) (hash(x)=23533768) +3926 train 7.127822 (lr=2.0667e-05) (hash(x)=24263615) +3927 train 6.934963 (lr=2.0648e-05) (hash(x)=22835000) +3928 train 7.170101 (lr=2.0629e-05) (hash(x)=26076156) +3929 train 7.118476 (lr=2.0610e-05) (hash(x)=25171508) +3930 train 7.109821 (lr=2.0591e-05) (hash(x)=22021396) +3931 train 7.446419 (lr=2.0572e-05) (hash(x)=28767849) +3932 train 7.369672 (lr=2.0553e-05) (hash(x)=29497606) +3933 train 7.005495 (lr=2.0534e-05) (hash(x)=22723124) +3934 train 7.278736 (lr=2.0515e-05) (hash(x)=27106616) +3935 train 7.120673 (lr=2.0496e-05) (hash(x)=22839049) +3936 train 7.154661 (lr=2.0478e-05) (hash(x)=25101923) +3937 train 7.131400 (lr=2.0459e-05) (hash(x)=25945975) +3938 train 7.273563 (lr=2.0440e-05) (hash(x)=25382013) +3939 train 6.840393 (lr=2.0421e-05) (hash(x)=19930900) +3940 train 6.992301 (lr=2.0402e-05) (hash(x)=22202373) +3941 train 7.124226 (lr=2.0383e-05) (hash(x)=24592992) +3942 train 7.039418 (lr=2.0364e-05) (hash(x)=25002271) +3943 train 6.914193 (lr=2.0346e-05) (hash(x)=20654136) +3944 train 6.967678 (lr=2.0327e-05) (hash(x)=20061590) +3945 train 6.922143 (lr=2.0308e-05) (hash(x)=21441361) +3946 train 7.119284 (lr=2.0289e-05) (hash(x)=20055468) +3947 train 7.793349 (lr=2.0271e-05) (hash(x)=28495621) +3948 train 7.227501 (lr=2.0252e-05) (hash(x)=25959236) +3949 train 7.555479 (lr=2.0233e-05) (hash(x)=26750193) +3950 val loss 7.2569 +3950 val perplexity 1417.7953 +3950 train 7.390177 (lr=2.0215e-05) (hash(x)=25882605) +3951 train 7.444864 (lr=2.0196e-05) (hash(x)=26776000) +3952 train 7.039499 (lr=2.0177e-05) (hash(x)=24155107) +3953 train 7.135605 (lr=2.0159e-05) (hash(x)=23441845) +3954 train 7.064605 (lr=2.0140e-05) (hash(x)=22860915) +3955 train 6.847347 (lr=2.0121e-05) (hash(x)=21584429) +3956 train 6.463548 (lr=2.0103e-05) (hash(x)=16535556) +3957 train 6.553783 (lr=2.0084e-05) (hash(x)=17946180) +3958 train 7.058735 (lr=2.0066e-05) (hash(x)=25367610) +3959 train 6.973946 (lr=2.0047e-05) (hash(x)=22560658) +3960 train 7.226407 (lr=2.0028e-05) (hash(x)=23809585) +3961 train 7.458858 (lr=2.0010e-05) (hash(x)=20438213) +3962 train 7.757434 (lr=1.9991e-05) (hash(x)=30520037) +3963 train 7.462390 (lr=1.9973e-05) (hash(x)=25276565) +3964 train 7.160816 (lr=1.9954e-05) (hash(x)=26796532) +3965 train 6.964914 (lr=1.9936e-05) (hash(x)=22850475) +3966 train 7.449379 (lr=1.9917e-05) (hash(x)=25983698) +3967 train 7.347114 (lr=1.9899e-05) (hash(x)=25995933) +3968 train 7.551528 (lr=1.9881e-05) (hash(x)=25319339) +3969 train 7.180907 (lr=1.9862e-05) (hash(x)=25066892) +3970 train 7.360512 (lr=1.9844e-05) (hash(x)=26931819) +3971 train 7.304718 (lr=1.9825e-05) (hash(x)=24163910) +3972 train 7.230680 (lr=1.9807e-05) (hash(x)=25359634) +3973 train 7.151448 (lr=1.9789e-05) (hash(x)=24323444) +3974 train 7.286655 (lr=1.9770e-05) (hash(x)=26529231) +3975 train 7.296010 (lr=1.9752e-05) (hash(x)=24635394) +3976 train 7.584383 (lr=1.9734e-05) (hash(x)=24783093) +3977 train 7.705125 (lr=1.9716e-05) (hash(x)=26710509) +3978 train 7.140041 (lr=1.9697e-05) (hash(x)=25396630) +3979 train 7.052254 (lr=1.9679e-05) (hash(x)=22556381) +3980 train 7.357282 (lr=1.9661e-05) (hash(x)=26912161) +3981 train 6.936830 (lr=1.9643e-05) (hash(x)=22268078) +3982 train 7.902248 (lr=1.9624e-05) (hash(x)=30430328) +3983 train 7.537224 (lr=1.9606e-05) (hash(x)=27537228) +3984 train 6.995328 (lr=1.9588e-05) (hash(x)=24468603) +3985 train 7.348474 (lr=1.9570e-05) (hash(x)=27006663) +3986 train 7.557740 (lr=1.9552e-05) (hash(x)=27014728) +3987 train 6.987566 (lr=1.9533e-05) (hash(x)=20883633) +3988 train 7.090970 (lr=1.9515e-05) (hash(x)=23361791) +3989 train 7.224699 (lr=1.9497e-05) (hash(x)=26775925) +3990 train 7.775127 (lr=1.9479e-05) (hash(x)=30648934) +3991 train 7.311232 (lr=1.9461e-05) (hash(x)=26496730) +3992 train 7.105630 (lr=1.9443e-05) (hash(x)=25942897) +3993 train 7.094756 (lr=1.9425e-05) (hash(x)=24887111) +3994 train 6.998628 (lr=1.9407e-05) (hash(x)=22908550) +3995 train 6.750473 (lr=1.9389e-05) (hash(x)=20342150) +3996 train 7.000378 (lr=1.9371e-05) (hash(x)=22261760) +3997 train 7.040336 (lr=1.9353e-05) (hash(x)=22731641) +3998 train 6.960004 (lr=1.9335e-05) (hash(x)=20669749) +3999 train 6.917806 (lr=1.9317e-05) (hash(x)=16533310) +4000 val loss 7.2519 +4000 val perplexity 1410.8073 +4000 train 7.086201 (lr=1.9299e-05) (hash(x)=23661341) +4001 train 7.087288 (lr=1.9281e-05) (hash(x)=24644301) +4002 train 6.926353 (lr=1.9263e-05) (hash(x)=22938438) +4003 train 7.040864 (lr=1.9245e-05) (hash(x)=24315862) +4004 train 7.245325 (lr=1.9228e-05) (hash(x)=25169315) +4005 train 7.180469 (lr=1.9210e-05) (hash(x)=24752796) +4006 train 7.177413 (lr=1.9192e-05) (hash(x)=23103706) +4007 train 7.229926 (lr=1.9174e-05) (hash(x)=24881176) +4008 train 7.103860 (lr=1.9156e-05) (hash(x)=23971947) +4009 train 7.450788 (lr=1.9138e-05) (hash(x)=27741054) +4010 train 7.796773 (lr=1.9121e-05) (hash(x)=30956251) +4011 train 7.206573 (lr=1.9103e-05) (hash(x)=23649686) +4012 train 7.061855 (lr=1.9085e-05) (hash(x)=23344798) +4013 train 7.668399 (lr=1.9067e-05) (hash(x)=29529498) +4014 train 7.186538 (lr=1.9050e-05) (hash(x)=24688359) +4015 train 7.171689 (lr=1.9032e-05) (hash(x)=25593613) +4016 train 7.257964 (lr=1.9014e-05) (hash(x)=25674488) +4017 train 6.746225 (lr=1.8997e-05) (hash(x)=21345346) +4018 train 7.069744 (lr=1.8979e-05) (hash(x)=21978324) +4019 train 7.060979 (lr=1.8961e-05) (hash(x)=23669244) +4020 train 6.959947 (lr=1.8944e-05) (hash(x)=22479613) +4021 train 6.941979 (lr=1.8926e-05) (hash(x)=22855256) +4022 train 7.337926 (lr=1.8908e-05) (hash(x)=19759826) +4023 train 7.243800 (lr=1.8891e-05) (hash(x)=22886646) +4024 train 7.188938 (lr=1.8873e-05) (hash(x)=25553008) +4025 train 7.075953 (lr=1.8856e-05) (hash(x)=25487028) +4026 train 7.620946 (lr=1.8838e-05) (hash(x)=26799246) +4027 train 7.940216 (lr=1.8821e-05) (hash(x)=30728540) +4028 train 7.374843 (lr=1.8803e-05) (hash(x)=23966676) +4029 train 7.090503 (lr=1.8786e-05) (hash(x)=22118783) +4030 train 7.192600 (lr=1.8768e-05) (hash(x)=24744703) +4031 train 7.171498 (lr=1.8751e-05) (hash(x)=21407676) +4032 train 7.171071 (lr=1.8733e-05) (hash(x)=20623349) +4033 train 6.916574 (lr=1.8716e-05) (hash(x)=24723788) +4034 train 7.222638 (lr=1.8698e-05) (hash(x)=25030709) +4035 train 7.255323 (lr=1.8681e-05) (hash(x)=26326164) +4036 train 7.130930 (lr=1.8664e-05) (hash(x)=23754475) +4037 train 7.744937 (lr=1.8646e-05) (hash(x)=30112933) +4038 train 7.487817 (lr=1.8629e-05) (hash(x)=27474299) +4039 train 6.977217 (lr=1.8612e-05) (hash(x)=21720304) +4040 train 7.392880 (lr=1.8594e-05) (hash(x)=25142674) +4041 train 7.581819 (lr=1.8577e-05) (hash(x)=25284552) +4042 train 7.484848 (lr=1.8560e-05) (hash(x)=24554942) +4043 train 7.240216 (lr=1.8542e-05) (hash(x)=23773870) +4044 train 7.039516 (lr=1.8525e-05) (hash(x)=23896338) +4045 train 7.857285 (lr=1.8508e-05) (hash(x)=34984911) +4046 train 7.114658 (lr=1.8491e-05) (hash(x)=23854263) +4047 train 7.391984 (lr=1.8473e-05) (hash(x)=27263416) +4048 train 7.068655 (lr=1.8456e-05) (hash(x)=24989642) +4049 train 7.096233 (lr=1.8439e-05) (hash(x)=24492055) +4050 val loss 7.2551 +4050 val perplexity 1415.3251 +4050 train 7.009512 (lr=1.8422e-05) (hash(x)=21579916) +4051 train 7.230223 (lr=1.8405e-05) (hash(x)=25274710) +4052 train 7.114648 (lr=1.8388e-05) (hash(x)=24701947) +4053 train 7.113590 (lr=1.8371e-05) (hash(x)=25477340) +4054 train 7.026653 (lr=1.8353e-05) (hash(x)=23774195) +4055 train 7.289253 (lr=1.8336e-05) (hash(x)=25840801) +4056 train 7.494826 (lr=1.8319e-05) (hash(x)=27972529) +4057 train 7.243463 (lr=1.8302e-05) (hash(x)=26952458) +4058 train 6.791033 (lr=1.8285e-05) (hash(x)=22683653) +4059 train 6.798946 (lr=1.8268e-05) (hash(x)=20984129) +4060 train 6.995561 (lr=1.8251e-05) (hash(x)=22816482) +4061 train 7.254245 (lr=1.8234e-05) (hash(x)=24285302) +4062 train 7.663854 (lr=1.8217e-05) (hash(x)=31517950) +4063 train 7.977191 (lr=1.8200e-05) (hash(x)=31424568) +4064 train 7.626760 (lr=1.8183e-05) (hash(x)=29497876) +4065 train 7.433945 (lr=1.8166e-05) (hash(x)=27277376) +4066 train 7.215140 (lr=1.8149e-05) (hash(x)=26832588) +4067 train 7.063676 (lr=1.8133e-05) (hash(x)=25149712) +4068 train 7.033865 (lr=1.8116e-05) (hash(x)=23728457) +4069 train 6.959790 (lr=1.8099e-05) (hash(x)=25265136) +4070 train 7.498085 (lr=1.8082e-05) (hash(x)=25241681) +4071 train 7.202472 (lr=1.8065e-05) (hash(x)=23403065) +4072 train 7.155052 (lr=1.8048e-05) (hash(x)=25808207) +4073 train 7.093751 (lr=1.8031e-05) (hash(x)=23904844) +4074 train 6.759161 (lr=1.8015e-05) (hash(x)=18865309) +4075 train 7.227647 (lr=1.7998e-05) (hash(x)=23531744) +4076 train 7.270241 (lr=1.7981e-05) (hash(x)=25784275) +4077 train 6.989433 (lr=1.7964e-05) (hash(x)=22417529) +4078 train 6.985574 (lr=1.7948e-05) (hash(x)=23095491) +4079 train 7.136966 (lr=1.7931e-05) (hash(x)=22656033) +4080 train 7.129528 (lr=1.7914e-05) (hash(x)=25865435) +4081 train 7.264750 (lr=1.7898e-05) (hash(x)=25699377) +4082 train 7.252567 (lr=1.7881e-05) (hash(x)=20854084) +4083 train 6.838875 (lr=1.7864e-05) (hash(x)=18950799) +4084 train 7.057179 (lr=1.7848e-05) (hash(x)=22633739) +4085 train 7.906198 (lr=1.7831e-05) (hash(x)=34054446) +4086 train 7.364204 (lr=1.7815e-05) (hash(x)=27599387) +4087 train 7.215015 (lr=1.7798e-05) (hash(x)=26869295) +4088 train 7.217436 (lr=1.7781e-05) (hash(x)=24075139) +4089 train 7.621231 (lr=1.7765e-05) (hash(x)=29784110) +4090 train 7.922456 (lr=1.7748e-05) (hash(x)=34273918) +4091 train 8.450038 (lr=1.7732e-05) (hash(x)=34472685) +4092 train 7.759235 (lr=1.7715e-05) (hash(x)=30113791) +4093 train 6.934128 (lr=1.7699e-05) (hash(x)=22366381) +4094 train 7.175476 (lr=1.7682e-05) (hash(x)=24922935) +4095 train 7.374765 (lr=1.7666e-05) (hash(x)=25504151) +4096 train 7.326027 (lr=1.7649e-05) (hash(x)=24517375) +4097 train 7.995145 (lr=1.7633e-05) (hash(x)=25871651) +4098 train 7.096643 (lr=1.7617e-05) (hash(x)=23480225) +4099 train 6.955528 (lr=1.7600e-05) (hash(x)=22559978) +4100 val loss 7.2500 +4100 val perplexity 1408.0646 +4100 train 7.350560 (lr=1.7584e-05) (hash(x)=25795272) +4101 train 7.315654 (lr=1.7568e-05) (hash(x)=25440399) +4102 train 6.973303 (lr=1.7551e-05) (hash(x)=21581806) +4103 train 7.019155 (lr=1.7535e-05) (hash(x)=25781518) +4104 train 7.163939 (lr=1.7519e-05) (hash(x)=24682372) +4105 train 6.994874 (lr=1.7502e-05) (hash(x)=22440094) +4106 train 7.199916 (lr=1.7486e-05) (hash(x)=23661032) +4107 train 7.461289 (lr=1.7470e-05) (hash(x)=26966012) +4108 train 7.446572 (lr=1.7453e-05) (hash(x)=26232227) +4109 train 7.071928 (lr=1.7437e-05) (hash(x)=24110656) +4110 train 7.344340 (lr=1.7421e-05) (hash(x)=25938621) +4111 train 7.228088 (lr=1.7405e-05) (hash(x)=26432850) +4112 train 7.163080 (lr=1.7389e-05) (hash(x)=25387672) +4113 train 6.933892 (lr=1.7373e-05) (hash(x)=22740017) +4114 train 7.314009 (lr=1.7356e-05) (hash(x)=26384190) +4115 train 7.024279 (lr=1.7340e-05) (hash(x)=24725583) +4116 train 7.149135 (lr=1.7324e-05) (hash(x)=23986700) +4117 train 7.173457 (lr=1.7308e-05) (hash(x)=18529900) +4118 train 7.177083 (lr=1.7292e-05) (hash(x)=22236257) +4119 train 6.862944 (lr=1.7276e-05) (hash(x)=20155894) +4120 train 6.684757 (lr=1.7260e-05) (hash(x)=17423813) +4121 train 6.627328 (lr=1.7244e-05) (hash(x)=18905183) +4122 train 6.983137 (lr=1.7228e-05) (hash(x)=22534398) +4123 train 7.600923 (lr=1.7212e-05) (hash(x)=25247868) +4124 train 7.141282 (lr=1.7196e-05) (hash(x)=23994188) +4125 train 7.041460 (lr=1.7180e-05) (hash(x)=22929754) +4126 train 6.941978 (lr=1.7164e-05) (hash(x)=22485897) +4127 train 6.972261 (lr=1.7148e-05) (hash(x)=22270169) +4128 train 6.936218 (lr=1.7132e-05) (hash(x)=23638027) +4129 train 7.233974 (lr=1.7116e-05) (hash(x)=23821210) +4130 train 7.091423 (lr=1.7100e-05) (hash(x)=25021512) +4131 train 7.195798 (lr=1.7084e-05) (hash(x)=25240141) +4132 train 7.149342 (lr=1.7068e-05) (hash(x)=22833160) +4133 train 7.073688 (lr=1.7053e-05) (hash(x)=22909944) +4134 train 7.334470 (lr=1.7037e-05) (hash(x)=26163558) +4135 train 7.054868 (lr=1.7021e-05) (hash(x)=22108461) +4136 train 7.014565 (lr=1.7005e-05) (hash(x)=22549232) +4137 train 7.210203 (lr=1.6989e-05) (hash(x)=24701302) +4138 train 7.311437 (lr=1.6974e-05) (hash(x)=25206013) +4139 train 7.286092 (lr=1.6958e-05) (hash(x)=27896130) +4140 train 7.027233 (lr=1.6942e-05) (hash(x)=24106243) +4141 train 7.598514 (lr=1.6927e-05) (hash(x)=27158651) +4142 train 7.202782 (lr=1.6911e-05) (hash(x)=23841147) +4143 train 7.203344 (lr=1.6895e-05) (hash(x)=24802848) +4144 train 7.410877 (lr=1.6880e-05) (hash(x)=24911295) +4145 train 7.195813 (lr=1.6864e-05) (hash(x)=26473900) +4146 train 7.298698 (lr=1.6848e-05) (hash(x)=26785092) +4147 train 7.584572 (lr=1.6833e-05) (hash(x)=30188532) +4148 train 7.103268 (lr=1.6817e-05) (hash(x)=25010649) +4149 train 7.081509 (lr=1.6801e-05) (hash(x)=22409016) +4150 val loss 7.2497 +4150 val perplexity 1407.7498 +4150 train 7.819559 (lr=1.6786e-05) (hash(x)=31675024) +4151 train 7.113677 (lr=1.6770e-05) (hash(x)=25086604) +4152 train 7.096348 (lr=1.6755e-05) (hash(x)=24429343) +4153 train 7.278008 (lr=1.6739e-05) (hash(x)=25014232) +4154 train 7.203339 (lr=1.6724e-05) (hash(x)=25366275) +4155 train 7.697950 (lr=1.6708e-05) (hash(x)=24031473) +4156 train 7.218813 (lr=1.6693e-05) (hash(x)=26651059) +4157 train 7.296856 (lr=1.6677e-05) (hash(x)=26069721) +4158 train 7.410178 (lr=1.6662e-05) (hash(x)=28114382) +4159 train 7.396327 (lr=1.6647e-05) (hash(x)=26983186) +4160 train 6.805115 (lr=1.6631e-05) (hash(x)=21944670) +4161 train 7.502651 (lr=1.6616e-05) (hash(x)=28155702) +4162 train 6.968738 (lr=1.6600e-05) (hash(x)=24765002) +4163 train 7.213918 (lr=1.6585e-05) (hash(x)=26492636) +4164 train 7.197197 (lr=1.6570e-05) (hash(x)=24063705) +4165 train 7.475131 (lr=1.6554e-05) (hash(x)=27079573) +4166 train 7.138991 (lr=1.6539e-05) (hash(x)=24912201) +4167 train 7.194446 (lr=1.6524e-05) (hash(x)=27208507) +4168 train 7.141916 (lr=1.6509e-05) (hash(x)=25824320) +4169 train 7.691483 (lr=1.6493e-05) (hash(x)=29641677) +4170 train 7.388181 (lr=1.6478e-05) (hash(x)=26275614) +4171 train 7.202834 (lr=1.6463e-05) (hash(x)=25227725) +4172 train 7.301579 (lr=1.6448e-05) (hash(x)=27417375) +4173 train 7.465018 (lr=1.6433e-05) (hash(x)=25581973) +4174 train 7.737603 (lr=1.6417e-05) (hash(x)=30360417) +4175 train 7.026326 (lr=1.6402e-05) (hash(x)=23862845) +4176 train 7.137854 (lr=1.6387e-05) (hash(x)=25415130) +4177 train 7.090061 (lr=1.6372e-05) (hash(x)=23111123) +4178 train 7.095660 (lr=1.6357e-05) (hash(x)=24022804) +4179 train 7.092203 (lr=1.6342e-05) (hash(x)=25148490) +4180 train 7.329669 (lr=1.6327e-05) (hash(x)=22792092) +4181 train 7.444597 (lr=1.6312e-05) (hash(x)=24779698) +4182 train 7.321983 (lr=1.6297e-05) (hash(x)=24870844) +4183 train 6.993320 (lr=1.6282e-05) (hash(x)=22664494) +4184 train 7.101425 (lr=1.6267e-05) (hash(x)=22599729) +4185 train 7.252786 (lr=1.6252e-05) (hash(x)=24707078) +4186 train 7.049605 (lr=1.6237e-05) (hash(x)=23823945) +4187 train 6.781876 (lr=1.6222e-05) (hash(x)=22219856) +4188 train 7.470401 (lr=1.6207e-05) (hash(x)=27061401) +4189 train 7.177318 (lr=1.6192e-05) (hash(x)=23398766) +4190 train 7.263332 (lr=1.6177e-05) (hash(x)=27916730) +4191 train 7.161159 (lr=1.6162e-05) (hash(x)=24092927) +4192 train 7.217612 (lr=1.6147e-05) (hash(x)=24723657) +4193 train 7.245596 (lr=1.6132e-05) (hash(x)=24676155) +4194 train 7.160857 (lr=1.6118e-05) (hash(x)=23455369) +4195 train 7.086278 (lr=1.6103e-05) (hash(x)=21999890) +4196 train 7.005124 (lr=1.6088e-05) (hash(x)=23385567) +4197 train 7.226519 (lr=1.6073e-05) (hash(x)=25120814) +4198 train 6.917243 (lr=1.6058e-05) (hash(x)=21308113) +4199 train 7.232824 (lr=1.6044e-05) (hash(x)=27213812) +4200 val loss 7.2468 +4200 val perplexity 1403.5377 +4200 train 6.807105 (lr=1.6029e-05) (hash(x)=19675382) +4201 train 7.088089 (lr=1.6014e-05) (hash(x)=23882161) +4202 train 7.069582 (lr=1.5999e-05) (hash(x)=24338567) +4203 train 7.354889 (lr=1.5985e-05) (hash(x)=27649723) +4204 train 7.211929 (lr=1.5970e-05) (hash(x)=27563514) +4205 train 7.183156 (lr=1.5955e-05) (hash(x)=23128552) +4206 train 7.081487 (lr=1.5941e-05) (hash(x)=26203283) +4207 train 7.105329 (lr=1.5926e-05) (hash(x)=23929955) +4208 train 6.824298 (lr=1.5912e-05) (hash(x)=20978691) +4209 train 7.129694 (lr=1.5897e-05) (hash(x)=21875178) +4210 train 7.157752 (lr=1.5882e-05) (hash(x)=23563293) +4211 train 7.270415 (lr=1.5868e-05) (hash(x)=25538503) +4212 train 7.328485 (lr=1.5853e-05) (hash(x)=24171014) +4213 train 7.178331 (lr=1.5839e-05) (hash(x)=22306665) +4214 train 7.122548 (lr=1.5824e-05) (hash(x)=26082318) +4215 train 6.896291 (lr=1.5810e-05) (hash(x)=23025790) +4216 train 6.986530 (lr=1.5795e-05) (hash(x)=21146597) +4217 train 7.373009 (lr=1.5781e-05) (hash(x)=27470230) +4218 train 7.113496 (lr=1.5766e-05) (hash(x)=22691005) +4219 train 6.887436 (lr=1.5752e-05) (hash(x)=21550313) +4220 train 6.999108 (lr=1.5738e-05) (hash(x)=20618443) +4221 train 7.091938 (lr=1.5723e-05) (hash(x)=25260787) +4222 train 7.162038 (lr=1.5709e-05) (hash(x)=25249873) +4223 train 6.798460 (lr=1.5695e-05) (hash(x)=20452272) +4224 train 7.055312 (lr=1.5680e-05) (hash(x)=25649764) +4225 train 6.941195 (lr=1.5666e-05) (hash(x)=19589460) +4226 train 7.364342 (lr=1.5652e-05) (hash(x)=26477595) +4227 train 7.523807 (lr=1.5637e-05) (hash(x)=27585442) +4228 train 7.366661 (lr=1.5623e-05) (hash(x)=25821343) +4229 train 7.269947 (lr=1.5609e-05) (hash(x)=24549919) +4230 train 7.185242 (lr=1.5595e-05) (hash(x)=26124522) +4231 train 7.466653 (lr=1.5580e-05) (hash(x)=26473464) +4232 train 7.445905 (lr=1.5566e-05) (hash(x)=28883028) +4233 train 7.406065 (lr=1.5552e-05) (hash(x)=29611296) +4234 train 7.317676 (lr=1.5538e-05) (hash(x)=29059941) +4235 train 7.171360 (lr=1.5524e-05) (hash(x)=26368203) +4236 train 7.200955 (lr=1.5510e-05) (hash(x)=27021360) +4237 train 7.146194 (lr=1.5495e-05) (hash(x)=26135379) +4238 train 6.938484 (lr=1.5481e-05) (hash(x)=25862549) +4239 train 7.326833 (lr=1.5467e-05) (hash(x)=28276603) +4240 train 6.924991 (lr=1.5453e-05) (hash(x)=22170090) +4241 train 7.232830 (lr=1.5439e-05) (hash(x)=22625589) +4242 train 7.277832 (lr=1.5425e-05) (hash(x)=25751475) +4243 train 7.168941 (lr=1.5411e-05) (hash(x)=25836838) +4244 train 7.108922 (lr=1.5397e-05) (hash(x)=23938214) +4245 train 7.058307 (lr=1.5383e-05) (hash(x)=22759365) +4246 train 7.000932 (lr=1.5369e-05) (hash(x)=24964628) +4247 train 6.724098 (lr=1.5355e-05) (hash(x)=21480367) +4248 train 7.293869 (lr=1.5341e-05) (hash(x)=25974694) +4249 train 7.648041 (lr=1.5327e-05) (hash(x)=29830546) +4250 val loss 7.2453 +4250 val perplexity 1401.5548 +4250 train 7.293364 (lr=1.5314e-05) (hash(x)=26283200) +4251 train 7.308726 (lr=1.5300e-05) (hash(x)=25605672) +4252 train 6.987495 (lr=1.5286e-05) (hash(x)=21439107) +4253 train 6.875080 (lr=1.5272e-05) (hash(x)=22626883) +4254 train 7.254300 (lr=1.5258e-05) (hash(x)=25627150) +4255 train 7.408005 (lr=1.5244e-05) (hash(x)=24658642) +4256 train 7.526387 (lr=1.5231e-05) (hash(x)=29755505) +4257 train 7.191437 (lr=1.5217e-05) (hash(x)=22750846) +4258 train 7.101461 (lr=1.5203e-05) (hash(x)=21892651) +4259 train 7.148580 (lr=1.5189e-05) (hash(x)=22487960) +4260 train 7.202785 (lr=1.5176e-05) (hash(x)=24059869) +4261 train 7.011430 (lr=1.5162e-05) (hash(x)=21090180) +4262 train 7.125945 (lr=1.5148e-05) (hash(x)=22716452) +4263 train 7.376820 (lr=1.5134e-05) (hash(x)=26854801) +4264 train 7.152093 (lr=1.5121e-05) (hash(x)=23815428) +4265 train 7.033845 (lr=1.5107e-05) (hash(x)=23368704) +4266 train 7.053294 (lr=1.5094e-05) (hash(x)=24301098) +4267 train 7.282883 (lr=1.5080e-05) (hash(x)=25025039) +4268 train 7.026147 (lr=1.5066e-05) (hash(x)=25425736) +4269 train 7.256757 (lr=1.5053e-05) (hash(x)=27439380) +4270 train 6.697196 (lr=1.5039e-05) (hash(x)=18682756) +4271 train 6.839458 (lr=1.5026e-05) (hash(x)=17862226) +4272 train 7.441274 (lr=1.5012e-05) (hash(x)=29946491) +4273 train 6.698767 (lr=1.4999e-05) (hash(x)=21392062) +4274 train 7.249207 (lr=1.4985e-05) (hash(x)=25195556) +4275 train 7.205519 (lr=1.4972e-05) (hash(x)=26682036) +4276 train 7.155183 (lr=1.4958e-05) (hash(x)=21235260) +4277 train 6.970924 (lr=1.4945e-05) (hash(x)=22118984) +4278 train 7.014600 (lr=1.4931e-05) (hash(x)=24094510) +4279 train 7.505931 (lr=1.4918e-05) (hash(x)=28519182) +4280 train 7.159477 (lr=1.4905e-05) (hash(x)=26652859) +4281 train 7.086040 (lr=1.4891e-05) (hash(x)=24463139) +4282 train 7.061379 (lr=1.4878e-05) (hash(x)=23281870) +4283 train 7.272045 (lr=1.4865e-05) (hash(x)=29181174) +4284 train 6.971021 (lr=1.4851e-05) (hash(x)=24797417) +4285 train 7.313589 (lr=1.4838e-05) (hash(x)=29026537) +4286 train 7.114263 (lr=1.4825e-05) (hash(x)=23045165) +4287 train 7.040989 (lr=1.4812e-05) (hash(x)=25193694) +4288 train 7.076720 (lr=1.4798e-05) (hash(x)=23475407) +4289 train 7.208148 (lr=1.4785e-05) (hash(x)=24875410) +4290 train 7.170063 (lr=1.4772e-05) (hash(x)=26328101) +4291 train 7.373095 (lr=1.4759e-05) (hash(x)=26273661) +4292 train 7.106529 (lr=1.4745e-05) (hash(x)=23271891) +4293 train 7.067707 (lr=1.4732e-05) (hash(x)=23300732) +4294 train 7.183722 (lr=1.4719e-05) (hash(x)=24243693) +4295 train 7.257076 (lr=1.4706e-05) (hash(x)=25642620) +4296 train 7.289571 (lr=1.4693e-05) (hash(x)=27730411) +4297 train 7.087566 (lr=1.4680e-05) (hash(x)=25485335) +4298 train 6.954878 (lr=1.4667e-05) (hash(x)=25268789) +4299 train 7.397058 (lr=1.4654e-05) (hash(x)=28917143) +4300 val loss 7.2447 +4300 val perplexity 1400.7043 +4300 train 7.525857 (lr=1.4641e-05) (hash(x)=28987991) +4301 train 7.272894 (lr=1.4628e-05) (hash(x)=25989151) +4302 train 7.157208 (lr=1.4615e-05) (hash(x)=25658195) +4303 train 7.148696 (lr=1.4602e-05) (hash(x)=25765909) +4304 train 7.150875 (lr=1.4589e-05) (hash(x)=25704261) +4305 train 7.142852 (lr=1.4576e-05) (hash(x)=24438198) +4306 train 6.964265 (lr=1.4563e-05) (hash(x)=22871710) +4307 train 6.818696 (lr=1.4550e-05) (hash(x)=20160896) +4308 train 7.384055 (lr=1.4537e-05) (hash(x)=24218641) +4309 train 6.793534 (lr=1.4524e-05) (hash(x)=22073751) +4310 train 7.119124 (lr=1.4511e-05) (hash(x)=26434959) +4311 train 6.793694 (lr=1.4498e-05) (hash(x)=20750531) +4312 train 6.943273 (lr=1.4486e-05) (hash(x)=22232293) +4313 train 7.314781 (lr=1.4473e-05) (hash(x)=27324521) +4314 train 6.912990 (lr=1.4460e-05) (hash(x)=22217862) +4315 train 7.390889 (lr=1.4447e-05) (hash(x)=25741958) +4316 train 7.107297 (lr=1.4435e-05) (hash(x)=22738456) +4317 train 7.139452 (lr=1.4422e-05) (hash(x)=25387302) +4318 train 7.098003 (lr=1.4409e-05) (hash(x)=24669014) +4319 train 7.219228 (lr=1.4396e-05) (hash(x)=24917098) +4320 train 7.176367 (lr=1.4384e-05) (hash(x)=26698227) +4321 train 6.993841 (lr=1.4371e-05) (hash(x)=23518293) +4322 train 6.940010 (lr=1.4358e-05) (hash(x)=23643971) +4323 train 7.134185 (lr=1.4346e-05) (hash(x)=25659505) +4324 train 6.943741 (lr=1.4333e-05) (hash(x)=22697720) +4325 train 7.407884 (lr=1.4320e-05) (hash(x)=25082178) +4326 train 6.966170 (lr=1.4308e-05) (hash(x)=24166546) +4327 train 7.131401 (lr=1.4295e-05) (hash(x)=24499766) +4328 train 7.291643 (lr=1.4283e-05) (hash(x)=24338607) +4329 train 7.029795 (lr=1.4270e-05) (hash(x)=23225420) +4330 train 7.169908 (lr=1.4258e-05) (hash(x)=25907032) +4331 train 7.014037 (lr=1.4245e-05) (hash(x)=24634979) +4332 train 7.098228 (lr=1.4233e-05) (hash(x)=22161377) +4333 train 7.207138 (lr=1.4220e-05) (hash(x)=22559939) +4334 train 7.008546 (lr=1.4208e-05) (hash(x)=20840022) +4335 train 7.290215 (lr=1.4195e-05) (hash(x)=25067358) +4336 train 6.926397 (lr=1.4183e-05) (hash(x)=23432626) +4337 train 7.105095 (lr=1.4171e-05) (hash(x)=23820385) +4338 train 7.829025 (lr=1.4158e-05) (hash(x)=31594930) +4339 train 7.292530 (lr=1.4146e-05) (hash(x)=27138750) +4340 train 7.492147 (lr=1.4134e-05) (hash(x)=30031341) +4341 train 7.084033 (lr=1.4121e-05) (hash(x)=24602807) +4342 train 6.864923 (lr=1.4109e-05) (hash(x)=21584976) +4343 train 7.287962 (lr=1.4097e-05) (hash(x)=27479796) +4344 train 6.943604 (lr=1.4084e-05) (hash(x)=22746241) +4345 train 7.116638 (lr=1.4072e-05) (hash(x)=19728452) +4346 train 6.912659 (lr=1.4060e-05) (hash(x)=24502020) +4347 train 7.387541 (lr=1.4048e-05) (hash(x)=28225954) +4348 train 7.012650 (lr=1.4035e-05) (hash(x)=23893447) +4349 train 7.316101 (lr=1.4023e-05) (hash(x)=25654586) +4350 val loss 7.2382 +4350 val perplexity 1391.5851 +4350 train 7.183563 (lr=1.4011e-05) (hash(x)=23856469) +4351 train 7.093489 (lr=1.3999e-05) (hash(x)=23136080) +4352 train 7.256504 (lr=1.3987e-05) (hash(x)=26532918) +4353 train 7.158936 (lr=1.3975e-05) (hash(x)=25461947) +4354 train 7.161781 (lr=1.3963e-05) (hash(x)=26590231) +4355 train 6.872427 (lr=1.3951e-05) (hash(x)=21441985) +4356 train 7.164903 (lr=1.3939e-05) (hash(x)=26507941) +4357 train 7.447743 (lr=1.3926e-05) (hash(x)=26245238) +4358 train 7.211133 (lr=1.3914e-05) (hash(x)=24879059) +4359 train 7.474234 (lr=1.3902e-05) (hash(x)=29810074) +4360 train 6.910520 (lr=1.3890e-05) (hash(x)=24258069) +4361 train 7.093246 (lr=1.3878e-05) (hash(x)=25229360) +4362 train 7.272847 (lr=1.3867e-05) (hash(x)=25440206) +4363 train 7.129784 (lr=1.3855e-05) (hash(x)=23222125) +4364 train 6.959917 (lr=1.3843e-05) (hash(x)=23353186) +4365 train 7.171727 (lr=1.3831e-05) (hash(x)=26995240) +4366 train 7.105525 (lr=1.3819e-05) (hash(x)=24135899) +4367 train 7.150612 (lr=1.3807e-05) (hash(x)=24765539) +4368 train 7.201680 (lr=1.3795e-05) (hash(x)=26051004) +4369 train 6.949361 (lr=1.3783e-05) (hash(x)=22559142) +4370 train 6.829923 (lr=1.3772e-05) (hash(x)=20364388) +4371 train 7.316261 (lr=1.3760e-05) (hash(x)=25938817) +4372 train 7.354917 (lr=1.3748e-05) (hash(x)=26060945) +4373 train 7.274181 (lr=1.3736e-05) (hash(x)=27866714) +4374 train 7.205883 (lr=1.3724e-05) (hash(x)=27104972) +4375 train 6.884977 (lr=1.3713e-05) (hash(x)=22216309) +4376 train 6.979466 (lr=1.3701e-05) (hash(x)=20781533) +4377 train 6.894464 (lr=1.3689e-05) (hash(x)=18784350) +4378 train 6.967548 (lr=1.3678e-05) (hash(x)=21102897) +4379 train 7.236311 (lr=1.3666e-05) (hash(x)=25647489) +4380 train 7.049553 (lr=1.3654e-05) (hash(x)=24486462) +4381 train 7.306390 (lr=1.3643e-05) (hash(x)=26539114) +4382 train 6.951229 (lr=1.3631e-05) (hash(x)=20026045) +4383 train 7.231247 (lr=1.3620e-05) (hash(x)=20613861) +4384 train 6.956712 (lr=1.3608e-05) (hash(x)=20676237) +4385 train 7.181828 (lr=1.3596e-05) (hash(x)=24893163) +4386 train 6.743314 (lr=1.3585e-05) (hash(x)=17299395) +4387 train 6.899349 (lr=1.3573e-05) (hash(x)=19580191) +4388 train 7.052254 (lr=1.3562e-05) (hash(x)=25588218) +4389 train 7.215122 (lr=1.3550e-05) (hash(x)=26433063) +4390 train 7.299897 (lr=1.3539e-05) (hash(x)=24917693) +4391 train 6.963201 (lr=1.3528e-05) (hash(x)=23462447) +4392 train 7.189084 (lr=1.3516e-05) (hash(x)=27185416) +4393 train 7.277462 (lr=1.3505e-05) (hash(x)=24109010) +4394 train 7.063522 (lr=1.3493e-05) (hash(x)=21486000) +4395 train 6.974180 (lr=1.3482e-05) (hash(x)=22230006) +4396 train 7.358552 (lr=1.3471e-05) (hash(x)=26092311) +4397 train 7.114549 (lr=1.3459e-05) (hash(x)=24112426) +4398 train 6.956209 (lr=1.3448e-05) (hash(x)=21881373) +4399 train 7.098180 (lr=1.3437e-05) (hash(x)=26739455) +4400 val loss 7.2397 +4400 val perplexity 1393.6251 +4400 train 6.981338 (lr=1.3425e-05) (hash(x)=22873602) +4401 train 7.050596 (lr=1.3414e-05) (hash(x)=26748712) +4402 train 7.255798 (lr=1.3403e-05) (hash(x)=26306618) +4403 train 7.426147 (lr=1.3392e-05) (hash(x)=26898808) +4404 train 7.118872 (lr=1.3380e-05) (hash(x)=25067751) +4405 train 7.167633 (lr=1.3369e-05) (hash(x)=25397145) +4406 train 7.303188 (lr=1.3358e-05) (hash(x)=24796962) +4407 train 7.110158 (lr=1.3347e-05) (hash(x)=23222996) +4408 train 7.091434 (lr=1.3336e-05) (hash(x)=24820189) +4409 train 7.492552 (lr=1.3325e-05) (hash(x)=27669038) +4410 train 7.107245 (lr=1.3314e-05) (hash(x)=24283976) +4411 train 7.333847 (lr=1.3303e-05) (hash(x)=25018789) +4412 train 7.164197 (lr=1.3291e-05) (hash(x)=26247064) +4413 train 7.225841 (lr=1.3280e-05) (hash(x)=22942904) +4414 train 7.107361 (lr=1.3269e-05) (hash(x)=23918746) +4415 train 7.193501 (lr=1.3258e-05) (hash(x)=26489285) +4416 train 6.208901 (lr=1.3247e-05) (hash(x)=14942495) +4417 train 7.031743 (lr=1.3236e-05) (hash(x)=23908505) +4418 train 7.252051 (lr=1.3225e-05) (hash(x)=25854036) +4419 train 7.145775 (lr=1.3214e-05) (hash(x)=27522868) +4420 train 7.053768 (lr=1.3204e-05) (hash(x)=26549205) +4421 train 6.916236 (lr=1.3193e-05) (hash(x)=24565522) +4422 train 7.248842 (lr=1.3182e-05) (hash(x)=23919123) +4423 train 7.120363 (lr=1.3171e-05) (hash(x)=25185942) +4424 train 7.107973 (lr=1.3160e-05) (hash(x)=24818969) +4425 train 7.246961 (lr=1.3149e-05) (hash(x)=26750372) +4426 train 7.206483 (lr=1.3138e-05) (hash(x)=25621536) +4427 train 7.687871 (lr=1.3128e-05) (hash(x)=28037060) +4428 train 7.742322 (lr=1.3117e-05) (hash(x)=30829517) +4429 train 7.290119 (lr=1.3106e-05) (hash(x)=28728766) +4430 train 7.181328 (lr=1.3095e-05) (hash(x)=25936895) +4431 train 7.365964 (lr=1.3085e-05) (hash(x)=27476158) +4432 train 7.084882 (lr=1.3074e-05) (hash(x)=23297921) +4433 train 7.037418 (lr=1.3063e-05) (hash(x)=23201299) +4434 train 6.998824 (lr=1.3053e-05) (hash(x)=22681766) +4435 train 6.972454 (lr=1.3042e-05) (hash(x)=23217512) +4436 train 7.452590 (lr=1.3031e-05) (hash(x)=29322443) +4437 train 7.039918 (lr=1.3021e-05) (hash(x)=23502072) +4438 train 7.175943 (lr=1.3010e-05) (hash(x)=28873527) +4439 train 7.176319 (lr=1.2999e-05) (hash(x)=23653175) +4440 train 6.980258 (lr=1.2989e-05) (hash(x)=21635879) +4441 train 7.008360 (lr=1.2978e-05) (hash(x)=22201854) +4442 train 6.967502 (lr=1.2968e-05) (hash(x)=23101164) +4443 train 7.341913 (lr=1.2957e-05) (hash(x)=25475122) +4444 train 7.091690 (lr=1.2947e-05) (hash(x)=25124825) +4445 train 7.226623 (lr=1.2936e-05) (hash(x)=26883852) +4446 train 7.025163 (lr=1.2926e-05) (hash(x)=24731829) +4447 train 7.005231 (lr=1.2915e-05) (hash(x)=22405076) +4448 train 7.155702 (lr=1.2905e-05) (hash(x)=27633869) +4449 train 7.222588 (lr=1.2895e-05) (hash(x)=25162594) +4450 val loss 7.2358 +4450 val perplexity 1388.2885 +4450 train 7.212706 (lr=1.2884e-05) (hash(x)=26438149) +4451 train 7.225699 (lr=1.2874e-05) (hash(x)=26748800) +4452 train 6.968158 (lr=1.2864e-05) (hash(x)=22971620) +4453 train 7.109117 (lr=1.2853e-05) (hash(x)=25886430) +4454 train 6.890729 (lr=1.2843e-05) (hash(x)=21084137) +4455 train 7.085075 (lr=1.2833e-05) (hash(x)=25673545) +4456 train 7.691455 (lr=1.2822e-05) (hash(x)=29389002) +4457 train 6.830647 (lr=1.2812e-05) (hash(x)=21676076) +4458 train 6.902823 (lr=1.2802e-05) (hash(x)=22616647) +4459 train 7.257545 (lr=1.2792e-05) (hash(x)=22771197) +4460 train 7.216335 (lr=1.2781e-05) (hash(x)=26393514) +4461 train 7.422227 (lr=1.2771e-05) (hash(x)=24996433) +4462 train 7.124247 (lr=1.2761e-05) (hash(x)=19594028) +4463 train 7.233440 (lr=1.2751e-05) (hash(x)=22675428) +4464 train 7.208256 (lr=1.2741e-05) (hash(x)=26566551) +4465 train 7.201116 (lr=1.2731e-05) (hash(x)=22469290) +4466 train 7.678540 (lr=1.2721e-05) (hash(x)=29821654) +4467 train 7.249079 (lr=1.2710e-05) (hash(x)=26305388) +4468 train 7.068527 (lr=1.2700e-05) (hash(x)=21998506) +4469 train 7.481721 (lr=1.2690e-05) (hash(x)=23953315) +4470 train 7.111556 (lr=1.2680e-05) (hash(x)=23985456) +4471 train 7.461417 (lr=1.2670e-05) (hash(x)=28168456) +4472 train 7.177762 (lr=1.2660e-05) (hash(x)=25126411) +4473 train 6.962687 (lr=1.2650e-05) (hash(x)=24619336) +4474 train 7.194572 (lr=1.2640e-05) (hash(x)=24467798) +4475 train 7.969809 (lr=1.2631e-05) (hash(x)=31673254) +4476 train 7.786405 (lr=1.2621e-05) (hash(x)=29929610) +4477 train 7.510930 (lr=1.2611e-05) (hash(x)=29412572) +4478 train 7.678712 (lr=1.2601e-05) (hash(x)=31910006) +4479 train 7.287735 (lr=1.2591e-05) (hash(x)=26072586) +4480 train 7.244328 (lr=1.2581e-05) (hash(x)=25782825) +4481 train 7.078273 (lr=1.2571e-05) (hash(x)=21131363) +4482 train 7.210854 (lr=1.2562e-05) (hash(x)=25071223) +4483 train 7.825990 (lr=1.2552e-05) (hash(x)=32249577) +4484 train 7.020994 (lr=1.2542e-05) (hash(x)=24752808) +4485 train 7.105118 (lr=1.2532e-05) (hash(x)=24970539) +4486 train 7.040022 (lr=1.2522e-05) (hash(x)=24191005) +4487 train 7.250644 (lr=1.2513e-05) (hash(x)=24974331) +4488 train 7.383276 (lr=1.2503e-05) (hash(x)=27043409) +4489 train 6.815300 (lr=1.2493e-05) (hash(x)=11320385) +4490 train 6.755605 (lr=1.2484e-05) (hash(x)=11919565) +4491 train 6.839714 (lr=1.2474e-05) (hash(x)=10404694) +4492 train 6.883556 (lr=1.2464e-05) (hash(x)=12393159) +4493 train 6.785074 (lr=1.2455e-05) (hash(x)=11843609) +4494 train 6.843217 (lr=1.2445e-05) (hash(x)=12632729) +4495 train 7.096549 (lr=1.2436e-05) (hash(x)=21951984) +4496 train 7.761057 (lr=1.2426e-05) (hash(x)=19411544) +4497 train 7.740659 (lr=1.2417e-05) (hash(x)=21000228) +4498 train 7.314211 (lr=1.2407e-05) (hash(x)=26018207) +4499 train 7.328967 (lr=1.2398e-05) (hash(x)=24659058) +4500 val loss 7.2396 +4500 val perplexity 1393.6031 +4500 train 7.504433 (lr=1.2388e-05) (hash(x)=27919597) +4501 train 7.103757 (lr=1.2379e-05) (hash(x)=26232596) +4502 train 7.252316 (lr=1.2369e-05) (hash(x)=26248912) +4503 train 7.123628 (lr=1.2360e-05) (hash(x)=25403751) +4504 train 7.094341 (lr=1.2350e-05) (hash(x)=21096637) +4505 train 7.216489 (lr=1.2341e-05) (hash(x)=26560941) +4506 train 7.193929 (lr=1.2332e-05) (hash(x)=24942406) +4507 train 7.241905 (lr=1.2322e-05) (hash(x)=24405748) +4508 train 7.157965 (lr=1.2313e-05) (hash(x)=22975455) +4509 train 7.079381 (lr=1.2304e-05) (hash(x)=26358820) +4510 train 7.064634 (lr=1.2294e-05) (hash(x)=24211938) +4511 train 7.273247 (lr=1.2285e-05) (hash(x)=26396012) +4512 train 6.959428 (lr=1.2276e-05) (hash(x)=22534410) +4513 train 7.113067 (lr=1.2267e-05) (hash(x)=23855025) +4514 train 6.950234 (lr=1.2257e-05) (hash(x)=22722345) +4515 train 6.945497 (lr=1.2248e-05) (hash(x)=22779251) +4516 train 7.228015 (lr=1.2239e-05) (hash(x)=23973078) +4517 train 7.113567 (lr=1.2230e-05) (hash(x)=19886228) +4518 train 7.165515 (lr=1.2221e-05) (hash(x)=23849694) +4519 train 7.515911 (lr=1.2212e-05) (hash(x)=24827190) +4520 train 7.112100 (lr=1.2202e-05) (hash(x)=25111498) +4521 train 7.957802 (lr=1.2193e-05) (hash(x)=29752556) +4522 train 7.400177 (lr=1.2184e-05) (hash(x)=25606805) +4523 train 7.154603 (lr=1.2175e-05) (hash(x)=22209714) +4524 train 6.936193 (lr=1.2166e-05) (hash(x)=24991834) +4525 train 7.176652 (lr=1.2157e-05) (hash(x)=27808158) +4526 train 7.091588 (lr=1.2148e-05) (hash(x)=23041199) +4527 train 7.170399 (lr=1.2139e-05) (hash(x)=24847458) +4528 train 7.098960 (lr=1.2130e-05) (hash(x)=25091787) +4529 train 8.063352 (lr=1.2121e-05) (hash(x)=29745551) +4530 train 6.830961 (lr=1.2112e-05) (hash(x)=20447167) +4531 train 7.013472 (lr=1.2103e-05) (hash(x)=20720911) +4532 train 7.181758 (lr=1.2095e-05) (hash(x)=24803353) +4533 train 7.221579 (lr=1.2086e-05) (hash(x)=23780724) +4534 train 7.217251 (lr=1.2077e-05) (hash(x)=23423120) +4535 train 6.930413 (lr=1.2068e-05) (hash(x)=22159088) +4536 train 7.128325 (lr=1.2059e-05) (hash(x)=25820304) +4537 train 6.927989 (lr=1.2050e-05) (hash(x)=22813612) +4538 train 7.268738 (lr=1.2042e-05) (hash(x)=27827979) +4539 train 7.256619 (lr=1.2033e-05) (hash(x)=25737179) +4540 train 7.484689 (lr=1.2024e-05) (hash(x)=23401504) +4541 train 7.094861 (lr=1.2015e-05) (hash(x)=25071988) +4542 train 7.155739 (lr=1.2007e-05) (hash(x)=22844541) +4543 train 6.934850 (lr=1.1998e-05) (hash(x)=22140034) +4544 train 7.172784 (lr=1.1989e-05) (hash(x)=26522091) +4545 train 7.163474 (lr=1.1981e-05) (hash(x)=24099725) +4546 train 6.788702 (lr=1.1972e-05) (hash(x)=19127182) +4547 train 6.920621 (lr=1.1963e-05) (hash(x)=18992693) +4548 train 7.912918 (lr=1.1955e-05) (hash(x)=26723015) +4549 train 7.681993 (lr=1.1946e-05) (hash(x)=30389969) +4550 val loss 7.2349 +4550 val perplexity 1387.0200 +4550 train 7.036419 (lr=1.1938e-05) (hash(x)=24065654) +4551 train 6.888186 (lr=1.1929e-05) (hash(x)=19044797) +4552 train 7.277217 (lr=1.1921e-05) (hash(x)=24919665) +4553 train 7.299352 (lr=1.1912e-05) (hash(x)=22780968) +4554 train 7.054035 (lr=1.1904e-05) (hash(x)=24549699) +4555 train 6.935796 (lr=1.1895e-05) (hash(x)=21374811) +4556 train 7.080753 (lr=1.1887e-05) (hash(x)=25225950) +4557 train 7.197909 (lr=1.1878e-05) (hash(x)=25691882) +4558 train 7.097394 (lr=1.1870e-05) (hash(x)=24685235) +4559 train 6.941854 (lr=1.1861e-05) (hash(x)=23932794) +4560 train 7.536149 (lr=1.1853e-05) (hash(x)=28152043) +4561 train 7.017818 (lr=1.1845e-05) (hash(x)=23417051) +4562 train 7.084752 (lr=1.1836e-05) (hash(x)=26250211) +4563 train 7.308816 (lr=1.1828e-05) (hash(x)=25428813) +4564 train 7.460027 (lr=1.1820e-05) (hash(x)=27477379) +4565 train 7.241441 (lr=1.1812e-05) (hash(x)=23015212) +4566 train 6.961956 (lr=1.1803e-05) (hash(x)=22837608) +4567 train 7.072118 (lr=1.1795e-05) (hash(x)=25256890) +4568 train 6.993516 (lr=1.1787e-05) (hash(x)=22742827) +4569 train 7.371654 (lr=1.1779e-05) (hash(x)=30167922) +4570 train 7.077536 (lr=1.1770e-05) (hash(x)=24540265) +4571 train 7.389662 (lr=1.1762e-05) (hash(x)=26752941) +4572 train 7.210621 (lr=1.1754e-05) (hash(x)=25094026) +4573 train 7.871315 (lr=1.1746e-05) (hash(x)=28508785) +4574 train 7.305132 (lr=1.1738e-05) (hash(x)=26501871) +4575 train 7.091124 (lr=1.1730e-05) (hash(x)=24161711) +4576 train 7.042099 (lr=1.1722e-05) (hash(x)=24313695) +4577 train 7.481378 (lr=1.1714e-05) (hash(x)=28248933) +4578 train 7.619954 (lr=1.1706e-05) (hash(x)=28445722) +4579 train 7.215292 (lr=1.1698e-05) (hash(x)=24589015) +4580 train 7.359306 (lr=1.1690e-05) (hash(x)=26192193) +4581 train 7.004515 (lr=1.1682e-05) (hash(x)=25131316) +4582 train 7.109539 (lr=1.1674e-05) (hash(x)=26631504) +4583 train 6.958407 (lr=1.1666e-05) (hash(x)=22036817) +4584 train 7.550570 (lr=1.1658e-05) (hash(x)=28361254) +4585 train 7.181868 (lr=1.1650e-05) (hash(x)=24828340) +4586 train 6.888833 (lr=1.1642e-05) (hash(x)=24067304) +4587 train 6.680665 (lr=1.1634e-05) (hash(x)=20733289) +4588 train 6.566841 (lr=1.1626e-05) (hash(x)=19526622) +4589 train 7.025212 (lr=1.1618e-05) (hash(x)=22148688) +4590 train 7.192136 (lr=1.1610e-05) (hash(x)=24141800) +4591 train 7.223892 (lr=1.1603e-05) (hash(x)=26663208) +4592 train 6.913235 (lr=1.1595e-05) (hash(x)=22536305) +4593 train 7.169083 (lr=1.1587e-05) (hash(x)=23608185) +4594 train 7.048154 (lr=1.1579e-05) (hash(x)=23348495) +4595 train 7.182426 (lr=1.1572e-05) (hash(x)=25409759) +4596 train 7.158868 (lr=1.1564e-05) (hash(x)=25572131) +4597 train 7.131944 (lr=1.1556e-05) (hash(x)=21782039) +4598 train 7.106380 (lr=1.1549e-05) (hash(x)=24643923) +4599 train 7.064640 (lr=1.1541e-05) (hash(x)=24072213) +4600 val loss 7.2358 +4600 val perplexity 1388.2931 +4600 train 7.014034 (lr=1.1533e-05) (hash(x)=23925612) +4601 train 7.092932 (lr=1.1526e-05) (hash(x)=23315415) +4602 train 7.086813 (lr=1.1518e-05) (hash(x)=21793800) +4603 train 7.033431 (lr=1.1511e-05) (hash(x)=24921200) +4604 train 7.291327 (lr=1.1503e-05) (hash(x)=27226113) +4605 train 7.076151 (lr=1.1495e-05) (hash(x)=22920960) +4606 train 7.016531 (lr=1.1488e-05) (hash(x)=21947750) +4607 train 7.089104 (lr=1.1480e-05) (hash(x)=22766044) +4608 train 7.470871 (lr=1.1473e-05) (hash(x)=28237005) +4609 train 6.951397 (lr=1.1465e-05) (hash(x)=24922621) +4610 train 7.150384 (lr=1.1458e-05) (hash(x)=24899830) +4611 train 7.561652 (lr=1.1451e-05) (hash(x)=32920298) +4612 train 7.053896 (lr=1.1443e-05) (hash(x)=25083835) +4613 train 7.050116 (lr=1.1436e-05) (hash(x)=22863054) +4614 train 7.106467 (lr=1.1428e-05) (hash(x)=24841464) +4615 train 7.390798 (lr=1.1421e-05) (hash(x)=27871153) +4616 train 7.514227 (lr=1.1414e-05) (hash(x)=28025163) +4617 train 7.057888 (lr=1.1406e-05) (hash(x)=24659561) +4618 train 7.115074 (lr=1.1399e-05) (hash(x)=25067194) +4619 train 7.175382 (lr=1.1392e-05) (hash(x)=22731460) +4620 train 7.077826 (lr=1.1385e-05) (hash(x)=20445873) +4621 train 7.185385 (lr=1.1377e-05) (hash(x)=26033948) +4622 train 7.059215 (lr=1.1370e-05) (hash(x)=22473213) +4623 train 7.588877 (lr=1.1363e-05) (hash(x)=24037280) +4624 train 7.978272 (lr=1.1356e-05) (hash(x)=25624131) +4625 train 7.647928 (lr=1.1349e-05) (hash(x)=26799867) +4626 train 7.209897 (lr=1.1341e-05) (hash(x)=27187602) +4627 train 7.125128 (lr=1.1334e-05) (hash(x)=23277695) +4628 train 7.140560 (lr=1.1327e-05) (hash(x)=24748234) +4629 train 7.243806 (lr=1.1320e-05) (hash(x)=26103104) +4630 train 7.161336 (lr=1.1313e-05) (hash(x)=24327389) +4631 train 7.271780 (lr=1.1306e-05) (hash(x)=24121850) +4632 train 7.132875 (lr=1.1299e-05) (hash(x)=23714590) +4633 train 7.166309 (lr=1.1292e-05) (hash(x)=22379412) +4634 train 7.367577 (lr=1.1285e-05) (hash(x)=24454713) +4635 train 7.056970 (lr=1.1278e-05) (hash(x)=22966977) +4636 train 7.042438 (lr=1.1271e-05) (hash(x)=23764884) +4637 train 6.954144 (lr=1.1264e-05) (hash(x)=23827429) +4638 train 7.147766 (lr=1.1257e-05) (hash(x)=24088592) +4639 train 7.138205 (lr=1.1250e-05) (hash(x)=24380031) +4640 train 7.222470 (lr=1.1243e-05) (hash(x)=26065050) +4641 train 7.124991 (lr=1.1236e-05) (hash(x)=24442902) +4642 train 6.739809 (lr=1.1230e-05) (hash(x)=18548782) +4643 train 7.235498 (lr=1.1223e-05) (hash(x)=26957303) +4644 train 7.231084 (lr=1.1216e-05) (hash(x)=25032727) +4645 train 7.110868 (lr=1.1209e-05) (hash(x)=27224706) +4646 train 7.284768 (lr=1.1202e-05) (hash(x)=27508476) +4647 train 6.963727 (lr=1.1196e-05) (hash(x)=23055215) +4648 train 7.104687 (lr=1.1189e-05) (hash(x)=24496194) +4649 train 8.329185 (lr=1.1182e-05) (hash(x)=13982941) +4650 val loss 7.2307 +4650 val perplexity 1381.2549 +4650 train 7.599174 (lr=1.1176e-05) (hash(x)=16721547) +4651 train 7.120088 (lr=1.1169e-05) (hash(x)=22929154) +4652 train 7.050568 (lr=1.1162e-05) (hash(x)=23323994) +4653 train 7.371946 (lr=1.1156e-05) (hash(x)=24877951) +4654 train 7.228612 (lr=1.1149e-05) (hash(x)=24096183) +4655 train 7.086460 (lr=1.1142e-05) (hash(x)=25329724) +4656 train 7.028232 (lr=1.1136e-05) (hash(x)=23877337) +4657 train 6.688779 (lr=1.1129e-05) (hash(x)=20923083) +4658 train 6.986194 (lr=1.1123e-05) (hash(x)=23807996) +4659 train 7.090308 (lr=1.1116e-05) (hash(x)=24370475) +4660 train 7.486907 (lr=1.1110e-05) (hash(x)=28202255) +4661 train 7.211530 (lr=1.1103e-05) (hash(x)=26142119) +4662 train 6.957882 (lr=1.1097e-05) (hash(x)=21387743) +4663 train 7.101145 (lr=1.1090e-05) (hash(x)=25662408) +4664 train 7.149925 (lr=1.1084e-05) (hash(x)=23962815) +4665 train 7.122243 (lr=1.1077e-05) (hash(x)=23987677) +4666 train 7.369973 (lr=1.1071e-05) (hash(x)=26554284) +4667 train 7.408612 (lr=1.1065e-05) (hash(x)=25991817) +4668 train 7.115160 (lr=1.1058e-05) (hash(x)=24256966) +4669 train 6.906879 (lr=1.1052e-05) (hash(x)=22187158) +4670 train 7.204266 (lr=1.1046e-05) (hash(x)=26295320) +4671 train 7.246143 (lr=1.1039e-05) (hash(x)=26346814) +4672 train 7.474364 (lr=1.1033e-05) (hash(x)=26594196) +4673 train 7.251346 (lr=1.1027e-05) (hash(x)=24322101) +4674 train 7.349565 (lr=1.1020e-05) (hash(x)=27274566) +4675 train 7.146263 (lr=1.1014e-05) (hash(x)=24505725) +4676 train 7.332340 (lr=1.1008e-05) (hash(x)=26167371) +4677 train 7.411453 (lr=1.1002e-05) (hash(x)=28062311) +4678 train 7.147540 (lr=1.0996e-05) (hash(x)=23476009) +4679 train 7.217683 (lr=1.0989e-05) (hash(x)=25283256) +4680 train 6.985264 (lr=1.0983e-05) (hash(x)=22033246) +4681 train 6.991670 (lr=1.0977e-05) (hash(x)=22716214) +4682 train 7.158223 (lr=1.0971e-05) (hash(x)=25672672) +4683 train 7.045960 (lr=1.0965e-05) (hash(x)=22979072) +4684 train 7.243129 (lr=1.0959e-05) (hash(x)=27439204) +4685 train 7.178049 (lr=1.0953e-05) (hash(x)=24857737) +4686 train 7.380457 (lr=1.0947e-05) (hash(x)=29615897) +4687 train 6.966149 (lr=1.0941e-05) (hash(x)=24021771) +4688 train 7.126077 (lr=1.0935e-05) (hash(x)=27410807) +4689 train 6.919254 (lr=1.0929e-05) (hash(x)=22850411) +4690 train 7.215013 (lr=1.0923e-05) (hash(x)=24949696) +4691 train 7.045354 (lr=1.0917e-05) (hash(x)=22956381) +4692 train 7.561573 (lr=1.0911e-05) (hash(x)=28193458) +4693 train 7.051960 (lr=1.0905e-05) (hash(x)=25596844) +4694 train 7.035135 (lr=1.0899e-05) (hash(x)=22101377) +4695 train 6.954910 (lr=1.0894e-05) (hash(x)=23576840) +4696 train 6.961808 (lr=1.0888e-05) (hash(x)=21849758) +4697 train 7.134454 (lr=1.0882e-05) (hash(x)=26431349) +4698 train 7.227240 (lr=1.0876e-05) (hash(x)=22960758) +4699 train 7.133055 (lr=1.0870e-05) (hash(x)=23243097) +4700 val loss 7.2308 +4700 val perplexity 1381.2706 +4700 train 7.026758 (lr=1.0865e-05) (hash(x)=23715370) +4701 train 7.678188 (lr=1.0859e-05) (hash(x)=30678293) +4702 train 7.758237 (lr=1.0853e-05) (hash(x)=32481620) +4703 train 7.292642 (lr=1.0848e-05) (hash(x)=26414858) +4704 train 7.191246 (lr=1.0842e-05) (hash(x)=24768691) +4705 train 6.875678 (lr=1.0836e-05) (hash(x)=21627762) +4706 train 6.967096 (lr=1.0831e-05) (hash(x)=21024917) +4707 train 6.946393 (lr=1.0825e-05) (hash(x)=23570951) +4708 train 7.051136 (lr=1.0819e-05) (hash(x)=23729185) +4709 train 7.375757 (lr=1.0814e-05) (hash(x)=25933754) +4710 train 6.895061 (lr=1.0808e-05) (hash(x)=23091014) +4711 train 6.947605 (lr=1.0803e-05) (hash(x)=20099261) +4712 train 7.116270 (lr=1.0797e-05) (hash(x)=26807297) +4713 train 7.045705 (lr=1.0792e-05) (hash(x)=25332115) +4714 train 7.011636 (lr=1.0786e-05) (hash(x)=23247605) +4715 train 6.902510 (lr=1.0781e-05) (hash(x)=23786549) +4716 train 6.985188 (lr=1.0775e-05) (hash(x)=23981166) +4717 train 7.139361 (lr=1.0770e-05) (hash(x)=25967754) +4718 train 7.019058 (lr=1.0764e-05) (hash(x)=23659116) +4719 train 7.064168 (lr=1.0759e-05) (hash(x)=22453718) +4720 train 6.988634 (lr=1.0754e-05) (hash(x)=22597951) +4721 train 7.243856 (lr=1.0748e-05) (hash(x)=25284885) +4722 train 7.173975 (lr=1.0743e-05) (hash(x)=24748569) +4723 train 6.791387 (lr=1.0738e-05) (hash(x)=19448608) +4724 train 7.170305 (lr=1.0732e-05) (hash(x)=24888040) +4725 train 7.027996 (lr=1.0727e-05) (hash(x)=23203503) +4726 train 6.791997 (lr=1.0722e-05) (hash(x)=20387787) +4727 train 6.874558 (lr=1.0716e-05) (hash(x)=22529445) +4728 train 7.130432 (lr=1.0711e-05) (hash(x)=22455471) +4729 train 7.150221 (lr=1.0706e-05) (hash(x)=25661132) +4730 train 7.121410 (lr=1.0701e-05) (hash(x)=24997711) +4731 train 7.231589 (lr=1.0696e-05) (hash(x)=22575521) +4732 train 6.987936 (lr=1.0690e-05) (hash(x)=22640285) +4733 train 6.889331 (lr=1.0685e-05) (hash(x)=18637357) +4734 train 7.003208 (lr=1.0680e-05) (hash(x)=22845826) +4735 train 7.182111 (lr=1.0675e-05) (hash(x)=24484543) +4736 train 7.048906 (lr=1.0670e-05) (hash(x)=23352320) +4737 train 6.855657 (lr=1.0665e-05) (hash(x)=21544758) +4738 train 6.668738 (lr=1.0660e-05) (hash(x)=18292136) +4739 train 7.308600 (lr=1.0655e-05) (hash(x)=24893614) +4740 train 7.149268 (lr=1.0650e-05) (hash(x)=28103443) +4741 train 7.015959 (lr=1.0645e-05) (hash(x)=22233356) +4742 train 6.859308 (lr=1.0640e-05) (hash(x)=21133541) +4743 train 7.120384 (lr=1.0635e-05) (hash(x)=24043998) +4744 train 7.411184 (lr=1.0630e-05) (hash(x)=24801185) +4745 train 7.212627 (lr=1.0625e-05) (hash(x)=23858358) +4746 train 7.214435 (lr=1.0620e-05) (hash(x)=23926989) +4747 train 7.274456 (lr=1.0616e-05) (hash(x)=24813708) +4748 train 7.078388 (lr=1.0611e-05) (hash(x)=26339467) +4749 train 6.952249 (lr=1.0606e-05) (hash(x)=21850656) +4750 val loss 7.2324 +4750 val perplexity 1383.5614 +4750 train 6.941528 (lr=1.0601e-05) (hash(x)=21475802) +4751 train 7.118248 (lr=1.0596e-05) (hash(x)=24301906) +4752 train 6.952611 (lr=1.0591e-05) (hash(x)=22748495) +4753 train 7.112744 (lr=1.0587e-05) (hash(x)=25649256) +4754 train 7.035233 (lr=1.0582e-05) (hash(x)=23934346) +4755 train 7.145711 (lr=1.0577e-05) (hash(x)=26332892) +4756 train 7.017980 (lr=1.0573e-05) (hash(x)=23279389) +4757 train 7.082069 (lr=1.0568e-05) (hash(x)=23146858) +4758 train 7.422179 (lr=1.0563e-05) (hash(x)=26892932) +4759 train 6.949969 (lr=1.0559e-05) (hash(x)=26328881) +4760 train 7.069207 (lr=1.0554e-05) (hash(x)=24394655) +4761 train 7.037724 (lr=1.0549e-05) (hash(x)=22122308) +4762 train 7.199790 (lr=1.0545e-05) (hash(x)=24200369) +4763 train 7.305593 (lr=1.0540e-05) (hash(x)=26841776) +4764 train 7.265234 (lr=1.0536e-05) (hash(x)=27196641) +4765 train 7.018372 (lr=1.0531e-05) (hash(x)=24912822) +4766 train 7.274166 (lr=1.0527e-05) (hash(x)=25946055) +4767 train 6.865613 (lr=1.0522e-05) (hash(x)=23101508) +4768 train 7.035020 (lr=1.0518e-05) (hash(x)=24287798) +4769 train 7.154611 (lr=1.0513e-05) (hash(x)=22798964) +4770 train 7.053247 (lr=1.0509e-05) (hash(x)=24164479) +4771 train 7.108163 (lr=1.0504e-05) (hash(x)=24946464) +4772 train 7.235576 (lr=1.0500e-05) (hash(x)=25154423) +4773 train 6.948720 (lr=1.0496e-05) (hash(x)=23173476) +4774 train 7.162004 (lr=1.0491e-05) (hash(x)=25373559) +4775 train 7.156008 (lr=1.0487e-05) (hash(x)=23527176) +4776 train 7.115767 (lr=1.0483e-05) (hash(x)=24865403) +4777 train 7.053639 (lr=1.0478e-05) (hash(x)=24451067) +4778 train 7.687917 (lr=1.0474e-05) (hash(x)=28187162) +4779 train 7.837375 (lr=1.0470e-05) (hash(x)=31163350) +4780 train 8.203231 (lr=1.0466e-05) (hash(x)=33563280) +4781 train 8.252170 (lr=1.0461e-05) (hash(x)=34939183) +4782 train 7.740831 (lr=1.0457e-05) (hash(x)=30263543) +4783 train 7.021915 (lr=1.0453e-05) (hash(x)=22705673) +4784 train 6.920264 (lr=1.0449e-05) (hash(x)=21415023) +4785 train 7.118756 (lr=1.0445e-05) (hash(x)=26079097) +4786 train 7.444347 (lr=1.0441e-05) (hash(x)=25503836) +4787 train 7.300674 (lr=1.0437e-05) (hash(x)=24705721) +4788 train 7.147283 (lr=1.0432e-05) (hash(x)=24384657) +4789 train 7.081707 (lr=1.0428e-05) (hash(x)=22550579) +4790 train 7.140224 (lr=1.0424e-05) (hash(x)=22452164) +4791 train 7.404845 (lr=1.0420e-05) (hash(x)=28664796) +4792 train 7.718273 (lr=1.0416e-05) (hash(x)=26139280) +4793 train 7.387573 (lr=1.0412e-05) (hash(x)=23862341) +4794 train 6.989032 (lr=1.0408e-05) (hash(x)=23784757) +4795 train 6.847290 (lr=1.0404e-05) (hash(x)=22659441) +4796 train 7.595853 (lr=1.0401e-05) (hash(x)=29744216) +4797 train 7.504323 (lr=1.0397e-05) (hash(x)=25822591) +4798 train 6.921364 (lr=1.0393e-05) (hash(x)=22370895) +4799 train 7.342158 (lr=1.0389e-05) (hash(x)=27102890) +4800 val loss 7.2299 +4800 val perplexity 1380.1119 +4800 train 7.409098 (lr=1.0385e-05) (hash(x)=27014625) +4801 train 7.169972 (lr=1.0381e-05) (hash(x)=25755963) +4802 train 7.401690 (lr=1.0377e-05) (hash(x)=29675278) +4803 train 7.506940 (lr=1.0374e-05) (hash(x)=26660930) +4804 train 7.443659 (lr=1.0370e-05) (hash(x)=24557060) +4805 train 7.595633 (lr=1.0366e-05) (hash(x)=24622741) +4806 train 7.624169 (lr=1.0362e-05) (hash(x)=23952601) +4807 train 7.224145 (lr=1.0359e-05) (hash(x)=26787259) +4808 train 7.506166 (lr=1.0355e-05) (hash(x)=28919605) +4809 train 7.816292 (lr=1.0351e-05) (hash(x)=37061654) +4810 train 7.594261 (lr=1.0347e-05) (hash(x)=30379739) +4811 train 7.320625 (lr=1.0344e-05) (hash(x)=26097180) +4812 train 7.484931 (lr=1.0340e-05) (hash(x)=26327092) +4813 train 7.290500 (lr=1.0337e-05) (hash(x)=23258030) +4814 train 7.346439 (lr=1.0333e-05) (hash(x)=25582015) +4815 train 7.043453 (lr=1.0329e-05) (hash(x)=23396088) +4816 train 7.018614 (lr=1.0326e-05) (hash(x)=21904146) +4817 train 7.230055 (lr=1.0322e-05) (hash(x)=26281676) +4818 train 6.985938 (lr=1.0319e-05) (hash(x)=23140470) +4819 train 7.300545 (lr=1.0315e-05) (hash(x)=24611098) +4820 train 7.117624 (lr=1.0312e-05) (hash(x)=23832642) +4821 train 7.296733 (lr=1.0308e-05) (hash(x)=21439671) +4822 train 7.142874 (lr=1.0305e-05) (hash(x)=25128845) +4823 train 7.079045 (lr=1.0302e-05) (hash(x)=24911831) +4824 train 7.257562 (lr=1.0298e-05) (hash(x)=26051723) +4825 train 7.256317 (lr=1.0295e-05) (hash(x)=26479565) +4826 train 7.385483 (lr=1.0291e-05) (hash(x)=26228987) +4827 train 7.268487 (lr=1.0288e-05) (hash(x)=25131300) +4828 train 6.994068 (lr=1.0285e-05) (hash(x)=19921978) +4829 train 6.986710 (lr=1.0282e-05) (hash(x)=23173449) +4830 train 7.293077 (lr=1.0278e-05) (hash(x)=24791832) +4831 train 7.022531 (lr=1.0275e-05) (hash(x)=23453491) +4832 train 7.174925 (lr=1.0272e-05) (hash(x)=22564139) +4833 train 7.007549 (lr=1.0269e-05) (hash(x)=21659918) +4834 train 7.150168 (lr=1.0265e-05) (hash(x)=22956076) +4835 train 7.257120 (lr=1.0262e-05) (hash(x)=22237612) +4836 train 7.371848 (lr=1.0259e-05) (hash(x)=24736427) +4837 train 7.451303 (lr=1.0256e-05) (hash(x)=24939751) +4838 train 7.260273 (lr=1.0253e-05) (hash(x)=25059298) +4839 train 7.179749 (lr=1.0250e-05) (hash(x)=23453396) +4840 train 6.706931 (lr=1.0247e-05) (hash(x)=17919338) +4841 train 7.217354 (lr=1.0243e-05) (hash(x)=23428815) +4842 train 7.477629 (lr=1.0240e-05) (hash(x)=27042659) +4843 train 7.576116 (lr=1.0237e-05) (hash(x)=25161278) +4844 train 7.342073 (lr=1.0234e-05) (hash(x)=24113253) +4845 train 7.426190 (lr=1.0231e-05) (hash(x)=26139263) +4846 train 7.499979 (lr=1.0228e-05) (hash(x)=27787006) +4847 train 7.217975 (lr=1.0225e-05) (hash(x)=23869612) +4848 train 7.340707 (lr=1.0222e-05) (hash(x)=26092193) +4849 train 7.397699 (lr=1.0220e-05) (hash(x)=29351182) +4850 val loss 7.2221 +4850 val perplexity 1369.4149 +4850 train 7.542254 (lr=1.0217e-05) (hash(x)=28773463) +4851 train 7.470589 (lr=1.0214e-05) (hash(x)=28207741) +4852 train 7.026210 (lr=1.0211e-05) (hash(x)=23280878) +4853 train 7.484645 (lr=1.0208e-05) (hash(x)=26742336) +4854 train 7.262409 (lr=1.0205e-05) (hash(x)=23543321) +4855 train 7.588787 (lr=1.0202e-05) (hash(x)=26581590) +4856 train 7.092603 (lr=1.0200e-05) (hash(x)=22728668) +4857 train 6.925392 (lr=1.0197e-05) (hash(x)=19854534) +4858 train 7.333373 (lr=1.0194e-05) (hash(x)=26612813) +4859 train 7.463369 (lr=1.0191e-05) (hash(x)=25827863) +4860 train 7.168233 (lr=1.0189e-05) (hash(x)=24574997) +4861 train 7.336002 (lr=1.0186e-05) (hash(x)=26187830) +4862 train 7.266389 (lr=1.0183e-05) (hash(x)=25105823) +4863 train 7.334362 (lr=1.0181e-05) (hash(x)=28056342) +4864 train 7.218846 (lr=1.0178e-05) (hash(x)=21885801) +4865 train 7.403023 (lr=1.0176e-05) (hash(x)=25659043) +4866 train 7.381303 (lr=1.0173e-05) (hash(x)=23852824) +4867 train 7.184303 (lr=1.0170e-05) (hash(x)=23965470) +4868 train 7.177236 (lr=1.0168e-05) (hash(x)=25035012) +4869 train 7.374219 (lr=1.0165e-05) (hash(x)=26639165) +4870 train 7.329567 (lr=1.0163e-05) (hash(x)=29205362) +4871 train 7.197277 (lr=1.0160e-05) (hash(x)=25900866) +4872 train 7.230666 (lr=1.0158e-05) (hash(x)=25636242) +4873 train 7.305858 (lr=1.0155e-05) (hash(x)=25430698) +4874 train 7.279641 (lr=1.0153e-05) (hash(x)=27629981) +4875 train 7.264957 (lr=1.0151e-05) (hash(x)=27682625) +4876 train 7.535497 (lr=1.0148e-05) (hash(x)=27549409) +4877 train 7.224506 (lr=1.0146e-05) (hash(x)=24661627) +4878 train 7.282372 (lr=1.0143e-05) (hash(x)=25196542) +4879 train 7.228531 (lr=1.0141e-05) (hash(x)=24549177) +4880 train 7.193971 (lr=1.0139e-05) (hash(x)=23740600) +4881 train 7.068195 (lr=1.0136e-05) (hash(x)=21460850) +4882 train 7.348405 (lr=1.0134e-05) (hash(x)=27101400) +4883 train 7.324821 (lr=1.0132e-05) (hash(x)=24193076) +4884 train 7.225719 (lr=1.0130e-05) (hash(x)=24582947) +4885 train 7.212653 (lr=1.0127e-05) (hash(x)=25133839) +4886 train 7.207890 (lr=1.0125e-05) (hash(x)=24759454) +4887 train 7.281482 (lr=1.0123e-05) (hash(x)=28239583) +4888 train 7.537241 (lr=1.0121e-05) (hash(x)=29594489) +4889 train 7.221153 (lr=1.0119e-05) (hash(x)=23833431) +4890 train 7.212020 (lr=1.0117e-05) (hash(x)=23139411) +4891 train 7.126382 (lr=1.0114e-05) (hash(x)=20885864) +4892 train 7.529083 (lr=1.0112e-05) (hash(x)=26217418) +4893 train 7.329346 (lr=1.0110e-05) (hash(x)=27321870) +4894 train 6.830179 (lr=1.0108e-05) (hash(x)=19912955) +4895 train 7.158594 (lr=1.0106e-05) (hash(x)=23223554) +4896 train 7.336764 (lr=1.0104e-05) (hash(x)=25667219) +4897 train 7.553526 (lr=1.0102e-05) (hash(x)=28007972) +4898 train 7.371999 (lr=1.0100e-05) (hash(x)=27748764) +4899 train 7.323425 (lr=1.0098e-05) (hash(x)=27425770) +4900 val loss 7.2202 +4900 val perplexity 1366.7703 +4900 train 7.422206 (lr=1.0096e-05) (hash(x)=28394020) +4901 train 7.276948 (lr=1.0094e-05) (hash(x)=24080235) +4902 train 7.125182 (lr=1.0093e-05) (hash(x)=23309527) +4903 train 7.127103 (lr=1.0091e-05) (hash(x)=24793480) +4904 train 7.357395 (lr=1.0089e-05) (hash(x)=25344456) +4905 train 7.295827 (lr=1.0087e-05) (hash(x)=24590670) +4906 train 7.230648 (lr=1.0085e-05) (hash(x)=26937171) +4907 train 7.336380 (lr=1.0083e-05) (hash(x)=26949097) +4908 train 7.057205 (lr=1.0082e-05) (hash(x)=22443915) +4909 train 7.132463 (lr=1.0080e-05) (hash(x)=23814995) +4910 train 7.200702 (lr=1.0078e-05) (hash(x)=26135871) +4911 train 7.035923 (lr=1.0076e-05) (hash(x)=25415570) +4912 train 7.310497 (lr=1.0075e-05) (hash(x)=26756326) +4913 train 7.227226 (lr=1.0073e-05) (hash(x)=22920200) +4914 train 7.301799 (lr=1.0071e-05) (hash(x)=26710977) +4915 train 7.191610 (lr=1.0070e-05) (hash(x)=24985634) +4916 train 7.301114 (lr=1.0068e-05) (hash(x)=26004335) +4917 train 7.227108 (lr=1.0066e-05) (hash(x)=25637457) +4918 train 7.443189 (lr=1.0065e-05) (hash(x)=26645180) +4919 train 7.290033 (lr=1.0063e-05) (hash(x)=24425760) +4920 train 7.494667 (lr=1.0062e-05) (hash(x)=28223544) +4921 train 7.219788 (lr=1.0060e-05) (hash(x)=25538618) +4922 train 7.484293 (lr=1.0059e-05) (hash(x)=26984784) +4923 train 7.503807 (lr=1.0057e-05) (hash(x)=29154578) +4924 train 7.212558 (lr=1.0056e-05) (hash(x)=25308123) +4925 train 7.485272 (lr=1.0054e-05) (hash(x)=27939259) +4926 train 7.107358 (lr=1.0053e-05) (hash(x)=21984545) +4927 train 7.150878 (lr=1.0051e-05) (hash(x)=23707134) +4928 train 7.214262 (lr=1.0050e-05) (hash(x)=27201034) +4929 train 7.612011 (lr=1.0049e-05) (hash(x)=31623877) +4930 train 7.206838 (lr=1.0047e-05) (hash(x)=22162782) +4931 train 7.103092 (lr=1.0046e-05) (hash(x)=20049335) +4932 train 7.077387 (lr=1.0045e-05) (hash(x)=25594665) +4933 train 7.196959 (lr=1.0043e-05) (hash(x)=25265312) +4934 train 7.302992 (lr=1.0042e-05) (hash(x)=27094896) +4935 train 7.681219 (lr=1.0041e-05) (hash(x)=28321697) +4936 train 7.163122 (lr=1.0039e-05) (hash(x)=25006013) +4937 train 7.379479 (lr=1.0038e-05) (hash(x)=24596431) +4938 train 7.400127 (lr=1.0037e-05) (hash(x)=25150510) +4939 train 6.926027 (lr=1.0036e-05) (hash(x)=21497535) +4940 train 7.197963 (lr=1.0035e-05) (hash(x)=25094669) +4941 train 7.082834 (lr=1.0034e-05) (hash(x)=24024557) +4942 train 7.383080 (lr=1.0032e-05) (hash(x)=24370776) +4943 train 7.202734 (lr=1.0031e-05) (hash(x)=23434031) +4944 train 7.227415 (lr=1.0030e-05) (hash(x)=24383517) +4945 train 7.223393 (lr=1.0029e-05) (hash(x)=25858759) +4946 train 6.827361 (lr=1.0028e-05) (hash(x)=20409561) +4947 train 7.508098 (lr=1.0027e-05) (hash(x)=27469117) +4948 train 7.058221 (lr=1.0026e-05) (hash(x)=22086623) +4949 train 7.348170 (lr=1.0025e-05) (hash(x)=25759281) +4950 val loss 7.2162 +4950 val perplexity 1361.2769 +4950 train 7.256008 (lr=1.0024e-05) (hash(x)=27130117) +4951 train 7.151916 (lr=1.0023e-05) (hash(x)=27003481) +4952 train 7.465860 (lr=1.0022e-05) (hash(x)=26725937) +4953 train 7.202720 (lr=1.0021e-05) (hash(x)=22691119) +4954 train 7.265499 (lr=1.0020e-05) (hash(x)=17272898) +4955 train 7.059724 (lr=1.0020e-05) (hash(x)=17850370) +4956 train 7.078147 (lr=1.0019e-05) (hash(x)=18729639) +4957 train 7.279530 (lr=1.0018e-05) (hash(x)=25327160) +4958 train 7.435464 (lr=1.0017e-05) (hash(x)=28709044) +4959 train 6.990578 (lr=1.0016e-05) (hash(x)=22236893) +4960 train 6.965465 (lr=1.0015e-05) (hash(x)=21729251) +4961 train 7.087924 (lr=1.0015e-05) (hash(x)=23852346) +4962 train 7.259767 (lr=1.0014e-05) (hash(x)=23974368) +4963 train 7.228405 (lr=1.0013e-05) (hash(x)=25764691) +4964 train 7.605964 (lr=1.0012e-05) (hash(x)=28341865) +4965 train 7.091378 (lr=1.0012e-05) (hash(x)=23856238) +4966 train 7.328397 (lr=1.0011e-05) (hash(x)=24568904) +4967 train 7.231565 (lr=1.0010e-05) (hash(x)=26857458) +4968 train 7.099382 (lr=1.0010e-05) (hash(x)=20507972) +4969 train 7.284807 (lr=1.0009e-05) (hash(x)=23139455) +4970 train 7.134124 (lr=1.0009e-05) (hash(x)=24853703) +4971 train 7.160662 (lr=1.0008e-05) (hash(x)=25654849) +4972 train 7.006885 (lr=1.0008e-05) (hash(x)=22963710) +4973 train 7.371922 (lr=1.0007e-05) (hash(x)=25652110) +4974 train 7.314678 (lr=1.0007e-05) (hash(x)=24085957) +4975 train 7.521515 (lr=1.0006e-05) (hash(x)=26413122) +4976 train 7.630502 (lr=1.0006e-05) (hash(x)=26989387) +4977 train 7.314693 (lr=1.0005e-05) (hash(x)=22784033) +4978 train 7.642503 (lr=1.0005e-05) (hash(x)=26694945) +4979 train 7.592977 (lr=1.0004e-05) (hash(x)=24507726) +4980 train 7.642839 (lr=1.0004e-05) (hash(x)=26490335) +4981 train 7.574146 (lr=1.0003e-05) (hash(x)=25624751) +4982 train 7.543934 (lr=1.0003e-05) (hash(x)=27846204) +4983 train 7.408142 (lr=1.0003e-05) (hash(x)=27696537) +4984 train 7.287497 (lr=1.0002e-05) (hash(x)=28915842) +4985 train 7.386154 (lr=1.0002e-05) (hash(x)=28274576) +4986 train 7.409059 (lr=1.0002e-05) (hash(x)=28923892) +4987 train 7.034904 (lr=1.0002e-05) (hash(x)=21602520) +4988 train 6.958627 (lr=1.0001e-05) (hash(x)=21061011) +4989 train 7.447284 (lr=1.0001e-05) (hash(x)=28060542) +4990 train 7.231644 (lr=1.0001e-05) (hash(x)=24838134) +4991 train 7.193036 (lr=1.0001e-05) (hash(x)=21950234) +4992 train 7.443066 (lr=1.0001e-05) (hash(x)=27192740) +4993 train 7.407979 (lr=1.0000e-05) (hash(x)=26770105) +4994 train 7.102185 (lr=1.0000e-05) (hash(x)=23721261) +4995 train 7.155115 (lr=1.0000e-05) (hash(x)=26064895) +4996 train 7.351424 (lr=1.0000e-05) (hash(x)=25651075) +4997 train 7.198274 (lr=1.0000e-05) (hash(x)=25029447) +4998 train 7.342973 (lr=1.0000e-05) (hash(x)=26088225) +4999 val loss 7.2180 +4999 val perplexity 1363.7393 +4999 train 7.250989 (lr=1.0000e-05) (hash(x)=24051952) diff --git a/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/model_02500.pt b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/model_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..471a3ef2be99615e2f13410ac35e8656df4ad71d --- /dev/null +++ b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/model_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f609d1a2e6ea68416fa07062cfbd1f640635cff91d8aba889b0d320c59f5fac +size 38587970 diff --git a/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/model_04999.pt b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/model_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..fc2a36dc0cce4d193118220cc844ebcf8a44961a --- /dev/null +++ b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/model_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cfd5520930ddc4b6acb48304c85e1cfe4cf16226f3d9df365771c2455dd61ca +size 38587970 diff --git a/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/optimizer_02500.pt b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/optimizer_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..b666dbec795f85a6779bb7dc85e28e43ff49a7bb --- /dev/null +++ b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/optimizer_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45f53280a3d3926a4004543bb9e86125621f12a2c15e1733e1729e740f8fed43 +size 70895430 diff --git a/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/optimizer_04999.pt b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/optimizer_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..6593b9f6ce07be37a3bc501771ba9d89be5d9694 --- /dev/null +++ b/lr1e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps200/optimizer_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a8726521185a763753957b51425eda1505fabe7cd436fb31da7891edb03aec6 +size 70895430