diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/args.json b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/args.json new file mode 100644 index 0000000000000000000000000000000000000000..9db63d19ed0172b0a00b005059c652529c13a080 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/args.json @@ -0,0 +1 @@ +{"hellaswag": true, "attention_kind": "selective", "log_dir": "proxy_model_sweep_2/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339", "resume_checkpoint": null, "resume_optimizer": false, "add_a_head": false, "add_head_to_start": true, "new_head_init": "normal", "n_heads": 2, "protect_bos_token": true, "prevent_from_masking_myself": true, "max_steps": 5000, "warmup_steps": 1, "group": "proxy_model_sweep_2", "use_wandb": true, "kill_self_after_run": false, "random_seed": 1339, "memory_penalty_epsilon": 0.1, "selection_head_linear_combo": "none", "selection_head_linear_combo_scale": 1.0, "protection_kind": "none", "leaky_relu_alpha": null, "leaky_relu_bias": null, "use_compile": true, "use_mini_model": false, "upload_to_hf": true, "seq_len": 256, "batch_size": 20, "total_batch_size": 5120, "protection_head_scaling_factor": 1.0, "protection_head_bias": 0.0, "n_sliced_masks": null, "n_latent_masks": null, "mask_layernorm": false, "residual_attention_masks": false, "compute_base_shapes": false, "base_shapes_savefile": null, "mup": true, "disable_selection": false, "mup_enable_coord_check_logging": false, "max_lr": 0.000175, "decay_lr": false, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "n_embd": 128} \ No newline at end of file diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/dataloader_02500.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/dataloader_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bc253f8fc6225637fb651d7b45bcde02b1c9ff0 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/dataloader_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5f86eba64e08aa3145708d463ef689ecaee47ebe0a97035e6e0aeb59f377344 +size 964 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/dataloader_04999.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/dataloader_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..0618c479f1dc6588bdd52311cf3417cbd843ddd9 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/dataloader_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431842dc67f0d83e5eb85cf9c36fd024e295001fe78f3ba5deeae77865394feb +size 964 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/log2.txt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/log2.txt new file mode 100644 index 0000000000000000000000000000000000000000..27bc74ec9e922b85d8a12e1b00d543d4d37dba60 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/log2.txt @@ -0,0 +1,5203 @@ +max_steps: 5000 +0 val loss 11.7530 +0 val perplexity 127132.9688 +0 train 11.730812 (lr=1.7500e-04) (hash(x)=22886834) +1 train 11.396555 (lr=1.7500e-04) (hash(x)=26375038) +2 train 11.169489 (lr=1.7500e-04) (hash(x)=30598777) +3 train 11.027948 (lr=1.7500e-04) (hash(x)=27234506) +4 train 10.743355 (lr=1.7500e-04) (hash(x)=27767880) +5 train 10.570519 (lr=1.7500e-04) (hash(x)=23702020) +6 train 10.599805 (lr=1.7500e-04) (hash(x)=31986844) +7 train 10.435844 (lr=1.7500e-04) (hash(x)=20782690) +8 train 10.407110 (lr=1.7500e-04) (hash(x)=25201599) +9 train 10.263606 (lr=1.7500e-04) (hash(x)=23094976) +10 train 10.265764 (lr=1.7500e-04) (hash(x)=23841096) +11 train 10.278152 (lr=1.7500e-04) (hash(x)=26532095) +12 train 10.212722 (lr=1.7500e-04) (hash(x)=24432298) +13 train 10.159808 (lr=1.7500e-04) (hash(x)=27151649) +14 train 10.195521 (lr=1.7500e-04) (hash(x)=24596846) +15 train 9.935138 (lr=1.7500e-04) (hash(x)=23890908) +16 train 9.881206 (lr=1.7500e-04) (hash(x)=28913955) +17 train 9.752540 (lr=1.7500e-04) (hash(x)=25588236) +18 train 9.801448 (lr=1.7500e-04) (hash(x)=23770034) +19 train 9.635512 (lr=1.7500e-04) (hash(x)=24011372) +20 train 9.453375 (lr=1.7500e-04) (hash(x)=25441898) +21 train 9.622111 (lr=1.7500e-04) (hash(x)=28375581) +22 train 9.263880 (lr=1.7500e-04) (hash(x)=24046679) +23 train 9.333375 (lr=1.7500e-04) (hash(x)=24611628) +24 train 9.323980 (lr=1.7500e-04) (hash(x)=26169030) +25 train 9.342830 (lr=1.7500e-04) (hash(x)=30298407) +26 train 9.066312 (lr=1.7500e-04) (hash(x)=23711112) +27 train 8.889734 (lr=1.7500e-04) (hash(x)=19245352) +28 train 8.810900 (lr=1.7500e-04) (hash(x)=21529136) +29 train 9.179865 (lr=1.7500e-04) (hash(x)=28936608) +30 train 8.721114 (lr=1.7500e-04) (hash(x)=24339013) +31 train 8.556380 (lr=1.7500e-04) (hash(x)=25767553) +32 train 8.713610 (lr=1.7500e-04) (hash(x)=26439905) +33 train 8.889589 (lr=1.7500e-04) (hash(x)=31093473) +34 train 8.501918 (lr=1.7500e-04) (hash(x)=25450374) +35 train 8.397277 (lr=1.7500e-04) (hash(x)=24809873) +36 train 8.544780 (lr=1.7500e-04) (hash(x)=23253252) +37 train 8.620289 (lr=1.7500e-04) (hash(x)=27852919) +38 train 8.350981 (lr=1.7500e-04) (hash(x)=23327497) +39 train 8.204629 (lr=1.7500e-04) (hash(x)=22512166) +40 train 8.338959 (lr=1.7500e-04) (hash(x)=22859419) +41 train 8.299472 (lr=1.7500e-04) (hash(x)=27620338) +42 train 8.368865 (lr=1.7500e-04) (hash(x)=26397837) +43 train 8.378649 (lr=1.7500e-04) (hash(x)=28092148) +44 train 8.188556 (lr=1.7500e-04) (hash(x)=24662703) +45 train 8.357420 (lr=1.7500e-04) (hash(x)=27938767) +46 train 8.664148 (lr=1.7500e-04) (hash(x)=26037988) +47 train 8.062140 (lr=1.7500e-04) (hash(x)=24732833) +48 train 8.190636 (lr=1.7500e-04) (hash(x)=25259526) +49 train 8.152381 (lr=1.7500e-04) (hash(x)=23200230) +50 val loss 8.1088 +50 val perplexity 3323.7424 +50 train 8.177659 (lr=1.7500e-04) (hash(x)=26721357) +51 train 7.975617 (lr=1.7500e-04) (hash(x)=22694718) +52 train 8.073786 (lr=1.7500e-04) (hash(x)=28066766) +53 train 8.017853 (lr=1.7500e-04) (hash(x)=23125151) +54 train 8.019969 (lr=1.7500e-04) (hash(x)=27193725) +55 train 7.912093 (lr=1.7500e-04) (hash(x)=25129410) +56 train 8.026929 (lr=1.7500e-04) (hash(x)=24263988) +57 train 7.838060 (lr=1.7500e-04) (hash(x)=23059154) +58 train 8.050242 (lr=1.7500e-04) (hash(x)=26063864) +59 train 8.327651 (lr=1.7500e-04) (hash(x)=27858570) +60 train 8.019467 (lr=1.7500e-04) (hash(x)=23874620) +61 train 7.894326 (lr=1.7500e-04) (hash(x)=22402617) +62 train 7.988628 (lr=1.7500e-04) (hash(x)=23600822) +63 train 7.840704 (lr=1.7500e-04) (hash(x)=26582391) +64 train 7.849367 (lr=1.7500e-04) (hash(x)=23225283) +65 train 8.211998 (lr=1.7500e-04) (hash(x)=26075451) +66 train 7.887206 (lr=1.7500e-04) (hash(x)=24723419) +67 train 8.039772 (lr=1.7500e-04) (hash(x)=27279806) +68 train 7.828607 (lr=1.7500e-04) (hash(x)=25870391) +69 train 8.048182 (lr=1.7500e-04) (hash(x)=26188136) +70 train 8.164133 (lr=1.7500e-04) (hash(x)=30373443) +71 train 8.092785 (lr=1.7500e-04) (hash(x)=26472336) +72 train 7.858301 (lr=1.7500e-04) (hash(x)=26651572) +73 train 8.004233 (lr=1.7500e-04) (hash(x)=26376212) +74 train 7.974628 (lr=1.7500e-04) (hash(x)=26733350) +75 train 8.123560 (lr=1.7500e-04) (hash(x)=28301589) +76 train 7.995377 (lr=1.7500e-04) (hash(x)=27599559) +77 train 7.971474 (lr=1.7500e-04) (hash(x)=28035221) +78 train 7.975227 (lr=1.7500e-04) (hash(x)=25016783) +79 train 8.042075 (lr=1.7500e-04) (hash(x)=27654289) +80 train 7.886360 (lr=1.7500e-04) (hash(x)=24597558) +81 train 7.661455 (lr=1.7500e-04) (hash(x)=21560904) +82 train 7.645824 (lr=1.7500e-04) (hash(x)=21983837) +83 train 7.815588 (lr=1.7500e-04) (hash(x)=24995715) +84 train 8.124804 (lr=1.7500e-04) (hash(x)=29876413) +85 train 7.765382 (lr=1.7500e-04) (hash(x)=23792508) +86 train 7.744119 (lr=1.7500e-04) (hash(x)=25509120) +87 train 7.958678 (lr=1.7500e-04) (hash(x)=26559876) +88 train 7.893159 (lr=1.7500e-04) (hash(x)=23569647) +89 train 7.881908 (lr=1.7500e-04) (hash(x)=25758852) +90 train 7.744821 (lr=1.7500e-04) (hash(x)=25706298) +91 train 7.893353 (lr=1.7500e-04) (hash(x)=28364895) +92 train 7.756313 (lr=1.7500e-04) (hash(x)=25304663) +93 train 7.820131 (lr=1.7500e-04) (hash(x)=25269299) +94 train 7.958913 (lr=1.7500e-04) (hash(x)=25870566) +95 train 7.560973 (lr=1.7500e-04) (hash(x)=21770329) +96 train 8.053795 (lr=1.7500e-04) (hash(x)=27595900) +97 train 7.973756 (lr=1.7500e-04) (hash(x)=24785397) +98 train 7.665471 (lr=1.7500e-04) (hash(x)=21521480) +99 train 7.791159 (lr=1.7500e-04) (hash(x)=24628606) +100 val loss 7.8402 +100 val perplexity 2540.7771 +100 train 7.909635 (lr=1.7500e-04) (hash(x)=24670150) +101 train 7.811881 (lr=1.7500e-04) (hash(x)=23181910) +102 train 7.780936 (lr=1.7500e-04) (hash(x)=22714991) +103 train 7.761182 (lr=1.7500e-04) (hash(x)=22723459) +104 train 7.697221 (lr=1.7500e-04) (hash(x)=21524316) +105 train 7.876626 (lr=1.7500e-04) (hash(x)=25506632) +106 train 7.561470 (lr=1.7500e-04) (hash(x)=21675672) +107 train 7.661810 (lr=1.7500e-04) (hash(x)=22897919) +108 train 7.708295 (lr=1.7500e-04) (hash(x)=23321631) +109 train 7.887444 (lr=1.7500e-04) (hash(x)=26546719) +110 train 8.950775 (lr=1.7500e-04) (hash(x)=31962348) +111 train 8.235358 (lr=1.7500e-04) (hash(x)=30338342) +112 train 7.790555 (lr=1.7500e-04) (hash(x)=23724471) +113 train 7.949436 (lr=1.7500e-04) (hash(x)=29175888) +114 train 7.946006 (lr=1.7500e-04) (hash(x)=23256716) +115 train 8.056595 (lr=1.7500e-04) (hash(x)=27063280) +116 train 8.072675 (lr=1.7500e-04) (hash(x)=31057659) +117 train 8.284288 (lr=1.7500e-04) (hash(x)=32915097) +118 train 8.102925 (lr=1.7500e-04) (hash(x)=28842717) +119 train 7.787332 (lr=1.7500e-04) (hash(x)=25678059) +120 train 7.629570 (lr=1.7500e-04) (hash(x)=21593510) +121 train 7.570438 (lr=1.7500e-04) (hash(x)=20083773) +122 train 7.715068 (lr=1.7500e-04) (hash(x)=23002820) +123 train 7.579315 (lr=1.7500e-04) (hash(x)=21853028) +124 train 7.841597 (lr=1.7500e-04) (hash(x)=26985625) +125 train 7.565362 (lr=1.7500e-04) (hash(x)=21808483) +126 train 7.964963 (lr=1.7500e-04) (hash(x)=28873251) +127 train 7.854646 (lr=1.7500e-04) (hash(x)=26109335) +128 train 8.026166 (lr=1.7500e-04) (hash(x)=26334674) +129 train 7.880516 (lr=1.7500e-04) (hash(x)=24916754) +130 train 7.829212 (lr=1.7500e-04) (hash(x)=25449624) +131 train 7.897440 (lr=1.7500e-04) (hash(x)=25334848) +132 train 8.168159 (lr=1.7500e-04) (hash(x)=27484863) +133 train 7.750125 (lr=1.7500e-04) (hash(x)=24917705) +134 train 7.737061 (lr=1.7500e-04) (hash(x)=25143449) +135 train 7.776746 (lr=1.7500e-04) (hash(x)=25044885) +136 train 7.978964 (lr=1.7500e-04) (hash(x)=27821028) +137 train 7.935985 (lr=1.7500e-04) (hash(x)=28747022) +138 train 7.908286 (lr=1.7500e-04) (hash(x)=27182888) +139 train 7.698439 (lr=1.7500e-04) (hash(x)=23678349) +140 train 7.812323 (lr=1.7500e-04) (hash(x)=23593235) +141 train 8.131122 (lr=1.7500e-04) (hash(x)=28529813) +142 train 8.449798 (lr=1.7500e-04) (hash(x)=32074661) +143 train 8.007034 (lr=1.7500e-04) (hash(x)=28870690) +144 train 7.962647 (lr=1.7500e-04) (hash(x)=27307705) +145 train 7.817974 (lr=1.7500e-04) (hash(x)=25044834) +146 train 7.866621 (lr=1.7500e-04) (hash(x)=23712023) +147 train 8.366024 (lr=1.7500e-04) (hash(x)=32982615) +148 train 8.143027 (lr=1.7500e-04) (hash(x)=30113660) +149 train 7.598140 (lr=1.7500e-04) (hash(x)=20970960) +150 val loss 7.8094 +150 val perplexity 2463.6638 +150 train 7.788681 (lr=1.7500e-04) (hash(x)=23132684) +151 train 9.550034 (lr=1.7500e-04) (hash(x)=35279941) +152 train 8.703839 (lr=1.7500e-04) (hash(x)=31227444) +153 train 7.753027 (lr=1.7500e-04) (hash(x)=25529472) +154 train 7.846207 (lr=1.7500e-04) (hash(x)=24350409) +155 train 8.124321 (lr=1.7500e-04) (hash(x)=26400041) +156 train 7.813891 (lr=1.7500e-04) (hash(x)=25262621) +157 train 7.857075 (lr=1.7500e-04) (hash(x)=24656138) +158 train 8.075266 (lr=1.7500e-04) (hash(x)=26803414) +159 train 7.942709 (lr=1.7500e-04) (hash(x)=25015923) +160 train 7.652966 (lr=1.7500e-04) (hash(x)=23581172) +161 train 7.789327 (lr=1.7500e-04) (hash(x)=22924885) +162 train 7.724106 (lr=1.7500e-04) (hash(x)=23414296) +163 train 7.915267 (lr=1.7500e-04) (hash(x)=24853586) +164 train 7.974779 (lr=1.7500e-04) (hash(x)=25000130) +165 train 7.866339 (lr=1.7500e-04) (hash(x)=27004780) +166 train 7.859138 (lr=1.7500e-04) (hash(x)=26148573) +167 train 7.820839 (lr=1.7500e-04) (hash(x)=26740855) +168 train 7.506124 (lr=1.7500e-04) (hash(x)=20965419) +169 train 7.738639 (lr=1.7500e-04) (hash(x)=23950114) +170 train 7.673870 (lr=1.7500e-04) (hash(x)=24951982) +171 train 7.791021 (lr=1.7500e-04) (hash(x)=24584116) +172 train 7.744225 (lr=1.7500e-04) (hash(x)=24378759) +173 train 7.759203 (lr=1.7500e-04) (hash(x)=25718516) +174 train 7.899930 (lr=1.7500e-04) (hash(x)=28424396) +175 train 7.698026 (lr=1.7500e-04) (hash(x)=22262151) +176 train 7.952837 (lr=1.7500e-04) (hash(x)=26438412) +177 train 7.835645 (lr=1.7500e-04) (hash(x)=23025303) +178 train 7.791521 (lr=1.7500e-04) (hash(x)=24190770) +179 train 8.245699 (lr=1.7500e-04) (hash(x)=26627860) +180 train 7.824049 (lr=1.7500e-04) (hash(x)=23663439) +181 train 8.129807 (lr=1.7500e-04) (hash(x)=23700532) +182 train 7.891254 (lr=1.7500e-04) (hash(x)=23075676) +183 train 7.936607 (lr=1.7500e-04) (hash(x)=26621834) +184 train 8.007244 (lr=1.7500e-04) (hash(x)=29426269) +185 train 7.630728 (lr=1.7500e-04) (hash(x)=21821465) +186 train 7.841345 (lr=1.7500e-04) (hash(x)=26506130) +187 train 8.088679 (lr=1.7500e-04) (hash(x)=26930630) +188 train 7.576506 (lr=1.7500e-04) (hash(x)=22993793) +189 train 7.446027 (lr=1.7500e-04) (hash(x)=19557946) +190 train 7.794292 (lr=1.7500e-04) (hash(x)=23572891) +191 train 7.617348 (lr=1.7500e-04) (hash(x)=23234741) +192 train 7.690465 (lr=1.7500e-04) (hash(x)=25547951) +193 train 7.814093 (lr=1.7500e-04) (hash(x)=26713563) +194 train 7.798448 (lr=1.7500e-04) (hash(x)=25913622) +195 train 8.060022 (lr=1.7500e-04) (hash(x)=28102443) +196 train 7.767414 (lr=1.7500e-04) (hash(x)=23093351) +197 train 8.438293 (lr=1.7500e-04) (hash(x)=31689122) +198 train 8.283806 (lr=1.7500e-04) (hash(x)=32252517) +199 train 7.894222 (lr=1.7500e-04) (hash(x)=25470563) +200 val loss 7.8460 +200 val perplexity 2555.4253 +200 train 7.927710 (lr=1.7500e-04) (hash(x)=25597614) +201 train 7.963249 (lr=1.7500e-04) (hash(x)=23757479) +202 train 7.794241 (lr=1.7500e-04) (hash(x)=25140048) +203 train 7.933336 (lr=1.7500e-04) (hash(x)=28282861) +204 train 7.731200 (lr=1.7500e-04) (hash(x)=24754885) +205 train 7.944847 (lr=1.7500e-04) (hash(x)=26731964) +206 train 8.033517 (lr=1.7500e-04) (hash(x)=26660561) +207 train 7.622277 (lr=1.7500e-04) (hash(x)=21799102) +208 train 7.837569 (lr=1.7500e-04) (hash(x)=27025986) +209 train 7.690694 (lr=1.7500e-04) (hash(x)=24672077) +210 train 7.753848 (lr=1.7500e-04) (hash(x)=25322984) +211 train 7.630615 (lr=1.7500e-04) (hash(x)=23471769) +212 train 7.460430 (lr=1.7500e-04) (hash(x)=20766491) +213 train 7.933251 (lr=1.7500e-04) (hash(x)=24058931) +214 train 7.678239 (lr=1.7500e-04) (hash(x)=23872843) +215 train 7.736856 (lr=1.7500e-04) (hash(x)=23275479) +216 train 7.818363 (lr=1.7500e-04) (hash(x)=24914695) +217 train 7.691237 (lr=1.7500e-04) (hash(x)=24364396) +218 train 7.945640 (lr=1.7500e-04) (hash(x)=27986474) +219 train 7.833647 (lr=1.7500e-04) (hash(x)=24473581) +220 train 7.744743 (lr=1.7500e-04) (hash(x)=22974689) +221 train 7.802795 (lr=1.7500e-04) (hash(x)=23774644) +222 train 7.751188 (lr=1.7500e-04) (hash(x)=23245327) +223 train 7.569769 (lr=1.7500e-04) (hash(x)=22091862) +224 train 7.646726 (lr=1.7500e-04) (hash(x)=24362839) +225 train 7.825891 (lr=1.7500e-04) (hash(x)=25482303) +226 train 7.903543 (lr=1.7500e-04) (hash(x)=24911853) +227 train 7.875500 (lr=1.7500e-04) (hash(x)=26018202) +228 train 7.724420 (lr=1.7500e-04) (hash(x)=26124495) +229 train 7.846442 (lr=1.7500e-04) (hash(x)=24560096) +230 train 7.799600 (lr=1.7500e-04) (hash(x)=24695331) +231 train 7.534322 (lr=1.7500e-04) (hash(x)=17430373) +232 train 7.564418 (lr=1.7500e-04) (hash(x)=21813345) +233 train 7.237757 (lr=1.7500e-04) (hash(x)=20098681) +234 train 7.546315 (lr=1.7500e-04) (hash(x)=25095928) +235 train 7.649704 (lr=1.7500e-04) (hash(x)=24078083) +236 train 7.643732 (lr=1.7500e-04) (hash(x)=22901505) +237 train 7.893411 (lr=1.7500e-04) (hash(x)=26595592) +238 train 7.758193 (lr=1.7500e-04) (hash(x)=27663196) +239 train 7.553413 (lr=1.7500e-04) (hash(x)=22954861) +240 train 8.004030 (lr=1.7500e-04) (hash(x)=30159234) +241 train 7.929531 (lr=1.7500e-04) (hash(x)=29294271) +242 train 7.862804 (lr=1.7500e-04) (hash(x)=23728322) +243 train 7.894406 (lr=1.7500e-04) (hash(x)=28695016) +244 train 8.025711 (lr=1.7500e-04) (hash(x)=26702728) +245 train 7.824727 (lr=1.7500e-04) (hash(x)=27100115) +246 train 7.734431 (lr=1.7500e-04) (hash(x)=25082752) +247 train 8.087722 (lr=1.7500e-04) (hash(x)=26671799) +248 train 7.810709 (lr=1.7500e-04) (hash(x)=23718946) +249 train 8.015184 (lr=1.7500e-04) (hash(x)=28137394) +250 val loss 7.7526 +250 val perplexity 2327.6323 +250 train 8.044301 (lr=1.7500e-04) (hash(x)=23893495) +251 train 7.824704 (lr=1.7500e-04) (hash(x)=23166092) +252 train 7.785588 (lr=1.7500e-04) (hash(x)=25907665) +253 train 7.785545 (lr=1.7500e-04) (hash(x)=25885986) +254 train 7.812982 (lr=1.7500e-04) (hash(x)=25262712) +255 train 7.768513 (lr=1.7500e-04) (hash(x)=26924723) +256 train 7.926662 (lr=1.7500e-04) (hash(x)=28744736) +257 train 7.674947 (lr=1.7500e-04) (hash(x)=26140590) +258 train 7.876205 (lr=1.7500e-04) (hash(x)=25780449) +259 train 7.712479 (lr=1.7500e-04) (hash(x)=25138659) +260 train 8.039403 (lr=1.7500e-04) (hash(x)=27244046) +261 train 7.876209 (lr=1.7500e-04) (hash(x)=27224685) +262 train 8.126907 (lr=1.7500e-04) (hash(x)=28274477) +263 train 7.649992 (lr=1.7500e-04) (hash(x)=23557495) +264 train 7.768669 (lr=1.7500e-04) (hash(x)=24680596) +265 train 7.796749 (lr=1.7500e-04) (hash(x)=23928957) +266 train 7.738622 (lr=1.7500e-04) (hash(x)=23761390) +267 train 7.624763 (lr=1.7500e-04) (hash(x)=25288123) +268 train 7.923713 (lr=1.7500e-04) (hash(x)=28705502) +269 train 7.538313 (lr=1.7500e-04) (hash(x)=23246294) +270 train 7.648372 (lr=1.7500e-04) (hash(x)=28639079) +271 train 7.529457 (lr=1.7500e-04) (hash(x)=27804380) +272 train 7.724401 (lr=1.7500e-04) (hash(x)=24172235) +273 train 7.779552 (lr=1.7500e-04) (hash(x)=23089140) +274 train 8.007133 (lr=1.7500e-04) (hash(x)=27163701) +275 train 8.093090 (lr=1.7500e-04) (hash(x)=26993263) +276 train 7.797729 (lr=1.7500e-04) (hash(x)=28224233) +277 train 8.134597 (lr=1.7500e-04) (hash(x)=27397203) +278 train 8.010958 (lr=1.7500e-04) (hash(x)=27923882) +279 train 7.866006 (lr=1.7500e-04) (hash(x)=26654908) +280 train 7.763147 (lr=1.7500e-04) (hash(x)=24213147) +281 train 7.511524 (lr=1.7500e-04) (hash(x)=21965022) +282 train 7.679630 (lr=1.7500e-04) (hash(x)=25465685) +283 train 7.893494 (lr=1.7500e-04) (hash(x)=27347722) +284 train 7.891587 (lr=1.7500e-04) (hash(x)=26732050) +285 train 8.056346 (lr=1.7500e-04) (hash(x)=28314127) +286 train 7.586658 (lr=1.7500e-04) (hash(x)=21471186) +287 train 7.596805 (lr=1.7500e-04) (hash(x)=23627518) +288 train 7.553645 (lr=1.7500e-04) (hash(x)=20870353) +289 train 7.686697 (lr=1.7500e-04) (hash(x)=25024764) +290 train 7.495965 (lr=1.7500e-04) (hash(x)=20683822) +291 train 7.757658 (lr=1.7500e-04) (hash(x)=21768671) +292 train 7.790665 (lr=1.7500e-04) (hash(x)=25557309) +293 train 7.933755 (lr=1.7500e-04) (hash(x)=25076667) +294 train 7.577945 (lr=1.7500e-04) (hash(x)=23765822) +295 train 7.528297 (lr=1.7500e-04) (hash(x)=21889990) +296 train 7.762619 (lr=1.7500e-04) (hash(x)=26339893) +297 train 7.454120 (lr=1.7500e-04) (hash(x)=20932794) +298 train 7.610628 (lr=1.7500e-04) (hash(x)=21750070) +299 train 7.786567 (lr=1.7500e-04) (hash(x)=23665838) +300 val loss 7.6958 +300 val perplexity 2199.0920 +300 train 8.580429 (lr=1.7500e-04) (hash(x)=32888061) +301 train 8.314158 (lr=1.7500e-04) (hash(x)=30223582) +302 train 8.031529 (lr=1.7500e-04) (hash(x)=26908418) +303 train 7.399283 (lr=1.7500e-04) (hash(x)=22528001) +304 train 7.931489 (lr=1.7500e-04) (hash(x)=27452187) +305 train 7.672408 (lr=1.7500e-04) (hash(x)=25181641) +306 train 7.804146 (lr=1.7500e-04) (hash(x)=25546593) +307 train 7.813054 (lr=1.7500e-04) (hash(x)=22487328) +308 train 7.939009 (lr=1.7500e-04) (hash(x)=27804274) +309 train 7.976827 (lr=1.7500e-04) (hash(x)=26544630) +310 train 8.093137 (lr=1.7500e-04) (hash(x)=27738934) +311 train 7.922958 (lr=1.7500e-04) (hash(x)=29248942) +312 train 7.661747 (lr=1.7500e-04) (hash(x)=25103452) +313 train 7.900254 (lr=1.7500e-04) (hash(x)=25052066) +314 train 7.681593 (lr=1.7500e-04) (hash(x)=24481302) +315 train 7.633351 (lr=1.7500e-04) (hash(x)=23543273) +316 train 7.665300 (lr=1.7500e-04) (hash(x)=25608244) +317 train 7.800185 (lr=1.7500e-04) (hash(x)=27451288) +318 train 7.500599 (lr=1.7500e-04) (hash(x)=22806491) +319 train 7.682228 (lr=1.7500e-04) (hash(x)=25533417) +320 train 7.705356 (lr=1.7500e-04) (hash(x)=24557997) +321 train 7.767145 (lr=1.7500e-04) (hash(x)=24432899) +322 train 8.002137 (lr=1.7500e-04) (hash(x)=27583287) +323 train 7.892192 (lr=1.7500e-04) (hash(x)=25552036) +324 train 7.608246 (lr=1.7500e-04) (hash(x)=24201868) +325 train 7.894786 (lr=1.7500e-04) (hash(x)=28149782) +326 train 7.693096 (lr=1.7500e-04) (hash(x)=25529698) +327 train 7.398406 (lr=1.7500e-04) (hash(x)=20612533) +328 train 7.434108 (lr=1.7500e-04) (hash(x)=20699000) +329 train 7.370869 (lr=1.7500e-04) (hash(x)=19774173) +330 train 7.392698 (lr=1.7500e-04) (hash(x)=21681646) +331 train 7.266801 (lr=1.7500e-04) (hash(x)=20216795) +332 train 8.025762 (lr=1.7500e-04) (hash(x)=27697998) +333 train 7.759305 (lr=1.7500e-04) (hash(x)=25896435) +334 train 7.597009 (lr=1.7500e-04) (hash(x)=21585310) +335 train 7.651588 (lr=1.7500e-04) (hash(x)=24677740) +336 train 7.410300 (lr=1.7500e-04) (hash(x)=22027900) +337 train 7.498882 (lr=1.7500e-04) (hash(x)=21835643) +338 train 7.339835 (lr=1.7500e-04) (hash(x)=20558462) +339 train 7.212299 (lr=1.7500e-04) (hash(x)=16722715) +340 train 7.422504 (lr=1.7500e-04) (hash(x)=20972655) +341 train 7.957059 (lr=1.7500e-04) (hash(x)=26303975) +342 train 7.688234 (lr=1.7500e-04) (hash(x)=22938170) +343 train 7.784055 (lr=1.7500e-04) (hash(x)=25347203) +344 train 7.707160 (lr=1.7500e-04) (hash(x)=27398686) +345 train 7.702481 (lr=1.7500e-04) (hash(x)=25973417) +346 train 7.703769 (lr=1.7500e-04) (hash(x)=26918389) +347 train 7.614301 (lr=1.7500e-04) (hash(x)=24272489) +348 train 7.708725 (lr=1.7500e-04) (hash(x)=25593714) +349 train 7.766904 (lr=1.7500e-04) (hash(x)=29260846) +350 val loss 7.6519 +350 val perplexity 2104.5640 +350 train 7.831416 (lr=1.7500e-04) (hash(x)=27951602) +351 train 7.937148 (lr=1.7500e-04) (hash(x)=28922363) +352 train 7.802319 (lr=1.7500e-04) (hash(x)=27210734) +353 train 7.851314 (lr=1.7500e-04) (hash(x)=26322572) +354 train 7.723561 (lr=1.7500e-04) (hash(x)=27084665) +355 train 7.592803 (lr=1.7500e-04) (hash(x)=25510798) +356 train 7.723393 (lr=1.7500e-04) (hash(x)=24970921) +357 train 7.759249 (lr=1.7500e-04) (hash(x)=24138948) +358 train 7.647165 (lr=1.7500e-04) (hash(x)=24790211) +359 train 7.710422 (lr=1.7500e-04) (hash(x)=25631397) +360 train 7.559658 (lr=1.7500e-04) (hash(x)=23226625) +361 train 7.651483 (lr=1.7500e-04) (hash(x)=24001903) +362 train 7.565179 (lr=1.7500e-04) (hash(x)=24587948) +363 train 7.296557 (lr=1.7500e-04) (hash(x)=21333676) +364 train 7.104328 (lr=1.7500e-04) (hash(x)=23673779) +365 train 8.664104 (lr=1.7500e-04) (hash(x)=30770484) +366 train 7.754497 (lr=1.7500e-04) (hash(x)=26564899) +367 train 7.746643 (lr=1.7500e-04) (hash(x)=26237983) +368 train 7.427526 (lr=1.7500e-04) (hash(x)=23764356) +369 train 7.869657 (lr=1.7500e-04) (hash(x)=26205744) +370 train 7.475315 (lr=1.7500e-04) (hash(x)=19208770) +371 train 7.727670 (lr=1.7500e-04) (hash(x)=25976502) +372 train 7.581638 (lr=1.7500e-04) (hash(x)=23983933) +373 train 7.535388 (lr=1.7500e-04) (hash(x)=24080636) +374 train 7.664429 (lr=1.7500e-04) (hash(x)=24404047) +375 train 7.570652 (lr=1.7500e-04) (hash(x)=24742645) +376 train 7.629879 (lr=1.7500e-04) (hash(x)=24159600) +377 train 7.937825 (lr=1.7500e-04) (hash(x)=28677257) +378 train 7.592191 (lr=1.7500e-04) (hash(x)=25604111) +379 train 7.600008 (lr=1.7500e-04) (hash(x)=27086333) +380 train 7.494152 (lr=1.7500e-04) (hash(x)=25188207) +381 train 7.778464 (lr=1.7500e-04) (hash(x)=27855233) +382 train 7.379163 (lr=1.7500e-04) (hash(x)=19470039) +383 train 7.683569 (lr=1.7500e-04) (hash(x)=26157660) +384 train 7.563476 (lr=1.7500e-04) (hash(x)=25291570) +385 train 7.502792 (lr=1.7500e-04) (hash(x)=25046062) +386 train 7.869732 (lr=1.7500e-04) (hash(x)=27020337) +387 train 7.502826 (lr=1.7500e-04) (hash(x)=23616370) +388 train 7.155725 (lr=1.7500e-04) (hash(x)=19113218) +389 train 7.519283 (lr=1.7500e-04) (hash(x)=24302232) +390 train 7.542854 (lr=1.7500e-04) (hash(x)=22188949) +391 train 7.309073 (lr=1.7500e-04) (hash(x)=22582169) +392 train 7.540673 (lr=1.7500e-04) (hash(x)=24700570) +393 train 7.449344 (lr=1.7500e-04) (hash(x)=22773833) +394 train 7.291751 (lr=1.7500e-04) (hash(x)=21875928) +395 train 7.630817 (lr=1.7500e-04) (hash(x)=26233189) +396 train 7.466350 (lr=1.7500e-04) (hash(x)=24321467) +397 train 7.717978 (lr=1.7500e-04) (hash(x)=26431507) +398 train 7.809882 (lr=1.7500e-04) (hash(x)=28690877) +399 train 7.780175 (lr=1.7500e-04) (hash(x)=26431960) +400 val loss 7.6096 +400 val perplexity 2017.5028 +400 train 7.526238 (lr=1.7500e-04) (hash(x)=24580300) +401 train 7.536166 (lr=1.7500e-04) (hash(x)=25112360) +402 train 7.685495 (lr=1.7500e-04) (hash(x)=27597243) +403 train 8.183596 (lr=1.7500e-04) (hash(x)=30707498) +404 train 7.818031 (lr=1.7500e-04) (hash(x)=28485465) +405 train 7.423120 (lr=1.7500e-04) (hash(x)=22586447) +406 train 7.545776 (lr=1.7500e-04) (hash(x)=23175270) +407 train 7.624724 (lr=1.7500e-04) (hash(x)=25716176) +408 train 7.730843 (lr=1.7500e-04) (hash(x)=26861373) +409 train 7.820634 (lr=1.7500e-04) (hash(x)=25118971) +410 train 7.279767 (lr=1.7500e-04) (hash(x)=19829066) +411 train 7.512903 (lr=1.7500e-04) (hash(x)=26256420) +412 train 7.782024 (lr=1.7500e-04) (hash(x)=27796153) +413 train 7.520835 (lr=1.7500e-04) (hash(x)=22633318) +414 train 7.538892 (lr=1.7500e-04) (hash(x)=22589383) +415 train 7.939420 (lr=1.7500e-04) (hash(x)=28019788) +416 train 7.849170 (lr=1.7500e-04) (hash(x)=28970440) +417 train 7.561487 (lr=1.7500e-04) (hash(x)=27396089) +418 train 7.533662 (lr=1.7500e-04) (hash(x)=21183513) +419 train 7.556262 (lr=1.7500e-04) (hash(x)=23510110) +420 train 7.771890 (lr=1.7500e-04) (hash(x)=28833467) +421 train 7.671130 (lr=1.7500e-04) (hash(x)=23646926) +422 train 7.619278 (lr=1.7500e-04) (hash(x)=24697272) +423 train 7.354688 (lr=1.7500e-04) (hash(x)=20382963) +424 train 7.394840 (lr=1.7500e-04) (hash(x)=23467595) +425 train 7.568456 (lr=1.7500e-04) (hash(x)=24304768) +426 train 7.466043 (lr=1.7500e-04) (hash(x)=21392328) +427 train 7.496085 (lr=1.7500e-04) (hash(x)=25339466) +428 train 7.460753 (lr=1.7500e-04) (hash(x)=22092542) +429 train 7.559765 (lr=1.7500e-04) (hash(x)=22088696) +430 train 7.415007 (lr=1.7500e-04) (hash(x)=22184471) +431 train 7.506888 (lr=1.7500e-04) (hash(x)=24489647) +432 train 7.603917 (lr=1.7500e-04) (hash(x)=26794132) +433 train 7.376066 (lr=1.7500e-04) (hash(x)=22940357) +434 train 7.508032 (lr=1.7500e-04) (hash(x)=23719522) +435 train 7.424075 (lr=1.7500e-04) (hash(x)=22927699) +436 train 7.577641 (lr=1.7500e-04) (hash(x)=26068576) +437 train 7.718105 (lr=1.7500e-04) (hash(x)=27631132) +438 train 7.593140 (lr=1.7500e-04) (hash(x)=26739991) +439 train 7.689129 (lr=1.7500e-04) (hash(x)=25128502) +440 train 7.747481 (lr=1.7500e-04) (hash(x)=25657260) +441 train 7.441381 (lr=1.7500e-04) (hash(x)=23576982) +442 train 7.695076 (lr=1.7500e-04) (hash(x)=27117886) +443 train 7.653554 (lr=1.7500e-04) (hash(x)=25808969) +444 train 7.575954 (lr=1.7500e-04) (hash(x)=24738238) +445 train 7.584928 (lr=1.7500e-04) (hash(x)=23429962) +446 train 7.718694 (lr=1.7500e-04) (hash(x)=25075165) +447 train 7.585050 (lr=1.7500e-04) (hash(x)=25231390) +448 train 7.363148 (lr=1.7500e-04) (hash(x)=22055054) +449 train 7.567537 (lr=1.7500e-04) (hash(x)=25395441) +450 val loss 7.5752 +450 val perplexity 1949.1526 +450 train 7.639679 (lr=1.7500e-04) (hash(x)=25863209) +451 train 7.315136 (lr=1.7500e-04) (hash(x)=21154388) +452 train 7.293800 (lr=1.7500e-04) (hash(x)=21600876) +453 train 7.395726 (lr=1.7500e-04) (hash(x)=24278611) +454 train 7.219447 (lr=1.7500e-04) (hash(x)=23221720) +455 train 7.496548 (lr=1.7500e-04) (hash(x)=22708977) +456 train 8.115539 (lr=1.7500e-04) (hash(x)=23637758) +457 train 7.832208 (lr=1.7500e-04) (hash(x)=28228490) +458 train 7.902397 (lr=1.7500e-04) (hash(x)=28638071) +459 train 7.705774 (lr=1.7500e-04) (hash(x)=27258353) +460 train 7.730859 (lr=1.7500e-04) (hash(x)=26604728) +461 train 7.593203 (lr=1.7500e-04) (hash(x)=23252199) +462 train 7.647072 (lr=1.7500e-04) (hash(x)=26441427) +463 train 7.370794 (lr=1.7500e-04) (hash(x)=24364920) +464 train 7.585687 (lr=1.7500e-04) (hash(x)=25623792) +465 train 7.463439 (lr=1.7500e-04) (hash(x)=23283905) +466 train 7.914066 (lr=1.7500e-04) (hash(x)=26025267) +467 train 7.674257 (lr=1.7500e-04) (hash(x)=27243972) +468 train 8.080201 (lr=1.7500e-04) (hash(x)=30449945) +469 train 7.753093 (lr=1.7500e-04) (hash(x)=28113043) +470 train 7.533245 (lr=1.7500e-04) (hash(x)=25182521) +471 train 7.561672 (lr=1.7500e-04) (hash(x)=24932925) +472 train 7.362860 (lr=1.7500e-04) (hash(x)=20353098) +473 train 7.136924 (lr=1.7500e-04) (hash(x)=19001259) +474 train 7.826799 (lr=1.7500e-04) (hash(x)=27585685) +475 train 7.478296 (lr=1.7500e-04) (hash(x)=26371091) +476 train 7.382292 (lr=1.7500e-04) (hash(x)=24891798) +477 train 7.419273 (lr=1.7500e-04) (hash(x)=24258817) +478 train 7.516737 (lr=1.7500e-04) (hash(x)=24330263) +479 train 7.558259 (lr=1.7500e-04) (hash(x)=26913684) +480 train 7.588998 (lr=1.7500e-04) (hash(x)=26338455) +481 train 7.897449 (lr=1.7500e-04) (hash(x)=27753043) +482 train 7.576154 (lr=1.7500e-04) (hash(x)=26123289) +483 train 7.666658 (lr=1.7500e-04) (hash(x)=29239611) +484 train 7.533975 (lr=1.7500e-04) (hash(x)=26553003) +485 train 7.543214 (lr=1.7500e-04) (hash(x)=22984557) +486 train 7.077086 (lr=1.7500e-04) (hash(x)=16947491) +487 train 7.042747 (lr=1.7500e-04) (hash(x)=18017792) +488 train 7.226139 (lr=1.7500e-04) (hash(x)=19918608) +489 train 7.738334 (lr=1.7500e-04) (hash(x)=23374526) +490 train 7.575647 (lr=1.7500e-04) (hash(x)=25009505) +491 train 7.539747 (lr=1.7500e-04) (hash(x)=27574089) +492 train 7.688652 (lr=1.7500e-04) (hash(x)=24122664) +493 train 7.547842 (lr=1.7500e-04) (hash(x)=26154906) +494 train 7.540112 (lr=1.7500e-04) (hash(x)=25192767) +495 train 7.673608 (lr=1.7500e-04) (hash(x)=28613882) +496 train 7.492127 (lr=1.7500e-04) (hash(x)=23547219) +497 train 7.546072 (lr=1.7500e-04) (hash(x)=25272182) +498 train 7.395175 (lr=1.7500e-04) (hash(x)=24992761) +499 train 7.657895 (lr=1.7500e-04) (hash(x)=26981914) +500 val loss 7.5203 +500 val perplexity 1845.0554 +500 train 7.487930 (lr=1.7500e-04) (hash(x)=22051933) +501 train 7.603360 (lr=1.7500e-04) (hash(x)=24232348) +502 train 7.588006 (lr=1.7500e-04) (hash(x)=23158331) +503 train 7.420133 (lr=1.7500e-04) (hash(x)=22652243) +504 train 7.457157 (lr=1.7500e-04) (hash(x)=23805602) +505 train 7.757715 (lr=1.7500e-04) (hash(x)=25411991) +506 train 6.850754 (lr=1.7500e-04) (hash(x)=18827215) +507 train 6.544044 (lr=1.7500e-04) (hash(x)=15446025) +508 train 7.004520 (lr=1.7500e-04) (hash(x)=20516263) +509 train 7.590997 (lr=1.7500e-04) (hash(x)=27846176) +510 train 7.338348 (lr=1.7500e-04) (hash(x)=23342449) +511 train 7.594433 (lr=1.7500e-04) (hash(x)=27194521) +512 train 7.369399 (lr=1.7500e-04) (hash(x)=23008284) +513 train 7.910737 (lr=1.7500e-04) (hash(x)=29430001) +514 train 7.165875 (lr=1.7500e-04) (hash(x)=22579319) +515 train 7.185378 (lr=1.7500e-04) (hash(x)=25264518) +516 train 7.571426 (lr=1.7500e-04) (hash(x)=25359075) +517 train 7.529247 (lr=1.7500e-04) (hash(x)=25568956) +518 train 7.802692 (lr=1.7500e-04) (hash(x)=32004108) +519 train 7.459302 (lr=1.7500e-04) (hash(x)=24936836) +520 train 7.593617 (lr=1.7500e-04) (hash(x)=27263338) +521 train 7.649681 (lr=1.7500e-04) (hash(x)=27452099) +522 train 7.587093 (lr=1.7500e-04) (hash(x)=25965406) +523 train 7.748584 (lr=1.7500e-04) (hash(x)=28197282) +524 train 7.503150 (lr=1.7500e-04) (hash(x)=22466209) +525 train 7.551320 (lr=1.7500e-04) (hash(x)=22931889) +526 train 7.655018 (lr=1.7500e-04) (hash(x)=26903920) +527 train 7.492599 (lr=1.7500e-04) (hash(x)=24765578) +528 train 7.611858 (lr=1.7500e-04) (hash(x)=27811359) +529 train 7.391037 (lr=1.7500e-04) (hash(x)=25078649) +530 train 7.574047 (lr=1.7500e-04) (hash(x)=25572416) +531 train 7.758014 (lr=1.7500e-04) (hash(x)=27448185) +532 train 7.784315 (lr=1.7500e-04) (hash(x)=25923719) +533 train 7.573846 (lr=1.7500e-04) (hash(x)=24804856) +534 train 7.618515 (lr=1.7500e-04) (hash(x)=23207829) +535 train 7.509172 (lr=1.7500e-04) (hash(x)=23107416) +536 train 7.386140 (lr=1.7500e-04) (hash(x)=26739531) +537 train 7.379132 (lr=1.7500e-04) (hash(x)=24960796) +538 train 7.498010 (lr=1.7500e-04) (hash(x)=24667802) +539 train 7.613809 (lr=1.7500e-04) (hash(x)=26755138) +540 train 7.526568 (lr=1.7500e-04) (hash(x)=25537132) +541 train 7.430368 (lr=1.7500e-04) (hash(x)=24542526) +542 train 7.213128 (lr=1.7500e-04) (hash(x)=21296355) +543 train 7.795139 (lr=1.7500e-04) (hash(x)=29314255) +544 train 7.518909 (lr=1.7500e-04) (hash(x)=26001799) +545 train 7.562548 (lr=1.7500e-04) (hash(x)=27347755) +546 train 7.503572 (lr=1.7500e-04) (hash(x)=25107798) +547 train 7.303904 (lr=1.7500e-04) (hash(x)=22112669) +548 train 7.337986 (lr=1.7500e-04) (hash(x)=21897967) +549 train 7.470850 (lr=1.7500e-04) (hash(x)=25161929) +550 val loss 7.4678 +550 val perplexity 1750.7794 +550 train 7.372939 (lr=1.7500e-04) (hash(x)=27465106) +551 train 7.458660 (lr=1.7500e-04) (hash(x)=24013079) +552 train 7.336610 (lr=1.7500e-04) (hash(x)=23142015) +553 train 7.506664 (lr=1.7500e-04) (hash(x)=26768629) +554 train 7.527913 (lr=1.7500e-04) (hash(x)=26393383) +555 train 7.396179 (lr=1.7500e-04) (hash(x)=22537194) +556 train 7.625112 (lr=1.7500e-04) (hash(x)=24046036) +557 train 7.564077 (lr=1.7500e-04) (hash(x)=24974360) +558 train 7.803484 (lr=1.7500e-04) (hash(x)=28379928) +559 train 7.515786 (lr=1.7500e-04) (hash(x)=25322001) +560 train 7.643776 (lr=1.7500e-04) (hash(x)=26622031) +561 train 7.246243 (lr=1.7500e-04) (hash(x)=20562247) +562 train 7.648747 (lr=1.7500e-04) (hash(x)=27381885) +563 train 7.773759 (lr=1.7500e-04) (hash(x)=27028126) +564 train 7.594742 (lr=1.7500e-04) (hash(x)=28882928) +565 train 7.489864 (lr=1.7500e-04) (hash(x)=25666355) +566 train 7.648702 (lr=1.7500e-04) (hash(x)=24330810) +567 train 7.555126 (lr=1.7500e-04) (hash(x)=26690440) +568 train 7.453819 (lr=1.7500e-04) (hash(x)=22923592) +569 train 7.548141 (lr=1.7500e-04) (hash(x)=27348418) +570 train 7.593192 (lr=1.7500e-04) (hash(x)=28849848) +571 train 7.601803 (lr=1.7500e-04) (hash(x)=26967331) +572 train 7.390497 (lr=1.7500e-04) (hash(x)=22831467) +573 train 7.452960 (lr=1.7500e-04) (hash(x)=24765121) +574 train 7.446095 (lr=1.7500e-04) (hash(x)=24331857) +575 train 7.253447 (lr=1.7500e-04) (hash(x)=22598512) +576 train 7.400053 (lr=1.7500e-04) (hash(x)=25149353) +577 train 7.362390 (lr=1.7500e-04) (hash(x)=23725598) +578 train 7.605775 (lr=1.7500e-04) (hash(x)=26449557) +579 train 7.622603 (lr=1.7500e-04) (hash(x)=24697985) +580 train 7.607975 (lr=1.7500e-04) (hash(x)=26923059) +581 train 7.415559 (lr=1.7500e-04) (hash(x)=25201962) +582 train 7.060765 (lr=1.7500e-04) (hash(x)=20931520) +583 train 7.154312 (lr=1.7500e-04) (hash(x)=18473911) +584 train 7.280846 (lr=1.7500e-04) (hash(x)=21306267) +585 train 7.533910 (lr=1.7500e-04) (hash(x)=25982840) +586 train 7.446116 (lr=1.7500e-04) (hash(x)=25364874) +587 train 7.346456 (lr=1.7500e-04) (hash(x)=23172124) +588 train 7.667469 (lr=1.7500e-04) (hash(x)=27876897) +589 train 8.328910 (lr=1.7500e-04) (hash(x)=34646114) +590 train 8.678882 (lr=1.7500e-04) (hash(x)=35153576) +591 train 7.465322 (lr=1.7500e-04) (hash(x)=22322442) +592 train 7.695746 (lr=1.7500e-04) (hash(x)=27907331) +593 train 7.568390 (lr=1.7500e-04) (hash(x)=26211794) +594 train 7.787305 (lr=1.7500e-04) (hash(x)=29291512) +595 train 8.011477 (lr=1.7500e-04) (hash(x)=29659121) +596 train 7.832226 (lr=1.7500e-04) (hash(x)=29674399) +597 train 7.416451 (lr=1.7500e-04) (hash(x)=23538306) +598 train 7.627129 (lr=1.7500e-04) (hash(x)=21991524) +599 train 7.559648 (lr=1.7500e-04) (hash(x)=26324153) +600 val loss 7.4879 +600 val perplexity 1786.3519 +600 train 7.448486 (lr=1.7500e-04) (hash(x)=23712082) +601 train 7.544455 (lr=1.7500e-04) (hash(x)=24910403) +602 train 7.505996 (lr=1.7500e-04) (hash(x)=26737205) +603 train 7.605049 (lr=1.7500e-04) (hash(x)=26939970) +604 train 7.494028 (lr=1.7500e-04) (hash(x)=27651943) +605 train 7.812263 (lr=1.7500e-04) (hash(x)=27515446) +606 train 7.705673 (lr=1.7500e-04) (hash(x)=26753129) +607 train 7.386160 (lr=1.7500e-04) (hash(x)=23446058) +608 train 7.593910 (lr=1.7500e-04) (hash(x)=27587849) +609 train 7.574812 (lr=1.7500e-04) (hash(x)=25308253) +610 train 7.589453 (lr=1.7500e-04) (hash(x)=26615098) +611 train 7.651570 (lr=1.7500e-04) (hash(x)=29981801) +612 train 7.712164 (lr=1.7500e-04) (hash(x)=29592345) +613 train 7.778605 (lr=1.7500e-04) (hash(x)=23470413) +614 train 7.631278 (lr=1.7500e-04) (hash(x)=24742370) +615 train 7.558864 (lr=1.7500e-04) (hash(x)=24843741) +616 train 7.504998 (lr=1.7500e-04) (hash(x)=25192548) +617 train 7.541310 (lr=1.7500e-04) (hash(x)=27176996) +618 train 7.372661 (lr=1.7500e-04) (hash(x)=23964552) +619 train 7.400856 (lr=1.7500e-04) (hash(x)=22855363) +620 train 7.372038 (lr=1.7500e-04) (hash(x)=26332996) +621 train 7.230648 (lr=1.7500e-04) (hash(x)=22960957) +622 train 7.580568 (lr=1.7500e-04) (hash(x)=22752597) +623 train 7.457639 (lr=1.7500e-04) (hash(x)=23197102) +624 train 7.959637 (lr=1.7500e-04) (hash(x)=27383319) +625 train 7.544844 (lr=1.7500e-04) (hash(x)=26132276) +626 train 7.456809 (lr=1.7500e-04) (hash(x)=19810497) +627 train 7.495492 (lr=1.7500e-04) (hash(x)=25704919) +628 train 7.656635 (lr=1.7500e-04) (hash(x)=27174264) +629 train 7.755229 (lr=1.7500e-04) (hash(x)=22280814) +630 train 8.423602 (lr=1.7500e-04) (hash(x)=24279448) +631 train 7.937549 (lr=1.7500e-04) (hash(x)=23054940) +632 train 8.073924 (lr=1.7500e-04) (hash(x)=23942400) +633 train 8.293210 (lr=1.7500e-04) (hash(x)=24712416) +634 train 7.919747 (lr=1.7500e-04) (hash(x)=24564658) +635 train 7.632784 (lr=1.7500e-04) (hash(x)=24909904) +636 train 7.668402 (lr=1.7500e-04) (hash(x)=23049534) +637 train 7.721426 (lr=1.7500e-04) (hash(x)=24321591) +638 train 7.482796 (lr=1.7500e-04) (hash(x)=26153298) +639 train 7.499077 (lr=1.7500e-04) (hash(x)=27140757) +640 train 7.264390 (lr=1.7500e-04) (hash(x)=25115907) +641 train 7.307783 (lr=1.7500e-04) (hash(x)=26563770) +642 train 7.512940 (lr=1.7500e-04) (hash(x)=28089252) +643 train 7.472246 (lr=1.7500e-04) (hash(x)=25993110) +644 train 7.425407 (lr=1.7500e-04) (hash(x)=25150008) +645 train 7.710918 (lr=1.7500e-04) (hash(x)=28520222) +646 train 7.339935 (lr=1.7500e-04) (hash(x)=21349943) +647 train 7.401000 (lr=1.7500e-04) (hash(x)=25149419) +648 train 7.616390 (lr=1.7500e-04) (hash(x)=25730641) +649 train 7.781488 (lr=1.7500e-04) (hash(x)=26112813) +650 val loss 7.5247 +650 val perplexity 1853.1851 +650 train 7.553628 (lr=1.7500e-04) (hash(x)=25907805) +651 train 7.621886 (lr=1.7500e-04) (hash(x)=27623643) +652 train 7.567317 (lr=1.7500e-04) (hash(x)=26484959) +653 train 7.646099 (lr=1.7500e-04) (hash(x)=29199854) +654 train 7.597834 (lr=1.7500e-04) (hash(x)=28369628) +655 train 7.417857 (lr=1.7500e-04) (hash(x)=24727764) +656 train 7.241707 (lr=1.7500e-04) (hash(x)=22610673) +657 train 7.204498 (lr=1.7500e-04) (hash(x)=22667179) +658 train 7.024899 (lr=1.7500e-04) (hash(x)=18477300) +659 train 7.390633 (lr=1.7500e-04) (hash(x)=23155773) +660 train 7.142326 (lr=1.7500e-04) (hash(x)=19461032) +661 train 7.429654 (lr=1.7500e-04) (hash(x)=23453788) +662 train 7.569164 (lr=1.7500e-04) (hash(x)=24543466) +663 train 7.335663 (lr=1.7500e-04) (hash(x)=21935931) +664 train 7.172663 (lr=1.7500e-04) (hash(x)=19910292) +665 train 7.507432 (lr=1.7500e-04) (hash(x)=24481079) +666 train 7.164412 (lr=1.7500e-04) (hash(x)=18922411) +667 train 7.187006 (lr=1.7500e-04) (hash(x)=20054917) +668 train 7.425064 (lr=1.7500e-04) (hash(x)=24850470) +669 train 7.405344 (lr=1.7500e-04) (hash(x)=25907741) +670 train 7.564474 (lr=1.7500e-04) (hash(x)=26873522) +671 train 7.619421 (lr=1.7500e-04) (hash(x)=27606073) +672 train 7.733865 (lr=1.7500e-04) (hash(x)=26209645) +673 train 7.526495 (lr=1.7500e-04) (hash(x)=25202001) +674 train 7.591003 (lr=1.7500e-04) (hash(x)=25569462) +675 train 7.594392 (lr=1.7500e-04) (hash(x)=26534487) +676 train 7.545579 (lr=1.7500e-04) (hash(x)=26455057) +677 train 7.441799 (lr=1.7500e-04) (hash(x)=24095850) +678 train 7.648533 (lr=1.7500e-04) (hash(x)=25287752) +679 train 7.172832 (lr=1.7500e-04) (hash(x)=22450341) +680 train 7.877290 (lr=1.7500e-04) (hash(x)=29004853) +681 train 7.565515 (lr=1.7500e-04) (hash(x)=27993763) +682 train 7.393589 (lr=1.7500e-04) (hash(x)=26382658) +683 train 7.550196 (lr=1.7500e-04) (hash(x)=25013073) +684 train 7.573383 (lr=1.7500e-04) (hash(x)=30595809) +685 train 7.667375 (lr=1.7500e-04) (hash(x)=30934371) +686 train 8.211116 (lr=1.7500e-04) (hash(x)=33060834) +687 train 7.547794 (lr=1.7500e-04) (hash(x)=25945859) +688 train 7.438144 (lr=1.7500e-04) (hash(x)=23375678) +689 train 7.441709 (lr=1.7500e-04) (hash(x)=25218689) +690 train 7.548290 (lr=1.7500e-04) (hash(x)=28127397) +691 train 7.452634 (lr=1.7500e-04) (hash(x)=24418091) +692 train 7.385952 (lr=1.7500e-04) (hash(x)=22761099) +693 train 7.382404 (lr=1.7500e-04) (hash(x)=24615466) +694 train 7.550597 (lr=1.7500e-04) (hash(x)=24699240) +695 train 7.409824 (lr=1.7500e-04) (hash(x)=21613707) +696 train 7.462393 (lr=1.7500e-04) (hash(x)=24977554) +697 train 7.405859 (lr=1.7500e-04) (hash(x)=24348175) +698 train 7.576234 (lr=1.7500e-04) (hash(x)=25102767) +699 train 7.538904 (lr=1.7500e-04) (hash(x)=26386157) +700 val loss 7.4419 +700 val perplexity 1705.9775 +700 train 7.464005 (lr=1.7500e-04) (hash(x)=26423460) +701 train 7.423553 (lr=1.7500e-04) (hash(x)=25771047) +702 train 7.491243 (lr=1.7500e-04) (hash(x)=26999875) +703 train 7.384878 (lr=1.7500e-04) (hash(x)=24396519) +704 train 7.387468 (lr=1.7500e-04) (hash(x)=22588122) +705 train 7.741374 (lr=1.7500e-04) (hash(x)=25142399) +706 train 7.494976 (lr=1.7500e-04) (hash(x)=20440214) +707 train 7.322048 (lr=1.7500e-04) (hash(x)=23265507) +708 train 7.413648 (lr=1.7500e-04) (hash(x)=24563470) +709 train 7.298805 (lr=1.7500e-04) (hash(x)=22514858) +710 train 7.633441 (lr=1.7500e-04) (hash(x)=26691212) +711 train 7.706652 (lr=1.7500e-04) (hash(x)=29138828) +712 train 7.696019 (lr=1.7500e-04) (hash(x)=28028528) +713 train 7.566310 (lr=1.7500e-04) (hash(x)=20531210) +714 train 7.444734 (lr=1.7500e-04) (hash(x)=25075352) +715 train 7.499320 (lr=1.7500e-04) (hash(x)=24265353) +716 train 7.587338 (lr=1.7500e-04) (hash(x)=24635726) +717 train 7.441294 (lr=1.7500e-04) (hash(x)=24999726) +718 train 7.631425 (lr=1.7500e-04) (hash(x)=27412910) +719 train 7.385408 (lr=1.7500e-04) (hash(x)=24685515) +720 train 7.446691 (lr=1.7500e-04) (hash(x)=23780329) +721 train 7.253711 (lr=1.7500e-04) (hash(x)=25071701) +722 train 7.388603 (lr=1.7500e-04) (hash(x)=23767130) +723 train 7.364548 (lr=1.7500e-04) (hash(x)=24876269) +724 train 7.507215 (lr=1.7500e-04) (hash(x)=26405773) +725 train 7.957503 (lr=1.7500e-04) (hash(x)=31733180) +726 train 7.106536 (lr=1.7500e-04) (hash(x)=21337509) +727 train 7.268662 (lr=1.7500e-04) (hash(x)=22825749) +728 train 7.622133 (lr=1.7500e-04) (hash(x)=28638695) +729 train 7.484409 (lr=1.7500e-04) (hash(x)=26393943) +730 train 7.653288 (lr=1.7500e-04) (hash(x)=27563583) +731 train 7.146951 (lr=1.7500e-04) (hash(x)=21239652) +732 train 7.244195 (lr=1.7500e-04) (hash(x)=23986428) +733 train 7.268165 (lr=1.7500e-04) (hash(x)=24943881) +734 train 7.766065 (lr=1.7500e-04) (hash(x)=29691448) +735 train 7.722219 (lr=1.7500e-04) (hash(x)=28767869) +736 train 7.375475 (lr=1.7500e-04) (hash(x)=23628188) +737 train 7.659474 (lr=1.7500e-04) (hash(x)=29341482) +738 train 7.514019 (lr=1.7500e-04) (hash(x)=30336570) +739 train 7.501521 (lr=1.7500e-04) (hash(x)=25614301) +740 train 7.348698 (lr=1.7500e-04) (hash(x)=24160500) +741 train 7.597883 (lr=1.7500e-04) (hash(x)=26030058) +742 train 7.966130 (lr=1.7500e-04) (hash(x)=29243936) +743 train 7.222634 (lr=1.7500e-04) (hash(x)=21159060) +744 train 7.318788 (lr=1.7500e-04) (hash(x)=23701853) +745 train 7.533273 (lr=1.7500e-04) (hash(x)=24629937) +746 train 7.441344 (lr=1.7500e-04) (hash(x)=25110108) +747 train 7.464409 (lr=1.7500e-04) (hash(x)=26751788) +748 train 7.499359 (lr=1.7500e-04) (hash(x)=26430427) +749 train 7.339029 (lr=1.7500e-04) (hash(x)=26012353) +750 val loss 7.3923 +750 val perplexity 1623.5165 +750 train 7.502220 (lr=1.7500e-04) (hash(x)=22735910) +751 train 7.308794 (lr=1.7500e-04) (hash(x)=25045397) +752 train 7.036663 (lr=1.7500e-04) (hash(x)=21554427) +753 train 7.148553 (lr=1.7500e-04) (hash(x)=23751143) +754 train 7.921376 (lr=1.7500e-04) (hash(x)=28602273) +755 train 7.957419 (lr=1.7500e-04) (hash(x)=29989709) +756 train 7.329488 (lr=1.7500e-04) (hash(x)=22331648) +757 train 7.766525 (lr=1.7500e-04) (hash(x)=31017246) +758 train 7.732034 (lr=1.7500e-04) (hash(x)=29709045) +759 train 7.803342 (lr=1.7500e-04) (hash(x)=25560928) +760 train 7.424945 (lr=1.7500e-04) (hash(x)=25075464) +761 train 7.482210 (lr=1.7500e-04) (hash(x)=27352253) +762 train 7.697673 (lr=1.7500e-04) (hash(x)=28187891) +763 train 7.559318 (lr=1.7500e-04) (hash(x)=26062687) +764 train 7.578176 (lr=1.7500e-04) (hash(x)=27427811) +765 train 7.633412 (lr=1.7500e-04) (hash(x)=27614522) +766 train 7.415768 (lr=1.7500e-04) (hash(x)=26129544) +767 train 8.003952 (lr=1.7500e-04) (hash(x)=28959222) +768 train 7.534773 (lr=1.7500e-04) (hash(x)=26860067) +769 train 7.330017 (lr=1.7500e-04) (hash(x)=25122598) +770 train 7.418294 (lr=1.7500e-04) (hash(x)=25245030) +771 train 7.394557 (lr=1.7500e-04) (hash(x)=25434884) +772 train 7.445492 (lr=1.7500e-04) (hash(x)=27732790) +773 train 7.502294 (lr=1.7500e-04) (hash(x)=27824438) +774 train 7.605505 (lr=1.7500e-04) (hash(x)=27201953) +775 train 7.359607 (lr=1.7500e-04) (hash(x)=21248405) +776 train 7.103120 (lr=1.7500e-04) (hash(x)=22805934) +777 train 7.497449 (lr=1.7500e-04) (hash(x)=26482588) +778 train 7.518985 (lr=1.7500e-04) (hash(x)=24153691) +779 train 7.646226 (lr=1.7500e-04) (hash(x)=25044192) +780 train 7.566466 (lr=1.7500e-04) (hash(x)=25910078) +781 train 7.512277 (lr=1.7500e-04) (hash(x)=28645524) +782 train 7.331572 (lr=1.7500e-04) (hash(x)=24368498) +783 train 7.464005 (lr=1.7500e-04) (hash(x)=25830182) +784 train 7.567131 (lr=1.7500e-04) (hash(x)=29181807) +785 train 7.496101 (lr=1.7500e-04) (hash(x)=25585137) +786 train 7.406190 (lr=1.7500e-04) (hash(x)=24798246) +787 train 7.494410 (lr=1.7500e-04) (hash(x)=26621419) +788 train 7.037766 (lr=1.7500e-04) (hash(x)=21446891) +789 train 6.988637 (lr=1.7500e-04) (hash(x)=22165286) +790 train 7.238098 (lr=1.7500e-04) (hash(x)=23477219) +791 train 7.546516 (lr=1.7500e-04) (hash(x)=25173113) +792 train 7.407903 (lr=1.7500e-04) (hash(x)=25853788) +793 train 7.532791 (lr=1.7500e-04) (hash(x)=27267091) +794 train 7.303107 (lr=1.7500e-04) (hash(x)=23743694) +795 train 7.290245 (lr=1.7500e-04) (hash(x)=24400133) +796 train 7.435510 (lr=1.7500e-04) (hash(x)=23663639) +797 train 7.331163 (lr=1.7500e-04) (hash(x)=23103223) +798 train 7.802136 (lr=1.7500e-04) (hash(x)=28748411) +799 train 7.039166 (lr=1.7500e-04) (hash(x)=23486277) +800 val loss 7.4092 +800 val perplexity 1651.0863 +800 train 7.414771 (lr=1.7500e-04) (hash(x)=25678518) +801 train 7.342174 (lr=1.7500e-04) (hash(x)=23421286) +802 train 7.486741 (lr=1.7500e-04) (hash(x)=26054104) +803 train 7.472580 (lr=1.7500e-04) (hash(x)=25978130) +804 train 7.497421 (lr=1.7500e-04) (hash(x)=26006525) +805 train 7.461339 (lr=1.7500e-04) (hash(x)=25769432) +806 train 7.293289 (lr=1.7500e-04) (hash(x)=22430795) +807 train 7.664487 (lr=1.7500e-04) (hash(x)=28916006) +808 train 7.407275 (lr=1.7500e-04) (hash(x)=25166800) +809 train 7.547523 (lr=1.7500e-04) (hash(x)=24226056) +810 train 7.358396 (lr=1.7500e-04) (hash(x)=25057934) +811 train 8.244418 (lr=1.7500e-04) (hash(x)=33195100) +812 train 7.543333 (lr=1.7500e-04) (hash(x)=26312888) +813 train 7.764880 (lr=1.7500e-04) (hash(x)=27730410) +814 train 7.584635 (lr=1.7500e-04) (hash(x)=27372474) +815 train 7.409558 (lr=1.7500e-04) (hash(x)=25556929) +816 train 7.528139 (lr=1.7500e-04) (hash(x)=26909985) +817 train 7.324037 (lr=1.7500e-04) (hash(x)=25991247) +818 train 7.493713 (lr=1.7500e-04) (hash(x)=27438141) +819 train 7.613869 (lr=1.7500e-04) (hash(x)=29536986) +820 train 7.374996 (lr=1.7500e-04) (hash(x)=24478391) +821 train 7.391595 (lr=1.7500e-04) (hash(x)=26125216) +822 train 7.457988 (lr=1.7500e-04) (hash(x)=26422130) +823 train 7.664558 (lr=1.7500e-04) (hash(x)=29648798) +824 train 7.290378 (lr=1.7500e-04) (hash(x)=21247770) +825 train 7.459188 (lr=1.7500e-04) (hash(x)=23195388) +826 train 7.396245 (lr=1.7500e-04) (hash(x)=25796725) +827 train 7.415533 (lr=1.7500e-04) (hash(x)=23124767) +828 train 7.447438 (lr=1.7500e-04) (hash(x)=25233464) +829 train 7.425386 (lr=1.7500e-04) (hash(x)=25713275) +830 train 7.399054 (lr=1.7500e-04) (hash(x)=25550167) +831 train 7.283234 (lr=1.7500e-04) (hash(x)=24976217) +832 train 7.606431 (lr=1.7500e-04) (hash(x)=28536827) +833 train 7.489233 (lr=1.7500e-04) (hash(x)=27500801) +834 train 7.307111 (lr=1.7500e-04) (hash(x)=25545765) +835 train 7.311550 (lr=1.7500e-04) (hash(x)=23632825) +836 train 7.337198 (lr=1.7500e-04) (hash(x)=25708009) +837 train 7.385168 (lr=1.7500e-04) (hash(x)=24456276) +838 train 7.548010 (lr=1.7500e-04) (hash(x)=29189855) +839 train 7.767520 (lr=1.7500e-04) (hash(x)=31019606) +840 train 7.704900 (lr=1.7500e-04) (hash(x)=26328013) +841 train 7.574966 (lr=1.7500e-04) (hash(x)=25027904) +842 train 7.375733 (lr=1.7500e-04) (hash(x)=23734189) +843 train 7.610321 (lr=1.7500e-04) (hash(x)=28236580) +844 train 7.494836 (lr=1.7500e-04) (hash(x)=26509780) +845 train 7.556143 (lr=1.7500e-04) (hash(x)=25386473) +846 train 7.456436 (lr=1.7500e-04) (hash(x)=24052671) +847 train 7.645670 (lr=1.7500e-04) (hash(x)=28269421) +848 train 7.041150 (lr=1.7500e-04) (hash(x)=22251724) +849 train 7.256082 (lr=1.7500e-04) (hash(x)=24308447) +850 val loss 7.3952 +850 val perplexity 1628.1820 +850 train 7.242393 (lr=1.7500e-04) (hash(x)=24242830) +851 train 7.479885 (lr=1.7500e-04) (hash(x)=25563279) +852 train 7.504116 (lr=1.7500e-04) (hash(x)=26354481) +853 train 7.667969 (lr=1.7500e-04) (hash(x)=26152637) +854 train 7.651901 (lr=1.7500e-04) (hash(x)=28051025) +855 train 7.468441 (lr=1.7500e-04) (hash(x)=24865358) +856 train 7.362855 (lr=1.7500e-04) (hash(x)=24288911) +857 train 7.254312 (lr=1.7500e-04) (hash(x)=22230964) +858 train 7.155771 (lr=1.7500e-04) (hash(x)=21303832) +859 train 7.305019 (lr=1.7500e-04) (hash(x)=22155546) +860 train 7.414144 (lr=1.7500e-04) (hash(x)=25296428) +861 train 7.603715 (lr=1.7500e-04) (hash(x)=29142319) +862 train 7.392538 (lr=1.7500e-04) (hash(x)=25545430) +863 train 7.197968 (lr=1.7500e-04) (hash(x)=26984272) +864 train 7.416005 (lr=1.7500e-04) (hash(x)=25429005) +865 train 7.444261 (lr=1.7500e-04) (hash(x)=27077032) +866 train 7.477153 (lr=1.7500e-04) (hash(x)=26494424) +867 train 7.493306 (lr=1.7500e-04) (hash(x)=23193673) +868 train 7.487604 (lr=1.7500e-04) (hash(x)=25075134) +869 train 7.509958 (lr=1.7500e-04) (hash(x)=27112558) +870 train 7.660222 (lr=1.7500e-04) (hash(x)=27436608) +871 train 7.362347 (lr=1.7500e-04) (hash(x)=24544116) +872 train 7.732268 (lr=1.7500e-04) (hash(x)=31632686) +873 train 7.400307 (lr=1.7500e-04) (hash(x)=25890184) +874 train 7.532193 (lr=1.7500e-04) (hash(x)=22887555) +875 train 7.304517 (lr=1.7500e-04) (hash(x)=24547533) +876 train 7.501595 (lr=1.7500e-04) (hash(x)=26553496) +877 train 7.576198 (lr=1.7500e-04) (hash(x)=27467688) +878 train 7.323195 (lr=1.7500e-04) (hash(x)=24766934) +879 train 7.236108 (lr=1.7500e-04) (hash(x)=22059850) +880 train 7.635681 (lr=1.7500e-04) (hash(x)=22871702) +881 train 7.424844 (lr=1.7500e-04) (hash(x)=23893130) +882 train 7.481293 (lr=1.7500e-04) (hash(x)=25125691) +883 train 7.404839 (lr=1.7500e-04) (hash(x)=25994573) +884 train 7.465562 (lr=1.7500e-04) (hash(x)=26076345) +885 train 7.371289 (lr=1.7500e-04) (hash(x)=26577783) +886 train 7.530980 (lr=1.7500e-04) (hash(x)=27395225) +887 train 7.371368 (lr=1.7500e-04) (hash(x)=23926632) +888 train 7.194808 (lr=1.7500e-04) (hash(x)=21737239) +889 train 7.500844 (lr=1.7500e-04) (hash(x)=23574207) +890 train 7.204950 (lr=1.7500e-04) (hash(x)=24365231) +891 train 7.371107 (lr=1.7500e-04) (hash(x)=27111369) +892 train 7.649293 (lr=1.7500e-04) (hash(x)=27290015) +893 train 7.403500 (lr=1.7500e-04) (hash(x)=23979820) +894 train 7.521175 (lr=1.7500e-04) (hash(x)=26450121) +895 train 7.406612 (lr=1.7500e-04) (hash(x)=27025333) +896 train 7.410785 (lr=1.7500e-04) (hash(x)=23624605) +897 train 7.183890 (lr=1.7500e-04) (hash(x)=22846386) +898 train 7.287849 (lr=1.7500e-04) (hash(x)=22970561) +899 train 7.140538 (lr=1.7500e-04) (hash(x)=16908068) +900 val loss 7.3864 +900 val perplexity 1613.8121 +900 train 7.350637 (lr=1.7500e-04) (hash(x)=24661446) +901 train 7.502079 (lr=1.7500e-04) (hash(x)=25664727) +902 train 7.455620 (lr=1.7500e-04) (hash(x)=25667011) +903 train 7.532434 (lr=1.7500e-04) (hash(x)=29120407) +904 train 7.559106 (lr=1.7500e-04) (hash(x)=23385735) +905 train 7.599941 (lr=1.7500e-04) (hash(x)=25564213) +906 train 7.669744 (lr=1.7500e-04) (hash(x)=25413898) +907 train 7.614892 (lr=1.7500e-04) (hash(x)=27092710) +908 train 7.374545 (lr=1.7500e-04) (hash(x)=25789923) +909 train 7.481065 (lr=1.7500e-04) (hash(x)=28533197) +910 train 7.274076 (lr=1.7500e-04) (hash(x)=22982996) +911 train 7.369358 (lr=1.7500e-04) (hash(x)=23827393) +912 train 7.021712 (lr=1.7500e-04) (hash(x)=21242640) +913 train 7.442632 (lr=1.7500e-04) (hash(x)=24154233) +914 train 7.416318 (lr=1.7500e-04) (hash(x)=24331967) +915 train 7.747570 (lr=1.7500e-04) (hash(x)=32812727) +916 train 7.310997 (lr=1.7500e-04) (hash(x)=23572994) +917 train 7.300490 (lr=1.7500e-04) (hash(x)=26305435) +918 train 7.407455 (lr=1.7500e-04) (hash(x)=26268355) +919 train 7.572693 (lr=1.7500e-04) (hash(x)=27230027) +920 train 7.362432 (lr=1.7500e-04) (hash(x)=23885377) +921 train 7.288701 (lr=1.7500e-04) (hash(x)=23532437) +922 train 7.373631 (lr=1.7500e-04) (hash(x)=25577034) +923 train 7.503413 (lr=1.7500e-04) (hash(x)=25703381) +924 train 7.512585 (lr=1.7500e-04) (hash(x)=27113866) +925 train 7.305991 (lr=1.7500e-04) (hash(x)=26961429) +926 train 7.132499 (lr=1.7500e-04) (hash(x)=21355372) +927 train 7.209527 (lr=1.7500e-04) (hash(x)=24968260) +928 train 7.234359 (lr=1.7500e-04) (hash(x)=25357517) +929 train 7.343935 (lr=1.7500e-04) (hash(x)=24854265) +930 train 7.188950 (lr=1.7500e-04) (hash(x)=21102770) +931 train 7.462997 (lr=1.7500e-04) (hash(x)=25676468) +932 train 7.283340 (lr=1.7500e-04) (hash(x)=22809869) +933 train 7.375047 (lr=1.7500e-04) (hash(x)=25503865) +934 train 7.248812 (lr=1.7500e-04) (hash(x)=24853995) +935 train 7.510807 (lr=1.7500e-04) (hash(x)=27544803) +936 train 7.537375 (lr=1.7500e-04) (hash(x)=25981933) +937 train 7.301664 (lr=1.7500e-04) (hash(x)=24658683) +938 train 7.458095 (lr=1.7500e-04) (hash(x)=23855201) +939 train 7.369068 (lr=1.7500e-04) (hash(x)=24331407) +940 train 7.576315 (lr=1.7500e-04) (hash(x)=29265551) +941 train 7.306507 (lr=1.7500e-04) (hash(x)=21892556) +942 train 7.329126 (lr=1.7500e-04) (hash(x)=27183405) +943 train 7.288505 (lr=1.7500e-04) (hash(x)=26540663) +944 train 7.208400 (lr=1.7500e-04) (hash(x)=25718393) +945 train 7.420593 (lr=1.7500e-04) (hash(x)=26819462) +946 train 7.395538 (lr=1.7500e-04) (hash(x)=27427540) +947 train 7.356272 (lr=1.7500e-04) (hash(x)=25532657) +948 train 7.610534 (lr=1.7500e-04) (hash(x)=27641372) +949 train 7.292428 (lr=1.7500e-04) (hash(x)=26515570) +950 val loss 7.3560 +950 val perplexity 1565.5281 +950 train 7.546826 (lr=1.7500e-04) (hash(x)=26911957) +951 train 7.713254 (lr=1.7500e-04) (hash(x)=25856625) +952 train 7.253039 (lr=1.7500e-04) (hash(x)=25219129) +953 train 7.172776 (lr=1.7500e-04) (hash(x)=25260471) +954 train 7.618770 (lr=1.7500e-04) (hash(x)=29373370) +955 train 7.133287 (lr=1.7500e-04) (hash(x)=23437426) +956 train 7.504541 (lr=1.7500e-04) (hash(x)=23769521) +957 train 7.536029 (lr=1.7500e-04) (hash(x)=25961833) +958 train 7.193843 (lr=1.7500e-04) (hash(x)=23582666) +959 train 7.316535 (lr=1.7500e-04) (hash(x)=23164356) +960 train 7.271329 (lr=1.7500e-04) (hash(x)=24443114) +961 train 7.357213 (lr=1.7500e-04) (hash(x)=25052665) +962 train 7.514091 (lr=1.7500e-04) (hash(x)=27802272) +963 train 7.315563 (lr=1.7500e-04) (hash(x)=25957896) +964 train 7.361308 (lr=1.7500e-04) (hash(x)=26737251) +965 train 7.489246 (lr=1.7500e-04) (hash(x)=24723263) +966 train 7.426053 (lr=1.7500e-04) (hash(x)=24707011) +967 train 7.391458 (lr=1.7500e-04) (hash(x)=25646282) +968 train 7.413394 (lr=1.7500e-04) (hash(x)=27544665) +969 train 7.357665 (lr=1.7500e-04) (hash(x)=25851993) +970 train 7.648601 (lr=1.7500e-04) (hash(x)=29059700) +971 train 7.368187 (lr=1.7500e-04) (hash(x)=21513584) +972 train 7.065210 (lr=1.7500e-04) (hash(x)=23151267) +973 train 7.411225 (lr=1.7500e-04) (hash(x)=26017176) +974 train 7.429189 (lr=1.7500e-04) (hash(x)=26979518) +975 train 7.431782 (lr=1.7500e-04) (hash(x)=23843233) +976 train 7.633324 (lr=1.7500e-04) (hash(x)=24193010) +977 train 7.347241 (lr=1.7500e-04) (hash(x)=21476847) +978 train 7.209559 (lr=1.7500e-04) (hash(x)=21366504) +979 train 7.226724 (lr=1.7500e-04) (hash(x)=23226697) +980 train 6.993163 (lr=1.7500e-04) (hash(x)=19961773) +981 train 6.899022 (lr=1.7500e-04) (hash(x)=19772969) +982 train 7.244602 (lr=1.7500e-04) (hash(x)=23110142) +983 train 7.523007 (lr=1.7500e-04) (hash(x)=24506028) +984 train 7.581339 (lr=1.7500e-04) (hash(x)=25480731) +985 train 7.362323 (lr=1.7500e-04) (hash(x)=21077417) +986 train 7.386018 (lr=1.7500e-04) (hash(x)=23686713) +987 train 7.433716 (lr=1.7500e-04) (hash(x)=26024321) +988 train 7.539458 (lr=1.7500e-04) (hash(x)=27424109) +989 train 7.643678 (lr=1.7500e-04) (hash(x)=27786174) +990 train 7.402584 (lr=1.7500e-04) (hash(x)=25232502) +991 train 7.375505 (lr=1.7500e-04) (hash(x)=22781277) +992 train 7.482637 (lr=1.7500e-04) (hash(x)=26184527) +993 train 7.428085 (lr=1.7500e-04) (hash(x)=24459895) +994 train 7.431478 (lr=1.7500e-04) (hash(x)=25244624) +995 train 7.539929 (lr=1.7500e-04) (hash(x)=24451843) +996 train 7.558896 (lr=1.7500e-04) (hash(x)=22129897) +997 train 7.368594 (lr=1.7500e-04) (hash(x)=21116390) +998 train 7.165475 (lr=1.7500e-04) (hash(x)=20650070) +999 train 7.498334 (lr=1.7500e-04) (hash(x)=24948650) +1000 val loss 7.3946 +1000 val perplexity 1627.1288 +1000 train 7.381589 (lr=1.7500e-04) (hash(x)=25444553) +1001 train 7.363495 (lr=1.7500e-04) (hash(x)=25617781) +1002 train 7.237468 (lr=1.7500e-04) (hash(x)=23862434) +1003 train 7.311025 (lr=1.7500e-04) (hash(x)=25559534) +1004 train 7.540910 (lr=1.7500e-04) (hash(x)=26577585) +1005 train 7.393758 (lr=1.7500e-04) (hash(x)=25546274) +1006 train 7.476916 (lr=1.7500e-04) (hash(x)=26284202) +1007 train 7.516160 (lr=1.7500e-04) (hash(x)=26373991) +1008 train 7.414352 (lr=1.7500e-04) (hash(x)=24612851) +1009 train 7.514825 (lr=1.7500e-04) (hash(x)=26410662) +1010 train 7.568994 (lr=1.7500e-04) (hash(x)=23824841) +1011 train 7.875675 (lr=1.7500e-04) (hash(x)=27756673) +1012 train 7.601673 (lr=1.7500e-04) (hash(x)=25427447) +1013 train 7.583519 (lr=1.7500e-04) (hash(x)=23661686) +1014 train 7.492078 (lr=1.7500e-04) (hash(x)=25129504) +1015 train 7.413153 (lr=1.7500e-04) (hash(x)=23402396) +1016 train 7.682727 (lr=1.7500e-04) (hash(x)=26145557) +1017 train 7.404950 (lr=1.7500e-04) (hash(x)=26547918) +1018 train 7.520596 (lr=1.7500e-04) (hash(x)=26653070) +1019 train 7.514915 (lr=1.7500e-04) (hash(x)=28250354) +1020 train 7.488919 (lr=1.7500e-04) (hash(x)=25437401) +1021 train 7.528549 (lr=1.7500e-04) (hash(x)=25598861) +1022 train 7.320018 (lr=1.7500e-04) (hash(x)=24572587) +1023 train 7.434164 (lr=1.7500e-04) (hash(x)=21562133) +1024 train 7.806380 (lr=1.7500e-04) (hash(x)=27718876) +1025 train 7.409221 (lr=1.7500e-04) (hash(x)=25312391) +1026 train 7.477193 (lr=1.7500e-04) (hash(x)=26579535) +1027 train 7.718181 (lr=1.7500e-04) (hash(x)=27253861) +1028 train 7.572798 (lr=1.7500e-04) (hash(x)=28451867) +1029 train 7.314832 (lr=1.7500e-04) (hash(x)=26795921) +1030 train 7.432426 (lr=1.7500e-04) (hash(x)=26147208) +1031 train 7.484540 (lr=1.7500e-04) (hash(x)=25009210) +1032 train 7.388565 (lr=1.7500e-04) (hash(x)=25213771) +1033 train 7.286027 (lr=1.7500e-04) (hash(x)=26254538) +1034 train 7.342825 (lr=1.7500e-04) (hash(x)=25565614) +1035 train 7.216310 (lr=1.7500e-04) (hash(x)=23052577) +1036 train 8.021876 (lr=1.7500e-04) (hash(x)=29630613) +1037 train 7.244499 (lr=1.7500e-04) (hash(x)=23667224) +1038 train 7.324318 (lr=1.7500e-04) (hash(x)=25740670) +1039 train 7.447698 (lr=1.7500e-04) (hash(x)=27161811) +1040 train 7.602923 (lr=1.7500e-04) (hash(x)=26385663) +1041 train 7.304294 (lr=1.7500e-04) (hash(x)=26313522) +1042 train 7.442934 (lr=1.7500e-04) (hash(x)=26814686) +1043 train 7.541039 (lr=1.7500e-04) (hash(x)=27302459) +1044 train 7.834231 (lr=1.7500e-04) (hash(x)=26758132) +1045 train 7.439397 (lr=1.7500e-04) (hash(x)=26837963) +1046 train 7.191489 (lr=1.7500e-04) (hash(x)=22089547) +1047 train 7.756479 (lr=1.7500e-04) (hash(x)=29515100) +1048 train 7.390477 (lr=1.7500e-04) (hash(x)=25471442) +1049 train 7.378006 (lr=1.7500e-04) (hash(x)=26674478) +1050 val loss 7.3731 +1050 val perplexity 1592.5665 +1050 train 7.344266 (lr=1.7500e-04) (hash(x)=25373386) +1051 train 7.381242 (lr=1.7500e-04) (hash(x)=25318001) +1052 train 7.548140 (lr=1.7500e-04) (hash(x)=27255021) +1053 train 7.508863 (lr=1.7500e-04) (hash(x)=25174043) +1054 train 7.254479 (lr=1.7500e-04) (hash(x)=23857597) +1055 train 7.468526 (lr=1.7500e-04) (hash(x)=25305929) +1056 train 7.511483 (lr=1.7500e-04) (hash(x)=27009246) +1057 train 7.548280 (lr=1.7500e-04) (hash(x)=26175477) +1058 train 7.243923 (lr=1.7500e-04) (hash(x)=22700025) +1059 train 7.370670 (lr=1.7500e-04) (hash(x)=24339043) +1060 train 7.226433 (lr=1.7500e-04) (hash(x)=22139900) +1061 train 7.997289 (lr=1.7500e-04) (hash(x)=25412772) +1062 train 7.451338 (lr=1.7500e-04) (hash(x)=27020849) +1063 train 7.318374 (lr=1.7500e-04) (hash(x)=26808543) +1064 train 7.107770 (lr=1.7500e-04) (hash(x)=23061527) +1065 train 7.342075 (lr=1.7500e-04) (hash(x)=24738650) +1066 train 7.166858 (lr=1.7500e-04) (hash(x)=24036715) +1067 train 7.253294 (lr=1.7500e-04) (hash(x)=25763991) +1068 train 7.527648 (lr=1.7500e-04) (hash(x)=27393753) +1069 train 7.627165 (lr=1.7500e-04) (hash(x)=28182190) +1070 train 7.298447 (lr=1.7500e-04) (hash(x)=23358569) +1071 train 7.495471 (lr=1.7500e-04) (hash(x)=25669509) +1072 train 7.555133 (lr=1.7500e-04) (hash(x)=29139024) +1073 train 7.495718 (lr=1.7500e-04) (hash(x)=25616522) +1074 train 7.355653 (lr=1.7500e-04) (hash(x)=25695789) +1075 train 7.541727 (lr=1.7500e-04) (hash(x)=27676869) +1076 train 7.430767 (lr=1.7500e-04) (hash(x)=25952695) +1077 train 7.413908 (lr=1.7500e-04) (hash(x)=26316170) +1078 train 7.330745 (lr=1.7500e-04) (hash(x)=24081867) +1079 train 7.515007 (lr=1.7500e-04) (hash(x)=28435805) +1080 train 7.382787 (lr=1.7500e-04) (hash(x)=23375063) +1081 train 7.380888 (lr=1.7500e-04) (hash(x)=26869022) +1082 train 7.260608 (lr=1.7500e-04) (hash(x)=25793007) +1083 train 7.212935 (lr=1.7500e-04) (hash(x)=23455211) +1084 train 7.307617 (lr=1.7500e-04) (hash(x)=20441501) +1085 train 7.686022 (lr=1.7500e-04) (hash(x)=29321187) +1086 train 7.812850 (lr=1.7500e-04) (hash(x)=32627505) +1087 train 7.318038 (lr=1.7500e-04) (hash(x)=26482758) +1088 train 7.171348 (lr=1.7500e-04) (hash(x)=21431511) +1089 train 7.403332 (lr=1.7500e-04) (hash(x)=26046639) +1090 train 7.498190 (lr=1.7500e-04) (hash(x)=27464841) +1091 train 7.369232 (lr=1.7500e-04) (hash(x)=27068280) +1092 train 7.223825 (lr=1.7500e-04) (hash(x)=23119133) +1093 train 7.458742 (lr=1.7500e-04) (hash(x)=26782091) +1094 train 7.470769 (lr=1.7500e-04) (hash(x)=26265326) +1095 train 7.461782 (lr=1.7500e-04) (hash(x)=24929929) +1096 train 7.344063 (lr=1.7500e-04) (hash(x)=23158628) +1097 train 7.437323 (lr=1.7500e-04) (hash(x)=25950541) +1098 train 7.294384 (lr=1.7500e-04) (hash(x)=22093912) +1099 train 7.466092 (lr=1.7500e-04) (hash(x)=25373676) +1100 val loss 7.3785 +1100 val perplexity 1601.1755 +1100 train 7.142743 (lr=1.7500e-04) (hash(x)=18986670) +1101 train 7.625417 (lr=1.7500e-04) (hash(x)=27283187) +1102 train 7.398546 (lr=1.7500e-04) (hash(x)=25474743) +1103 train 7.251720 (lr=1.7500e-04) (hash(x)=25043037) +1104 train 7.200531 (lr=1.7500e-04) (hash(x)=23156261) +1105 train 7.653530 (lr=1.7500e-04) (hash(x)=27027534) +1106 train 7.262457 (lr=1.7500e-04) (hash(x)=22733630) +1107 train 7.508618 (lr=1.7500e-04) (hash(x)=27906976) +1108 train 7.465991 (lr=1.7500e-04) (hash(x)=27848655) +1109 train 7.366408 (lr=1.7500e-04) (hash(x)=23889709) +1110 train 8.351659 (lr=1.7500e-04) (hash(x)=33189918) +1111 train 7.942085 (lr=1.7500e-04) (hash(x)=29151257) +1112 train 7.629494 (lr=1.7500e-04) (hash(x)=23881512) +1113 train 7.360479 (lr=1.7500e-04) (hash(x)=21307974) +1114 train 7.357684 (lr=1.7500e-04) (hash(x)=25264524) +1115 train 7.503495 (lr=1.7500e-04) (hash(x)=26405613) +1116 train 7.195439 (lr=1.7500e-04) (hash(x)=21918678) +1117 train 7.226900 (lr=1.7500e-04) (hash(x)=24233887) +1118 train 6.835851 (lr=1.7500e-04) (hash(x)=19490509) +1119 train 7.518651 (lr=1.7500e-04) (hash(x)=26400365) +1120 train 7.792000 (lr=1.7500e-04) (hash(x)=28572086) +1121 train 7.202200 (lr=1.7500e-04) (hash(x)=22293114) +1122 train 7.334718 (lr=1.7500e-04) (hash(x)=26845479) +1123 train 7.225927 (lr=1.7500e-04) (hash(x)=23971905) +1124 train 7.445322 (lr=1.7500e-04) (hash(x)=25639959) +1125 train 7.057532 (lr=1.7500e-04) (hash(x)=20076502) +1126 train 7.424941 (lr=1.7500e-04) (hash(x)=25089255) +1127 train 7.302945 (lr=1.7500e-04) (hash(x)=24098812) +1128 train 7.326161 (lr=1.7500e-04) (hash(x)=23493707) +1129 train 7.528772 (lr=1.7500e-04) (hash(x)=27610410) +1130 train 7.327405 (lr=1.7500e-04) (hash(x)=24540186) +1131 train 7.623854 (lr=1.7500e-04) (hash(x)=29402976) +1132 train 7.210043 (lr=1.7500e-04) (hash(x)=23776025) +1133 train 6.951473 (lr=1.7500e-04) (hash(x)=19032564) +1134 train 7.540639 (lr=1.7500e-04) (hash(x)=26921117) +1135 train 7.118599 (lr=1.7500e-04) (hash(x)=20967666) +1136 train 7.165085 (lr=1.7500e-04) (hash(x)=23394540) +1137 train 7.227578 (lr=1.7500e-04) (hash(x)=22666342) +1138 train 7.448381 (lr=1.7500e-04) (hash(x)=23482498) +1139 train 7.481154 (lr=1.7500e-04) (hash(x)=24287610) +1140 train 7.551343 (lr=1.7500e-04) (hash(x)=24512831) +1141 train 7.788120 (lr=1.7500e-04) (hash(x)=28637634) +1142 train 8.008140 (lr=1.7500e-04) (hash(x)=24107127) +1143 train 7.679185 (lr=1.7500e-04) (hash(x)=28667963) +1144 train 7.613233 (lr=1.7500e-04) (hash(x)=26302492) +1145 train 7.597867 (lr=1.7500e-04) (hash(x)=23621685) +1146 train 7.290742 (lr=1.7500e-04) (hash(x)=23997414) +1147 train 7.354921 (lr=1.7500e-04) (hash(x)=25974316) +1148 train 7.260529 (lr=1.7500e-04) (hash(x)=23464988) +1149 train 7.381332 (lr=1.7500e-04) (hash(x)=24487710) +1150 val loss 7.3716 +1150 val perplexity 1590.2271 +1150 train 7.644165 (lr=1.7500e-04) (hash(x)=29610350) +1151 train 7.768388 (lr=1.7500e-04) (hash(x)=27083417) +1152 train 7.032895 (lr=1.7500e-04) (hash(x)=20666288) +1153 train 7.111530 (lr=1.7500e-04) (hash(x)=22850633) +1154 train 7.317291 (lr=1.7500e-04) (hash(x)=24741872) +1155 train 7.709653 (lr=1.7500e-04) (hash(x)=28605205) +1156 train 7.180669 (lr=1.7500e-04) (hash(x)=22624463) +1157 train 7.385952 (lr=1.7500e-04) (hash(x)=24786468) +1158 train 7.158745 (lr=1.7500e-04) (hash(x)=21365399) +1159 train 7.387733 (lr=1.7500e-04) (hash(x)=23649001) +1160 train 7.457036 (lr=1.7500e-04) (hash(x)=28203982) +1161 train 7.312674 (lr=1.7500e-04) (hash(x)=26473994) +1162 train 6.949329 (lr=1.7500e-04) (hash(x)=19476441) +1163 train 7.269055 (lr=1.7500e-04) (hash(x)=25921700) +1164 train 7.123828 (lr=1.7500e-04) (hash(x)=23064343) +1165 train 7.276552 (lr=1.7500e-04) (hash(x)=24117626) +1166 train 7.235555 (lr=1.7500e-04) (hash(x)=21764556) +1167 train 8.162691 (lr=1.7500e-04) (hash(x)=31338300) +1168 train 7.577531 (lr=1.7500e-04) (hash(x)=27443187) +1169 train 6.919794 (lr=1.7500e-04) (hash(x)=21337692) +1170 train 7.459691 (lr=1.7500e-04) (hash(x)=27845383) +1171 train 7.282556 (lr=1.7500e-04) (hash(x)=23862328) +1172 train 7.535342 (lr=1.7500e-04) (hash(x)=23811014) +1173 train 7.482456 (lr=1.7500e-04) (hash(x)=24380098) +1174 train 7.113481 (lr=1.7500e-04) (hash(x)=22351136) +1175 train 7.463389 (lr=1.7500e-04) (hash(x)=30603174) +1176 train 7.466490 (lr=1.7500e-04) (hash(x)=27924596) +1177 train 7.826151 (lr=1.7500e-04) (hash(x)=30882548) +1178 train 7.282263 (lr=1.7500e-04) (hash(x)=22339464) +1179 train 7.121062 (lr=1.7500e-04) (hash(x)=23603806) +1180 train 7.485147 (lr=1.7500e-04) (hash(x)=24809041) +1181 train 7.307676 (lr=1.7500e-04) (hash(x)=24382442) +1182 train 7.251064 (lr=1.7500e-04) (hash(x)=23134077) +1183 train 7.274723 (lr=1.7500e-04) (hash(x)=24830965) +1184 train 7.378677 (lr=1.7500e-04) (hash(x)=25527259) +1185 train 7.448813 (lr=1.7500e-04) (hash(x)=25547480) +1186 train 7.261323 (lr=1.7500e-04) (hash(x)=24424314) +1187 train 7.689497 (lr=1.7500e-04) (hash(x)=32488729) +1188 train 7.603176 (lr=1.7500e-04) (hash(x)=31168462) +1189 train 7.763658 (lr=1.7500e-04) (hash(x)=31331643) +1190 train 7.520792 (lr=1.7500e-04) (hash(x)=28746633) +1191 train 7.562210 (lr=1.7500e-04) (hash(x)=27269893) +1192 train 7.349121 (lr=1.7500e-04) (hash(x)=23484031) +1193 train 7.356441 (lr=1.7500e-04) (hash(x)=23278725) +1194 train 7.436594 (lr=1.7500e-04) (hash(x)=25440745) +1195 train 7.438407 (lr=1.7500e-04) (hash(x)=25215077) +1196 train 7.491874 (lr=1.7500e-04) (hash(x)=28309266) +1197 train 7.198892 (lr=1.7500e-04) (hash(x)=22442404) +1198 train 7.253334 (lr=1.7500e-04) (hash(x)=20775262) +1199 train 7.316741 (lr=1.7500e-04) (hash(x)=24825041) +1200 val loss 7.3880 +1200 val perplexity 1616.4530 +1200 train 7.507840 (lr=1.7500e-04) (hash(x)=29016896) +1201 train 7.442066 (lr=1.7500e-04) (hash(x)=25590276) +1202 train 7.306835 (lr=1.7500e-04) (hash(x)=22816384) +1203 train 7.459648 (lr=1.7500e-04) (hash(x)=25893804) +1204 train 7.314533 (lr=1.7500e-04) (hash(x)=23983816) +1205 train 7.243828 (lr=1.7500e-04) (hash(x)=22222468) +1206 train 7.273322 (lr=1.7500e-04) (hash(x)=23039141) +1207 train 7.263451 (lr=1.7500e-04) (hash(x)=22724871) +1208 train 7.316438 (lr=1.7500e-04) (hash(x)=25253062) +1209 train 7.284322 (lr=1.7500e-04) (hash(x)=25140744) +1210 train 7.390550 (lr=1.7500e-04) (hash(x)=24717218) +1211 train 7.502578 (lr=1.7500e-04) (hash(x)=27317554) +1212 train 7.165121 (lr=1.7500e-04) (hash(x)=22013236) +1213 train 7.697782 (lr=1.7500e-04) (hash(x)=26692343) +1214 train 7.183568 (lr=1.7500e-04) (hash(x)=19859225) +1215 train 7.186038 (lr=1.7500e-04) (hash(x)=24683717) +1216 train 7.204022 (lr=1.7500e-04) (hash(x)=21932013) +1217 train 7.438697 (lr=1.7500e-04) (hash(x)=26849303) +1218 train 7.503448 (lr=1.7500e-04) (hash(x)=26458000) +1219 train 7.318780 (lr=1.7500e-04) (hash(x)=21584083) +1220 train 7.669519 (lr=1.7500e-04) (hash(x)=23598625) +1221 train 7.355458 (lr=1.7500e-04) (hash(x)=26059939) +1222 train 7.665158 (lr=1.7500e-04) (hash(x)=25481982) +1223 train 7.491258 (lr=1.7500e-04) (hash(x)=26190337) +1224 train 7.686708 (lr=1.7500e-04) (hash(x)=28767755) +1225 train 7.289964 (lr=1.7500e-04) (hash(x)=23663918) +1226 train 7.399706 (lr=1.7500e-04) (hash(x)=21293227) +1227 train 7.380437 (lr=1.7500e-04) (hash(x)=22249019) +1228 train 7.493489 (lr=1.7500e-04) (hash(x)=26886529) +1229 train 7.300197 (lr=1.7500e-04) (hash(x)=25779849) +1230 train 7.453026 (lr=1.7500e-04) (hash(x)=26228964) +1231 train 7.347588 (lr=1.7500e-04) (hash(x)=23086289) +1232 train 7.468119 (lr=1.7500e-04) (hash(x)=23198922) +1233 train 7.442562 (lr=1.7500e-04) (hash(x)=27523941) +1234 train 7.281612 (lr=1.7500e-04) (hash(x)=24293992) +1235 train 7.957979 (lr=1.7500e-04) (hash(x)=28047044) +1236 train 7.459400 (lr=1.7500e-04) (hash(x)=23688671) +1237 train 7.346438 (lr=1.7500e-04) (hash(x)=25125498) +1238 train 7.256299 (lr=1.7500e-04) (hash(x)=21977292) +1239 train 7.318178 (lr=1.7500e-04) (hash(x)=23593875) +1240 train 7.228920 (lr=1.7500e-04) (hash(x)=22659030) +1241 train 7.331356 (lr=1.7500e-04) (hash(x)=25117733) +1242 train 7.336496 (lr=1.7500e-04) (hash(x)=22322808) +1243 train 7.349205 (lr=1.7500e-04) (hash(x)=26059735) +1244 train 7.317132 (lr=1.7500e-04) (hash(x)=22485526) +1245 train 7.243318 (lr=1.7500e-04) (hash(x)=23028679) +1246 train 7.270007 (lr=1.7500e-04) (hash(x)=22906035) +1247 train 7.177413 (lr=1.7500e-04) (hash(x)=22414190) +1248 train 7.489788 (lr=1.7500e-04) (hash(x)=26229624) +1249 train 7.263433 (lr=1.7500e-04) (hash(x)=22223137) +1250 val loss 7.3844 +1250 val perplexity 1610.6555 +1250 train 7.510259 (lr=1.7500e-04) (hash(x)=24911520) +1251 train 7.691617 (lr=1.7500e-04) (hash(x)=24204591) +1252 train 7.246023 (lr=1.7500e-04) (hash(x)=24379601) +1253 train 7.197100 (lr=1.7500e-04) (hash(x)=22922475) +1254 train 7.207283 (lr=1.7500e-04) (hash(x)=23426249) +1255 train 7.506847 (lr=1.7500e-04) (hash(x)=26758114) +1256 train 7.188106 (lr=1.7500e-04) (hash(x)=24027111) +1257 train 7.337797 (lr=1.7500e-04) (hash(x)=25358064) +1258 train 7.244553 (lr=1.7500e-04) (hash(x)=22571285) +1259 train 7.639743 (lr=1.7500e-04) (hash(x)=20084233) +1260 train 7.425299 (lr=1.7500e-04) (hash(x)=18786581) +1261 train 7.350840 (lr=1.7500e-04) (hash(x)=26395104) +1262 train 7.210258 (lr=1.7500e-04) (hash(x)=24212567) +1263 train 7.028564 (lr=1.7500e-04) (hash(x)=21563184) +1264 train 7.329073 (lr=1.7500e-04) (hash(x)=26490150) +1265 train 7.422176 (lr=1.7500e-04) (hash(x)=25207694) +1266 train 7.259044 (lr=1.7500e-04) (hash(x)=23914544) +1267 train 7.253057 (lr=1.7500e-04) (hash(x)=23861489) +1268 train 7.724761 (lr=1.7500e-04) (hash(x)=30714540) +1269 train 7.271677 (lr=1.7500e-04) (hash(x)=23471007) +1270 train 7.271665 (lr=1.7500e-04) (hash(x)=23244293) +1271 train 7.208035 (lr=1.7500e-04) (hash(x)=19218470) +1272 train 7.473076 (lr=1.7500e-04) (hash(x)=26965136) +1273 train 7.215476 (lr=1.7500e-04) (hash(x)=22944035) +1274 train 7.285559 (lr=1.7500e-04) (hash(x)=22002714) +1275 train 7.567300 (lr=1.7500e-04) (hash(x)=28469562) +1276 train 7.624300 (lr=1.7500e-04) (hash(x)=26889992) +1277 train 7.692098 (lr=1.7500e-04) (hash(x)=26452814) +1278 train 7.443944 (lr=1.7500e-04) (hash(x)=28397488) +1279 train 7.520888 (lr=1.7500e-04) (hash(x)=25588469) +1280 train 7.376956 (lr=1.7500e-04) (hash(x)=24833139) +1281 train 7.239334 (lr=1.7500e-04) (hash(x)=24788298) +1282 train 7.480945 (lr=1.7500e-04) (hash(x)=24979383) +1283 train 7.505254 (lr=1.7500e-04) (hash(x)=25236367) +1284 train 7.388596 (lr=1.7500e-04) (hash(x)=22638257) +1285 train 7.168224 (lr=1.7500e-04) (hash(x)=23069067) +1286 train 7.349232 (lr=1.7500e-04) (hash(x)=25133239) +1287 train 7.918953 (lr=1.7500e-04) (hash(x)=30433767) +1288 train 7.945481 (lr=1.7500e-04) (hash(x)=34319079) +1289 train 7.776337 (lr=1.7500e-04) (hash(x)=29268881) +1290 train 7.388715 (lr=1.7500e-04) (hash(x)=24528336) +1291 train 7.553342 (lr=1.7500e-04) (hash(x)=26302626) +1292 train 7.504768 (lr=1.7500e-04) (hash(x)=25479111) +1293 train 7.737635 (lr=1.7500e-04) (hash(x)=24749682) +1294 train 7.323289 (lr=1.7500e-04) (hash(x)=24111393) +1295 train 7.072377 (lr=1.7500e-04) (hash(x)=17851621) +1296 train 7.289841 (lr=1.7500e-04) (hash(x)=26463070) +1297 train 7.359844 (lr=1.7500e-04) (hash(x)=25620741) +1298 train 7.981195 (lr=1.7500e-04) (hash(x)=28225676) +1299 train 7.772937 (lr=1.7500e-04) (hash(x)=27028191) +1300 val loss 7.3620 +1300 val perplexity 1575.0029 +1300 train 7.394087 (lr=1.7500e-04) (hash(x)=29006516) +1301 train 7.545208 (lr=1.7500e-04) (hash(x)=27590299) +1302 train 7.696257 (lr=1.7500e-04) (hash(x)=28678983) +1303 train 7.546997 (lr=1.7500e-04) (hash(x)=25183690) +1304 train 7.053734 (lr=1.7500e-04) (hash(x)=19918097) +1305 train 7.860376 (lr=1.7500e-04) (hash(x)=31114252) +1306 train 7.810882 (lr=1.7500e-04) (hash(x)=30913255) +1307 train 7.387653 (lr=1.7500e-04) (hash(x)=26182243) +1308 train 7.656728 (lr=1.7500e-04) (hash(x)=27420668) +1309 train 7.828454 (lr=1.7500e-04) (hash(x)=30419908) +1310 train 7.763304 (lr=1.7500e-04) (hash(x)=29002281) +1311 train 7.447852 (lr=1.7500e-04) (hash(x)=27040642) +1312 train 7.328085 (lr=1.7500e-04) (hash(x)=26929300) +1313 train 7.407530 (lr=1.7500e-04) (hash(x)=26240761) +1314 train 7.472496 (lr=1.7500e-04) (hash(x)=27161876) +1315 train 7.288358 (lr=1.7500e-04) (hash(x)=24489607) +1316 train 7.704103 (lr=1.7500e-04) (hash(x)=27040115) +1317 train 7.358400 (lr=1.7500e-04) (hash(x)=25012872) +1318 train 6.965058 (lr=1.7500e-04) (hash(x)=20894720) +1319 train 7.058263 (lr=1.7500e-04) (hash(x)=22183303) +1320 train 7.450761 (lr=1.7500e-04) (hash(x)=26291778) +1321 train 7.517568 (lr=1.7500e-04) (hash(x)=27682633) +1322 train 7.248621 (lr=1.7500e-04) (hash(x)=26490892) +1323 train 7.685047 (lr=1.7500e-04) (hash(x)=28844646) +1324 train 8.002334 (lr=1.7500e-04) (hash(x)=29545304) +1325 train 8.171833 (lr=1.7500e-04) (hash(x)=31082070) +1326 train 7.791831 (lr=1.7500e-04) (hash(x)=27486316) +1327 train 7.725218 (lr=1.7500e-04) (hash(x)=27537063) +1328 train 7.539899 (lr=1.7500e-04) (hash(x)=26955557) +1329 train 7.489537 (lr=1.7500e-04) (hash(x)=26125988) +1330 train 7.451994 (lr=1.7500e-04) (hash(x)=22800125) +1331 train 7.619571 (lr=1.7500e-04) (hash(x)=25446686) +1332 train 7.661859 (lr=1.7500e-04) (hash(x)=28743746) +1333 train 7.384168 (lr=1.7500e-04) (hash(x)=19819857) +1334 train 7.132767 (lr=1.7500e-04) (hash(x)=23518628) +1335 train 7.080205 (lr=1.7500e-04) (hash(x)=19492832) +1336 train 7.354390 (lr=1.7500e-04) (hash(x)=24627720) +1337 train 7.248556 (lr=1.7500e-04) (hash(x)=23741214) +1338 train 7.350424 (lr=1.7500e-04) (hash(x)=25837914) +1339 train 7.303768 (lr=1.7500e-04) (hash(x)=25484958) +1340 train 7.261299 (lr=1.7500e-04) (hash(x)=23671284) +1341 train 7.389455 (lr=1.7500e-04) (hash(x)=25525370) +1342 train 7.511600 (lr=1.7500e-04) (hash(x)=26585300) +1343 train 7.533823 (lr=1.7500e-04) (hash(x)=25951629) +1344 train 7.707575 (lr=1.7500e-04) (hash(x)=28743135) +1345 train 7.868647 (lr=1.7500e-04) (hash(x)=28557663) +1346 train 7.235579 (lr=1.7500e-04) (hash(x)=22642751) +1347 train 7.153255 (lr=1.7500e-04) (hash(x)=23462798) +1348 train 7.052528 (lr=1.7500e-04) (hash(x)=24292328) +1349 train 7.388397 (lr=1.7500e-04) (hash(x)=27320280) +1350 val loss 7.3868 +1350 val perplexity 1614.5834 +1350 train 7.579124 (lr=1.7500e-04) (hash(x)=27352812) +1351 train 7.418441 (lr=1.7500e-04) (hash(x)=22408682) +1352 train 7.357755 (lr=1.7500e-04) (hash(x)=23144732) +1353 train 7.199159 (lr=1.7500e-04) (hash(x)=22230799) +1354 train 7.624628 (lr=1.7500e-04) (hash(x)=29747687) +1355 train 7.778553 (lr=1.7500e-04) (hash(x)=31317970) +1356 train 7.029390 (lr=1.7500e-04) (hash(x)=20131758) +1357 train 7.405119 (lr=1.7500e-04) (hash(x)=24020983) +1358 train 7.235435 (lr=1.7500e-04) (hash(x)=23998051) +1359 train 7.297960 (lr=1.7500e-04) (hash(x)=27633457) +1360 train 7.054131 (lr=1.7500e-04) (hash(x)=20155247) +1361 train 7.341741 (lr=1.7500e-04) (hash(x)=23766987) +1362 train 7.197496 (lr=1.7500e-04) (hash(x)=25960383) +1363 train 7.487575 (lr=1.7500e-04) (hash(x)=23729283) +1364 train 7.609932 (lr=1.7500e-04) (hash(x)=27775445) +1365 train 7.455657 (lr=1.7500e-04) (hash(x)=25975834) +1366 train 7.268199 (lr=1.7500e-04) (hash(x)=22765259) +1367 train 7.527723 (lr=1.7500e-04) (hash(x)=27635080) +1368 train 7.264288 (lr=1.7500e-04) (hash(x)=23848542) +1369 train 7.458359 (lr=1.7500e-04) (hash(x)=27181156) +1370 train 7.573040 (lr=1.7500e-04) (hash(x)=28321340) +1371 train 7.339007 (lr=1.7500e-04) (hash(x)=25918780) +1372 train 7.313611 (lr=1.7500e-04) (hash(x)=23338297) +1373 train 7.310673 (lr=1.7500e-04) (hash(x)=22370417) +1374 train 7.356268 (lr=1.7500e-04) (hash(x)=24272668) +1375 train 7.038570 (lr=1.7500e-04) (hash(x)=22287596) +1376 train 7.261287 (lr=1.7500e-04) (hash(x)=25257403) +1377 train 7.168926 (lr=1.7500e-04) (hash(x)=21584419) +1378 train 7.340597 (lr=1.7500e-04) (hash(x)=25318823) +1379 train 7.167713 (lr=1.7500e-04) (hash(x)=22694623) +1380 train 7.303639 (lr=1.7500e-04) (hash(x)=23743406) +1381 train 7.588506 (lr=1.7500e-04) (hash(x)=30820846) +1382 train 8.074697 (lr=1.7500e-04) (hash(x)=34639557) +1383 train 7.975713 (lr=1.7500e-04) (hash(x)=35895440) +1384 train 7.392952 (lr=1.7500e-04) (hash(x)=26304839) +1385 train 7.533417 (lr=1.7500e-04) (hash(x)=27058657) +1386 train 7.388086 (lr=1.7500e-04) (hash(x)=25209529) +1387 train 7.294603 (lr=1.7500e-04) (hash(x)=24298886) +1388 train 7.399858 (lr=1.7500e-04) (hash(x)=26200200) +1389 train 7.346116 (lr=1.7500e-04) (hash(x)=27303061) +1390 train 7.414772 (lr=1.7500e-04) (hash(x)=26531628) +1391 train 7.398109 (lr=1.7500e-04) (hash(x)=25888847) +1392 train 7.548973 (lr=1.7500e-04) (hash(x)=28924067) +1393 train 6.994971 (lr=1.7500e-04) (hash(x)=21267641) +1394 train 7.565359 (lr=1.7500e-04) (hash(x)=29419156) +1395 train 7.782665 (lr=1.7500e-04) (hash(x)=30860646) +1396 train 7.360040 (lr=1.7500e-04) (hash(x)=25744434) +1397 train 7.364076 (lr=1.7500e-04) (hash(x)=26881837) +1398 train 7.336110 (lr=1.7500e-04) (hash(x)=26676176) +1399 train 7.541455 (lr=1.7500e-04) (hash(x)=26518800) +1400 val loss 7.3555 +1400 val perplexity 1564.8340 +1400 train 7.267527 (lr=1.7500e-04) (hash(x)=25043238) +1401 train 7.585130 (lr=1.7500e-04) (hash(x)=25863277) +1402 train 7.255171 (lr=1.7500e-04) (hash(x)=24073623) +1403 train 7.342229 (lr=1.7500e-04) (hash(x)=25385523) +1404 train 7.376758 (lr=1.7500e-04) (hash(x)=24958112) +1405 train 7.249813 (lr=1.7500e-04) (hash(x)=23362519) +1406 train 7.523505 (lr=1.7500e-04) (hash(x)=29262616) +1407 train 7.902115 (lr=1.7500e-04) (hash(x)=37519283) +1408 train 8.149146 (lr=1.7500e-04) (hash(x)=33716930) +1409 train 7.326721 (lr=1.7500e-04) (hash(x)=23392584) +1410 train 7.794796 (lr=1.7500e-04) (hash(x)=22877779) +1411 train 8.121569 (lr=1.7500e-04) (hash(x)=20564397) +1412 train 7.577985 (lr=1.7500e-04) (hash(x)=24366235) +1413 train 7.458654 (lr=1.7500e-04) (hash(x)=27065499) +1414 train 7.310529 (lr=1.7500e-04) (hash(x)=26844114) +1415 train 7.459981 (lr=1.7500e-04) (hash(x)=25141945) +1416 train 7.633763 (lr=1.7500e-04) (hash(x)=28813116) +1417 train 7.426657 (lr=1.7500e-04) (hash(x)=25466598) +1418 train 7.301691 (lr=1.7500e-04) (hash(x)=22800032) +1419 train 7.319958 (lr=1.7500e-04) (hash(x)=22717866) +1420 train 7.836629 (lr=1.7500e-04) (hash(x)=28040763) +1421 train 7.943282 (lr=1.7500e-04) (hash(x)=29648992) +1422 train 7.909564 (lr=1.7500e-04) (hash(x)=31747228) +1423 train 7.415480 (lr=1.7500e-04) (hash(x)=28527939) +1424 train 7.390250 (lr=1.7500e-04) (hash(x)=21563992) +1425 train 7.402905 (lr=1.7500e-04) (hash(x)=25134784) +1426 train 7.626863 (lr=1.7500e-04) (hash(x)=28442823) +1427 train 8.096197 (lr=1.7500e-04) (hash(x)=32757059) +1428 train 7.576489 (lr=1.7500e-04) (hash(x)=24110500) +1429 train 7.560287 (lr=1.7500e-04) (hash(x)=24145729) +1430 train 7.542840 (lr=1.7500e-04) (hash(x)=23541086) +1431 train 7.425986 (lr=1.7500e-04) (hash(x)=21942471) +1432 train 7.522335 (lr=1.7500e-04) (hash(x)=24736836) +1433 train 7.689424 (lr=1.7500e-04) (hash(x)=25325444) +1434 train 7.686817 (lr=1.7500e-04) (hash(x)=25188954) +1435 train 8.165796 (lr=1.7500e-04) (hash(x)=24247339) +1436 train 7.713245 (lr=1.7500e-04) (hash(x)=23773363) +1437 train 7.477159 (lr=1.7500e-04) (hash(x)=24142989) +1438 train 7.480672 (lr=1.7500e-04) (hash(x)=24226952) +1439 train 7.728378 (lr=1.7500e-04) (hash(x)=24955630) +1440 train 7.644708 (lr=1.7500e-04) (hash(x)=24563233) +1441 train 7.718994 (lr=1.7500e-04) (hash(x)=25491335) +1442 train 7.941469 (lr=1.7500e-04) (hash(x)=33253763) +1443 train 7.597246 (lr=1.7500e-04) (hash(x)=21368780) +1444 train 7.659477 (lr=1.7500e-04) (hash(x)=26615500) +1445 train 7.812378 (lr=1.7500e-04) (hash(x)=27146278) +1446 train 7.693981 (lr=1.7500e-04) (hash(x)=25904861) +1447 train 7.527483 (lr=1.7500e-04) (hash(x)=25541230) +1448 train 7.686435 (lr=1.7500e-04) (hash(x)=25434227) +1449 train 7.660726 (lr=1.7500e-04) (hash(x)=25375355) +1450 val loss 7.6404 +1450 val perplexity 2080.4924 +1450 train 7.483081 (lr=1.7500e-04) (hash(x)=21921129) +1451 train 7.504184 (lr=1.7500e-04) (hash(x)=23098806) +1452 train 7.542024 (lr=1.7500e-04) (hash(x)=22000544) +1453 train 7.465697 (lr=1.7500e-04) (hash(x)=22061174) +1454 train 7.528764 (lr=1.7500e-04) (hash(x)=24326286) +1455 train 7.565808 (lr=1.7500e-04) (hash(x)=23501481) +1456 train 7.733454 (lr=1.7500e-04) (hash(x)=26397938) +1457 train 7.669912 (lr=1.7500e-04) (hash(x)=24656430) +1458 train 7.341574 (lr=1.7500e-04) (hash(x)=23494971) +1459 train 7.376353 (lr=1.7500e-04) (hash(x)=23802681) +1460 train 7.355376 (lr=1.7500e-04) (hash(x)=21990153) +1461 train 7.324796 (lr=1.7500e-04) (hash(x)=23496118) +1462 train 7.298042 (lr=1.7500e-04) (hash(x)=24233822) +1463 train 7.625232 (lr=1.7500e-04) (hash(x)=22754988) +1464 train 7.304718 (lr=1.7500e-04) (hash(x)=23116635) +1465 train 7.058099 (lr=1.7500e-04) (hash(x)=21461650) +1466 train 7.185001 (lr=1.7500e-04) (hash(x)=22274473) +1467 train 7.217597 (lr=1.7500e-04) (hash(x)=22183009) +1468 train 7.448334 (lr=1.7500e-04) (hash(x)=24972441) +1469 train 7.286932 (lr=1.7500e-04) (hash(x)=22300616) +1470 train 7.082752 (lr=1.7500e-04) (hash(x)=21443060) +1471 train 7.312131 (lr=1.7500e-04) (hash(x)=23475070) +1472 train 7.176540 (lr=1.7500e-04) (hash(x)=22316810) +1473 train 7.607574 (lr=1.7500e-04) (hash(x)=24508407) +1474 train 7.655178 (lr=1.7500e-04) (hash(x)=24603557) +1475 train 7.240218 (lr=1.7500e-04) (hash(x)=23359061) +1476 train 7.317932 (lr=1.7500e-04) (hash(x)=22950844) +1477 train 7.356571 (lr=1.7500e-04) (hash(x)=22588667) +1478 train 7.473298 (lr=1.7500e-04) (hash(x)=26083526) +1479 train 7.375736 (lr=1.7500e-04) (hash(x)=23609959) +1480 train 7.370420 (lr=1.7500e-04) (hash(x)=24088171) +1481 train 7.383254 (lr=1.7500e-04) (hash(x)=25394852) +1482 train 7.332279 (lr=1.7500e-04) (hash(x)=24503040) +1483 train 7.050836 (lr=1.7500e-04) (hash(x)=22408449) +1484 train 7.312464 (lr=1.7500e-04) (hash(x)=25069325) +1485 train 7.355458 (lr=1.7500e-04) (hash(x)=26947398) +1486 train 6.802890 (lr=1.7500e-04) (hash(x)=17527161) +1487 train 7.237769 (lr=1.7500e-04) (hash(x)=23441847) +1488 train 7.272869 (lr=1.7500e-04) (hash(x)=25592861) +1489 train 7.165924 (lr=1.7500e-04) (hash(x)=23101350) +1490 train 7.159645 (lr=1.7500e-04) (hash(x)=24201380) +1491 train 7.274158 (lr=1.7500e-04) (hash(x)=23676365) +1492 train 7.327805 (lr=1.7500e-04) (hash(x)=26668088) +1493 train 7.461652 (lr=1.7500e-04) (hash(x)=26488811) +1494 train 7.451112 (lr=1.7500e-04) (hash(x)=27248109) +1495 train 7.506116 (lr=1.7500e-04) (hash(x)=23096292) +1496 train 7.425294 (lr=1.7500e-04) (hash(x)=22101981) +1497 train 7.587671 (lr=1.7500e-04) (hash(x)=24512380) +1498 train 7.375122 (lr=1.7500e-04) (hash(x)=25367738) +1499 train 7.363239 (lr=1.7500e-04) (hash(x)=27706294) +1500 val loss 7.3486 +1500 val perplexity 1554.0555 +1500 train 7.491161 (lr=1.7500e-04) (hash(x)=24154026) +1501 train 7.188530 (lr=1.7500e-04) (hash(x)=21892472) +1502 train 7.267600 (lr=1.7500e-04) (hash(x)=23662543) +1503 train 7.345338 (lr=1.7500e-04) (hash(x)=26171093) +1504 train 7.360283 (lr=1.7500e-04) (hash(x)=25974292) +1505 train 7.228679 (lr=1.7500e-04) (hash(x)=23191101) +1506 train 7.457881 (lr=1.7500e-04) (hash(x)=26498861) +1507 train 8.021647 (lr=1.7500e-04) (hash(x)=34946941) +1508 train 7.606609 (lr=1.7500e-04) (hash(x)=25442719) +1509 train 7.431856 (lr=1.7500e-04) (hash(x)=25569942) +1510 train 7.177266 (lr=1.7500e-04) (hash(x)=21265828) +1511 train 7.109661 (lr=1.7500e-04) (hash(x)=20060838) +1512 train 7.260068 (lr=1.7500e-04) (hash(x)=22588251) +1513 train 7.217470 (lr=1.7500e-04) (hash(x)=24581020) +1514 train 7.224960 (lr=1.7500e-04) (hash(x)=21882493) +1515 train 7.175606 (lr=1.7500e-04) (hash(x)=21591702) +1516 train 7.195021 (lr=1.7500e-04) (hash(x)=19813285) +1517 train 7.250930 (lr=1.7500e-04) (hash(x)=21870012) +1518 train 7.302789 (lr=1.7500e-04) (hash(x)=26895498) +1519 train 7.366653 (lr=1.7500e-04) (hash(x)=25451055) +1520 train 7.412459 (lr=1.7500e-04) (hash(x)=25395865) +1521 train 6.946153 (lr=1.7500e-04) (hash(x)=18989695) +1522 train 6.813928 (lr=1.7500e-04) (hash(x)=17040678) +1523 train 6.920971 (lr=1.7500e-04) (hash(x)=18691455) +1524 train 6.994400 (lr=1.7500e-04) (hash(x)=19017167) +1525 train 7.311154 (lr=1.7500e-04) (hash(x)=22406503) +1526 train 7.425621 (lr=1.7500e-04) (hash(x)=23036138) +1527 train 7.366373 (lr=1.7500e-04) (hash(x)=24934792) +1528 train 7.403581 (lr=1.7500e-04) (hash(x)=22843127) +1529 train 7.302238 (lr=1.7500e-04) (hash(x)=24249677) +1530 train 7.171513 (lr=1.7500e-04) (hash(x)=23318555) +1531 train 7.189117 (lr=1.7500e-04) (hash(x)=23864361) +1532 train 7.067743 (lr=1.7500e-04) (hash(x)=20242060) +1533 train 7.240318 (lr=1.7500e-04) (hash(x)=21549554) +1534 train 7.061021 (lr=1.7500e-04) (hash(x)=21642024) +1535 train 7.516938 (lr=1.7500e-04) (hash(x)=25367597) +1536 train 7.715196 (lr=1.7500e-04) (hash(x)=27224144) +1537 train 7.273219 (lr=1.7500e-04) (hash(x)=24409290) +1538 train 7.367237 (lr=1.7500e-04) (hash(x)=24987180) +1539 train 7.257785 (lr=1.7500e-04) (hash(x)=27016702) +1540 train 7.505960 (lr=1.7500e-04) (hash(x)=25819636) +1541 train 7.422822 (lr=1.7500e-04) (hash(x)=25520453) +1542 train 7.154421 (lr=1.7500e-04) (hash(x)=23580496) +1543 train 7.399560 (lr=1.7500e-04) (hash(x)=25022148) +1544 train 7.391783 (lr=1.7500e-04) (hash(x)=25447327) +1545 train 7.397914 (lr=1.7500e-04) (hash(x)=25010319) +1546 train 7.326151 (lr=1.7500e-04) (hash(x)=25511777) +1547 train 7.270509 (lr=1.7500e-04) (hash(x)=24459012) +1548 train 7.331371 (lr=1.7500e-04) (hash(x)=25082785) +1549 train 7.383667 (lr=1.7500e-04) (hash(x)=26528670) +1550 val loss 7.3504 +1550 val perplexity 1556.8235 +1550 train 7.361125 (lr=1.7500e-04) (hash(x)=26684367) +1551 train 7.346838 (lr=1.7500e-04) (hash(x)=25431365) +1552 train 7.314982 (lr=1.7500e-04) (hash(x)=24802747) +1553 train 7.152864 (lr=1.7500e-04) (hash(x)=24229522) +1554 train 7.361159 (lr=1.7500e-04) (hash(x)=24757176) +1555 train 7.470708 (lr=1.7500e-04) (hash(x)=25958785) +1556 train 7.501444 (lr=1.7500e-04) (hash(x)=26810735) +1557 train 7.108762 (lr=1.7500e-04) (hash(x)=22882640) +1558 train 7.580259 (lr=1.7500e-04) (hash(x)=27220057) +1559 train 7.839103 (lr=1.7500e-04) (hash(x)=29307788) +1560 train 7.286771 (lr=1.7500e-04) (hash(x)=25214030) +1561 train 7.139586 (lr=1.7500e-04) (hash(x)=23167825) +1562 train 7.206018 (lr=1.7500e-04) (hash(x)=24658511) +1563 train 7.372949 (lr=1.7500e-04) (hash(x)=24965435) +1564 train 7.126538 (lr=1.7500e-04) (hash(x)=23620579) +1565 train 7.095399 (lr=1.7500e-04) (hash(x)=23772949) +1566 train 7.262562 (lr=1.7500e-04) (hash(x)=23807939) +1567 train 7.488822 (lr=1.7500e-04) (hash(x)=25651929) +1568 train 7.424368 (lr=1.7500e-04) (hash(x)=25549933) +1569 train 7.119298 (lr=1.7500e-04) (hash(x)=23146724) +1570 train 7.224989 (lr=1.7500e-04) (hash(x)=24099275) +1571 train 7.423751 (lr=1.7500e-04) (hash(x)=28451031) +1572 train 7.462490 (lr=1.7500e-04) (hash(x)=25488511) +1573 train 7.282532 (lr=1.7500e-04) (hash(x)=23796771) +1574 train 7.335459 (lr=1.7500e-04) (hash(x)=22642764) +1575 train 7.430576 (lr=1.7500e-04) (hash(x)=26312387) +1576 train 7.248106 (lr=1.7500e-04) (hash(x)=22486223) +1577 train 7.264899 (lr=1.7500e-04) (hash(x)=21257377) +1578 train 7.388829 (lr=1.7500e-04) (hash(x)=24328365) +1579 train 7.440693 (lr=1.7500e-04) (hash(x)=25326650) +1580 train 7.387900 (lr=1.7500e-04) (hash(x)=26484837) +1581 train 7.174629 (lr=1.7500e-04) (hash(x)=24605603) +1582 train 7.274832 (lr=1.7500e-04) (hash(x)=24668537) +1583 train 7.182294 (lr=1.7500e-04) (hash(x)=23804913) +1584 train 7.433956 (lr=1.7500e-04) (hash(x)=23615391) +1585 train 7.410227 (lr=1.7500e-04) (hash(x)=24322926) +1586 train 7.192127 (lr=1.7500e-04) (hash(x)=19753104) +1587 train 7.646019 (lr=1.7500e-04) (hash(x)=25537529) +1588 train 7.045653 (lr=1.7500e-04) (hash(x)=22835476) +1589 train 7.180104 (lr=1.7500e-04) (hash(x)=25707197) +1590 train 7.187425 (lr=1.7500e-04) (hash(x)=24191203) +1591 train 7.438739 (lr=1.7500e-04) (hash(x)=26115519) +1592 train 7.355731 (lr=1.7500e-04) (hash(x)=25781547) +1593 train 7.196783 (lr=1.7500e-04) (hash(x)=24850654) +1594 train 7.108507 (lr=1.7500e-04) (hash(x)=23300928) +1595 train 7.352495 (lr=1.7500e-04) (hash(x)=25494804) +1596 train 7.346930 (lr=1.7500e-04) (hash(x)=28169410) +1597 train 7.097547 (lr=1.7500e-04) (hash(x)=21972022) +1598 train 7.650027 (lr=1.7500e-04) (hash(x)=27687290) +1599 train 7.550981 (lr=1.7500e-04) (hash(x)=23210747) +1600 val loss 7.3159 +1600 val perplexity 1503.9529 +1600 train 7.580358 (lr=1.7500e-04) (hash(x)=20362758) +1601 train 7.378829 (lr=1.7500e-04) (hash(x)=17064773) +1602 train 7.364450 (lr=1.7500e-04) (hash(x)=17173694) +1603 train 7.454337 (lr=1.7500e-04) (hash(x)=15717069) +1604 train 7.533067 (lr=1.7500e-04) (hash(x)=15117973) +1605 train 7.344408 (lr=1.7500e-04) (hash(x)=16189636) +1606 train 7.281566 (lr=1.7500e-04) (hash(x)=16552095) +1607 train 7.153870 (lr=1.7500e-04) (hash(x)=18463712) +1608 train 7.306492 (lr=1.7500e-04) (hash(x)=17572155) +1609 train 7.289052 (lr=1.7500e-04) (hash(x)=19970072) +1610 train 7.320626 (lr=1.7500e-04) (hash(x)=20463871) +1611 train 7.359720 (lr=1.7500e-04) (hash(x)=20705573) +1612 train 7.187767 (lr=1.7500e-04) (hash(x)=24441646) +1613 train 7.359239 (lr=1.7500e-04) (hash(x)=22913147) +1614 train 7.498513 (lr=1.7500e-04) (hash(x)=23081598) +1615 train 7.225542 (lr=1.7500e-04) (hash(x)=23245699) +1616 train 7.268256 (lr=1.7500e-04) (hash(x)=23003072) +1617 train 7.534044 (lr=1.7500e-04) (hash(x)=27121904) +1618 train 7.290504 (lr=1.7500e-04) (hash(x)=25092305) +1619 train 7.336827 (lr=1.7500e-04) (hash(x)=23444521) +1620 train 7.389773 (lr=1.7500e-04) (hash(x)=22130531) +1621 train 7.169343 (lr=1.7500e-04) (hash(x)=20917937) +1622 train 7.294557 (lr=1.7500e-04) (hash(x)=22526838) +1623 train 7.387885 (lr=1.7500e-04) (hash(x)=21770300) +1624 train 8.433039 (lr=1.7500e-04) (hash(x)=22333537) +1625 train 8.438319 (lr=1.7500e-04) (hash(x)=24642519) +1626 train 7.623714 (lr=1.7500e-04) (hash(x)=25199038) +1627 train 7.398230 (lr=1.7500e-04) (hash(x)=23334569) +1628 train 7.299445 (lr=1.7500e-04) (hash(x)=23785360) +1629 train 6.986470 (lr=1.7500e-04) (hash(x)=21796200) +1630 train 7.022541 (lr=1.7500e-04) (hash(x)=22389081) +1631 train 7.261810 (lr=1.7500e-04) (hash(x)=25387532) +1632 train 6.861418 (lr=1.7500e-04) (hash(x)=17247578) +1633 train 7.226678 (lr=1.7500e-04) (hash(x)=22203733) +1634 train 7.426391 (lr=1.7500e-04) (hash(x)=24387455) +1635 train 7.934856 (lr=1.7500e-04) (hash(x)=29466743) +1636 train 7.292271 (lr=1.7500e-04) (hash(x)=25354152) +1637 train 7.361032 (lr=1.7500e-04) (hash(x)=21756102) +1638 train 7.304352 (lr=1.7500e-04) (hash(x)=23544029) +1639 train 7.422119 (lr=1.7500e-04) (hash(x)=27718703) +1640 train 7.389137 (lr=1.7500e-04) (hash(x)=25697138) +1641 train 7.210608 (lr=1.7500e-04) (hash(x)=22978681) +1642 train 7.798593 (lr=1.7500e-04) (hash(x)=29527067) +1643 train 6.906667 (lr=1.7500e-04) (hash(x)=17631973) +1644 train 7.338220 (lr=1.7500e-04) (hash(x)=24860172) +1645 train 7.660133 (lr=1.7500e-04) (hash(x)=27947891) +1646 train 7.352678 (lr=1.7500e-04) (hash(x)=23819556) +1647 train 7.397659 (lr=1.7500e-04) (hash(x)=27661052) +1648 train 7.172369 (lr=1.7500e-04) (hash(x)=23014209) +1649 train 7.108507 (lr=1.7500e-04) (hash(x)=23061452) +1650 val loss 7.3664 +1650 val perplexity 1581.8890 +1650 train 7.231430 (lr=1.7500e-04) (hash(x)=21949051) +1651 train 7.288648 (lr=1.7500e-04) (hash(x)=22244096) +1652 train 7.280126 (lr=1.7500e-04) (hash(x)=25997585) +1653 train 7.366152 (lr=1.7500e-04) (hash(x)=25389713) +1654 train 7.284316 (lr=1.7500e-04) (hash(x)=24390520) +1655 train 7.556367 (lr=1.7500e-04) (hash(x)=26538928) +1656 train 7.474638 (lr=1.7500e-04) (hash(x)=28708088) +1657 train 7.585231 (lr=1.7500e-04) (hash(x)=25685569) +1658 train 7.094911 (lr=1.7500e-04) (hash(x)=22163531) +1659 train 7.270345 (lr=1.7500e-04) (hash(x)=26256802) +1660 train 7.719831 (lr=1.7500e-04) (hash(x)=30016026) +1661 train 7.271377 (lr=1.7500e-04) (hash(x)=24412323) +1662 train 7.322438 (lr=1.7500e-04) (hash(x)=24722307) +1663 train 7.205637 (lr=1.7500e-04) (hash(x)=21772654) +1664 train 7.159461 (lr=1.7500e-04) (hash(x)=24984527) +1665 train 7.322026 (lr=1.7500e-04) (hash(x)=25456825) +1666 train 7.657285 (lr=1.7500e-04) (hash(x)=24383976) +1667 train 7.555575 (lr=1.7500e-04) (hash(x)=25026277) +1668 train 7.494674 (lr=1.7500e-04) (hash(x)=28121715) +1669 train 7.490045 (lr=1.7500e-04) (hash(x)=26855439) +1670 train 7.604901 (lr=1.7500e-04) (hash(x)=33370924) +1671 train 7.435666 (lr=1.7500e-04) (hash(x)=26263254) +1672 train 7.907545 (lr=1.7500e-04) (hash(x)=29958158) +1673 train 7.195101 (lr=1.7500e-04) (hash(x)=21917396) +1674 train 7.330289 (lr=1.7500e-04) (hash(x)=24196295) +1675 train 7.364079 (lr=1.7500e-04) (hash(x)=24726314) +1676 train 7.153508 (lr=1.7500e-04) (hash(x)=22137742) +1677 train 7.289863 (lr=1.7500e-04) (hash(x)=24375100) +1678 train 7.235341 (lr=1.7500e-04) (hash(x)=23965039) +1679 train 7.274722 (lr=1.7500e-04) (hash(x)=23552356) +1680 train 7.267833 (lr=1.7500e-04) (hash(x)=26136969) +1681 train 7.495313 (lr=1.7500e-04) (hash(x)=25343112) +1682 train 7.175270 (lr=1.7500e-04) (hash(x)=22831508) +1683 train 7.437698 (lr=1.7500e-04) (hash(x)=26699819) +1684 train 7.563581 (lr=1.7500e-04) (hash(x)=25435504) +1685 train 7.713244 (lr=1.7500e-04) (hash(x)=25218858) +1686 train 8.326731 (lr=1.7500e-04) (hash(x)=25664448) +1687 train 7.433423 (lr=1.7500e-04) (hash(x)=22707141) +1688 train 7.570975 (lr=1.7500e-04) (hash(x)=28001383) +1689 train 7.791243 (lr=1.7500e-04) (hash(x)=29168269) +1690 train 7.776214 (lr=1.7500e-04) (hash(x)=29637522) +1691 train 7.803609 (lr=1.7500e-04) (hash(x)=25676149) +1692 train 7.236033 (lr=1.7500e-04) (hash(x)=20919831) +1693 train 7.402172 (lr=1.7500e-04) (hash(x)=24324401) +1694 train 7.452179 (lr=1.7500e-04) (hash(x)=26862625) +1695 train 7.851770 (lr=1.7500e-04) (hash(x)=34234481) +1696 train 7.398645 (lr=1.7500e-04) (hash(x)=27415195) +1697 train 7.247929 (lr=1.7500e-04) (hash(x)=24511386) +1698 train 7.386205 (lr=1.7500e-04) (hash(x)=26904299) +1699 train 7.256253 (lr=1.7500e-04) (hash(x)=25401624) +1700 val loss 7.3476 +1700 val perplexity 1552.4076 +1700 train 7.307014 (lr=1.7500e-04) (hash(x)=26498489) +1701 train 7.283363 (lr=1.7500e-04) (hash(x)=22340685) +1702 train 7.391576 (lr=1.7500e-04) (hash(x)=26396757) +1703 train 7.933673 (lr=1.7500e-04) (hash(x)=35008670) +1704 train 7.700386 (lr=1.7500e-04) (hash(x)=31782020) +1705 train 7.612925 (lr=1.7500e-04) (hash(x)=29662286) +1706 train 7.763060 (lr=1.7500e-04) (hash(x)=34215782) +1707 train 7.299619 (lr=1.7500e-04) (hash(x)=25682280) +1708 train 7.522867 (lr=1.7500e-04) (hash(x)=27109048) +1709 train 7.559309 (lr=1.7500e-04) (hash(x)=27686498) +1710 train 7.369950 (lr=1.7500e-04) (hash(x)=24247565) +1711 train 7.338913 (lr=1.7500e-04) (hash(x)=25891543) +1712 train 7.476103 (lr=1.7500e-04) (hash(x)=26436778) +1713 train 7.090272 (lr=1.7500e-04) (hash(x)=22538881) +1714 train 7.054045 (lr=1.7500e-04) (hash(x)=21993512) +1715 train 7.567214 (lr=1.7500e-04) (hash(x)=25962407) +1716 train 7.389496 (lr=1.7500e-04) (hash(x)=24130284) +1717 train 7.238594 (lr=1.7500e-04) (hash(x)=24819073) +1718 train 7.112060 (lr=1.7500e-04) (hash(x)=23496648) +1719 train 7.172780 (lr=1.7500e-04) (hash(x)=21971224) +1720 train 7.069923 (lr=1.7500e-04) (hash(x)=21498081) +1721 train 7.082775 (lr=1.7500e-04) (hash(x)=20951317) +1722 train 7.636647 (lr=1.7500e-04) (hash(x)=28848134) +1723 train 7.653120 (lr=1.7500e-04) (hash(x)=30838142) +1724 train 7.595611 (lr=1.7500e-04) (hash(x)=28844392) +1725 train 7.287204 (lr=1.7500e-04) (hash(x)=23102419) +1726 train 7.300822 (lr=1.7500e-04) (hash(x)=22374479) +1727 train 7.546053 (lr=1.7500e-04) (hash(x)=27312186) +1728 train 7.831041 (lr=1.7500e-04) (hash(x)=34362559) +1729 train 7.762703 (lr=1.7500e-04) (hash(x)=30920030) +1730 train 7.114241 (lr=1.7500e-04) (hash(x)=23684126) +1731 train 7.394337 (lr=1.7500e-04) (hash(x)=23657081) +1732 train 7.592193 (lr=1.7500e-04) (hash(x)=28463299) +1733 train 7.856043 (lr=1.7500e-04) (hash(x)=35351214) +1734 train 7.430601 (lr=1.7500e-04) (hash(x)=28855662) +1735 train 6.967111 (lr=1.7500e-04) (hash(x)=22163749) +1736 train 7.007521 (lr=1.7500e-04) (hash(x)=22024585) +1737 train 7.199502 (lr=1.7500e-04) (hash(x)=24629160) +1738 train 7.267227 (lr=1.7500e-04) (hash(x)=25220941) +1739 train 7.176277 (lr=1.7500e-04) (hash(x)=24829818) +1740 train 7.576602 (lr=1.7500e-04) (hash(x)=28453898) +1741 train 7.605052 (lr=1.7500e-04) (hash(x)=25424550) +1742 train 7.194231 (lr=1.7500e-04) (hash(x)=23437814) +1743 train 7.304911 (lr=1.7500e-04) (hash(x)=25942888) +1744 train 7.258789 (lr=1.7500e-04) (hash(x)=24503801) +1745 train 7.590445 (lr=1.7500e-04) (hash(x)=26418501) +1746 train 7.489941 (lr=1.7500e-04) (hash(x)=27177691) +1747 train 7.183127 (lr=1.7500e-04) (hash(x)=23785671) +1748 train 7.613559 (lr=1.7500e-04) (hash(x)=27362772) +1749 train 7.382040 (lr=1.7500e-04) (hash(x)=25097859) +1750 val loss 7.3552 +1750 val perplexity 1564.2686 +1750 train 7.319115 (lr=1.7500e-04) (hash(x)=24662466) +1751 train 7.224023 (lr=1.7500e-04) (hash(x)=25493916) +1752 train 7.323297 (lr=1.7500e-04) (hash(x)=24655868) +1753 train 7.523945 (lr=1.7500e-04) (hash(x)=19819210) +1754 train 7.166589 (lr=1.7500e-04) (hash(x)=21377155) +1755 train 8.009475 (lr=1.7500e-04) (hash(x)=28618702) +1756 train 7.886417 (lr=1.7500e-04) (hash(x)=27324953) +1757 train 7.626952 (lr=1.7500e-04) (hash(x)=29707907) +1758 train 7.359581 (lr=1.7500e-04) (hash(x)=24485921) +1759 train 7.472601 (lr=1.7500e-04) (hash(x)=24289951) +1760 train 7.156056 (lr=1.7500e-04) (hash(x)=22496716) +1761 train 7.312898 (lr=1.7500e-04) (hash(x)=25147026) +1762 train 7.381835 (lr=1.7500e-04) (hash(x)=26851828) +1763 train 7.342349 (lr=1.7500e-04) (hash(x)=26331486) +1764 train 7.223804 (lr=1.7500e-04) (hash(x)=24383054) +1765 train 7.456197 (lr=1.7500e-04) (hash(x)=25885126) +1766 train 7.409830 (lr=1.7500e-04) (hash(x)=25848470) +1767 train 7.228130 (lr=1.7500e-04) (hash(x)=23648671) +1768 train 7.155915 (lr=1.7500e-04) (hash(x)=23168674) +1769 train 6.998694 (lr=1.7500e-04) (hash(x)=20252079) +1770 train 7.251514 (lr=1.7500e-04) (hash(x)=23914287) +1771 train 7.537395 (lr=1.7500e-04) (hash(x)=27292797) +1772 train 6.719145 (lr=1.7500e-04) (hash(x)=16175151) +1773 train 6.874383 (lr=1.7500e-04) (hash(x)=18317379) +1774 train 7.255757 (lr=1.7500e-04) (hash(x)=24464271) +1775 train 7.233061 (lr=1.7500e-04) (hash(x)=24992055) +1776 train 7.859313 (lr=1.7500e-04) (hash(x)=26032451) +1777 train 7.619684 (lr=1.7500e-04) (hash(x)=24734221) +1778 train 7.583112 (lr=1.7500e-04) (hash(x)=25413430) +1779 train 7.475568 (lr=1.7500e-04) (hash(x)=24398330) +1780 train 7.313069 (lr=1.7500e-04) (hash(x)=24568049) +1781 train 7.187191 (lr=1.7500e-04) (hash(x)=23573984) +1782 train 7.436214 (lr=1.7500e-04) (hash(x)=27338410) +1783 train 7.369153 (lr=1.7500e-04) (hash(x)=26005549) +1784 train 7.192691 (lr=1.7500e-04) (hash(x)=24332331) +1785 train 7.059497 (lr=1.7500e-04) (hash(x)=22583878) +1786 train 7.215343 (lr=1.7500e-04) (hash(x)=24599113) +1787 train 7.652754 (lr=1.7500e-04) (hash(x)=30259737) +1788 train 7.465604 (lr=1.7500e-04) (hash(x)=26504237) +1789 train 7.320439 (lr=1.7500e-04) (hash(x)=25196470) +1790 train 7.204756 (lr=1.7500e-04) (hash(x)=23607871) +1791 train 7.115505 (lr=1.7500e-04) (hash(x)=21046554) +1792 train 7.399912 (lr=1.7500e-04) (hash(x)=27285635) +1793 train 7.346961 (lr=1.7500e-04) (hash(x)=25454371) +1794 train 7.404429 (lr=1.7500e-04) (hash(x)=26486575) +1795 train 6.893912 (lr=1.7500e-04) (hash(x)=18773877) +1796 train 7.051301 (lr=1.7500e-04) (hash(x)=22506761) +1797 train 7.301764 (lr=1.7500e-04) (hash(x)=24645168) +1798 train 7.417751 (lr=1.7500e-04) (hash(x)=25046236) +1799 train 7.459326 (lr=1.7500e-04) (hash(x)=26321539) +1800 val loss 7.3155 +1800 val perplexity 1503.4302 +1800 train 7.252061 (lr=1.7500e-04) (hash(x)=24602494) +1801 train 7.404080 (lr=1.7500e-04) (hash(x)=25722713) +1802 train 7.156235 (lr=1.7500e-04) (hash(x)=23711219) +1803 train 7.269120 (lr=1.7500e-04) (hash(x)=22850804) +1804 train 7.634384 (lr=1.7500e-04) (hash(x)=25829388) +1805 train 7.118597 (lr=1.7500e-04) (hash(x)=22503524) +1806 train 7.411509 (lr=1.7500e-04) (hash(x)=26669453) +1807 train 7.323769 (lr=1.7500e-04) (hash(x)=27807872) +1808 train 7.340094 (lr=1.7500e-04) (hash(x)=23543560) +1809 train 7.467033 (lr=1.7500e-04) (hash(x)=25845590) +1810 train 7.236911 (lr=1.7500e-04) (hash(x)=23026635) +1811 train 7.206384 (lr=1.7500e-04) (hash(x)=25545137) +1812 train 7.674138 (lr=1.7500e-04) (hash(x)=27746841) +1813 train 7.113590 (lr=1.7500e-04) (hash(x)=25471231) +1814 train 7.246363 (lr=1.7500e-04) (hash(x)=24333204) +1815 train 7.120378 (lr=1.7500e-04) (hash(x)=21555364) +1816 train 7.326211 (lr=1.7500e-04) (hash(x)=26317977) +1817 train 7.378236 (lr=1.7500e-04) (hash(x)=24474988) +1818 train 7.030022 (lr=1.7500e-04) (hash(x)=21975953) +1819 train 7.637975 (lr=1.7500e-04) (hash(x)=27243798) +1820 train 7.273190 (lr=1.7500e-04) (hash(x)=25097367) +1821 train 7.176984 (lr=1.7500e-04) (hash(x)=24419085) +1822 train 7.133411 (lr=1.7500e-04) (hash(x)=23058837) +1823 train 7.264974 (lr=1.7500e-04) (hash(x)=26325324) +1824 train 7.013547 (lr=1.7500e-04) (hash(x)=20581023) +1825 train 7.331069 (lr=1.7500e-04) (hash(x)=24822111) +1826 train 7.099934 (lr=1.7500e-04) (hash(x)=24336304) +1827 train 7.283438 (lr=1.7500e-04) (hash(x)=26228728) +1828 train 7.383504 (lr=1.7500e-04) (hash(x)=26445781) +1829 train 7.452469 (lr=1.7500e-04) (hash(x)=24707042) +1830 train 7.735935 (lr=1.7500e-04) (hash(x)=27882744) +1831 train 7.243529 (lr=1.7500e-04) (hash(x)=24956294) +1832 train 7.024002 (lr=1.7500e-04) (hash(x)=20984728) +1833 train 7.041482 (lr=1.7500e-04) (hash(x)=23424737) +1834 train 7.469835 (lr=1.7500e-04) (hash(x)=26207120) +1835 train 7.482564 (lr=1.7500e-04) (hash(x)=25592289) +1836 train 7.146789 (lr=1.7500e-04) (hash(x)=24326649) +1837 train 7.277175 (lr=1.7500e-04) (hash(x)=26826109) +1838 train 7.259720 (lr=1.7500e-04) (hash(x)=24759294) +1839 train 7.283995 (lr=1.7500e-04) (hash(x)=24429389) +1840 train 7.258388 (lr=1.7500e-04) (hash(x)=25537519) +1841 train 7.229547 (lr=1.7500e-04) (hash(x)=24747421) +1842 train 7.157835 (lr=1.7500e-04) (hash(x)=23079065) +1843 train 7.566345 (lr=1.7500e-04) (hash(x)=28733708) +1844 train 7.272827 (lr=1.7500e-04) (hash(x)=23937742) +1845 train 7.613118 (lr=1.7500e-04) (hash(x)=29704803) +1846 train 7.766165 (lr=1.7500e-04) (hash(x)=34617155) +1847 train 7.468051 (lr=1.7500e-04) (hash(x)=27929846) +1848 train 7.787207 (lr=1.7500e-04) (hash(x)=28280878) +1849 train 6.862955 (lr=1.7500e-04) (hash(x)=18961171) +1850 val loss 7.3384 +1850 val perplexity 1538.2231 +1850 train 7.435445 (lr=1.7500e-04) (hash(x)=27146015) +1851 train 7.179801 (lr=1.7500e-04) (hash(x)=22417476) +1852 train 7.358277 (lr=1.7500e-04) (hash(x)=24583152) +1853 train 7.388889 (lr=1.7500e-04) (hash(x)=26364120) +1854 train 7.583726 (lr=1.7500e-04) (hash(x)=25946767) +1855 train 7.409868 (lr=1.7500e-04) (hash(x)=25282897) +1856 train 7.339934 (lr=1.7500e-04) (hash(x)=25154557) +1857 train 7.045056 (lr=1.7500e-04) (hash(x)=22082503) +1858 train 7.069057 (lr=1.7500e-04) (hash(x)=23974606) +1859 train 7.221738 (lr=1.7500e-04) (hash(x)=22278062) +1860 train 7.182041 (lr=1.7500e-04) (hash(x)=19509639) +1861 train 7.409897 (lr=1.7500e-04) (hash(x)=24271468) +1862 train 7.001134 (lr=1.7500e-04) (hash(x)=21943809) +1863 train 7.278357 (lr=1.7500e-04) (hash(x)=26802508) +1864 train 7.871377 (lr=1.7500e-04) (hash(x)=34178409) +1865 train 7.984819 (lr=1.7500e-04) (hash(x)=33468379) +1866 train 7.168037 (lr=1.7500e-04) (hash(x)=22109262) +1867 train 6.917213 (lr=1.7500e-04) (hash(x)=22094832) +1868 train 7.217259 (lr=1.7500e-04) (hash(x)=24016953) +1869 train 7.479749 (lr=1.7500e-04) (hash(x)=26759850) +1870 train 7.315259 (lr=1.7500e-04) (hash(x)=23570779) +1871 train 7.689394 (lr=1.7500e-04) (hash(x)=28390416) +1872 train 7.691836 (lr=1.7500e-04) (hash(x)=26215770) +1873 train 7.556175 (lr=1.7500e-04) (hash(x)=22727956) +1874 train 7.363416 (lr=1.7500e-04) (hash(x)=21304587) +1875 train 7.649068 (lr=1.7500e-04) (hash(x)=26379331) +1876 train 7.736463 (lr=1.7500e-04) (hash(x)=25252419) +1877 train 7.547063 (lr=1.7500e-04) (hash(x)=25048158) +1878 train 7.512311 (lr=1.7500e-04) (hash(x)=23588991) +1879 train 7.529118 (lr=1.7500e-04) (hash(x)=26292451) +1880 train 7.395192 (lr=1.7500e-04) (hash(x)=23617086) +1881 train 7.268228 (lr=1.7500e-04) (hash(x)=23336031) +1882 train 7.249311 (lr=1.7500e-04) (hash(x)=19198742) +1883 train 7.950706 (lr=1.7500e-04) (hash(x)=26301866) +1884 train 7.922190 (lr=1.7500e-04) (hash(x)=30114703) +1885 train 7.418402 (lr=1.7500e-04) (hash(x)=26687040) +1886 train 7.221485 (lr=1.7500e-04) (hash(x)=25810717) +1887 train 7.052631 (lr=1.7500e-04) (hash(x)=22915344) +1888 train 7.414673 (lr=1.7500e-04) (hash(x)=27046189) +1889 train 7.067665 (lr=1.7500e-04) (hash(x)=19831900) +1890 train 7.433966 (lr=1.7500e-04) (hash(x)=27786987) +1891 train 7.293914 (lr=1.7500e-04) (hash(x)=25448318) +1892 train 7.300832 (lr=1.7500e-04) (hash(x)=25166953) +1893 train 7.247640 (lr=1.7500e-04) (hash(x)=24993116) +1894 train 7.332078 (lr=1.7500e-04) (hash(x)=25748002) +1895 train 7.500565 (lr=1.7500e-04) (hash(x)=24744383) +1896 train 7.290212 (lr=1.7500e-04) (hash(x)=25560120) +1897 train 7.105012 (lr=1.7500e-04) (hash(x)=23731849) +1898 train 7.102249 (lr=1.7500e-04) (hash(x)=24115851) +1899 train 7.126946 (lr=1.7500e-04) (hash(x)=22835201) +1900 val loss 7.2697 +1900 val perplexity 1436.0717 +1900 train 6.891388 (lr=1.7500e-04) (hash(x)=21927896) +1901 train 7.300796 (lr=1.7500e-04) (hash(x)=24652361) +1902 train 7.513950 (lr=1.7500e-04) (hash(x)=27332405) +1903 train 7.325350 (lr=1.7500e-04) (hash(x)=26284678) +1904 train 7.228708 (lr=1.7500e-04) (hash(x)=23441305) +1905 train 7.353508 (lr=1.7500e-04) (hash(x)=27522881) +1906 train 7.400920 (lr=1.7500e-04) (hash(x)=25521191) +1907 train 7.190783 (lr=1.7500e-04) (hash(x)=24745936) +1908 train 7.083284 (lr=1.7500e-04) (hash(x)=21653364) +1909 train 7.110172 (lr=1.7500e-04) (hash(x)=21973969) +1910 train 7.134311 (lr=1.7500e-04) (hash(x)=24318192) +1911 train 7.091020 (lr=1.7500e-04) (hash(x)=21654269) +1912 train 7.148843 (lr=1.7500e-04) (hash(x)=24142904) +1913 train 7.026985 (lr=1.7500e-04) (hash(x)=21708739) +1914 train 7.282883 (lr=1.7500e-04) (hash(x)=22937923) +1915 train 7.860500 (lr=1.7500e-04) (hash(x)=32387999) +1916 train 8.076729 (lr=1.7500e-04) (hash(x)=28958671) +1917 train 8.102009 (lr=1.7500e-04) (hash(x)=32662682) +1918 train 7.995164 (lr=1.7500e-04) (hash(x)=31364539) +1919 train 8.068294 (lr=1.7500e-04) (hash(x)=29466268) +1920 train 8.043139 (lr=1.7500e-04) (hash(x)=31407564) +1921 train 7.894744 (lr=1.7500e-04) (hash(x)=28372973) +1922 train 8.014940 (lr=1.7500e-04) (hash(x)=28620993) +1923 train 8.051944 (lr=1.7500e-04) (hash(x)=30736727) +1924 train 7.956504 (lr=1.7500e-04) (hash(x)=30370374) +1925 train 7.910148 (lr=1.7500e-04) (hash(x)=29935562) +1926 train 7.917135 (lr=1.7500e-04) (hash(x)=30528627) +1927 train 7.950626 (lr=1.7500e-04) (hash(x)=32616762) +1928 train 7.800096 (lr=1.7500e-04) (hash(x)=29150044) +1929 train 7.936894 (lr=1.7500e-04) (hash(x)=32861403) +1930 train 7.879248 (lr=1.7500e-04) (hash(x)=31053918) +1931 train 7.782442 (lr=1.7500e-04) (hash(x)=29358578) +1932 train 7.874196 (lr=1.7500e-04) (hash(x)=31521292) +1933 train 7.838950 (lr=1.7500e-04) (hash(x)=31218966) +1934 train 7.838428 (lr=1.7500e-04) (hash(x)=31811872) +1935 train 7.999773 (lr=1.7500e-04) (hash(x)=32201138) +1936 train 7.754974 (lr=1.7500e-04) (hash(x)=28631348) +1937 train 7.827542 (lr=1.7500e-04) (hash(x)=30545133) +1938 train 7.869571 (lr=1.7500e-04) (hash(x)=32136080) +1939 train 7.968666 (lr=1.7500e-04) (hash(x)=30041621) +1940 train 7.759960 (lr=1.7500e-04) (hash(x)=30537181) +1941 train 7.776051 (lr=1.7500e-04) (hash(x)=30371023) +1942 train 7.913644 (lr=1.7500e-04) (hash(x)=30734634) +1943 train 7.819781 (lr=1.7500e-04) (hash(x)=33683468) +1944 train 7.855495 (lr=1.7500e-04) (hash(x)=30472451) +1945 train 7.714892 (lr=1.7500e-04) (hash(x)=29809830) +1946 train 7.497511 (lr=1.7500e-04) (hash(x)=26077593) +1947 train 7.499541 (lr=1.7500e-04) (hash(x)=26837755) +1948 train 7.469617 (lr=1.7500e-04) (hash(x)=23910920) +1949 train 7.477601 (lr=1.7500e-04) (hash(x)=26084089) +1950 val loss 7.4004 +1950 val perplexity 1636.7125 +1950 train 7.579003 (lr=1.7500e-04) (hash(x)=26963533) +1951 train 7.446693 (lr=1.7500e-04) (hash(x)=27498125) +1952 train 7.634892 (lr=1.7500e-04) (hash(x)=29512508) +1953 train 7.881305 (lr=1.7500e-04) (hash(x)=34478395) +1954 train 7.529130 (lr=1.7500e-04) (hash(x)=25357046) +1955 train 7.325942 (lr=1.7500e-04) (hash(x)=22372507) +1956 train 7.294852 (lr=1.7500e-04) (hash(x)=24501779) +1957 train 7.372209 (lr=1.7500e-04) (hash(x)=25638879) +1958 train 7.223335 (lr=1.7500e-04) (hash(x)=24243109) +1959 train 7.190428 (lr=1.7500e-04) (hash(x)=25164318) +1960 train 7.381162 (lr=1.7500e-04) (hash(x)=24139533) +1961 train 7.395658 (lr=1.7500e-04) (hash(x)=27271900) +1962 train 7.236073 (lr=1.7500e-04) (hash(x)=24869232) +1963 train 7.385403 (lr=1.7500e-04) (hash(x)=26562947) +1964 train 7.270792 (lr=1.7500e-04) (hash(x)=26477326) +1965 train 7.378208 (lr=1.7500e-04) (hash(x)=24917192) +1966 train 7.154031 (lr=1.7500e-04) (hash(x)=23110147) +1967 train 7.259278 (lr=1.7500e-04) (hash(x)=25690221) +1968 train 7.739319 (lr=1.7500e-04) (hash(x)=26999273) +1969 train 7.359890 (lr=1.7500e-04) (hash(x)=24807841) +1970 train 7.249238 (lr=1.7500e-04) (hash(x)=23918831) +1971 train 7.174696 (lr=1.7500e-04) (hash(x)=21947305) +1972 train 7.242876 (lr=1.7500e-04) (hash(x)=22874486) +1973 train 7.182477 (lr=1.7500e-04) (hash(x)=22195089) +1974 train 7.320779 (lr=1.7500e-04) (hash(x)=25345359) +1975 train 7.488921 (lr=1.7500e-04) (hash(x)=29031550) +1976 train 7.432793 (lr=1.7500e-04) (hash(x)=29947423) +1977 train 7.621629 (lr=1.7500e-04) (hash(x)=29395823) +1978 train 7.366447 (lr=1.7500e-04) (hash(x)=26968216) +1979 train 7.394628 (lr=1.7500e-04) (hash(x)=26551589) +1980 train 7.386810 (lr=1.7500e-04) (hash(x)=25657210) +1981 train 7.315814 (lr=1.7500e-04) (hash(x)=23689487) +1982 train 7.447517 (lr=1.7500e-04) (hash(x)=25744240) +1983 train 7.433697 (lr=1.7500e-04) (hash(x)=24094093) +1984 train 7.121277 (lr=1.7500e-04) (hash(x)=21724872) +1985 train 7.184175 (lr=1.7500e-04) (hash(x)=24106453) +1986 train 7.246395 (lr=1.7500e-04) (hash(x)=25004577) +1987 train 7.271918 (lr=1.7500e-04) (hash(x)=23639076) +1988 train 7.546876 (lr=1.7500e-04) (hash(x)=29408797) +1989 train 7.202672 (lr=1.7500e-04) (hash(x)=25107314) +1990 train 9.861073 (lr=1.7500e-04) (hash(x)=49896019) +1991 train 11.231833 (lr=1.7500e-04) (hash(x)=61455960) +1992 train 10.842163 (lr=1.7500e-04) (hash(x)=63788199) +1993 train 10.707119 (lr=1.7500e-04) (hash(x)=63899424) +1994 train 10.290471 (lr=1.7500e-04) (hash(x)=66412689) +1995 train 9.796231 (lr=1.7500e-04) (hash(x)=65636572) +1996 train 9.722178 (lr=1.7500e-04) (hash(x)=69649789) +1997 train 9.392444 (lr=1.7500e-04) (hash(x)=71578682) +1998 train 8.976417 (lr=1.7500e-04) (hash(x)=58341730) +1999 train 9.021538 (lr=1.7500e-04) (hash(x)=61104710) +2000 val loss 8.8873 +2000 val perplexity 7239.6226 +2000 train 8.878765 (lr=1.7500e-04) (hash(x)=52865322) +2001 train 9.087209 (lr=1.7500e-04) (hash(x)=23633693) +2002 train 8.783666 (lr=1.7500e-04) (hash(x)=25297571) +2003 train 8.962546 (lr=1.7500e-04) (hash(x)=24123821) +2004 train 8.055229 (lr=1.7500e-04) (hash(x)=20161517) +2005 train 7.915806 (lr=1.7500e-04) (hash(x)=19919984) +2006 train 7.905309 (lr=1.7500e-04) (hash(x)=18626507) +2007 train 8.071975 (lr=1.7500e-04) (hash(x)=20881126) +2008 train 8.195664 (lr=1.7500e-04) (hash(x)=26261448) +2009 train 8.138931 (lr=1.7500e-04) (hash(x)=27528050) +2010 train 8.063903 (lr=1.7500e-04) (hash(x)=26692097) +2011 train 7.640123 (lr=1.7500e-04) (hash(x)=23209969) +2012 train 7.569327 (lr=1.7500e-04) (hash(x)=26083446) +2013 train 7.692215 (lr=1.7500e-04) (hash(x)=28426467) +2014 train 7.459048 (lr=1.7500e-04) (hash(x)=26158154) +2015 train 7.569927 (lr=1.7500e-04) (hash(x)=26920243) +2016 train 7.260821 (lr=1.7500e-04) (hash(x)=21365321) +2017 train 7.381881 (lr=1.7500e-04) (hash(x)=25730699) +2018 train 7.473922 (lr=1.7500e-04) (hash(x)=25177106) +2019 train 7.374790 (lr=1.7500e-04) (hash(x)=26127756) +2020 train 6.905443 (lr=1.7500e-04) (hash(x)=19770037) +2021 train 7.353180 (lr=1.7500e-04) (hash(x)=26479346) +2022 train 7.354134 (lr=1.7500e-04) (hash(x)=25967643) +2023 train 7.235347 (lr=1.7500e-04) (hash(x)=21970343) +2024 train 7.495203 (lr=1.7500e-04) (hash(x)=26449648) +2025 train 7.351712 (lr=1.7500e-04) (hash(x)=24874094) +2026 train 7.036739 (lr=1.7500e-04) (hash(x)=21399697) +2027 train 7.246967 (lr=1.7500e-04) (hash(x)=24097897) +2028 train 7.275046 (lr=1.7500e-04) (hash(x)=24453548) +2029 train 7.431267 (lr=1.7500e-04) (hash(x)=26692093) +2030 train 7.257903 (lr=1.7500e-04) (hash(x)=27217002) +2031 train 7.639954 (lr=1.7500e-04) (hash(x)=31676352) +2032 train 7.293742 (lr=1.7500e-04) (hash(x)=23396350) +2033 train 7.353851 (lr=1.7500e-04) (hash(x)=26245173) +2034 train 7.358721 (lr=1.7500e-04) (hash(x)=24821033) +2035 train 7.379108 (lr=1.7500e-04) (hash(x)=23908053) +2036 train 7.130828 (lr=1.7500e-04) (hash(x)=23469373) +2037 train 7.154820 (lr=1.7500e-04) (hash(x)=24102198) +2038 train 7.224567 (lr=1.7500e-04) (hash(x)=24712135) +2039 train 7.448602 (lr=1.7500e-04) (hash(x)=25600562) +2040 train 7.375418 (lr=1.7500e-04) (hash(x)=23193393) +2041 train 7.373634 (lr=1.7500e-04) (hash(x)=24776954) +2042 train 7.472647 (lr=1.7500e-04) (hash(x)=28066546) +2043 train 7.080920 (lr=1.7500e-04) (hash(x)=23549168) +2044 train 7.118465 (lr=1.7500e-04) (hash(x)=22681487) +2045 train 7.316505 (lr=1.7500e-04) (hash(x)=26663184) +2046 train 7.258668 (lr=1.7500e-04) (hash(x)=23320809) +2047 train 7.146075 (lr=1.7500e-04) (hash(x)=22022924) +2048 train 7.489425 (lr=1.7500e-04) (hash(x)=27960930) +2049 train 7.263162 (lr=1.7500e-04) (hash(x)=24899178) +2050 val loss 7.2866 +2050 val perplexity 1460.6201 +2050 train 7.186905 (lr=1.7500e-04) (hash(x)=24450711) +2051 train 7.127278 (lr=1.7500e-04) (hash(x)=23294980) +2052 train 7.064339 (lr=1.7500e-04) (hash(x)=23243665) +2053 train 6.910266 (lr=1.7500e-04) (hash(x)=21004461) +2054 train 7.247925 (lr=1.7500e-04) (hash(x)=24493583) +2055 train 7.182191 (lr=1.7500e-04) (hash(x)=22777085) +2056 train 7.108992 (lr=1.7500e-04) (hash(x)=25169889) +2057 train 7.758269 (lr=1.7500e-04) (hash(x)=28395880) +2058 train 7.677049 (lr=1.7500e-04) (hash(x)=29603726) +2059 train 7.342459 (lr=1.7500e-04) (hash(x)=26271115) +2060 train 7.321035 (lr=1.7500e-04) (hash(x)=25616212) +2061 train 7.430949 (lr=1.7500e-04) (hash(x)=26398325) +2062 train 7.115921 (lr=1.7500e-04) (hash(x)=23836586) +2063 train 6.981148 (lr=1.7500e-04) (hash(x)=21727744) +2064 train 7.290366 (lr=1.7500e-04) (hash(x)=25183195) +2065 train 7.412010 (lr=1.7500e-04) (hash(x)=27108132) +2066 train 7.067118 (lr=1.7500e-04) (hash(x)=20987812) +2067 train 7.412223 (lr=1.7500e-04) (hash(x)=22729318) +2068 train 7.209024 (lr=1.7500e-04) (hash(x)=23129709) +2069 train 7.776535 (lr=1.7500e-04) (hash(x)=32820084) +2070 train 7.842569 (lr=1.7500e-04) (hash(x)=33763489) +2071 train 7.268594 (lr=1.7500e-04) (hash(x)=20701998) +2072 train 7.460967 (lr=1.7500e-04) (hash(x)=27765988) +2073 train 7.215894 (lr=1.7500e-04) (hash(x)=24157446) +2074 train 7.168656 (lr=1.7500e-04) (hash(x)=22014978) +2075 train 7.671310 (lr=1.7500e-04) (hash(x)=27928398) +2076 train 7.521626 (lr=1.7500e-04) (hash(x)=27880142) +2077 train 7.832613 (lr=1.7500e-04) (hash(x)=34991795) +2078 train 7.397530 (lr=1.7500e-04) (hash(x)=25944128) +2079 train 7.131896 (lr=1.7500e-04) (hash(x)=20863982) +2080 train 7.524357 (lr=1.7500e-04) (hash(x)=28036097) +2081 train 7.555326 (lr=1.7500e-04) (hash(x)=25813615) +2082 train 6.985967 (lr=1.7500e-04) (hash(x)=22862316) +2083 train 7.056587 (lr=1.7500e-04) (hash(x)=22827054) +2084 train 7.151535 (lr=1.7500e-04) (hash(x)=23996531) +2085 train 7.270355 (lr=1.7500e-04) (hash(x)=25756087) +2086 train 7.311693 (lr=1.7500e-04) (hash(x)=23165889) +2087 train 7.524621 (lr=1.7500e-04) (hash(x)=25084926) +2088 train 7.336823 (lr=1.7500e-04) (hash(x)=26063862) +2089 train 7.366460 (lr=1.7500e-04) (hash(x)=27843638) +2090 train 7.636035 (lr=1.7500e-04) (hash(x)=27375554) +2091 train 7.405666 (lr=1.7500e-04) (hash(x)=25540961) +2092 train 7.180383 (lr=1.7500e-04) (hash(x)=22933785) +2093 train 7.317594 (lr=1.7500e-04) (hash(x)=23996956) +2094 train 7.088571 (lr=1.7500e-04) (hash(x)=22915854) +2095 train 7.338652 (lr=1.7500e-04) (hash(x)=24412897) +2096 train 7.358082 (lr=1.7500e-04) (hash(x)=25152336) +2097 train 7.641376 (lr=1.7500e-04) (hash(x)=29525589) +2098 train 7.466746 (lr=1.7500e-04) (hash(x)=26435656) +2099 train 7.357503 (lr=1.7500e-04) (hash(x)=26269869) +2100 val loss 7.2790 +2100 val perplexity 1449.4967 +2100 train 7.102728 (lr=1.7500e-04) (hash(x)=23856783) +2101 train 7.374040 (lr=1.7500e-04) (hash(x)=26039611) +2102 train 7.113039 (lr=1.7500e-04) (hash(x)=25048861) +2103 train 7.248283 (lr=1.7500e-04) (hash(x)=25434913) +2104 train 7.420436 (lr=1.7500e-04) (hash(x)=24203891) +2105 train 7.281032 (lr=1.7500e-04) (hash(x)=26016998) +2106 train 7.375995 (lr=1.7500e-04) (hash(x)=23986767) +2107 train 7.285831 (lr=1.7500e-04) (hash(x)=25157653) +2108 train 7.427448 (lr=1.7500e-04) (hash(x)=30193751) +2109 train 7.285177 (lr=1.7500e-04) (hash(x)=22630574) +2110 train 7.184606 (lr=1.7500e-04) (hash(x)=23475467) +2111 train 7.436821 (lr=1.7500e-04) (hash(x)=26302544) +2112 train 7.267076 (lr=1.7500e-04) (hash(x)=21276592) +2113 train 7.489500 (lr=1.7500e-04) (hash(x)=27566393) +2114 train 7.243691 (lr=1.7500e-04) (hash(x)=25028015) +2115 train 7.010787 (lr=1.7500e-04) (hash(x)=22010703) +2116 train 7.339543 (lr=1.7500e-04) (hash(x)=23711709) +2117 train 7.402775 (lr=1.7500e-04) (hash(x)=26105026) +2118 train 7.816711 (lr=1.7500e-04) (hash(x)=34433894) +2119 train 7.874696 (lr=1.7500e-04) (hash(x)=34976197) +2120 train 7.339486 (lr=1.7500e-04) (hash(x)=27690727) +2121 train 7.186357 (lr=1.7500e-04) (hash(x)=24368234) +2122 train 7.195644 (lr=1.7500e-04) (hash(x)=25095726) +2123 train 7.376578 (lr=1.7500e-04) (hash(x)=28248301) +2124 train 7.127859 (lr=1.7500e-04) (hash(x)=23322302) +2125 train 7.558547 (lr=1.7500e-04) (hash(x)=26416200) +2126 train 7.207242 (lr=1.7500e-04) (hash(x)=26577567) +2127 train 7.263257 (lr=1.7500e-04) (hash(x)=23870805) +2128 train 7.185382 (lr=1.7500e-04) (hash(x)=25440544) +2129 train 7.306301 (lr=1.7500e-04) (hash(x)=25795021) +2130 train 7.160797 (lr=1.7500e-04) (hash(x)=20896402) +2131 train 7.200368 (lr=1.7500e-04) (hash(x)=24457252) +2132 train 7.267805 (lr=1.7500e-04) (hash(x)=25926760) +2133 train 7.147977 (lr=1.7500e-04) (hash(x)=23503725) +2134 train 7.714097 (lr=1.7500e-04) (hash(x)=28728828) +2135 train 7.221318 (lr=1.7500e-04) (hash(x)=25041103) +2136 train 7.232296 (lr=1.7500e-04) (hash(x)=22863770) +2137 train 7.033109 (lr=1.7500e-04) (hash(x)=23037755) +2138 train 7.287774 (lr=1.7500e-04) (hash(x)=25848413) +2139 train 7.352206 (lr=1.7500e-04) (hash(x)=25998487) +2140 train 7.206957 (lr=1.7500e-04) (hash(x)=22754440) +2141 train 7.462009 (lr=1.7500e-04) (hash(x)=27705382) +2142 train 7.466367 (lr=1.7500e-04) (hash(x)=27629095) +2143 train 7.360921 (lr=1.7500e-04) (hash(x)=26041745) +2144 train 7.133173 (lr=1.7500e-04) (hash(x)=21909712) +2145 train 7.307495 (lr=1.7500e-04) (hash(x)=24353905) +2146 train 7.244003 (lr=1.7500e-04) (hash(x)=24482587) +2147 train 7.358144 (lr=1.7500e-04) (hash(x)=27249810) +2148 train 7.480665 (lr=1.7500e-04) (hash(x)=26709938) +2149 train 7.143992 (lr=1.7500e-04) (hash(x)=23831457) +2150 val loss 7.2601 +2150 val perplexity 1422.3383 +2150 train 7.512866 (lr=1.7500e-04) (hash(x)=29776243) +2151 train 7.005592 (lr=1.7500e-04) (hash(x)=24068619) +2152 train 7.228649 (lr=1.7500e-04) (hash(x)=22208671) +2153 train 7.381818 (lr=1.7500e-04) (hash(x)=26680905) +2154 train 7.259697 (lr=1.7500e-04) (hash(x)=23567808) +2155 train 7.514409 (lr=1.7500e-04) (hash(x)=26359528) +2156 train 7.299438 (lr=1.7500e-04) (hash(x)=23787652) +2157 train 7.582390 (lr=1.7500e-04) (hash(x)=28347177) +2158 train 7.252516 (lr=1.7500e-04) (hash(x)=25266519) +2159 train 7.188268 (lr=1.7500e-04) (hash(x)=25441262) +2160 train 7.104891 (lr=1.7500e-04) (hash(x)=23959943) +2161 train 7.345355 (lr=1.7500e-04) (hash(x)=27888093) +2162 train 7.232761 (lr=1.7500e-04) (hash(x)=25547833) +2163 train 7.166232 (lr=1.7500e-04) (hash(x)=24413659) +2164 train 8.576993 (lr=1.7500e-04) (hash(x)=34397626) +2165 train 7.116406 (lr=1.7500e-04) (hash(x)=21159323) +2166 train 7.322084 (lr=1.7500e-04) (hash(x)=25360269) +2167 train 7.369618 (lr=1.7500e-04) (hash(x)=29181867) +2168 train 7.188710 (lr=1.7500e-04) (hash(x)=22501613) +2169 train 7.250832 (lr=1.7500e-04) (hash(x)=26469077) +2170 train 7.234340 (lr=1.7500e-04) (hash(x)=26665118) +2171 train 7.879925 (lr=1.7500e-04) (hash(x)=31551575) +2172 train 7.175100 (lr=1.7500e-04) (hash(x)=24803935) +2173 train 7.069139 (lr=1.7500e-04) (hash(x)=20896465) +2174 train 7.506363 (lr=1.7500e-04) (hash(x)=25702284) +2175 train 7.527375 (lr=1.7500e-04) (hash(x)=27093757) +2176 train 7.301227 (lr=1.7500e-04) (hash(x)=26024255) +2177 train 7.399739 (lr=1.7500e-04) (hash(x)=26443521) +2178 train 7.369077 (lr=1.7500e-04) (hash(x)=25478467) +2179 train 7.238136 (lr=1.7500e-04) (hash(x)=23624298) +2180 train 7.315034 (lr=1.7500e-04) (hash(x)=27304178) +2181 train 7.092704 (lr=1.7500e-04) (hash(x)=23016570) +2182 train 7.083660 (lr=1.7500e-04) (hash(x)=21073756) +2183 train 7.184229 (lr=1.7500e-04) (hash(x)=25150275) +2184 train 7.010545 (lr=1.7500e-04) (hash(x)=21004187) +2185 train 7.248009 (lr=1.7500e-04) (hash(x)=25876062) +2186 train 7.166323 (lr=1.7500e-04) (hash(x)=24221275) +2187 train 7.476401 (lr=1.7500e-04) (hash(x)=26239886) +2188 train 7.164824 (lr=1.7500e-04) (hash(x)=23299261) +2189 train 7.595573 (lr=1.7500e-04) (hash(x)=31024703) +2190 train 7.719083 (lr=1.7500e-04) (hash(x)=30084774) +2191 train 7.995024 (lr=1.7500e-04) (hash(x)=33457102) +2192 train 7.194900 (lr=1.7500e-04) (hash(x)=22423723) +2193 train 7.198321 (lr=1.7500e-04) (hash(x)=21989055) +2194 train 7.233654 (lr=1.7500e-04) (hash(x)=23286499) +2195 train 7.194966 (lr=1.7500e-04) (hash(x)=17499738) +2196 train 7.220016 (lr=1.7500e-04) (hash(x)=25329557) +2197 train 7.110315 (lr=1.7500e-04) (hash(x)=24195578) +2198 train 7.373774 (lr=1.7500e-04) (hash(x)=26646383) +2199 train 7.278352 (lr=1.7500e-04) (hash(x)=25755322) +2200 val loss 7.2605 +2200 val perplexity 1422.9121 +2200 train 7.287003 (lr=1.7500e-04) (hash(x)=27592223) +2201 train 7.502287 (lr=1.7500e-04) (hash(x)=26164625) +2202 train 7.358337 (lr=1.7500e-04) (hash(x)=21856341) +2203 train 7.208837 (lr=1.7500e-04) (hash(x)=23722795) +2204 train 7.306488 (lr=1.7500e-04) (hash(x)=25409645) +2205 train 7.251900 (lr=1.7500e-04) (hash(x)=23415339) +2206 train 7.216796 (lr=1.7500e-04) (hash(x)=24147928) +2207 train 7.129631 (lr=1.7500e-04) (hash(x)=23630794) +2208 train 7.251634 (lr=1.7500e-04) (hash(x)=27361452) +2209 train 7.249150 (lr=1.7500e-04) (hash(x)=25632158) +2210 train 7.120601 (lr=1.7500e-04) (hash(x)=21159789) +2211 train 7.203384 (lr=1.7500e-04) (hash(x)=23374168) +2212 train 7.247551 (lr=1.7500e-04) (hash(x)=24844739) +2213 train 7.177190 (lr=1.7500e-04) (hash(x)=23461285) +2214 train 7.215257 (lr=1.7500e-04) (hash(x)=27958481) +2215 train 7.109859 (lr=1.7500e-04) (hash(x)=25167987) +2216 train 7.298899 (lr=1.7500e-04) (hash(x)=22873204) +2217 train 7.833464 (lr=1.7500e-04) (hash(x)=31038116) +2218 train 7.349905 (lr=1.7500e-04) (hash(x)=28883155) +2219 train 7.226111 (lr=1.7500e-04) (hash(x)=30941010) +2220 train 7.227222 (lr=1.7500e-04) (hash(x)=24947521) +2221 train 7.271533 (lr=1.7500e-04) (hash(x)=22703293) +2222 train 7.229371 (lr=1.7500e-04) (hash(x)=23976007) +2223 train 7.161376 (lr=1.7500e-04) (hash(x)=24043224) +2224 train 7.085403 (lr=1.7500e-04) (hash(x)=23981093) +2225 train 7.243809 (lr=1.7500e-04) (hash(x)=26445994) +2226 train 7.506884 (lr=1.7500e-04) (hash(x)=27252393) +2227 train 7.485024 (lr=1.7500e-04) (hash(x)=29736627) +2228 train 7.414489 (lr=1.7500e-04) (hash(x)=24698933) +2229 train 7.074326 (lr=1.7500e-04) (hash(x)=24357840) +2230 train 7.223802 (lr=1.7500e-04) (hash(x)=25384498) +2231 train 7.409093 (lr=1.7500e-04) (hash(x)=24665411) +2232 train 7.240116 (lr=1.7500e-04) (hash(x)=24646352) +2233 train 7.240299 (lr=1.7500e-04) (hash(x)=25670741) +2234 train 7.260800 (lr=1.7500e-04) (hash(x)=26648242) +2235 train 7.506526 (lr=1.7500e-04) (hash(x)=27916043) +2236 train 7.200923 (lr=1.7500e-04) (hash(x)=25963100) +2237 train 7.296275 (lr=1.7500e-04) (hash(x)=27357379) +2238 train 7.104520 (lr=1.7500e-04) (hash(x)=21852360) +2239 train 7.041032 (lr=1.7500e-04) (hash(x)=17321657) +2240 train 7.006618 (lr=1.7500e-04) (hash(x)=18446645) +2241 train 6.775630 (lr=1.7500e-04) (hash(x)=17550988) +2242 train 7.213974 (lr=1.7500e-04) (hash(x)=27052347) +2243 train 7.069655 (lr=1.7500e-04) (hash(x)=23829833) +2244 train 7.334238 (lr=1.7500e-04) (hash(x)=27267264) +2245 train 7.546751 (lr=1.7500e-04) (hash(x)=24673611) +2246 train 7.471555 (lr=1.7500e-04) (hash(x)=25248507) +2247 train 7.752402 (lr=1.7500e-04) (hash(x)=27932591) +2248 train 7.561513 (lr=1.7500e-04) (hash(x)=26078877) +2249 train 7.635876 (lr=1.7500e-04) (hash(x)=26067367) +2250 val loss 7.2782 +2250 val perplexity 1448.3671 +2250 train 7.626129 (lr=1.7500e-04) (hash(x)=29143527) +2251 train 7.621311 (lr=1.7500e-04) (hash(x)=28206079) +2252 train 8.036813 (lr=1.7500e-04) (hash(x)=28894494) +2253 train 7.644231 (lr=1.7500e-04) (hash(x)=27977422) +2254 train 7.291687 (lr=1.7500e-04) (hash(x)=26446420) +2255 train 7.443260 (lr=1.7500e-04) (hash(x)=29447954) +2256 train 7.326514 (lr=1.7500e-04) (hash(x)=22181789) +2257 train 7.327090 (lr=1.7500e-04) (hash(x)=24976337) +2258 train 7.239911 (lr=1.7500e-04) (hash(x)=23277532) +2259 train 7.416482 (lr=1.7500e-04) (hash(x)=25935364) +2260 train 7.567772 (lr=1.7500e-04) (hash(x)=26988889) +2261 train 7.309517 (lr=1.7500e-04) (hash(x)=26887303) +2262 train 7.306627 (lr=1.7500e-04) (hash(x)=25021426) +2263 train 7.218328 (lr=1.7500e-04) (hash(x)=24621816) +2264 train 7.078532 (lr=1.7500e-04) (hash(x)=22132007) +2265 train 6.993567 (lr=1.7500e-04) (hash(x)=22648602) +2266 train 7.330093 (lr=1.7500e-04) (hash(x)=23132242) +2267 train 7.355133 (lr=1.7500e-04) (hash(x)=24070405) +2268 train 6.963108 (lr=1.7500e-04) (hash(x)=21412906) +2269 train 7.678708 (lr=1.7500e-04) (hash(x)=27547292) +2270 train 7.414362 (lr=1.7500e-04) (hash(x)=27740500) +2271 train 7.115111 (lr=1.7500e-04) (hash(x)=24682294) +2272 train 7.583771 (lr=1.7500e-04) (hash(x)=27969424) +2273 train 7.274547 (lr=1.7500e-04) (hash(x)=22172182) +2274 train 7.247815 (lr=1.7500e-04) (hash(x)=26485905) +2275 train 7.123451 (lr=1.7500e-04) (hash(x)=24050209) +2276 train 7.308086 (lr=1.7500e-04) (hash(x)=28802650) +2277 train 7.083973 (lr=1.7500e-04) (hash(x)=23644616) +2278 train 7.221791 (lr=1.7500e-04) (hash(x)=25409768) +2279 train 7.419178 (lr=1.7500e-04) (hash(x)=28057095) +2280 train 7.898727 (lr=1.7500e-04) (hash(x)=31689723) +2281 train 7.056335 (lr=1.7500e-04) (hash(x)=22252427) +2282 train 7.291514 (lr=1.7500e-04) (hash(x)=24142092) +2283 train 7.224096 (lr=1.7500e-04) (hash(x)=22523232) +2284 train 7.432955 (lr=1.7500e-04) (hash(x)=26017294) +2285 train 7.270387 (lr=1.7500e-04) (hash(x)=25025388) +2286 train 7.071904 (lr=1.7500e-04) (hash(x)=23819479) +2287 train 7.249362 (lr=1.7500e-04) (hash(x)=24547536) +2288 train 7.043660 (lr=1.7500e-04) (hash(x)=22622789) +2289 train 7.006102 (lr=1.7500e-04) (hash(x)=23874051) +2290 train 7.338245 (lr=1.7500e-04) (hash(x)=25015641) +2291 train 7.226556 (lr=1.7500e-04) (hash(x)=24978712) +2292 train 7.290103 (lr=1.7500e-04) (hash(x)=25311986) +2293 train 7.078478 (lr=1.7500e-04) (hash(x)=24298295) +2294 train 7.159990 (lr=1.7500e-04) (hash(x)=26481527) +2295 train 6.863525 (lr=1.7500e-04) (hash(x)=18987545) +2296 train 7.101540 (lr=1.7500e-04) (hash(x)=24617990) +2297 train 7.148328 (lr=1.7500e-04) (hash(x)=23903200) +2298 train 7.441468 (lr=1.7500e-04) (hash(x)=26278697) +2299 train 7.199335 (lr=1.7500e-04) (hash(x)=24092784) +2300 val loss 7.2371 +2300 val perplexity 1390.0366 +2300 train 7.125067 (lr=1.7500e-04) (hash(x)=22894919) +2301 train 7.225160 (lr=1.7500e-04) (hash(x)=24253964) +2302 train 7.173301 (lr=1.7500e-04) (hash(x)=23750610) +2303 train 7.198952 (lr=1.7500e-04) (hash(x)=26745063) +2304 train 7.034689 (lr=1.7500e-04) (hash(x)=21407001) +2305 train 7.404388 (lr=1.7500e-04) (hash(x)=26680082) +2306 train 7.302110 (lr=1.7500e-04) (hash(x)=26722122) +2307 train 7.151533 (lr=1.7500e-04) (hash(x)=22539112) +2308 train 6.947025 (lr=1.7500e-04) (hash(x)=19927356) +2309 train 7.063282 (lr=1.7500e-04) (hash(x)=21431267) +2310 train 7.017143 (lr=1.7500e-04) (hash(x)=21073487) +2311 train 7.006348 (lr=1.7500e-04) (hash(x)=21447406) +2312 train 7.001313 (lr=1.7500e-04) (hash(x)=22667253) +2313 train 6.970611 (lr=1.7500e-04) (hash(x)=20849089) +2314 train 6.962490 (lr=1.7500e-04) (hash(x)=19168351) +2315 train 6.975067 (lr=1.7500e-04) (hash(x)=21082139) +2316 train 6.971808 (lr=1.7500e-04) (hash(x)=21493530) +2317 train 6.912987 (lr=1.7500e-04) (hash(x)=19506447) +2318 train 7.046350 (lr=1.7500e-04) (hash(x)=23128797) +2319 train 7.146802 (lr=1.7500e-04) (hash(x)=24650655) +2320 train 6.900688 (lr=1.7500e-04) (hash(x)=21833080) +2321 train 7.468866 (lr=1.7500e-04) (hash(x)=26355512) +2322 train 7.605223 (lr=1.7500e-04) (hash(x)=26746363) +2323 train 7.064236 (lr=1.7500e-04) (hash(x)=22130721) +2324 train 7.427058 (lr=1.7500e-04) (hash(x)=28301752) +2325 train 7.230012 (lr=1.7500e-04) (hash(x)=26444359) +2326 train 7.623226 (lr=1.7500e-04) (hash(x)=24836130) +2327 train 7.927496 (lr=1.7500e-04) (hash(x)=26519976) +2328 train 9.190403 (lr=1.7500e-04) (hash(x)=35558906) +2329 train 7.672863 (lr=1.7500e-04) (hash(x)=30877729) +2330 train 7.545307 (lr=1.7500e-04) (hash(x)=28028485) +2331 train 7.669838 (lr=1.7500e-04) (hash(x)=25582440) +2332 train 7.969167 (lr=1.7500e-04) (hash(x)=29402491) +2333 train 7.318105 (lr=1.7500e-04) (hash(x)=25200284) +2334 train 7.268696 (lr=1.7500e-04) (hash(x)=26288480) +2335 train 7.074586 (lr=1.7500e-04) (hash(x)=20106514) +2336 train 7.049156 (lr=1.7500e-04) (hash(x)=22522123) +2337 train 7.061059 (lr=1.7500e-04) (hash(x)=23362041) +2338 train 7.149272 (lr=1.7500e-04) (hash(x)=26003099) +2339 train 7.219917 (lr=1.7500e-04) (hash(x)=25695510) +2340 train 7.184489 (lr=1.7500e-04) (hash(x)=27225904) +2341 train 6.951389 (lr=1.7500e-04) (hash(x)=21573008) +2342 train 7.394966 (lr=1.7500e-04) (hash(x)=21386628) +2343 train 7.161890 (lr=1.7500e-04) (hash(x)=20117808) +2344 train 7.285137 (lr=1.7500e-04) (hash(x)=21592790) +2345 train 7.187691 (lr=1.7500e-04) (hash(x)=19909192) +2346 train 7.351730 (lr=1.7500e-04) (hash(x)=22529262) +2347 train 7.374402 (lr=1.7500e-04) (hash(x)=24501900) +2348 train 7.186295 (lr=1.7500e-04) (hash(x)=25912171) +2349 train 7.278014 (lr=1.7500e-04) (hash(x)=25606665) +2350 val loss 7.2478 +2350 val perplexity 1405.0417 +2350 train 7.190958 (lr=1.7500e-04) (hash(x)=24487351) +2351 train 7.440280 (lr=1.7500e-04) (hash(x)=25510334) +2352 train 7.352050 (lr=1.7500e-04) (hash(x)=25357989) +2353 train 7.004707 (lr=1.7500e-04) (hash(x)=24656801) +2354 train 7.082573 (lr=1.7500e-04) (hash(x)=23312772) +2355 train 6.935115 (lr=1.7500e-04) (hash(x)=22099158) +2356 train 7.011407 (lr=1.7500e-04) (hash(x)=26507898) +2357 train 7.302219 (lr=1.7500e-04) (hash(x)=28351614) +2358 train 7.322404 (lr=1.7500e-04) (hash(x)=27489567) +2359 train 7.289704 (lr=1.7500e-04) (hash(x)=25749120) +2360 train 7.608125 (lr=1.7500e-04) (hash(x)=31711338) +2361 train 7.711919 (lr=1.7500e-04) (hash(x)=29645018) +2362 train 7.735731 (lr=1.7500e-04) (hash(x)=29713268) +2363 train 6.918474 (lr=1.7500e-04) (hash(x)=21720691) +2364 train 7.024248 (lr=1.7500e-04) (hash(x)=24316633) +2365 train 6.946715 (lr=1.7500e-04) (hash(x)=21597124) +2366 train 7.017239 (lr=1.7500e-04) (hash(x)=22520345) +2367 train 7.040054 (lr=1.7500e-04) (hash(x)=24357241) +2368 train 7.179105 (lr=1.7500e-04) (hash(x)=24085450) +2369 train 7.090643 (lr=1.7500e-04) (hash(x)=25136495) +2370 train 7.610562 (lr=1.7500e-04) (hash(x)=26073986) +2371 train 7.500825 (lr=1.7500e-04) (hash(x)=28911272) +2372 train 7.288621 (lr=1.7500e-04) (hash(x)=26667356) +2373 train 7.102656 (lr=1.7500e-04) (hash(x)=25225894) +2374 train 7.130004 (lr=1.7500e-04) (hash(x)=24404081) +2375 train 7.241380 (lr=1.7500e-04) (hash(x)=25584945) +2376 train 7.053429 (lr=1.7500e-04) (hash(x)=23831571) +2377 train 7.058812 (lr=1.7500e-04) (hash(x)=23521916) +2378 train 7.085161 (lr=1.7500e-04) (hash(x)=25318634) +2379 train 6.930646 (lr=1.7500e-04) (hash(x)=21847287) +2380 train 7.341435 (lr=1.7500e-04) (hash(x)=23877060) +2381 train 7.092487 (lr=1.7500e-04) (hash(x)=24069020) +2382 train 6.886500 (lr=1.7500e-04) (hash(x)=21724290) +2383 train 7.167057 (lr=1.7500e-04) (hash(x)=25198897) +2384 train 7.038049 (lr=1.7500e-04) (hash(x)=24109958) +2385 train 6.897629 (lr=1.7500e-04) (hash(x)=20122390) +2386 train 7.143428 (lr=1.7500e-04) (hash(x)=24062305) +2387 train 6.953128 (lr=1.7500e-04) (hash(x)=22436833) +2388 train 7.262611 (lr=1.7500e-04) (hash(x)=26013214) +2389 train 7.636681 (lr=1.7500e-04) (hash(x)=27691436) +2390 train 7.742146 (lr=1.7500e-04) (hash(x)=30802878) +2391 train 6.900301 (lr=1.7500e-04) (hash(x)=23475891) +2392 train 6.901399 (lr=1.7500e-04) (hash(x)=23118133) +2393 train 6.813959 (lr=1.7500e-04) (hash(x)=21469159) +2394 train 7.183591 (lr=1.7500e-04) (hash(x)=26444484) +2395 train 7.042942 (lr=1.7500e-04) (hash(x)=25083992) +2396 train 7.354573 (lr=1.7500e-04) (hash(x)=23461229) +2397 train 7.257078 (lr=1.7500e-04) (hash(x)=20441653) +2398 train 7.349007 (lr=1.7500e-04) (hash(x)=28024211) +2399 train 7.179512 (lr=1.7500e-04) (hash(x)=23644804) +2400 val loss 7.2318 +2400 val perplexity 1382.6823 +2400 train 7.005284 (lr=1.7500e-04) (hash(x)=26685301) +2401 train 6.861929 (lr=1.7500e-04) (hash(x)=20820913) +2402 train 7.010041 (lr=1.7500e-04) (hash(x)=22178190) +2403 train 7.696925 (lr=1.7500e-04) (hash(x)=31377168) +2404 train 7.898088 (lr=1.7500e-04) (hash(x)=33795307) +2405 train 7.989216 (lr=1.7500e-04) (hash(x)=34450341) +2406 train 7.168972 (lr=1.7500e-04) (hash(x)=25834183) +2407 train 7.388435 (lr=1.7500e-04) (hash(x)=25629584) +2408 train 7.134726 (lr=1.7500e-04) (hash(x)=25080123) +2409 train 7.022211 (lr=1.7500e-04) (hash(x)=21975628) +2410 train 7.614688 (lr=1.7500e-04) (hash(x)=27430197) +2411 train 7.741413 (lr=1.7500e-04) (hash(x)=29285135) +2412 train 7.426866 (lr=1.7500e-04) (hash(x)=24640105) +2413 train 7.558202 (lr=1.7500e-04) (hash(x)=29628864) +2414 train 7.760406 (lr=1.7500e-04) (hash(x)=30096444) +2415 train 7.559000 (lr=1.7500e-04) (hash(x)=29797280) +2416 train 6.958549 (lr=1.7500e-04) (hash(x)=22686143) +2417 train 7.525041 (lr=1.7500e-04) (hash(x)=28346842) +2418 train 7.511923 (lr=1.7500e-04) (hash(x)=28167937) +2419 train 7.765172 (lr=1.7500e-04) (hash(x)=33122326) +2420 train 7.814128 (lr=1.7500e-04) (hash(x)=33044913) +2421 train 7.635742 (lr=1.7500e-04) (hash(x)=31250981) +2422 train 7.776464 (lr=1.7500e-04) (hash(x)=29827111) +2423 train 7.675095 (lr=1.7500e-04) (hash(x)=30026394) +2424 train 7.725105 (lr=1.7500e-04) (hash(x)=26998238) +2425 train 7.655735 (lr=1.7500e-04) (hash(x)=24850684) +2426 train 7.957399 (lr=1.7500e-04) (hash(x)=36659853) +2427 train 7.848952 (lr=1.7500e-04) (hash(x)=34353164) +2428 train 7.175872 (lr=1.7500e-04) (hash(x)=23630644) +2429 train 7.216308 (lr=1.7500e-04) (hash(x)=24528186) +2430 train 7.102849 (lr=1.7500e-04) (hash(x)=22665222) +2431 train 7.219583 (lr=1.7500e-04) (hash(x)=26594177) +2432 train 7.561774 (lr=1.7500e-04) (hash(x)=29300546) +2433 train 7.002141 (lr=1.7500e-04) (hash(x)=21331715) +2434 train 7.290996 (lr=1.7500e-04) (hash(x)=26290885) +2435 train 7.217294 (lr=1.7500e-04) (hash(x)=25554738) +2436 train 7.488568 (lr=1.7500e-04) (hash(x)=26744311) +2437 train 7.397100 (lr=1.7500e-04) (hash(x)=26872344) +2438 train 7.465801 (lr=1.7500e-04) (hash(x)=27636081) +2439 train 7.228142 (lr=1.7500e-04) (hash(x)=23766256) +2440 train 7.329710 (lr=1.7500e-04) (hash(x)=24434438) +2441 train 7.152001 (lr=1.7500e-04) (hash(x)=22992618) +2442 train 7.022270 (lr=1.7500e-04) (hash(x)=22393467) +2443 train 7.294183 (lr=1.7500e-04) (hash(x)=26853444) +2444 train 7.222049 (lr=1.7500e-04) (hash(x)=25101020) +2445 train 7.134988 (lr=1.7500e-04) (hash(x)=24705456) +2446 train 7.460828 (lr=1.7500e-04) (hash(x)=26798611) +2447 train 7.113481 (lr=1.7500e-04) (hash(x)=24250150) +2448 train 7.181508 (lr=1.7500e-04) (hash(x)=24494331) +2449 train 7.198741 (lr=1.7500e-04) (hash(x)=27579257) +2450 val loss 7.2459 +2450 val perplexity 1402.3597 +2450 train 6.976996 (lr=1.7500e-04) (hash(x)=22377407) +2451 train 7.265130 (lr=1.7500e-04) (hash(x)=26289588) +2452 train 7.200462 (lr=1.7500e-04) (hash(x)=25871900) +2453 train 7.089351 (lr=1.7500e-04) (hash(x)=23437197) +2454 train 7.350240 (lr=1.7500e-04) (hash(x)=23557786) +2455 train 7.305383 (lr=1.7500e-04) (hash(x)=26108817) +2456 train 7.195796 (lr=1.7500e-04) (hash(x)=26440482) +2457 train 7.198570 (lr=1.7500e-04) (hash(x)=24583191) +2458 train 7.215637 (lr=1.7500e-04) (hash(x)=23756440) +2459 train 7.055656 (lr=1.7500e-04) (hash(x)=23814987) +2460 train 7.422124 (lr=1.7500e-04) (hash(x)=28508433) +2461 train 7.078984 (lr=1.7500e-04) (hash(x)=25692442) +2462 train 7.083425 (lr=1.7500e-04) (hash(x)=24699197) +2463 train 6.767697 (lr=1.7500e-04) (hash(x)=18582688) +2464 train 7.115843 (lr=1.7500e-04) (hash(x)=23266625) +2465 train 7.398314 (lr=1.7500e-04) (hash(x)=26565489) +2466 train 6.919446 (lr=1.7500e-04) (hash(x)=21686599) +2467 train 7.215430 (lr=1.7500e-04) (hash(x)=25558792) +2468 train 6.972864 (lr=1.7500e-04) (hash(x)=25110035) +2469 train 7.339216 (lr=1.7500e-04) (hash(x)=26263661) +2470 train 7.053798 (lr=1.7500e-04) (hash(x)=22282189) +2471 train 7.039116 (lr=1.7500e-04) (hash(x)=23272705) +2472 train 7.115979 (lr=1.7500e-04) (hash(x)=25300067) +2473 train 7.300792 (lr=1.7500e-04) (hash(x)=26802369) +2474 train 7.019033 (lr=1.7500e-04) (hash(x)=24646471) +2475 train 6.985614 (lr=1.7500e-04) (hash(x)=24709241) +2476 train 7.070204 (lr=1.7500e-04) (hash(x)=26747197) +2477 train 7.133607 (lr=1.7500e-04) (hash(x)=25201108) +2478 train 7.242448 (lr=1.7500e-04) (hash(x)=24962427) +2479 train 7.093843 (lr=1.7500e-04) (hash(x)=24793412) +2480 train 7.148621 (lr=1.7500e-04) (hash(x)=24452301) +2481 train 7.140145 (lr=1.7500e-04) (hash(x)=25177251) +2482 train 7.067443 (lr=1.7500e-04) (hash(x)=25801499) +2483 train 7.243344 (lr=1.7500e-04) (hash(x)=27256707) +2484 train 7.489974 (lr=1.7500e-04) (hash(x)=25303237) +2485 train 7.072610 (lr=1.7500e-04) (hash(x)=21641481) +2486 train 7.071152 (lr=1.7500e-04) (hash(x)=23818831) +2487 train 6.845770 (lr=1.7500e-04) (hash(x)=19280989) +2488 train 7.215535 (lr=1.7500e-04) (hash(x)=24075167) +2489 train 7.206131 (lr=1.7500e-04) (hash(x)=26651546) +2490 train 7.152071 (lr=1.7500e-04) (hash(x)=25367186) +2491 train 7.091649 (lr=1.7500e-04) (hash(x)=26508642) +2492 train 7.224590 (lr=1.7500e-04) (hash(x)=25294182) +2493 train 7.083961 (lr=1.7500e-04) (hash(x)=23916886) +2494 train 6.951362 (lr=1.7500e-04) (hash(x)=21189910) +2495 train 7.073037 (lr=1.7500e-04) (hash(x)=22751150) +2496 train 7.495477 (lr=1.7500e-04) (hash(x)=26608502) +2497 train 7.848359 (lr=1.7500e-04) (hash(x)=25372010) +2498 train 7.147090 (lr=1.7500e-04) (hash(x)=22006251) +2499 train 7.120489 (lr=1.7500e-04) (hash(x)=23880160) +2500 val loss 7.2638 +2500 val perplexity 1427.6056 +2500 train 7.066785 (lr=1.7500e-04) (hash(x)=23225337) +2501 train 7.254780 (lr=1.7500e-04) (hash(x)=24932950) +2502 train 6.982209 (lr=1.7500e-04) (hash(x)=20022340) +2503 train 7.354918 (lr=1.7500e-04) (hash(x)=23537942) +2504 train 7.239452 (lr=1.7500e-04) (hash(x)=24884288) +2505 train 6.883118 (lr=1.7500e-04) (hash(x)=21296580) +2506 train 7.103224 (lr=1.7500e-04) (hash(x)=23001455) +2507 train 7.413152 (lr=1.7500e-04) (hash(x)=26975313) +2508 train 7.399679 (lr=1.7500e-04) (hash(x)=26029962) +2509 train 7.115684 (lr=1.7500e-04) (hash(x)=24302204) +2510 train 6.808296 (lr=1.7500e-04) (hash(x)=22997203) +2511 train 6.950245 (lr=1.7500e-04) (hash(x)=23748375) +2512 train 7.184711 (lr=1.7500e-04) (hash(x)=24453191) +2513 train 6.850358 (lr=1.7500e-04) (hash(x)=22026776) +2514 train 6.960457 (lr=1.7500e-04) (hash(x)=19934168) +2515 train 7.270561 (lr=1.7500e-04) (hash(x)=25541754) +2516 train 7.599067 (lr=1.7500e-04) (hash(x)=26604471) +2517 train 7.580954 (lr=1.7500e-04) (hash(x)=27900386) +2518 train 7.542863 (lr=1.7500e-04) (hash(x)=26403431) +2519 train 7.557323 (lr=1.7500e-04) (hash(x)=27413825) +2520 train 7.631670 (lr=1.7500e-04) (hash(x)=28332637) +2521 train 7.442897 (lr=1.7500e-04) (hash(x)=27223027) +2522 train 7.439238 (lr=1.7500e-04) (hash(x)=23843387) +2523 train 7.444392 (lr=1.7500e-04) (hash(x)=27075951) +2524 train 7.607548 (lr=1.7500e-04) (hash(x)=29300154) +2525 train 7.236270 (lr=1.7500e-04) (hash(x)=28100582) +2526 train 7.348998 (lr=1.7500e-04) (hash(x)=28051084) +2527 train 7.075801 (lr=1.7500e-04) (hash(x)=21682445) +2528 train 7.254314 (lr=1.7500e-04) (hash(x)=24062589) +2529 train 7.486240 (lr=1.7500e-04) (hash(x)=29616079) +2530 train 7.378881 (lr=1.7500e-04) (hash(x)=25170523) +2531 train 6.950136 (lr=1.7500e-04) (hash(x)=23361504) +2532 train 7.167397 (lr=1.7500e-04) (hash(x)=24444462) +2533 train 7.171228 (lr=1.7500e-04) (hash(x)=24035993) +2534 train 7.122177 (lr=1.7500e-04) (hash(x)=24696651) +2535 train 7.118237 (lr=1.7500e-04) (hash(x)=22040184) +2536 train 7.050579 (lr=1.7500e-04) (hash(x)=27400103) +2537 train 7.360585 (lr=1.7500e-04) (hash(x)=27383080) +2538 train 7.154120 (lr=1.7500e-04) (hash(x)=24212212) +2539 train 7.029080 (lr=1.7500e-04) (hash(x)=23727731) +2540 train 7.168869 (lr=1.7500e-04) (hash(x)=24149487) +2541 train 6.946031 (lr=1.7500e-04) (hash(x)=23794649) +2542 train 7.130208 (lr=1.7500e-04) (hash(x)=26147774) +2543 train 7.227463 (lr=1.7500e-04) (hash(x)=24463229) +2544 train 7.318005 (lr=1.7500e-04) (hash(x)=26361238) +2545 train 6.958832 (lr=1.7500e-04) (hash(x)=18891545) +2546 train 7.502969 (lr=1.7500e-04) (hash(x)=30380438) +2547 train 7.723655 (lr=1.7500e-04) (hash(x)=32663792) +2548 train 7.140713 (lr=1.7500e-04) (hash(x)=25175499) +2549 train 7.333047 (lr=1.7500e-04) (hash(x)=26702407) +2550 val loss 7.2146 +2550 val perplexity 1359.1274 +2550 train 7.131624 (lr=1.7500e-04) (hash(x)=24578061) +2551 train 7.134735 (lr=1.7500e-04) (hash(x)=24091954) +2552 train 7.169356 (lr=1.7500e-04) (hash(x)=23041778) +2553 train 6.942993 (lr=1.7500e-04) (hash(x)=23686239) +2554 train 7.079614 (lr=1.7500e-04) (hash(x)=22745355) +2555 train 7.129727 (lr=1.7500e-04) (hash(x)=23599013) +2556 train 7.056730 (lr=1.7500e-04) (hash(x)=26033088) +2557 train 7.141528 (lr=1.7500e-04) (hash(x)=21634218) +2558 train 7.056743 (lr=1.7500e-04) (hash(x)=20985281) +2559 train 7.291677 (lr=1.7500e-04) (hash(x)=26670219) +2560 train 7.060154 (lr=1.7500e-04) (hash(x)=26499936) +2561 train 7.165987 (lr=1.7500e-04) (hash(x)=23547908) +2562 train 7.027174 (lr=1.7500e-04) (hash(x)=22306373) +2563 train 7.150085 (lr=1.7500e-04) (hash(x)=24380893) +2564 train 7.096655 (lr=1.7500e-04) (hash(x)=23726190) +2565 train 7.136109 (lr=1.7500e-04) (hash(x)=26967512) +2566 train 7.225406 (lr=1.7500e-04) (hash(x)=23414576) +2567 train 7.473358 (lr=1.7500e-04) (hash(x)=25558986) +2568 train 7.362743 (lr=1.7500e-04) (hash(x)=27057505) +2569 train 7.324135 (lr=1.7500e-04) (hash(x)=26048135) +2570 train 7.314137 (lr=1.7500e-04) (hash(x)=26991032) +2571 train 7.344619 (lr=1.7500e-04) (hash(x)=25729492) +2572 train 6.879488 (lr=1.7500e-04) (hash(x)=20611723) +2573 train 6.979355 (lr=1.7500e-04) (hash(x)=24563606) +2574 train 7.078430 (lr=1.7500e-04) (hash(x)=23330043) +2575 train 7.121715 (lr=1.7500e-04) (hash(x)=19218943) +2576 train 7.464386 (lr=1.7500e-04) (hash(x)=20985122) +2577 train 7.081534 (lr=1.7500e-04) (hash(x)=24133609) +2578 train 7.407955 (lr=1.7500e-04) (hash(x)=28368610) +2579 train 7.129871 (lr=1.7500e-04) (hash(x)=23952206) +2580 train 7.021043 (lr=1.7500e-04) (hash(x)=23068957) +2581 train 7.149298 (lr=1.7500e-04) (hash(x)=25365277) +2582 train 7.419852 (lr=1.7500e-04) (hash(x)=24721184) +2583 train 7.164315 (lr=1.7500e-04) (hash(x)=24551402) +2584 train 6.913200 (lr=1.7500e-04) (hash(x)=20469327) +2585 train 7.340292 (lr=1.7500e-04) (hash(x)=24966478) +2586 train 7.072422 (lr=1.7500e-04) (hash(x)=18626184) +2587 train 7.099381 (lr=1.7500e-04) (hash(x)=24007642) +2588 train 7.056058 (lr=1.7500e-04) (hash(x)=23521875) +2589 train 7.277275 (lr=1.7500e-04) (hash(x)=25204207) +2590 train 7.046674 (lr=1.7500e-04) (hash(x)=25449801) +2591 train 7.242726 (lr=1.7500e-04) (hash(x)=25229281) +2592 train 7.097318 (lr=1.7500e-04) (hash(x)=23202696) +2593 train 6.948209 (lr=1.7500e-04) (hash(x)=22435944) +2594 train 6.994730 (lr=1.7500e-04) (hash(x)=20787439) +2595 train 6.548057 (lr=1.7500e-04) (hash(x)=18214283) +2596 train 6.753582 (lr=1.7500e-04) (hash(x)=20851477) +2597 train 6.729627 (lr=1.7500e-04) (hash(x)=20609675) +2598 train 6.885056 (lr=1.7500e-04) (hash(x)=20061218) +2599 train 6.893304 (lr=1.7500e-04) (hash(x)=21251127) +2600 val loss 7.2237 +2600 val perplexity 1371.5427 +2600 train 7.465057 (lr=1.7500e-04) (hash(x)=30948038) +2601 train 7.634116 (lr=1.7500e-04) (hash(x)=32279160) +2602 train 7.329557 (lr=1.7500e-04) (hash(x)=26607151) +2603 train 7.210980 (lr=1.7500e-04) (hash(x)=25097619) +2604 train 6.785544 (lr=1.7500e-04) (hash(x)=20892421) +2605 train 6.973821 (lr=1.7500e-04) (hash(x)=22212821) +2606 train 7.285348 (lr=1.7500e-04) (hash(x)=24720588) +2607 train 7.316324 (lr=1.7500e-04) (hash(x)=25800857) +2608 train 7.101912 (lr=1.7500e-04) (hash(x)=22901279) +2609 train 6.982704 (lr=1.7500e-04) (hash(x)=20921910) +2610 train 7.200086 (lr=1.7500e-04) (hash(x)=24846267) +2611 train 7.095431 (lr=1.7500e-04) (hash(x)=22918428) +2612 train 7.042740 (lr=1.7500e-04) (hash(x)=22805901) +2613 train 7.190774 (lr=1.7500e-04) (hash(x)=24345816) +2614 train 7.109908 (lr=1.7500e-04) (hash(x)=22962012) +2615 train 7.367973 (lr=1.7500e-04) (hash(x)=25836189) +2616 train 7.386471 (lr=1.7500e-04) (hash(x)=27922916) +2617 train 7.148950 (lr=1.7500e-04) (hash(x)=21697866) +2618 train 7.145364 (lr=1.7500e-04) (hash(x)=24283369) +2619 train 7.038014 (lr=1.7500e-04) (hash(x)=24504567) +2620 train 7.162475 (lr=1.7500e-04) (hash(x)=25557725) +2621 train 7.214747 (lr=1.7500e-04) (hash(x)=23135849) +2622 train 7.163276 (lr=1.7500e-04) (hash(x)=22888908) +2623 train 7.334913 (lr=1.7500e-04) (hash(x)=25999255) +2624 train 7.207926 (lr=1.7500e-04) (hash(x)=24446851) +2625 train 6.933025 (lr=1.7500e-04) (hash(x)=21137520) +2626 train 7.271057 (lr=1.7500e-04) (hash(x)=26245754) +2627 train 7.567375 (lr=1.7500e-04) (hash(x)=27308968) +2628 train 7.331542 (lr=1.7500e-04) (hash(x)=23961169) +2629 train 7.274417 (lr=1.7500e-04) (hash(x)=25924731) +2630 train 7.319396 (lr=1.7500e-04) (hash(x)=25782315) +2631 train 7.390646 (lr=1.7500e-04) (hash(x)=20149394) +2632 train 7.473129 (lr=1.7500e-04) (hash(x)=23801981) +2633 train 7.228001 (lr=1.7500e-04) (hash(x)=23830286) +2634 train 7.152382 (lr=1.7500e-04) (hash(x)=25325236) +2635 train 7.187564 (lr=1.7500e-04) (hash(x)=24498556) +2636 train 7.101112 (lr=1.7500e-04) (hash(x)=23693078) +2637 train 7.274437 (lr=1.7500e-04) (hash(x)=25484922) +2638 train 6.973555 (lr=1.7500e-04) (hash(x)=22645025) +2639 train 6.934497 (lr=1.7500e-04) (hash(x)=21999338) +2640 train 7.161220 (lr=1.7500e-04) (hash(x)=21758019) +2641 train 7.094427 (lr=1.7500e-04) (hash(x)=24064168) +2642 train 7.119841 (lr=1.7500e-04) (hash(x)=26847292) +2643 train 6.984970 (lr=1.7500e-04) (hash(x)=23280568) +2644 train 7.006068 (lr=1.7500e-04) (hash(x)=21749161) +2645 train 7.608031 (lr=1.7500e-04) (hash(x)=30082352) +2646 train 7.493129 (lr=1.7500e-04) (hash(x)=28334297) +2647 train 7.658638 (lr=1.7500e-04) (hash(x)=27611302) +2648 train 7.988204 (lr=1.7500e-04) (hash(x)=31007436) +2649 train 6.938690 (lr=1.7500e-04) (hash(x)=22356183) +2650 val loss 7.3303 +2650 val perplexity 1525.8815 +2650 train 7.055798 (lr=1.7500e-04) (hash(x)=23071731) +2651 train 7.101468 (lr=1.7500e-04) (hash(x)=23982308) +2652 train 7.471122 (lr=1.7500e-04) (hash(x)=25673823) +2653 train 7.243372 (lr=1.7500e-04) (hash(x)=22973788) +2654 train 7.344312 (lr=1.7500e-04) (hash(x)=25386647) +2655 train 7.031827 (lr=1.7500e-04) (hash(x)=22778356) +2656 train 7.328221 (lr=1.7500e-04) (hash(x)=26669130) +2657 train 7.051984 (lr=1.7500e-04) (hash(x)=23542930) +2658 train 7.180345 (lr=1.7500e-04) (hash(x)=23307871) +2659 train 7.127576 (lr=1.7500e-04) (hash(x)=23467046) +2660 train 7.269927 (lr=1.7500e-04) (hash(x)=24728872) +2661 train 7.953166 (lr=1.7500e-04) (hash(x)=29719902) +2662 train 7.165420 (lr=1.7500e-04) (hash(x)=25114165) +2663 train 7.086862 (lr=1.7500e-04) (hash(x)=24195959) +2664 train 7.255560 (lr=1.7500e-04) (hash(x)=26938509) +2665 train 7.487430 (lr=1.7500e-04) (hash(x)=27168434) +2666 train 7.589555 (lr=1.7500e-04) (hash(x)=27488221) +2667 train 8.201678 (lr=1.7500e-04) (hash(x)=32710438) +2668 train 7.425153 (lr=1.7500e-04) (hash(x)=25073185) +2669 train 7.476387 (lr=1.7500e-04) (hash(x)=26951664) +2670 train 7.643912 (lr=1.7500e-04) (hash(x)=24886228) +2671 train 7.056394 (lr=1.7500e-04) (hash(x)=19127465) +2672 train 7.302271 (lr=1.7500e-04) (hash(x)=27134917) +2673 train 7.229032 (lr=1.7500e-04) (hash(x)=25673955) +2674 train 7.714092 (lr=1.7500e-04) (hash(x)=27111776) +2675 train 7.697713 (lr=1.7500e-04) (hash(x)=28962580) +2676 train 7.170984 (lr=1.7500e-04) (hash(x)=25593381) +2677 train 7.263983 (lr=1.7500e-04) (hash(x)=25238916) +2678 train 7.170031 (lr=1.7500e-04) (hash(x)=27453574) +2679 train 7.153057 (lr=1.7500e-04) (hash(x)=22426274) +2680 train 7.135144 (lr=1.7500e-04) (hash(x)=22974780) +2681 train 7.181601 (lr=1.7500e-04) (hash(x)=24668644) +2682 train 7.171973 (lr=1.7500e-04) (hash(x)=26182084) +2683 train 7.337121 (lr=1.7500e-04) (hash(x)=25606512) +2684 train 7.167073 (lr=1.7500e-04) (hash(x)=24885252) +2685 train 6.987418 (lr=1.7500e-04) (hash(x)=21290254) +2686 train 6.967195 (lr=1.7500e-04) (hash(x)=21367078) +2687 train 7.129532 (lr=1.7500e-04) (hash(x)=23785205) +2688 train 7.051469 (lr=1.7500e-04) (hash(x)=24640056) +2689 train 7.471654 (lr=1.7500e-04) (hash(x)=27083886) +2690 train 7.186827 (lr=1.7500e-04) (hash(x)=23603571) +2691 train 7.268810 (lr=1.7500e-04) (hash(x)=24779414) +2692 train 6.933140 (lr=1.7500e-04) (hash(x)=22200693) +2693 train 7.232559 (lr=1.7500e-04) (hash(x)=26907868) +2694 train 7.570706 (lr=1.7500e-04) (hash(x)=32034827) +2695 train 7.435165 (lr=1.7500e-04) (hash(x)=28505676) +2696 train 7.046478 (lr=1.7500e-04) (hash(x)=23805750) +2697 train 7.419525 (lr=1.7500e-04) (hash(x)=29804750) +2698 train 7.705978 (lr=1.7500e-04) (hash(x)=28443583) +2699 train 7.607048 (lr=1.7500e-04) (hash(x)=29156288) +2700 val loss 7.2345 +2700 val perplexity 1386.4911 +2700 train 7.255554 (lr=1.7500e-04) (hash(x)=25895743) +2701 train 6.867954 (lr=1.7500e-04) (hash(x)=21173795) +2702 train 6.793265 (lr=1.7500e-04) (hash(x)=20790866) +2703 train 7.376320 (lr=1.7500e-04) (hash(x)=27706477) +2704 train 7.472441 (lr=1.7500e-04) (hash(x)=30358985) +2705 train 7.080364 (lr=1.7500e-04) (hash(x)=23548492) +2706 train 7.207082 (lr=1.7500e-04) (hash(x)=25879696) +2707 train 7.082340 (lr=1.7500e-04) (hash(x)=23711800) +2708 train 7.567136 (lr=1.7500e-04) (hash(x)=28763123) +2709 train 7.197119 (lr=1.7500e-04) (hash(x)=23327642) +2710 train 7.251575 (lr=1.7500e-04) (hash(x)=25634166) +2711 train 7.176659 (lr=1.7500e-04) (hash(x)=28684175) +2712 train 7.260789 (lr=1.7500e-04) (hash(x)=23996278) +2713 train 6.877176 (lr=1.7500e-04) (hash(x)=21795980) +2714 train 7.246511 (lr=1.7500e-04) (hash(x)=24840769) +2715 train 7.181396 (lr=1.7500e-04) (hash(x)=25225466) +2716 train 7.476582 (lr=1.7500e-04) (hash(x)=27500471) +2717 train 7.142600 (lr=1.7500e-04) (hash(x)=24703036) +2718 train 7.277883 (lr=1.7500e-04) (hash(x)=24294293) +2719 train 7.234014 (lr=1.7500e-04) (hash(x)=28003600) +2720 train 6.992084 (lr=1.7500e-04) (hash(x)=22822962) +2721 train 6.827402 (lr=1.7500e-04) (hash(x)=24189246) +2722 train 6.968781 (lr=1.7500e-04) (hash(x)=22608951) +2723 train 7.562245 (lr=1.7500e-04) (hash(x)=27989890) +2724 train 7.273651 (lr=1.7500e-04) (hash(x)=24175838) +2725 train 7.205191 (lr=1.7500e-04) (hash(x)=24781792) +2726 train 7.033876 (lr=1.7500e-04) (hash(x)=23413276) +2727 train 7.416341 (lr=1.7500e-04) (hash(x)=27586845) +2728 train 7.232432 (lr=1.7500e-04) (hash(x)=27336264) +2729 train 7.259917 (lr=1.7500e-04) (hash(x)=26808464) +2730 train 7.110967 (lr=1.7500e-04) (hash(x)=22312009) +2731 train 7.130710 (lr=1.7500e-04) (hash(x)=22373927) +2732 train 7.078887 (lr=1.7500e-04) (hash(x)=23428834) +2733 train 7.130585 (lr=1.7500e-04) (hash(x)=25304441) +2734 train 7.143478 (lr=1.7500e-04) (hash(x)=24798164) +2735 train 6.956635 (lr=1.7500e-04) (hash(x)=21176405) +2736 train 7.035530 (lr=1.7500e-04) (hash(x)=22343075) +2737 train 7.100134 (lr=1.7500e-04) (hash(x)=23825332) +2738 train 7.134557 (lr=1.7500e-04) (hash(x)=24191865) +2739 train 6.939209 (lr=1.7500e-04) (hash(x)=23806052) +2740 train 6.984226 (lr=1.7500e-04) (hash(x)=21764591) +2741 train 7.166532 (lr=1.7500e-04) (hash(x)=25548695) +2742 train 7.403011 (lr=1.7500e-04) (hash(x)=26847535) +2743 train 7.064394 (lr=1.7500e-04) (hash(x)=25888433) +2744 train 7.021497 (lr=1.7500e-04) (hash(x)=24327454) +2745 train 6.940982 (lr=1.7500e-04) (hash(x)=22543301) +2746 train 7.388045 (lr=1.7500e-04) (hash(x)=24593022) +2747 train 7.994119 (lr=1.7500e-04) (hash(x)=27797727) +2748 train 7.430166 (lr=1.7500e-04) (hash(x)=28067682) +2749 train 7.053136 (lr=1.7500e-04) (hash(x)=25278538) +2750 val loss 7.2228 +2750 val perplexity 1370.3654 +2750 train 7.017752 (lr=1.7500e-04) (hash(x)=23875731) +2751 train 7.184817 (lr=1.7500e-04) (hash(x)=27916982) +2752 train 7.154319 (lr=1.7500e-04) (hash(x)=25726799) +2753 train 6.991078 (lr=1.7500e-04) (hash(x)=25227141) +2754 train 7.273942 (lr=1.7500e-04) (hash(x)=27679212) +2755 train 6.920769 (lr=1.7500e-04) (hash(x)=24621793) +2756 train 6.874425 (lr=1.7500e-04) (hash(x)=21962296) +2757 train 7.225441 (lr=1.7500e-04) (hash(x)=24899679) +2758 train 6.934860 (lr=1.7500e-04) (hash(x)=21452158) +2759 train 7.049790 (lr=1.7500e-04) (hash(x)=24334708) +2760 train 7.291393 (lr=1.7500e-04) (hash(x)=25523041) +2761 train 7.366663 (lr=1.7500e-04) (hash(x)=30389813) +2762 train 6.983015 (lr=1.7500e-04) (hash(x)=22426014) +2763 train 7.043601 (lr=1.7500e-04) (hash(x)=24419143) +2764 train 7.149271 (lr=1.7500e-04) (hash(x)=24850536) +2765 train 7.200530 (lr=1.7500e-04) (hash(x)=24181393) +2766 train 6.730175 (lr=1.7500e-04) (hash(x)=18882503) +2767 train 7.206160 (lr=1.7500e-04) (hash(x)=25617709) +2768 train 7.163214 (lr=1.7500e-04) (hash(x)=24076662) +2769 train 7.077602 (lr=1.7500e-04) (hash(x)=21656802) +2770 train 7.034482 (lr=1.7500e-04) (hash(x)=21014265) +2771 train 7.176013 (lr=1.7500e-04) (hash(x)=24556034) +2772 train 6.914337 (lr=1.7500e-04) (hash(x)=22046665) +2773 train 7.215545 (lr=1.7500e-04) (hash(x)=26761579) +2774 train 8.725920 (lr=1.7500e-04) (hash(x)=41414315) +2775 train 7.109634 (lr=1.7500e-04) (hash(x)=25152362) +2776 train 7.250183 (lr=1.7500e-04) (hash(x)=25567641) +2777 train 7.214088 (lr=1.7500e-04) (hash(x)=25427935) +2778 train 7.299886 (lr=1.7500e-04) (hash(x)=25824457) +2779 train 7.228584 (lr=1.7500e-04) (hash(x)=24326376) +2780 train 7.229284 (lr=1.7500e-04) (hash(x)=27447230) +2781 train 7.109990 (lr=1.7500e-04) (hash(x)=24003710) +2782 train 7.035095 (lr=1.7500e-04) (hash(x)=24157390) +2783 train 7.145454 (lr=1.7500e-04) (hash(x)=24276512) +2784 train 6.929100 (lr=1.7500e-04) (hash(x)=21503752) +2785 train 6.853275 (lr=1.7500e-04) (hash(x)=20031488) +2786 train 6.892416 (lr=1.7500e-04) (hash(x)=21788715) +2787 train 7.135100 (lr=1.7500e-04) (hash(x)=24344695) +2788 train 7.186887 (lr=1.7500e-04) (hash(x)=22927763) +2789 train 7.040746 (lr=1.7500e-04) (hash(x)=23710755) +2790 train 7.286611 (lr=1.7500e-04) (hash(x)=26924620) +2791 train 7.594205 (lr=1.7500e-04) (hash(x)=26776133) +2792 train 7.044116 (lr=1.7500e-04) (hash(x)=19936770) +2793 train 7.195584 (lr=1.7500e-04) (hash(x)=25440959) +2794 train 7.131081 (lr=1.7500e-04) (hash(x)=25146097) +2795 train 6.944644 (lr=1.7500e-04) (hash(x)=21847282) +2796 train 7.138758 (lr=1.7500e-04) (hash(x)=25639784) +2797 train 6.931540 (lr=1.7500e-04) (hash(x)=21199921) +2798 train 7.097131 (lr=1.7500e-04) (hash(x)=22360806) +2799 train 6.578201 (lr=1.7500e-04) (hash(x)=20254159) +2800 val loss 7.2228 +2800 val perplexity 1370.3131 +2800 train 6.702682 (lr=1.7500e-04) (hash(x)=23348345) +2801 train 7.299606 (lr=1.7500e-04) (hash(x)=24908033) +2802 train 7.046070 (lr=1.7500e-04) (hash(x)=23350309) +2803 train 7.188484 (lr=1.7500e-04) (hash(x)=25044762) +2804 train 7.025397 (lr=1.7500e-04) (hash(x)=24071026) +2805 train 6.854791 (lr=1.7500e-04) (hash(x)=22169363) +2806 train 7.174142 (lr=1.7500e-04) (hash(x)=23757564) +2807 train 7.569940 (lr=1.7500e-04) (hash(x)=27873855) +2808 train 7.329987 (lr=1.7500e-04) (hash(x)=26577893) +2809 train 7.381526 (lr=1.7500e-04) (hash(x)=27001634) +2810 train 7.155812 (lr=1.7500e-04) (hash(x)=24796541) +2811 train 7.071102 (lr=1.7500e-04) (hash(x)=22575615) +2812 train 7.158611 (lr=1.7500e-04) (hash(x)=25876475) +2813 train 7.155964 (lr=1.7500e-04) (hash(x)=24765155) +2814 train 7.106087 (lr=1.7500e-04) (hash(x)=25785699) +2815 train 7.288050 (lr=1.7500e-04) (hash(x)=25113614) +2816 train 7.142628 (lr=1.7500e-04) (hash(x)=24415748) +2817 train 7.239862 (lr=1.7500e-04) (hash(x)=25140622) +2818 train 7.106699 (lr=1.7500e-04) (hash(x)=24845866) +2819 train 7.622044 (lr=1.7500e-04) (hash(x)=28062905) +2820 train 7.143799 (lr=1.7500e-04) (hash(x)=22041086) +2821 train 7.236320 (lr=1.7500e-04) (hash(x)=24957184) +2822 train 7.135189 (lr=1.7500e-04) (hash(x)=24360380) +2823 train 7.287971 (lr=1.7500e-04) (hash(x)=26192886) +2824 train 7.166563 (lr=1.7500e-04) (hash(x)=25001858) +2825 train 7.133276 (lr=1.7500e-04) (hash(x)=24721193) +2826 train 7.178731 (lr=1.7500e-04) (hash(x)=26186227) +2827 train 7.117043 (lr=1.7500e-04) (hash(x)=25770338) +2828 train 7.221373 (lr=1.7500e-04) (hash(x)=25920767) +2829 train 7.133205 (lr=1.7500e-04) (hash(x)=25060684) +2830 train 6.846749 (lr=1.7500e-04) (hash(x)=22933946) +2831 train 7.009843 (lr=1.7500e-04) (hash(x)=24614912) +2832 train 6.774420 (lr=1.7500e-04) (hash(x)=19955522) +2833 train 6.826976 (lr=1.7500e-04) (hash(x)=21111215) +2834 train 7.718607 (lr=1.7500e-04) (hash(x)=28817924) +2835 train 7.224286 (lr=1.7500e-04) (hash(x)=26934071) +2836 train 7.158737 (lr=1.7500e-04) (hash(x)=24768851) +2837 train 7.141695 (lr=1.7500e-04) (hash(x)=25706447) +2838 train 6.923814 (lr=1.7500e-04) (hash(x)=19579834) +2839 train 7.150579 (lr=1.7500e-04) (hash(x)=25397093) +2840 train 7.557806 (lr=1.7500e-04) (hash(x)=27902141) +2841 train 7.198830 (lr=1.7500e-04) (hash(x)=25383069) +2842 train 7.019653 (lr=1.7500e-04) (hash(x)=22007373) +2843 train 7.079495 (lr=1.7500e-04) (hash(x)=25925963) +2844 train 7.178903 (lr=1.7500e-04) (hash(x)=25711128) +2845 train 6.892342 (lr=1.7500e-04) (hash(x)=21881216) +2846 train 7.035362 (lr=1.7500e-04) (hash(x)=20277075) +2847 train 7.095369 (lr=1.7500e-04) (hash(x)=19811802) +2848 train 7.020647 (lr=1.7500e-04) (hash(x)=23878906) +2849 train 7.241457 (lr=1.7500e-04) (hash(x)=25034966) +2850 val loss 7.2408 +2850 val perplexity 1395.1730 +2850 train 7.307448 (lr=1.7500e-04) (hash(x)=24359507) +2851 train 7.056720 (lr=1.7500e-04) (hash(x)=23248423) +2852 train 7.041975 (lr=1.7500e-04) (hash(x)=21782773) +2853 train 7.161701 (lr=1.7500e-04) (hash(x)=23804418) +2854 train 7.163002 (lr=1.7500e-04) (hash(x)=22525078) +2855 train 7.174934 (lr=1.7500e-04) (hash(x)=25579655) +2856 train 7.290407 (lr=1.7500e-04) (hash(x)=27048876) +2857 train 7.411895 (lr=1.7500e-04) (hash(x)=26468479) +2858 train 7.128709 (lr=1.7500e-04) (hash(x)=23854933) +2859 train 7.512749 (lr=1.7500e-04) (hash(x)=25537603) +2860 train 6.927494 (lr=1.7500e-04) (hash(x)=20979252) +2861 train 7.467952 (lr=1.7500e-04) (hash(x)=26504374) +2862 train 7.244614 (lr=1.7500e-04) (hash(x)=27561842) +2863 train 7.256984 (lr=1.7500e-04) (hash(x)=26096514) +2864 train 7.258869 (lr=1.7500e-04) (hash(x)=25926899) +2865 train 7.308002 (lr=1.7500e-04) (hash(x)=26058348) +2866 train 7.305013 (lr=1.7500e-04) (hash(x)=29802259) +2867 train 7.209747 (lr=1.7500e-04) (hash(x)=24132888) +2868 train 6.910659 (lr=1.7500e-04) (hash(x)=23369410) +2869 train 7.119568 (lr=1.7500e-04) (hash(x)=25387506) +2870 train 7.308918 (lr=1.7500e-04) (hash(x)=27375344) +2871 train 7.013706 (lr=1.7500e-04) (hash(x)=22589633) +2872 train 7.178765 (lr=1.7500e-04) (hash(x)=23250237) +2873 train 7.086499 (lr=1.7500e-04) (hash(x)=25511322) +2874 train 6.790211 (lr=1.7500e-04) (hash(x)=18356418) +2875 train 7.184244 (lr=1.7500e-04) (hash(x)=27781566) +2876 train 7.012718 (lr=1.7500e-04) (hash(x)=24878173) +2877 train 7.530908 (lr=1.7500e-04) (hash(x)=30018637) +2878 train 7.379962 (lr=1.7500e-04) (hash(x)=27168416) +2879 train 7.373249 (lr=1.7500e-04) (hash(x)=26757147) +2880 train 7.379573 (lr=1.7500e-04) (hash(x)=26637081) +2881 train 7.251137 (lr=1.7500e-04) (hash(x)=24795024) +2882 train 7.526040 (lr=1.7500e-04) (hash(x)=29787745) +2883 train 7.364737 (lr=1.7500e-04) (hash(x)=26649864) +2884 train 7.181929 (lr=1.7500e-04) (hash(x)=27306612) +2885 train 7.269991 (lr=1.7500e-04) (hash(x)=27568311) +2886 train 7.296432 (lr=1.7500e-04) (hash(x)=27440150) +2887 train 7.038437 (lr=1.7500e-04) (hash(x)=24963730) +2888 train 7.056770 (lr=1.7500e-04) (hash(x)=23619807) +2889 train 7.554975 (lr=1.7500e-04) (hash(x)=29447356) +2890 train 7.080184 (lr=1.7500e-04) (hash(x)=25144675) +2891 train 7.015719 (lr=1.7500e-04) (hash(x)=25249959) +2892 train 7.012304 (lr=1.7500e-04) (hash(x)=26608712) +2893 train 7.025412 (lr=1.7500e-04) (hash(x)=26333258) +2894 train 6.830808 (lr=1.7500e-04) (hash(x)=20682182) +2895 train 7.233388 (lr=1.7500e-04) (hash(x)=27703124) +2896 train 7.055465 (lr=1.7500e-04) (hash(x)=23228180) +2897 train 6.920278 (lr=1.7500e-04) (hash(x)=25252411) +2898 train 6.923107 (lr=1.7500e-04) (hash(x)=22879178) +2899 train 7.205763 (lr=1.7500e-04) (hash(x)=26459082) +2900 val loss 7.2093 +2900 val perplexity 1352.0082 +2900 train 7.037365 (lr=1.7500e-04) (hash(x)=24569501) +2901 train 6.823898 (lr=1.7500e-04) (hash(x)=19803884) +2902 train 6.876224 (lr=1.7500e-04) (hash(x)=18799747) +2903 train 7.161294 (lr=1.7500e-04) (hash(x)=24781713) +2904 train 7.305473 (lr=1.7500e-04) (hash(x)=25016590) +2905 train 7.500108 (lr=1.7500e-04) (hash(x)=29006906) +2906 train 7.240286 (lr=1.7500e-04) (hash(x)=24069959) +2907 train 7.417119 (lr=1.7500e-04) (hash(x)=26597693) +2908 train 7.046805 (lr=1.7500e-04) (hash(x)=25014146) +2909 train 7.241796 (lr=1.7500e-04) (hash(x)=24943747) +2910 train 7.144397 (lr=1.7500e-04) (hash(x)=27847542) +2911 train 7.066109 (lr=1.7500e-04) (hash(x)=24720476) +2912 train 6.924596 (lr=1.7500e-04) (hash(x)=24388804) +2913 train 7.063221 (lr=1.7500e-04) (hash(x)=23567535) +2914 train 7.382968 (lr=1.7500e-04) (hash(x)=29673625) +2915 train 7.116287 (lr=1.7500e-04) (hash(x)=23691295) +2916 train 7.459538 (lr=1.7500e-04) (hash(x)=26572819) +2917 train 7.104389 (lr=1.7500e-04) (hash(x)=23237812) +2918 train 7.386832 (lr=1.7500e-04) (hash(x)=26531016) +2919 train 6.915995 (lr=1.7500e-04) (hash(x)=23481301) +2920 train 7.200223 (lr=1.7500e-04) (hash(x)=24839184) +2921 train 7.064728 (lr=1.7500e-04) (hash(x)=23327755) +2922 train 7.301932 (lr=1.7500e-04) (hash(x)=26347114) +2923 train 6.954620 (lr=1.7500e-04) (hash(x)=23295676) +2924 train 7.018682 (lr=1.7500e-04) (hash(x)=24557178) +2925 train 7.100679 (lr=1.7500e-04) (hash(x)=26067788) +2926 train 7.044199 (lr=1.7500e-04) (hash(x)=25694982) +2927 train 7.136741 (lr=1.7500e-04) (hash(x)=25641033) +2928 train 7.177382 (lr=1.7500e-04) (hash(x)=24906422) +2929 train 7.371986 (lr=1.7500e-04) (hash(x)=27803515) +2930 train 7.324613 (lr=1.7500e-04) (hash(x)=26208803) +2931 train 6.817751 (lr=1.7500e-04) (hash(x)=22441379) +2932 train 7.115103 (lr=1.7500e-04) (hash(x)=24741626) +2933 train 7.019971 (lr=1.7500e-04) (hash(x)=24595257) +2934 train 7.050305 (lr=1.7500e-04) (hash(x)=23939167) +2935 train 7.276661 (lr=1.7500e-04) (hash(x)=27369437) +2936 train 6.937157 (lr=1.7500e-04) (hash(x)=21409783) +2937 train 7.206302 (lr=1.7500e-04) (hash(x)=25923735) +2938 train 7.208079 (lr=1.7500e-04) (hash(x)=29559511) +2939 train 7.094904 (lr=1.7500e-04) (hash(x)=24482272) +2940 train 7.073631 (lr=1.7500e-04) (hash(x)=24767658) +2941 train 7.263970 (lr=1.7500e-04) (hash(x)=26425020) +2942 train 7.626070 (lr=1.7500e-04) (hash(x)=27444868) +2943 train 7.076212 (lr=1.7500e-04) (hash(x)=24760900) +2944 train 7.123260 (lr=1.7500e-04) (hash(x)=25605407) +2945 train 6.965096 (lr=1.7500e-04) (hash(x)=22886951) +2946 train 7.305269 (lr=1.7500e-04) (hash(x)=26112205) +2947 train 7.148719 (lr=1.7500e-04) (hash(x)=23919156) +2948 train 7.100985 (lr=1.7500e-04) (hash(x)=23729312) +2949 train 7.414165 (lr=1.7500e-04) (hash(x)=30440878) +2950 val loss 7.2026 +2950 val perplexity 1342.9697 +2950 train 6.838632 (lr=1.7500e-04) (hash(x)=20004041) +2951 train 6.837486 (lr=1.7500e-04) (hash(x)=21692546) +2952 train 6.876276 (lr=1.7500e-04) (hash(x)=23021681) +2953 train 7.215849 (lr=1.7500e-04) (hash(x)=26663597) +2954 train 7.089499 (lr=1.7500e-04) (hash(x)=23727385) +2955 train 7.077591 (lr=1.7500e-04) (hash(x)=27692087) +2956 train 7.109495 (lr=1.7500e-04) (hash(x)=24003378) +2957 train 7.729784 (lr=1.7500e-04) (hash(x)=29534673) +2958 train 7.005910 (lr=1.7500e-04) (hash(x)=22875068) +2959 train 6.968605 (lr=1.7500e-04) (hash(x)=22720391) +2960 train 6.765375 (lr=1.7500e-04) (hash(x)=17997400) +2961 train 6.980579 (lr=1.7500e-04) (hash(x)=22853822) +2962 train 7.046820 (lr=1.7500e-04) (hash(x)=25238004) +2963 train 7.157020 (lr=1.7500e-04) (hash(x)=26146560) +2964 train 7.298334 (lr=1.7500e-04) (hash(x)=21894867) +2965 train 7.261308 (lr=1.7500e-04) (hash(x)=23001150) +2966 train 6.986288 (lr=1.7500e-04) (hash(x)=23392923) +2967 train 7.077152 (lr=1.7500e-04) (hash(x)=24376979) +2968 train 7.050220 (lr=1.7500e-04) (hash(x)=23781449) +2969 train 7.157298 (lr=1.7500e-04) (hash(x)=25315495) +2970 train 7.308152 (lr=1.7500e-04) (hash(x)=27165470) +2971 train 7.146707 (lr=1.7500e-04) (hash(x)=22917712) +2972 train 7.465417 (lr=1.7500e-04) (hash(x)=27928456) +2973 train 6.912437 (lr=1.7500e-04) (hash(x)=19890855) +2974 train 6.844371 (lr=1.7500e-04) (hash(x)=21318134) +2975 train 6.991457 (lr=1.7500e-04) (hash(x)=22244509) +2976 train 6.910512 (lr=1.7500e-04) (hash(x)=21293137) +2977 train 7.005544 (lr=1.7500e-04) (hash(x)=23465789) +2978 train 6.955652 (lr=1.7500e-04) (hash(x)=21169753) +2979 train 7.349359 (lr=1.7500e-04) (hash(x)=25243385) +2980 train 7.376585 (lr=1.7500e-04) (hash(x)=27465812) +2981 train 7.081257 (lr=1.7500e-04) (hash(x)=24615492) +2982 train 7.022621 (lr=1.7500e-04) (hash(x)=23081307) +2983 train 6.804409 (lr=1.7500e-04) (hash(x)=21831960) +2984 train 6.942214 (lr=1.7500e-04) (hash(x)=23242850) +2985 train 7.050712 (lr=1.7500e-04) (hash(x)=24308188) +2986 train 7.227043 (lr=1.7500e-04) (hash(x)=28541601) +2987 train 7.110045 (lr=1.7500e-04) (hash(x)=24842373) +2988 train 6.860580 (lr=1.7500e-04) (hash(x)=21967126) +2989 train 7.047493 (lr=1.7500e-04) (hash(x)=22951616) +2990 train 7.160799 (lr=1.7500e-04) (hash(x)=24325714) +2991 train 6.951351 (lr=1.7500e-04) (hash(x)=24921535) +2992 train 7.191632 (lr=1.7500e-04) (hash(x)=25937112) +2993 train 6.871133 (lr=1.7500e-04) (hash(x)=20716218) +2994 train 7.157430 (lr=1.7500e-04) (hash(x)=25450724) +2995 train 7.092737 (lr=1.7500e-04) (hash(x)=24344615) +2996 train 6.833696 (lr=1.7500e-04) (hash(x)=20299058) +2997 train 7.073045 (lr=1.7500e-04) (hash(x)=23859426) +2998 train 7.054476 (lr=1.7500e-04) (hash(x)=23094397) +2999 train 7.330310 (lr=1.7500e-04) (hash(x)=25381251) +3000 val loss 7.2221 +3000 val perplexity 1369.3242 +3000 train 7.120769 (lr=1.7500e-04) (hash(x)=23586527) +3001 train 7.001631 (lr=1.7500e-04) (hash(x)=24220410) +3002 train 6.865219 (lr=1.7500e-04) (hash(x)=20597347) +3003 train 6.941490 (lr=1.7500e-04) (hash(x)=22887303) +3004 train 7.248396 (lr=1.7500e-04) (hash(x)=25869462) +3005 train 7.004930 (lr=1.7500e-04) (hash(x)=22098530) +3006 train 7.301544 (lr=1.7500e-04) (hash(x)=26246291) +3007 train 7.248899 (lr=1.7500e-04) (hash(x)=25687352) +3008 train 6.972694 (lr=1.7500e-04) (hash(x)=25425646) +3009 train 7.171147 (lr=1.7500e-04) (hash(x)=26021124) +3010 train 7.186887 (lr=1.7500e-04) (hash(x)=25392057) +3011 train 7.264316 (lr=1.7500e-04) (hash(x)=27791412) +3012 train 7.092397 (lr=1.7500e-04) (hash(x)=23181098) +3013 train 7.121930 (lr=1.7500e-04) (hash(x)=25521889) +3014 train 6.937735 (lr=1.7500e-04) (hash(x)=21685795) +3015 train 7.109984 (lr=1.7500e-04) (hash(x)=25221654) +3016 train 7.259391 (lr=1.7500e-04) (hash(x)=24888744) +3017 train 7.158296 (lr=1.7500e-04) (hash(x)=24200150) +3018 train 7.113129 (lr=1.7500e-04) (hash(x)=26943942) +3019 train 7.081995 (lr=1.7500e-04) (hash(x)=23243731) +3020 train 6.907097 (lr=1.7500e-04) (hash(x)=21068284) +3021 train 7.104047 (lr=1.7500e-04) (hash(x)=23876902) +3022 train 7.255042 (lr=1.7500e-04) (hash(x)=25337639) +3023 train 7.143460 (lr=1.7500e-04) (hash(x)=24469863) +3024 train 7.605245 (lr=1.7500e-04) (hash(x)=27850876) +3025 train 7.409780 (lr=1.7500e-04) (hash(x)=20515778) +3026 train 7.205457 (lr=1.7500e-04) (hash(x)=29019173) +3027 train 6.879005 (lr=1.7500e-04) (hash(x)=22484936) +3028 train 7.035262 (lr=1.7500e-04) (hash(x)=24639400) +3029 train 7.228565 (lr=1.7500e-04) (hash(x)=26835174) +3030 train 7.338493 (lr=1.7500e-04) (hash(x)=29843763) +3031 train 7.039638 (lr=1.7500e-04) (hash(x)=25291413) +3032 train 7.012567 (lr=1.7500e-04) (hash(x)=24590244) +3033 train 7.259946 (lr=1.7500e-04) (hash(x)=28880142) +3034 train 6.962930 (lr=1.7500e-04) (hash(x)=23372199) +3035 train 6.960403 (lr=1.7500e-04) (hash(x)=23952225) +3036 train 7.123300 (lr=1.7500e-04) (hash(x)=24589186) +3037 train 7.097878 (lr=1.7500e-04) (hash(x)=23260323) +3038 train 7.247077 (lr=1.7500e-04) (hash(x)=25824498) +3039 train 7.192717 (lr=1.7500e-04) (hash(x)=25744274) +3040 train 7.152378 (lr=1.7500e-04) (hash(x)=21610247) +3041 train 7.278108 (lr=1.7500e-04) (hash(x)=25079786) +3042 train 6.943622 (lr=1.7500e-04) (hash(x)=23219195) +3043 train 6.869856 (lr=1.7500e-04) (hash(x)=22616739) +3044 train 7.144745 (lr=1.7500e-04) (hash(x)=24908480) +3045 train 7.020993 (lr=1.7500e-04) (hash(x)=22293489) +3046 train 7.026742 (lr=1.7500e-04) (hash(x)=23557651) +3047 train 7.052020 (lr=1.7500e-04) (hash(x)=24246963) +3048 train 7.196164 (lr=1.7500e-04) (hash(x)=24490083) +3049 train 7.162349 (lr=1.7500e-04) (hash(x)=22372895) +3050 val loss 7.2178 +3050 val perplexity 1363.4694 +3050 train 6.890507 (lr=1.7500e-04) (hash(x)=21759470) +3051 train 6.795857 (lr=1.7500e-04) (hash(x)=19407094) +3052 train 7.153028 (lr=1.7500e-04) (hash(x)=23957047) +3053 train 7.250754 (lr=1.7500e-04) (hash(x)=24719318) +3054 train 7.040034 (lr=1.7500e-04) (hash(x)=20719314) +3055 train 7.003502 (lr=1.7500e-04) (hash(x)=19724058) +3056 train 6.834835 (lr=1.7500e-04) (hash(x)=14407266) +3057 train 6.676805 (lr=1.7500e-04) (hash(x)=12468292) +3058 train 6.980791 (lr=1.7500e-04) (hash(x)=16098279) +3059 train 7.044240 (lr=1.7500e-04) (hash(x)=18836491) +3060 train 6.872221 (lr=1.7500e-04) (hash(x)=19132277) +3061 train 7.001537 (lr=1.7500e-04) (hash(x)=22814208) +3062 train 7.075604 (lr=1.7500e-04) (hash(x)=24838508) +3063 train 6.979700 (lr=1.7500e-04) (hash(x)=20705649) +3064 train 7.966338 (lr=1.7500e-04) (hash(x)=29416914) +3065 train 7.398571 (lr=1.7500e-04) (hash(x)=25972430) +3066 train 6.801700 (lr=1.7500e-04) (hash(x)=23705805) +3067 train 6.878450 (lr=1.7500e-04) (hash(x)=21325875) +3068 train 7.140734 (lr=1.7500e-04) (hash(x)=23526506) +3069 train 7.580308 (lr=1.7500e-04) (hash(x)=27282337) +3070 train 7.440196 (lr=1.7500e-04) (hash(x)=27968043) +3071 train 7.243010 (lr=1.7500e-04) (hash(x)=24938685) +3072 train 7.453041 (lr=1.7500e-04) (hash(x)=26942737) +3073 train 7.334405 (lr=1.7500e-04) (hash(x)=23506879) +3074 train 7.044026 (lr=1.7500e-04) (hash(x)=23589913) +3075 train 7.198942 (lr=1.7500e-04) (hash(x)=25152403) +3076 train 7.354527 (lr=1.7500e-04) (hash(x)=23425868) +3077 train 7.472668 (lr=1.7500e-04) (hash(x)=23966181) +3078 train 7.587026 (lr=1.7500e-04) (hash(x)=27312570) +3079 train 7.218767 (lr=1.7500e-04) (hash(x)=21707000) +3080 train 7.107325 (lr=1.7500e-04) (hash(x)=25600427) +3081 train 7.258228 (lr=1.7500e-04) (hash(x)=24270631) +3082 train 7.306594 (lr=1.7500e-04) (hash(x)=25199537) +3083 train 6.669083 (lr=1.7500e-04) (hash(x)=17952018) +3084 train 6.801576 (lr=1.7500e-04) (hash(x)=18733143) +3085 train 7.317535 (lr=1.7500e-04) (hash(x)=26946100) +3086 train 7.195493 (lr=1.7500e-04) (hash(x)=25547515) +3087 train 7.127122 (lr=1.7500e-04) (hash(x)=24948980) +3088 train 8.262822 (lr=1.7500e-04) (hash(x)=35461645) +3089 train 7.388240 (lr=1.7500e-04) (hash(x)=28330877) +3090 train 7.277675 (lr=1.7500e-04) (hash(x)=27687861) +3091 train 7.420118 (lr=1.7500e-04) (hash(x)=28012110) +3092 train 7.272985 (lr=1.7500e-04) (hash(x)=24684480) +3093 train 7.286994 (lr=1.7500e-04) (hash(x)=26225786) +3094 train 6.948509 (lr=1.7500e-04) (hash(x)=23098156) +3095 train 7.536759 (lr=1.7500e-04) (hash(x)=30773958) +3096 train 7.794669 (lr=1.7500e-04) (hash(x)=28640406) +3097 train 7.692488 (lr=1.7500e-04) (hash(x)=28201086) +3098 train 8.072163 (lr=1.7500e-04) (hash(x)=35002344) +3099 train 7.574409 (lr=1.7500e-04) (hash(x)=29481068) +3100 val loss 7.2733 +3100 val perplexity 1441.3287 +3100 train 7.148174 (lr=1.7500e-04) (hash(x)=26374528) +3101 train 7.154542 (lr=1.7500e-04) (hash(x)=24153602) +3102 train 7.143179 (lr=1.7500e-04) (hash(x)=25478746) +3103 train 7.463973 (lr=1.7500e-04) (hash(x)=26769046) +3104 train 7.064771 (lr=1.7500e-04) (hash(x)=21841970) +3105 train 7.355268 (lr=1.7500e-04) (hash(x)=27693052) +3106 train 6.883836 (lr=1.7500e-04) (hash(x)=20689448) +3107 train 7.178802 (lr=1.7500e-04) (hash(x)=26755048) +3108 train 7.216760 (lr=1.7500e-04) (hash(x)=24431904) +3109 train 7.064308 (lr=1.7500e-04) (hash(x)=21009792) +3110 train 7.123020 (lr=1.7500e-04) (hash(x)=21909003) +3111 train 7.187547 (lr=1.7500e-04) (hash(x)=18849656) +3112 train 7.286956 (lr=1.7500e-04) (hash(x)=22223376) +3113 train 7.561121 (lr=1.7500e-04) (hash(x)=25652491) +3114 train 7.456238 (lr=1.7500e-04) (hash(x)=23521434) +3115 train 7.480653 (lr=1.7500e-04) (hash(x)=25449800) +3116 train 7.812384 (lr=1.7500e-04) (hash(x)=27655847) +3117 train 7.850388 (lr=1.7500e-04) (hash(x)=29878248) +3118 train 7.835451 (lr=1.7500e-04) (hash(x)=30444094) +3119 train 7.580580 (lr=1.7500e-04) (hash(x)=24624950) +3120 train 7.028778 (lr=1.7500e-04) (hash(x)=20798511) +3121 train 7.327737 (lr=1.7500e-04) (hash(x)=26581679) +3122 train 7.223942 (lr=1.7500e-04) (hash(x)=25333422) +3123 train 7.270206 (lr=1.7500e-04) (hash(x)=26174069) +3124 train 7.330063 (lr=1.7500e-04) (hash(x)=25219475) +3125 train 7.248358 (lr=1.7500e-04) (hash(x)=20919061) +3126 train 7.122260 (lr=1.7500e-04) (hash(x)=23828688) +3127 train 7.642670 (lr=1.7500e-04) (hash(x)=27299605) +3128 train 7.022809 (lr=1.7500e-04) (hash(x)=23797514) +3129 train 7.304398 (lr=1.7500e-04) (hash(x)=23601883) +3130 train 7.496639 (lr=1.7500e-04) (hash(x)=31003964) +3131 train 7.188937 (lr=1.7500e-04) (hash(x)=24777273) +3132 train 7.112507 (lr=1.7500e-04) (hash(x)=25403249) +3133 train 7.324623 (lr=1.7500e-04) (hash(x)=28913150) +3134 train 7.258312 (lr=1.7500e-04) (hash(x)=26541508) +3135 train 7.231407 (lr=1.7500e-04) (hash(x)=24113445) +3136 train 7.044148 (lr=1.7500e-04) (hash(x)=25464565) +3137 train 7.281905 (lr=1.7500e-04) (hash(x)=26581432) +3138 train 7.108404 (lr=1.7500e-04) (hash(x)=23074513) +3139 train 6.986730 (lr=1.7500e-04) (hash(x)=23970384) +3140 train 7.235183 (lr=1.7500e-04) (hash(x)=26694495) +3141 train 7.211668 (lr=1.7500e-04) (hash(x)=26883445) +3142 train 7.364070 (lr=1.7500e-04) (hash(x)=28632211) +3143 train 7.757210 (lr=1.7500e-04) (hash(x)=32644465) +3144 train 7.485931 (lr=1.7500e-04) (hash(x)=27490443) +3145 train 7.061128 (lr=1.7500e-04) (hash(x)=23814853) +3146 train 7.510301 (lr=1.7500e-04) (hash(x)=29664236) +3147 train 7.862267 (lr=1.7500e-04) (hash(x)=29951548) +3148 train 7.537090 (lr=1.7500e-04) (hash(x)=28426503) +3149 train 6.968469 (lr=1.7500e-04) (hash(x)=23727657) +3150 val loss 7.2668 +3150 val perplexity 1432.0215 +3150 train 7.144475 (lr=1.7500e-04) (hash(x)=21430659) +3151 train 7.218085 (lr=1.7500e-04) (hash(x)=25829219) +3152 train 7.393446 (lr=1.7500e-04) (hash(x)=29735208) +3153 train 7.425380 (lr=1.7500e-04) (hash(x)=28173447) +3154 train 7.117271 (lr=1.7500e-04) (hash(x)=22909641) +3155 train 7.270198 (lr=1.7500e-04) (hash(x)=20556094) +3156 train 7.005820 (lr=1.7500e-04) (hash(x)=24013769) +3157 train 6.995758 (lr=1.7500e-04) (hash(x)=22525971) +3158 train 7.067120 (lr=1.7500e-04) (hash(x)=25492728) +3159 train 7.137017 (lr=1.7500e-04) (hash(x)=25194550) +3160 train 7.234410 (lr=1.7500e-04) (hash(x)=25610603) +3161 train 7.236758 (lr=1.7500e-04) (hash(x)=23848640) +3162 train 7.043049 (lr=1.7500e-04) (hash(x)=24082226) +3163 train 7.430910 (lr=1.7500e-04) (hash(x)=28482186) +3164 train 7.311214 (lr=1.7500e-04) (hash(x)=27542978) +3165 train 7.118398 (lr=1.7500e-04) (hash(x)=22540954) +3166 train 7.216026 (lr=1.7500e-04) (hash(x)=26103641) +3167 train 7.153037 (lr=1.7500e-04) (hash(x)=25941804) +3168 train 7.180428 (lr=1.7500e-04) (hash(x)=25965921) +3169 train 7.394347 (lr=1.7500e-04) (hash(x)=25631269) +3170 train 7.016769 (lr=1.7500e-04) (hash(x)=23471525) +3171 train 7.240996 (lr=1.7500e-04) (hash(x)=27049208) +3172 train 7.238731 (lr=1.7500e-04) (hash(x)=27074992) +3173 train 7.168911 (lr=1.7500e-04) (hash(x)=25712617) +3174 train 7.151556 (lr=1.7500e-04) (hash(x)=25884917) +3175 train 7.176029 (lr=1.7500e-04) (hash(x)=24075727) +3176 train 7.047001 (lr=1.7500e-04) (hash(x)=23681759) +3177 train 7.319673 (lr=1.7500e-04) (hash(x)=25786577) +3178 train 7.290185 (lr=1.7500e-04) (hash(x)=27307614) +3179 train 7.305413 (lr=1.7500e-04) (hash(x)=25082806) +3180 train 7.276196 (lr=1.7500e-04) (hash(x)=26098308) +3181 train 7.063709 (lr=1.7500e-04) (hash(x)=24080140) +3182 train 7.265873 (lr=1.7500e-04) (hash(x)=26399395) +3183 train 7.296182 (lr=1.7500e-04) (hash(x)=23104539) +3184 train 6.968720 (lr=1.7500e-04) (hash(x)=23356930) +3185 train 7.218074 (lr=1.7500e-04) (hash(x)=27972420) +3186 train 6.904121 (lr=1.7500e-04) (hash(x)=21338924) +3187 train 7.319483 (lr=1.7500e-04) (hash(x)=25351113) +3188 train 7.265499 (lr=1.7500e-04) (hash(x)=26019439) +3189 train 7.307457 (lr=1.7500e-04) (hash(x)=30149312) +3190 train 7.039196 (lr=1.7500e-04) (hash(x)=23028152) +3191 train 7.391645 (lr=1.7500e-04) (hash(x)=23018983) +3192 train 7.037212 (lr=1.7500e-04) (hash(x)=23190787) +3193 train 7.444917 (lr=1.7500e-04) (hash(x)=27798543) +3194 train 7.203179 (lr=1.7500e-04) (hash(x)=25193663) +3195 train 7.036667 (lr=1.7500e-04) (hash(x)=25302106) +3196 train 7.172456 (lr=1.7500e-04) (hash(x)=24325364) +3197 train 7.192887 (lr=1.7500e-04) (hash(x)=25399101) +3198 train 7.031993 (lr=1.7500e-04) (hash(x)=23606439) +3199 train 7.073779 (lr=1.7500e-04) (hash(x)=24422929) +3200 val loss 7.2081 +3200 val perplexity 1350.3743 +3200 train 7.251046 (lr=1.7500e-04) (hash(x)=24760381) +3201 train 6.935010 (lr=1.7500e-04) (hash(x)=23278576) +3202 train 7.150862 (lr=1.7500e-04) (hash(x)=24897511) +3203 train 7.441368 (lr=1.7500e-04) (hash(x)=29052117) +3204 train 7.146909 (lr=1.7500e-04) (hash(x)=25772923) +3205 train 7.320833 (lr=1.7500e-04) (hash(x)=25885977) +3206 train 7.107654 (lr=1.7500e-04) (hash(x)=21985272) +3207 train 7.036283 (lr=1.7500e-04) (hash(x)=23389696) +3208 train 6.932559 (lr=1.7500e-04) (hash(x)=25299042) +3209 train 7.198628 (lr=1.7500e-04) (hash(x)=23703987) +3210 train 7.089868 (lr=1.7500e-04) (hash(x)=23362342) +3211 train 7.176956 (lr=1.7500e-04) (hash(x)=23962503) +3212 train 7.053406 (lr=1.7500e-04) (hash(x)=21216023) +3213 train 7.154515 (lr=1.7500e-04) (hash(x)=25841931) +3214 train 7.014099 (lr=1.7500e-04) (hash(x)=23631428) +3215 train 7.378383 (lr=1.7500e-04) (hash(x)=29102969) +3216 train 7.190830 (lr=1.7500e-04) (hash(x)=25782766) +3217 train 7.439766 (lr=1.7500e-04) (hash(x)=28825867) +3218 train 7.364563 (lr=1.7500e-04) (hash(x)=24609499) +3219 train 7.304210 (lr=1.7500e-04) (hash(x)=24948166) +3220 train 7.393272 (lr=1.7500e-04) (hash(x)=26919841) +3221 train 7.216313 (lr=1.7500e-04) (hash(x)=27236198) +3222 train 7.035141 (lr=1.7500e-04) (hash(x)=24029305) +3223 train 7.583833 (lr=1.7500e-04) (hash(x)=28359859) +3224 train 7.385297 (lr=1.7500e-04) (hash(x)=24886008) +3225 train 7.217316 (lr=1.7500e-04) (hash(x)=27159867) +3226 train 7.448469 (lr=1.7500e-04) (hash(x)=20672023) +3227 train 7.118626 (lr=1.7500e-04) (hash(x)=22360298) +3228 train 7.527350 (lr=1.7500e-04) (hash(x)=27478658) +3229 train 7.293443 (lr=1.7500e-04) (hash(x)=26575886) +3230 train 7.487932 (lr=1.7500e-04) (hash(x)=26890615) +3231 train 7.146015 (lr=1.7500e-04) (hash(x)=24630955) +3232 train 7.407338 (lr=1.7500e-04) (hash(x)=27016054) +3233 train 7.682565 (lr=1.7500e-04) (hash(x)=28444407) +3234 train 7.110875 (lr=1.7500e-04) (hash(x)=24053336) +3235 train 7.417221 (lr=1.7500e-04) (hash(x)=26897402) +3236 train 7.580935 (lr=1.7500e-04) (hash(x)=29451214) +3237 train 7.364823 (lr=1.7500e-04) (hash(x)=27268677) +3238 train 7.489891 (lr=1.7500e-04) (hash(x)=27494000) +3239 train 7.179936 (lr=1.7500e-04) (hash(x)=22969113) +3240 train 7.140260 (lr=1.7500e-04) (hash(x)=21944576) +3241 train 7.252510 (lr=1.7500e-04) (hash(x)=21671079) +3242 train 7.127599 (lr=1.7500e-04) (hash(x)=23912980) +3243 train 7.140590 (lr=1.7500e-04) (hash(x)=25205781) +3244 train 7.116332 (lr=1.7500e-04) (hash(x)=25654244) +3245 train 7.027152 (lr=1.7500e-04) (hash(x)=23335929) +3246 train 7.439031 (lr=1.7500e-04) (hash(x)=27953926) +3247 train 7.229547 (lr=1.7500e-04) (hash(x)=27004415) +3248 train 6.924649 (lr=1.7500e-04) (hash(x)=20471566) +3249 train 7.116652 (lr=1.7500e-04) (hash(x)=25797941) +3250 val loss 7.2251 +3250 val perplexity 1373.4662 +3250 train 6.991255 (lr=1.7500e-04) (hash(x)=21787064) +3251 train 7.037096 (lr=1.7500e-04) (hash(x)=22974875) +3252 train 7.230451 (lr=1.7500e-04) (hash(x)=28431267) +3253 train 7.158731 (lr=1.7500e-04) (hash(x)=25584910) +3254 train 6.953928 (lr=1.7500e-04) (hash(x)=23888922) +3255 train 7.178961 (lr=1.7500e-04) (hash(x)=22265063) +3256 train 6.755512 (lr=1.7500e-04) (hash(x)=21926624) +3257 train 7.050066 (lr=1.7500e-04) (hash(x)=23073191) +3258 train 7.068178 (lr=1.7500e-04) (hash(x)=24409183) +3259 train 7.111845 (lr=1.7500e-04) (hash(x)=23312114) +3260 train 7.005850 (lr=1.7500e-04) (hash(x)=21001289) +3261 train 7.227974 (lr=1.7500e-04) (hash(x)=25514824) +3262 train 7.007371 (lr=1.7500e-04) (hash(x)=22526800) +3263 train 7.391545 (lr=1.7500e-04) (hash(x)=26905990) +3264 train 7.101974 (lr=1.7500e-04) (hash(x)=24469631) +3265 train 6.915090 (lr=1.7500e-04) (hash(x)=21149081) +3266 train 7.144107 (lr=1.7500e-04) (hash(x)=24696215) +3267 train 7.512033 (lr=1.7500e-04) (hash(x)=27089280) +3268 train 7.071036 (lr=1.7500e-04) (hash(x)=23100446) +3269 train 7.288182 (lr=1.7500e-04) (hash(x)=25061229) +3270 train 7.176149 (lr=1.7500e-04) (hash(x)=24337543) +3271 train 7.221596 (lr=1.7500e-04) (hash(x)=24047679) +3272 train 7.269293 (lr=1.7500e-04) (hash(x)=27616773) +3273 train 7.145405 (lr=1.7500e-04) (hash(x)=25315110) +3274 train 7.243127 (lr=1.7500e-04) (hash(x)=28354645) +3275 train 7.078088 (lr=1.7500e-04) (hash(x)=25034684) +3276 train 7.123499 (lr=1.7500e-04) (hash(x)=23550342) +3277 train 7.859019 (lr=1.7500e-04) (hash(x)=28661487) +3278 train 7.361515 (lr=1.7500e-04) (hash(x)=24724622) +3279 train 7.293668 (lr=1.7500e-04) (hash(x)=26905582) +3280 train 7.372215 (lr=1.7500e-04) (hash(x)=26838818) +3281 train 7.104833 (lr=1.7500e-04) (hash(x)=23949017) +3282 train 6.639139 (lr=1.7500e-04) (hash(x)=18846300) +3283 train 6.960340 (lr=1.7500e-04) (hash(x)=21406950) +3284 train 6.830200 (lr=1.7500e-04) (hash(x)=21157696) +3285 train 6.924850 (lr=1.7500e-04) (hash(x)=21440152) +3286 train 7.106207 (lr=1.7500e-04) (hash(x)=26749182) +3287 train 7.281330 (lr=1.7500e-04) (hash(x)=29018970) +3288 train 7.238361 (lr=1.7500e-04) (hash(x)=27577517) +3289 train 6.868958 (lr=1.7500e-04) (hash(x)=19190537) +3290 train 6.896472 (lr=1.7500e-04) (hash(x)=21957991) +3291 train 6.919336 (lr=1.7500e-04) (hash(x)=20853530) +3292 train 6.847821 (lr=1.7500e-04) (hash(x)=22291731) +3293 train 7.068577 (lr=1.7500e-04) (hash(x)=23786853) +3294 train 7.206127 (lr=1.7500e-04) (hash(x)=25740147) +3295 train 7.334392 (lr=1.7500e-04) (hash(x)=24503315) +3296 train 7.031699 (lr=1.7500e-04) (hash(x)=22541728) +3297 train 7.377399 (lr=1.7500e-04) (hash(x)=27067328) +3298 train 7.024017 (lr=1.7500e-04) (hash(x)=22600715) +3299 train 7.026230 (lr=1.7500e-04) (hash(x)=23080074) +3300 val loss 7.2027 +3300 val perplexity 1343.1144 +3300 train 6.807508 (lr=1.7500e-04) (hash(x)=22097758) +3301 train 7.028095 (lr=1.7500e-04) (hash(x)=24105430) +3302 train 6.871031 (lr=1.7500e-04) (hash(x)=23343775) +3303 train 7.112456 (lr=1.7500e-04) (hash(x)=22607537) +3304 train 7.190595 (lr=1.7500e-04) (hash(x)=26501182) +3305 train 7.427882 (lr=1.7500e-04) (hash(x)=26063650) +3306 train 7.060760 (lr=1.7500e-04) (hash(x)=23486602) +3307 train 8.175074 (lr=1.7500e-04) (hash(x)=32179773) +3308 train 11.732677 (lr=1.7500e-04) (hash(x)=66155855) +3309 train 8.567499 (lr=1.7500e-04) (hash(x)=37724427) +3310 train 7.571027 (lr=1.7500e-04) (hash(x)=28861610) +3311 train 7.519446 (lr=1.7500e-04) (hash(x)=26690225) +3312 train 7.126771 (lr=1.7500e-04) (hash(x)=24136450) +3313 train 7.320767 (lr=1.7500e-04) (hash(x)=23702010) +3314 train 7.552605 (lr=1.7500e-04) (hash(x)=28761762) +3315 train 6.916145 (lr=1.7500e-04) (hash(x)=22109609) +3316 train 7.236978 (lr=1.7500e-04) (hash(x)=25168631) +3317 train 7.106453 (lr=1.7500e-04) (hash(x)=24503786) +3318 train 7.113050 (lr=1.7500e-04) (hash(x)=23698606) +3319 train 7.166194 (lr=1.7500e-04) (hash(x)=24226255) +3320 train 7.752972 (lr=1.7500e-04) (hash(x)=31110577) +3321 train 7.133283 (lr=1.7500e-04) (hash(x)=24752754) +3322 train 6.991096 (lr=1.7500e-04) (hash(x)=21135610) +3323 train 6.952728 (lr=1.7500e-04) (hash(x)=23013573) +3324 train 6.714935 (lr=1.7500e-04) (hash(x)=20289715) +3325 train 6.968730 (lr=1.7500e-04) (hash(x)=22700287) +3326 train 7.073655 (lr=1.7500e-04) (hash(x)=21320362) +3327 train 7.169806 (lr=1.7500e-04) (hash(x)=23622702) +3328 train 7.451309 (lr=1.7500e-04) (hash(x)=27435461) +3329 train 7.181591 (lr=1.7500e-04) (hash(x)=25435452) +3330 train 7.209974 (lr=1.7500e-04) (hash(x)=27952557) +3331 train 6.844965 (lr=1.7500e-04) (hash(x)=21517429) +3332 train 6.988032 (lr=1.7500e-04) (hash(x)=24288985) +3333 train 7.164383 (lr=1.7500e-04) (hash(x)=23374788) +3334 train 6.959897 (lr=1.7500e-04) (hash(x)=22042499) +3335 train 7.210117 (lr=1.7500e-04) (hash(x)=23910425) +3336 train 7.537857 (lr=1.7500e-04) (hash(x)=28118508) +3337 train 7.361913 (lr=1.7500e-04) (hash(x)=26737440) +3338 train 7.140655 (lr=1.7500e-04) (hash(x)=24472271) +3339 train 7.041942 (lr=1.7500e-04) (hash(x)=24407484) +3340 train 7.620187 (lr=1.7500e-04) (hash(x)=27908937) +3341 train 7.724225 (lr=1.7500e-04) (hash(x)=29038937) +3342 train 7.475522 (lr=1.7500e-04) (hash(x)=24802580) +3343 train 7.476711 (lr=1.7500e-04) (hash(x)=27213318) +3344 train 7.508427 (lr=1.7500e-04) (hash(x)=28693458) +3345 train 6.812370 (lr=1.7500e-04) (hash(x)=20332324) +3346 train 7.212564 (lr=1.7500e-04) (hash(x)=26726007) +3347 train 7.122100 (lr=1.7500e-04) (hash(x)=25524191) +3348 train 7.207492 (lr=1.7500e-04) (hash(x)=25553293) +3349 train 7.120183 (lr=1.7500e-04) (hash(x)=25614848) +3350 val loss 7.1928 +3350 val perplexity 1329.8463 +3350 train 7.232053 (lr=1.7500e-04) (hash(x)=25747903) +3351 train 7.197097 (lr=1.7500e-04) (hash(x)=26701577) +3352 train 6.925210 (lr=1.7500e-04) (hash(x)=21964135) +3353 train 7.064117 (lr=1.7500e-04) (hash(x)=24461007) +3354 train 7.093141 (lr=1.7500e-04) (hash(x)=25818495) +3355 train 6.902069 (lr=1.7500e-04) (hash(x)=22091266) +3356 train 6.894232 (lr=1.7500e-04) (hash(x)=24476213) +3357 train 7.314798 (lr=1.7500e-04) (hash(x)=24500423) +3358 train 7.044902 (lr=1.7500e-04) (hash(x)=21754841) +3359 train 7.368613 (lr=1.7500e-04) (hash(x)=26216794) +3360 train 6.851526 (lr=1.7500e-04) (hash(x)=24267249) +3361 train 7.201099 (lr=1.7500e-04) (hash(x)=23143515) +3362 train 7.077955 (lr=1.7500e-04) (hash(x)=24120302) +3363 train 7.242443 (lr=1.7500e-04) (hash(x)=20817340) +3364 train 7.205419 (lr=1.7500e-04) (hash(x)=22285847) +3365 train 7.517899 (lr=1.7500e-04) (hash(x)=28151597) +3366 train 7.937238 (lr=1.7500e-04) (hash(x)=31593285) +3367 train 7.578536 (lr=1.7500e-04) (hash(x)=27579623) +3368 train 7.181725 (lr=1.7500e-04) (hash(x)=24995988) +3369 train 6.849862 (lr=1.7500e-04) (hash(x)=22166810) +3370 train 7.080216 (lr=1.7500e-04) (hash(x)=23948298) +3371 train 6.983396 (lr=1.7500e-04) (hash(x)=21532187) +3372 train 7.050249 (lr=1.7500e-04) (hash(x)=23571652) +3373 train 7.431360 (lr=1.7500e-04) (hash(x)=26911513) +3374 train 7.363864 (lr=1.7500e-04) (hash(x)=24011329) +3375 train 7.578914 (lr=1.7500e-04) (hash(x)=26086198) +3376 train 7.130223 (lr=1.7500e-04) (hash(x)=22844402) +3377 train 7.111379 (lr=1.7500e-04) (hash(x)=21817762) +3378 train 7.164009 (lr=1.7500e-04) (hash(x)=23903232) +3379 train 7.117809 (lr=1.7500e-04) (hash(x)=23911729) +3380 train 7.105252 (lr=1.7500e-04) (hash(x)=24485288) +3381 train 7.288293 (lr=1.7500e-04) (hash(x)=27955492) +3382 train 6.978971 (lr=1.7500e-04) (hash(x)=25884586) +3383 train 7.204484 (lr=1.7500e-04) (hash(x)=24863441) +3384 train 7.506510 (lr=1.7500e-04) (hash(x)=22045992) +3385 train 7.647621 (lr=1.7500e-04) (hash(x)=29174796) +3386 train 7.968079 (lr=1.7500e-04) (hash(x)=32589942) +3387 train 7.541742 (lr=1.7500e-04) (hash(x)=28856978) +3388 train 6.968727 (lr=1.7500e-04) (hash(x)=21667904) +3389 train 6.990428 (lr=1.7500e-04) (hash(x)=23431801) +3390 train 6.814125 (lr=1.7500e-04) (hash(x)=20877285) +3391 train 7.061344 (lr=1.7500e-04) (hash(x)=25236385) +3392 train 7.272064 (lr=1.7500e-04) (hash(x)=25373071) +3393 train 7.431787 (lr=1.7500e-04) (hash(x)=25713464) +3394 train 7.391013 (lr=1.7500e-04) (hash(x)=25713475) +3395 train 7.255470 (lr=1.7500e-04) (hash(x)=24278687) +3396 train 7.363290 (lr=1.7500e-04) (hash(x)=27491349) +3397 train 7.241493 (lr=1.7500e-04) (hash(x)=24513692) +3398 train 7.378632 (lr=1.7500e-04) (hash(x)=26853415) +3399 train 7.452119 (lr=1.7500e-04) (hash(x)=25330803) +3400 val loss 7.2234 +3400 val perplexity 1371.0916 +3400 train 7.387679 (lr=1.7500e-04) (hash(x)=26578066) +3401 train 7.435047 (lr=1.7500e-04) (hash(x)=26811522) +3402 train 7.169132 (lr=1.7500e-04) (hash(x)=25611092) +3403 train 6.987248 (lr=1.7500e-04) (hash(x)=21568545) +3404 train 6.981776 (lr=1.7500e-04) (hash(x)=22756484) +3405 train 7.229363 (lr=1.7500e-04) (hash(x)=27927608) +3406 train 7.235342 (lr=1.7500e-04) (hash(x)=27497018) +3407 train 7.023132 (lr=1.7500e-04) (hash(x)=22508532) +3408 train 7.460773 (lr=1.7500e-04) (hash(x)=26673287) +3409 train 7.132726 (lr=1.7500e-04) (hash(x)=23675869) +3410 train 7.068317 (lr=1.7500e-04) (hash(x)=25496948) +3411 train 7.049857 (lr=1.7500e-04) (hash(x)=24850662) +3412 train 7.360494 (lr=1.7500e-04) (hash(x)=29790167) +3413 train 6.974829 (lr=1.7500e-04) (hash(x)=24193434) +3414 train 7.321641 (lr=1.7500e-04) (hash(x)=25310919) +3415 train 6.996536 (lr=1.7500e-04) (hash(x)=21799261) +3416 train 7.325777 (lr=1.7500e-04) (hash(x)=26620074) +3417 train 7.254846 (lr=1.7500e-04) (hash(x)=26719309) +3418 train 7.594239 (lr=1.7500e-04) (hash(x)=23190530) +3419 train 7.242246 (lr=1.7500e-04) (hash(x)=24884891) +3420 train 7.225069 (lr=1.7500e-04) (hash(x)=25545849) +3421 train 7.211844 (lr=1.7500e-04) (hash(x)=26021405) +3422 train 7.116608 (lr=1.7500e-04) (hash(x)=23887343) +3423 train 7.161766 (lr=1.7500e-04) (hash(x)=26311168) +3424 train 6.880823 (lr=1.7500e-04) (hash(x)=21051541) +3425 train 7.223312 (lr=1.7500e-04) (hash(x)=23553179) +3426 train 7.107169 (lr=1.7500e-04) (hash(x)=24345540) +3427 train 7.567232 (lr=1.7500e-04) (hash(x)=27549895) +3428 train 6.895984 (lr=1.7500e-04) (hash(x)=22559753) +3429 train 6.863423 (lr=1.7500e-04) (hash(x)=21647642) +3430 train 6.740594 (lr=1.7500e-04) (hash(x)=20130901) +3431 train 6.921104 (lr=1.7500e-04) (hash(x)=20977430) +3432 train 6.905962 (lr=1.7500e-04) (hash(x)=21356429) +3433 train 6.918420 (lr=1.7500e-04) (hash(x)=23494380) +3434 train 7.157014 (lr=1.7500e-04) (hash(x)=23805501) +3435 train 7.113074 (lr=1.7500e-04) (hash(x)=23448855) +3436 train 7.462114 (lr=1.7500e-04) (hash(x)=26000319) +3437 train 6.957891 (lr=1.7500e-04) (hash(x)=21760032) +3438 train 7.070671 (lr=1.7500e-04) (hash(x)=24424886) +3439 train 7.460866 (lr=1.7500e-04) (hash(x)=26941617) +3440 train 7.475752 (lr=1.7500e-04) (hash(x)=26798528) +3441 train 7.499890 (lr=1.7500e-04) (hash(x)=27464193) +3442 train 7.400321 (lr=1.7500e-04) (hash(x)=25649118) +3443 train 7.427318 (lr=1.7500e-04) (hash(x)=26953192) +3444 train 7.262464 (lr=1.7500e-04) (hash(x)=22224958) +3445 train 7.077669 (lr=1.7500e-04) (hash(x)=24044587) +3446 train 7.530373 (lr=1.7500e-04) (hash(x)=29584466) +3447 train 7.877117 (lr=1.7500e-04) (hash(x)=30008957) +3448 train 7.759664 (lr=1.7500e-04) (hash(x)=26059290) +3449 train 6.763605 (lr=1.7500e-04) (hash(x)=19733965) +3450 val loss 7.2172 +3450 val perplexity 1362.6608 +3450 train 7.259402 (lr=1.7500e-04) (hash(x)=23960200) +3451 train 7.466934 (lr=1.7500e-04) (hash(x)=27069893) +3452 train 7.081334 (lr=1.7500e-04) (hash(x)=23947772) +3453 train 7.139050 (lr=1.7500e-04) (hash(x)=22707406) +3454 train 7.296085 (lr=1.7500e-04) (hash(x)=27832550) +3455 train 7.180001 (lr=1.7500e-04) (hash(x)=27125962) +3456 train 7.066682 (lr=1.7500e-04) (hash(x)=24510254) +3457 train 6.863248 (lr=1.7500e-04) (hash(x)=23545652) +3458 train 6.959206 (lr=1.7500e-04) (hash(x)=23554751) +3459 train 7.083217 (lr=1.7500e-04) (hash(x)=23341415) +3460 train 7.213527 (lr=1.7500e-04) (hash(x)=21784583) +3461 train 7.019448 (lr=1.7500e-04) (hash(x)=22214769) +3462 train 7.104676 (lr=1.7500e-04) (hash(x)=24206922) +3463 train 7.212940 (lr=1.7500e-04) (hash(x)=25888358) +3464 train 7.053460 (lr=1.7500e-04) (hash(x)=22689666) +3465 train 7.134786 (lr=1.7500e-04) (hash(x)=24918697) +3466 train 7.424528 (lr=1.7500e-04) (hash(x)=28237214) +3467 train 7.528797 (lr=1.7500e-04) (hash(x)=26761645) +3468 train 7.210937 (lr=1.7500e-04) (hash(x)=26979307) +3469 train 7.084485 (lr=1.7500e-04) (hash(x)=23553754) +3470 train 7.244132 (lr=1.7500e-04) (hash(x)=25256849) +3471 train 7.090164 (lr=1.7500e-04) (hash(x)=21725719) +3472 train 7.209329 (lr=1.7500e-04) (hash(x)=24897801) +3473 train 7.112587 (lr=1.7500e-04) (hash(x)=26175307) +3474 train 6.930013 (lr=1.7500e-04) (hash(x)=23309218) +3475 train 7.021270 (lr=1.7500e-04) (hash(x)=25746493) +3476 train 7.352359 (lr=1.7500e-04) (hash(x)=27169613) +3477 train 7.026443 (lr=1.7500e-04) (hash(x)=22937341) +3478 train 7.135162 (lr=1.7500e-04) (hash(x)=24250636) +3479 train 6.964552 (lr=1.7500e-04) (hash(x)=21669704) +3480 train 6.944828 (lr=1.7500e-04) (hash(x)=24431839) +3481 train 7.009268 (lr=1.7500e-04) (hash(x)=22763387) +3482 train 6.947610 (lr=1.7500e-04) (hash(x)=20489446) +3483 train 6.926874 (lr=1.7500e-04) (hash(x)=21167493) +3484 train 6.892438 (lr=1.7500e-04) (hash(x)=23465087) +3485 train 7.189943 (lr=1.7500e-04) (hash(x)=26175023) +3486 train 7.275075 (lr=1.7500e-04) (hash(x)=24986207) +3487 train 6.876287 (lr=1.7500e-04) (hash(x)=23166993) +3488 train 7.157880 (lr=1.7500e-04) (hash(x)=25281216) +3489 train 6.958724 (lr=1.7500e-04) (hash(x)=21824285) +3490 train 6.984529 (lr=1.7500e-04) (hash(x)=22352750) +3491 train 7.254926 (lr=1.7500e-04) (hash(x)=23947208) +3492 train 7.263008 (lr=1.7500e-04) (hash(x)=26257363) +3493 train 7.100029 (lr=1.7500e-04) (hash(x)=25103214) +3494 train 7.166355 (lr=1.7500e-04) (hash(x)=25267583) +3495 train 7.251809 (lr=1.7500e-04) (hash(x)=26235974) +3496 train 7.451217 (lr=1.7500e-04) (hash(x)=26430769) +3497 train 7.829006 (lr=1.7500e-04) (hash(x)=28282027) +3498 train 7.740407 (lr=1.7500e-04) (hash(x)=28386462) +3499 train 7.330841 (lr=1.7500e-04) (hash(x)=29822604) +3500 val loss 7.2091 +3500 val perplexity 1351.6349 +3500 train 7.237160 (lr=1.7500e-04) (hash(x)=29225386) +3501 train 7.142135 (lr=1.7500e-04) (hash(x)=25249294) +3502 train 6.883392 (lr=1.7500e-04) (hash(x)=20020741) +3503 train 7.046834 (lr=1.7500e-04) (hash(x)=25426430) +3504 train 7.012740 (lr=1.7500e-04) (hash(x)=25720411) +3505 train 7.054771 (lr=1.7500e-04) (hash(x)=25602639) +3506 train 7.136890 (lr=1.7500e-04) (hash(x)=26724388) +3507 train 7.056088 (lr=1.7500e-04) (hash(x)=26043735) +3508 train 7.018759 (lr=1.7500e-04) (hash(x)=24955163) +3509 train 6.985990 (lr=1.7500e-04) (hash(x)=20936107) +3510 train 6.995975 (lr=1.7500e-04) (hash(x)=20317378) +3511 train 7.011463 (lr=1.7500e-04) (hash(x)=22966314) +3512 train 7.342390 (lr=1.7500e-04) (hash(x)=25870930) +3513 train 7.146077 (lr=1.7500e-04) (hash(x)=24656635) +3514 train 7.453224 (lr=1.7500e-04) (hash(x)=28576810) +3515 train 7.337610 (lr=1.7500e-04) (hash(x)=27944619) +3516 train 7.219921 (lr=1.7500e-04) (hash(x)=27421509) +3517 train 6.982175 (lr=1.7500e-04) (hash(x)=20844620) +3518 train 7.119652 (lr=1.7500e-04) (hash(x)=28569406) +3519 train 7.032537 (lr=1.7500e-04) (hash(x)=23448505) +3520 train 7.186785 (lr=1.7500e-04) (hash(x)=24852577) +3521 train 7.075142 (lr=1.7500e-04) (hash(x)=23963103) +3522 train 6.953781 (lr=1.7500e-04) (hash(x)=24816516) +3523 train 7.169370 (lr=1.7500e-04) (hash(x)=24205942) +3524 train 6.735414 (lr=1.7500e-04) (hash(x)=20988660) +3525 train 6.858726 (lr=1.7500e-04) (hash(x)=21631366) +3526 train 7.061575 (lr=1.7500e-04) (hash(x)=23499370) +3527 train 7.196010 (lr=1.7500e-04) (hash(x)=26330693) +3528 train 6.827635 (lr=1.7500e-04) (hash(x)=23937176) +3529 train 7.111897 (lr=1.7500e-04) (hash(x)=27345885) +3530 train 6.808324 (lr=1.7500e-04) (hash(x)=21104610) +3531 train 7.175870 (lr=1.7500e-04) (hash(x)=24844466) +3532 train 6.537283 (lr=1.7500e-04) (hash(x)=21055483) +3533 train 6.871173 (lr=1.7500e-04) (hash(x)=23229414) +3534 train 7.183660 (lr=1.7500e-04) (hash(x)=26676920) +3535 train 7.154782 (lr=1.7500e-04) (hash(x)=29550596) +3536 train 6.893990 (lr=1.7500e-04) (hash(x)=22231942) +3537 train 7.114519 (lr=1.7500e-04) (hash(x)=25843852) +3538 train 7.251659 (lr=1.7500e-04) (hash(x)=27110533) +3539 train 6.780977 (lr=1.7500e-04) (hash(x)=20506540) +3540 train 6.926334 (lr=1.7500e-04) (hash(x)=21599346) +3541 train 7.118291 (lr=1.7500e-04) (hash(x)=26395519) +3542 train 7.084946 (lr=1.7500e-04) (hash(x)=25892512) +3543 train 7.150228 (lr=1.7500e-04) (hash(x)=22124892) +3544 train 7.004041 (lr=1.7500e-04) (hash(x)=21882567) +3545 train 7.067388 (lr=1.7500e-04) (hash(x)=24316212) +3546 train 7.005956 (lr=1.7500e-04) (hash(x)=24296310) +3547 train 7.108055 (lr=1.7500e-04) (hash(x)=24867036) +3548 train 7.067020 (lr=1.7500e-04) (hash(x)=23351896) +3549 train 7.080606 (lr=1.7500e-04) (hash(x)=21576408) +3550 val loss 7.1873 +3550 val perplexity 1322.4830 +3550 train 7.155057 (lr=1.7500e-04) (hash(x)=26377338) +3551 train 7.013452 (lr=1.7500e-04) (hash(x)=25607640) +3552 train 7.378293 (lr=1.7500e-04) (hash(x)=27619776) +3553 train 6.834975 (lr=1.7500e-04) (hash(x)=23454533) +3554 train 7.031589 (lr=1.7500e-04) (hash(x)=22542519) +3555 train 7.085419 (lr=1.7500e-04) (hash(x)=26176930) +3556 train 6.880166 (lr=1.7500e-04) (hash(x)=22815181) +3557 train 6.893137 (lr=1.7500e-04) (hash(x)=21821757) +3558 train 6.932230 (lr=1.7500e-04) (hash(x)=23988293) +3559 train 6.811380 (lr=1.7500e-04) (hash(x)=23795894) +3560 train 6.771771 (lr=1.7500e-04) (hash(x)=22898969) +3561 train 6.792296 (lr=1.7500e-04) (hash(x)=21510825) +3562 train 6.728596 (lr=1.7500e-04) (hash(x)=22499317) +3563 train 6.736810 (lr=1.7500e-04) (hash(x)=23756298) +3564 train 6.777876 (lr=1.7500e-04) (hash(x)=23964512) +3565 train 6.935037 (lr=1.7500e-04) (hash(x)=23262803) +3566 train 7.155137 (lr=1.7500e-04) (hash(x)=23347279) +3567 train 7.071181 (lr=1.7500e-04) (hash(x)=24165449) +3568 train 7.165892 (lr=1.7500e-04) (hash(x)=25503946) +3569 train 7.133405 (lr=1.7500e-04) (hash(x)=26532839) +3570 train 6.815365 (lr=1.7500e-04) (hash(x)=21889816) +3571 train 7.085123 (lr=1.7500e-04) (hash(x)=26643739) +3572 train 7.285422 (lr=1.7500e-04) (hash(x)=26826130) +3573 train 7.274278 (lr=1.7500e-04) (hash(x)=25810624) +3574 train 7.157666 (lr=1.7500e-04) (hash(x)=23080331) +3575 train 7.279148 (lr=1.7500e-04) (hash(x)=24697756) +3576 train 7.140207 (lr=1.7500e-04) (hash(x)=25158900) +3577 train 7.260700 (lr=1.7500e-04) (hash(x)=25793633) +3578 train 6.812683 (lr=1.7500e-04) (hash(x)=21468493) +3579 train 7.164628 (lr=1.7500e-04) (hash(x)=24431101) +3580 train 7.062984 (lr=1.7500e-04) (hash(x)=27314357) +3581 train 7.270378 (lr=1.7500e-04) (hash(x)=26286249) +3582 train 7.455792 (lr=1.7500e-04) (hash(x)=25954856) +3583 train 7.369650 (lr=1.7500e-04) (hash(x)=27218899) +3584 train 7.157440 (lr=1.7500e-04) (hash(x)=24249114) +3585 train 7.042347 (lr=1.7500e-04) (hash(x)=23659934) +3586 train 7.047621 (lr=1.7500e-04) (hash(x)=25995600) +3587 train 7.007604 (lr=1.7500e-04) (hash(x)=29462219) +3588 train 7.101691 (lr=1.7500e-04) (hash(x)=23346714) +3589 train 7.218746 (lr=1.7500e-04) (hash(x)=27168432) +3590 train 7.019947 (lr=1.7500e-04) (hash(x)=23954240) +3591 train 7.037846 (lr=1.7500e-04) (hash(x)=24748522) +3592 train 7.218143 (lr=1.7500e-04) (hash(x)=24887007) +3593 train 6.984981 (lr=1.7500e-04) (hash(x)=25539383) +3594 train 6.899555 (lr=1.7500e-04) (hash(x)=20104613) +3595 train 7.408160 (lr=1.7500e-04) (hash(x)=24843486) +3596 train 7.393120 (lr=1.7500e-04) (hash(x)=24357864) +3597 train 7.127584 (lr=1.7500e-04) (hash(x)=23873745) +3598 train 7.251960 (lr=1.7500e-04) (hash(x)=25142829) +3599 train 7.329160 (lr=1.7500e-04) (hash(x)=24965317) +3600 val loss 7.2366 +3600 val perplexity 1389.4282 +3600 train 6.852269 (lr=1.7500e-04) (hash(x)=18505205) +3601 train 6.915417 (lr=1.7500e-04) (hash(x)=23632877) +3602 train 7.128879 (lr=1.7500e-04) (hash(x)=23704554) +3603 train 7.277574 (lr=1.7500e-04) (hash(x)=26584754) +3604 train 6.860388 (lr=1.7500e-04) (hash(x)=20667709) +3605 train 6.741026 (lr=1.7500e-04) (hash(x)=20573248) +3606 train 6.864833 (lr=1.7500e-04) (hash(x)=23998997) +3607 train 7.058270 (lr=1.7500e-04) (hash(x)=22031210) +3608 train 7.124509 (lr=1.7500e-04) (hash(x)=24124536) +3609 train 7.028994 (lr=1.7500e-04) (hash(x)=22650144) +3610 train 7.097640 (lr=1.7500e-04) (hash(x)=23796998) +3611 train 7.162698 (lr=1.7500e-04) (hash(x)=24860582) +3612 train 6.693513 (lr=1.7500e-04) (hash(x)=20591300) +3613 train 7.136956 (lr=1.7500e-04) (hash(x)=23447130) +3614 train 7.145543 (lr=1.7500e-04) (hash(x)=26237963) +3615 train 7.224857 (lr=1.7500e-04) (hash(x)=25877990) +3616 train 7.024402 (lr=1.7500e-04) (hash(x)=24808003) +3617 train 7.225547 (lr=1.7500e-04) (hash(x)=24103543) +3618 train 7.147137 (lr=1.7500e-04) (hash(x)=24877184) +3619 train 7.233791 (lr=1.7500e-04) (hash(x)=24970646) +3620 train 7.205815 (lr=1.7500e-04) (hash(x)=25764524) +3621 train 7.374956 (lr=1.7500e-04) (hash(x)=25313591) +3622 train 7.226070 (lr=1.7500e-04) (hash(x)=23260940) +3623 train 7.155789 (lr=1.7500e-04) (hash(x)=24382381) +3624 train 7.067543 (lr=1.7500e-04) (hash(x)=24618902) +3625 train 7.238309 (lr=1.7500e-04) (hash(x)=25074871) +3626 train 6.936568 (lr=1.7500e-04) (hash(x)=24472251) +3627 train 7.072385 (lr=1.7500e-04) (hash(x)=25221746) +3628 train 7.184087 (lr=1.7500e-04) (hash(x)=27448790) +3629 train 7.143446 (lr=1.7500e-04) (hash(x)=25221431) +3630 train 6.730443 (lr=1.7500e-04) (hash(x)=22034366) +3631 train 7.287455 (lr=1.7500e-04) (hash(x)=24551999) +3632 train 7.016749 (lr=1.7500e-04) (hash(x)=24330217) +3633 train 7.095411 (lr=1.7500e-04) (hash(x)=22792380) +3634 train 6.897406 (lr=1.7500e-04) (hash(x)=22393767) +3635 train 7.209932 (lr=1.7500e-04) (hash(x)=28151378) +3636 train 7.237660 (lr=1.7500e-04) (hash(x)=26999341) +3637 train 7.277270 (lr=1.7500e-04) (hash(x)=27251870) +3638 train 7.208320 (lr=1.7500e-04) (hash(x)=23439462) +3639 train 7.291496 (lr=1.7500e-04) (hash(x)=25765516) +3640 train 7.143433 (lr=1.7500e-04) (hash(x)=24720171) +3641 train 7.332870 (lr=1.7500e-04) (hash(x)=23927187) +3642 train 7.157878 (lr=1.7500e-04) (hash(x)=23879561) +3643 train 7.262832 (lr=1.7500e-04) (hash(x)=25630696) +3644 train 6.825095 (lr=1.7500e-04) (hash(x)=22030016) +3645 train 7.282523 (lr=1.7500e-04) (hash(x)=28781600) +3646 train 7.302036 (lr=1.7500e-04) (hash(x)=26668019) +3647 train 7.316202 (lr=1.7500e-04) (hash(x)=25204247) +3648 train 7.593051 (lr=1.7500e-04) (hash(x)=31261394) +3649 train 7.355641 (lr=1.7500e-04) (hash(x)=26193103) +3650 val loss 7.2324 +3650 val perplexity 1383.5112 +3650 train 7.175376 (lr=1.7500e-04) (hash(x)=23872456) +3651 train 7.031192 (lr=1.7500e-04) (hash(x)=26326447) +3652 train 7.060642 (lr=1.7500e-04) (hash(x)=26449631) +3653 train 7.326247 (lr=1.7500e-04) (hash(x)=26373461) +3654 train 7.160161 (lr=1.7500e-04) (hash(x)=24882768) +3655 train 7.258870 (lr=1.7500e-04) (hash(x)=26321813) +3656 train 7.265514 (lr=1.7500e-04) (hash(x)=27056428) +3657 train 7.252054 (lr=1.7500e-04) (hash(x)=24583976) +3658 train 6.927818 (lr=1.7500e-04) (hash(x)=22259624) +3659 train 7.090352 (lr=1.7500e-04) (hash(x)=25400396) +3660 train 6.927243 (lr=1.7500e-04) (hash(x)=21095507) +3661 train 7.167473 (lr=1.7500e-04) (hash(x)=27231042) +3662 train 6.977301 (lr=1.7500e-04) (hash(x)=27292771) +3663 train 7.379006 (lr=1.7500e-04) (hash(x)=25528323) +3664 train 7.148235 (lr=1.7500e-04) (hash(x)=24374502) +3665 train 6.934302 (lr=1.7500e-04) (hash(x)=22463800) +3666 train 7.221307 (lr=1.7500e-04) (hash(x)=25413960) +3667 train 7.166191 (lr=1.7500e-04) (hash(x)=24035353) +3668 train 7.096982 (lr=1.7500e-04) (hash(x)=24815852) +3669 train 6.952869 (lr=1.7500e-04) (hash(x)=22995856) +3670 train 7.264917 (lr=1.7500e-04) (hash(x)=28128238) +3671 train 7.270036 (lr=1.7500e-04) (hash(x)=25114729) +3672 train 7.023129 (lr=1.7500e-04) (hash(x)=19337726) +3673 train 7.425729 (lr=1.7500e-04) (hash(x)=26674420) +3674 train 6.942834 (lr=1.7500e-04) (hash(x)=22553270) +3675 train 6.784685 (lr=1.7500e-04) (hash(x)=21634962) +3676 train 7.015900 (lr=1.7500e-04) (hash(x)=23362669) +3677 train 7.157826 (lr=1.7500e-04) (hash(x)=24781824) +3678 train 6.672733 (lr=1.7500e-04) (hash(x)=17909688) +3679 train 7.935328 (lr=1.7500e-04) (hash(x)=31341964) +3680 train 7.396407 (lr=1.7500e-04) (hash(x)=29071335) +3681 train 6.813175 (lr=1.7500e-04) (hash(x)=19486640) +3682 train 6.973024 (lr=1.7500e-04) (hash(x)=24301133) +3683 train 7.178136 (lr=1.7500e-04) (hash(x)=29172813) +3684 train 7.766982 (lr=1.7500e-04) (hash(x)=31501337) +3685 train 7.326827 (lr=1.7500e-04) (hash(x)=27377840) +3686 train 7.098137 (lr=1.7500e-04) (hash(x)=24499761) +3687 train 7.132337 (lr=1.7500e-04) (hash(x)=26326024) +3688 train 7.109043 (lr=1.7500e-04) (hash(x)=23179996) +3689 train 6.798435 (lr=1.7500e-04) (hash(x)=20963675) +3690 train 7.066858 (lr=1.7500e-04) (hash(x)=26650521) +3691 train 6.818195 (lr=1.7500e-04) (hash(x)=20140071) +3692 train 6.814153 (lr=1.7500e-04) (hash(x)=21734340) +3693 train 7.109197 (lr=1.7500e-04) (hash(x)=23848422) +3694 train 7.169273 (lr=1.7500e-04) (hash(x)=27499953) +3695 train 7.406375 (lr=1.7500e-04) (hash(x)=27273311) +3696 train 7.329401 (lr=1.7500e-04) (hash(x)=25741091) +3697 train 7.052510 (lr=1.7500e-04) (hash(x)=22010794) +3698 train 7.141652 (lr=1.7500e-04) (hash(x)=24616138) +3699 train 7.503159 (lr=1.7500e-04) (hash(x)=31276487) +3700 val loss 7.2164 +3700 val perplexity 1361.6079 +3700 train 7.156156 (lr=1.7500e-04) (hash(x)=24042922) +3701 train 6.934798 (lr=1.7500e-04) (hash(x)=21985431) +3702 train 6.786048 (lr=1.7500e-04) (hash(x)=21336316) +3703 train 6.607648 (lr=1.7500e-04) (hash(x)=17819313) +3704 train 7.272508 (lr=1.7500e-04) (hash(x)=27033851) +3705 train 7.284432 (lr=1.7500e-04) (hash(x)=27260043) +3706 train 7.364691 (lr=1.7500e-04) (hash(x)=26847649) +3707 train 7.286580 (lr=1.7500e-04) (hash(x)=25843618) +3708 train 7.260350 (lr=1.7500e-04) (hash(x)=25828009) +3709 train 7.331783 (lr=1.7500e-04) (hash(x)=24960960) +3710 train 7.431276 (lr=1.7500e-04) (hash(x)=24852741) +3711 train 6.908560 (lr=1.7500e-04) (hash(x)=23769243) +3712 train 7.101116 (lr=1.7500e-04) (hash(x)=27110690) +3713 train 7.095993 (lr=1.7500e-04) (hash(x)=22817285) +3714 train 6.805736 (lr=1.7500e-04) (hash(x)=19618355) +3715 train 7.354099 (lr=1.7500e-04) (hash(x)=28731298) +3716 train 7.099819 (lr=1.7500e-04) (hash(x)=23091196) +3717 train 7.651822 (lr=1.7500e-04) (hash(x)=28825233) +3718 train 7.173088 (lr=1.7500e-04) (hash(x)=25778506) +3719 train 7.147948 (lr=1.7500e-04) (hash(x)=23788738) +3720 train 6.509408 (lr=1.7500e-04) (hash(x)=16684794) +3721 train 7.011464 (lr=1.7500e-04) (hash(x)=24755102) +3722 train 7.280457 (lr=1.7500e-04) (hash(x)=26839238) +3723 train 7.321555 (lr=1.7500e-04) (hash(x)=26599031) +3724 train 7.181303 (lr=1.7500e-04) (hash(x)=25945650) +3725 train 7.394812 (lr=1.7500e-04) (hash(x)=27434751) +3726 train 7.093065 (lr=1.7500e-04) (hash(x)=24814591) +3727 train 7.053525 (lr=1.7500e-04) (hash(x)=24818744) +3728 train 7.172753 (lr=1.7500e-04) (hash(x)=25649817) +3729 train 7.048013 (lr=1.7500e-04) (hash(x)=24987021) +3730 train 7.025529 (lr=1.7500e-04) (hash(x)=24667779) +3731 train 6.967438 (lr=1.7500e-04) (hash(x)=23053871) +3732 train 6.680758 (lr=1.7500e-04) (hash(x)=19264856) +3733 train 7.264310 (lr=1.7500e-04) (hash(x)=23718117) +3734 train 6.991078 (lr=1.7500e-04) (hash(x)=21904779) +3735 train 7.150563 (lr=1.7500e-04) (hash(x)=23472795) +3736 train 7.404469 (lr=1.7500e-04) (hash(x)=24650440) +3737 train 7.441998 (lr=1.7500e-04) (hash(x)=25243911) +3738 train 7.837744 (lr=1.7500e-04) (hash(x)=30423616) +3739 train 7.816036 (lr=1.7500e-04) (hash(x)=29748225) +3740 train 7.239237 (lr=1.7500e-04) (hash(x)=25180684) +3741 train 7.283571 (lr=1.7500e-04) (hash(x)=25619065) +3742 train 7.650597 (lr=1.7500e-04) (hash(x)=31847002) +3743 train 7.224135 (lr=1.7500e-04) (hash(x)=24991832) +3744 train 7.143970 (lr=1.7500e-04) (hash(x)=23836263) +3745 train 7.066332 (lr=1.7500e-04) (hash(x)=24651902) +3746 train 7.554906 (lr=1.7500e-04) (hash(x)=22936538) +3747 train 7.547261 (lr=1.7500e-04) (hash(x)=23681545) +3748 train 6.971280 (lr=1.7500e-04) (hash(x)=21140825) +3749 train 7.150698 (lr=1.7500e-04) (hash(x)=24932453) +3750 val loss 7.2155 +3750 val perplexity 1360.3275 +3750 train 7.290378 (lr=1.7500e-04) (hash(x)=25919062) +3751 train 7.087595 (lr=1.7500e-04) (hash(x)=22424066) +3752 train 7.168917 (lr=1.7500e-04) (hash(x)=23542210) +3753 train 7.003024 (lr=1.7500e-04) (hash(x)=22113561) +3754 train 6.927457 (lr=1.7500e-04) (hash(x)=24892794) +3755 train 7.379669 (lr=1.7500e-04) (hash(x)=25262748) +3756 train 7.152807 (lr=1.7500e-04) (hash(x)=24477975) +3757 train 6.942985 (lr=1.7500e-04) (hash(x)=24681189) +3758 train 6.990953 (lr=1.7500e-04) (hash(x)=24052603) +3759 train 7.211490 (lr=1.7500e-04) (hash(x)=26474878) +3760 train 7.758819 (lr=1.7500e-04) (hash(x)=28228836) +3761 train 7.282041 (lr=1.7500e-04) (hash(x)=23832522) +3762 train 7.227527 (lr=1.7500e-04) (hash(x)=24416789) +3763 train 7.041399 (lr=1.7500e-04) (hash(x)=23930593) +3764 train 7.080222 (lr=1.7500e-04) (hash(x)=23895092) +3765 train 7.030801 (lr=1.7500e-04) (hash(x)=26865287) +3766 train 7.040369 (lr=1.7500e-04) (hash(x)=21330722) +3767 train 7.128749 (lr=1.7500e-04) (hash(x)=22704349) +3768 train 7.252333 (lr=1.7500e-04) (hash(x)=27740886) +3769 train 7.215852 (lr=1.7500e-04) (hash(x)=24935936) +3770 train 7.097415 (lr=1.7500e-04) (hash(x)=23497487) +3771 train 7.308156 (lr=1.7500e-04) (hash(x)=24801048) +3772 train 7.069410 (lr=1.7500e-04) (hash(x)=25490486) +3773 train 7.091098 (lr=1.7500e-04) (hash(x)=21166466) +3774 train 7.311696 (lr=1.7500e-04) (hash(x)=23225244) +3775 train 7.122556 (lr=1.7500e-04) (hash(x)=22293673) +3776 train 7.355739 (lr=1.7500e-04) (hash(x)=25700016) +3777 train 6.935610 (lr=1.7500e-04) (hash(x)=22370207) +3778 train 7.301456 (lr=1.7500e-04) (hash(x)=25224849) +3779 train 7.189388 (lr=1.7500e-04) (hash(x)=23311934) +3780 train 6.972721 (lr=1.7500e-04) (hash(x)=19627124) +3781 train 7.372707 (lr=1.7500e-04) (hash(x)=27132838) +3782 train 7.404085 (lr=1.7500e-04) (hash(x)=27242104) +3783 train 6.888579 (lr=1.7500e-04) (hash(x)=21785487) +3784 train 7.209985 (lr=1.7500e-04) (hash(x)=25798262) +3785 train 7.106927 (lr=1.7500e-04) (hash(x)=24806937) +3786 train 6.987133 (lr=1.7500e-04) (hash(x)=24098756) +3787 train 6.950134 (lr=1.7500e-04) (hash(x)=22981456) +3788 train 7.360456 (lr=1.7500e-04) (hash(x)=22441908) +3789 train 7.278914 (lr=1.7500e-04) (hash(x)=25867804) +3790 train 7.243276 (lr=1.7500e-04) (hash(x)=22835586) +3791 train 7.446357 (lr=1.7500e-04) (hash(x)=25251063) +3792 train 7.232119 (lr=1.7500e-04) (hash(x)=27059729) +3793 train 7.218413 (lr=1.7500e-04) (hash(x)=23819311) +3794 train 6.890533 (lr=1.7500e-04) (hash(x)=21345757) +3795 train 7.168492 (lr=1.7500e-04) (hash(x)=25796422) +3796 train 6.838281 (lr=1.7500e-04) (hash(x)=21414971) +3797 train 7.122547 (lr=1.7500e-04) (hash(x)=26120920) +3798 train 7.078488 (lr=1.7500e-04) (hash(x)=22008247) +3799 train 7.165516 (lr=1.7500e-04) (hash(x)=22722211) +3800 val loss 7.2259 +3800 val perplexity 1374.5472 +3800 train 6.882240 (lr=1.7500e-04) (hash(x)=24484513) +3801 train 7.234333 (lr=1.7500e-04) (hash(x)=24463866) +3802 train 7.245197 (lr=1.7500e-04) (hash(x)=26470775) +3803 train 7.237303 (lr=1.7500e-04) (hash(x)=24296755) +3804 train 7.202148 (lr=1.7500e-04) (hash(x)=24381309) +3805 train 7.435835 (lr=1.7500e-04) (hash(x)=26781262) +3806 train 6.945805 (lr=1.7500e-04) (hash(x)=23563137) +3807 train 7.087574 (lr=1.7500e-04) (hash(x)=24522269) +3808 train 6.990030 (lr=1.7500e-04) (hash(x)=22871995) +3809 train 7.279279 (lr=1.7500e-04) (hash(x)=24751946) +3810 train 7.119778 (lr=1.7500e-04) (hash(x)=19879741) +3811 train 7.151160 (lr=1.7500e-04) (hash(x)=25617184) +3812 train 6.877606 (lr=1.7500e-04) (hash(x)=21776722) +3813 train 6.967237 (lr=1.7500e-04) (hash(x)=22663402) +3814 train 7.283971 (lr=1.7500e-04) (hash(x)=26072046) +3815 train 6.992639 (lr=1.7500e-04) (hash(x)=23329475) +3816 train 7.033662 (lr=1.7500e-04) (hash(x)=25519031) +3817 train 6.985017 (lr=1.7500e-04) (hash(x)=22846270) +3818 train 7.039865 (lr=1.7500e-04) (hash(x)=20299429) +3819 train 7.484100 (lr=1.7500e-04) (hash(x)=30652062) +3820 train 6.793813 (lr=1.7500e-04) (hash(x)=19824665) +3821 train 7.333708 (lr=1.7500e-04) (hash(x)=26698904) +3822 train 7.190789 (lr=1.7500e-04) (hash(x)=27612163) +3823 train 6.975451 (lr=1.7500e-04) (hash(x)=24735165) +3824 train 6.714325 (lr=1.7500e-04) (hash(x)=19965890) +3825 train 6.917610 (lr=1.7500e-04) (hash(x)=23518594) +3826 train 6.879084 (lr=1.7500e-04) (hash(x)=22388460) +3827 train 6.965556 (lr=1.7500e-04) (hash(x)=23795686) +3828 train 6.853299 (lr=1.7500e-04) (hash(x)=24470150) +3829 train 6.525044 (lr=1.7500e-04) (hash(x)=19483392) +3830 train 6.927238 (lr=1.7500e-04) (hash(x)=23304516) +3831 train 7.305571 (lr=1.7500e-04) (hash(x)=27002892) +3832 train 7.029031 (lr=1.7500e-04) (hash(x)=22114813) +3833 train 7.200857 (lr=1.7500e-04) (hash(x)=26221916) +3834 train 6.808455 (lr=1.7500e-04) (hash(x)=27261960) +3835 train 7.045951 (lr=1.7500e-04) (hash(x)=21189101) +3836 train 6.730945 (lr=1.7500e-04) (hash(x)=20638173) +3837 train 7.134815 (lr=1.7500e-04) (hash(x)=25497439) +3838 train 6.643718 (lr=1.7500e-04) (hash(x)=20460499) +3839 train 7.056888 (lr=1.7500e-04) (hash(x)=23499349) +3840 train 7.926324 (lr=1.7500e-04) (hash(x)=22671939) +3841 train 7.908748 (lr=1.7500e-04) (hash(x)=26809295) +3842 train 7.132736 (lr=1.7500e-04) (hash(x)=28094504) +3843 train 7.090368 (lr=1.7500e-04) (hash(x)=26807896) +3844 train 7.208187 (lr=1.7500e-04) (hash(x)=24749334) +3845 train 7.097646 (lr=1.7500e-04) (hash(x)=25031330) +3846 train 7.014278 (lr=1.7500e-04) (hash(x)=23008126) +3847 train 6.976389 (lr=1.7500e-04) (hash(x)=22461589) +3848 train 7.329893 (lr=1.7500e-04) (hash(x)=24959391) +3849 train 7.145101 (lr=1.7500e-04) (hash(x)=24239512) +3850 val loss 7.1908 +3850 val perplexity 1327.1046 +3850 train 6.977651 (lr=1.7500e-04) (hash(x)=24760422) +3851 train 7.501907 (lr=1.7500e-04) (hash(x)=26904123) +3852 train 6.629125 (lr=1.7500e-04) (hash(x)=17986444) +3853 train 6.965587 (lr=1.7500e-04) (hash(x)=21618533) +3854 train 7.047824 (lr=1.7500e-04) (hash(x)=27107027) +3855 train 7.295758 (lr=1.7500e-04) (hash(x)=26415040) +3856 train 7.820226 (lr=1.7500e-04) (hash(x)=28682703) +3857 train 7.008623 (lr=1.7500e-04) (hash(x)=22824767) +3858 train 7.151585 (lr=1.7500e-04) (hash(x)=24540450) +3859 train 7.127596 (lr=1.7500e-04) (hash(x)=24463181) +3860 train 7.057968 (lr=1.7500e-04) (hash(x)=22832558) +3861 train 7.234799 (lr=1.7500e-04) (hash(x)=26582384) +3862 train 7.854385 (lr=1.7500e-04) (hash(x)=32327364) +3863 train 7.264923 (lr=1.7500e-04) (hash(x)=26349465) +3864 train 6.998946 (lr=1.7500e-04) (hash(x)=23079414) +3865 train 7.031606 (lr=1.7500e-04) (hash(x)=23464639) +3866 train 6.867711 (lr=1.7500e-04) (hash(x)=21406620) +3867 train 6.764691 (lr=1.7500e-04) (hash(x)=21205988) +3868 train 6.853580 (lr=1.7500e-04) (hash(x)=22742634) +3869 train 6.901054 (lr=1.7500e-04) (hash(x)=24868938) +3870 train 7.244591 (lr=1.7500e-04) (hash(x)=28095283) +3871 train 6.918286 (lr=1.7500e-04) (hash(x)=21596677) +3872 train 7.164112 (lr=1.7500e-04) (hash(x)=26884381) +3873 train 7.222010 (lr=1.7500e-04) (hash(x)=26410272) +3874 train 6.995126 (lr=1.7500e-04) (hash(x)=22915785) +3875 train 6.992018 (lr=1.7500e-04) (hash(x)=23575666) +3876 train 6.966371 (lr=1.7500e-04) (hash(x)=25313223) +3877 train 6.462716 (lr=1.7500e-04) (hash(x)=16319719) +3878 train 7.067295 (lr=1.7500e-04) (hash(x)=23227579) +3879 train 6.994698 (lr=1.7500e-04) (hash(x)=24117012) +3880 train 7.058777 (lr=1.7500e-04) (hash(x)=24681517) +3881 train 6.996746 (lr=1.7500e-04) (hash(x)=23186527) +3882 train 6.976440 (lr=1.7500e-04) (hash(x)=23472784) +3883 train 7.000064 (lr=1.7500e-04) (hash(x)=26013014) +3884 train 7.177167 (lr=1.7500e-04) (hash(x)=25952206) +3885 train 7.333183 (lr=1.7500e-04) (hash(x)=23897834) +3886 train 7.023229 (lr=1.7500e-04) (hash(x)=26350364) +3887 train 7.072231 (lr=1.7500e-04) (hash(x)=24105761) +3888 train 7.180651 (lr=1.7500e-04) (hash(x)=22801707) +3889 train 7.028559 (lr=1.7500e-04) (hash(x)=21821937) +3890 train 6.950517 (lr=1.7500e-04) (hash(x)=24264640) +3891 train 6.889542 (lr=1.7500e-04) (hash(x)=20369133) +3892 train 6.881187 (lr=1.7500e-04) (hash(x)=24313506) +3893 train 6.875012 (lr=1.7500e-04) (hash(x)=22104086) +3894 train 7.104785 (lr=1.7500e-04) (hash(x)=25312602) +3895 train 7.171273 (lr=1.7500e-04) (hash(x)=25725049) +3896 train 6.982076 (lr=1.7500e-04) (hash(x)=22981231) +3897 train 6.842635 (lr=1.7500e-04) (hash(x)=18021467) +3898 train 6.821150 (lr=1.7500e-04) (hash(x)=17960254) +3899 train 6.960329 (lr=1.7500e-04) (hash(x)=19808118) +3900 val loss 7.1834 +3900 val perplexity 1317.3555 +3900 train 6.770433 (lr=1.7500e-04) (hash(x)=21022829) +3901 train 6.928877 (lr=1.7500e-04) (hash(x)=22434663) +3902 train 6.686482 (lr=1.7500e-04) (hash(x)=20208091) +3903 train 6.838209 (lr=1.7500e-04) (hash(x)=22892776) +3904 train 6.926350 (lr=1.7500e-04) (hash(x)=21554367) +3905 train 7.069768 (lr=1.7500e-04) (hash(x)=23704875) +3906 train 7.003575 (lr=1.7500e-04) (hash(x)=21690340) +3907 train 6.976837 (lr=1.7500e-04) (hash(x)=23736780) +3908 train 6.813546 (lr=1.7500e-04) (hash(x)=21060920) +3909 train 6.779757 (lr=1.7500e-04) (hash(x)=20091559) +3910 train 7.022777 (lr=1.7500e-04) (hash(x)=22147974) +3911 train 6.997982 (lr=1.7500e-04) (hash(x)=21630383) +3912 train 7.239049 (lr=1.7500e-04) (hash(x)=28339385) +3913 train 7.069108 (lr=1.7500e-04) (hash(x)=25355505) +3914 train 6.943170 (lr=1.7500e-04) (hash(x)=20843914) +3915 train 7.415128 (lr=1.7500e-04) (hash(x)=25397467) +3916 train 7.130700 (lr=1.7500e-04) (hash(x)=23587501) +3917 train 6.783502 (lr=1.7500e-04) (hash(x)=19036533) +3918 train 6.965160 (lr=1.7500e-04) (hash(x)=29749389) +3919 train 6.825258 (lr=1.7500e-04) (hash(x)=24727094) +3920 train 6.877875 (lr=1.7500e-04) (hash(x)=22723450) +3921 train 7.049274 (lr=1.7500e-04) (hash(x)=24424680) +3922 train 7.188539 (lr=1.7500e-04) (hash(x)=25817917) +3923 train 6.941356 (lr=1.7500e-04) (hash(x)=23951182) +3924 train 6.990026 (lr=1.7500e-04) (hash(x)=21177944) +3925 train 6.842972 (lr=1.7500e-04) (hash(x)=23533768) +3926 train 7.045918 (lr=1.7500e-04) (hash(x)=24263615) +3927 train 6.889008 (lr=1.7500e-04) (hash(x)=22835000) +3928 train 7.102020 (lr=1.7500e-04) (hash(x)=26076156) +3929 train 7.067903 (lr=1.7500e-04) (hash(x)=25171508) +3930 train 7.062412 (lr=1.7500e-04) (hash(x)=22021396) +3931 train 7.311697 (lr=1.7500e-04) (hash(x)=28767849) +3932 train 7.278730 (lr=1.7500e-04) (hash(x)=29497606) +3933 train 6.933743 (lr=1.7500e-04) (hash(x)=22723124) +3934 train 7.301647 (lr=1.7500e-04) (hash(x)=27106616) +3935 train 7.115608 (lr=1.7500e-04) (hash(x)=22839049) +3936 train 7.166790 (lr=1.7500e-04) (hash(x)=25101923) +3937 train 7.090327 (lr=1.7500e-04) (hash(x)=25945975) +3938 train 7.227907 (lr=1.7500e-04) (hash(x)=25382013) +3939 train 6.806161 (lr=1.7500e-04) (hash(x)=19930900) +3940 train 6.944988 (lr=1.7500e-04) (hash(x)=22202373) +3941 train 7.109036 (lr=1.7500e-04) (hash(x)=24592992) +3942 train 7.023353 (lr=1.7500e-04) (hash(x)=25002271) +3943 train 6.837386 (lr=1.7500e-04) (hash(x)=20654136) +3944 train 6.888767 (lr=1.7500e-04) (hash(x)=20061590) +3945 train 6.852384 (lr=1.7500e-04) (hash(x)=21441361) +3946 train 7.018978 (lr=1.7500e-04) (hash(x)=20055468) +3947 train 7.782985 (lr=1.7500e-04) (hash(x)=28495621) +3948 train 7.209092 (lr=1.7500e-04) (hash(x)=25959236) +3949 train 7.491807 (lr=1.7500e-04) (hash(x)=26750193) +3950 val loss 7.2169 +3950 val perplexity 1362.2593 +3950 train 7.332799 (lr=1.7500e-04) (hash(x)=25882605) +3951 train 7.412684 (lr=1.7500e-04) (hash(x)=26776000) +3952 train 7.001476 (lr=1.7500e-04) (hash(x)=24155107) +3953 train 7.051197 (lr=1.7500e-04) (hash(x)=23441845) +3954 train 6.999391 (lr=1.7500e-04) (hash(x)=22860915) +3955 train 6.798516 (lr=1.7500e-04) (hash(x)=21584429) +3956 train 6.464522 (lr=1.7500e-04) (hash(x)=16535556) +3957 train 6.519547 (lr=1.7500e-04) (hash(x)=17946180) +3958 train 7.023448 (lr=1.7500e-04) (hash(x)=25367610) +3959 train 6.917525 (lr=1.7500e-04) (hash(x)=22560658) +3960 train 7.183002 (lr=1.7500e-04) (hash(x)=23809585) +3961 train 7.445218 (lr=1.7500e-04) (hash(x)=20438213) +3962 train 7.767278 (lr=1.7500e-04) (hash(x)=30520037) +3963 train 7.396339 (lr=1.7500e-04) (hash(x)=25276565) +3964 train 7.094202 (lr=1.7500e-04) (hash(x)=26796532) +3965 train 6.904196 (lr=1.7500e-04) (hash(x)=22850475) +3966 train 7.399175 (lr=1.7500e-04) (hash(x)=25983698) +3967 train 7.271927 (lr=1.7500e-04) (hash(x)=25995933) +3968 train 7.488996 (lr=1.7500e-04) (hash(x)=25319339) +3969 train 7.127159 (lr=1.7500e-04) (hash(x)=25066892) +3970 train 7.315997 (lr=1.7500e-04) (hash(x)=26931819) +3971 train 7.261981 (lr=1.7500e-04) (hash(x)=24163910) +3972 train 7.181535 (lr=1.7500e-04) (hash(x)=25359634) +3973 train 7.077293 (lr=1.7500e-04) (hash(x)=24323444) +3974 train 7.241396 (lr=1.7500e-04) (hash(x)=26529231) +3975 train 7.238710 (lr=1.7500e-04) (hash(x)=24635394) +3976 train 7.502126 (lr=1.7500e-04) (hash(x)=24783093) +3977 train 7.631188 (lr=1.7500e-04) (hash(x)=26710509) +3978 train 7.099374 (lr=1.7500e-04) (hash(x)=25396630) +3979 train 7.004319 (lr=1.7500e-04) (hash(x)=22556381) +3980 train 7.337612 (lr=1.7500e-04) (hash(x)=26912161) +3981 train 6.916959 (lr=1.7500e-04) (hash(x)=22268078) +3982 train 7.883892 (lr=1.7500e-04) (hash(x)=30430328) +3983 train 7.497106 (lr=1.7500e-04) (hash(x)=27537228) +3984 train 6.983450 (lr=1.7500e-04) (hash(x)=24468603) +3985 train 7.257143 (lr=1.7500e-04) (hash(x)=27006663) +3986 train 7.494935 (lr=1.7500e-04) (hash(x)=27014728) +3987 train 6.959303 (lr=1.7500e-04) (hash(x)=20883633) +3988 train 7.053068 (lr=1.7500e-04) (hash(x)=23361791) +3989 train 7.159580 (lr=1.7500e-04) (hash(x)=26775925) +3990 train 7.683221 (lr=1.7500e-04) (hash(x)=30648934) +3991 train 7.207132 (lr=1.7500e-04) (hash(x)=26496730) +3992 train 7.001608 (lr=1.7500e-04) (hash(x)=25942897) +3993 train 7.012260 (lr=1.7500e-04) (hash(x)=24887111) +3994 train 6.954384 (lr=1.7500e-04) (hash(x)=22908550) +3995 train 6.689543 (lr=1.7500e-04) (hash(x)=20342150) +3996 train 6.962309 (lr=1.7500e-04) (hash(x)=22261760) +3997 train 7.012464 (lr=1.7500e-04) (hash(x)=22731641) +3998 train 6.887688 (lr=1.7500e-04) (hash(x)=20669749) +3999 train 6.833607 (lr=1.7500e-04) (hash(x)=16533310) +4000 val loss 7.1765 +4000 val perplexity 1308.3416 +4000 train 7.000967 (lr=1.7500e-04) (hash(x)=23661341) +4001 train 7.000374 (lr=1.7500e-04) (hash(x)=24644301) +4002 train 6.836368 (lr=1.7500e-04) (hash(x)=22938438) +4003 train 6.950292 (lr=1.7500e-04) (hash(x)=24315862) +4004 train 7.146466 (lr=1.7500e-04) (hash(x)=25169315) +4005 train 7.124622 (lr=1.7500e-04) (hash(x)=24752796) +4006 train 7.058736 (lr=1.7500e-04) (hash(x)=23103706) +4007 train 7.159515 (lr=1.7500e-04) (hash(x)=24881176) +4008 train 7.070771 (lr=1.7500e-04) (hash(x)=23971947) +4009 train 7.350759 (lr=1.7500e-04) (hash(x)=27741054) +4010 train 7.710708 (lr=1.7500e-04) (hash(x)=30956251) +4011 train 7.135933 (lr=1.7500e-04) (hash(x)=23649686) +4012 train 6.961044 (lr=1.7500e-04) (hash(x)=23344798) +4013 train 7.591518 (lr=1.7500e-04) (hash(x)=29529498) +4014 train 7.103458 (lr=1.7500e-04) (hash(x)=24688359) +4015 train 7.084244 (lr=1.7500e-04) (hash(x)=25593613) +4016 train 7.169290 (lr=1.7500e-04) (hash(x)=25674488) +4017 train 6.670923 (lr=1.7500e-04) (hash(x)=21345346) +4018 train 6.936397 (lr=1.7500e-04) (hash(x)=21978324) +4019 train 7.011991 (lr=1.7500e-04) (hash(x)=23669244) +4020 train 6.849997 (lr=1.7500e-04) (hash(x)=22479613) +4021 train 6.855739 (lr=1.7500e-04) (hash(x)=22855256) +4022 train 7.261070 (lr=1.7500e-04) (hash(x)=19759826) +4023 train 7.174779 (lr=1.7500e-04) (hash(x)=22886646) +4024 train 7.088483 (lr=1.7500e-04) (hash(x)=25553008) +4025 train 6.995363 (lr=1.7500e-04) (hash(x)=25487028) +4026 train 7.552705 (lr=1.7500e-04) (hash(x)=26799246) +4027 train 7.832428 (lr=1.7500e-04) (hash(x)=30728540) +4028 train 7.284790 (lr=1.7500e-04) (hash(x)=23966676) +4029 train 6.979034 (lr=1.7500e-04) (hash(x)=22118783) +4030 train 7.133085 (lr=1.7500e-04) (hash(x)=24744703) +4031 train 7.126765 (lr=1.7500e-04) (hash(x)=21407676) +4032 train 7.033156 (lr=1.7500e-04) (hash(x)=20623349) +4033 train 6.819570 (lr=1.7500e-04) (hash(x)=24723788) +4034 train 7.152753 (lr=1.7500e-04) (hash(x)=25030709) +4035 train 7.181690 (lr=1.7500e-04) (hash(x)=26326164) +4036 train 7.029781 (lr=1.7500e-04) (hash(x)=23754475) +4037 train 7.736980 (lr=1.7500e-04) (hash(x)=30112933) +4038 train 7.397260 (lr=1.7500e-04) (hash(x)=27474299) +4039 train 6.854515 (lr=1.7500e-04) (hash(x)=21720304) +4040 train 7.288594 (lr=1.7500e-04) (hash(x)=25142674) +4041 train 7.572137 (lr=1.7500e-04) (hash(x)=25284552) +4042 train 7.417762 (lr=1.7500e-04) (hash(x)=24554942) +4043 train 7.168468 (lr=1.7500e-04) (hash(x)=23773870) +4044 train 6.947312 (lr=1.7500e-04) (hash(x)=23896338) +4045 train 7.766472 (lr=1.7500e-04) (hash(x)=34984911) +4046 train 7.012027 (lr=1.7500e-04) (hash(x)=23854263) +4047 train 7.290067 (lr=1.7500e-04) (hash(x)=27263416) +4048 train 7.000493 (lr=1.7500e-04) (hash(x)=24989642) +4049 train 6.991769 (lr=1.7500e-04) (hash(x)=24492055) +4050 val loss 7.1951 +4050 val perplexity 1332.8420 +4050 train 6.898185 (lr=1.7500e-04) (hash(x)=21579916) +4051 train 7.142738 (lr=1.7500e-04) (hash(x)=25274710) +4052 train 7.023918 (lr=1.7500e-04) (hash(x)=24701947) +4053 train 7.013309 (lr=1.7500e-04) (hash(x)=25477340) +4054 train 6.951053 (lr=1.7500e-04) (hash(x)=23774195) +4055 train 7.211398 (lr=1.7500e-04) (hash(x)=25840801) +4056 train 7.394399 (lr=1.7500e-04) (hash(x)=27972529) +4057 train 7.176335 (lr=1.7500e-04) (hash(x)=26952458) +4058 train 6.688879 (lr=1.7500e-04) (hash(x)=22683653) +4059 train 6.722103 (lr=1.7500e-04) (hash(x)=20984129) +4060 train 6.884252 (lr=1.7500e-04) (hash(x)=22816482) +4061 train 7.160463 (lr=1.7500e-04) (hash(x)=24285302) +4062 train 7.599585 (lr=1.7500e-04) (hash(x)=31517950) +4063 train 7.883649 (lr=1.7500e-04) (hash(x)=31424568) +4064 train 7.575504 (lr=1.7500e-04) (hash(x)=29497876) +4065 train 7.422300 (lr=1.7500e-04) (hash(x)=27277376) +4066 train 7.178451 (lr=1.7500e-04) (hash(x)=26832588) +4067 train 6.974344 (lr=1.7500e-04) (hash(x)=25149712) +4068 train 6.976086 (lr=1.7500e-04) (hash(x)=23728457) +4069 train 6.884561 (lr=1.7500e-04) (hash(x)=25265136) +4070 train 7.446020 (lr=1.7500e-04) (hash(x)=25241681) +4071 train 7.140747 (lr=1.7500e-04) (hash(x)=23403065) +4072 train 7.091001 (lr=1.7500e-04) (hash(x)=25808207) +4073 train 7.003571 (lr=1.7500e-04) (hash(x)=23904844) +4074 train 6.689298 (lr=1.7500e-04) (hash(x)=18865309) +4075 train 7.124738 (lr=1.7500e-04) (hash(x)=23531744) +4076 train 7.179955 (lr=1.7500e-04) (hash(x)=25784275) +4077 train 6.897966 (lr=1.7500e-04) (hash(x)=22417529) +4078 train 6.911823 (lr=1.7500e-04) (hash(x)=23095491) +4079 train 7.069072 (lr=1.7500e-04) (hash(x)=22656033) +4080 train 7.064241 (lr=1.7500e-04) (hash(x)=25865435) +4081 train 7.157734 (lr=1.7500e-04) (hash(x)=25699377) +4082 train 7.180533 (lr=1.7500e-04) (hash(x)=20854084) +4083 train 6.713641 (lr=1.7500e-04) (hash(x)=18950799) +4084 train 6.953949 (lr=1.7500e-04) (hash(x)=22633739) +4085 train 7.731949 (lr=1.7500e-04) (hash(x)=34054446) +4086 train 7.308450 (lr=1.7500e-04) (hash(x)=27599387) +4087 train 7.146399 (lr=1.7500e-04) (hash(x)=26869295) +4088 train 7.102777 (lr=1.7500e-04) (hash(x)=24075139) +4089 train 7.553224 (lr=1.7500e-04) (hash(x)=29784110) +4090 train 7.871780 (lr=1.7500e-04) (hash(x)=34273918) +4091 train 8.254366 (lr=1.7500e-04) (hash(x)=34472685) +4092 train 7.595218 (lr=1.7500e-04) (hash(x)=30113791) +4093 train 6.884624 (lr=1.7500e-04) (hash(x)=22366381) +4094 train 7.122171 (lr=1.7500e-04) (hash(x)=24922935) +4095 train 7.314085 (lr=1.7500e-04) (hash(x)=25504151) +4096 train 7.213839 (lr=1.7500e-04) (hash(x)=24517375) +4097 train 8.019847 (lr=1.7500e-04) (hash(x)=25871651) +4098 train 7.002258 (lr=1.7500e-04) (hash(x)=23480225) +4099 train 6.818200 (lr=1.7500e-04) (hash(x)=22559978) +4100 val loss 7.1779 +4100 val perplexity 1310.1089 +4100 train 7.287630 (lr=1.7500e-04) (hash(x)=25795272) +4101 train 7.236427 (lr=1.7500e-04) (hash(x)=25440399) +4102 train 6.900770 (lr=1.7500e-04) (hash(x)=21581806) +4103 train 6.957257 (lr=1.7500e-04) (hash(x)=25781518) +4104 train 7.093778 (lr=1.7500e-04) (hash(x)=24682372) +4105 train 6.890388 (lr=1.7500e-04) (hash(x)=22440094) +4106 train 7.095169 (lr=1.7500e-04) (hash(x)=23661032) +4107 train 7.318396 (lr=1.7500e-04) (hash(x)=26966012) +4108 train 7.380472 (lr=1.7500e-04) (hash(x)=26232227) +4109 train 7.005099 (lr=1.7500e-04) (hash(x)=24110656) +4110 train 7.267516 (lr=1.7500e-04) (hash(x)=25938621) +4111 train 7.108960 (lr=1.7500e-04) (hash(x)=26432850) +4112 train 7.107198 (lr=1.7500e-04) (hash(x)=25387672) +4113 train 6.891559 (lr=1.7500e-04) (hash(x)=22740017) +4114 train 7.246034 (lr=1.7500e-04) (hash(x)=26384190) +4115 train 6.984977 (lr=1.7500e-04) (hash(x)=24725583) +4116 train 7.096517 (lr=1.7500e-04) (hash(x)=23986700) +4117 train 7.100330 (lr=1.7500e-04) (hash(x)=18529900) +4118 train 7.104082 (lr=1.7500e-04) (hash(x)=22236257) +4119 train 6.765010 (lr=1.7500e-04) (hash(x)=20155894) +4120 train 6.549457 (lr=1.7500e-04) (hash(x)=17423813) +4121 train 6.514537 (lr=1.7500e-04) (hash(x)=18905183) +4122 train 6.873062 (lr=1.7500e-04) (hash(x)=22534398) +4123 train 7.608878 (lr=1.7500e-04) (hash(x)=25247868) +4124 train 7.143308 (lr=1.7500e-04) (hash(x)=23994188) +4125 train 6.961737 (lr=1.7500e-04) (hash(x)=22929754) +4126 train 6.881038 (lr=1.7500e-04) (hash(x)=22485897) +4127 train 6.917809 (lr=1.7500e-04) (hash(x)=22270169) +4128 train 6.901237 (lr=1.7500e-04) (hash(x)=23638027) +4129 train 7.198311 (lr=1.7500e-04) (hash(x)=23821210) +4130 train 7.032632 (lr=1.7500e-04) (hash(x)=25021512) +4131 train 7.111447 (lr=1.7500e-04) (hash(x)=25240141) +4132 train 7.086700 (lr=1.7500e-04) (hash(x)=22833160) +4133 train 7.000119 (lr=1.7500e-04) (hash(x)=22909944) +4134 train 7.251502 (lr=1.7500e-04) (hash(x)=26163558) +4135 train 6.971900 (lr=1.7500e-04) (hash(x)=22108461) +4136 train 6.946776 (lr=1.7500e-04) (hash(x)=22549232) +4137 train 7.126455 (lr=1.7500e-04) (hash(x)=24701302) +4138 train 7.225071 (lr=1.7500e-04) (hash(x)=25206013) +4139 train 7.207681 (lr=1.7500e-04) (hash(x)=27896130) +4140 train 6.952734 (lr=1.7500e-04) (hash(x)=24106243) +4141 train 7.499333 (lr=1.7500e-04) (hash(x)=27158651) +4142 train 7.112433 (lr=1.7500e-04) (hash(x)=23841147) +4143 train 7.055466 (lr=1.7500e-04) (hash(x)=24802848) +4144 train 7.343148 (lr=1.7500e-04) (hash(x)=24911295) +4145 train 7.155746 (lr=1.7500e-04) (hash(x)=26473900) +4146 train 7.222847 (lr=1.7500e-04) (hash(x)=26785092) +4147 train 7.450803 (lr=1.7500e-04) (hash(x)=30188532) +4148 train 7.022661 (lr=1.7500e-04) (hash(x)=25010649) +4149 train 6.995924 (lr=1.7500e-04) (hash(x)=22409016) +4150 val loss 7.1815 +4150 val perplexity 1314.9354 +4150 train 7.760597 (lr=1.7500e-04) (hash(x)=31675024) +4151 train 7.027726 (lr=1.7500e-04) (hash(x)=25086604) +4152 train 7.056645 (lr=1.7500e-04) (hash(x)=24429343) +4153 train 7.187656 (lr=1.7500e-04) (hash(x)=25014232) +4154 train 7.143725 (lr=1.7500e-04) (hash(x)=25366275) +4155 train 7.590841 (lr=1.7500e-04) (hash(x)=24031473) +4156 train 7.150626 (lr=1.7500e-04) (hash(x)=26651059) +4157 train 7.230906 (lr=1.7500e-04) (hash(x)=26069721) +4158 train 7.381763 (lr=1.7500e-04) (hash(x)=28114382) +4159 train 7.343525 (lr=1.7500e-04) (hash(x)=26983186) +4160 train 6.716956 (lr=1.7500e-04) (hash(x)=21944670) +4161 train 7.429508 (lr=1.7500e-04) (hash(x)=28155702) +4162 train 6.880263 (lr=1.7500e-04) (hash(x)=24765002) +4163 train 7.126350 (lr=1.7500e-04) (hash(x)=26492636) +4164 train 7.094344 (lr=1.7500e-04) (hash(x)=24063705) +4165 train 7.389503 (lr=1.7500e-04) (hash(x)=27079573) +4166 train 7.026237 (lr=1.7500e-04) (hash(x)=24912201) +4167 train 7.149457 (lr=1.7500e-04) (hash(x)=27208507) +4168 train 7.062680 (lr=1.7500e-04) (hash(x)=25824320) +4169 train 7.588634 (lr=1.7500e-04) (hash(x)=29641677) +4170 train 7.302134 (lr=1.7500e-04) (hash(x)=26275614) +4171 train 7.147790 (lr=1.7500e-04) (hash(x)=25227725) +4172 train 7.215189 (lr=1.7500e-04) (hash(x)=27417375) +4173 train 7.399600 (lr=1.7500e-04) (hash(x)=25581973) +4174 train 7.655447 (lr=1.7500e-04) (hash(x)=30360417) +4175 train 6.992914 (lr=1.7500e-04) (hash(x)=23862845) +4176 train 7.053647 (lr=1.7500e-04) (hash(x)=25415130) +4177 train 7.034481 (lr=1.7500e-04) (hash(x)=23111123) +4178 train 6.970541 (lr=1.7500e-04) (hash(x)=24022804) +4179 train 7.013481 (lr=1.7500e-04) (hash(x)=25148490) +4180 train 7.217610 (lr=1.7500e-04) (hash(x)=22792092) +4181 train 7.289150 (lr=1.7500e-04) (hash(x)=24779698) +4182 train 7.243764 (lr=1.7500e-04) (hash(x)=24870844) +4183 train 6.928030 (lr=1.7500e-04) (hash(x)=22664494) +4184 train 6.964307 (lr=1.7500e-04) (hash(x)=22599729) +4185 train 7.205175 (lr=1.7500e-04) (hash(x)=24707078) +4186 train 6.943692 (lr=1.7500e-04) (hash(x)=23823945) +4187 train 6.682320 (lr=1.7500e-04) (hash(x)=22219856) +4188 train 7.410611 (lr=1.7500e-04) (hash(x)=27061401) +4189 train 7.079174 (lr=1.7500e-04) (hash(x)=23398766) +4190 train 7.185387 (lr=1.7500e-04) (hash(x)=27916730) +4191 train 7.063457 (lr=1.7500e-04) (hash(x)=24092927) +4192 train 7.106767 (lr=1.7500e-04) (hash(x)=24723657) +4193 train 7.180853 (lr=1.7500e-04) (hash(x)=24676155) +4194 train 7.072754 (lr=1.7500e-04) (hash(x)=23455369) +4195 train 7.003063 (lr=1.7500e-04) (hash(x)=21999890) +4196 train 6.938435 (lr=1.7500e-04) (hash(x)=23385567) +4197 train 7.143110 (lr=1.7500e-04) (hash(x)=25120814) +4198 train 6.828128 (lr=1.7500e-04) (hash(x)=21308113) +4199 train 7.146200 (lr=1.7500e-04) (hash(x)=27213812) +4200 val loss 7.1695 +4200 val perplexity 1299.2548 +4200 train 6.697279 (lr=1.7500e-04) (hash(x)=19675382) +4201 train 7.010198 (lr=1.7500e-04) (hash(x)=23882161) +4202 train 6.997776 (lr=1.7500e-04) (hash(x)=24338567) +4203 train 7.327405 (lr=1.7500e-04) (hash(x)=27649723) +4204 train 7.116547 (lr=1.7500e-04) (hash(x)=27563514) +4205 train 7.089330 (lr=1.7500e-04) (hash(x)=23128552) +4206 train 7.005749 (lr=1.7500e-04) (hash(x)=26203283) +4207 train 7.030797 (lr=1.7500e-04) (hash(x)=23929955) +4208 train 6.742946 (lr=1.7500e-04) (hash(x)=20978691) +4209 train 7.029201 (lr=1.7500e-04) (hash(x)=21875178) +4210 train 7.067285 (lr=1.7500e-04) (hash(x)=23563293) +4211 train 7.195328 (lr=1.7500e-04) (hash(x)=25538503) +4212 train 7.238702 (lr=1.7500e-04) (hash(x)=24171014) +4213 train 7.105831 (lr=1.7500e-04) (hash(x)=22306665) +4214 train 7.042263 (lr=1.7500e-04) (hash(x)=26082318) +4215 train 6.830184 (lr=1.7500e-04) (hash(x)=23025790) +4216 train 6.892579 (lr=1.7500e-04) (hash(x)=21146597) +4217 train 7.293611 (lr=1.7500e-04) (hash(x)=27470230) +4218 train 7.002979 (lr=1.7500e-04) (hash(x)=22691005) +4219 train 6.797750 (lr=1.7500e-04) (hash(x)=21550313) +4220 train 6.910160 (lr=1.7500e-04) (hash(x)=20618443) +4221 train 7.000999 (lr=1.7500e-04) (hash(x)=25260787) +4222 train 7.095131 (lr=1.7500e-04) (hash(x)=25249873) +4223 train 6.719541 (lr=1.7500e-04) (hash(x)=20452272) +4224 train 6.981467 (lr=1.7500e-04) (hash(x)=25649764) +4225 train 6.845258 (lr=1.7500e-04) (hash(x)=19589460) +4226 train 7.309988 (lr=1.7500e-04) (hash(x)=26477595) +4227 train 7.497326 (lr=1.7500e-04) (hash(x)=27585442) +4228 train 7.279702 (lr=1.7500e-04) (hash(x)=25821343) +4229 train 7.178108 (lr=1.7500e-04) (hash(x)=24549919) +4230 train 7.133444 (lr=1.7500e-04) (hash(x)=26124522) +4231 train 7.404054 (lr=1.7500e-04) (hash(x)=26473464) +4232 train 7.402432 (lr=1.7500e-04) (hash(x)=28883028) +4233 train 7.328322 (lr=1.7500e-04) (hash(x)=29611296) +4234 train 7.237484 (lr=1.7500e-04) (hash(x)=29059941) +4235 train 7.076489 (lr=1.7500e-04) (hash(x)=26368203) +4236 train 7.139178 (lr=1.7500e-04) (hash(x)=27021360) +4237 train 7.059555 (lr=1.7500e-04) (hash(x)=26135379) +4238 train 6.854101 (lr=1.7500e-04) (hash(x)=25862549) +4239 train 7.241362 (lr=1.7500e-04) (hash(x)=28276603) +4240 train 6.803359 (lr=1.7500e-04) (hash(x)=22170090) +4241 train 7.138546 (lr=1.7500e-04) (hash(x)=22625589) +4242 train 7.154102 (lr=1.7500e-04) (hash(x)=25751475) +4243 train 7.083768 (lr=1.7500e-04) (hash(x)=25836838) +4244 train 7.009249 (lr=1.7500e-04) (hash(x)=23938214) +4245 train 6.947584 (lr=1.7500e-04) (hash(x)=22759365) +4246 train 6.904858 (lr=1.7500e-04) (hash(x)=24964628) +4247 train 6.673882 (lr=1.7500e-04) (hash(x)=21480367) +4248 train 7.201444 (lr=1.7500e-04) (hash(x)=25974694) +4249 train 7.543663 (lr=1.7500e-04) (hash(x)=29830546) +4250 val loss 7.1662 +4250 val perplexity 1294.9037 +4250 train 7.190057 (lr=1.7500e-04) (hash(x)=26283200) +4251 train 7.246830 (lr=1.7500e-04) (hash(x)=25605672) +4252 train 6.874700 (lr=1.7500e-04) (hash(x)=21439107) +4253 train 6.808298 (lr=1.7500e-04) (hash(x)=22626883) +4254 train 7.169128 (lr=1.7500e-04) (hash(x)=25627150) +4255 train 7.334925 (lr=1.7500e-04) (hash(x)=24658642) +4256 train 7.429799 (lr=1.7500e-04) (hash(x)=29755505) +4257 train 7.146283 (lr=1.7500e-04) (hash(x)=22750846) +4258 train 7.081276 (lr=1.7500e-04) (hash(x)=21892651) +4259 train 7.134778 (lr=1.7500e-04) (hash(x)=22487960) +4260 train 7.199243 (lr=1.7500e-04) (hash(x)=24059869) +4261 train 6.901493 (lr=1.7500e-04) (hash(x)=21090180) +4262 train 7.010344 (lr=1.7500e-04) (hash(x)=22716452) +4263 train 7.237413 (lr=1.7500e-04) (hash(x)=26854801) +4264 train 7.095456 (lr=1.7500e-04) (hash(x)=23815428) +4265 train 6.940614 (lr=1.7500e-04) (hash(x)=23368704) +4266 train 7.018074 (lr=1.7500e-04) (hash(x)=24301098) +4267 train 7.252873 (lr=1.7500e-04) (hash(x)=25025039) +4268 train 6.986343 (lr=1.7500e-04) (hash(x)=25425736) +4269 train 7.175243 (lr=1.7500e-04) (hash(x)=27439380) +4270 train 6.728603 (lr=1.7500e-04) (hash(x)=18682756) +4271 train 6.835075 (lr=1.7500e-04) (hash(x)=17862226) +4272 train 7.362524 (lr=1.7500e-04) (hash(x)=29946491) +4273 train 6.666856 (lr=1.7500e-04) (hash(x)=21392062) +4274 train 7.191545 (lr=1.7500e-04) (hash(x)=25195556) +4275 train 7.183092 (lr=1.7500e-04) (hash(x)=26682036) +4276 train 7.111961 (lr=1.7500e-04) (hash(x)=21235260) +4277 train 6.928896 (lr=1.7500e-04) (hash(x)=22118984) +4278 train 6.961872 (lr=1.7500e-04) (hash(x)=24094510) +4279 train 7.453730 (lr=1.7500e-04) (hash(x)=28519182) +4280 train 7.132898 (lr=1.7500e-04) (hash(x)=26652859) +4281 train 7.031796 (lr=1.7500e-04) (hash(x)=24463139) +4282 train 7.016534 (lr=1.7500e-04) (hash(x)=23281870) +4283 train 7.218614 (lr=1.7500e-04) (hash(x)=29181174) +4284 train 6.905035 (lr=1.7500e-04) (hash(x)=24797417) +4285 train 7.233249 (lr=1.7500e-04) (hash(x)=29026537) +4286 train 7.041342 (lr=1.7500e-04) (hash(x)=23045165) +4287 train 6.954346 (lr=1.7500e-04) (hash(x)=25193694) +4288 train 7.004589 (lr=1.7500e-04) (hash(x)=23475407) +4289 train 7.152423 (lr=1.7500e-04) (hash(x)=24875410) +4290 train 7.077393 (lr=1.7500e-04) (hash(x)=26328101) +4291 train 7.352742 (lr=1.7500e-04) (hash(x)=26273661) +4292 train 7.063892 (lr=1.7500e-04) (hash(x)=23271891) +4293 train 7.039404 (lr=1.7500e-04) (hash(x)=23300732) +4294 train 7.113773 (lr=1.7500e-04) (hash(x)=24243693) +4295 train 7.199414 (lr=1.7500e-04) (hash(x)=25642620) +4296 train 7.209085 (lr=1.7500e-04) (hash(x)=27730411) +4297 train 6.986762 (lr=1.7500e-04) (hash(x)=25485335) +4298 train 6.863657 (lr=1.7500e-04) (hash(x)=25268789) +4299 train 7.285053 (lr=1.7500e-04) (hash(x)=28917143) +4300 val loss 7.1787 +4300 val perplexity 1311.2438 +4300 train 7.421751 (lr=1.7500e-04) (hash(x)=28987991) +4301 train 7.143438 (lr=1.7500e-04) (hash(x)=25989151) +4302 train 7.073333 (lr=1.7500e-04) (hash(x)=25658195) +4303 train 7.063443 (lr=1.7500e-04) (hash(x)=25765909) +4304 train 7.088564 (lr=1.7500e-04) (hash(x)=25704261) +4305 train 7.108331 (lr=1.7500e-04) (hash(x)=24438198) +4306 train 6.931589 (lr=1.7500e-04) (hash(x)=22871710) +4307 train 6.769924 (lr=1.7500e-04) (hash(x)=20160896) +4308 train 7.287242 (lr=1.7500e-04) (hash(x)=24218641) +4309 train 6.734738 (lr=1.7500e-04) (hash(x)=22073751) +4310 train 7.054608 (lr=1.7500e-04) (hash(x)=26434959) +4311 train 6.741456 (lr=1.7500e-04) (hash(x)=20750531) +4312 train 6.849524 (lr=1.7500e-04) (hash(x)=22232293) +4313 train 7.194767 (lr=1.7500e-04) (hash(x)=27324521) +4314 train 6.859647 (lr=1.7500e-04) (hash(x)=22217862) +4315 train 7.303782 (lr=1.7500e-04) (hash(x)=25741958) +4316 train 7.023166 (lr=1.7500e-04) (hash(x)=22738456) +4317 train 7.101196 (lr=1.7500e-04) (hash(x)=25387302) +4318 train 7.051609 (lr=1.7500e-04) (hash(x)=24669014) +4319 train 7.182189 (lr=1.7500e-04) (hash(x)=24917098) +4320 train 7.133243 (lr=1.7500e-04) (hash(x)=26698227) +4321 train 6.975340 (lr=1.7500e-04) (hash(x)=23518293) +4322 train 6.919801 (lr=1.7500e-04) (hash(x)=23643971) +4323 train 7.056888 (lr=1.7500e-04) (hash(x)=25659505) +4324 train 6.864670 (lr=1.7500e-04) (hash(x)=22697720) +4325 train 7.368103 (lr=1.7500e-04) (hash(x)=25082178) +4326 train 6.885800 (lr=1.7500e-04) (hash(x)=24166546) +4327 train 7.072067 (lr=1.7500e-04) (hash(x)=24499766) +4328 train 7.229611 (lr=1.7500e-04) (hash(x)=24338607) +4329 train 6.977919 (lr=1.7500e-04) (hash(x)=23225420) +4330 train 7.155843 (lr=1.7500e-04) (hash(x)=25907032) +4331 train 6.911420 (lr=1.7500e-04) (hash(x)=24634979) +4332 train 7.009197 (lr=1.7500e-04) (hash(x)=22161377) +4333 train 7.177176 (lr=1.7500e-04) (hash(x)=22559939) +4334 train 6.937551 (lr=1.7500e-04) (hash(x)=20840022) +4335 train 7.205789 (lr=1.7500e-04) (hash(x)=25067358) +4336 train 6.866952 (lr=1.7500e-04) (hash(x)=23432626) +4337 train 7.035783 (lr=1.7500e-04) (hash(x)=23820385) +4338 train 7.856923 (lr=1.7500e-04) (hash(x)=31594930) +4339 train 7.251676 (lr=1.7500e-04) (hash(x)=27138750) +4340 train 7.440366 (lr=1.7500e-04) (hash(x)=30031341) +4341 train 7.016966 (lr=1.7500e-04) (hash(x)=24602807) +4342 train 6.794734 (lr=1.7500e-04) (hash(x)=21584976) +4343 train 7.210627 (lr=1.7500e-04) (hash(x)=27479796) +4344 train 6.887300 (lr=1.7500e-04) (hash(x)=22746241) +4345 train 6.994865 (lr=1.7500e-04) (hash(x)=19728452) +4346 train 6.864316 (lr=1.7500e-04) (hash(x)=24502020) +4347 train 7.306602 (lr=1.7500e-04) (hash(x)=28225954) +4348 train 6.983953 (lr=1.7500e-04) (hash(x)=23893447) +4349 train 7.285240 (lr=1.7500e-04) (hash(x)=25654586) +4350 val loss 7.1651 +4350 val perplexity 1293.4374 +4350 train 7.140003 (lr=1.7500e-04) (hash(x)=23856469) +4351 train 7.063375 (lr=1.7500e-04) (hash(x)=23136080) +4352 train 7.171994 (lr=1.7500e-04) (hash(x)=26532918) +4353 train 7.150586 (lr=1.7500e-04) (hash(x)=25461947) +4354 train 7.143777 (lr=1.7500e-04) (hash(x)=26590231) +4355 train 6.851335 (lr=1.7500e-04) (hash(x)=21441985) +4356 train 7.087505 (lr=1.7500e-04) (hash(x)=26507941) +4357 train 7.375827 (lr=1.7500e-04) (hash(x)=26245238) +4358 train 7.194825 (lr=1.7500e-04) (hash(x)=24879059) +4359 train 7.411125 (lr=1.7500e-04) (hash(x)=29810074) +4360 train 6.875214 (lr=1.7500e-04) (hash(x)=24258069) +4361 train 6.988430 (lr=1.7500e-04) (hash(x)=25229360) +4362 train 7.219366 (lr=1.7500e-04) (hash(x)=25440206) +4363 train 7.050986 (lr=1.7500e-04) (hash(x)=23222125) +4364 train 6.921384 (lr=1.7500e-04) (hash(x)=23353186) +4365 train 7.099260 (lr=1.7500e-04) (hash(x)=26995240) +4366 train 7.041469 (lr=1.7500e-04) (hash(x)=24135899) +4367 train 7.089223 (lr=1.7500e-04) (hash(x)=24765539) +4368 train 7.110876 (lr=1.7500e-04) (hash(x)=26051004) +4369 train 6.871484 (lr=1.7500e-04) (hash(x)=22559142) +4370 train 6.772262 (lr=1.7500e-04) (hash(x)=20364388) +4371 train 7.245731 (lr=1.7500e-04) (hash(x)=25938817) +4372 train 7.299609 (lr=1.7500e-04) (hash(x)=26060945) +4373 train 7.220880 (lr=1.7500e-04) (hash(x)=27866714) +4374 train 7.133522 (lr=1.7500e-04) (hash(x)=27104972) +4375 train 6.803093 (lr=1.7500e-04) (hash(x)=22216309) +4376 train 6.867313 (lr=1.7500e-04) (hash(x)=20781533) +4377 train 6.815149 (lr=1.7500e-04) (hash(x)=18784350) +4378 train 6.941766 (lr=1.7500e-04) (hash(x)=21102897) +4379 train 7.203458 (lr=1.7500e-04) (hash(x)=25647489) +4380 train 7.012444 (lr=1.7500e-04) (hash(x)=24486462) +4381 train 7.261475 (lr=1.7500e-04) (hash(x)=26539114) +4382 train 6.875923 (lr=1.7500e-04) (hash(x)=20026045) +4383 train 7.169615 (lr=1.7500e-04) (hash(x)=20613861) +4384 train 6.877586 (lr=1.7500e-04) (hash(x)=20676237) +4385 train 7.127586 (lr=1.7500e-04) (hash(x)=24893163) +4386 train 6.649704 (lr=1.7500e-04) (hash(x)=17299395) +4387 train 6.807804 (lr=1.7500e-04) (hash(x)=19580191) +4388 train 7.009080 (lr=1.7500e-04) (hash(x)=25588218) +4389 train 7.164131 (lr=1.7500e-04) (hash(x)=26433063) +4390 train 7.228107 (lr=1.7500e-04) (hash(x)=24917693) +4391 train 6.885506 (lr=1.7500e-04) (hash(x)=23462447) +4392 train 7.142998 (lr=1.7500e-04) (hash(x)=27185416) +4393 train 7.232863 (lr=1.7500e-04) (hash(x)=24109010) +4394 train 6.982466 (lr=1.7500e-04) (hash(x)=21486000) +4395 train 6.845033 (lr=1.7500e-04) (hash(x)=22230006) +4396 train 7.314641 (lr=1.7500e-04) (hash(x)=26092311) +4397 train 7.040959 (lr=1.7500e-04) (hash(x)=24112426) +4398 train 6.864881 (lr=1.7500e-04) (hash(x)=21881373) +4399 train 7.049382 (lr=1.7500e-04) (hash(x)=26739455) +4400 val loss 7.1827 +4400 val perplexity 1316.5159 +4400 train 6.908609 (lr=1.7500e-04) (hash(x)=22873602) +4401 train 7.012979 (lr=1.7500e-04) (hash(x)=26748712) +4402 train 7.122038 (lr=1.7500e-04) (hash(x)=26306618) +4403 train 7.297161 (lr=1.7500e-04) (hash(x)=26898808) +4404 train 7.050775 (lr=1.7500e-04) (hash(x)=25067751) +4405 train 7.112035 (lr=1.7500e-04) (hash(x)=25397145) +4406 train 7.266866 (lr=1.7500e-04) (hash(x)=24796962) +4407 train 7.061435 (lr=1.7500e-04) (hash(x)=23222996) +4408 train 7.036926 (lr=1.7500e-04) (hash(x)=24820189) +4409 train 7.470453 (lr=1.7500e-04) (hash(x)=27669038) +4410 train 7.004437 (lr=1.7500e-04) (hash(x)=24283976) +4411 train 7.211784 (lr=1.7500e-04) (hash(x)=25018789) +4412 train 7.170685 (lr=1.7500e-04) (hash(x)=26247064) +4413 train 7.183591 (lr=1.7500e-04) (hash(x)=22942904) +4414 train 7.089504 (lr=1.7500e-04) (hash(x)=23918746) +4415 train 7.205833 (lr=1.7500e-04) (hash(x)=26489285) +4416 train 6.123775 (lr=1.7500e-04) (hash(x)=14942495) +4417 train 6.948135 (lr=1.7500e-04) (hash(x)=23908505) +4418 train 7.234908 (lr=1.7500e-04) (hash(x)=25854036) +4419 train 7.134871 (lr=1.7500e-04) (hash(x)=27522868) +4420 train 7.010770 (lr=1.7500e-04) (hash(x)=26549205) +4421 train 6.916480 (lr=1.7500e-04) (hash(x)=24565522) +4422 train 7.225191 (lr=1.7500e-04) (hash(x)=23919123) +4423 train 7.092373 (lr=1.7500e-04) (hash(x)=25185942) +4424 train 7.109244 (lr=1.7500e-04) (hash(x)=24818969) +4425 train 7.188457 (lr=1.7500e-04) (hash(x)=26750372) +4426 train 7.184393 (lr=1.7500e-04) (hash(x)=25621536) +4427 train 7.600681 (lr=1.7500e-04) (hash(x)=28037060) +4428 train 7.647892 (lr=1.7500e-04) (hash(x)=30829517) +4429 train 7.288978 (lr=1.7500e-04) (hash(x)=28728766) +4430 train 7.200568 (lr=1.7500e-04) (hash(x)=25936895) +4431 train 7.295846 (lr=1.7500e-04) (hash(x)=27476158) +4432 train 7.077800 (lr=1.7500e-04) (hash(x)=23297921) +4433 train 7.038209 (lr=1.7500e-04) (hash(x)=23201299) +4434 train 6.947747 (lr=1.7500e-04) (hash(x)=22681766) +4435 train 6.919052 (lr=1.7500e-04) (hash(x)=23217512) +4436 train 7.435666 (lr=1.7500e-04) (hash(x)=29322443) +4437 train 7.013352 (lr=1.7500e-04) (hash(x)=23502072) +4438 train 7.102082 (lr=1.7500e-04) (hash(x)=28873527) +4439 train 7.103415 (lr=1.7500e-04) (hash(x)=23653175) +4440 train 6.879716 (lr=1.7500e-04) (hash(x)=21635879) +4441 train 6.952434 (lr=1.7500e-04) (hash(x)=22201854) +4442 train 6.882661 (lr=1.7500e-04) (hash(x)=23101164) +4443 train 7.311519 (lr=1.7500e-04) (hash(x)=25475122) +4444 train 7.043148 (lr=1.7500e-04) (hash(x)=25124825) +4445 train 7.190001 (lr=1.7500e-04) (hash(x)=26883852) +4446 train 6.968242 (lr=1.7500e-04) (hash(x)=24731829) +4447 train 6.939916 (lr=1.7500e-04) (hash(x)=22405076) +4448 train 7.107736 (lr=1.7500e-04) (hash(x)=27633869) +4449 train 7.158165 (lr=1.7500e-04) (hash(x)=25162594) +4450 val loss 7.1862 +4450 val perplexity 1321.0442 +4450 train 7.162460 (lr=1.7500e-04) (hash(x)=26438149) +4451 train 7.180927 (lr=1.7500e-04) (hash(x)=26748800) +4452 train 6.900776 (lr=1.7500e-04) (hash(x)=22971620) +4453 train 7.042729 (lr=1.7500e-04) (hash(x)=25886430) +4454 train 6.840282 (lr=1.7500e-04) (hash(x)=21084137) +4455 train 7.013313 (lr=1.7500e-04) (hash(x)=25673545) +4456 train 7.640214 (lr=1.7500e-04) (hash(x)=29389002) +4457 train 6.735939 (lr=1.7500e-04) (hash(x)=21676076) +4458 train 6.850030 (lr=1.7500e-04) (hash(x)=22616647) +4459 train 7.281790 (lr=1.7500e-04) (hash(x)=22771197) +4460 train 7.160606 (lr=1.7500e-04) (hash(x)=26393514) +4461 train 7.388440 (lr=1.7500e-04) (hash(x)=24996433) +4462 train 6.979099 (lr=1.7500e-04) (hash(x)=19594028) +4463 train 7.145837 (lr=1.7500e-04) (hash(x)=22675428) +4464 train 7.178543 (lr=1.7500e-04) (hash(x)=26566551) +4465 train 7.173454 (lr=1.7500e-04) (hash(x)=22469290) +4466 train 7.655461 (lr=1.7500e-04) (hash(x)=29821654) +4467 train 7.170941 (lr=1.7500e-04) (hash(x)=26305388) +4468 train 7.024896 (lr=1.7500e-04) (hash(x)=21998506) +4469 train 7.428440 (lr=1.7500e-04) (hash(x)=23953315) +4470 train 7.077343 (lr=1.7500e-04) (hash(x)=23985456) +4471 train 7.447989 (lr=1.7500e-04) (hash(x)=28168456) +4472 train 7.142468 (lr=1.7500e-04) (hash(x)=25126411) +4473 train 6.949817 (lr=1.7500e-04) (hash(x)=24619336) +4474 train 7.089990 (lr=1.7500e-04) (hash(x)=24467798) +4475 train 7.864144 (lr=1.7500e-04) (hash(x)=31673254) +4476 train 7.685575 (lr=1.7500e-04) (hash(x)=29929610) +4477 train 7.468488 (lr=1.7500e-04) (hash(x)=29412572) +4478 train 7.598677 (lr=1.7500e-04) (hash(x)=31910006) +4479 train 7.290126 (lr=1.7500e-04) (hash(x)=26072586) +4480 train 7.231335 (lr=1.7500e-04) (hash(x)=25782825) +4481 train 7.066584 (lr=1.7500e-04) (hash(x)=21131363) +4482 train 7.164705 (lr=1.7500e-04) (hash(x)=25071223) +4483 train 7.698209 (lr=1.7500e-04) (hash(x)=32249577) +4484 train 7.023535 (lr=1.7500e-04) (hash(x)=24752808) +4485 train 7.048833 (lr=1.7500e-04) (hash(x)=24970539) +4486 train 6.939815 (lr=1.7500e-04) (hash(x)=24191005) +4487 train 7.172096 (lr=1.7500e-04) (hash(x)=24974331) +4488 train 7.291866 (lr=1.7500e-04) (hash(x)=27043409) +4489 train 6.853166 (lr=1.7500e-04) (hash(x)=11320385) +4490 train 6.785248 (lr=1.7500e-04) (hash(x)=11919565) +4491 train 6.744258 (lr=1.7500e-04) (hash(x)=10404694) +4492 train 6.747641 (lr=1.7500e-04) (hash(x)=12393159) +4493 train 6.526981 (lr=1.7500e-04) (hash(x)=11843609) +4494 train 6.522640 (lr=1.7500e-04) (hash(x)=12632729) +4495 train 7.131992 (lr=1.7500e-04) (hash(x)=21951984) +4496 train 7.954497 (lr=1.7500e-04) (hash(x)=19411544) +4497 train 7.866519 (lr=1.7500e-04) (hash(x)=21000228) +4498 train 7.344425 (lr=1.7500e-04) (hash(x)=26018207) +4499 train 7.431676 (lr=1.7500e-04) (hash(x)=24659058) +4500 val loss 7.2583 +4500 val perplexity 1419.8676 +4500 train 7.518547 (lr=1.7500e-04) (hash(x)=27919597) +4501 train 7.119926 (lr=1.7500e-04) (hash(x)=26232596) +4502 train 7.263667 (lr=1.7500e-04) (hash(x)=26248912) +4503 train 7.180841 (lr=1.7500e-04) (hash(x)=25403751) +4504 train 7.065799 (lr=1.7500e-04) (hash(x)=21096637) +4505 train 7.253107 (lr=1.7500e-04) (hash(x)=26560941) +4506 train 7.231022 (lr=1.7500e-04) (hash(x)=24942406) +4507 train 7.276388 (lr=1.7500e-04) (hash(x)=24405748) +4508 train 7.161522 (lr=1.7500e-04) (hash(x)=22975455) +4509 train 7.091343 (lr=1.7500e-04) (hash(x)=26358820) +4510 train 7.084265 (lr=1.7500e-04) (hash(x)=24211938) +4511 train 7.244218 (lr=1.7500e-04) (hash(x)=26396012) +4512 train 6.913654 (lr=1.7500e-04) (hash(x)=22534410) +4513 train 7.022513 (lr=1.7500e-04) (hash(x)=23855025) +4514 train 6.913028 (lr=1.7500e-04) (hash(x)=22722345) +4515 train 6.916971 (lr=1.7500e-04) (hash(x)=22779251) +4516 train 7.191771 (lr=1.7500e-04) (hash(x)=23973078) +4517 train 7.079093 (lr=1.7500e-04) (hash(x)=19886228) +4518 train 7.114059 (lr=1.7500e-04) (hash(x)=23849694) +4519 train 7.536098 (lr=1.7500e-04) (hash(x)=24827190) +4520 train 7.045812 (lr=1.7500e-04) (hash(x)=25111498) +4521 train 7.894850 (lr=1.7500e-04) (hash(x)=29752556) +4522 train 7.336542 (lr=1.7500e-04) (hash(x)=25606805) +4523 train 7.164508 (lr=1.7500e-04) (hash(x)=22209714) +4524 train 6.909875 (lr=1.7500e-04) (hash(x)=24991834) +4525 train 7.159003 (lr=1.7500e-04) (hash(x)=27808158) +4526 train 7.089771 (lr=1.7500e-04) (hash(x)=23041199) +4527 train 7.144529 (lr=1.7500e-04) (hash(x)=24847458) +4528 train 7.108750 (lr=1.7500e-04) (hash(x)=25091787) +4529 train 7.947613 (lr=1.7500e-04) (hash(x)=29745551) +4530 train 6.825283 (lr=1.7500e-04) (hash(x)=20447167) +4531 train 7.058170 (lr=1.7500e-04) (hash(x)=20720911) +4532 train 7.147108 (lr=1.7500e-04) (hash(x)=24803353) +4533 train 7.236859 (lr=1.7500e-04) (hash(x)=23780724) +4534 train 7.232574 (lr=1.7500e-04) (hash(x)=23423120) +4535 train 6.929872 (lr=1.7500e-04) (hash(x)=22159088) +4536 train 7.109204 (lr=1.7500e-04) (hash(x)=25820304) +4537 train 6.887807 (lr=1.7500e-04) (hash(x)=22813612) +4538 train 7.219734 (lr=1.7500e-04) (hash(x)=27827979) +4539 train 7.244732 (lr=1.7500e-04) (hash(x)=25737179) +4540 train 7.403848 (lr=1.7500e-04) (hash(x)=23401504) +4541 train 7.096180 (lr=1.7500e-04) (hash(x)=25071988) +4542 train 7.154031 (lr=1.7500e-04) (hash(x)=22844541) +4543 train 6.866906 (lr=1.7500e-04) (hash(x)=22140034) +4544 train 7.122617 (lr=1.7500e-04) (hash(x)=26522091) +4545 train 7.183856 (lr=1.7500e-04) (hash(x)=24099725) +4546 train 6.774953 (lr=1.7500e-04) (hash(x)=19127182) +4547 train 6.887975 (lr=1.7500e-04) (hash(x)=18992693) +4548 train 7.867909 (lr=1.7500e-04) (hash(x)=26723015) +4549 train 7.641265 (lr=1.7500e-04) (hash(x)=30389969) +4550 val loss 7.1905 +4550 val perplexity 1326.8003 +4550 train 7.006035 (lr=1.7500e-04) (hash(x)=24065654) +4551 train 6.831380 (lr=1.7500e-04) (hash(x)=19044797) +4552 train 7.226192 (lr=1.7500e-04) (hash(x)=24919665) +4553 train 7.235281 (lr=1.7500e-04) (hash(x)=22780968) +4554 train 6.998090 (lr=1.7500e-04) (hash(x)=24549699) +4555 train 6.906101 (lr=1.7500e-04) (hash(x)=21374811) +4556 train 7.065541 (lr=1.7500e-04) (hash(x)=25225950) +4557 train 7.141174 (lr=1.7500e-04) (hash(x)=25691882) +4558 train 7.057294 (lr=1.7500e-04) (hash(x)=24685235) +4559 train 6.906835 (lr=1.7500e-04) (hash(x)=23932794) +4560 train 7.454742 (lr=1.7500e-04) (hash(x)=28152043) +4561 train 6.970038 (lr=1.7500e-04) (hash(x)=23417051) +4562 train 7.052517 (lr=1.7500e-04) (hash(x)=26250211) +4563 train 7.256317 (lr=1.7500e-04) (hash(x)=25428813) +4564 train 7.379193 (lr=1.7500e-04) (hash(x)=27477379) +4565 train 7.166096 (lr=1.7500e-04) (hash(x)=23015212) +4566 train 6.937347 (lr=1.7500e-04) (hash(x)=22837608) +4567 train 7.044811 (lr=1.7500e-04) (hash(x)=25256890) +4568 train 6.945938 (lr=1.7500e-04) (hash(x)=22742827) +4569 train 7.339177 (lr=1.7500e-04) (hash(x)=30167922) +4570 train 7.035118 (lr=1.7500e-04) (hash(x)=24540265) +4571 train 7.305699 (lr=1.7500e-04) (hash(x)=26752941) +4572 train 7.168863 (lr=1.7500e-04) (hash(x)=25094026) +4573 train 7.881898 (lr=1.7500e-04) (hash(x)=28508785) +4574 train 7.226482 (lr=1.7500e-04) (hash(x)=26501871) +4575 train 7.007733 (lr=1.7500e-04) (hash(x)=24161711) +4576 train 6.976713 (lr=1.7500e-04) (hash(x)=24313695) +4577 train 7.397710 (lr=1.7500e-04) (hash(x)=28248933) +4578 train 7.511617 (lr=1.7500e-04) (hash(x)=28445722) +4579 train 7.138785 (lr=1.7500e-04) (hash(x)=24589015) +4580 train 7.312976 (lr=1.7500e-04) (hash(x)=26192193) +4581 train 6.986103 (lr=1.7500e-04) (hash(x)=25131316) +4582 train 7.077590 (lr=1.7500e-04) (hash(x)=26631504) +4583 train 6.900379 (lr=1.7500e-04) (hash(x)=22036817) +4584 train 7.489135 (lr=1.7500e-04) (hash(x)=28361254) +4585 train 7.147342 (lr=1.7500e-04) (hash(x)=24828340) +4586 train 6.832655 (lr=1.7500e-04) (hash(x)=24067304) +4587 train 6.628331 (lr=1.7500e-04) (hash(x)=20733289) +4588 train 6.548786 (lr=1.7500e-04) (hash(x)=19526622) +4589 train 6.931387 (lr=1.7500e-04) (hash(x)=22148688) +4590 train 7.131898 (lr=1.7500e-04) (hash(x)=24141800) +4591 train 7.180421 (lr=1.7500e-04) (hash(x)=26663208) +4592 train 6.862649 (lr=1.7500e-04) (hash(x)=22536305) +4593 train 7.106206 (lr=1.7500e-04) (hash(x)=23608185) +4594 train 6.985953 (lr=1.7500e-04) (hash(x)=23348495) +4595 train 7.140810 (lr=1.7500e-04) (hash(x)=25409759) +4596 train 7.109324 (lr=1.7500e-04) (hash(x)=25572131) +4597 train 7.131177 (lr=1.7500e-04) (hash(x)=21782039) +4598 train 7.077167 (lr=1.7500e-04) (hash(x)=24643923) +4599 train 7.053404 (lr=1.7500e-04) (hash(x)=24072213) +4600 val loss 7.1925 +4600 val perplexity 1329.3911 +4600 train 6.955107 (lr=1.7500e-04) (hash(x)=23925612) +4601 train 7.063059 (lr=1.7500e-04) (hash(x)=23315415) +4602 train 7.053046 (lr=1.7500e-04) (hash(x)=21793800) +4603 train 6.987657 (lr=1.7500e-04) (hash(x)=24921200) +4604 train 7.236133 (lr=1.7500e-04) (hash(x)=27226113) +4605 train 6.992635 (lr=1.7500e-04) (hash(x)=22920960) +4606 train 6.968759 (lr=1.7500e-04) (hash(x)=21947750) +4607 train 7.024988 (lr=1.7500e-04) (hash(x)=22766044) +4608 train 7.457903 (lr=1.7500e-04) (hash(x)=28237005) +4609 train 6.888061 (lr=1.7500e-04) (hash(x)=24922621) +4610 train 7.133428 (lr=1.7500e-04) (hash(x)=24899830) +4611 train 7.510976 (lr=1.7500e-04) (hash(x)=32920298) +4612 train 6.934743 (lr=1.7500e-04) (hash(x)=25083835) +4613 train 7.025468 (lr=1.7500e-04) (hash(x)=22863054) +4614 train 7.052299 (lr=1.7500e-04) (hash(x)=24841464) +4615 train 7.321353 (lr=1.7500e-04) (hash(x)=27871153) +4616 train 7.341180 (lr=1.7500e-04) (hash(x)=28025163) +4617 train 6.979553 (lr=1.7500e-04) (hash(x)=24659561) +4618 train 7.077087 (lr=1.7500e-04) (hash(x)=25067194) +4619 train 7.121755 (lr=1.7500e-04) (hash(x)=22731460) +4620 train 7.071033 (lr=1.7500e-04) (hash(x)=20445873) +4621 train 7.116323 (lr=1.7500e-04) (hash(x)=26033948) +4622 train 6.998811 (lr=1.7500e-04) (hash(x)=22473213) +4623 train 7.532472 (lr=1.7500e-04) (hash(x)=24037280) +4624 train 7.905114 (lr=1.7500e-04) (hash(x)=25624131) +4625 train 7.600450 (lr=1.7500e-04) (hash(x)=26799867) +4626 train 7.154359 (lr=1.7500e-04) (hash(x)=27187602) +4627 train 7.101784 (lr=1.7500e-04) (hash(x)=23277695) +4628 train 7.107353 (lr=1.7500e-04) (hash(x)=24748234) +4629 train 7.244222 (lr=1.7500e-04) (hash(x)=26103104) +4630 train 7.174535 (lr=1.7500e-04) (hash(x)=24327389) +4631 train 7.261617 (lr=1.7500e-04) (hash(x)=24121850) +4632 train 7.126437 (lr=1.7500e-04) (hash(x)=23714590) +4633 train 7.146745 (lr=1.7500e-04) (hash(x)=22379412) +4634 train 7.366968 (lr=1.7500e-04) (hash(x)=24454713) +4635 train 7.027668 (lr=1.7500e-04) (hash(x)=22966977) +4636 train 7.044600 (lr=1.7500e-04) (hash(x)=23764884) +4637 train 6.918208 (lr=1.7500e-04) (hash(x)=23827429) +4638 train 7.135612 (lr=1.7500e-04) (hash(x)=24088592) +4639 train 7.116225 (lr=1.7500e-04) (hash(x)=24380031) +4640 train 7.192264 (lr=1.7500e-04) (hash(x)=26065050) +4641 train 7.133337 (lr=1.7500e-04) (hash(x)=24442902) +4642 train 6.712791 (lr=1.7500e-04) (hash(x)=18548782) +4643 train 7.214386 (lr=1.7500e-04) (hash(x)=26957303) +4644 train 7.186469 (lr=1.7500e-04) (hash(x)=25032727) +4645 train 7.085419 (lr=1.7500e-04) (hash(x)=27224706) +4646 train 7.210853 (lr=1.7500e-04) (hash(x)=27508476) +4647 train 6.977525 (lr=1.7500e-04) (hash(x)=23055215) +4648 train 7.054597 (lr=1.7500e-04) (hash(x)=24496194) +4649 train 8.442904 (lr=1.7500e-04) (hash(x)=13982941) +4650 val loss 7.2207 +4650 val perplexity 1367.4822 +4650 train 7.627807 (lr=1.7500e-04) (hash(x)=16721547) +4651 train 7.110841 (lr=1.7500e-04) (hash(x)=22929154) +4652 train 6.976673 (lr=1.7500e-04) (hash(x)=23323994) +4653 train 7.356464 (lr=1.7500e-04) (hash(x)=24877951) +4654 train 7.204323 (lr=1.7500e-04) (hash(x)=24096183) +4655 train 7.061931 (lr=1.7500e-04) (hash(x)=25329724) +4656 train 6.996016 (lr=1.7500e-04) (hash(x)=23877337) +4657 train 6.637315 (lr=1.7500e-04) (hash(x)=20923083) +4658 train 6.951288 (lr=1.7500e-04) (hash(x)=23807996) +4659 train 7.085926 (lr=1.7500e-04) (hash(x)=24370475) +4660 train 7.488068 (lr=1.7500e-04) (hash(x)=28202255) +4661 train 7.210028 (lr=1.7500e-04) (hash(x)=26142119) +4662 train 6.960904 (lr=1.7500e-04) (hash(x)=21387743) +4663 train 7.080130 (lr=1.7500e-04) (hash(x)=25662408) +4664 train 7.150711 (lr=1.7500e-04) (hash(x)=23962815) +4665 train 7.084817 (lr=1.7500e-04) (hash(x)=23987677) +4666 train 7.362976 (lr=1.7500e-04) (hash(x)=26554284) +4667 train 7.405643 (lr=1.7500e-04) (hash(x)=25991817) +4668 train 7.129449 (lr=1.7500e-04) (hash(x)=24256966) +4669 train 6.883232 (lr=1.7500e-04) (hash(x)=22187158) +4670 train 7.184963 (lr=1.7500e-04) (hash(x)=26295320) +4671 train 7.211379 (lr=1.7500e-04) (hash(x)=26346814) +4672 train 7.468494 (lr=1.7500e-04) (hash(x)=26594196) +4673 train 7.265673 (lr=1.7500e-04) (hash(x)=24322101) +4674 train 7.298714 (lr=1.7500e-04) (hash(x)=27274566) +4675 train 7.141479 (lr=1.7500e-04) (hash(x)=24505725) +4676 train 7.288841 (lr=1.7500e-04) (hash(x)=26167371) +4677 train 7.350577 (lr=1.7500e-04) (hash(x)=28062311) +4678 train 7.093138 (lr=1.7500e-04) (hash(x)=23476009) +4679 train 7.216118 (lr=1.7500e-04) (hash(x)=25283256) +4680 train 6.952613 (lr=1.7500e-04) (hash(x)=22033246) +4681 train 6.941846 (lr=1.7500e-04) (hash(x)=22716214) +4682 train 7.136395 (lr=1.7500e-04) (hash(x)=25672672) +4683 train 6.994644 (lr=1.7500e-04) (hash(x)=22979072) +4684 train 7.179198 (lr=1.7500e-04) (hash(x)=27439204) +4685 train 7.116101 (lr=1.7500e-04) (hash(x)=24857737) +4686 train 7.409672 (lr=1.7500e-04) (hash(x)=29615897) +4687 train 6.958290 (lr=1.7500e-04) (hash(x)=24021771) +4688 train 7.130638 (lr=1.7500e-04) (hash(x)=27410807) +4689 train 6.928554 (lr=1.7500e-04) (hash(x)=22850411) +4690 train 7.202081 (lr=1.7500e-04) (hash(x)=24949696) +4691 train 6.988144 (lr=1.7500e-04) (hash(x)=22956381) +4692 train 7.544907 (lr=1.7500e-04) (hash(x)=28193458) +4693 train 7.014180 (lr=1.7500e-04) (hash(x)=25596844) +4694 train 6.990255 (lr=1.7500e-04) (hash(x)=22101377) +4695 train 6.906440 (lr=1.7500e-04) (hash(x)=23576840) +4696 train 6.890172 (lr=1.7500e-04) (hash(x)=21849758) +4697 train 7.090829 (lr=1.7500e-04) (hash(x)=26431349) +4698 train 7.214905 (lr=1.7500e-04) (hash(x)=22960758) +4699 train 7.110933 (lr=1.7500e-04) (hash(x)=23243097) +4700 val loss 7.2046 +4700 val perplexity 1345.6588 +4700 train 7.005764 (lr=1.7500e-04) (hash(x)=23715370) +4701 train 7.699795 (lr=1.7500e-04) (hash(x)=30678293) +4702 train 7.770657 (lr=1.7500e-04) (hash(x)=32481620) +4703 train 7.267362 (lr=1.7500e-04) (hash(x)=26414858) +4704 train 7.150569 (lr=1.7500e-04) (hash(x)=24768691) +4705 train 6.824271 (lr=1.7500e-04) (hash(x)=21627762) +4706 train 6.929414 (lr=1.7500e-04) (hash(x)=21024917) +4707 train 6.840218 (lr=1.7500e-04) (hash(x)=23570951) +4708 train 6.983602 (lr=1.7500e-04) (hash(x)=23729185) +4709 train 7.343620 (lr=1.7500e-04) (hash(x)=25933754) +4710 train 6.823163 (lr=1.7500e-04) (hash(x)=23091014) +4711 train 6.903839 (lr=1.7500e-04) (hash(x)=20099261) +4712 train 7.067445 (lr=1.7500e-04) (hash(x)=26807297) +4713 train 6.936096 (lr=1.7500e-04) (hash(x)=25332115) +4714 train 6.972029 (lr=1.7500e-04) (hash(x)=23247605) +4715 train 6.830731 (lr=1.7500e-04) (hash(x)=23786549) +4716 train 6.992992 (lr=1.7500e-04) (hash(x)=23981166) +4717 train 7.142923 (lr=1.7500e-04) (hash(x)=25967754) +4718 train 6.991985 (lr=1.7500e-04) (hash(x)=23659116) +4719 train 7.130787 (lr=1.7500e-04) (hash(x)=22453718) +4720 train 7.034767 (lr=1.7500e-04) (hash(x)=22597951) +4721 train 7.237365 (lr=1.7500e-04) (hash(x)=25284885) +4722 train 7.194779 (lr=1.7500e-04) (hash(x)=24748569) +4723 train 6.832826 (lr=1.7500e-04) (hash(x)=19448608) +4724 train 7.174229 (lr=1.7500e-04) (hash(x)=24888040) +4725 train 7.008333 (lr=1.7500e-04) (hash(x)=23203503) +4726 train 6.761481 (lr=1.7500e-04) (hash(x)=20387787) +4727 train 6.875497 (lr=1.7500e-04) (hash(x)=22529445) +4728 train 7.167384 (lr=1.7500e-04) (hash(x)=22455471) +4729 train 7.163727 (lr=1.7500e-04) (hash(x)=25661132) +4730 train 7.137363 (lr=1.7500e-04) (hash(x)=24997711) +4731 train 7.229539 (lr=1.7500e-04) (hash(x)=22575521) +4732 train 7.033475 (lr=1.7500e-04) (hash(x)=22640285) +4733 train 6.889374 (lr=1.7500e-04) (hash(x)=18637357) +4734 train 7.029735 (lr=1.7500e-04) (hash(x)=22845826) +4735 train 7.199048 (lr=1.7500e-04) (hash(x)=24484543) +4736 train 7.004312 (lr=1.7500e-04) (hash(x)=23352320) +4737 train 6.855295 (lr=1.7500e-04) (hash(x)=21544758) +4738 train 6.697238 (lr=1.7500e-04) (hash(x)=18292136) +4739 train 7.334262 (lr=1.7500e-04) (hash(x)=24893614) +4740 train 7.100106 (lr=1.7500e-04) (hash(x)=28103443) +4741 train 6.970680 (lr=1.7500e-04) (hash(x)=22233356) +4742 train 6.862545 (lr=1.7500e-04) (hash(x)=21133541) +4743 train 7.132439 (lr=1.7500e-04) (hash(x)=24043998) +4744 train 7.384087 (lr=1.7500e-04) (hash(x)=24801185) +4745 train 7.139601 (lr=1.7500e-04) (hash(x)=23858358) +4746 train 7.153375 (lr=1.7500e-04) (hash(x)=23926989) +4747 train 7.247168 (lr=1.7500e-04) (hash(x)=24813708) +4748 train 7.062562 (lr=1.7500e-04) (hash(x)=26339467) +4749 train 6.940840 (lr=1.7500e-04) (hash(x)=21850656) +4750 val loss 7.2079 +4750 val perplexity 1350.0729 +4750 train 6.931835 (lr=1.7500e-04) (hash(x)=21475802) +4751 train 7.102959 (lr=1.7500e-04) (hash(x)=24301906) +4752 train 6.943053 (lr=1.7500e-04) (hash(x)=22748495) +4753 train 7.096360 (lr=1.7500e-04) (hash(x)=25649256) +4754 train 6.973441 (lr=1.7500e-04) (hash(x)=23934346) +4755 train 7.096442 (lr=1.7500e-04) (hash(x)=26332892) +4756 train 6.945523 (lr=1.7500e-04) (hash(x)=23279389) +4757 train 7.041965 (lr=1.7500e-04) (hash(x)=23146858) +4758 train 7.416736 (lr=1.7500e-04) (hash(x)=26892932) +4759 train 6.956409 (lr=1.7500e-04) (hash(x)=26328881) +4760 train 7.030213 (lr=1.7500e-04) (hash(x)=24394655) +4761 train 7.027882 (lr=1.7500e-04) (hash(x)=22122308) +4762 train 7.160515 (lr=1.7500e-04) (hash(x)=24200369) +4763 train 7.302938 (lr=1.7500e-04) (hash(x)=26841776) +4764 train 7.265434 (lr=1.7500e-04) (hash(x)=27196641) +4765 train 6.979177 (lr=1.7500e-04) (hash(x)=24912822) +4766 train 7.241863 (lr=1.7500e-04) (hash(x)=25946055) +4767 train 6.847585 (lr=1.7500e-04) (hash(x)=23101508) +4768 train 7.013142 (lr=1.7500e-04) (hash(x)=24287798) +4769 train 7.080360 (lr=1.7500e-04) (hash(x)=22798964) +4770 train 7.016068 (lr=1.7500e-04) (hash(x)=24164479) +4771 train 7.080905 (lr=1.7500e-04) (hash(x)=24946464) +4772 train 7.198865 (lr=1.7500e-04) (hash(x)=25154423) +4773 train 6.914453 (lr=1.7500e-04) (hash(x)=23173476) +4774 train 7.154817 (lr=1.7500e-04) (hash(x)=25373559) +4775 train 7.132059 (lr=1.7500e-04) (hash(x)=23527176) +4776 train 7.094640 (lr=1.7500e-04) (hash(x)=24865403) +4777 train 7.017841 (lr=1.7500e-04) (hash(x)=24451067) +4778 train 7.656274 (lr=1.7500e-04) (hash(x)=28187162) +4779 train 7.808298 (lr=1.7500e-04) (hash(x)=31163350) +4780 train 8.157247 (lr=1.7500e-04) (hash(x)=33563280) +4781 train 8.201530 (lr=1.7500e-04) (hash(x)=34939183) +4782 train 7.666069 (lr=1.7500e-04) (hash(x)=30263543) +4783 train 7.005429 (lr=1.7500e-04) (hash(x)=22705673) +4784 train 6.860265 (lr=1.7500e-04) (hash(x)=21415023) +4785 train 7.109506 (lr=1.7500e-04) (hash(x)=26079097) +4786 train 7.410367 (lr=1.7500e-04) (hash(x)=25503836) +4787 train 7.245374 (lr=1.7500e-04) (hash(x)=24705721) +4788 train 7.127042 (lr=1.7500e-04) (hash(x)=24384657) +4789 train 7.011465 (lr=1.7500e-04) (hash(x)=22550579) +4790 train 7.066677 (lr=1.7500e-04) (hash(x)=22452164) +4791 train 7.360397 (lr=1.7500e-04) (hash(x)=28664796) +4792 train 7.669000 (lr=1.7500e-04) (hash(x)=26139280) +4793 train 7.295196 (lr=1.7500e-04) (hash(x)=23862341) +4794 train 6.931092 (lr=1.7500e-04) (hash(x)=23784757) +4795 train 6.807836 (lr=1.7500e-04) (hash(x)=22659441) +4796 train 7.542699 (lr=1.7500e-04) (hash(x)=29744216) +4797 train 7.452407 (lr=1.7500e-04) (hash(x)=25822591) +4798 train 6.923741 (lr=1.7500e-04) (hash(x)=22370895) +4799 train 7.345284 (lr=1.7500e-04) (hash(x)=27102890) +4800 val loss 7.2037 +4800 val perplexity 1344.3607 +4800 train 7.363229 (lr=1.7500e-04) (hash(x)=27014625) +4801 train 7.152093 (lr=1.7500e-04) (hash(x)=25755963) +4802 train 7.384814 (lr=1.7500e-04) (hash(x)=29675278) +4803 train 7.491370 (lr=1.7500e-04) (hash(x)=26660930) +4804 train 7.401357 (lr=1.7500e-04) (hash(x)=24557060) +4805 train 7.518086 (lr=1.7500e-04) (hash(x)=24622741) +4806 train 7.577025 (lr=1.7500e-04) (hash(x)=23952601) +4807 train 7.215194 (lr=1.7500e-04) (hash(x)=26787259) +4808 train 7.448941 (lr=1.7500e-04) (hash(x)=28919605) +4809 train 7.837429 (lr=1.7500e-04) (hash(x)=37061654) +4810 train 7.574090 (lr=1.7500e-04) (hash(x)=30379739) +4811 train 7.329135 (lr=1.7500e-04) (hash(x)=26097180) +4812 train 7.479450 (lr=1.7500e-04) (hash(x)=26327092) +4813 train 7.250492 (lr=1.7500e-04) (hash(x)=23258030) +4814 train 7.326398 (lr=1.7500e-04) (hash(x)=25582015) +4815 train 7.039445 (lr=1.7500e-04) (hash(x)=23396088) +4816 train 7.008055 (lr=1.7500e-04) (hash(x)=21904146) +4817 train 7.212293 (lr=1.7500e-04) (hash(x)=26281676) +4818 train 6.989873 (lr=1.7500e-04) (hash(x)=23140470) +4819 train 7.220639 (lr=1.7500e-04) (hash(x)=24611098) +4820 train 7.082607 (lr=1.7500e-04) (hash(x)=23832642) +4821 train 7.223222 (lr=1.7500e-04) (hash(x)=21439671) +4822 train 7.087536 (lr=1.7500e-04) (hash(x)=25128845) +4823 train 7.006886 (lr=1.7500e-04) (hash(x)=24911831) +4824 train 7.183365 (lr=1.7500e-04) (hash(x)=26051723) +4825 train 7.214597 (lr=1.7500e-04) (hash(x)=26479565) +4826 train 7.318039 (lr=1.7500e-04) (hash(x)=26228987) +4827 train 7.242458 (lr=1.7500e-04) (hash(x)=25131300) +4828 train 6.886636 (lr=1.7500e-04) (hash(x)=19921978) +4829 train 6.923982 (lr=1.7500e-04) (hash(x)=23173449) +4830 train 7.236767 (lr=1.7500e-04) (hash(x)=24791832) +4831 train 6.969426 (lr=1.7500e-04) (hash(x)=23453491) +4832 train 7.125323 (lr=1.7500e-04) (hash(x)=22564139) +4833 train 6.966185 (lr=1.7500e-04) (hash(x)=21659918) +4834 train 7.140410 (lr=1.7500e-04) (hash(x)=22956076) +4835 train 7.169591 (lr=1.7500e-04) (hash(x)=22237612) +4836 train 7.243253 (lr=1.7500e-04) (hash(x)=24736427) +4837 train 7.380725 (lr=1.7500e-04) (hash(x)=24939751) +4838 train 7.209305 (lr=1.7500e-04) (hash(x)=25059298) +4839 train 7.131714 (lr=1.7500e-04) (hash(x)=23453396) +4840 train 6.666987 (lr=1.7500e-04) (hash(x)=17919338) +4841 train 7.156521 (lr=1.7500e-04) (hash(x)=23428815) +4842 train 7.439865 (lr=1.7500e-04) (hash(x)=27042659) +4843 train 7.444570 (lr=1.7500e-04) (hash(x)=25161278) +4844 train 7.254028 (lr=1.7500e-04) (hash(x)=24113253) +4845 train 7.397330 (lr=1.7500e-04) (hash(x)=26139263) +4846 train 7.407654 (lr=1.7500e-04) (hash(x)=27787006) +4847 train 7.161000 (lr=1.7500e-04) (hash(x)=23869612) +4848 train 7.270102 (lr=1.7500e-04) (hash(x)=26092193) +4849 train 7.354348 (lr=1.7500e-04) (hash(x)=29351182) +4850 val loss 7.1621 +4850 val perplexity 1289.6086 +4850 train 7.433928 (lr=1.7500e-04) (hash(x)=28773463) +4851 train 7.397369 (lr=1.7500e-04) (hash(x)=28207741) +4852 train 6.974003 (lr=1.7500e-04) (hash(x)=23280878) +4853 train 7.434709 (lr=1.7500e-04) (hash(x)=26742336) +4854 train 7.184352 (lr=1.7500e-04) (hash(x)=23543321) +4855 train 7.548038 (lr=1.7500e-04) (hash(x)=26581590) +4856 train 6.995206 (lr=1.7500e-04) (hash(x)=22728668) +4857 train 6.874800 (lr=1.7500e-04) (hash(x)=19854534) +4858 train 7.273960 (lr=1.7500e-04) (hash(x)=26612813) +4859 train 7.397507 (lr=1.7500e-04) (hash(x)=25827863) +4860 train 7.068546 (lr=1.7500e-04) (hash(x)=24574997) +4861 train 7.273374 (lr=1.7500e-04) (hash(x)=26187830) +4862 train 7.209878 (lr=1.7500e-04) (hash(x)=25105823) +4863 train 7.289751 (lr=1.7500e-04) (hash(x)=28056342) +4864 train 7.150067 (lr=1.7500e-04) (hash(x)=21885801) +4865 train 7.353878 (lr=1.7500e-04) (hash(x)=25659043) +4866 train 7.363808 (lr=1.7500e-04) (hash(x)=23852824) +4867 train 7.124887 (lr=1.7500e-04) (hash(x)=23965470) +4868 train 7.128566 (lr=1.7500e-04) (hash(x)=25035012) +4869 train 7.360598 (lr=1.7500e-04) (hash(x)=26639165) +4870 train 7.280926 (lr=1.7500e-04) (hash(x)=29205362) +4871 train 7.114030 (lr=1.7500e-04) (hash(x)=25900866) +4872 train 7.176239 (lr=1.7500e-04) (hash(x)=25636242) +4873 train 7.240324 (lr=1.7500e-04) (hash(x)=25430698) +4874 train 7.235060 (lr=1.7500e-04) (hash(x)=27629981) +4875 train 7.219087 (lr=1.7500e-04) (hash(x)=27682625) +4876 train 7.524544 (lr=1.7500e-04) (hash(x)=27549409) +4877 train 7.253551 (lr=1.7500e-04) (hash(x)=24661627) +4878 train 7.273906 (lr=1.7500e-04) (hash(x)=25196542) +4879 train 7.164463 (lr=1.7500e-04) (hash(x)=24549177) +4880 train 7.103796 (lr=1.7500e-04) (hash(x)=23740600) +4881 train 7.021285 (lr=1.7500e-04) (hash(x)=21460850) +4882 train 7.275017 (lr=1.7500e-04) (hash(x)=27101400) +4883 train 7.305450 (lr=1.7500e-04) (hash(x)=24193076) +4884 train 7.217649 (lr=1.7500e-04) (hash(x)=24582947) +4885 train 7.182492 (lr=1.7500e-04) (hash(x)=25133839) +4886 train 7.165840 (lr=1.7500e-04) (hash(x)=24759454) +4887 train 7.236600 (lr=1.7500e-04) (hash(x)=28239583) +4888 train 7.467709 (lr=1.7500e-04) (hash(x)=29594489) +4889 train 7.159123 (lr=1.7500e-04) (hash(x)=23833431) +4890 train 7.112662 (lr=1.7500e-04) (hash(x)=23139411) +4891 train 7.073240 (lr=1.7500e-04) (hash(x)=20885864) +4892 train 7.502193 (lr=1.7500e-04) (hash(x)=26217418) +4893 train 7.253711 (lr=1.7500e-04) (hash(x)=27321870) +4894 train 6.777093 (lr=1.7500e-04) (hash(x)=19912955) +4895 train 7.087247 (lr=1.7500e-04) (hash(x)=23223554) +4896 train 7.253328 (lr=1.7500e-04) (hash(x)=25667219) +4897 train 7.465118 (lr=1.7500e-04) (hash(x)=28007972) +4898 train 7.287550 (lr=1.7500e-04) (hash(x)=27748764) +4899 train 7.214406 (lr=1.7500e-04) (hash(x)=27425770) +4900 val loss 7.1484 +4900 val perplexity 1272.1191 +4900 train 7.349153 (lr=1.7500e-04) (hash(x)=28394020) +4901 train 7.195414 (lr=1.7500e-04) (hash(x)=24080235) +4902 train 7.054235 (lr=1.7500e-04) (hash(x)=23309527) +4903 train 7.028030 (lr=1.7500e-04) (hash(x)=24793480) +4904 train 7.251115 (lr=1.7500e-04) (hash(x)=25344456) +4905 train 7.176388 (lr=1.7500e-04) (hash(x)=24590670) +4906 train 7.146801 (lr=1.7500e-04) (hash(x)=26937171) +4907 train 7.295391 (lr=1.7500e-04) (hash(x)=26949097) +4908 train 6.992989 (lr=1.7500e-04) (hash(x)=22443915) +4909 train 7.041206 (lr=1.7500e-04) (hash(x)=23814995) +4910 train 7.101887 (lr=1.7500e-04) (hash(x)=26135871) +4911 train 6.953134 (lr=1.7500e-04) (hash(x)=25415570) +4912 train 7.249322 (lr=1.7500e-04) (hash(x)=26756326) +4913 train 7.119910 (lr=1.7500e-04) (hash(x)=22920200) +4914 train 7.230534 (lr=1.7500e-04) (hash(x)=26710977) +4915 train 7.161473 (lr=1.7500e-04) (hash(x)=24985634) +4916 train 7.245157 (lr=1.7500e-04) (hash(x)=26004335) +4917 train 7.191922 (lr=1.7500e-04) (hash(x)=25637457) +4918 train 7.380952 (lr=1.7500e-04) (hash(x)=26645180) +4919 train 7.228210 (lr=1.7500e-04) (hash(x)=24425760) +4920 train 7.445383 (lr=1.7500e-04) (hash(x)=28223544) +4921 train 7.170007 (lr=1.7500e-04) (hash(x)=25538618) +4922 train 7.377059 (lr=1.7500e-04) (hash(x)=26984784) +4923 train 7.414421 (lr=1.7500e-04) (hash(x)=29154578) +4924 train 7.107097 (lr=1.7500e-04) (hash(x)=25308123) +4925 train 7.446855 (lr=1.7500e-04) (hash(x)=27939259) +4926 train 7.031635 (lr=1.7500e-04) (hash(x)=21984545) +4927 train 7.088013 (lr=1.7500e-04) (hash(x)=23707134) +4928 train 7.127228 (lr=1.7500e-04) (hash(x)=27201034) +4929 train 7.501993 (lr=1.7500e-04) (hash(x)=31623877) +4930 train 7.142334 (lr=1.7500e-04) (hash(x)=22162782) +4931 train 7.067287 (lr=1.7500e-04) (hash(x)=20049335) +4932 train 7.021927 (lr=1.7500e-04) (hash(x)=25594665) +4933 train 7.129225 (lr=1.7500e-04) (hash(x)=25265312) +4934 train 7.187354 (lr=1.7500e-04) (hash(x)=27094896) +4935 train 7.469448 (lr=1.7500e-04) (hash(x)=28321697) +4936 train 7.102464 (lr=1.7500e-04) (hash(x)=25006013) +4937 train 7.294635 (lr=1.7500e-04) (hash(x)=24596431) +4938 train 7.289987 (lr=1.7500e-04) (hash(x)=25150510) +4939 train 6.853044 (lr=1.7500e-04) (hash(x)=21497535) +4940 train 7.117056 (lr=1.7500e-04) (hash(x)=25094669) +4941 train 7.024467 (lr=1.7500e-04) (hash(x)=24024557) +4942 train 7.271749 (lr=1.7500e-04) (hash(x)=24370776) +4943 train 7.108398 (lr=1.7500e-04) (hash(x)=23434031) +4944 train 7.104105 (lr=1.7500e-04) (hash(x)=24383517) +4945 train 7.135364 (lr=1.7500e-04) (hash(x)=25858759) +4946 train 6.706741 (lr=1.7500e-04) (hash(x)=20409561) +4947 train 7.414609 (lr=1.7500e-04) (hash(x)=27469117) +4948 train 6.977438 (lr=1.7500e-04) (hash(x)=22086623) +4949 train 7.267471 (lr=1.7500e-04) (hash(x)=25759281) +4950 val loss 7.1300 +4950 val perplexity 1248.8914 +4950 train 7.177648 (lr=1.7500e-04) (hash(x)=27130117) +4951 train 7.064579 (lr=1.7500e-04) (hash(x)=27003481) +4952 train 7.387348 (lr=1.7500e-04) (hash(x)=26725937) +4953 train 7.105563 (lr=1.7500e-04) (hash(x)=22691119) +4954 train 7.118980 (lr=1.7500e-04) (hash(x)=17272898) +4955 train 6.938070 (lr=1.7500e-04) (hash(x)=17850370) +4956 train 6.961753 (lr=1.7500e-04) (hash(x)=18729639) +4957 train 7.201715 (lr=1.7500e-04) (hash(x)=25327160) +4958 train 7.367887 (lr=1.7500e-04) (hash(x)=28709044) +4959 train 6.930652 (lr=1.7500e-04) (hash(x)=22236893) +4960 train 6.878226 (lr=1.7500e-04) (hash(x)=21729251) +4961 train 6.969022 (lr=1.7500e-04) (hash(x)=23852346) +4962 train 7.208299 (lr=1.7500e-04) (hash(x)=23974368) +4963 train 7.130769 (lr=1.7500e-04) (hash(x)=25764691) +4964 train 7.515660 (lr=1.7500e-04) (hash(x)=28341865) +4965 train 7.042117 (lr=1.7500e-04) (hash(x)=23856238) +4966 train 7.252830 (lr=1.7500e-04) (hash(x)=24568904) +4967 train 7.174881 (lr=1.7500e-04) (hash(x)=26857458) +4968 train 6.967166 (lr=1.7500e-04) (hash(x)=20507972) +4969 train 7.194116 (lr=1.7500e-04) (hash(x)=23139455) +4970 train 7.043088 (lr=1.7500e-04) (hash(x)=24853703) +4971 train 7.097202 (lr=1.7500e-04) (hash(x)=25654849) +4972 train 6.913653 (lr=1.7500e-04) (hash(x)=22963710) +4973 train 7.311159 (lr=1.7500e-04) (hash(x)=25652110) +4974 train 7.222490 (lr=1.7500e-04) (hash(x)=24085957) +4975 train 7.451244 (lr=1.7500e-04) (hash(x)=26413122) +4976 train 7.562483 (lr=1.7500e-04) (hash(x)=26989387) +4977 train 7.166473 (lr=1.7500e-04) (hash(x)=22784033) +4978 train 7.520119 (lr=1.7500e-04) (hash(x)=26694945) +4979 train 7.460730 (lr=1.7500e-04) (hash(x)=24507726) +4980 train 7.514897 (lr=1.7500e-04) (hash(x)=26490335) +4981 train 7.426230 (lr=1.7500e-04) (hash(x)=25624751) +4982 train 7.458258 (lr=1.7500e-04) (hash(x)=27846204) +4983 train 7.359600 (lr=1.7500e-04) (hash(x)=27696537) +4984 train 7.190567 (lr=1.7500e-04) (hash(x)=28915842) +4985 train 7.314443 (lr=1.7500e-04) (hash(x)=28274576) +4986 train 7.390892 (lr=1.7500e-04) (hash(x)=28923892) +4987 train 6.995088 (lr=1.7500e-04) (hash(x)=21602520) +4988 train 6.949066 (lr=1.7500e-04) (hash(x)=21061011) +4989 train 7.423206 (lr=1.7500e-04) (hash(x)=28060542) +4990 train 7.234509 (lr=1.7500e-04) (hash(x)=24838134) +4991 train 7.127361 (lr=1.7500e-04) (hash(x)=21950234) +4992 train 7.384769 (lr=1.7500e-04) (hash(x)=27192740) +4993 train 7.392925 (lr=1.7500e-04) (hash(x)=26770105) +4994 train 7.081674 (lr=1.7500e-04) (hash(x)=23721261) +4995 train 7.113248 (lr=1.7500e-04) (hash(x)=26064895) +4996 train 7.283420 (lr=1.7500e-04) (hash(x)=25651075) +4997 train 7.126018 (lr=1.7500e-04) (hash(x)=25029447) +4998 train 7.267946 (lr=1.7500e-04) (hash(x)=26088225) +4999 val loss 7.1676 +4999 val perplexity 1296.6639 +4999 train 7.182974 (lr=1.7500e-04) (hash(x)=24051952) diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/model_02500.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/model_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..b45dc346d9d1c9072ffe4f2c6357730a4a1ec06b --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/model_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6fcf0ee03a58594c744c0491c1b87add24ee55937fa2027c9a1901ff9d9a679 +size 38587970 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/model_04999.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/model_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..2285b46cea30914829e296739f6e6111bb38c525 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/model_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66528171e765332921d4edff5987b485a3c16944b09c56bf5cde0429daf9139f +size 38587970 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/optimizer_02500.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/optimizer_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..41d118ec3f5a83d46e4570a1709da10e6177c456 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/optimizer_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8770519a4ff0f7ff2a98dac8fb56a3fd40551960683c317b1eee675bd693881 +size 70895430 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/optimizer_04999.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/optimizer_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..931484256b40d8818fc1dd7440dc7a15f1206f33 --- /dev/null +++ b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrfalse_attention_kindselective_warmup_steps1_seed1339/optimizer_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd6f89ae93b561383278e71b83b9d5e607303d7db9999f8fb0fc5d272f5b0a6a +size 70895430