diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/args.json b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/args.json new file mode 100644 index 0000000000000000000000000000000000000000..aa2450448b250a6d3414b084b1b4cac1f93f0ba0 --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/args.json @@ -0,0 +1 @@ +{"hellaswag": true, "attention_kind": "selective", "log_dir": "proxy_model_sweep_2/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_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": 0.0002, "decay_lr": true, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "n_embd": 128} \ No newline at end of file diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/dataloader_02500.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/dataloader_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bc253f8fc6225637fb651d7b45bcde02b1c9ff0 --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_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/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/dataloader_04999.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/dataloader_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..0618c479f1dc6588bdd52311cf3417cbd843ddd9 --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_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/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/log2.txt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/log2.txt new file mode 100644 index 0000000000000000000000000000000000000000..585d6956785f261fe8885ddd19ad7cfaa81b919d --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_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=2.0000e-04) (hash(x)=22886834) +1 train 11.379649 (lr=2.0000e-04) (hash(x)=26375038) +2 train 11.081805 (lr=2.0000e-04) (hash(x)=30598777) +3 train 10.950965 (lr=2.0000e-04) (hash(x)=27234506) +4 train 10.639201 (lr=2.0000e-04) (hash(x)=27767880) +5 train 10.505271 (lr=2.0000e-04) (hash(x)=23702020) +6 train 10.531298 (lr=2.0000e-04) (hash(x)=31986844) +7 train 10.375012 (lr=2.0000e-04) (hash(x)=20782690) +8 train 10.353520 (lr=2.0000e-04) (hash(x)=25201599) +9 train 10.200073 (lr=2.0000e-04) (hash(x)=23094976) +10 train 10.153651 (lr=2.0000e-04) (hash(x)=23841096) +11 train 10.153434 (lr=2.0000e-04) (hash(x)=26532095) +12 train 10.101538 (lr=2.0000e-04) (hash(x)=24432298) +13 train 10.059499 (lr=2.0000e-04) (hash(x)=27151649) +14 train 10.098697 (lr=2.0000e-04) (hash(x)=24596846) +15 train 9.840433 (lr=2.0000e-04) (hash(x)=23890908) +16 train 9.786355 (lr=2.0000e-04) (hash(x)=28913955) +17 train 9.651813 (lr=2.0000e-04) (hash(x)=25588236) +18 train 9.726213 (lr=1.9999e-04) (hash(x)=23770034) +19 train 9.585085 (lr=1.9999e-04) (hash(x)=24011372) +20 train 9.414638 (lr=1.9999e-04) (hash(x)=25441898) +21 train 9.610459 (lr=1.9999e-04) (hash(x)=28375581) +22 train 9.259327 (lr=1.9999e-04) (hash(x)=24046679) +23 train 9.325616 (lr=1.9999e-04) (hash(x)=24611628) +24 train 9.297533 (lr=1.9999e-04) (hash(x)=26169030) +25 train 9.351884 (lr=1.9999e-04) (hash(x)=30298407) +26 train 9.094450 (lr=1.9999e-04) (hash(x)=23711112) +27 train 8.933887 (lr=1.9999e-04) (hash(x)=19245352) +28 train 8.844779 (lr=1.9999e-04) (hash(x)=21529136) +29 train 9.221315 (lr=1.9999e-04) (hash(x)=28936608) +30 train 8.753537 (lr=1.9999e-04) (hash(x)=24339013) +31 train 8.591319 (lr=1.9998e-04) (hash(x)=25767553) +32 train 8.738496 (lr=1.9998e-04) (hash(x)=26439905) +33 train 8.907289 (lr=1.9998e-04) (hash(x)=31093473) +34 train 8.497307 (lr=1.9998e-04) (hash(x)=25450374) +35 train 8.374611 (lr=1.9998e-04) (hash(x)=24809873) +36 train 8.528095 (lr=1.9998e-04) (hash(x)=23253252) +37 train 8.629929 (lr=1.9998e-04) (hash(x)=27852919) +38 train 8.372147 (lr=1.9998e-04) (hash(x)=23327497) +39 train 8.223920 (lr=1.9997e-04) (hash(x)=22512166) +40 train 8.383137 (lr=1.9997e-04) (hash(x)=22859419) +41 train 8.334603 (lr=1.9997e-04) (hash(x)=27620338) +42 train 8.385012 (lr=1.9997e-04) (hash(x)=26397837) +43 train 8.401919 (lr=1.9997e-04) (hash(x)=28092148) +44 train 8.253217 (lr=1.9997e-04) (hash(x)=24662703) +45 train 8.411976 (lr=1.9997e-04) (hash(x)=27938767) +46 train 8.707789 (lr=1.9996e-04) (hash(x)=26037988) +47 train 8.098781 (lr=1.9996e-04) (hash(x)=24732833) +48 train 8.218209 (lr=1.9996e-04) (hash(x)=25259526) +49 train 8.203238 (lr=1.9996e-04) (hash(x)=23200230) +50 val loss 8.1344 +50 val perplexity 3409.6733 +50 train 8.190382 (lr=1.9996e-04) (hash(x)=26721357) +51 train 8.008536 (lr=1.9996e-04) (hash(x)=22694718) +52 train 8.113480 (lr=1.9995e-04) (hash(x)=28066766) +53 train 8.059821 (lr=1.9995e-04) (hash(x)=23125151) +54 train 8.063167 (lr=1.9995e-04) (hash(x)=27193725) +55 train 7.947708 (lr=1.9995e-04) (hash(x)=25129410) +56 train 8.050158 (lr=1.9995e-04) (hash(x)=24263988) +57 train 7.846250 (lr=1.9994e-04) (hash(x)=23059154) +58 train 8.071419 (lr=1.9994e-04) (hash(x)=26063864) +59 train 8.329873 (lr=1.9994e-04) (hash(x)=27858570) +60 train 8.028394 (lr=1.9994e-04) (hash(x)=23874620) +61 train 7.900727 (lr=1.9994e-04) (hash(x)=22402617) +62 train 8.001443 (lr=1.9993e-04) (hash(x)=23600822) +63 train 7.859153 (lr=1.9993e-04) (hash(x)=26582391) +64 train 7.842309 (lr=1.9993e-04) (hash(x)=23225283) +65 train 8.174219 (lr=1.9993e-04) (hash(x)=26075451) +66 train 7.886510 (lr=1.9992e-04) (hash(x)=24723419) +67 train 8.040839 (lr=1.9992e-04) (hash(x)=27279806) +68 train 7.850938 (lr=1.9992e-04) (hash(x)=25870391) +69 train 8.063654 (lr=1.9992e-04) (hash(x)=26188136) +70 train 8.188848 (lr=1.9992e-04) (hash(x)=30373443) +71 train 8.107734 (lr=1.9991e-04) (hash(x)=26472336) +72 train 7.898253 (lr=1.9991e-04) (hash(x)=26651572) +73 train 8.017183 (lr=1.9991e-04) (hash(x)=26376212) +74 train 7.963014 (lr=1.9991e-04) (hash(x)=26733350) +75 train 8.125873 (lr=1.9990e-04) (hash(x)=28301589) +76 train 8.000297 (lr=1.9990e-04) (hash(x)=27599559) +77 train 7.993956 (lr=1.9990e-04) (hash(x)=28035221) +78 train 7.979986 (lr=1.9989e-04) (hash(x)=25016783) +79 train 8.049251 (lr=1.9989e-04) (hash(x)=27654289) +80 train 7.891961 (lr=1.9989e-04) (hash(x)=24597558) +81 train 7.692192 (lr=1.9989e-04) (hash(x)=21560904) +82 train 7.645821 (lr=1.9988e-04) (hash(x)=21983837) +83 train 7.829930 (lr=1.9988e-04) (hash(x)=24995715) +84 train 8.160611 (lr=1.9988e-04) (hash(x)=29876413) +85 train 7.746759 (lr=1.9987e-04) (hash(x)=23792508) +86 train 7.721910 (lr=1.9987e-04) (hash(x)=25509120) +87 train 7.978683 (lr=1.9987e-04) (hash(x)=26559876) +88 train 7.916638 (lr=1.9987e-04) (hash(x)=23569647) +89 train 7.915776 (lr=1.9986e-04) (hash(x)=25758852) +90 train 7.768932 (lr=1.9986e-04) (hash(x)=25706298) +91 train 7.940249 (lr=1.9986e-04) (hash(x)=28364895) +92 train 7.713100 (lr=1.9985e-04) (hash(x)=25304663) +93 train 7.800247 (lr=1.9985e-04) (hash(x)=25269299) +94 train 7.962390 (lr=1.9985e-04) (hash(x)=25870566) +95 train 7.562553 (lr=1.9984e-04) (hash(x)=21770329) +96 train 8.050999 (lr=1.9984e-04) (hash(x)=27595900) +97 train 7.987342 (lr=1.9984e-04) (hash(x)=24785397) +98 train 7.690097 (lr=1.9983e-04) (hash(x)=21521480) +99 train 7.822014 (lr=1.9983e-04) (hash(x)=24628606) +100 val loss 7.8501 +100 val perplexity 2566.0056 +100 train 7.929802 (lr=1.9983e-04) (hash(x)=24670150) +101 train 7.825349 (lr=1.9982e-04) (hash(x)=23181910) +102 train 7.773438 (lr=1.9982e-04) (hash(x)=22714991) +103 train 7.708326 (lr=1.9982e-04) (hash(x)=22723459) +104 train 7.678170 (lr=1.9981e-04) (hash(x)=21524316) +105 train 7.891313 (lr=1.9981e-04) (hash(x)=25506632) +106 train 7.574304 (lr=1.9980e-04) (hash(x)=21675672) +107 train 7.685133 (lr=1.9980e-04) (hash(x)=22897919) +108 train 7.711804 (lr=1.9980e-04) (hash(x)=23321631) +109 train 7.894204 (lr=1.9979e-04) (hash(x)=26546719) +110 train 8.995490 (lr=1.9979e-04) (hash(x)=31962348) +111 train 8.264678 (lr=1.9979e-04) (hash(x)=30338342) +112 train 7.842975 (lr=1.9978e-04) (hash(x)=23724471) +113 train 7.968410 (lr=1.9978e-04) (hash(x)=29175888) +114 train 7.963317 (lr=1.9977e-04) (hash(x)=23256716) +115 train 8.041760 (lr=1.9977e-04) (hash(x)=27063280) +116 train 8.047627 (lr=1.9977e-04) (hash(x)=31057659) +117 train 8.271605 (lr=1.9976e-04) (hash(x)=32915097) +118 train 8.089511 (lr=1.9976e-04) (hash(x)=28842717) +119 train 7.798555 (lr=1.9975e-04) (hash(x)=25678059) +120 train 7.673547 (lr=1.9975e-04) (hash(x)=21593510) +121 train 7.604174 (lr=1.9974e-04) (hash(x)=20083773) +122 train 7.773786 (lr=1.9974e-04) (hash(x)=23002820) +123 train 7.596078 (lr=1.9974e-04) (hash(x)=21853028) +124 train 7.872403 (lr=1.9973e-04) (hash(x)=26985625) +125 train 7.609079 (lr=1.9973e-04) (hash(x)=21808483) +126 train 8.010583 (lr=1.9972e-04) (hash(x)=28873251) +127 train 7.840001 (lr=1.9972e-04) (hash(x)=26109335) +128 train 8.054553 (lr=1.9971e-04) (hash(x)=26334674) +129 train 7.925037 (lr=1.9971e-04) (hash(x)=24916754) +130 train 7.872235 (lr=1.9970e-04) (hash(x)=25449624) +131 train 7.952384 (lr=1.9970e-04) (hash(x)=25334848) +132 train 8.240796 (lr=1.9970e-04) (hash(x)=27484863) +133 train 7.774479 (lr=1.9969e-04) (hash(x)=24917705) +134 train 7.742425 (lr=1.9969e-04) (hash(x)=25143449) +135 train 7.761883 (lr=1.9968e-04) (hash(x)=25044885) +136 train 7.966508 (lr=1.9968e-04) (hash(x)=27821028) +137 train 7.975964 (lr=1.9967e-04) (hash(x)=28747022) +138 train 7.923314 (lr=1.9967e-04) (hash(x)=27182888) +139 train 7.701033 (lr=1.9966e-04) (hash(x)=23678349) +140 train 7.837358 (lr=1.9966e-04) (hash(x)=23593235) +141 train 8.183313 (lr=1.9965e-04) (hash(x)=28529813) +142 train 8.480906 (lr=1.9965e-04) (hash(x)=32074661) +143 train 8.060768 (lr=1.9964e-04) (hash(x)=28870690) +144 train 8.027299 (lr=1.9964e-04) (hash(x)=27307705) +145 train 7.862905 (lr=1.9963e-04) (hash(x)=25044834) +146 train 7.903053 (lr=1.9963e-04) (hash(x)=23712023) +147 train 8.392436 (lr=1.9962e-04) (hash(x)=32982615) +148 train 8.145416 (lr=1.9962e-04) (hash(x)=30113660) +149 train 7.554648 (lr=1.9961e-04) (hash(x)=20970960) +150 val loss 7.7899 +150 val perplexity 2415.9580 +150 train 7.755577 (lr=1.9961e-04) (hash(x)=23132684) +151 train 9.706033 (lr=1.9960e-04) (hash(x)=35279941) +152 train 8.771363 (lr=1.9960e-04) (hash(x)=31227444) +153 train 7.739788 (lr=1.9959e-04) (hash(x)=25529472) +154 train 7.846558 (lr=1.9958e-04) (hash(x)=24350409) +155 train 8.146171 (lr=1.9958e-04) (hash(x)=26400041) +156 train 7.832115 (lr=1.9957e-04) (hash(x)=25262621) +157 train 7.861015 (lr=1.9957e-04) (hash(x)=24656138) +158 train 8.090689 (lr=1.9956e-04) (hash(x)=26803414) +159 train 7.974932 (lr=1.9956e-04) (hash(x)=25015923) +160 train 7.709831 (lr=1.9955e-04) (hash(x)=23581172) +161 train 7.817947 (lr=1.9955e-04) (hash(x)=22924885) +162 train 7.732895 (lr=1.9954e-04) (hash(x)=23414296) +163 train 7.916290 (lr=1.9953e-04) (hash(x)=24853586) +164 train 7.959280 (lr=1.9953e-04) (hash(x)=25000130) +165 train 7.868057 (lr=1.9952e-04) (hash(x)=27004780) +166 train 7.841615 (lr=1.9952e-04) (hash(x)=26148573) +167 train 7.796281 (lr=1.9951e-04) (hash(x)=26740855) +168 train 7.456259 (lr=1.9950e-04) (hash(x)=20965419) +169 train 7.709873 (lr=1.9950e-04) (hash(x)=23950114) +170 train 7.648441 (lr=1.9949e-04) (hash(x)=24951982) +171 train 7.786270 (lr=1.9949e-04) (hash(x)=24584116) +172 train 7.759915 (lr=1.9948e-04) (hash(x)=24378759) +173 train 7.750431 (lr=1.9947e-04) (hash(x)=25718516) +174 train 7.904709 (lr=1.9947e-04) (hash(x)=28424396) +175 train 7.704423 (lr=1.9946e-04) (hash(x)=22262151) +176 train 7.950799 (lr=1.9946e-04) (hash(x)=26438412) +177 train 7.710027 (lr=1.9945e-04) (hash(x)=23025303) +178 train 7.753860 (lr=1.9944e-04) (hash(x)=24190770) +179 train 7.915322 (lr=1.9944e-04) (hash(x)=26627860) +180 train 7.687455 (lr=1.9943e-04) (hash(x)=23663439) +181 train 7.568958 (lr=1.9942e-04) (hash(x)=23700532) +182 train 7.630166 (lr=1.9942e-04) (hash(x)=23075676) +183 train 7.865700 (lr=1.9941e-04) (hash(x)=26621834) +184 train 7.945657 (lr=1.9941e-04) (hash(x)=29426269) +185 train 7.572820 (lr=1.9940e-04) (hash(x)=21821465) +186 train 7.793309 (lr=1.9939e-04) (hash(x)=26506130) +187 train 8.058341 (lr=1.9939e-04) (hash(x)=26930630) +188 train 7.604681 (lr=1.9938e-04) (hash(x)=22993793) +189 train 7.486650 (lr=1.9937e-04) (hash(x)=19557946) +190 train 7.818714 (lr=1.9937e-04) (hash(x)=23572891) +191 train 7.637670 (lr=1.9936e-04) (hash(x)=23234741) +192 train 7.699103 (lr=1.9935e-04) (hash(x)=25547951) +193 train 7.787937 (lr=1.9935e-04) (hash(x)=26713563) +194 train 7.799692 (lr=1.9934e-04) (hash(x)=25913622) +195 train 8.048295 (lr=1.9933e-04) (hash(x)=28102443) +196 train 7.716974 (lr=1.9933e-04) (hash(x)=23093351) +197 train 8.495520 (lr=1.9932e-04) (hash(x)=31689122) +198 train 8.328792 (lr=1.9931e-04) (hash(x)=32252517) +199 train 7.875295 (lr=1.9930e-04) (hash(x)=25470563) +200 val loss 7.8492 +200 val perplexity 2563.5647 +200 train 7.913259 (lr=1.9930e-04) (hash(x)=25597614) +201 train 8.007076 (lr=1.9929e-04) (hash(x)=23757479) +202 train 7.811181 (lr=1.9928e-04) (hash(x)=25140048) +203 train 7.973131 (lr=1.9928e-04) (hash(x)=28282861) +204 train 7.720665 (lr=1.9927e-04) (hash(x)=24754885) +205 train 7.941879 (lr=1.9926e-04) (hash(x)=26731964) +206 train 8.040538 (lr=1.9925e-04) (hash(x)=26660561) +207 train 7.592179 (lr=1.9925e-04) (hash(x)=21799102) +208 train 7.815315 (lr=1.9924e-04) (hash(x)=27025986) +209 train 7.649143 (lr=1.9923e-04) (hash(x)=24672077) +210 train 7.721910 (lr=1.9922e-04) (hash(x)=25322984) +211 train 7.576882 (lr=1.9922e-04) (hash(x)=23471769) +212 train 7.422409 (lr=1.9921e-04) (hash(x)=20766491) +213 train 7.940513 (lr=1.9920e-04) (hash(x)=24058931) +214 train 7.659640 (lr=1.9919e-04) (hash(x)=23872843) +215 train 7.689445 (lr=1.9919e-04) (hash(x)=23275479) +216 train 7.809155 (lr=1.9918e-04) (hash(x)=24914695) +217 train 7.678403 (lr=1.9917e-04) (hash(x)=24364396) +218 train 7.941271 (lr=1.9916e-04) (hash(x)=27986474) +219 train 7.853551 (lr=1.9916e-04) (hash(x)=24473581) +220 train 7.745821 (lr=1.9915e-04) (hash(x)=22974689) +221 train 7.800232 (lr=1.9914e-04) (hash(x)=23774644) +222 train 7.749626 (lr=1.9913e-04) (hash(x)=23245327) +223 train 7.552100 (lr=1.9913e-04) (hash(x)=22091862) +224 train 7.634839 (lr=1.9912e-04) (hash(x)=24362839) +225 train 7.794972 (lr=1.9911e-04) (hash(x)=25482303) +226 train 7.876171 (lr=1.9910e-04) (hash(x)=24911853) +227 train 7.859030 (lr=1.9909e-04) (hash(x)=26018202) +228 train 7.689749 (lr=1.9909e-04) (hash(x)=26124495) +229 train 7.790337 (lr=1.9908e-04) (hash(x)=24560096) +230 train 7.765278 (lr=1.9907e-04) (hash(x)=24695331) +231 train 7.515001 (lr=1.9906e-04) (hash(x)=17430373) +232 train 7.544694 (lr=1.9905e-04) (hash(x)=21813345) +233 train 7.180407 (lr=1.9905e-04) (hash(x)=20098681) +234 train 7.519460 (lr=1.9904e-04) (hash(x)=25095928) +235 train 7.645313 (lr=1.9903e-04) (hash(x)=24078083) +236 train 7.648288 (lr=1.9902e-04) (hash(x)=22901505) +237 train 7.872079 (lr=1.9901e-04) (hash(x)=26595592) +238 train 7.744952 (lr=1.9900e-04) (hash(x)=27663196) +239 train 7.541899 (lr=1.9900e-04) (hash(x)=22954861) +240 train 8.018788 (lr=1.9899e-04) (hash(x)=30159234) +241 train 7.939548 (lr=1.9898e-04) (hash(x)=29294271) +242 train 7.890033 (lr=1.9897e-04) (hash(x)=23728322) +243 train 7.952408 (lr=1.9896e-04) (hash(x)=28695016) +244 train 8.060839 (lr=1.9895e-04) (hash(x)=26702728) +245 train 7.862952 (lr=1.9894e-04) (hash(x)=27100115) +246 train 7.766617 (lr=1.9894e-04) (hash(x)=25082752) +247 train 8.088559 (lr=1.9893e-04) (hash(x)=26671799) +248 train 7.776036 (lr=1.9892e-04) (hash(x)=23718946) +249 train 8.011844 (lr=1.9891e-04) (hash(x)=28137394) +250 val loss 7.7366 +250 val perplexity 2290.7002 +250 train 8.030824 (lr=1.9890e-04) (hash(x)=23893495) +251 train 7.805775 (lr=1.9889e-04) (hash(x)=23166092) +252 train 7.736110 (lr=1.9888e-04) (hash(x)=25907665) +253 train 7.730484 (lr=1.9887e-04) (hash(x)=25885986) +254 train 7.785961 (lr=1.9886e-04) (hash(x)=25262712) +255 train 7.758485 (lr=1.9886e-04) (hash(x)=26924723) +256 train 7.928570 (lr=1.9885e-04) (hash(x)=28744736) +257 train 7.696358 (lr=1.9884e-04) (hash(x)=26140590) +258 train 7.902668 (lr=1.9883e-04) (hash(x)=25780449) +259 train 7.729908 (lr=1.9882e-04) (hash(x)=25138659) +260 train 8.038405 (lr=1.9881e-04) (hash(x)=27244046) +261 train 7.848638 (lr=1.9880e-04) (hash(x)=27224685) +262 train 8.107730 (lr=1.9879e-04) (hash(x)=28274477) +263 train 7.630710 (lr=1.9878e-04) (hash(x)=23557495) +264 train 7.744530 (lr=1.9877e-04) (hash(x)=24680596) +265 train 7.758840 (lr=1.9876e-04) (hash(x)=23928957) +266 train 7.693599 (lr=1.9875e-04) (hash(x)=23761390) +267 train 7.650251 (lr=1.9875e-04) (hash(x)=25288123) +268 train 7.959899 (lr=1.9874e-04) (hash(x)=28705502) +269 train 7.539578 (lr=1.9873e-04) (hash(x)=23246294) +270 train 7.645916 (lr=1.9872e-04) (hash(x)=28639079) +271 train 7.541950 (lr=1.9871e-04) (hash(x)=27804380) +272 train 7.704048 (lr=1.9870e-04) (hash(x)=24172235) +273 train 7.761076 (lr=1.9869e-04) (hash(x)=23089140) +274 train 8.020633 (lr=1.9868e-04) (hash(x)=27163701) +275 train 8.071158 (lr=1.9867e-04) (hash(x)=26993263) +276 train 7.793381 (lr=1.9866e-04) (hash(x)=28224233) +277 train 8.097757 (lr=1.9865e-04) (hash(x)=27397203) +278 train 8.010875 (lr=1.9864e-04) (hash(x)=27923882) +279 train 7.840083 (lr=1.9863e-04) (hash(x)=26654908) +280 train 7.760541 (lr=1.9862e-04) (hash(x)=24213147) +281 train 7.486460 (lr=1.9861e-04) (hash(x)=21965022) +282 train 7.669702 (lr=1.9860e-04) (hash(x)=25465685) +283 train 7.884872 (lr=1.9859e-04) (hash(x)=27347722) +284 train 7.876236 (lr=1.9858e-04) (hash(x)=26732050) +285 train 8.037466 (lr=1.9857e-04) (hash(x)=28314127) +286 train 7.593141 (lr=1.9856e-04) (hash(x)=21471186) +287 train 7.585442 (lr=1.9855e-04) (hash(x)=23627518) +288 train 7.567958 (lr=1.9854e-04) (hash(x)=20870353) +289 train 7.670418 (lr=1.9853e-04) (hash(x)=25024764) +290 train 7.471074 (lr=1.9852e-04) (hash(x)=20683822) +291 train 7.760152 (lr=1.9851e-04) (hash(x)=21768671) +292 train 7.785179 (lr=1.9850e-04) (hash(x)=25557309) +293 train 7.963165 (lr=1.9849e-04) (hash(x)=25076667) +294 train 7.593573 (lr=1.9848e-04) (hash(x)=23765822) +295 train 7.568265 (lr=1.9847e-04) (hash(x)=21889990) +296 train 7.784870 (lr=1.9846e-04) (hash(x)=26339893) +297 train 7.470905 (lr=1.9845e-04) (hash(x)=20932794) +298 train 7.608037 (lr=1.9844e-04) (hash(x)=21750070) +299 train 7.797231 (lr=1.9843e-04) (hash(x)=23665838) +300 val loss 7.7128 +300 val perplexity 2236.7358 +300 train 8.543353 (lr=1.9842e-04) (hash(x)=32888061) +301 train 8.317902 (lr=1.9841e-04) (hash(x)=30223582) +302 train 7.996028 (lr=1.9839e-04) (hash(x)=26908418) +303 train 7.325021 (lr=1.9838e-04) (hash(x)=22528001) +304 train 7.906178 (lr=1.9837e-04) (hash(x)=27452187) +305 train 7.717210 (lr=1.9836e-04) (hash(x)=25181641) +306 train 7.823622 (lr=1.9835e-04) (hash(x)=25546593) +307 train 7.830319 (lr=1.9834e-04) (hash(x)=22487328) +308 train 7.956085 (lr=1.9833e-04) (hash(x)=27804274) +309 train 8.041492 (lr=1.9832e-04) (hash(x)=26544630) +310 train 8.146339 (lr=1.9831e-04) (hash(x)=27738934) +311 train 7.949981 (lr=1.9830e-04) (hash(x)=29248942) +312 train 7.709128 (lr=1.9829e-04) (hash(x)=25103452) +313 train 7.922505 (lr=1.9828e-04) (hash(x)=25052066) +314 train 7.737386 (lr=1.9826e-04) (hash(x)=24481302) +315 train 7.691553 (lr=1.9825e-04) (hash(x)=23543273) +316 train 7.692563 (lr=1.9824e-04) (hash(x)=25608244) +317 train 7.877473 (lr=1.9823e-04) (hash(x)=27451288) +318 train 7.569854 (lr=1.9822e-04) (hash(x)=22806491) +319 train 7.744556 (lr=1.9821e-04) (hash(x)=25533417) +320 train 7.733398 (lr=1.9820e-04) (hash(x)=24557997) +321 train 7.782449 (lr=1.9819e-04) (hash(x)=24432899) +322 train 8.002124 (lr=1.9817e-04) (hash(x)=27583287) +323 train 7.916305 (lr=1.9816e-04) (hash(x)=25552036) +324 train 7.648118 (lr=1.9815e-04) (hash(x)=24201868) +325 train 7.957065 (lr=1.9814e-04) (hash(x)=28149782) +326 train 7.746021 (lr=1.9813e-04) (hash(x)=25529698) +327 train 7.407300 (lr=1.9812e-04) (hash(x)=20612533) +328 train 7.468617 (lr=1.9811e-04) (hash(x)=20699000) +329 train 7.379007 (lr=1.9809e-04) (hash(x)=19774173) +330 train 7.444495 (lr=1.9808e-04) (hash(x)=21681646) +331 train 7.312831 (lr=1.9807e-04) (hash(x)=20216795) +332 train 8.031967 (lr=1.9806e-04) (hash(x)=27697998) +333 train 7.760948 (lr=1.9805e-04) (hash(x)=25896435) +334 train 7.615683 (lr=1.9804e-04) (hash(x)=21585310) +335 train 7.681482 (lr=1.9802e-04) (hash(x)=24677740) +336 train 7.492341 (lr=1.9801e-04) (hash(x)=22027900) +337 train 7.525607 (lr=1.9800e-04) (hash(x)=21835643) +338 train 7.455582 (lr=1.9799e-04) (hash(x)=20558462) +339 train 7.352216 (lr=1.9798e-04) (hash(x)=16722715) +340 train 7.528745 (lr=1.9797e-04) (hash(x)=20972655) +341 train 7.976569 (lr=1.9795e-04) (hash(x)=26303975) +342 train 7.727930 (lr=1.9794e-04) (hash(x)=22938170) +343 train 7.794806 (lr=1.9793e-04) (hash(x)=25347203) +344 train 7.778100 (lr=1.9792e-04) (hash(x)=27398686) +345 train 7.717871 (lr=1.9791e-04) (hash(x)=25973417) +346 train 7.748358 (lr=1.9789e-04) (hash(x)=26918389) +347 train 7.668578 (lr=1.9788e-04) (hash(x)=24272489) +348 train 7.728252 (lr=1.9787e-04) (hash(x)=25593714) +349 train 7.819314 (lr=1.9786e-04) (hash(x)=29260846) +350 val loss 7.7073 +350 val perplexity 2224.4519 +350 train 7.899871 (lr=1.9784e-04) (hash(x)=27951602) +351 train 8.000037 (lr=1.9783e-04) (hash(x)=28922363) +352 train 7.851014 (lr=1.9782e-04) (hash(x)=27210734) +353 train 7.880325 (lr=1.9781e-04) (hash(x)=26322572) +354 train 7.793701 (lr=1.9779e-04) (hash(x)=27084665) +355 train 7.691683 (lr=1.9778e-04) (hash(x)=25510798) +356 train 7.837499 (lr=1.9777e-04) (hash(x)=24970921) +357 train 7.893306 (lr=1.9776e-04) (hash(x)=24138948) +358 train 7.804064 (lr=1.9774e-04) (hash(x)=24790211) +359 train 7.793904 (lr=1.9773e-04) (hash(x)=25631397) +360 train 7.651727 (lr=1.9772e-04) (hash(x)=23226625) +361 train 7.697836 (lr=1.9771e-04) (hash(x)=24001903) +362 train 7.701619 (lr=1.9769e-04) (hash(x)=24587948) +363 train 7.392876 (lr=1.9768e-04) (hash(x)=21333676) +364 train 7.222165 (lr=1.9767e-04) (hash(x)=23673779) +365 train 8.700417 (lr=1.9766e-04) (hash(x)=30770484) +366 train 7.823058 (lr=1.9764e-04) (hash(x)=26564899) +367 train 7.795375 (lr=1.9763e-04) (hash(x)=26237983) +368 train 7.566206 (lr=1.9762e-04) (hash(x)=23764356) +369 train 7.922582 (lr=1.9760e-04) (hash(x)=26205744) +370 train 7.582228 (lr=1.9759e-04) (hash(x)=19208770) +371 train 7.784778 (lr=1.9758e-04) (hash(x)=25976502) +372 train 7.650169 (lr=1.9756e-04) (hash(x)=23983933) +373 train 7.613423 (lr=1.9755e-04) (hash(x)=24080636) +374 train 7.717135 (lr=1.9754e-04) (hash(x)=24404047) +375 train 7.687460 (lr=1.9753e-04) (hash(x)=24742645) +376 train 7.728925 (lr=1.9751e-04) (hash(x)=24159600) +377 train 7.986490 (lr=1.9750e-04) (hash(x)=28677257) +378 train 7.724925 (lr=1.9749e-04) (hash(x)=25604111) +379 train 7.718404 (lr=1.9747e-04) (hash(x)=27086333) +380 train 7.676243 (lr=1.9746e-04) (hash(x)=25188207) +381 train 7.919281 (lr=1.9745e-04) (hash(x)=27855233) +382 train 7.540565 (lr=1.9743e-04) (hash(x)=19470039) +383 train 7.768280 (lr=1.9742e-04) (hash(x)=26157660) +384 train 7.661445 (lr=1.9741e-04) (hash(x)=25291570) +385 train 7.610250 (lr=1.9739e-04) (hash(x)=25046062) +386 train 7.957223 (lr=1.9738e-04) (hash(x)=27020337) +387 train 7.600890 (lr=1.9736e-04) (hash(x)=23616370) +388 train 7.271482 (lr=1.9735e-04) (hash(x)=19113218) +389 train 7.655911 (lr=1.9734e-04) (hash(x)=24302232) +390 train 7.682871 (lr=1.9732e-04) (hash(x)=22188949) +391 train 7.451862 (lr=1.9731e-04) (hash(x)=22582169) +392 train 7.641994 (lr=1.9730e-04) (hash(x)=24700570) +393 train 7.552658 (lr=1.9728e-04) (hash(x)=22773833) +394 train 7.432649 (lr=1.9727e-04) (hash(x)=21875928) +395 train 7.749359 (lr=1.9726e-04) (hash(x)=26233189) +396 train 7.580096 (lr=1.9724e-04) (hash(x)=24321467) +397 train 7.841465 (lr=1.9723e-04) (hash(x)=26431507) +398 train 7.891521 (lr=1.9721e-04) (hash(x)=28690877) +399 train 7.839517 (lr=1.9720e-04) (hash(x)=26431960) +400 val loss 7.7013 +400 val perplexity 2211.1504 +400 train 7.633636 (lr=1.9719e-04) (hash(x)=24580300) +401 train 7.631412 (lr=1.9717e-04) (hash(x)=25112360) +402 train 7.735324 (lr=1.9716e-04) (hash(x)=27597243) +403 train 8.232841 (lr=1.9714e-04) (hash(x)=30707498) +404 train 7.873178 (lr=1.9713e-04) (hash(x)=28485465) +405 train 7.536017 (lr=1.9711e-04) (hash(x)=22586447) +406 train 7.662443 (lr=1.9710e-04) (hash(x)=23175270) +407 train 7.768501 (lr=1.9709e-04) (hash(x)=25716176) +408 train 7.850217 (lr=1.9707e-04) (hash(x)=26861373) +409 train 7.925716 (lr=1.9706e-04) (hash(x)=25118971) +410 train 7.418045 (lr=1.9704e-04) (hash(x)=19829066) +411 train 7.603081 (lr=1.9703e-04) (hash(x)=26256420) +412 train 7.860834 (lr=1.9701e-04) (hash(x)=27796153) +413 train 7.631026 (lr=1.9700e-04) (hash(x)=22633318) +414 train 7.644066 (lr=1.9699e-04) (hash(x)=22589383) +415 train 8.021689 (lr=1.9697e-04) (hash(x)=28019788) +416 train 7.953120 (lr=1.9696e-04) (hash(x)=28970440) +417 train 7.631784 (lr=1.9694e-04) (hash(x)=27396089) +418 train 7.640883 (lr=1.9693e-04) (hash(x)=21183513) +419 train 7.650351 (lr=1.9691e-04) (hash(x)=23510110) +420 train 7.871228 (lr=1.9690e-04) (hash(x)=28833467) +421 train 7.711185 (lr=1.9688e-04) (hash(x)=23646926) +422 train 7.701204 (lr=1.9687e-04) (hash(x)=24697272) +423 train 7.440569 (lr=1.9685e-04) (hash(x)=20382963) +424 train 7.474378 (lr=1.9684e-04) (hash(x)=23467595) +425 train 7.649072 (lr=1.9682e-04) (hash(x)=24304768) +426 train 7.550464 (lr=1.9681e-04) (hash(x)=21392328) +427 train 7.596878 (lr=1.9679e-04) (hash(x)=25339466) +428 train 7.547259 (lr=1.9678e-04) (hash(x)=22092542) +429 train 7.659819 (lr=1.9676e-04) (hash(x)=22088696) +430 train 7.531342 (lr=1.9675e-04) (hash(x)=22184471) +431 train 7.638597 (lr=1.9673e-04) (hash(x)=24489647) +432 train 7.688076 (lr=1.9672e-04) (hash(x)=26794132) +433 train 7.491278 (lr=1.9670e-04) (hash(x)=22940357) +434 train 7.626694 (lr=1.9669e-04) (hash(x)=23719522) +435 train 7.475252 (lr=1.9667e-04) (hash(x)=22927699) +436 train 7.646797 (lr=1.9666e-04) (hash(x)=26068576) +437 train 7.817956 (lr=1.9664e-04) (hash(x)=27631132) +438 train 7.686038 (lr=1.9663e-04) (hash(x)=26739991) +439 train 7.756540 (lr=1.9661e-04) (hash(x)=25128502) +440 train 7.781647 (lr=1.9660e-04) (hash(x)=25657260) +441 train 7.511739 (lr=1.9658e-04) (hash(x)=23576982) +442 train 7.762699 (lr=1.9657e-04) (hash(x)=27117886) +443 train 7.756660 (lr=1.9655e-04) (hash(x)=25808969) +444 train 7.647826 (lr=1.9653e-04) (hash(x)=24738238) +445 train 7.615150 (lr=1.9652e-04) (hash(x)=23429962) +446 train 7.804805 (lr=1.9650e-04) (hash(x)=25075165) +447 train 7.640863 (lr=1.9649e-04) (hash(x)=25231390) +448 train 7.453339 (lr=1.9647e-04) (hash(x)=22055054) +449 train 7.618154 (lr=1.9646e-04) (hash(x)=25395441) +450 val loss 7.6442 +450 val perplexity 2088.4390 +450 train 7.703149 (lr=1.9644e-04) (hash(x)=25863209) +451 train 7.404397 (lr=1.9643e-04) (hash(x)=21154388) +452 train 7.393228 (lr=1.9641e-04) (hash(x)=21600876) +453 train 7.509789 (lr=1.9639e-04) (hash(x)=24278611) +454 train 7.340119 (lr=1.9638e-04) (hash(x)=23221720) +455 train 7.592807 (lr=1.9636e-04) (hash(x)=22708977) +456 train 8.219383 (lr=1.9635e-04) (hash(x)=23637758) +457 train 7.905181 (lr=1.9633e-04) (hash(x)=28228490) +458 train 7.921716 (lr=1.9631e-04) (hash(x)=28638071) +459 train 7.745230 (lr=1.9630e-04) (hash(x)=27258353) +460 train 7.760964 (lr=1.9628e-04) (hash(x)=26604728) +461 train 7.660321 (lr=1.9627e-04) (hash(x)=23252199) +462 train 7.727689 (lr=1.9625e-04) (hash(x)=26441427) +463 train 7.477579 (lr=1.9623e-04) (hash(x)=24364920) +464 train 7.625496 (lr=1.9622e-04) (hash(x)=25623792) +465 train 7.521569 (lr=1.9620e-04) (hash(x)=23283905) +466 train 7.918860 (lr=1.9618e-04) (hash(x)=26025267) +467 train 7.699079 (lr=1.9617e-04) (hash(x)=27243972) +468 train 8.069392 (lr=1.9615e-04) (hash(x)=30449945) +469 train 7.810892 (lr=1.9614e-04) (hash(x)=28113043) +470 train 7.605489 (lr=1.9612e-04) (hash(x)=25182521) +471 train 7.637203 (lr=1.9610e-04) (hash(x)=24932925) +472 train 7.450251 (lr=1.9609e-04) (hash(x)=20353098) +473 train 7.255181 (lr=1.9607e-04) (hash(x)=19001259) +474 train 7.952809 (lr=1.9605e-04) (hash(x)=27585685) +475 train 7.570631 (lr=1.9604e-04) (hash(x)=26371091) +476 train 7.448705 (lr=1.9602e-04) (hash(x)=24891798) +477 train 7.512531 (lr=1.9600e-04) (hash(x)=24258817) +478 train 7.598625 (lr=1.9599e-04) (hash(x)=24330263) +479 train 7.640058 (lr=1.9597e-04) (hash(x)=26913684) +480 train 7.633996 (lr=1.9595e-04) (hash(x)=26338455) +481 train 7.956349 (lr=1.9594e-04) (hash(x)=27753043) +482 train 7.660849 (lr=1.9592e-04) (hash(x)=26123289) +483 train 7.741689 (lr=1.9590e-04) (hash(x)=29239611) +484 train 7.620810 (lr=1.9589e-04) (hash(x)=26553003) +485 train 7.606475 (lr=1.9587e-04) (hash(x)=22984557) +486 train 7.107419 (lr=1.9585e-04) (hash(x)=16947491) +487 train 7.156438 (lr=1.9583e-04) (hash(x)=18017792) +488 train 7.294026 (lr=1.9582e-04) (hash(x)=19918608) +489 train 7.781901 (lr=1.9580e-04) (hash(x)=23374526) +490 train 7.618740 (lr=1.9578e-04) (hash(x)=25009505) +491 train 7.599594 (lr=1.9577e-04) (hash(x)=27574089) +492 train 7.755374 (lr=1.9575e-04) (hash(x)=24122664) +493 train 7.628324 (lr=1.9573e-04) (hash(x)=26154906) +494 train 7.609853 (lr=1.9571e-04) (hash(x)=25192767) +495 train 7.756801 (lr=1.9570e-04) (hash(x)=28613882) +496 train 7.592916 (lr=1.9568e-04) (hash(x)=23547219) +497 train 7.625295 (lr=1.9566e-04) (hash(x)=25272182) +498 train 7.448129 (lr=1.9565e-04) (hash(x)=24992761) +499 train 7.714818 (lr=1.9563e-04) (hash(x)=26981914) +500 val loss 7.6253 +500 val perplexity 2049.4185 +500 train 7.577941 (lr=1.9561e-04) (hash(x)=22051933) +501 train 7.729242 (lr=1.9559e-04) (hash(x)=24232348) +502 train 7.760598 (lr=1.9558e-04) (hash(x)=23158331) +503 train 7.572074 (lr=1.9556e-04) (hash(x)=22652243) +504 train 7.599100 (lr=1.9554e-04) (hash(x)=23805602) +505 train 7.901721 (lr=1.9552e-04) (hash(x)=25411991) +506 train 7.078039 (lr=1.9551e-04) (hash(x)=18827215) +507 train 6.810681 (lr=1.9549e-04) (hash(x)=15446025) +508 train 7.254811 (lr=1.9547e-04) (hash(x)=20516263) +509 train 7.746569 (lr=1.9545e-04) (hash(x)=27846176) +510 train 7.498198 (lr=1.9543e-04) (hash(x)=23342449) +511 train 7.718301 (lr=1.9542e-04) (hash(x)=27194521) +512 train 7.512514 (lr=1.9540e-04) (hash(x)=23008284) +513 train 7.991457 (lr=1.9538e-04) (hash(x)=29430001) +514 train 7.318058 (lr=1.9536e-04) (hash(x)=22579319) +515 train 7.322517 (lr=1.9535e-04) (hash(x)=25264518) +516 train 7.652515 (lr=1.9533e-04) (hash(x)=25359075) +517 train 7.655258 (lr=1.9531e-04) (hash(x)=25568956) +518 train 7.903568 (lr=1.9529e-04) (hash(x)=32004108) +519 train 7.561253 (lr=1.9527e-04) (hash(x)=24936836) +520 train 7.739322 (lr=1.9526e-04) (hash(x)=27263338) +521 train 7.789815 (lr=1.9524e-04) (hash(x)=27452099) +522 train 7.692944 (lr=1.9522e-04) (hash(x)=25965406) +523 train 7.850702 (lr=1.9520e-04) (hash(x)=28197282) +524 train 7.638652 (lr=1.9518e-04) (hash(x)=22466209) +525 train 7.681159 (lr=1.9516e-04) (hash(x)=22931889) +526 train 7.798551 (lr=1.9515e-04) (hash(x)=26903920) +527 train 7.632439 (lr=1.9513e-04) (hash(x)=24765578) +528 train 7.735560 (lr=1.9511e-04) (hash(x)=27811359) +529 train 7.519763 (lr=1.9509e-04) (hash(x)=25078649) +530 train 7.665631 (lr=1.9507e-04) (hash(x)=25572416) +531 train 7.823332 (lr=1.9505e-04) (hash(x)=27448185) +532 train 7.872909 (lr=1.9504e-04) (hash(x)=25923719) +533 train 7.643764 (lr=1.9502e-04) (hash(x)=24804856) +534 train 7.707042 (lr=1.9500e-04) (hash(x)=23207829) +535 train 7.612613 (lr=1.9498e-04) (hash(x)=23107416) +536 train 7.465136 (lr=1.9496e-04) (hash(x)=26739531) +537 train 7.490192 (lr=1.9494e-04) (hash(x)=24960796) +538 train 7.617149 (lr=1.9492e-04) (hash(x)=24667802) +539 train 7.715718 (lr=1.9490e-04) (hash(x)=26755138) +540 train 7.642261 (lr=1.9489e-04) (hash(x)=25537132) +541 train 7.554319 (lr=1.9487e-04) (hash(x)=24542526) +542 train 7.339870 (lr=1.9485e-04) (hash(x)=21296355) +543 train 7.843549 (lr=1.9483e-04) (hash(x)=29314255) +544 train 7.623137 (lr=1.9481e-04) (hash(x)=26001799) +545 train 7.670967 (lr=1.9479e-04) (hash(x)=27347755) +546 train 7.629630 (lr=1.9477e-04) (hash(x)=25107798) +547 train 7.446090 (lr=1.9475e-04) (hash(x)=22112669) +548 train 7.475134 (lr=1.9473e-04) (hash(x)=21897967) +549 train 7.579767 (lr=1.9472e-04) (hash(x)=25161929) +550 val loss 7.5949 +550 val perplexity 1987.9944 +550 train 7.495749 (lr=1.9470e-04) (hash(x)=27465106) +551 train 7.602890 (lr=1.9468e-04) (hash(x)=24013079) +552 train 7.454889 (lr=1.9466e-04) (hash(x)=23142015) +553 train 7.576215 (lr=1.9464e-04) (hash(x)=26768629) +554 train 7.610061 (lr=1.9462e-04) (hash(x)=26393383) +555 train 7.475636 (lr=1.9460e-04) (hash(x)=22537194) +556 train 7.751487 (lr=1.9458e-04) (hash(x)=24046036) +557 train 7.694603 (lr=1.9456e-04) (hash(x)=24974360) +558 train 7.889000 (lr=1.9454e-04) (hash(x)=28379928) +559 train 7.634614 (lr=1.9452e-04) (hash(x)=25322001) +560 train 7.743020 (lr=1.9450e-04) (hash(x)=26622031) +561 train 7.398677 (lr=1.9448e-04) (hash(x)=20562247) +562 train 7.753723 (lr=1.9446e-04) (hash(x)=27381885) +563 train 7.905502 (lr=1.9444e-04) (hash(x)=27028126) +564 train 7.752962 (lr=1.9443e-04) (hash(x)=28882928) +565 train 7.661266 (lr=1.9441e-04) (hash(x)=25666355) +566 train 7.764888 (lr=1.9439e-04) (hash(x)=24330810) +567 train 7.686339 (lr=1.9437e-04) (hash(x)=26690440) +568 train 7.570658 (lr=1.9435e-04) (hash(x)=22923592) +569 train 7.682393 (lr=1.9433e-04) (hash(x)=27348418) +570 train 7.683315 (lr=1.9431e-04) (hash(x)=28849848) +571 train 7.752333 (lr=1.9429e-04) (hash(x)=26967331) +572 train 7.518600 (lr=1.9427e-04) (hash(x)=22831467) +573 train 7.583878 (lr=1.9425e-04) (hash(x)=24765121) +574 train 7.570598 (lr=1.9423e-04) (hash(x)=24331857) +575 train 7.408922 (lr=1.9421e-04) (hash(x)=22598512) +576 train 7.553712 (lr=1.9419e-04) (hash(x)=25149353) +577 train 7.454937 (lr=1.9417e-04) (hash(x)=23725598) +578 train 7.725097 (lr=1.9415e-04) (hash(x)=26449557) +579 train 7.751052 (lr=1.9413e-04) (hash(x)=24697985) +580 train 7.702730 (lr=1.9411e-04) (hash(x)=26923059) +581 train 7.545484 (lr=1.9409e-04) (hash(x)=25201962) +582 train 7.184509 (lr=1.9407e-04) (hash(x)=20931520) +583 train 7.273117 (lr=1.9405e-04) (hash(x)=18473911) +584 train 7.416673 (lr=1.9403e-04) (hash(x)=21306267) +585 train 7.681380 (lr=1.9401e-04) (hash(x)=25982840) +586 train 7.583234 (lr=1.9399e-04) (hash(x)=25364874) +587 train 7.469063 (lr=1.9397e-04) (hash(x)=23172124) +588 train 7.776967 (lr=1.9395e-04) (hash(x)=27876897) +589 train 8.366553 (lr=1.9392e-04) (hash(x)=34646114) +590 train 8.635230 (lr=1.9390e-04) (hash(x)=35153576) +591 train 7.599731 (lr=1.9388e-04) (hash(x)=22322442) +592 train 7.829455 (lr=1.9386e-04) (hash(x)=27907331) +593 train 7.724464 (lr=1.9384e-04) (hash(x)=26211794) +594 train 7.880051 (lr=1.9382e-04) (hash(x)=29291512) +595 train 8.108188 (lr=1.9380e-04) (hash(x)=29659121) +596 train 7.999228 (lr=1.9378e-04) (hash(x)=29674399) +597 train 7.629614 (lr=1.9376e-04) (hash(x)=23538306) +598 train 7.716559 (lr=1.9374e-04) (hash(x)=21991524) +599 train 7.630410 (lr=1.9372e-04) (hash(x)=26324153) +600 val loss 7.6331 +600 val perplexity 2065.4873 +600 train 7.624641 (lr=1.9370e-04) (hash(x)=23712082) +601 train 7.721190 (lr=1.9368e-04) (hash(x)=24910403) +602 train 7.631606 (lr=1.9366e-04) (hash(x)=26737205) +603 train 7.749408 (lr=1.9364e-04) (hash(x)=26939970) +604 train 7.628553 (lr=1.9361e-04) (hash(x)=27651943) +605 train 7.954942 (lr=1.9359e-04) (hash(x)=27515446) +606 train 7.826512 (lr=1.9357e-04) (hash(x)=26753129) +607 train 7.533415 (lr=1.9355e-04) (hash(x)=23446058) +608 train 7.831813 (lr=1.9353e-04) (hash(x)=27587849) +609 train 7.731412 (lr=1.9351e-04) (hash(x)=25308253) +610 train 7.723964 (lr=1.9349e-04) (hash(x)=26615098) +611 train 7.761972 (lr=1.9347e-04) (hash(x)=29981801) +612 train 7.841925 (lr=1.9345e-04) (hash(x)=29592345) +613 train 7.836712 (lr=1.9343e-04) (hash(x)=23470413) +614 train 7.741451 (lr=1.9340e-04) (hash(x)=24742370) +615 train 7.718843 (lr=1.9338e-04) (hash(x)=24843741) +616 train 7.624388 (lr=1.9336e-04) (hash(x)=25192548) +617 train 7.684887 (lr=1.9334e-04) (hash(x)=27176996) +618 train 7.546904 (lr=1.9332e-04) (hash(x)=23964552) +619 train 7.525666 (lr=1.9330e-04) (hash(x)=22855363) +620 train 7.523996 (lr=1.9328e-04) (hash(x)=26332996) +621 train 7.345310 (lr=1.9325e-04) (hash(x)=22960957) +622 train 7.625247 (lr=1.9323e-04) (hash(x)=22752597) +623 train 7.529828 (lr=1.9321e-04) (hash(x)=23197102) +624 train 8.037064 (lr=1.9319e-04) (hash(x)=27383319) +625 train 7.632664 (lr=1.9317e-04) (hash(x)=26132276) +626 train 7.550399 (lr=1.9315e-04) (hash(x)=19810497) +627 train 7.594400 (lr=1.9312e-04) (hash(x)=25704919) +628 train 7.759424 (lr=1.9310e-04) (hash(x)=27174264) +629 train 7.857778 (lr=1.9308e-04) (hash(x)=22280814) +630 train 8.523013 (lr=1.9306e-04) (hash(x)=24279448) +631 train 8.024995 (lr=1.9304e-04) (hash(x)=23054940) +632 train 8.136218 (lr=1.9302e-04) (hash(x)=23942400) +633 train 8.342194 (lr=1.9299e-04) (hash(x)=24712416) +634 train 7.977928 (lr=1.9297e-04) (hash(x)=24564658) +635 train 7.725038 (lr=1.9295e-04) (hash(x)=24909904) +636 train 7.736335 (lr=1.9293e-04) (hash(x)=23049534) +637 train 7.787306 (lr=1.9291e-04) (hash(x)=24321591) +638 train 7.551557 (lr=1.9288e-04) (hash(x)=26153298) +639 train 7.581841 (lr=1.9286e-04) (hash(x)=27140757) +640 train 7.344629 (lr=1.9284e-04) (hash(x)=25115907) +641 train 7.384073 (lr=1.9282e-04) (hash(x)=26563770) +642 train 7.609605 (lr=1.9280e-04) (hash(x)=28089252) +643 train 7.506900 (lr=1.9277e-04) (hash(x)=25993110) +644 train 7.484668 (lr=1.9275e-04) (hash(x)=25150008) +645 train 7.735718 (lr=1.9273e-04) (hash(x)=28520222) +646 train 7.383705 (lr=1.9271e-04) (hash(x)=21349943) +647 train 7.475362 (lr=1.9268e-04) (hash(x)=25149419) +648 train 7.689133 (lr=1.9266e-04) (hash(x)=25730641) +649 train 7.806447 (lr=1.9264e-04) (hash(x)=26112813) +650 val loss 7.5854 +650 val perplexity 1969.2560 +650 train 7.621953 (lr=1.9262e-04) (hash(x)=25907805) +651 train 7.666776 (lr=1.9259e-04) (hash(x)=27623643) +652 train 7.612927 (lr=1.9257e-04) (hash(x)=26484959) +653 train 7.669882 (lr=1.9255e-04) (hash(x)=29199854) +654 train 7.670561 (lr=1.9253e-04) (hash(x)=28369628) +655 train 7.509019 (lr=1.9250e-04) (hash(x)=24727764) +656 train 7.303108 (lr=1.9248e-04) (hash(x)=22610673) +657 train 7.245244 (lr=1.9246e-04) (hash(x)=22667179) +658 train 7.040958 (lr=1.9244e-04) (hash(x)=18477300) +659 train 7.443982 (lr=1.9241e-04) (hash(x)=23155773) +660 train 7.217862 (lr=1.9239e-04) (hash(x)=19461032) +661 train 7.501010 (lr=1.9237e-04) (hash(x)=23453788) +662 train 7.623306 (lr=1.9235e-04) (hash(x)=24543466) +663 train 7.409601 (lr=1.9232e-04) (hash(x)=21935931) +664 train 7.279697 (lr=1.9230e-04) (hash(x)=19910292) +665 train 7.556608 (lr=1.9228e-04) (hash(x)=24481079) +666 train 7.294113 (lr=1.9225e-04) (hash(x)=18922411) +667 train 7.309866 (lr=1.9223e-04) (hash(x)=20054917) +668 train 7.538738 (lr=1.9221e-04) (hash(x)=24850470) +669 train 7.537271 (lr=1.9219e-04) (hash(x)=25907741) +670 train 7.655618 (lr=1.9216e-04) (hash(x)=26873522) +671 train 7.689215 (lr=1.9214e-04) (hash(x)=27606073) +672 train 7.798611 (lr=1.9212e-04) (hash(x)=26209645) +673 train 7.629193 (lr=1.9209e-04) (hash(x)=25202001) +674 train 7.676885 (lr=1.9207e-04) (hash(x)=25569462) +675 train 7.673842 (lr=1.9205e-04) (hash(x)=26534487) +676 train 7.621496 (lr=1.9202e-04) (hash(x)=26455057) +677 train 7.525959 (lr=1.9200e-04) (hash(x)=24095850) +678 train 7.752656 (lr=1.9198e-04) (hash(x)=25287752) +679 train 7.263608 (lr=1.9195e-04) (hash(x)=22450341) +680 train 7.963615 (lr=1.9193e-04) (hash(x)=29004853) +681 train 7.665812 (lr=1.9191e-04) (hash(x)=27993763) +682 train 7.507243 (lr=1.9188e-04) (hash(x)=26382658) +683 train 7.652953 (lr=1.9186e-04) (hash(x)=25013073) +684 train 7.687328 (lr=1.9184e-04) (hash(x)=30595809) +685 train 7.748322 (lr=1.9181e-04) (hash(x)=30934371) +686 train 8.352550 (lr=1.9179e-04) (hash(x)=33060834) +687 train 7.627830 (lr=1.9177e-04) (hash(x)=25945859) +688 train 7.475389 (lr=1.9174e-04) (hash(x)=23375678) +689 train 7.515725 (lr=1.9172e-04) (hash(x)=25218689) +690 train 7.616770 (lr=1.9169e-04) (hash(x)=28127397) +691 train 7.537526 (lr=1.9167e-04) (hash(x)=24418091) +692 train 7.490119 (lr=1.9165e-04) (hash(x)=22761099) +693 train 7.489070 (lr=1.9162e-04) (hash(x)=24615466) +694 train 7.599761 (lr=1.9160e-04) (hash(x)=24699240) +695 train 7.492803 (lr=1.9158e-04) (hash(x)=21613707) +696 train 7.525112 (lr=1.9155e-04) (hash(x)=24977554) +697 train 7.489271 (lr=1.9153e-04) (hash(x)=24348175) +698 train 7.712944 (lr=1.9150e-04) (hash(x)=25102767) +699 train 7.667881 (lr=1.9148e-04) (hash(x)=26386157) +700 val loss 7.5431 +700 val perplexity 1887.7661 +700 train 7.585376 (lr=1.9146e-04) (hash(x)=26423460) +701 train 7.507616 (lr=1.9143e-04) (hash(x)=25771047) +702 train 7.568486 (lr=1.9141e-04) (hash(x)=26999875) +703 train 7.496883 (lr=1.9138e-04) (hash(x)=24396519) +704 train 7.517514 (lr=1.9136e-04) (hash(x)=22588122) +705 train 7.820305 (lr=1.9133e-04) (hash(x)=25142399) +706 train 7.558529 (lr=1.9131e-04) (hash(x)=20440214) +707 train 7.434194 (lr=1.9129e-04) (hash(x)=23265507) +708 train 7.520380 (lr=1.9126e-04) (hash(x)=24563470) +709 train 7.414839 (lr=1.9124e-04) (hash(x)=22514858) +710 train 7.748240 (lr=1.9121e-04) (hash(x)=26691212) +711 train 7.818761 (lr=1.9119e-04) (hash(x)=29138828) +712 train 7.803549 (lr=1.9116e-04) (hash(x)=28028528) +713 train 7.686094 (lr=1.9114e-04) (hash(x)=20531210) +714 train 7.491241 (lr=1.9112e-04) (hash(x)=25075352) +715 train 7.567659 (lr=1.9109e-04) (hash(x)=24265353) +716 train 7.656331 (lr=1.9107e-04) (hash(x)=24635726) +717 train 7.503920 (lr=1.9104e-04) (hash(x)=24999726) +718 train 7.707677 (lr=1.9102e-04) (hash(x)=27412910) +719 train 7.496233 (lr=1.9099e-04) (hash(x)=24685515) +720 train 7.570995 (lr=1.9097e-04) (hash(x)=23780329) +721 train 7.377382 (lr=1.9094e-04) (hash(x)=25071701) +722 train 7.511989 (lr=1.9092e-04) (hash(x)=23767130) +723 train 7.486267 (lr=1.9089e-04) (hash(x)=24876269) +724 train 7.607656 (lr=1.9087e-04) (hash(x)=26405773) +725 train 8.021695 (lr=1.9084e-04) (hash(x)=31733180) +726 train 7.210886 (lr=1.9082e-04) (hash(x)=21337509) +727 train 7.293944 (lr=1.9079e-04) (hash(x)=22825749) +728 train 7.721610 (lr=1.9077e-04) (hash(x)=28638695) +729 train 7.567253 (lr=1.9074e-04) (hash(x)=26393943) +730 train 7.736843 (lr=1.9072e-04) (hash(x)=27563583) +731 train 7.245988 (lr=1.9069e-04) (hash(x)=21239652) +732 train 7.369316 (lr=1.9067e-04) (hash(x)=23986428) +733 train 7.403347 (lr=1.9064e-04) (hash(x)=24943881) +734 train 7.900892 (lr=1.9062e-04) (hash(x)=29691448) +735 train 7.816803 (lr=1.9059e-04) (hash(x)=28767869) +736 train 7.518747 (lr=1.9057e-04) (hash(x)=23628188) +737 train 7.795070 (lr=1.9054e-04) (hash(x)=29341482) +738 train 7.632913 (lr=1.9052e-04) (hash(x)=30336570) +739 train 7.594577 (lr=1.9049e-04) (hash(x)=25614301) +740 train 7.455953 (lr=1.9047e-04) (hash(x)=24160500) +741 train 7.687822 (lr=1.9044e-04) (hash(x)=26030058) +742 train 8.032826 (lr=1.9042e-04) (hash(x)=29243936) +743 train 7.301311 (lr=1.9039e-04) (hash(x)=21159060) +744 train 7.422341 (lr=1.9037e-04) (hash(x)=23701853) +745 train 7.633247 (lr=1.9034e-04) (hash(x)=24629937) +746 train 7.566473 (lr=1.9031e-04) (hash(x)=25110108) +747 train 7.605831 (lr=1.9029e-04) (hash(x)=26751788) +748 train 7.629521 (lr=1.9026e-04) (hash(x)=26430427) +749 train 7.501653 (lr=1.9024e-04) (hash(x)=26012353) +750 val loss 7.5449 +750 val perplexity 1891.1132 +750 train 7.656543 (lr=1.9021e-04) (hash(x)=22735910) +751 train 7.467627 (lr=1.9019e-04) (hash(x)=25045397) +752 train 7.157014 (lr=1.9016e-04) (hash(x)=21554427) +753 train 7.299072 (lr=1.9014e-04) (hash(x)=23751143) +754 train 8.062296 (lr=1.9011e-04) (hash(x)=28602273) +755 train 8.082914 (lr=1.9008e-04) (hash(x)=29989709) +756 train 7.482961 (lr=1.9006e-04) (hash(x)=22331648) +757 train 7.942587 (lr=1.9003e-04) (hash(x)=31017246) +758 train 7.856950 (lr=1.9001e-04) (hash(x)=29709045) +759 train 7.880826 (lr=1.8998e-04) (hash(x)=25560928) +760 train 7.598560 (lr=1.8995e-04) (hash(x)=25075464) +761 train 7.680012 (lr=1.8993e-04) (hash(x)=27352253) +762 train 7.880782 (lr=1.8990e-04) (hash(x)=28187891) +763 train 7.750357 (lr=1.8988e-04) (hash(x)=26062687) +764 train 7.770188 (lr=1.8985e-04) (hash(x)=27427811) +765 train 7.818424 (lr=1.8982e-04) (hash(x)=27614522) +766 train 7.577754 (lr=1.8980e-04) (hash(x)=26129544) +767 train 8.103576 (lr=1.8977e-04) (hash(x)=28959222) +768 train 7.672199 (lr=1.8975e-04) (hash(x)=26860067) +769 train 7.435475 (lr=1.8972e-04) (hash(x)=25122598) +770 train 7.516602 (lr=1.8969e-04) (hash(x)=25245030) +771 train 7.532543 (lr=1.8967e-04) (hash(x)=25434884) +772 train 7.600574 (lr=1.8964e-04) (hash(x)=27732790) +773 train 7.604436 (lr=1.8961e-04) (hash(x)=27824438) +774 train 7.724609 (lr=1.8959e-04) (hash(x)=27201953) +775 train 7.471506 (lr=1.8956e-04) (hash(x)=21248405) +776 train 7.276261 (lr=1.8953e-04) (hash(x)=22805934) +777 train 7.578818 (lr=1.8951e-04) (hash(x)=26482588) +778 train 7.638446 (lr=1.8948e-04) (hash(x)=24153691) +779 train 7.738917 (lr=1.8946e-04) (hash(x)=25044192) +780 train 7.700694 (lr=1.8943e-04) (hash(x)=25910078) +781 train 7.678293 (lr=1.8940e-04) (hash(x)=28645524) +782 train 7.486431 (lr=1.8938e-04) (hash(x)=24368498) +783 train 7.589303 (lr=1.8935e-04) (hash(x)=25830182) +784 train 7.666599 (lr=1.8932e-04) (hash(x)=29181807) +785 train 7.615364 (lr=1.8930e-04) (hash(x)=25585137) +786 train 7.531271 (lr=1.8927e-04) (hash(x)=24798246) +787 train 7.637050 (lr=1.8924e-04) (hash(x)=26621419) +788 train 7.181035 (lr=1.8921e-04) (hash(x)=21446891) +789 train 7.137176 (lr=1.8919e-04) (hash(x)=22165286) +790 train 7.367311 (lr=1.8916e-04) (hash(x)=23477219) +791 train 7.655820 (lr=1.8913e-04) (hash(x)=25173113) +792 train 7.558277 (lr=1.8911e-04) (hash(x)=25853788) +793 train 7.645557 (lr=1.8908e-04) (hash(x)=27267091) +794 train 7.488943 (lr=1.8905e-04) (hash(x)=23743694) +795 train 7.443974 (lr=1.8903e-04) (hash(x)=24400133) +796 train 7.552766 (lr=1.8900e-04) (hash(x)=23663639) +797 train 7.401793 (lr=1.8897e-04) (hash(x)=23103223) +798 train 7.920854 (lr=1.8894e-04) (hash(x)=28748411) +799 train 7.176970 (lr=1.8892e-04) (hash(x)=23486277) +800 val loss 7.5395 +800 val perplexity 1880.8440 +800 train 7.535150 (lr=1.8889e-04) (hash(x)=25678518) +801 train 7.497371 (lr=1.8886e-04) (hash(x)=23421286) +802 train 7.576753 (lr=1.8884e-04) (hash(x)=26054104) +803 train 7.576230 (lr=1.8881e-04) (hash(x)=25978130) +804 train 7.597446 (lr=1.8878e-04) (hash(x)=26006525) +805 train 7.576250 (lr=1.8875e-04) (hash(x)=25769432) +806 train 7.384600 (lr=1.8873e-04) (hash(x)=22430795) +807 train 7.758740 (lr=1.8870e-04) (hash(x)=28916006) +808 train 7.552162 (lr=1.8867e-04) (hash(x)=25166800) +809 train 7.681138 (lr=1.8864e-04) (hash(x)=24226056) +810 train 7.496132 (lr=1.8862e-04) (hash(x)=25057934) +811 train 8.320796 (lr=1.8859e-04) (hash(x)=33195100) +812 train 7.672934 (lr=1.8856e-04) (hash(x)=26312888) +813 train 7.869380 (lr=1.8853e-04) (hash(x)=27730410) +814 train 7.695189 (lr=1.8851e-04) (hash(x)=27372474) +815 train 7.520135 (lr=1.8848e-04) (hash(x)=25556929) +816 train 7.654149 (lr=1.8845e-04) (hash(x)=26909985) +817 train 7.473993 (lr=1.8842e-04) (hash(x)=25991247) +818 train 7.668622 (lr=1.8840e-04) (hash(x)=27438141) +819 train 7.794049 (lr=1.8837e-04) (hash(x)=29536986) +820 train 7.556516 (lr=1.8834e-04) (hash(x)=24478391) +821 train 7.532324 (lr=1.8831e-04) (hash(x)=26125216) +822 train 7.520984 (lr=1.8828e-04) (hash(x)=26422130) +823 train 7.799072 (lr=1.8826e-04) (hash(x)=29648798) +824 train 7.410736 (lr=1.8823e-04) (hash(x)=21247770) +825 train 7.553314 (lr=1.8820e-04) (hash(x)=23195388) +826 train 7.523274 (lr=1.8817e-04) (hash(x)=25796725) +827 train 7.570422 (lr=1.8814e-04) (hash(x)=23124767) +828 train 7.603062 (lr=1.8812e-04) (hash(x)=25233464) +829 train 7.591307 (lr=1.8809e-04) (hash(x)=25713275) +830 train 7.542479 (lr=1.8806e-04) (hash(x)=25550167) +831 train 7.423940 (lr=1.8803e-04) (hash(x)=24976217) +832 train 7.720571 (lr=1.8800e-04) (hash(x)=28536827) +833 train 7.634487 (lr=1.8798e-04) (hash(x)=27500801) +834 train 7.468436 (lr=1.8795e-04) (hash(x)=25545765) +835 train 7.467725 (lr=1.8792e-04) (hash(x)=23632825) +836 train 7.495294 (lr=1.8789e-04) (hash(x)=25708009) +837 train 7.528351 (lr=1.8786e-04) (hash(x)=24456276) +838 train 7.704273 (lr=1.8783e-04) (hash(x)=29189855) +839 train 7.951376 (lr=1.8781e-04) (hash(x)=31019606) +840 train 7.804888 (lr=1.8778e-04) (hash(x)=26328013) +841 train 7.718584 (lr=1.8775e-04) (hash(x)=25027904) +842 train 7.467554 (lr=1.8772e-04) (hash(x)=23734189) +843 train 7.719471 (lr=1.8769e-04) (hash(x)=28236580) +844 train 7.529120 (lr=1.8766e-04) (hash(x)=26509780) +845 train 7.604041 (lr=1.8763e-04) (hash(x)=25386473) +846 train 7.544554 (lr=1.8761e-04) (hash(x)=24052671) +847 train 7.740640 (lr=1.8758e-04) (hash(x)=28269421) +848 train 7.232244 (lr=1.8755e-04) (hash(x)=22251724) +849 train 7.411638 (lr=1.8752e-04) (hash(x)=24308447) +850 val loss 7.5252 +850 val perplexity 1854.1874 +850 train 7.366802 (lr=1.8749e-04) (hash(x)=24242830) +851 train 7.583405 (lr=1.8746e-04) (hash(x)=25563279) +852 train 7.591216 (lr=1.8743e-04) (hash(x)=26354481) +853 train 7.758051 (lr=1.8740e-04) (hash(x)=26152637) +854 train 7.784485 (lr=1.8738e-04) (hash(x)=28051025) +855 train 7.588390 (lr=1.8735e-04) (hash(x)=24865358) +856 train 7.482543 (lr=1.8732e-04) (hash(x)=24288911) +857 train 7.359396 (lr=1.8729e-04) (hash(x)=22230964) +858 train 7.283880 (lr=1.8726e-04) (hash(x)=21303832) +859 train 7.409852 (lr=1.8723e-04) (hash(x)=22155546) +860 train 7.522541 (lr=1.8720e-04) (hash(x)=25296428) +861 train 7.706449 (lr=1.8717e-04) (hash(x)=29142319) +862 train 7.530541 (lr=1.8714e-04) (hash(x)=25545430) +863 train 7.355808 (lr=1.8711e-04) (hash(x)=26984272) +864 train 7.542317 (lr=1.8708e-04) (hash(x)=25429005) +865 train 7.567186 (lr=1.8706e-04) (hash(x)=27077032) +866 train 7.590890 (lr=1.8703e-04) (hash(x)=26494424) +867 train 7.569725 (lr=1.8700e-04) (hash(x)=23193673) +868 train 7.592155 (lr=1.8697e-04) (hash(x)=25075134) +869 train 7.619718 (lr=1.8694e-04) (hash(x)=27112558) +870 train 7.748166 (lr=1.8691e-04) (hash(x)=27436608) +871 train 7.466914 (lr=1.8688e-04) (hash(x)=24544116) +872 train 7.817700 (lr=1.8685e-04) (hash(x)=31632686) +873 train 7.533554 (lr=1.8682e-04) (hash(x)=25890184) +874 train 7.648286 (lr=1.8679e-04) (hash(x)=22887555) +875 train 7.462884 (lr=1.8676e-04) (hash(x)=24547533) +876 train 7.630909 (lr=1.8673e-04) (hash(x)=26553496) +877 train 7.708074 (lr=1.8670e-04) (hash(x)=27467688) +878 train 7.472884 (lr=1.8667e-04) (hash(x)=24766934) +879 train 7.331149 (lr=1.8664e-04) (hash(x)=22059850) +880 train 7.721840 (lr=1.8661e-04) (hash(x)=22871702) +881 train 7.526302 (lr=1.8658e-04) (hash(x)=23893130) +882 train 7.596469 (lr=1.8655e-04) (hash(x)=25125691) +883 train 7.535504 (lr=1.8652e-04) (hash(x)=25994573) +884 train 7.581831 (lr=1.8650e-04) (hash(x)=26076345) +885 train 7.504912 (lr=1.8647e-04) (hash(x)=26577783) +886 train 7.638969 (lr=1.8644e-04) (hash(x)=27395225) +887 train 7.455678 (lr=1.8641e-04) (hash(x)=23926632) +888 train 7.293045 (lr=1.8638e-04) (hash(x)=21737239) +889 train 7.584934 (lr=1.8635e-04) (hash(x)=23574207) +890 train 7.284618 (lr=1.8632e-04) (hash(x)=24365231) +891 train 7.452211 (lr=1.8629e-04) (hash(x)=27111369) +892 train 7.724492 (lr=1.8626e-04) (hash(x)=27290015) +893 train 7.502913 (lr=1.8623e-04) (hash(x)=23979820) +894 train 7.597821 (lr=1.8620e-04) (hash(x)=26450121) +895 train 7.485863 (lr=1.8617e-04) (hash(x)=27025333) +896 train 7.479669 (lr=1.8614e-04) (hash(x)=23624605) +897 train 7.292817 (lr=1.8611e-04) (hash(x)=22846386) +898 train 7.378346 (lr=1.8607e-04) (hash(x)=22970561) +899 train 7.226773 (lr=1.8604e-04) (hash(x)=16908068) +900 val loss 7.4843 +900 val perplexity 1779.8381 +900 train 7.446625 (lr=1.8601e-04) (hash(x)=24661446) +901 train 7.567777 (lr=1.8598e-04) (hash(x)=25664727) +902 train 7.524841 (lr=1.8595e-04) (hash(x)=25667011) +903 train 7.617426 (lr=1.8592e-04) (hash(x)=29120407) +904 train 7.636790 (lr=1.8589e-04) (hash(x)=23385735) +905 train 7.675539 (lr=1.8586e-04) (hash(x)=25564213) +906 train 7.753693 (lr=1.8583e-04) (hash(x)=25413898) +907 train 7.698610 (lr=1.8580e-04) (hash(x)=27092710) +908 train 7.483224 (lr=1.8577e-04) (hash(x)=25789923) +909 train 7.589893 (lr=1.8574e-04) (hash(x)=28533197) +910 train 7.389104 (lr=1.8571e-04) (hash(x)=22982996) +911 train 7.464044 (lr=1.8568e-04) (hash(x)=23827393) +912 train 7.135906 (lr=1.8565e-04) (hash(x)=21242640) +913 train 7.504979 (lr=1.8562e-04) (hash(x)=24154233) +914 train 7.526035 (lr=1.8559e-04) (hash(x)=24331967) +915 train 7.784093 (lr=1.8556e-04) (hash(x)=32812727) +916 train 7.424121 (lr=1.8553e-04) (hash(x)=23572994) +917 train 7.416400 (lr=1.8550e-04) (hash(x)=26305435) +918 train 7.508594 (lr=1.8546e-04) (hash(x)=26268355) +919 train 7.686709 (lr=1.8543e-04) (hash(x)=27230027) +920 train 7.469996 (lr=1.8540e-04) (hash(x)=23885377) +921 train 7.402808 (lr=1.8537e-04) (hash(x)=23532437) +922 train 7.494147 (lr=1.8534e-04) (hash(x)=25577034) +923 train 7.658893 (lr=1.8531e-04) (hash(x)=25703381) +924 train 7.672624 (lr=1.8528e-04) (hash(x)=27113866) +925 train 7.510452 (lr=1.8525e-04) (hash(x)=26961429) +926 train 7.368797 (lr=1.8522e-04) (hash(x)=21355372) +927 train 7.482704 (lr=1.8519e-04) (hash(x)=24968260) +928 train 7.470380 (lr=1.8515e-04) (hash(x)=25357517) +929 train 7.616046 (lr=1.8512e-04) (hash(x)=24854265) +930 train 7.401031 (lr=1.8509e-04) (hash(x)=21102770) +931 train 7.674588 (lr=1.8506e-04) (hash(x)=25676468) +932 train 7.549570 (lr=1.8503e-04) (hash(x)=22809869) +933 train 7.610652 (lr=1.8500e-04) (hash(x)=25503865) +934 train 7.509114 (lr=1.8497e-04) (hash(x)=24853995) +935 train 7.749284 (lr=1.8494e-04) (hash(x)=27544803) +936 train 7.689457 (lr=1.8490e-04) (hash(x)=25981933) +937 train 7.513303 (lr=1.8487e-04) (hash(x)=24658683) +938 train 7.649535 (lr=1.8484e-04) (hash(x)=23855201) +939 train 7.576869 (lr=1.8481e-04) (hash(x)=24331407) +940 train 7.771158 (lr=1.8478e-04) (hash(x)=29265551) +941 train 7.471474 (lr=1.8475e-04) (hash(x)=21892556) +942 train 7.519928 (lr=1.8472e-04) (hash(x)=27183405) +943 train 7.498152 (lr=1.8468e-04) (hash(x)=26540663) +944 train 7.447149 (lr=1.8465e-04) (hash(x)=25718393) +945 train 7.599303 (lr=1.8462e-04) (hash(x)=26819462) +946 train 7.607306 (lr=1.8459e-04) (hash(x)=27427540) +947 train 7.550046 (lr=1.8456e-04) (hash(x)=25532657) +948 train 7.789712 (lr=1.8453e-04) (hash(x)=27641372) +949 train 7.516582 (lr=1.8449e-04) (hash(x)=26515570) +950 val loss 7.5468 +950 val perplexity 1894.6224 +950 train 7.755608 (lr=1.8446e-04) (hash(x)=26911957) +951 train 7.922750 (lr=1.8443e-04) (hash(x)=25856625) +952 train 7.390218 (lr=1.8440e-04) (hash(x)=25219129) +953 train 7.350244 (lr=1.8437e-04) (hash(x)=25260471) +954 train 7.772118 (lr=1.8434e-04) (hash(x)=29373370) +955 train 7.295959 (lr=1.8430e-04) (hash(x)=23437426) +956 train 7.624169 (lr=1.8427e-04) (hash(x)=23769521) +957 train 7.661403 (lr=1.8424e-04) (hash(x)=25961833) +958 train 7.345471 (lr=1.8421e-04) (hash(x)=23582666) +959 train 7.442237 (lr=1.8418e-04) (hash(x)=23164356) +960 train 7.402407 (lr=1.8414e-04) (hash(x)=24443114) +961 train 7.483787 (lr=1.8411e-04) (hash(x)=25052665) +962 train 7.628709 (lr=1.8408e-04) (hash(x)=27802272) +963 train 7.444197 (lr=1.8405e-04) (hash(x)=25957896) +964 train 7.511619 (lr=1.8402e-04) (hash(x)=26737251) +965 train 7.670702 (lr=1.8398e-04) (hash(x)=24723263) +966 train 7.561044 (lr=1.8395e-04) (hash(x)=24707011) +967 train 7.560422 (lr=1.8392e-04) (hash(x)=25646282) +968 train 7.595925 (lr=1.8389e-04) (hash(x)=27544665) +969 train 7.474121 (lr=1.8385e-04) (hash(x)=25851993) +970 train 7.773519 (lr=1.8382e-04) (hash(x)=29059700) +971 train 7.509840 (lr=1.8379e-04) (hash(x)=21513584) +972 train 7.231571 (lr=1.8376e-04) (hash(x)=23151267) +973 train 7.523444 (lr=1.8372e-04) (hash(x)=26017176) +974 train 7.571571 (lr=1.8369e-04) (hash(x)=26979518) +975 train 7.556788 (lr=1.8366e-04) (hash(x)=23843233) +976 train 7.743552 (lr=1.8363e-04) (hash(x)=24193010) +977 train 7.450974 (lr=1.8359e-04) (hash(x)=21476847) +978 train 7.335432 (lr=1.8356e-04) (hash(x)=21366504) +979 train 7.373358 (lr=1.8353e-04) (hash(x)=23226697) +980 train 7.130269 (lr=1.8350e-04) (hash(x)=19961773) +981 train 7.015712 (lr=1.8346e-04) (hash(x)=19772969) +982 train 7.330718 (lr=1.8343e-04) (hash(x)=23110142) +983 train 7.582716 (lr=1.8340e-04) (hash(x)=24506028) +984 train 7.635768 (lr=1.8337e-04) (hash(x)=25480731) +985 train 7.474681 (lr=1.8333e-04) (hash(x)=21077417) +986 train 7.427766 (lr=1.8330e-04) (hash(x)=23686713) +987 train 7.472702 (lr=1.8327e-04) (hash(x)=26024321) +988 train 7.560155 (lr=1.8323e-04) (hash(x)=27424109) +989 train 7.729559 (lr=1.8320e-04) (hash(x)=27786174) +990 train 7.482930 (lr=1.8317e-04) (hash(x)=25232502) +991 train 7.495161 (lr=1.8314e-04) (hash(x)=22781277) +992 train 7.558895 (lr=1.8310e-04) (hash(x)=26184527) +993 train 7.554023 (lr=1.8307e-04) (hash(x)=24459895) +994 train 7.524082 (lr=1.8304e-04) (hash(x)=25244624) +995 train 7.655572 (lr=1.8300e-04) (hash(x)=24451843) +996 train 7.634778 (lr=1.8297e-04) (hash(x)=22129897) +997 train 7.418988 (lr=1.8294e-04) (hash(x)=21116390) +998 train 7.249752 (lr=1.8290e-04) (hash(x)=20650070) +999 train 7.624819 (lr=1.8287e-04) (hash(x)=24948650) +1000 val loss 7.4783 +1000 val perplexity 1769.1986 +1000 train 7.488975 (lr=1.8284e-04) (hash(x)=25444553) +1001 train 7.455392 (lr=1.8280e-04) (hash(x)=25617781) +1002 train 7.337297 (lr=1.8277e-04) (hash(x)=23862434) +1003 train 7.367260 (lr=1.8274e-04) (hash(x)=25559534) +1004 train 7.588360 (lr=1.8270e-04) (hash(x)=26577585) +1005 train 7.420183 (lr=1.8267e-04) (hash(x)=25546274) +1006 train 7.510986 (lr=1.8264e-04) (hash(x)=26284202) +1007 train 7.514080 (lr=1.8260e-04) (hash(x)=26373991) +1008 train 7.411301 (lr=1.8257e-04) (hash(x)=24612851) +1009 train 7.509464 (lr=1.8254e-04) (hash(x)=26410662) +1010 train 7.547057 (lr=1.8250e-04) (hash(x)=23824841) +1011 train 7.854910 (lr=1.8247e-04) (hash(x)=27756673) +1012 train 7.613019 (lr=1.8244e-04) (hash(x)=25427447) +1013 train 7.573247 (lr=1.8240e-04) (hash(x)=23661686) +1014 train 7.497032 (lr=1.8237e-04) (hash(x)=25129504) +1015 train 7.435289 (lr=1.8234e-04) (hash(x)=23402396) +1016 train 7.674261 (lr=1.8230e-04) (hash(x)=26145557) +1017 train 7.413479 (lr=1.8227e-04) (hash(x)=26547918) +1018 train 7.528908 (lr=1.8224e-04) (hash(x)=26653070) +1019 train 7.531677 (lr=1.8220e-04) (hash(x)=28250354) +1020 train 7.505873 (lr=1.8217e-04) (hash(x)=25437401) +1021 train 7.568417 (lr=1.8213e-04) (hash(x)=25598861) +1022 train 7.374352 (lr=1.8210e-04) (hash(x)=24572587) +1023 train 7.415479 (lr=1.8207e-04) (hash(x)=21562133) +1024 train 7.840711 (lr=1.8203e-04) (hash(x)=27718876) +1025 train 7.388573 (lr=1.8200e-04) (hash(x)=25312391) +1026 train 7.504556 (lr=1.8196e-04) (hash(x)=26579535) +1027 train 7.718033 (lr=1.8193e-04) (hash(x)=27253861) +1028 train 7.612280 (lr=1.8190e-04) (hash(x)=28451867) +1029 train 7.332388 (lr=1.8186e-04) (hash(x)=26795921) +1030 train 7.499320 (lr=1.8183e-04) (hash(x)=26147208) +1031 train 7.516480 (lr=1.8179e-04) (hash(x)=25009210) +1032 train 7.472943 (lr=1.8176e-04) (hash(x)=25213771) +1033 train 7.382289 (lr=1.8173e-04) (hash(x)=26254538) +1034 train 7.396498 (lr=1.8169e-04) (hash(x)=25565614) +1035 train 7.231339 (lr=1.8166e-04) (hash(x)=23052577) +1036 train 8.029510 (lr=1.8162e-04) (hash(x)=29630613) +1037 train 7.287833 (lr=1.8159e-04) (hash(x)=23667224) +1038 train 7.411792 (lr=1.8156e-04) (hash(x)=25740670) +1039 train 7.502862 (lr=1.8152e-04) (hash(x)=27161811) +1040 train 7.637152 (lr=1.8149e-04) (hash(x)=26385663) +1041 train 7.343164 (lr=1.8145e-04) (hash(x)=26313522) +1042 train 7.485365 (lr=1.8142e-04) (hash(x)=26814686) +1043 train 7.599428 (lr=1.8138e-04) (hash(x)=27302459) +1044 train 7.858920 (lr=1.8135e-04) (hash(x)=26758132) +1045 train 7.467883 (lr=1.8131e-04) (hash(x)=26837963) +1046 train 7.270635 (lr=1.8128e-04) (hash(x)=22089547) +1047 train 7.798841 (lr=1.8125e-04) (hash(x)=29515100) +1048 train 7.432205 (lr=1.8121e-04) (hash(x)=25471442) +1049 train 7.433720 (lr=1.8118e-04) (hash(x)=26674478) +1050 val loss 7.4348 +1050 val perplexity 1693.9498 +1050 train 7.399289 (lr=1.8114e-04) (hash(x)=25373386) +1051 train 7.442926 (lr=1.8111e-04) (hash(x)=25318001) +1052 train 7.615469 (lr=1.8107e-04) (hash(x)=27255021) +1053 train 7.546700 (lr=1.8104e-04) (hash(x)=25174043) +1054 train 7.252389 (lr=1.8100e-04) (hash(x)=23857597) +1055 train 7.534021 (lr=1.8097e-04) (hash(x)=25305929) +1056 train 7.568001 (lr=1.8093e-04) (hash(x)=27009246) +1057 train 7.617799 (lr=1.8090e-04) (hash(x)=26175477) +1058 train 7.280422 (lr=1.8086e-04) (hash(x)=22700025) +1059 train 7.411406 (lr=1.8083e-04) (hash(x)=24339043) +1060 train 7.235569 (lr=1.8079e-04) (hash(x)=22139900) +1061 train 8.016894 (lr=1.8076e-04) (hash(x)=25412772) +1062 train 7.507115 (lr=1.8072e-04) (hash(x)=27020849) +1063 train 7.405425 (lr=1.8069e-04) (hash(x)=26808543) +1064 train 7.198565 (lr=1.8065e-04) (hash(x)=23061527) +1065 train 7.410440 (lr=1.8062e-04) (hash(x)=24738650) +1066 train 7.250724 (lr=1.8058e-04) (hash(x)=24036715) +1067 train 7.307840 (lr=1.8055e-04) (hash(x)=25763991) +1068 train 7.590347 (lr=1.8051e-04) (hash(x)=27393753) +1069 train 7.737175 (lr=1.8048e-04) (hash(x)=28182190) +1070 train 7.384284 (lr=1.8044e-04) (hash(x)=23358569) +1071 train 7.590778 (lr=1.8041e-04) (hash(x)=25669509) +1072 train 7.662338 (lr=1.8037e-04) (hash(x)=29139024) +1073 train 7.597898 (lr=1.8034e-04) (hash(x)=25616522) +1074 train 7.434719 (lr=1.8030e-04) (hash(x)=25695789) +1075 train 7.622476 (lr=1.8027e-04) (hash(x)=27676869) +1076 train 7.528061 (lr=1.8023e-04) (hash(x)=25952695) +1077 train 7.502694 (lr=1.8020e-04) (hash(x)=26316170) +1078 train 7.418973 (lr=1.8016e-04) (hash(x)=24081867) +1079 train 7.616455 (lr=1.8012e-04) (hash(x)=28435805) +1080 train 7.471802 (lr=1.8009e-04) (hash(x)=23375063) +1081 train 7.482817 (lr=1.8005e-04) (hash(x)=26869022) +1082 train 7.354146 (lr=1.8002e-04) (hash(x)=25793007) +1083 train 7.315380 (lr=1.7998e-04) (hash(x)=23455211) +1084 train 7.355966 (lr=1.7995e-04) (hash(x)=20441501) +1085 train 7.738588 (lr=1.7991e-04) (hash(x)=29321187) +1086 train 7.897317 (lr=1.7988e-04) (hash(x)=32627505) +1087 train 7.414051 (lr=1.7984e-04) (hash(x)=26482758) +1088 train 7.225254 (lr=1.7980e-04) (hash(x)=21431511) +1089 train 7.506154 (lr=1.7977e-04) (hash(x)=26046639) +1090 train 7.580395 (lr=1.7973e-04) (hash(x)=27464841) +1091 train 7.461569 (lr=1.7970e-04) (hash(x)=27068280) +1092 train 7.312717 (lr=1.7966e-04) (hash(x)=23119133) +1093 train 7.524580 (lr=1.7963e-04) (hash(x)=26782091) +1094 train 7.534027 (lr=1.7959e-04) (hash(x)=26265326) +1095 train 7.558074 (lr=1.7955e-04) (hash(x)=24929929) +1096 train 7.402122 (lr=1.7952e-04) (hash(x)=23158628) +1097 train 7.515707 (lr=1.7948e-04) (hash(x)=25950541) +1098 train 7.297147 (lr=1.7945e-04) (hash(x)=22093912) +1099 train 7.456811 (lr=1.7941e-04) (hash(x)=25373676) +1100 val loss 7.4520 +1100 val perplexity 1723.2318 +1100 train 7.191942 (lr=1.7937e-04) (hash(x)=18986670) +1101 train 7.706848 (lr=1.7934e-04) (hash(x)=27283187) +1102 train 7.450453 (lr=1.7930e-04) (hash(x)=25474743) +1103 train 7.322176 (lr=1.7927e-04) (hash(x)=25043037) +1104 train 7.284593 (lr=1.7923e-04) (hash(x)=23156261) +1105 train 7.730462 (lr=1.7919e-04) (hash(x)=27027534) +1106 train 7.291905 (lr=1.7916e-04) (hash(x)=22733630) +1107 train 7.567310 (lr=1.7912e-04) (hash(x)=27906976) +1108 train 7.503017 (lr=1.7909e-04) (hash(x)=27848655) +1109 train 7.445636 (lr=1.7905e-04) (hash(x)=23889709) +1110 train 8.445752 (lr=1.7901e-04) (hash(x)=33189918) +1111 train 8.017964 (lr=1.7898e-04) (hash(x)=29151257) +1112 train 7.701642 (lr=1.7894e-04) (hash(x)=23881512) +1113 train 7.434904 (lr=1.7890e-04) (hash(x)=21307974) +1114 train 7.471462 (lr=1.7887e-04) (hash(x)=25264524) +1115 train 7.609323 (lr=1.7883e-04) (hash(x)=26405613) +1116 train 7.348114 (lr=1.7879e-04) (hash(x)=21918678) +1117 train 7.364511 (lr=1.7876e-04) (hash(x)=24233887) +1118 train 7.033799 (lr=1.7872e-04) (hash(x)=19490509) +1119 train 7.583812 (lr=1.7868e-04) (hash(x)=26400365) +1120 train 7.779435 (lr=1.7865e-04) (hash(x)=28572086) +1121 train 7.303174 (lr=1.7861e-04) (hash(x)=22293114) +1122 train 7.395128 (lr=1.7858e-04) (hash(x)=26845479) +1123 train 7.254632 (lr=1.7854e-04) (hash(x)=23971905) +1124 train 7.502144 (lr=1.7850e-04) (hash(x)=25639959) +1125 train 7.126427 (lr=1.7846e-04) (hash(x)=20076502) +1126 train 7.486572 (lr=1.7843e-04) (hash(x)=25089255) +1127 train 7.375051 (lr=1.7839e-04) (hash(x)=24098812) +1128 train 7.393399 (lr=1.7835e-04) (hash(x)=23493707) +1129 train 7.626814 (lr=1.7832e-04) (hash(x)=27610410) +1130 train 7.393041 (lr=1.7828e-04) (hash(x)=24540186) +1131 train 7.685011 (lr=1.7824e-04) (hash(x)=29402976) +1132 train 7.250156 (lr=1.7821e-04) (hash(x)=23776025) +1133 train 7.016950 (lr=1.7817e-04) (hash(x)=19032564) +1134 train 7.589362 (lr=1.7813e-04) (hash(x)=26921117) +1135 train 7.195315 (lr=1.7810e-04) (hash(x)=20967666) +1136 train 7.234907 (lr=1.7806e-04) (hash(x)=23394540) +1137 train 7.289749 (lr=1.7802e-04) (hash(x)=22666342) +1138 train 7.429760 (lr=1.7799e-04) (hash(x)=23482498) +1139 train 7.489172 (lr=1.7795e-04) (hash(x)=24287610) +1140 train 7.547104 (lr=1.7791e-04) (hash(x)=24512831) +1141 train 7.785475 (lr=1.7787e-04) (hash(x)=28637634) +1142 train 8.036101 (lr=1.7784e-04) (hash(x)=24107127) +1143 train 7.693112 (lr=1.7780e-04) (hash(x)=28667963) +1144 train 7.582062 (lr=1.7776e-04) (hash(x)=26302492) +1145 train 7.593779 (lr=1.7773e-04) (hash(x)=23621685) +1146 train 7.294486 (lr=1.7769e-04) (hash(x)=23997414) +1147 train 7.391884 (lr=1.7765e-04) (hash(x)=25974316) +1148 train 7.320152 (lr=1.7761e-04) (hash(x)=23464988) +1149 train 7.437881 (lr=1.7758e-04) (hash(x)=24487710) +1150 val loss 7.4082 +1150 val perplexity 1649.4441 +1150 train 7.662616 (lr=1.7754e-04) (hash(x)=29610350) +1151 train 7.756845 (lr=1.7750e-04) (hash(x)=27083417) +1152 train 7.077808 (lr=1.7746e-04) (hash(x)=20666288) +1153 train 7.162094 (lr=1.7743e-04) (hash(x)=22850633) +1154 train 7.358693 (lr=1.7739e-04) (hash(x)=24741872) +1155 train 7.751570 (lr=1.7735e-04) (hash(x)=28605205) +1156 train 7.205077 (lr=1.7731e-04) (hash(x)=22624463) +1157 train 7.441099 (lr=1.7728e-04) (hash(x)=24786468) +1158 train 7.177835 (lr=1.7724e-04) (hash(x)=21365399) +1159 train 7.425496 (lr=1.7720e-04) (hash(x)=23649001) +1160 train 7.492436 (lr=1.7716e-04) (hash(x)=28203982) +1161 train 7.409760 (lr=1.7713e-04) (hash(x)=26473994) +1162 train 7.074273 (lr=1.7709e-04) (hash(x)=19476441) +1163 train 7.382787 (lr=1.7705e-04) (hash(x)=25921700) +1164 train 7.178465 (lr=1.7701e-04) (hash(x)=23064343) +1165 train 7.337369 (lr=1.7698e-04) (hash(x)=24117626) +1166 train 7.272934 (lr=1.7694e-04) (hash(x)=21764556) +1167 train 8.170796 (lr=1.7690e-04) (hash(x)=31338300) +1168 train 7.604163 (lr=1.7686e-04) (hash(x)=27443187) +1169 train 7.033925 (lr=1.7682e-04) (hash(x)=21337692) +1170 train 7.542263 (lr=1.7679e-04) (hash(x)=27845383) +1171 train 7.350903 (lr=1.7675e-04) (hash(x)=23862328) +1172 train 7.565248 (lr=1.7671e-04) (hash(x)=23811014) +1173 train 7.520618 (lr=1.7667e-04) (hash(x)=24380098) +1174 train 7.188180 (lr=1.7663e-04) (hash(x)=22351136) +1175 train 7.470631 (lr=1.7660e-04) (hash(x)=30603174) +1176 train 7.507009 (lr=1.7656e-04) (hash(x)=27924596) +1177 train 7.887871 (lr=1.7652e-04) (hash(x)=30882548) +1178 train 7.311867 (lr=1.7648e-04) (hash(x)=22339464) +1179 train 7.150870 (lr=1.7644e-04) (hash(x)=23603806) +1180 train 7.529317 (lr=1.7641e-04) (hash(x)=24809041) +1181 train 7.328872 (lr=1.7637e-04) (hash(x)=24382442) +1182 train 7.290235 (lr=1.7633e-04) (hash(x)=23134077) +1183 train 7.321997 (lr=1.7629e-04) (hash(x)=24830965) +1184 train 7.405435 (lr=1.7625e-04) (hash(x)=25527259) +1185 train 7.480150 (lr=1.7621e-04) (hash(x)=25547480) +1186 train 7.292096 (lr=1.7618e-04) (hash(x)=24424314) +1187 train 7.706510 (lr=1.7614e-04) (hash(x)=32488729) +1188 train 7.650330 (lr=1.7610e-04) (hash(x)=31168462) +1189 train 7.872941 (lr=1.7606e-04) (hash(x)=31331643) +1190 train 7.535308 (lr=1.7602e-04) (hash(x)=28746633) +1191 train 7.520323 (lr=1.7598e-04) (hash(x)=27269893) +1192 train 7.337029 (lr=1.7595e-04) (hash(x)=23484031) +1193 train 7.328578 (lr=1.7591e-04) (hash(x)=23278725) +1194 train 7.421716 (lr=1.7587e-04) (hash(x)=25440745) +1195 train 7.429334 (lr=1.7583e-04) (hash(x)=25215077) +1196 train 7.482830 (lr=1.7579e-04) (hash(x)=28309266) +1197 train 7.215535 (lr=1.7575e-04) (hash(x)=22442404) +1198 train 7.237722 (lr=1.7571e-04) (hash(x)=20775262) +1199 train 7.336222 (lr=1.7568e-04) (hash(x)=24825041) +1200 val loss 7.3930 +1200 val perplexity 1624.5836 +1200 train 7.534601 (lr=1.7564e-04) (hash(x)=29016896) +1201 train 7.451547 (lr=1.7560e-04) (hash(x)=25590276) +1202 train 7.275079 (lr=1.7556e-04) (hash(x)=22816384) +1203 train 7.443574 (lr=1.7552e-04) (hash(x)=25893804) +1204 train 7.329518 (lr=1.7548e-04) (hash(x)=23983816) +1205 train 7.231846 (lr=1.7544e-04) (hash(x)=22222468) +1206 train 7.291197 (lr=1.7540e-04) (hash(x)=23039141) +1207 train 7.221485 (lr=1.7537e-04) (hash(x)=22724871) +1208 train 7.292392 (lr=1.7533e-04) (hash(x)=25253062) +1209 train 7.275968 (lr=1.7529e-04) (hash(x)=25140744) +1210 train 7.357548 (lr=1.7525e-04) (hash(x)=24717218) +1211 train 7.448641 (lr=1.7521e-04) (hash(x)=27317554) +1212 train 7.099817 (lr=1.7517e-04) (hash(x)=22013236) +1213 train 7.681880 (lr=1.7513e-04) (hash(x)=26692343) +1214 train 7.228824 (lr=1.7509e-04) (hash(x)=19859225) +1215 train 7.115663 (lr=1.7505e-04) (hash(x)=24683717) +1216 train 7.168130 (lr=1.7501e-04) (hash(x)=21932013) +1217 train 7.438980 (lr=1.7497e-04) (hash(x)=26849303) +1218 train 7.519499 (lr=1.7494e-04) (hash(x)=26458000) +1219 train 7.286864 (lr=1.7490e-04) (hash(x)=21584083) +1220 train 7.679368 (lr=1.7486e-04) (hash(x)=23598625) +1221 train 7.388253 (lr=1.7482e-04) (hash(x)=26059939) +1222 train 7.622708 (lr=1.7478e-04) (hash(x)=25481982) +1223 train 7.505296 (lr=1.7474e-04) (hash(x)=26190337) +1224 train 7.692769 (lr=1.7470e-04) (hash(x)=28767755) +1225 train 7.358737 (lr=1.7466e-04) (hash(x)=23663918) +1226 train 7.468124 (lr=1.7462e-04) (hash(x)=21293227) +1227 train 7.485379 (lr=1.7458e-04) (hash(x)=22249019) +1228 train 7.577231 (lr=1.7454e-04) (hash(x)=26886529) +1229 train 7.423498 (lr=1.7450e-04) (hash(x)=25779849) +1230 train 7.548297 (lr=1.7446e-04) (hash(x)=26228964) +1231 train 7.443773 (lr=1.7442e-04) (hash(x)=23086289) +1232 train 7.535752 (lr=1.7439e-04) (hash(x)=23198922) +1233 train 7.533200 (lr=1.7435e-04) (hash(x)=27523941) +1234 train 7.306540 (lr=1.7431e-04) (hash(x)=24293992) +1235 train 8.072480 (lr=1.7427e-04) (hash(x)=28047044) +1236 train 7.530025 (lr=1.7423e-04) (hash(x)=23688671) +1237 train 7.391099 (lr=1.7419e-04) (hash(x)=25125498) +1238 train 7.283675 (lr=1.7415e-04) (hash(x)=21977292) +1239 train 7.311144 (lr=1.7411e-04) (hash(x)=23593875) +1240 train 7.314363 (lr=1.7407e-04) (hash(x)=22659030) +1241 train 7.412677 (lr=1.7403e-04) (hash(x)=25117733) +1242 train 7.392111 (lr=1.7399e-04) (hash(x)=22322808) +1243 train 7.413259 (lr=1.7395e-04) (hash(x)=26059735) +1244 train 7.335739 (lr=1.7391e-04) (hash(x)=22485526) +1245 train 7.245177 (lr=1.7387e-04) (hash(x)=23028679) +1246 train 7.257726 (lr=1.7383e-04) (hash(x)=22906035) +1247 train 7.159841 (lr=1.7379e-04) (hash(x)=22414190) +1248 train 7.454271 (lr=1.7375e-04) (hash(x)=26229624) +1249 train 7.246662 (lr=1.7371e-04) (hash(x)=22223137) +1250 val loss 7.3838 +1250 val perplexity 1609.7334 +1250 train 7.512401 (lr=1.7367e-04) (hash(x)=24911520) +1251 train 7.643278 (lr=1.7363e-04) (hash(x)=24204591) +1252 train 7.215745 (lr=1.7359e-04) (hash(x)=24379601) +1253 train 7.217497 (lr=1.7355e-04) (hash(x)=22922475) +1254 train 7.252309 (lr=1.7351e-04) (hash(x)=23426249) +1255 train 7.526900 (lr=1.7347e-04) (hash(x)=26758114) +1256 train 7.208327 (lr=1.7343e-04) (hash(x)=24027111) +1257 train 7.371495 (lr=1.7339e-04) (hash(x)=25358064) +1258 train 7.263323 (lr=1.7335e-04) (hash(x)=22571285) +1259 train 7.658848 (lr=1.7331e-04) (hash(x)=20084233) +1260 train 7.469411 (lr=1.7327e-04) (hash(x)=18786581) +1261 train 7.397087 (lr=1.7323e-04) (hash(x)=26395104) +1262 train 7.279648 (lr=1.7319e-04) (hash(x)=24212567) +1263 train 7.106262 (lr=1.7315e-04) (hash(x)=21563184) +1264 train 7.369036 (lr=1.7311e-04) (hash(x)=26490150) +1265 train 7.450015 (lr=1.7307e-04) (hash(x)=25207694) +1266 train 7.282104 (lr=1.7303e-04) (hash(x)=23914544) +1267 train 7.286892 (lr=1.7299e-04) (hash(x)=23861489) +1268 train 7.765959 (lr=1.7295e-04) (hash(x)=30714540) +1269 train 7.257008 (lr=1.7291e-04) (hash(x)=23471007) +1270 train 7.252495 (lr=1.7287e-04) (hash(x)=23244293) +1271 train 7.190836 (lr=1.7282e-04) (hash(x)=19218470) +1272 train 7.470499 (lr=1.7278e-04) (hash(x)=26965136) +1273 train 7.221916 (lr=1.7274e-04) (hash(x)=22944035) +1274 train 7.298028 (lr=1.7270e-04) (hash(x)=22002714) +1275 train 7.577922 (lr=1.7266e-04) (hash(x)=28469562) +1276 train 7.606325 (lr=1.7262e-04) (hash(x)=26889992) +1277 train 7.672605 (lr=1.7258e-04) (hash(x)=26452814) +1278 train 7.444424 (lr=1.7254e-04) (hash(x)=28397488) +1279 train 7.529459 (lr=1.7250e-04) (hash(x)=25588469) +1280 train 7.410791 (lr=1.7246e-04) (hash(x)=24833139) +1281 train 7.266348 (lr=1.7242e-04) (hash(x)=24788298) +1282 train 7.512260 (lr=1.7238e-04) (hash(x)=24979383) +1283 train 7.526352 (lr=1.7234e-04) (hash(x)=25236367) +1284 train 7.381297 (lr=1.7230e-04) (hash(x)=22638257) +1285 train 7.175127 (lr=1.7226e-04) (hash(x)=23069067) +1286 train 7.324851 (lr=1.7221e-04) (hash(x)=25133239) +1287 train 7.939229 (lr=1.7217e-04) (hash(x)=30433767) +1288 train 7.952671 (lr=1.7213e-04) (hash(x)=34319079) +1289 train 7.792927 (lr=1.7209e-04) (hash(x)=29268881) +1290 train 7.423558 (lr=1.7205e-04) (hash(x)=24528336) +1291 train 7.590790 (lr=1.7201e-04) (hash(x)=26302626) +1292 train 7.539595 (lr=1.7197e-04) (hash(x)=25479111) +1293 train 7.744297 (lr=1.7193e-04) (hash(x)=24749682) +1294 train 7.359175 (lr=1.7189e-04) (hash(x)=24111393) +1295 train 7.036157 (lr=1.7185e-04) (hash(x)=17851621) +1296 train 7.309477 (lr=1.7180e-04) (hash(x)=26463070) +1297 train 7.373903 (lr=1.7176e-04) (hash(x)=25620741) +1298 train 8.021807 (lr=1.7172e-04) (hash(x)=28225676) +1299 train 7.811702 (lr=1.7168e-04) (hash(x)=27028191) +1300 val loss 7.3746 +1300 val perplexity 1595.0084 +1300 train 7.442833 (lr=1.7164e-04) (hash(x)=29006516) +1301 train 7.574065 (lr=1.7160e-04) (hash(x)=27590299) +1302 train 7.714825 (lr=1.7156e-04) (hash(x)=28678983) +1303 train 7.546834 (lr=1.7152e-04) (hash(x)=25183690) +1304 train 7.151859 (lr=1.7147e-04) (hash(x)=19918097) +1305 train 7.881271 (lr=1.7143e-04) (hash(x)=31114252) +1306 train 7.834545 (lr=1.7139e-04) (hash(x)=30913255) +1307 train 7.416626 (lr=1.7135e-04) (hash(x)=26182243) +1308 train 7.628537 (lr=1.7131e-04) (hash(x)=27420668) +1309 train 7.886653 (lr=1.7127e-04) (hash(x)=30419908) +1310 train 7.778972 (lr=1.7123e-04) (hash(x)=29002281) +1311 train 7.432297 (lr=1.7118e-04) (hash(x)=27040642) +1312 train 7.354000 (lr=1.7114e-04) (hash(x)=26929300) +1313 train 7.471628 (lr=1.7110e-04) (hash(x)=26240761) +1314 train 7.506155 (lr=1.7106e-04) (hash(x)=27161876) +1315 train 7.352890 (lr=1.7102e-04) (hash(x)=24489607) +1316 train 7.743648 (lr=1.7098e-04) (hash(x)=27040115) +1317 train 7.398000 (lr=1.7094e-04) (hash(x)=25012872) +1318 train 7.040944 (lr=1.7089e-04) (hash(x)=20894720) +1319 train 7.198967 (lr=1.7085e-04) (hash(x)=22183303) +1320 train 7.400104 (lr=1.7081e-04) (hash(x)=26291778) +1321 train 7.523273 (lr=1.7077e-04) (hash(x)=27682633) +1322 train 7.301755 (lr=1.7073e-04) (hash(x)=26490892) +1323 train 7.751082 (lr=1.7069e-04) (hash(x)=28844646) +1324 train 8.074229 (lr=1.7064e-04) (hash(x)=29545304) +1325 train 8.246567 (lr=1.7060e-04) (hash(x)=31082070) +1326 train 7.817445 (lr=1.7056e-04) (hash(x)=27486316) +1327 train 7.709578 (lr=1.7052e-04) (hash(x)=27537063) +1328 train 7.462945 (lr=1.7048e-04) (hash(x)=26955557) +1329 train 7.454256 (lr=1.7043e-04) (hash(x)=26125988) +1330 train 7.456417 (lr=1.7039e-04) (hash(x)=22800125) +1331 train 7.620410 (lr=1.7035e-04) (hash(x)=25446686) +1332 train 7.722822 (lr=1.7031e-04) (hash(x)=28743746) +1333 train 7.455388 (lr=1.7027e-04) (hash(x)=19819857) +1334 train 7.189072 (lr=1.7022e-04) (hash(x)=23518628) +1335 train 7.132161 (lr=1.7018e-04) (hash(x)=19492832) +1336 train 7.371420 (lr=1.7014e-04) (hash(x)=24627720) +1337 train 7.267599 (lr=1.7010e-04) (hash(x)=23741214) +1338 train 7.374976 (lr=1.7006e-04) (hash(x)=25837914) +1339 train 7.284429 (lr=1.7001e-04) (hash(x)=25484958) +1340 train 7.254360 (lr=1.6997e-04) (hash(x)=23671284) +1341 train 7.376156 (lr=1.6993e-04) (hash(x)=25525370) +1342 train 7.474725 (lr=1.6989e-04) (hash(x)=26585300) +1343 train 7.501735 (lr=1.6985e-04) (hash(x)=25951629) +1344 train 7.687939 (lr=1.6980e-04) (hash(x)=28743135) +1345 train 7.854125 (lr=1.6976e-04) (hash(x)=28557663) +1346 train 7.227628 (lr=1.6972e-04) (hash(x)=22642751) +1347 train 7.167208 (lr=1.6968e-04) (hash(x)=23462798) +1348 train 7.051756 (lr=1.6963e-04) (hash(x)=24292328) +1349 train 7.374149 (lr=1.6959e-04) (hash(x)=27320280) +1350 val loss 7.3608 +1350 val perplexity 1573.1467 +1350 train 7.577303 (lr=1.6955e-04) (hash(x)=27352812) +1351 train 7.372594 (lr=1.6951e-04) (hash(x)=22408682) +1352 train 7.307039 (lr=1.6946e-04) (hash(x)=23144732) +1353 train 7.157362 (lr=1.6942e-04) (hash(x)=22230799) +1354 train 7.578517 (lr=1.6938e-04) (hash(x)=29747687) +1355 train 7.774010 (lr=1.6934e-04) (hash(x)=31317970) +1356 train 6.989181 (lr=1.6929e-04) (hash(x)=20131758) +1357 train 7.401107 (lr=1.6925e-04) (hash(x)=24020983) +1358 train 7.233522 (lr=1.6921e-04) (hash(x)=23998051) +1359 train 7.309311 (lr=1.6917e-04) (hash(x)=27633457) +1360 train 7.093405 (lr=1.6912e-04) (hash(x)=20155247) +1361 train 7.333150 (lr=1.6908e-04) (hash(x)=23766987) +1362 train 7.237206 (lr=1.6904e-04) (hash(x)=25960383) +1363 train 7.491313 (lr=1.6900e-04) (hash(x)=23729283) +1364 train 7.594772 (lr=1.6895e-04) (hash(x)=27775445) +1365 train 7.457634 (lr=1.6891e-04) (hash(x)=25975834) +1366 train 7.259202 (lr=1.6887e-04) (hash(x)=22765259) +1367 train 7.547074 (lr=1.6882e-04) (hash(x)=27635080) +1368 train 7.311595 (lr=1.6878e-04) (hash(x)=23848542) +1369 train 7.458553 (lr=1.6874e-04) (hash(x)=27181156) +1370 train 7.611990 (lr=1.6870e-04) (hash(x)=28321340) +1371 train 7.303258 (lr=1.6865e-04) (hash(x)=25918780) +1372 train 7.310297 (lr=1.6861e-04) (hash(x)=23338297) +1373 train 7.390512 (lr=1.6857e-04) (hash(x)=22370417) +1374 train 7.359989 (lr=1.6852e-04) (hash(x)=24272668) +1375 train 7.050967 (lr=1.6848e-04) (hash(x)=22287596) +1376 train 7.252351 (lr=1.6844e-04) (hash(x)=25257403) +1377 train 7.180731 (lr=1.6840e-04) (hash(x)=21584419) +1378 train 7.373046 (lr=1.6835e-04) (hash(x)=25318823) +1379 train 7.163761 (lr=1.6831e-04) (hash(x)=22694623) +1380 train 7.294925 (lr=1.6827e-04) (hash(x)=23743406) +1381 train 7.583887 (lr=1.6822e-04) (hash(x)=30820846) +1382 train 8.104634 (lr=1.6818e-04) (hash(x)=34639557) +1383 train 7.988367 (lr=1.6814e-04) (hash(x)=35895440) +1384 train 7.383494 (lr=1.6809e-04) (hash(x)=26304839) +1385 train 7.522121 (lr=1.6805e-04) (hash(x)=27058657) +1386 train 7.385963 (lr=1.6801e-04) (hash(x)=25209529) +1387 train 7.307753 (lr=1.6796e-04) (hash(x)=24298886) +1388 train 7.431247 (lr=1.6792e-04) (hash(x)=26200200) +1389 train 7.349344 (lr=1.6788e-04) (hash(x)=27303061) +1390 train 7.427536 (lr=1.6783e-04) (hash(x)=26531628) +1391 train 7.411519 (lr=1.6779e-04) (hash(x)=25888847) +1392 train 7.584251 (lr=1.6775e-04) (hash(x)=28924067) +1393 train 7.004642 (lr=1.6770e-04) (hash(x)=21267641) +1394 train 7.625123 (lr=1.6766e-04) (hash(x)=29419156) +1395 train 7.823911 (lr=1.6762e-04) (hash(x)=30860646) +1396 train 7.360802 (lr=1.6757e-04) (hash(x)=25744434) +1397 train 7.372126 (lr=1.6753e-04) (hash(x)=26881837) +1398 train 7.331239 (lr=1.6749e-04) (hash(x)=26676176) +1399 train 7.548582 (lr=1.6744e-04) (hash(x)=26518800) +1400 val loss 7.3491 +1400 val perplexity 1554.8190 +1400 train 7.284225 (lr=1.6740e-04) (hash(x)=25043238) +1401 train 7.550619 (lr=1.6736e-04) (hash(x)=25863277) +1402 train 7.219276 (lr=1.6731e-04) (hash(x)=24073623) +1403 train 7.269259 (lr=1.6727e-04) (hash(x)=25385523) +1404 train 7.344820 (lr=1.6723e-04) (hash(x)=24958112) +1405 train 7.210083 (lr=1.6718e-04) (hash(x)=23362519) +1406 train 7.506362 (lr=1.6714e-04) (hash(x)=29262616) +1407 train 7.931122 (lr=1.6709e-04) (hash(x)=37519283) +1408 train 8.214627 (lr=1.6705e-04) (hash(x)=33716930) +1409 train 7.355374 (lr=1.6701e-04) (hash(x)=23392584) +1410 train 7.855253 (lr=1.6696e-04) (hash(x)=22877779) +1411 train 8.222812 (lr=1.6692e-04) (hash(x)=20564397) +1412 train 7.556214 (lr=1.6688e-04) (hash(x)=24366235) +1413 train 7.451481 (lr=1.6683e-04) (hash(x)=27065499) +1414 train 7.277343 (lr=1.6679e-04) (hash(x)=26844114) +1415 train 7.424339 (lr=1.6674e-04) (hash(x)=25141945) +1416 train 7.650571 (lr=1.6670e-04) (hash(x)=28813116) +1417 train 7.444280 (lr=1.6666e-04) (hash(x)=25466598) +1418 train 7.326019 (lr=1.6661e-04) (hash(x)=22800032) +1419 train 7.379902 (lr=1.6657e-04) (hash(x)=22717866) +1420 train 7.895417 (lr=1.6652e-04) (hash(x)=28040763) +1421 train 7.986489 (lr=1.6648e-04) (hash(x)=29648992) +1422 train 7.941297 (lr=1.6644e-04) (hash(x)=31747228) +1423 train 7.401891 (lr=1.6639e-04) (hash(x)=28527939) +1424 train 7.324535 (lr=1.6635e-04) (hash(x)=21563992) +1425 train 7.249775 (lr=1.6630e-04) (hash(x)=25134784) +1426 train 7.444275 (lr=1.6626e-04) (hash(x)=28442823) +1427 train 8.016087 (lr=1.6622e-04) (hash(x)=32757059) +1428 train 7.212821 (lr=1.6617e-04) (hash(x)=24110500) +1429 train 7.281771 (lr=1.6613e-04) (hash(x)=24145729) +1430 train 7.332496 (lr=1.6608e-04) (hash(x)=23541086) +1431 train 7.169113 (lr=1.6604e-04) (hash(x)=21942471) +1432 train 7.289524 (lr=1.6599e-04) (hash(x)=24736836) +1433 train 7.437485 (lr=1.6595e-04) (hash(x)=25325444) +1434 train 7.442699 (lr=1.6591e-04) (hash(x)=25188954) +1435 train 7.939099 (lr=1.6586e-04) (hash(x)=24247339) +1436 train 7.411803 (lr=1.6582e-04) (hash(x)=23773363) +1437 train 7.174155 (lr=1.6577e-04) (hash(x)=24142989) +1438 train 7.183028 (lr=1.6573e-04) (hash(x)=24226952) +1439 train 7.402555 (lr=1.6568e-04) (hash(x)=24955630) +1440 train 7.348195 (lr=1.6564e-04) (hash(x)=24563233) +1441 train 7.461191 (lr=1.6559e-04) (hash(x)=25491335) +1442 train 7.807234 (lr=1.6555e-04) (hash(x)=33253763) +1443 train 7.254342 (lr=1.6551e-04) (hash(x)=21368780) +1444 train 7.282411 (lr=1.6546e-04) (hash(x)=26615500) +1445 train 7.514903 (lr=1.6542e-04) (hash(x)=27146278) +1446 train 7.351641 (lr=1.6537e-04) (hash(x)=25904861) +1447 train 7.179909 (lr=1.6533e-04) (hash(x)=25541230) +1448 train 7.384948 (lr=1.6528e-04) (hash(x)=25434227) +1449 train 7.315425 (lr=1.6524e-04) (hash(x)=25375355) +1450 val loss 7.3241 +1450 val perplexity 1516.4215 +1450 train 7.160417 (lr=1.6519e-04) (hash(x)=21921129) +1451 train 7.150495 (lr=1.6515e-04) (hash(x)=23098806) +1452 train 7.184892 (lr=1.6510e-04) (hash(x)=22000544) +1453 train 7.111558 (lr=1.6506e-04) (hash(x)=22061174) +1454 train 7.220478 (lr=1.6501e-04) (hash(x)=24326286) +1455 train 7.260054 (lr=1.6497e-04) (hash(x)=23501481) +1456 train 7.407838 (lr=1.6492e-04) (hash(x)=26397938) +1457 train 7.385083 (lr=1.6488e-04) (hash(x)=24656430) +1458 train 7.113672 (lr=1.6484e-04) (hash(x)=23494971) +1459 train 7.152306 (lr=1.6479e-04) (hash(x)=23802681) +1460 train 7.189362 (lr=1.6475e-04) (hash(x)=21990153) +1461 train 7.206406 (lr=1.6470e-04) (hash(x)=23496118) +1462 train 7.211502 (lr=1.6466e-04) (hash(x)=24233822) +1463 train 7.542123 (lr=1.6461e-04) (hash(x)=22754988) +1464 train 7.253890 (lr=1.6457e-04) (hash(x)=23116635) +1465 train 6.991863 (lr=1.6452e-04) (hash(x)=21461650) +1466 train 7.137294 (lr=1.6448e-04) (hash(x)=22274473) +1467 train 7.150588 (lr=1.6443e-04) (hash(x)=22183009) +1468 train 7.372768 (lr=1.6439e-04) (hash(x)=24972441) +1469 train 7.193379 (lr=1.6434e-04) (hash(x)=22300616) +1470 train 6.974577 (lr=1.6430e-04) (hash(x)=21443060) +1471 train 7.213384 (lr=1.6425e-04) (hash(x)=23475070) +1472 train 7.134131 (lr=1.6421e-04) (hash(x)=22316810) +1473 train 7.585620 (lr=1.6416e-04) (hash(x)=24508407) +1474 train 7.639927 (lr=1.6411e-04) (hash(x)=24603557) +1475 train 7.210811 (lr=1.6407e-04) (hash(x)=23359061) +1476 train 7.268090 (lr=1.6402e-04) (hash(x)=22950844) +1477 train 7.321014 (lr=1.6398e-04) (hash(x)=22588667) +1478 train 7.409235 (lr=1.6393e-04) (hash(x)=26083526) +1479 train 7.348712 (lr=1.6389e-04) (hash(x)=23609959) +1480 train 7.361320 (lr=1.6384e-04) (hash(x)=24088171) +1481 train 7.365772 (lr=1.6380e-04) (hash(x)=25394852) +1482 train 7.315186 (lr=1.6375e-04) (hash(x)=24503040) +1483 train 7.042473 (lr=1.6371e-04) (hash(x)=22408449) +1484 train 7.313747 (lr=1.6366e-04) (hash(x)=25069325) +1485 train 7.359159 (lr=1.6362e-04) (hash(x)=26947398) +1486 train 6.796403 (lr=1.6357e-04) (hash(x)=17527161) +1487 train 7.231296 (lr=1.6353e-04) (hash(x)=23441847) +1488 train 7.245351 (lr=1.6348e-04) (hash(x)=25592861) +1489 train 7.156029 (lr=1.6343e-04) (hash(x)=23101350) +1490 train 7.130173 (lr=1.6339e-04) (hash(x)=24201380) +1491 train 7.261903 (lr=1.6334e-04) (hash(x)=23676365) +1492 train 7.345384 (lr=1.6330e-04) (hash(x)=26668088) +1493 train 7.465477 (lr=1.6325e-04) (hash(x)=26488811) +1494 train 7.453815 (lr=1.6321e-04) (hash(x)=27248109) +1495 train 7.504468 (lr=1.6316e-04) (hash(x)=23096292) +1496 train 7.411344 (lr=1.6312e-04) (hash(x)=22101981) +1497 train 7.553178 (lr=1.6307e-04) (hash(x)=24512380) +1498 train 7.344463 (lr=1.6302e-04) (hash(x)=25367738) +1499 train 7.341691 (lr=1.6298e-04) (hash(x)=27706294) +1500 val loss 7.3324 +1500 val perplexity 1528.9863 +1500 train 7.465325 (lr=1.6293e-04) (hash(x)=24154026) +1501 train 7.167728 (lr=1.6289e-04) (hash(x)=21892472) +1502 train 7.255362 (lr=1.6284e-04) (hash(x)=23662543) +1503 train 7.299277 (lr=1.6280e-04) (hash(x)=26171093) +1504 train 7.323738 (lr=1.6275e-04) (hash(x)=25974292) +1505 train 7.182265 (lr=1.6270e-04) (hash(x)=23191101) +1506 train 7.451055 (lr=1.6266e-04) (hash(x)=26498861) +1507 train 7.983570 (lr=1.6261e-04) (hash(x)=34946941) +1508 train 7.568738 (lr=1.6257e-04) (hash(x)=25442719) +1509 train 7.394621 (lr=1.6252e-04) (hash(x)=25569942) +1510 train 7.134066 (lr=1.6247e-04) (hash(x)=21265828) +1511 train 7.028474 (lr=1.6243e-04) (hash(x)=20060838) +1512 train 7.248869 (lr=1.6238e-04) (hash(x)=22588251) +1513 train 7.194879 (lr=1.6234e-04) (hash(x)=24581020) +1514 train 7.170475 (lr=1.6229e-04) (hash(x)=21882493) +1515 train 7.140669 (lr=1.6224e-04) (hash(x)=21591702) +1516 train 7.144867 (lr=1.6220e-04) (hash(x)=19813285) +1517 train 7.221588 (lr=1.6215e-04) (hash(x)=21870012) +1518 train 7.273320 (lr=1.6211e-04) (hash(x)=26895498) +1519 train 7.272777 (lr=1.6206e-04) (hash(x)=25451055) +1520 train 7.332442 (lr=1.6201e-04) (hash(x)=25395865) +1521 train 6.802155 (lr=1.6197e-04) (hash(x)=18989695) +1522 train 6.652781 (lr=1.6192e-04) (hash(x)=17040678) +1523 train 6.775954 (lr=1.6188e-04) (hash(x)=18691455) +1524 train 6.885866 (lr=1.6183e-04) (hash(x)=19017167) +1525 train 7.214668 (lr=1.6178e-04) (hash(x)=22406503) +1526 train 7.409242 (lr=1.6174e-04) (hash(x)=23036138) +1527 train 7.236533 (lr=1.6169e-04) (hash(x)=24934792) +1528 train 7.260633 (lr=1.6164e-04) (hash(x)=22843127) +1529 train 7.216058 (lr=1.6160e-04) (hash(x)=24249677) +1530 train 7.094041 (lr=1.6155e-04) (hash(x)=23318555) +1531 train 7.115556 (lr=1.6150e-04) (hash(x)=23864361) +1532 train 7.015118 (lr=1.6146e-04) (hash(x)=20242060) +1533 train 7.217214 (lr=1.6141e-04) (hash(x)=21549554) +1534 train 7.007373 (lr=1.6137e-04) (hash(x)=21642024) +1535 train 7.490154 (lr=1.6132e-04) (hash(x)=25367597) +1536 train 7.667247 (lr=1.6127e-04) (hash(x)=27224144) +1537 train 7.213865 (lr=1.6123e-04) (hash(x)=24409290) +1538 train 7.247759 (lr=1.6118e-04) (hash(x)=24987180) +1539 train 7.199165 (lr=1.6113e-04) (hash(x)=27016702) +1540 train 7.432836 (lr=1.6109e-04) (hash(x)=25819636) +1541 train 7.374310 (lr=1.6104e-04) (hash(x)=25520453) +1542 train 7.139215 (lr=1.6099e-04) (hash(x)=23580496) +1543 train 7.340818 (lr=1.6095e-04) (hash(x)=25022148) +1544 train 7.346829 (lr=1.6090e-04) (hash(x)=25447327) +1545 train 7.329422 (lr=1.6085e-04) (hash(x)=25010319) +1546 train 7.272731 (lr=1.6081e-04) (hash(x)=25511777) +1547 train 7.221434 (lr=1.6076e-04) (hash(x)=24459012) +1548 train 7.270528 (lr=1.6071e-04) (hash(x)=25082785) +1549 train 7.327357 (lr=1.6067e-04) (hash(x)=26528670) +1550 val loss 7.3140 +1550 val perplexity 1501.1915 +1550 train 7.323439 (lr=1.6062e-04) (hash(x)=26684367) +1551 train 7.285046 (lr=1.6057e-04) (hash(x)=25431365) +1552 train 7.279563 (lr=1.6053e-04) (hash(x)=24802747) +1553 train 7.084631 (lr=1.6048e-04) (hash(x)=24229522) +1554 train 7.336785 (lr=1.6043e-04) (hash(x)=24757176) +1555 train 7.480025 (lr=1.6039e-04) (hash(x)=25958785) +1556 train 7.486081 (lr=1.6034e-04) (hash(x)=26810735) +1557 train 7.093858 (lr=1.6029e-04) (hash(x)=22882640) +1558 train 7.583481 (lr=1.6025e-04) (hash(x)=27220057) +1559 train 7.856793 (lr=1.6020e-04) (hash(x)=29307788) +1560 train 7.266174 (lr=1.6015e-04) (hash(x)=25214030) +1561 train 7.088940 (lr=1.6010e-04) (hash(x)=23167825) +1562 train 7.177600 (lr=1.6006e-04) (hash(x)=24658511) +1563 train 7.305288 (lr=1.6001e-04) (hash(x)=24965435) +1564 train 7.091023 (lr=1.5996e-04) (hash(x)=23620579) +1565 train 7.087151 (lr=1.5992e-04) (hash(x)=23772949) +1566 train 7.278614 (lr=1.5987e-04) (hash(x)=23807939) +1567 train 7.475849 (lr=1.5982e-04) (hash(x)=25651929) +1568 train 7.411354 (lr=1.5977e-04) (hash(x)=25549933) +1569 train 7.107694 (lr=1.5973e-04) (hash(x)=23146724) +1570 train 7.215247 (lr=1.5968e-04) (hash(x)=24099275) +1571 train 7.422967 (lr=1.5963e-04) (hash(x)=28451031) +1572 train 7.451024 (lr=1.5959e-04) (hash(x)=25488511) +1573 train 7.235963 (lr=1.5954e-04) (hash(x)=23796771) +1574 train 7.300888 (lr=1.5949e-04) (hash(x)=22642764) +1575 train 7.404259 (lr=1.5944e-04) (hash(x)=26312387) +1576 train 7.166879 (lr=1.5940e-04) (hash(x)=22486223) +1577 train 7.199352 (lr=1.5935e-04) (hash(x)=21257377) +1578 train 7.322838 (lr=1.5930e-04) (hash(x)=24328365) +1579 train 7.395105 (lr=1.5926e-04) (hash(x)=25326650) +1580 train 7.382376 (lr=1.5921e-04) (hash(x)=26484837) +1581 train 7.152586 (lr=1.5916e-04) (hash(x)=24605603) +1582 train 7.237544 (lr=1.5911e-04) (hash(x)=24668537) +1583 train 7.148670 (lr=1.5907e-04) (hash(x)=23804913) +1584 train 7.399851 (lr=1.5902e-04) (hash(x)=23615391) +1585 train 7.385810 (lr=1.5897e-04) (hash(x)=24322926) +1586 train 7.155737 (lr=1.5892e-04) (hash(x)=19753104) +1587 train 7.647575 (lr=1.5888e-04) (hash(x)=25537529) +1588 train 7.025648 (lr=1.5883e-04) (hash(x)=22835476) +1589 train 7.187121 (lr=1.5878e-04) (hash(x)=25707197) +1590 train 7.166637 (lr=1.5873e-04) (hash(x)=24191203) +1591 train 7.430658 (lr=1.5869e-04) (hash(x)=26115519) +1592 train 7.337701 (lr=1.5864e-04) (hash(x)=25781547) +1593 train 7.159664 (lr=1.5859e-04) (hash(x)=24850654) +1594 train 7.076869 (lr=1.5854e-04) (hash(x)=23300928) +1595 train 7.345007 (lr=1.5850e-04) (hash(x)=25494804) +1596 train 7.340717 (lr=1.5845e-04) (hash(x)=28169410) +1597 train 7.085023 (lr=1.5840e-04) (hash(x)=21972022) +1598 train 7.647707 (lr=1.5835e-04) (hash(x)=27687290) +1599 train 7.522214 (lr=1.5830e-04) (hash(x)=23210747) +1600 val loss 7.3292 +1600 val perplexity 1524.1471 +1600 train 7.530915 (lr=1.5826e-04) (hash(x)=20362758) +1601 train 7.367365 (lr=1.5821e-04) (hash(x)=17064773) +1602 train 7.354068 (lr=1.5816e-04) (hash(x)=17173694) +1603 train 7.445473 (lr=1.5811e-04) (hash(x)=15717069) +1604 train 7.551891 (lr=1.5807e-04) (hash(x)=15117973) +1605 train 7.382706 (lr=1.5802e-04) (hash(x)=16189636) +1606 train 7.317407 (lr=1.5797e-04) (hash(x)=16552095) +1607 train 7.219383 (lr=1.5792e-04) (hash(x)=18463712) +1608 train 7.400533 (lr=1.5787e-04) (hash(x)=17572155) +1609 train 7.422498 (lr=1.5783e-04) (hash(x)=19970072) +1610 train 7.444333 (lr=1.5778e-04) (hash(x)=20463871) +1611 train 7.485487 (lr=1.5773e-04) (hash(x)=20705573) +1612 train 7.270635 (lr=1.5768e-04) (hash(x)=24441646) +1613 train 7.428398 (lr=1.5763e-04) (hash(x)=22913147) +1614 train 7.584661 (lr=1.5759e-04) (hash(x)=23081598) +1615 train 7.349731 (lr=1.5754e-04) (hash(x)=23245699) +1616 train 7.393704 (lr=1.5749e-04) (hash(x)=23003072) +1617 train 7.618541 (lr=1.5744e-04) (hash(x)=27121904) +1618 train 7.381122 (lr=1.5739e-04) (hash(x)=25092305) +1619 train 7.412165 (lr=1.5735e-04) (hash(x)=23444521) +1620 train 7.432389 (lr=1.5730e-04) (hash(x)=22130531) +1621 train 7.227940 (lr=1.5725e-04) (hash(x)=20917937) +1622 train 7.331111 (lr=1.5720e-04) (hash(x)=22526838) +1623 train 7.453809 (lr=1.5715e-04) (hash(x)=21770300) +1624 train 8.467811 (lr=1.5711e-04) (hash(x)=22333537) +1625 train 8.451922 (lr=1.5706e-04) (hash(x)=24642519) +1626 train 7.630946 (lr=1.5701e-04) (hash(x)=25199038) +1627 train 7.493497 (lr=1.5696e-04) (hash(x)=23334569) +1628 train 7.342336 (lr=1.5691e-04) (hash(x)=23785360) +1629 train 6.977332 (lr=1.5686e-04) (hash(x)=21796200) +1630 train 7.056151 (lr=1.5682e-04) (hash(x)=22389081) +1631 train 7.356313 (lr=1.5677e-04) (hash(x)=25387532) +1632 train 6.944828 (lr=1.5672e-04) (hash(x)=17247578) +1633 train 7.322424 (lr=1.5667e-04) (hash(x)=22203733) +1634 train 7.479063 (lr=1.5662e-04) (hash(x)=24387455) +1635 train 7.931509 (lr=1.5657e-04) (hash(x)=29466743) +1636 train 7.307947 (lr=1.5653e-04) (hash(x)=25354152) +1637 train 7.377490 (lr=1.5648e-04) (hash(x)=21756102) +1638 train 7.309189 (lr=1.5643e-04) (hash(x)=23544029) +1639 train 7.489204 (lr=1.5638e-04) (hash(x)=27718703) +1640 train 7.441500 (lr=1.5633e-04) (hash(x)=25697138) +1641 train 7.290534 (lr=1.5628e-04) (hash(x)=22978681) +1642 train 7.834435 (lr=1.5624e-04) (hash(x)=29527067) +1643 train 6.916124 (lr=1.5619e-04) (hash(x)=17631973) +1644 train 7.304924 (lr=1.5614e-04) (hash(x)=24860172) +1645 train 7.637795 (lr=1.5609e-04) (hash(x)=27947891) +1646 train 7.332569 (lr=1.5604e-04) (hash(x)=23819556) +1647 train 7.366223 (lr=1.5599e-04) (hash(x)=27661052) +1648 train 7.139729 (lr=1.5594e-04) (hash(x)=23014209) +1649 train 7.090631 (lr=1.5590e-04) (hash(x)=23061452) +1650 val loss 7.3254 +1650 val perplexity 1518.3961 +1650 train 7.205214 (lr=1.5585e-04) (hash(x)=21949051) +1651 train 7.247837 (lr=1.5580e-04) (hash(x)=22244096) +1652 train 7.228632 (lr=1.5575e-04) (hash(x)=25997585) +1653 train 7.309448 (lr=1.5570e-04) (hash(x)=25389713) +1654 train 7.233179 (lr=1.5565e-04) (hash(x)=24390520) +1655 train 7.466449 (lr=1.5560e-04) (hash(x)=26538928) +1656 train 7.417726 (lr=1.5555e-04) (hash(x)=28708088) +1657 train 7.523670 (lr=1.5551e-04) (hash(x)=25685569) +1658 train 7.050260 (lr=1.5546e-04) (hash(x)=22163531) +1659 train 7.229573 (lr=1.5541e-04) (hash(x)=26256802) +1660 train 7.696523 (lr=1.5536e-04) (hash(x)=30016026) +1661 train 7.260982 (lr=1.5531e-04) (hash(x)=24412323) +1662 train 7.273695 (lr=1.5526e-04) (hash(x)=24722307) +1663 train 7.141683 (lr=1.5521e-04) (hash(x)=21772654) +1664 train 7.101729 (lr=1.5516e-04) (hash(x)=24984527) +1665 train 7.266603 (lr=1.5511e-04) (hash(x)=25456825) +1666 train 7.606624 (lr=1.5507e-04) (hash(x)=24383976) +1667 train 7.510156 (lr=1.5502e-04) (hash(x)=25026277) +1668 train 7.436834 (lr=1.5497e-04) (hash(x)=28121715) +1669 train 7.438498 (lr=1.5492e-04) (hash(x)=26855439) +1670 train 7.536640 (lr=1.5487e-04) (hash(x)=33370924) +1671 train 7.400093 (lr=1.5482e-04) (hash(x)=26263254) +1672 train 7.836685 (lr=1.5477e-04) (hash(x)=29958158) +1673 train 7.110687 (lr=1.5472e-04) (hash(x)=21917396) +1674 train 7.274998 (lr=1.5467e-04) (hash(x)=24196295) +1675 train 7.310693 (lr=1.5462e-04) (hash(x)=24726314) +1676 train 7.097482 (lr=1.5457e-04) (hash(x)=22137742) +1677 train 7.222825 (lr=1.5453e-04) (hash(x)=24375100) +1678 train 7.191040 (lr=1.5448e-04) (hash(x)=23965039) +1679 train 7.243970 (lr=1.5443e-04) (hash(x)=23552356) +1680 train 7.211543 (lr=1.5438e-04) (hash(x)=26136969) +1681 train 7.468736 (lr=1.5433e-04) (hash(x)=25343112) +1682 train 7.139069 (lr=1.5428e-04) (hash(x)=22831508) +1683 train 7.407240 (lr=1.5423e-04) (hash(x)=26699819) +1684 train 7.508347 (lr=1.5418e-04) (hash(x)=25435504) +1685 train 7.679271 (lr=1.5413e-04) (hash(x)=25218858) +1686 train 8.273698 (lr=1.5408e-04) (hash(x)=25664448) +1687 train 7.357221 (lr=1.5403e-04) (hash(x)=22707141) +1688 train 7.501120 (lr=1.5398e-04) (hash(x)=28001383) +1689 train 7.764487 (lr=1.5393e-04) (hash(x)=29168269) +1690 train 7.696289 (lr=1.5389e-04) (hash(x)=29637522) +1691 train 7.724192 (lr=1.5384e-04) (hash(x)=25676149) +1692 train 7.148990 (lr=1.5379e-04) (hash(x)=20919831) +1693 train 7.344814 (lr=1.5374e-04) (hash(x)=24324401) +1694 train 7.417902 (lr=1.5369e-04) (hash(x)=26862625) +1695 train 7.806140 (lr=1.5364e-04) (hash(x)=34234481) +1696 train 7.377317 (lr=1.5359e-04) (hash(x)=27415195) +1697 train 7.174274 (lr=1.5354e-04) (hash(x)=24511386) +1698 train 7.347640 (lr=1.5349e-04) (hash(x)=26904299) +1699 train 7.206284 (lr=1.5344e-04) (hash(x)=25401624) +1700 val loss 7.3054 +1700 val perplexity 1488.2660 +1700 train 7.264671 (lr=1.5339e-04) (hash(x)=26498489) +1701 train 7.230711 (lr=1.5334e-04) (hash(x)=22340685) +1702 train 7.370818 (lr=1.5329e-04) (hash(x)=26396757) +1703 train 7.971137 (lr=1.5324e-04) (hash(x)=35008670) +1704 train 7.704029 (lr=1.5319e-04) (hash(x)=31782020) +1705 train 7.596273 (lr=1.5314e-04) (hash(x)=29662286) +1706 train 7.785828 (lr=1.5309e-04) (hash(x)=34215782) +1707 train 7.285150 (lr=1.5304e-04) (hash(x)=25682280) +1708 train 7.469421 (lr=1.5299e-04) (hash(x)=27109048) +1709 train 7.511939 (lr=1.5294e-04) (hash(x)=27686498) +1710 train 7.352882 (lr=1.5289e-04) (hash(x)=24247565) +1711 train 7.340257 (lr=1.5284e-04) (hash(x)=25891543) +1712 train 7.447150 (lr=1.5279e-04) (hash(x)=26436778) +1713 train 7.102905 (lr=1.5274e-04) (hash(x)=22538881) +1714 train 7.045494 (lr=1.5270e-04) (hash(x)=21993512) +1715 train 7.540751 (lr=1.5265e-04) (hash(x)=25962407) +1716 train 7.336322 (lr=1.5260e-04) (hash(x)=24130284) +1717 train 7.199562 (lr=1.5255e-04) (hash(x)=24819073) +1718 train 7.064220 (lr=1.5250e-04) (hash(x)=23496648) +1719 train 7.139834 (lr=1.5245e-04) (hash(x)=21971224) +1720 train 7.024752 (lr=1.5240e-04) (hash(x)=21498081) +1721 train 7.056686 (lr=1.5235e-04) (hash(x)=20951317) +1722 train 7.614662 (lr=1.5230e-04) (hash(x)=28848134) +1723 train 7.639799 (lr=1.5225e-04) (hash(x)=30838142) +1724 train 7.597894 (lr=1.5220e-04) (hash(x)=28844392) +1725 train 7.223137 (lr=1.5215e-04) (hash(x)=23102419) +1726 train 7.264386 (lr=1.5210e-04) (hash(x)=22374479) +1727 train 7.520055 (lr=1.5205e-04) (hash(x)=27312186) +1728 train 7.895500 (lr=1.5200e-04) (hash(x)=34362559) +1729 train 7.802819 (lr=1.5195e-04) (hash(x)=30920030) +1730 train 7.095792 (lr=1.5190e-04) (hash(x)=23684126) +1731 train 7.329222 (lr=1.5185e-04) (hash(x)=23657081) +1732 train 7.585847 (lr=1.5180e-04) (hash(x)=28463299) +1733 train 7.869266 (lr=1.5175e-04) (hash(x)=35351214) +1734 train 7.422301 (lr=1.5170e-04) (hash(x)=28855662) +1735 train 6.926700 (lr=1.5165e-04) (hash(x)=22163749) +1736 train 6.939438 (lr=1.5160e-04) (hash(x)=22024585) +1737 train 7.155431 (lr=1.5155e-04) (hash(x)=24629160) +1738 train 7.240637 (lr=1.5150e-04) (hash(x)=25220941) +1739 train 7.191819 (lr=1.5145e-04) (hash(x)=24829818) +1740 train 7.533053 (lr=1.5139e-04) (hash(x)=28453898) +1741 train 7.569001 (lr=1.5134e-04) (hash(x)=25424550) +1742 train 7.204976 (lr=1.5129e-04) (hash(x)=23437814) +1743 train 7.309536 (lr=1.5124e-04) (hash(x)=25942888) +1744 train 7.264503 (lr=1.5119e-04) (hash(x)=24503801) +1745 train 7.587135 (lr=1.5114e-04) (hash(x)=26418501) +1746 train 7.478024 (lr=1.5109e-04) (hash(x)=27177691) +1747 train 7.163743 (lr=1.5104e-04) (hash(x)=23785671) +1748 train 7.600957 (lr=1.5099e-04) (hash(x)=27362772) +1749 train 7.349605 (lr=1.5094e-04) (hash(x)=25097859) +1750 val loss 7.3351 +1750 val perplexity 1533.2531 +1750 train 7.320099 (lr=1.5089e-04) (hash(x)=24662466) +1751 train 7.239547 (lr=1.5084e-04) (hash(x)=25493916) +1752 train 7.309470 (lr=1.5079e-04) (hash(x)=24655868) +1753 train 7.558277 (lr=1.5074e-04) (hash(x)=19819210) +1754 train 7.177780 (lr=1.5069e-04) (hash(x)=21377155) +1755 train 7.995093 (lr=1.5064e-04) (hash(x)=28618702) +1756 train 7.892625 (lr=1.5059e-04) (hash(x)=27324953) +1757 train 7.606987 (lr=1.5054e-04) (hash(x)=29707907) +1758 train 7.385737 (lr=1.5049e-04) (hash(x)=24485921) +1759 train 7.485284 (lr=1.5044e-04) (hash(x)=24289951) +1760 train 7.179798 (lr=1.5039e-04) (hash(x)=22496716) +1761 train 7.353939 (lr=1.5034e-04) (hash(x)=25147026) +1762 train 7.415267 (lr=1.5029e-04) (hash(x)=26851828) +1763 train 7.379607 (lr=1.5024e-04) (hash(x)=26331486) +1764 train 7.256271 (lr=1.5018e-04) (hash(x)=24383054) +1765 train 7.473812 (lr=1.5013e-04) (hash(x)=25885126) +1766 train 7.442216 (lr=1.5008e-04) (hash(x)=25848470) +1767 train 7.279483 (lr=1.5003e-04) (hash(x)=23648671) +1768 train 7.233661 (lr=1.4998e-04) (hash(x)=23168674) +1769 train 7.071495 (lr=1.4993e-04) (hash(x)=20252079) +1770 train 7.304790 (lr=1.4988e-04) (hash(x)=23914287) +1771 train 7.587963 (lr=1.4983e-04) (hash(x)=27292797) +1772 train 6.833487 (lr=1.4978e-04) (hash(x)=16175151) +1773 train 6.943680 (lr=1.4973e-04) (hash(x)=18317379) +1774 train 7.336252 (lr=1.4968e-04) (hash(x)=24464271) +1775 train 7.317476 (lr=1.4963e-04) (hash(x)=24992055) +1776 train 7.981631 (lr=1.4958e-04) (hash(x)=26032451) +1777 train 7.708795 (lr=1.4953e-04) (hash(x)=24734221) +1778 train 7.698940 (lr=1.4947e-04) (hash(x)=25413430) +1779 train 7.540718 (lr=1.4942e-04) (hash(x)=24398330) +1780 train 7.368510 (lr=1.4937e-04) (hash(x)=24568049) +1781 train 7.295645 (lr=1.4932e-04) (hash(x)=23573984) +1782 train 7.518906 (lr=1.4927e-04) (hash(x)=27338410) +1783 train 7.459840 (lr=1.4922e-04) (hash(x)=26005549) +1784 train 7.287740 (lr=1.4917e-04) (hash(x)=24332331) +1785 train 7.135872 (lr=1.4912e-04) (hash(x)=22583878) +1786 train 7.330471 (lr=1.4907e-04) (hash(x)=24599113) +1787 train 7.765870 (lr=1.4902e-04) (hash(x)=30259737) +1788 train 7.533711 (lr=1.4897e-04) (hash(x)=26504237) +1789 train 7.405928 (lr=1.4891e-04) (hash(x)=25196470) +1790 train 7.324490 (lr=1.4886e-04) (hash(x)=23607871) +1791 train 7.211329 (lr=1.4881e-04) (hash(x)=21046554) +1792 train 7.483716 (lr=1.4876e-04) (hash(x)=27285635) +1793 train 7.468553 (lr=1.4871e-04) (hash(x)=25454371) +1794 train 7.489063 (lr=1.4866e-04) (hash(x)=26486575) +1795 train 6.933516 (lr=1.4861e-04) (hash(x)=18773877) +1796 train 7.136083 (lr=1.4856e-04) (hash(x)=22506761) +1797 train 7.386828 (lr=1.4851e-04) (hash(x)=24645168) +1798 train 7.467833 (lr=1.4846e-04) (hash(x)=25046236) +1799 train 7.516750 (lr=1.4840e-04) (hash(x)=26321539) +1800 val loss 7.3515 +1800 val perplexity 1558.6069 +1800 train 7.267011 (lr=1.4835e-04) (hash(x)=24602494) +1801 train 7.461465 (lr=1.4830e-04) (hash(x)=25722713) +1802 train 7.208749 (lr=1.4825e-04) (hash(x)=23711219) +1803 train 7.305322 (lr=1.4820e-04) (hash(x)=22850804) +1804 train 7.616399 (lr=1.4815e-04) (hash(x)=25829388) +1805 train 7.130229 (lr=1.4810e-04) (hash(x)=22503524) +1806 train 7.453546 (lr=1.4805e-04) (hash(x)=26669453) +1807 train 7.364829 (lr=1.4799e-04) (hash(x)=27807872) +1808 train 7.375281 (lr=1.4794e-04) (hash(x)=23543560) +1809 train 7.526258 (lr=1.4789e-04) (hash(x)=25845590) +1810 train 7.256408 (lr=1.4784e-04) (hash(x)=23026635) +1811 train 7.245428 (lr=1.4779e-04) (hash(x)=25545137) +1812 train 7.728786 (lr=1.4774e-04) (hash(x)=27746841) +1813 train 7.119901 (lr=1.4769e-04) (hash(x)=25471231) +1814 train 7.256522 (lr=1.4764e-04) (hash(x)=24333204) +1815 train 7.131517 (lr=1.4758e-04) (hash(x)=21555364) +1816 train 7.350111 (lr=1.4753e-04) (hash(x)=26317977) +1817 train 7.399828 (lr=1.4748e-04) (hash(x)=24474988) +1818 train 7.070575 (lr=1.4743e-04) (hash(x)=21975953) +1819 train 7.674192 (lr=1.4738e-04) (hash(x)=27243798) +1820 train 7.284189 (lr=1.4733e-04) (hash(x)=25097367) +1821 train 7.211318 (lr=1.4728e-04) (hash(x)=24419085) +1822 train 7.174804 (lr=1.4722e-04) (hash(x)=23058837) +1823 train 7.330358 (lr=1.4717e-04) (hash(x)=26325324) +1824 train 7.025798 (lr=1.4712e-04) (hash(x)=20581023) +1825 train 7.367986 (lr=1.4707e-04) (hash(x)=24822111) +1826 train 7.150760 (lr=1.4702e-04) (hash(x)=24336304) +1827 train 7.320058 (lr=1.4697e-04) (hash(x)=26228728) +1828 train 7.434631 (lr=1.4691e-04) (hash(x)=26445781) +1829 train 7.505515 (lr=1.4686e-04) (hash(x)=24707042) +1830 train 7.766702 (lr=1.4681e-04) (hash(x)=27882744) +1831 train 7.266529 (lr=1.4676e-04) (hash(x)=24956294) +1832 train 7.087498 (lr=1.4671e-04) (hash(x)=20984728) +1833 train 7.118211 (lr=1.4666e-04) (hash(x)=23424737) +1834 train 7.521126 (lr=1.4660e-04) (hash(x)=26207120) +1835 train 7.518537 (lr=1.4655e-04) (hash(x)=25592289) +1836 train 7.194963 (lr=1.4650e-04) (hash(x)=24326649) +1837 train 7.322338 (lr=1.4645e-04) (hash(x)=26826109) +1838 train 7.321794 (lr=1.4640e-04) (hash(x)=24759294) +1839 train 7.313002 (lr=1.4635e-04) (hash(x)=24429389) +1840 train 7.282340 (lr=1.4629e-04) (hash(x)=25537519) +1841 train 7.267064 (lr=1.4624e-04) (hash(x)=24747421) +1842 train 7.144592 (lr=1.4619e-04) (hash(x)=23079065) +1843 train 7.568006 (lr=1.4614e-04) (hash(x)=28733708) +1844 train 7.267025 (lr=1.4609e-04) (hash(x)=23937742) +1845 train 7.579879 (lr=1.4604e-04) (hash(x)=29704803) +1846 train 7.757080 (lr=1.4598e-04) (hash(x)=34617155) +1847 train 7.464464 (lr=1.4593e-04) (hash(x)=27929846) +1848 train 7.827119 (lr=1.4588e-04) (hash(x)=28280878) +1849 train 6.835053 (lr=1.4583e-04) (hash(x)=18961171) +1850 val loss 7.3329 +1850 val perplexity 1529.8680 +1850 train 7.436330 (lr=1.4578e-04) (hash(x)=27146015) +1851 train 7.184671 (lr=1.4572e-04) (hash(x)=22417476) +1852 train 7.323654 (lr=1.4567e-04) (hash(x)=24583152) +1853 train 7.363658 (lr=1.4562e-04) (hash(x)=26364120) +1854 train 7.548364 (lr=1.4557e-04) (hash(x)=25946767) +1855 train 7.377593 (lr=1.4552e-04) (hash(x)=25282897) +1856 train 7.322505 (lr=1.4546e-04) (hash(x)=25154557) +1857 train 7.001316 (lr=1.4541e-04) (hash(x)=22082503) +1858 train 7.068157 (lr=1.4536e-04) (hash(x)=23974606) +1859 train 7.204801 (lr=1.4531e-04) (hash(x)=22278062) +1860 train 7.147350 (lr=1.4526e-04) (hash(x)=19509639) +1861 train 7.405010 (lr=1.4520e-04) (hash(x)=24271468) +1862 train 6.988198 (lr=1.4515e-04) (hash(x)=21943809) +1863 train 7.262592 (lr=1.4510e-04) (hash(x)=26802508) +1864 train 7.850883 (lr=1.4505e-04) (hash(x)=34178409) +1865 train 8.004568 (lr=1.4500e-04) (hash(x)=33468379) +1866 train 7.142645 (lr=1.4494e-04) (hash(x)=22109262) +1867 train 6.854647 (lr=1.4489e-04) (hash(x)=22094832) +1868 train 7.166618 (lr=1.4484e-04) (hash(x)=24016953) +1869 train 7.457114 (lr=1.4479e-04) (hash(x)=26759850) +1870 train 7.213985 (lr=1.4474e-04) (hash(x)=23570779) +1871 train 7.707106 (lr=1.4468e-04) (hash(x)=28390416) +1872 train 7.720885 (lr=1.4463e-04) (hash(x)=26215770) +1873 train 7.566600 (lr=1.4458e-04) (hash(x)=22727956) +1874 train 7.341714 (lr=1.4453e-04) (hash(x)=21304587) +1875 train 7.668118 (lr=1.4447e-04) (hash(x)=26379331) +1876 train 7.747528 (lr=1.4442e-04) (hash(x)=25252419) +1877 train 7.547290 (lr=1.4437e-04) (hash(x)=25048158) +1878 train 7.525826 (lr=1.4432e-04) (hash(x)=23588991) +1879 train 7.541109 (lr=1.4427e-04) (hash(x)=26292451) +1880 train 7.400484 (lr=1.4421e-04) (hash(x)=23617086) +1881 train 7.283528 (lr=1.4416e-04) (hash(x)=23336031) +1882 train 7.219244 (lr=1.4411e-04) (hash(x)=19198742) +1883 train 7.922928 (lr=1.4406e-04) (hash(x)=26301866) +1884 train 7.912107 (lr=1.4400e-04) (hash(x)=30114703) +1885 train 7.443386 (lr=1.4395e-04) (hash(x)=26687040) +1886 train 7.315868 (lr=1.4390e-04) (hash(x)=25810717) +1887 train 7.114030 (lr=1.4385e-04) (hash(x)=22915344) +1888 train 7.465273 (lr=1.4379e-04) (hash(x)=27046189) +1889 train 7.047985 (lr=1.4374e-04) (hash(x)=19831900) +1890 train 7.448694 (lr=1.4369e-04) (hash(x)=27786987) +1891 train 7.317153 (lr=1.4364e-04) (hash(x)=25448318) +1892 train 7.320833 (lr=1.4358e-04) (hash(x)=25166953) +1893 train 7.279903 (lr=1.4353e-04) (hash(x)=24993116) +1894 train 7.351337 (lr=1.4348e-04) (hash(x)=25748002) +1895 train 7.568626 (lr=1.4343e-04) (hash(x)=24744383) +1896 train 7.307642 (lr=1.4337e-04) (hash(x)=25560120) +1897 train 7.117862 (lr=1.4332e-04) (hash(x)=23731849) +1898 train 7.136518 (lr=1.4327e-04) (hash(x)=24115851) +1899 train 7.180072 (lr=1.4322e-04) (hash(x)=22835201) +1900 val loss 7.3032 +1900 val perplexity 1485.1135 +1900 train 6.932422 (lr=1.4316e-04) (hash(x)=21927896) +1901 train 7.342047 (lr=1.4311e-04) (hash(x)=24652361) +1902 train 7.520429 (lr=1.4306e-04) (hash(x)=27332405) +1903 train 7.334144 (lr=1.4301e-04) (hash(x)=26284678) +1904 train 7.308436 (lr=1.4295e-04) (hash(x)=23441305) +1905 train 7.367273 (lr=1.4290e-04) (hash(x)=27522881) +1906 train 7.410788 (lr=1.4285e-04) (hash(x)=25521191) +1907 train 7.195236 (lr=1.4280e-04) (hash(x)=24745936) +1908 train 7.093857 (lr=1.4274e-04) (hash(x)=21653364) +1909 train 7.136215 (lr=1.4269e-04) (hash(x)=21973969) +1910 train 7.125295 (lr=1.4264e-04) (hash(x)=24318192) +1911 train 7.090310 (lr=1.4258e-04) (hash(x)=21654269) +1912 train 7.143564 (lr=1.4253e-04) (hash(x)=24142904) +1913 train 7.050883 (lr=1.4248e-04) (hash(x)=21708739) +1914 train 7.279420 (lr=1.4243e-04) (hash(x)=22937923) +1915 train 7.870655 (lr=1.4237e-04) (hash(x)=32387999) +1916 train 8.043764 (lr=1.4232e-04) (hash(x)=28958671) +1917 train 8.104103 (lr=1.4227e-04) (hash(x)=32662682) +1918 train 7.976293 (lr=1.4222e-04) (hash(x)=31364539) +1919 train 8.058907 (lr=1.4216e-04) (hash(x)=29466268) +1920 train 8.042094 (lr=1.4211e-04) (hash(x)=31407564) +1921 train 7.899495 (lr=1.4206e-04) (hash(x)=28372973) +1922 train 8.004578 (lr=1.4200e-04) (hash(x)=28620993) +1923 train 8.052627 (lr=1.4195e-04) (hash(x)=30736727) +1924 train 7.985370 (lr=1.4190e-04) (hash(x)=30370374) +1925 train 7.918419 (lr=1.4185e-04) (hash(x)=29935562) +1926 train 7.900441 (lr=1.4179e-04) (hash(x)=30528627) +1927 train 7.926534 (lr=1.4174e-04) (hash(x)=32616762) +1928 train 7.754803 (lr=1.4169e-04) (hash(x)=29150044) +1929 train 7.943988 (lr=1.4163e-04) (hash(x)=32861403) +1930 train 7.880224 (lr=1.4158e-04) (hash(x)=31053918) +1931 train 7.794713 (lr=1.4153e-04) (hash(x)=29358578) +1932 train 7.885143 (lr=1.4147e-04) (hash(x)=31521292) +1933 train 7.850700 (lr=1.4142e-04) (hash(x)=31218966) +1934 train 7.854709 (lr=1.4137e-04) (hash(x)=31811872) +1935 train 8.044349 (lr=1.4132e-04) (hash(x)=32201138) +1936 train 7.750955 (lr=1.4126e-04) (hash(x)=28631348) +1937 train 7.814075 (lr=1.4121e-04) (hash(x)=30545133) +1938 train 7.881663 (lr=1.4116e-04) (hash(x)=32136080) +1939 train 7.970761 (lr=1.4110e-04) (hash(x)=30041621) +1940 train 7.737657 (lr=1.4105e-04) (hash(x)=30537181) +1941 train 7.763635 (lr=1.4100e-04) (hash(x)=30371023) +1942 train 7.889238 (lr=1.4094e-04) (hash(x)=30734634) +1943 train 7.824051 (lr=1.4089e-04) (hash(x)=33683468) +1944 train 7.871431 (lr=1.4084e-04) (hash(x)=30472451) +1945 train 7.732622 (lr=1.4078e-04) (hash(x)=29809830) +1946 train 7.527609 (lr=1.4073e-04) (hash(x)=26077593) +1947 train 7.523016 (lr=1.4068e-04) (hash(x)=26837755) +1948 train 7.460541 (lr=1.4063e-04) (hash(x)=23910920) +1949 train 7.446457 (lr=1.4057e-04) (hash(x)=26084089) +1950 val loss 7.4052 +1950 val perplexity 1644.4816 +1950 train 7.616385 (lr=1.4052e-04) (hash(x)=26963533) +1951 train 7.432414 (lr=1.4047e-04) (hash(x)=27498125) +1952 train 7.641885 (lr=1.4041e-04) (hash(x)=29512508) +1953 train 7.862547 (lr=1.4036e-04) (hash(x)=34478395) +1954 train 7.511644 (lr=1.4031e-04) (hash(x)=25357046) +1955 train 7.346077 (lr=1.4025e-04) (hash(x)=22372507) +1956 train 7.282787 (lr=1.4020e-04) (hash(x)=24501779) +1957 train 7.353055 (lr=1.4015e-04) (hash(x)=25638879) +1958 train 7.178777 (lr=1.4009e-04) (hash(x)=24243109) +1959 train 7.142711 (lr=1.4004e-04) (hash(x)=25164318) +1960 train 7.303917 (lr=1.3999e-04) (hash(x)=24139533) +1961 train 7.337531 (lr=1.3993e-04) (hash(x)=27271900) +1962 train 7.172009 (lr=1.3988e-04) (hash(x)=24869232) +1963 train 7.353657 (lr=1.3983e-04) (hash(x)=26562947) +1964 train 7.230741 (lr=1.3977e-04) (hash(x)=26477326) +1965 train 7.361471 (lr=1.3972e-04) (hash(x)=24917192) +1966 train 7.126708 (lr=1.3967e-04) (hash(x)=23110147) +1967 train 7.226743 (lr=1.3961e-04) (hash(x)=25690221) +1968 train 7.699070 (lr=1.3956e-04) (hash(x)=26999273) +1969 train 7.332662 (lr=1.3951e-04) (hash(x)=24807841) +1970 train 7.224690 (lr=1.3945e-04) (hash(x)=23918831) +1971 train 7.141183 (lr=1.3940e-04) (hash(x)=21947305) +1972 train 7.218976 (lr=1.3935e-04) (hash(x)=22874486) +1973 train 7.159164 (lr=1.3929e-04) (hash(x)=22195089) +1974 train 7.270903 (lr=1.3924e-04) (hash(x)=25345359) +1975 train 7.421174 (lr=1.3918e-04) (hash(x)=29031550) +1976 train 7.370091 (lr=1.3913e-04) (hash(x)=29947423) +1977 train 7.561127 (lr=1.3908e-04) (hash(x)=29395823) +1978 train 7.341350 (lr=1.3902e-04) (hash(x)=26968216) +1979 train 7.359914 (lr=1.3897e-04) (hash(x)=26551589) +1980 train 7.341852 (lr=1.3892e-04) (hash(x)=25657210) +1981 train 7.316763 (lr=1.3886e-04) (hash(x)=23689487) +1982 train 7.435631 (lr=1.3881e-04) (hash(x)=25744240) +1983 train 7.416451 (lr=1.3876e-04) (hash(x)=24094093) +1984 train 7.110149 (lr=1.3870e-04) (hash(x)=21724872) +1985 train 7.149716 (lr=1.3865e-04) (hash(x)=24106453) +1986 train 7.232968 (lr=1.3860e-04) (hash(x)=25004577) +1987 train 7.241866 (lr=1.3854e-04) (hash(x)=23639076) +1988 train 7.517017 (lr=1.3849e-04) (hash(x)=29408797) +1989 train 7.172601 (lr=1.3843e-04) (hash(x)=25107314) +1990 train 9.798052 (lr=1.3838e-04) (hash(x)=49896019) +1991 train 11.268143 (lr=1.3833e-04) (hash(x)=61455960) +1992 train 11.042198 (lr=1.3827e-04) (hash(x)=63788199) +1993 train 11.128433 (lr=1.3822e-04) (hash(x)=63899424) +1994 train 10.787713 (lr=1.3817e-04) (hash(x)=66412689) +1995 train 10.366029 (lr=1.3811e-04) (hash(x)=65636572) +1996 train 10.406960 (lr=1.3806e-04) (hash(x)=69649789) +1997 train 10.091975 (lr=1.3801e-04) (hash(x)=71578682) +1998 train 9.253240 (lr=1.3795e-04) (hash(x)=58341730) +1999 train 9.208707 (lr=1.3790e-04) (hash(x)=61104710) +2000 val loss 8.0643 +2000 val perplexity 3178.8105 +2000 train 8.780829 (lr=1.3784e-04) (hash(x)=52865322) +2001 train 8.323714 (lr=1.3779e-04) (hash(x)=23633693) +2002 train 8.180041 (lr=1.3774e-04) (hash(x)=25297571) +2003 train 8.511673 (lr=1.3768e-04) (hash(x)=24123821) +2004 train 7.776944 (lr=1.3763e-04) (hash(x)=20161517) +2005 train 7.573886 (lr=1.3757e-04) (hash(x)=19919984) +2006 train 7.507405 (lr=1.3752e-04) (hash(x)=18626507) +2007 train 7.581819 (lr=1.3747e-04) (hash(x)=20881126) +2008 train 7.682178 (lr=1.3741e-04) (hash(x)=26261448) +2009 train 7.749745 (lr=1.3736e-04) (hash(x)=27528050) +2010 train 7.739523 (lr=1.3731e-04) (hash(x)=26692097) +2011 train 7.428689 (lr=1.3725e-04) (hash(x)=23209969) +2012 train 7.422861 (lr=1.3720e-04) (hash(x)=26083446) +2013 train 7.720363 (lr=1.3714e-04) (hash(x)=28426467) +2014 train 7.515491 (lr=1.3709e-04) (hash(x)=26158154) +2015 train 7.660516 (lr=1.3704e-04) (hash(x)=26920243) +2016 train 7.304694 (lr=1.3698e-04) (hash(x)=21365321) +2017 train 7.407227 (lr=1.3693e-04) (hash(x)=25730699) +2018 train 7.509064 (lr=1.3687e-04) (hash(x)=25177106) +2019 train 7.360393 (lr=1.3682e-04) (hash(x)=26127756) +2020 train 6.894874 (lr=1.3677e-04) (hash(x)=19770037) +2021 train 7.356070 (lr=1.3671e-04) (hash(x)=26479346) +2022 train 7.364616 (lr=1.3666e-04) (hash(x)=25967643) +2023 train 7.283438 (lr=1.3660e-04) (hash(x)=21970343) +2024 train 7.576374 (lr=1.3655e-04) (hash(x)=26449648) +2025 train 7.457115 (lr=1.3650e-04) (hash(x)=24874094) +2026 train 7.066104 (lr=1.3644e-04) (hash(x)=21399697) +2027 train 7.286411 (lr=1.3639e-04) (hash(x)=24097897) +2028 train 7.361588 (lr=1.3633e-04) (hash(x)=24453548) +2029 train 7.458984 (lr=1.3628e-04) (hash(x)=26692093) +2030 train 7.285582 (lr=1.3623e-04) (hash(x)=27217002) +2031 train 7.685899 (lr=1.3617e-04) (hash(x)=31676352) +2032 train 7.302399 (lr=1.3612e-04) (hash(x)=23396350) +2033 train 7.371660 (lr=1.3606e-04) (hash(x)=26245173) +2034 train 7.384917 (lr=1.3601e-04) (hash(x)=24821033) +2035 train 7.419296 (lr=1.3595e-04) (hash(x)=23908053) +2036 train 7.142394 (lr=1.3590e-04) (hash(x)=23469373) +2037 train 7.228115 (lr=1.3585e-04) (hash(x)=24102198) +2038 train 7.247004 (lr=1.3579e-04) (hash(x)=24712135) +2039 train 7.577316 (lr=1.3574e-04) (hash(x)=25600562) +2040 train 7.400657 (lr=1.3568e-04) (hash(x)=23193393) +2041 train 7.413859 (lr=1.3563e-04) (hash(x)=24776954) +2042 train 7.529915 (lr=1.3558e-04) (hash(x)=28066546) +2043 train 7.098671 (lr=1.3552e-04) (hash(x)=23549168) +2044 train 7.130257 (lr=1.3547e-04) (hash(x)=22681487) +2045 train 7.357628 (lr=1.3541e-04) (hash(x)=26663184) +2046 train 7.270978 (lr=1.3536e-04) (hash(x)=23320809) +2047 train 7.189279 (lr=1.3530e-04) (hash(x)=22022924) +2048 train 7.506248 (lr=1.3525e-04) (hash(x)=27960930) +2049 train 7.312279 (lr=1.3520e-04) (hash(x)=24899178) +2050 val loss 7.3432 +2050 val perplexity 1545.5887 +2050 train 7.226035 (lr=1.3514e-04) (hash(x)=24450711) +2051 train 7.162334 (lr=1.3509e-04) (hash(x)=23294980) +2052 train 7.087103 (lr=1.3503e-04) (hash(x)=23243665) +2053 train 6.906487 (lr=1.3498e-04) (hash(x)=21004461) +2054 train 7.283055 (lr=1.3492e-04) (hash(x)=24493583) +2055 train 7.203678 (lr=1.3487e-04) (hash(x)=22777085) +2056 train 7.148392 (lr=1.3482e-04) (hash(x)=25169889) +2057 train 7.813533 (lr=1.3476e-04) (hash(x)=28395880) +2058 train 7.733703 (lr=1.3471e-04) (hash(x)=29603726) +2059 train 7.360837 (lr=1.3465e-04) (hash(x)=26271115) +2060 train 7.312487 (lr=1.3460e-04) (hash(x)=25616212) +2061 train 7.426698 (lr=1.3454e-04) (hash(x)=26398325) +2062 train 7.124536 (lr=1.3449e-04) (hash(x)=23836586) +2063 train 6.997262 (lr=1.3443e-04) (hash(x)=21727744) +2064 train 7.270501 (lr=1.3438e-04) (hash(x)=25183195) +2065 train 7.391737 (lr=1.3433e-04) (hash(x)=27108132) +2066 train 7.061101 (lr=1.3427e-04) (hash(x)=20987812) +2067 train 7.410362 (lr=1.3422e-04) (hash(x)=22729318) +2068 train 7.221088 (lr=1.3416e-04) (hash(x)=23129709) +2069 train 7.770175 (lr=1.3411e-04) (hash(x)=32820084) +2070 train 7.837570 (lr=1.3405e-04) (hash(x)=33763489) +2071 train 7.268829 (lr=1.3400e-04) (hash(x)=20701998) +2072 train 7.468742 (lr=1.3394e-04) (hash(x)=27765988) +2073 train 7.200180 (lr=1.3389e-04) (hash(x)=24157446) +2074 train 7.161651 (lr=1.3384e-04) (hash(x)=22014978) +2075 train 7.680416 (lr=1.3378e-04) (hash(x)=27928398) +2076 train 7.528024 (lr=1.3373e-04) (hash(x)=27880142) +2077 train 7.879377 (lr=1.3367e-04) (hash(x)=34991795) +2078 train 7.391802 (lr=1.3362e-04) (hash(x)=25944128) +2079 train 7.129288 (lr=1.3356e-04) (hash(x)=20863982) +2080 train 7.529097 (lr=1.3351e-04) (hash(x)=28036097) +2081 train 7.567128 (lr=1.3345e-04) (hash(x)=25813615) +2082 train 7.012006 (lr=1.3340e-04) (hash(x)=22862316) +2083 train 7.089517 (lr=1.3334e-04) (hash(x)=22827054) +2084 train 7.170532 (lr=1.3329e-04) (hash(x)=23996531) +2085 train 7.287459 (lr=1.3323e-04) (hash(x)=25756087) +2086 train 7.322019 (lr=1.3318e-04) (hash(x)=23165889) +2087 train 7.489545 (lr=1.3313e-04) (hash(x)=25084926) +2088 train 7.320034 (lr=1.3307e-04) (hash(x)=26063862) +2089 train 7.366540 (lr=1.3302e-04) (hash(x)=27843638) +2090 train 7.664140 (lr=1.3296e-04) (hash(x)=27375554) +2091 train 7.380311 (lr=1.3291e-04) (hash(x)=25540961) +2092 train 7.110775 (lr=1.3285e-04) (hash(x)=22933785) +2093 train 7.280548 (lr=1.3280e-04) (hash(x)=23996956) +2094 train 6.997835 (lr=1.3274e-04) (hash(x)=22915854) +2095 train 7.252510 (lr=1.3269e-04) (hash(x)=24412897) +2096 train 7.302869 (lr=1.3263e-04) (hash(x)=25152336) +2097 train 7.615434 (lr=1.3258e-04) (hash(x)=29525589) +2098 train 7.440253 (lr=1.3252e-04) (hash(x)=26435656) +2099 train 7.325139 (lr=1.3247e-04) (hash(x)=26269869) +2100 val loss 7.2799 +2100 val perplexity 1450.8057 +2100 train 7.119467 (lr=1.3241e-04) (hash(x)=23856783) +2101 train 7.369012 (lr=1.3236e-04) (hash(x)=26039611) +2102 train 7.116676 (lr=1.3230e-04) (hash(x)=25048861) +2103 train 7.234077 (lr=1.3225e-04) (hash(x)=25434913) +2104 train 7.391188 (lr=1.3219e-04) (hash(x)=24203891) +2105 train 7.291948 (lr=1.3214e-04) (hash(x)=26016998) +2106 train 7.362808 (lr=1.3209e-04) (hash(x)=23986767) +2107 train 7.271816 (lr=1.3203e-04) (hash(x)=25157653) +2108 train 7.437047 (lr=1.3198e-04) (hash(x)=30193751) +2109 train 7.266056 (lr=1.3192e-04) (hash(x)=22630574) +2110 train 7.133469 (lr=1.3187e-04) (hash(x)=23475467) +2111 train 7.430205 (lr=1.3181e-04) (hash(x)=26302544) +2112 train 7.204536 (lr=1.3176e-04) (hash(x)=21276592) +2113 train 7.474065 (lr=1.3170e-04) (hash(x)=27566393) +2114 train 7.195909 (lr=1.3165e-04) (hash(x)=25028015) +2115 train 7.002900 (lr=1.3159e-04) (hash(x)=22010703) +2116 train 7.329685 (lr=1.3154e-04) (hash(x)=23711709) +2117 train 7.364868 (lr=1.3148e-04) (hash(x)=26105026) +2118 train 7.835440 (lr=1.3143e-04) (hash(x)=34433894) +2119 train 7.904418 (lr=1.3137e-04) (hash(x)=34976197) +2120 train 7.336442 (lr=1.3132e-04) (hash(x)=27690727) +2121 train 7.156592 (lr=1.3126e-04) (hash(x)=24368234) +2122 train 7.144223 (lr=1.3121e-04) (hash(x)=25095726) +2123 train 7.318841 (lr=1.3115e-04) (hash(x)=28248301) +2124 train 7.066600 (lr=1.3110e-04) (hash(x)=23322302) +2125 train 7.537313 (lr=1.3104e-04) (hash(x)=26416200) +2126 train 7.201385 (lr=1.3099e-04) (hash(x)=26577567) +2127 train 7.250651 (lr=1.3093e-04) (hash(x)=23870805) +2128 train 7.181622 (lr=1.3088e-04) (hash(x)=25440544) +2129 train 7.309258 (lr=1.3082e-04) (hash(x)=25795021) +2130 train 7.147513 (lr=1.3077e-04) (hash(x)=20896402) +2131 train 7.186100 (lr=1.3071e-04) (hash(x)=24457252) +2132 train 7.275406 (lr=1.3066e-04) (hash(x)=25926760) +2133 train 7.145071 (lr=1.3060e-04) (hash(x)=23503725) +2134 train 7.704587 (lr=1.3055e-04) (hash(x)=28728828) +2135 train 7.202937 (lr=1.3049e-04) (hash(x)=25041103) +2136 train 7.239876 (lr=1.3044e-04) (hash(x)=22863770) +2137 train 7.079354 (lr=1.3038e-04) (hash(x)=23037755) +2138 train 7.331816 (lr=1.3033e-04) (hash(x)=25848413) +2139 train 7.361366 (lr=1.3027e-04) (hash(x)=25998487) +2140 train 7.193523 (lr=1.3022e-04) (hash(x)=22754440) +2141 train 7.467809 (lr=1.3016e-04) (hash(x)=27705382) +2142 train 7.525405 (lr=1.3011e-04) (hash(x)=27629095) +2143 train 7.377412 (lr=1.3005e-04) (hash(x)=26041745) +2144 train 7.120558 (lr=1.3000e-04) (hash(x)=21909712) +2145 train 7.319080 (lr=1.2994e-04) (hash(x)=24353905) +2146 train 7.246688 (lr=1.2989e-04) (hash(x)=24482587) +2147 train 7.355794 (lr=1.2983e-04) (hash(x)=27249810) +2148 train 7.520105 (lr=1.2977e-04) (hash(x)=26709938) +2149 train 7.117057 (lr=1.2972e-04) (hash(x)=23831457) +2150 val loss 7.2592 +2150 val perplexity 1421.1139 +2150 train 7.524339 (lr=1.2966e-04) (hash(x)=29776243) +2151 train 6.993618 (lr=1.2961e-04) (hash(x)=24068619) +2152 train 7.204029 (lr=1.2955e-04) (hash(x)=22208671) +2153 train 7.360706 (lr=1.2950e-04) (hash(x)=26680905) +2154 train 7.240299 (lr=1.2944e-04) (hash(x)=23567808) +2155 train 7.492305 (lr=1.2939e-04) (hash(x)=26359528) +2156 train 7.271283 (lr=1.2933e-04) (hash(x)=23787652) +2157 train 7.538217 (lr=1.2928e-04) (hash(x)=28347177) +2158 train 7.233893 (lr=1.2922e-04) (hash(x)=25266519) +2159 train 7.161427 (lr=1.2917e-04) (hash(x)=25441262) +2160 train 7.107712 (lr=1.2911e-04) (hash(x)=23959943) +2161 train 7.341008 (lr=1.2906e-04) (hash(x)=27888093) +2162 train 7.230680 (lr=1.2900e-04) (hash(x)=25547833) +2163 train 7.174489 (lr=1.2895e-04) (hash(x)=24413659) +2164 train 8.563148 (lr=1.2889e-04) (hash(x)=34397626) +2165 train 7.086800 (lr=1.2884e-04) (hash(x)=21159323) +2166 train 7.286307 (lr=1.2878e-04) (hash(x)=25360269) +2167 train 7.352951 (lr=1.2872e-04) (hash(x)=29181867) +2168 train 7.165987 (lr=1.2867e-04) (hash(x)=22501613) +2169 train 7.254762 (lr=1.2861e-04) (hash(x)=26469077) +2170 train 7.228889 (lr=1.2856e-04) (hash(x)=26665118) +2171 train 7.892637 (lr=1.2850e-04) (hash(x)=31551575) +2172 train 7.187259 (lr=1.2845e-04) (hash(x)=24803935) +2173 train 7.052918 (lr=1.2839e-04) (hash(x)=20896465) +2174 train 7.550860 (lr=1.2834e-04) (hash(x)=25702284) +2175 train 7.504613 (lr=1.2828e-04) (hash(x)=27093757) +2176 train 7.266783 (lr=1.2823e-04) (hash(x)=26024255) +2177 train 7.450587 (lr=1.2817e-04) (hash(x)=26443521) +2178 train 7.369843 (lr=1.2812e-04) (hash(x)=25478467) +2179 train 7.226413 (lr=1.2806e-04) (hash(x)=23624298) +2180 train 7.300226 (lr=1.2801e-04) (hash(x)=27304178) +2181 train 7.045799 (lr=1.2795e-04) (hash(x)=23016570) +2182 train 7.038411 (lr=1.2789e-04) (hash(x)=21073756) +2183 train 7.145316 (lr=1.2784e-04) (hash(x)=25150275) +2184 train 6.925658 (lr=1.2778e-04) (hash(x)=21004187) +2185 train 7.217795 (lr=1.2773e-04) (hash(x)=25876062) +2186 train 7.136009 (lr=1.2767e-04) (hash(x)=24221275) +2187 train 7.433984 (lr=1.2762e-04) (hash(x)=26239886) +2188 train 7.141098 (lr=1.2756e-04) (hash(x)=23299261) +2189 train 7.564314 (lr=1.2751e-04) (hash(x)=31024703) +2190 train 7.684291 (lr=1.2745e-04) (hash(x)=30084774) +2191 train 7.985597 (lr=1.2740e-04) (hash(x)=33457102) +2192 train 7.175048 (lr=1.2734e-04) (hash(x)=22423723) +2193 train 7.212644 (lr=1.2728e-04) (hash(x)=21989055) +2194 train 7.221808 (lr=1.2723e-04) (hash(x)=23286499) +2195 train 7.182043 (lr=1.2717e-04) (hash(x)=17499738) +2196 train 7.209957 (lr=1.2712e-04) (hash(x)=25329557) +2197 train 7.088675 (lr=1.2706e-04) (hash(x)=24195578) +2198 train 7.359306 (lr=1.2701e-04) (hash(x)=26646383) +2199 train 7.258556 (lr=1.2695e-04) (hash(x)=25755322) +2200 val loss 7.2428 +2200 val perplexity 1397.9692 +2200 train 7.278056 (lr=1.2690e-04) (hash(x)=27592223) +2201 train 7.482545 (lr=1.2684e-04) (hash(x)=26164625) +2202 train 7.328388 (lr=1.2678e-04) (hash(x)=21856341) +2203 train 7.204319 (lr=1.2673e-04) (hash(x)=23722795) +2204 train 7.287606 (lr=1.2667e-04) (hash(x)=25409645) +2205 train 7.206132 (lr=1.2662e-04) (hash(x)=23415339) +2206 train 7.179691 (lr=1.2656e-04) (hash(x)=24147928) +2207 train 7.097267 (lr=1.2651e-04) (hash(x)=23630794) +2208 train 7.207250 (lr=1.2645e-04) (hash(x)=27361452) +2209 train 7.222970 (lr=1.2640e-04) (hash(x)=25632158) +2210 train 7.056539 (lr=1.2634e-04) (hash(x)=21159789) +2211 train 7.191537 (lr=1.2628e-04) (hash(x)=23374168) +2212 train 7.237865 (lr=1.2623e-04) (hash(x)=24844739) +2213 train 7.143118 (lr=1.2617e-04) (hash(x)=23461285) +2214 train 7.182768 (lr=1.2612e-04) (hash(x)=27958481) +2215 train 7.086134 (lr=1.2606e-04) (hash(x)=25167987) +2216 train 7.271656 (lr=1.2601e-04) (hash(x)=22873204) +2217 train 7.836240 (lr=1.2595e-04) (hash(x)=31038116) +2218 train 7.325426 (lr=1.2589e-04) (hash(x)=28883155) +2219 train 7.219751 (lr=1.2584e-04) (hash(x)=30941010) +2220 train 7.204866 (lr=1.2578e-04) (hash(x)=24947521) +2221 train 7.242109 (lr=1.2573e-04) (hash(x)=22703293) +2222 train 7.193374 (lr=1.2567e-04) (hash(x)=23976007) +2223 train 7.128190 (lr=1.2562e-04) (hash(x)=24043224) +2224 train 7.059322 (lr=1.2556e-04) (hash(x)=23981093) +2225 train 7.242046 (lr=1.2550e-04) (hash(x)=26445994) +2226 train 7.521158 (lr=1.2545e-04) (hash(x)=27252393) +2227 train 7.483070 (lr=1.2539e-04) (hash(x)=29736627) +2228 train 7.412926 (lr=1.2534e-04) (hash(x)=24698933) +2229 train 7.064222 (lr=1.2528e-04) (hash(x)=24357840) +2230 train 7.178730 (lr=1.2523e-04) (hash(x)=25384498) +2231 train 7.375523 (lr=1.2517e-04) (hash(x)=24665411) +2232 train 7.217085 (lr=1.2511e-04) (hash(x)=24646352) +2233 train 7.199994 (lr=1.2506e-04) (hash(x)=25670741) +2234 train 7.236276 (lr=1.2500e-04) (hash(x)=26648242) +2235 train 7.515485 (lr=1.2495e-04) (hash(x)=27916043) +2236 train 7.202680 (lr=1.2489e-04) (hash(x)=25963100) +2237 train 7.267280 (lr=1.2484e-04) (hash(x)=27357379) +2238 train 7.095812 (lr=1.2478e-04) (hash(x)=21852360) +2239 train 6.979849 (lr=1.2472e-04) (hash(x)=17321657) +2240 train 6.986914 (lr=1.2467e-04) (hash(x)=18446645) +2241 train 6.823198 (lr=1.2461e-04) (hash(x)=17550988) +2242 train 7.240238 (lr=1.2456e-04) (hash(x)=27052347) +2243 train 7.057920 (lr=1.2450e-04) (hash(x)=23829833) +2244 train 7.278890 (lr=1.2444e-04) (hash(x)=27267264) +2245 train 7.498769 (lr=1.2439e-04) (hash(x)=24673611) +2246 train 7.440582 (lr=1.2433e-04) (hash(x)=25248507) +2247 train 7.716508 (lr=1.2428e-04) (hash(x)=27932591) +2248 train 7.539722 (lr=1.2422e-04) (hash(x)=26078877) +2249 train 7.592773 (lr=1.2417e-04) (hash(x)=26067367) +2250 val loss 7.2291 +2250 val perplexity 1378.9818 +2250 train 7.597740 (lr=1.2411e-04) (hash(x)=29143527) +2251 train 7.561662 (lr=1.2405e-04) (hash(x)=28206079) +2252 train 8.095336 (lr=1.2400e-04) (hash(x)=28894494) +2253 train 7.616188 (lr=1.2394e-04) (hash(x)=27977422) +2254 train 7.262998 (lr=1.2389e-04) (hash(x)=26446420) +2255 train 7.446836 (lr=1.2383e-04) (hash(x)=29447954) +2256 train 7.305061 (lr=1.2377e-04) (hash(x)=22181789) +2257 train 7.293356 (lr=1.2372e-04) (hash(x)=24976337) +2258 train 7.232510 (lr=1.2366e-04) (hash(x)=23277532) +2259 train 7.366216 (lr=1.2361e-04) (hash(x)=25935364) +2260 train 7.524576 (lr=1.2355e-04) (hash(x)=26988889) +2261 train 7.296563 (lr=1.2350e-04) (hash(x)=26887303) +2262 train 7.249759 (lr=1.2344e-04) (hash(x)=25021426) +2263 train 7.203773 (lr=1.2338e-04) (hash(x)=24621816) +2264 train 7.084293 (lr=1.2333e-04) (hash(x)=22132007) +2265 train 7.013645 (lr=1.2327e-04) (hash(x)=22648602) +2266 train 7.343634 (lr=1.2322e-04) (hash(x)=23132242) +2267 train 7.353754 (lr=1.2316e-04) (hash(x)=24070405) +2268 train 6.984904 (lr=1.2310e-04) (hash(x)=21412906) +2269 train 7.657362 (lr=1.2305e-04) (hash(x)=27547292) +2270 train 7.422939 (lr=1.2299e-04) (hash(x)=27740500) +2271 train 7.132447 (lr=1.2294e-04) (hash(x)=24682294) +2272 train 7.572864 (lr=1.2288e-04) (hash(x)=27969424) +2273 train 7.261708 (lr=1.2282e-04) (hash(x)=22172182) +2274 train 7.260063 (lr=1.2277e-04) (hash(x)=26485905) +2275 train 7.123294 (lr=1.2271e-04) (hash(x)=24050209) +2276 train 7.333040 (lr=1.2266e-04) (hash(x)=28802650) +2277 train 7.082608 (lr=1.2260e-04) (hash(x)=23644616) +2278 train 7.263341 (lr=1.2254e-04) (hash(x)=25409768) +2279 train 7.447769 (lr=1.2249e-04) (hash(x)=28057095) +2280 train 7.869972 (lr=1.2243e-04) (hash(x)=31689723) +2281 train 7.062637 (lr=1.2238e-04) (hash(x)=22252427) +2282 train 7.312992 (lr=1.2232e-04) (hash(x)=24142092) +2283 train 7.228340 (lr=1.2226e-04) (hash(x)=22523232) +2284 train 7.410745 (lr=1.2221e-04) (hash(x)=26017294) +2285 train 7.283575 (lr=1.2215e-04) (hash(x)=25025388) +2286 train 7.058339 (lr=1.2210e-04) (hash(x)=23819479) +2287 train 7.241606 (lr=1.2204e-04) (hash(x)=24547536) +2288 train 7.016077 (lr=1.2198e-04) (hash(x)=22622789) +2289 train 6.986823 (lr=1.2193e-04) (hash(x)=23874051) +2290 train 7.344247 (lr=1.2187e-04) (hash(x)=25015641) +2291 train 7.200745 (lr=1.2182e-04) (hash(x)=24978712) +2292 train 7.292519 (lr=1.2176e-04) (hash(x)=25311986) +2293 train 7.060912 (lr=1.2170e-04) (hash(x)=24298295) +2294 train 7.158491 (lr=1.2165e-04) (hash(x)=26481527) +2295 train 6.870995 (lr=1.2159e-04) (hash(x)=18987545) +2296 train 7.107625 (lr=1.2153e-04) (hash(x)=24617990) +2297 train 7.153272 (lr=1.2148e-04) (hash(x)=23903200) +2298 train 7.426502 (lr=1.2142e-04) (hash(x)=26278697) +2299 train 7.195631 (lr=1.2137e-04) (hash(x)=24092784) +2300 val loss 7.2276 +2300 val perplexity 1376.8925 +2300 train 7.146332 (lr=1.2131e-04) (hash(x)=22894919) +2301 train 7.208791 (lr=1.2125e-04) (hash(x)=24253964) +2302 train 7.177776 (lr=1.2120e-04) (hash(x)=23750610) +2303 train 7.193581 (lr=1.2114e-04) (hash(x)=26745063) +2304 train 7.012735 (lr=1.2109e-04) (hash(x)=21407001) +2305 train 7.391110 (lr=1.2103e-04) (hash(x)=26680082) +2306 train 7.303025 (lr=1.2097e-04) (hash(x)=26722122) +2307 train 7.153960 (lr=1.2092e-04) (hash(x)=22539112) +2308 train 6.946476 (lr=1.2086e-04) (hash(x)=19927356) +2309 train 7.041564 (lr=1.2081e-04) (hash(x)=21431267) +2310 train 6.978972 (lr=1.2075e-04) (hash(x)=21073487) +2311 train 7.027333 (lr=1.2069e-04) (hash(x)=21447406) +2312 train 7.003120 (lr=1.2064e-04) (hash(x)=22667253) +2313 train 6.984107 (lr=1.2058e-04) (hash(x)=20849089) +2314 train 6.975406 (lr=1.2052e-04) (hash(x)=19168351) +2315 train 7.017766 (lr=1.2047e-04) (hash(x)=21082139) +2316 train 7.010915 (lr=1.2041e-04) (hash(x)=21493530) +2317 train 6.944753 (lr=1.2036e-04) (hash(x)=19506447) +2318 train 7.049988 (lr=1.2030e-04) (hash(x)=23128797) +2319 train 7.126140 (lr=1.2024e-04) (hash(x)=24650655) +2320 train 6.890987 (lr=1.2019e-04) (hash(x)=21833080) +2321 train 7.423420 (lr=1.2013e-04) (hash(x)=26355512) +2322 train 7.618811 (lr=1.2007e-04) (hash(x)=26746363) +2323 train 7.015409 (lr=1.2002e-04) (hash(x)=22130721) +2324 train 7.368816 (lr=1.1996e-04) (hash(x)=28301752) +2325 train 7.204659 (lr=1.1991e-04) (hash(x)=26444359) +2326 train 7.542480 (lr=1.1985e-04) (hash(x)=24836130) +2327 train 7.946664 (lr=1.1979e-04) (hash(x)=26519976) +2328 train 9.283024 (lr=1.1974e-04) (hash(x)=35558906) +2329 train 7.628541 (lr=1.1968e-04) (hash(x)=30877729) +2330 train 7.481146 (lr=1.1963e-04) (hash(x)=28028485) +2331 train 7.582540 (lr=1.1957e-04) (hash(x)=25582440) +2332 train 7.899724 (lr=1.1951e-04) (hash(x)=29402491) +2333 train 7.247270 (lr=1.1946e-04) (hash(x)=25200284) +2334 train 7.264717 (lr=1.1940e-04) (hash(x)=26288480) +2335 train 7.001298 (lr=1.1934e-04) (hash(x)=20106514) +2336 train 7.031409 (lr=1.1929e-04) (hash(x)=22522123) +2337 train 7.052770 (lr=1.1923e-04) (hash(x)=23362041) +2338 train 7.171432 (lr=1.1918e-04) (hash(x)=26003099) +2339 train 7.187314 (lr=1.1912e-04) (hash(x)=25695510) +2340 train 7.181535 (lr=1.1906e-04) (hash(x)=27225904) +2341 train 6.935383 (lr=1.1901e-04) (hash(x)=21573008) +2342 train 7.401212 (lr=1.1895e-04) (hash(x)=21386628) +2343 train 7.200909 (lr=1.1889e-04) (hash(x)=20117808) +2344 train 7.324049 (lr=1.1884e-04) (hash(x)=21592790) +2345 train 7.240594 (lr=1.1878e-04) (hash(x)=19909192) +2346 train 7.353262 (lr=1.1872e-04) (hash(x)=22529262) +2347 train 7.365604 (lr=1.1867e-04) (hash(x)=24501900) +2348 train 7.147582 (lr=1.1861e-04) (hash(x)=25912171) +2349 train 7.267132 (lr=1.1856e-04) (hash(x)=25606665) +2350 val loss 7.2407 +2350 val perplexity 1395.0538 +2350 train 7.190338 (lr=1.1850e-04) (hash(x)=24487351) +2351 train 7.445334 (lr=1.1844e-04) (hash(x)=25510334) +2352 train 7.299257 (lr=1.1839e-04) (hash(x)=25357989) +2353 train 6.987865 (lr=1.1833e-04) (hash(x)=24656801) +2354 train 7.056830 (lr=1.1827e-04) (hash(x)=23312772) +2355 train 6.900327 (lr=1.1822e-04) (hash(x)=22099158) +2356 train 7.001520 (lr=1.1816e-04) (hash(x)=26507898) +2357 train 7.309671 (lr=1.1811e-04) (hash(x)=28351614) +2358 train 7.349455 (lr=1.1805e-04) (hash(x)=27489567) +2359 train 7.321847 (lr=1.1799e-04) (hash(x)=25749120) +2360 train 7.624931 (lr=1.1794e-04) (hash(x)=31711338) +2361 train 7.702178 (lr=1.1788e-04) (hash(x)=29645018) +2362 train 7.823733 (lr=1.1782e-04) (hash(x)=29713268) +2363 train 6.918579 (lr=1.1777e-04) (hash(x)=21720691) +2364 train 7.044391 (lr=1.1771e-04) (hash(x)=24316633) +2365 train 6.983174 (lr=1.1765e-04) (hash(x)=21597124) +2366 train 7.006705 (lr=1.1760e-04) (hash(x)=22520345) +2367 train 7.029340 (lr=1.1754e-04) (hash(x)=24357241) +2368 train 7.169319 (lr=1.1749e-04) (hash(x)=24085450) +2369 train 7.084177 (lr=1.1743e-04) (hash(x)=25136495) +2370 train 7.604350 (lr=1.1737e-04) (hash(x)=26073986) +2371 train 7.524021 (lr=1.1732e-04) (hash(x)=28911272) +2372 train 7.293542 (lr=1.1726e-04) (hash(x)=26667356) +2373 train 7.116348 (lr=1.1720e-04) (hash(x)=25225894) +2374 train 7.136504 (lr=1.1715e-04) (hash(x)=24404081) +2375 train 7.223837 (lr=1.1709e-04) (hash(x)=25584945) +2376 train 7.054599 (lr=1.1703e-04) (hash(x)=23831571) +2377 train 7.058730 (lr=1.1698e-04) (hash(x)=23521916) +2378 train 7.086220 (lr=1.1692e-04) (hash(x)=25318634) +2379 train 6.950208 (lr=1.1687e-04) (hash(x)=21847287) +2380 train 7.355430 (lr=1.1681e-04) (hash(x)=23877060) +2381 train 7.112457 (lr=1.1675e-04) (hash(x)=24069020) +2382 train 6.903724 (lr=1.1670e-04) (hash(x)=21724290) +2383 train 7.166065 (lr=1.1664e-04) (hash(x)=25198897) +2384 train 7.018491 (lr=1.1658e-04) (hash(x)=24109958) +2385 train 6.883173 (lr=1.1653e-04) (hash(x)=20122390) +2386 train 7.158623 (lr=1.1647e-04) (hash(x)=24062305) +2387 train 6.936641 (lr=1.1641e-04) (hash(x)=22436833) +2388 train 7.277940 (lr=1.1636e-04) (hash(x)=26013214) +2389 train 7.678865 (lr=1.1630e-04) (hash(x)=27691436) +2390 train 7.744350 (lr=1.1624e-04) (hash(x)=30802878) +2391 train 6.899847 (lr=1.1619e-04) (hash(x)=23475891) +2392 train 6.897672 (lr=1.1613e-04) (hash(x)=23118133) +2393 train 6.825157 (lr=1.1608e-04) (hash(x)=21469159) +2394 train 7.217726 (lr=1.1602e-04) (hash(x)=26444484) +2395 train 7.073097 (lr=1.1596e-04) (hash(x)=25083992) +2396 train 7.356419 (lr=1.1591e-04) (hash(x)=23461229) +2397 train 7.299864 (lr=1.1585e-04) (hash(x)=20441653) +2398 train 7.383234 (lr=1.1579e-04) (hash(x)=28024211) +2399 train 7.218852 (lr=1.1574e-04) (hash(x)=23644804) +2400 val loss 7.2417 +2400 val perplexity 1396.4462 +2400 train 7.022385 (lr=1.1568e-04) (hash(x)=26685301) +2401 train 6.871150 (lr=1.1562e-04) (hash(x)=20820913) +2402 train 7.052536 (lr=1.1557e-04) (hash(x)=22178190) +2403 train 7.624875 (lr=1.1551e-04) (hash(x)=31377168) +2404 train 7.831872 (lr=1.1545e-04) (hash(x)=33795307) +2405 train 7.986974 (lr=1.1540e-04) (hash(x)=34450341) +2406 train 7.160749 (lr=1.1534e-04) (hash(x)=25834183) +2407 train 7.397115 (lr=1.1529e-04) (hash(x)=25629584) +2408 train 7.115010 (lr=1.1523e-04) (hash(x)=25080123) +2409 train 6.993703 (lr=1.1517e-04) (hash(x)=21975628) +2410 train 7.594652 (lr=1.1512e-04) (hash(x)=27430197) +2411 train 7.764465 (lr=1.1506e-04) (hash(x)=29285135) +2412 train 7.473119 (lr=1.1500e-04) (hash(x)=24640105) +2413 train 7.543820 (lr=1.1495e-04) (hash(x)=29628864) +2414 train 7.753398 (lr=1.1489e-04) (hash(x)=30096444) +2415 train 7.580289 (lr=1.1483e-04) (hash(x)=29797280) +2416 train 6.968309 (lr=1.1478e-04) (hash(x)=22686143) +2417 train 7.548668 (lr=1.1472e-04) (hash(x)=28346842) +2418 train 7.541878 (lr=1.1466e-04) (hash(x)=28167937) +2419 train 7.766384 (lr=1.1461e-04) (hash(x)=33122326) +2420 train 7.805093 (lr=1.1455e-04) (hash(x)=33044913) +2421 train 7.620206 (lr=1.1449e-04) (hash(x)=31250981) +2422 train 7.830292 (lr=1.1444e-04) (hash(x)=29827111) +2423 train 7.737693 (lr=1.1438e-04) (hash(x)=30026394) +2424 train 7.764392 (lr=1.1433e-04) (hash(x)=26998238) +2425 train 7.690091 (lr=1.1427e-04) (hash(x)=24850684) +2426 train 8.087525 (lr=1.1421e-04) (hash(x)=36659853) +2427 train 7.936911 (lr=1.1416e-04) (hash(x)=34353164) +2428 train 7.209621 (lr=1.1410e-04) (hash(x)=23630644) +2429 train 7.222511 (lr=1.1404e-04) (hash(x)=24528186) +2430 train 7.089932 (lr=1.1399e-04) (hash(x)=22665222) +2431 train 7.233837 (lr=1.1393e-04) (hash(x)=26594177) +2432 train 7.587867 (lr=1.1387e-04) (hash(x)=29300546) +2433 train 6.989210 (lr=1.1382e-04) (hash(x)=21331715) +2434 train 7.267580 (lr=1.1376e-04) (hash(x)=26290885) +2435 train 7.164792 (lr=1.1370e-04) (hash(x)=25554738) +2436 train 7.435722 (lr=1.1365e-04) (hash(x)=26744311) +2437 train 7.371789 (lr=1.1359e-04) (hash(x)=26872344) +2438 train 7.422863 (lr=1.1353e-04) (hash(x)=27636081) +2439 train 7.223840 (lr=1.1348e-04) (hash(x)=23766256) +2440 train 7.353005 (lr=1.1342e-04) (hash(x)=24434438) +2441 train 7.157817 (lr=1.1336e-04) (hash(x)=22992618) +2442 train 7.023425 (lr=1.1331e-04) (hash(x)=22393467) +2443 train 7.294916 (lr=1.1325e-04) (hash(x)=26853444) +2444 train 7.236938 (lr=1.1319e-04) (hash(x)=25101020) +2445 train 7.121067 (lr=1.1314e-04) (hash(x)=24705456) +2446 train 7.449155 (lr=1.1308e-04) (hash(x)=26798611) +2447 train 7.102958 (lr=1.1303e-04) (hash(x)=24250150) +2448 train 7.141026 (lr=1.1297e-04) (hash(x)=24494331) +2449 train 7.184613 (lr=1.1291e-04) (hash(x)=27579257) +2450 val loss 7.2274 +2450 val perplexity 1376.6272 +2450 train 6.932630 (lr=1.1286e-04) (hash(x)=22377407) +2451 train 7.236723 (lr=1.1280e-04) (hash(x)=26289588) +2452 train 7.144348 (lr=1.1274e-04) (hash(x)=25871900) +2453 train 7.037457 (lr=1.1269e-04) (hash(x)=23437197) +2454 train 7.318466 (lr=1.1263e-04) (hash(x)=23557786) +2455 train 7.180861 (lr=1.1257e-04) (hash(x)=26108817) +2456 train 7.130498 (lr=1.1252e-04) (hash(x)=26440482) +2457 train 7.142075 (lr=1.1246e-04) (hash(x)=24583191) +2458 train 7.142108 (lr=1.1240e-04) (hash(x)=23756440) +2459 train 7.003882 (lr=1.1235e-04) (hash(x)=23814987) +2460 train 7.399384 (lr=1.1229e-04) (hash(x)=28508433) +2461 train 7.061274 (lr=1.1223e-04) (hash(x)=25692442) +2462 train 7.022183 (lr=1.1218e-04) (hash(x)=24699197) +2463 train 6.708691 (lr=1.1212e-04) (hash(x)=18582688) +2464 train 7.045743 (lr=1.1206e-04) (hash(x)=23266625) +2465 train 7.389975 (lr=1.1201e-04) (hash(x)=26565489) +2466 train 6.852931 (lr=1.1195e-04) (hash(x)=21686599) +2467 train 7.150085 (lr=1.1189e-04) (hash(x)=25558792) +2468 train 6.908693 (lr=1.1184e-04) (hash(x)=25110035) +2469 train 7.295907 (lr=1.1178e-04) (hash(x)=26263661) +2470 train 7.013082 (lr=1.1172e-04) (hash(x)=22282189) +2471 train 7.008319 (lr=1.1167e-04) (hash(x)=23272705) +2472 train 7.130285 (lr=1.1161e-04) (hash(x)=25300067) +2473 train 7.310152 (lr=1.1156e-04) (hash(x)=26802369) +2474 train 7.003635 (lr=1.1150e-04) (hash(x)=24646471) +2475 train 6.976592 (lr=1.1144e-04) (hash(x)=24709241) +2476 train 7.060765 (lr=1.1139e-04) (hash(x)=26747197) +2477 train 7.120313 (lr=1.1133e-04) (hash(x)=25201108) +2478 train 7.262793 (lr=1.1127e-04) (hash(x)=24962427) +2479 train 7.061469 (lr=1.1122e-04) (hash(x)=24793412) +2480 train 7.147278 (lr=1.1116e-04) (hash(x)=24452301) +2481 train 7.146366 (lr=1.1110e-04) (hash(x)=25177251) +2482 train 7.058395 (lr=1.1105e-04) (hash(x)=25801499) +2483 train 7.235471 (lr=1.1099e-04) (hash(x)=27256707) +2484 train 7.519875 (lr=1.1093e-04) (hash(x)=25303237) +2485 train 7.059302 (lr=1.1088e-04) (hash(x)=21641481) +2486 train 7.014662 (lr=1.1082e-04) (hash(x)=23818831) +2487 train 6.794998 (lr=1.1076e-04) (hash(x)=19280989) +2488 train 7.192244 (lr=1.1071e-04) (hash(x)=24075167) +2489 train 7.194531 (lr=1.1065e-04) (hash(x)=26651546) +2490 train 7.141135 (lr=1.1059e-04) (hash(x)=25367186) +2491 train 7.096426 (lr=1.1054e-04) (hash(x)=26508642) +2492 train 7.199098 (lr=1.1048e-04) (hash(x)=25294182) +2493 train 7.065090 (lr=1.1042e-04) (hash(x)=23916886) +2494 train 6.960317 (lr=1.1037e-04) (hash(x)=21189910) +2495 train 7.046710 (lr=1.1031e-04) (hash(x)=22751150) +2496 train 7.450471 (lr=1.1025e-04) (hash(x)=26608502) +2497 train 7.877042 (lr=1.1020e-04) (hash(x)=25372010) +2498 train 7.088614 (lr=1.1014e-04) (hash(x)=22006251) +2499 train 7.075455 (lr=1.1008e-04) (hash(x)=23880160) +2500 val loss 7.2130 +2500 val perplexity 1356.9374 +2500 train 6.991408 (lr=1.1003e-04) (hash(x)=23225337) +2501 train 7.180233 (lr=1.0997e-04) (hash(x)=24932950) +2502 train 6.894202 (lr=1.0992e-04) (hash(x)=20022340) +2503 train 7.307495 (lr=1.0986e-04) (hash(x)=23537942) +2504 train 7.176225 (lr=1.0980e-04) (hash(x)=24884288) +2505 train 6.819216 (lr=1.0975e-04) (hash(x)=21296580) +2506 train 7.075642 (lr=1.0969e-04) (hash(x)=23001455) +2507 train 7.401685 (lr=1.0963e-04) (hash(x)=26975313) +2508 train 7.378599 (lr=1.0958e-04) (hash(x)=26029962) +2509 train 7.083914 (lr=1.0952e-04) (hash(x)=24302204) +2510 train 6.785884 (lr=1.0946e-04) (hash(x)=22997203) +2511 train 6.918187 (lr=1.0941e-04) (hash(x)=23748375) +2512 train 7.157960 (lr=1.0935e-04) (hash(x)=24453191) +2513 train 6.829801 (lr=1.0929e-04) (hash(x)=22026776) +2514 train 6.932068 (lr=1.0924e-04) (hash(x)=19934168) +2515 train 7.257649 (lr=1.0918e-04) (hash(x)=25541754) +2516 train 7.624139 (lr=1.0912e-04) (hash(x)=26604471) +2517 train 7.645132 (lr=1.0907e-04) (hash(x)=27900386) +2518 train 7.572855 (lr=1.0901e-04) (hash(x)=26403431) +2519 train 7.605829 (lr=1.0895e-04) (hash(x)=27413825) +2520 train 7.657579 (lr=1.0890e-04) (hash(x)=28332637) +2521 train 7.450162 (lr=1.0884e-04) (hash(x)=27223027) +2522 train 7.465088 (lr=1.0878e-04) (hash(x)=23843387) +2523 train 7.463480 (lr=1.0873e-04) (hash(x)=27075951) +2524 train 7.623798 (lr=1.0867e-04) (hash(x)=29300154) +2525 train 7.268663 (lr=1.0861e-04) (hash(x)=28100582) +2526 train 7.337766 (lr=1.0856e-04) (hash(x)=28051084) +2527 train 7.091960 (lr=1.0850e-04) (hash(x)=21682445) +2528 train 7.249504 (lr=1.0844e-04) (hash(x)=24062589) +2529 train 7.456163 (lr=1.0839e-04) (hash(x)=29616079) +2530 train 7.354292 (lr=1.0833e-04) (hash(x)=25170523) +2531 train 6.948558 (lr=1.0828e-04) (hash(x)=23361504) +2532 train 7.142163 (lr=1.0822e-04) (hash(x)=24444462) +2533 train 7.158063 (lr=1.0816e-04) (hash(x)=24035993) +2534 train 7.085618 (lr=1.0811e-04) (hash(x)=24696651) +2535 train 7.122854 (lr=1.0805e-04) (hash(x)=22040184) +2536 train 7.025471 (lr=1.0799e-04) (hash(x)=27400103) +2537 train 7.387544 (lr=1.0794e-04) (hash(x)=27383080) +2538 train 7.149997 (lr=1.0788e-04) (hash(x)=24212212) +2539 train 7.029866 (lr=1.0782e-04) (hash(x)=23727731) +2540 train 7.191463 (lr=1.0777e-04) (hash(x)=24149487) +2541 train 6.965305 (lr=1.0771e-04) (hash(x)=23794649) +2542 train 7.135278 (lr=1.0765e-04) (hash(x)=26147774) +2543 train 7.243439 (lr=1.0760e-04) (hash(x)=24463229) +2544 train 7.314536 (lr=1.0754e-04) (hash(x)=26361238) +2545 train 6.970526 (lr=1.0748e-04) (hash(x)=18891545) +2546 train 7.519467 (lr=1.0743e-04) (hash(x)=30380438) +2547 train 7.726566 (lr=1.0737e-04) (hash(x)=32663792) +2548 train 7.127862 (lr=1.0731e-04) (hash(x)=25175499) +2549 train 7.330789 (lr=1.0726e-04) (hash(x)=26702407) +2550 val loss 7.2154 +2550 val perplexity 1360.2257 +2550 train 7.125757 (lr=1.0720e-04) (hash(x)=24578061) +2551 train 7.137951 (lr=1.0714e-04) (hash(x)=24091954) +2552 train 7.162526 (lr=1.0709e-04) (hash(x)=23041778) +2553 train 6.956511 (lr=1.0703e-04) (hash(x)=23686239) +2554 train 7.084430 (lr=1.0697e-04) (hash(x)=22745355) +2555 train 7.118511 (lr=1.0692e-04) (hash(x)=23599013) +2556 train 7.020276 (lr=1.0686e-04) (hash(x)=26033088) +2557 train 7.105844 (lr=1.0681e-04) (hash(x)=21634218) +2558 train 7.027371 (lr=1.0675e-04) (hash(x)=20985281) +2559 train 7.289726 (lr=1.0669e-04) (hash(x)=26670219) +2560 train 7.073312 (lr=1.0664e-04) (hash(x)=26499936) +2561 train 7.182243 (lr=1.0658e-04) (hash(x)=23547908) +2562 train 7.054155 (lr=1.0652e-04) (hash(x)=22306373) +2563 train 7.180234 (lr=1.0647e-04) (hash(x)=24380893) +2564 train 7.056233 (lr=1.0641e-04) (hash(x)=23726190) +2565 train 7.144134 (lr=1.0635e-04) (hash(x)=26967512) +2566 train 7.196758 (lr=1.0630e-04) (hash(x)=23414576) +2567 train 7.445224 (lr=1.0624e-04) (hash(x)=25558986) +2568 train 7.316361 (lr=1.0618e-04) (hash(x)=27057505) +2569 train 7.310021 (lr=1.0613e-04) (hash(x)=26048135) +2570 train 7.262126 (lr=1.0607e-04) (hash(x)=26991032) +2571 train 7.313545 (lr=1.0601e-04) (hash(x)=25729492) +2572 train 6.862068 (lr=1.0596e-04) (hash(x)=20611723) +2573 train 6.991584 (lr=1.0590e-04) (hash(x)=24563606) +2574 train 7.067623 (lr=1.0584e-04) (hash(x)=23330043) +2575 train 7.118486 (lr=1.0579e-04) (hash(x)=19218943) +2576 train 7.453172 (lr=1.0573e-04) (hash(x)=20985122) +2577 train 7.068074 (lr=1.0567e-04) (hash(x)=24133609) +2578 train 7.399095 (lr=1.0562e-04) (hash(x)=28368610) +2579 train 7.104953 (lr=1.0556e-04) (hash(x)=23952206) +2580 train 7.028366 (lr=1.0551e-04) (hash(x)=23068957) +2581 train 7.147237 (lr=1.0545e-04) (hash(x)=25365277) +2582 train 7.443274 (lr=1.0539e-04) (hash(x)=24721184) +2583 train 7.154583 (lr=1.0534e-04) (hash(x)=24551402) +2584 train 6.899057 (lr=1.0528e-04) (hash(x)=20469327) +2585 train 7.303675 (lr=1.0522e-04) (hash(x)=24966478) +2586 train 7.032965 (lr=1.0517e-04) (hash(x)=18626184) +2587 train 7.070334 (lr=1.0511e-04) (hash(x)=24007642) +2588 train 7.025229 (lr=1.0505e-04) (hash(x)=23521875) +2589 train 7.235273 (lr=1.0500e-04) (hash(x)=25204207) +2590 train 7.036550 (lr=1.0494e-04) (hash(x)=25449801) +2591 train 7.266262 (lr=1.0488e-04) (hash(x)=25229281) +2592 train 7.076798 (lr=1.0483e-04) (hash(x)=23202696) +2593 train 6.951755 (lr=1.0477e-04) (hash(x)=22435944) +2594 train 6.967328 (lr=1.0471e-04) (hash(x)=20787439) +2595 train 6.559270 (lr=1.0466e-04) (hash(x)=18214283) +2596 train 6.769575 (lr=1.0460e-04) (hash(x)=20851477) +2597 train 6.729810 (lr=1.0455e-04) (hash(x)=20609675) +2598 train 6.856371 (lr=1.0449e-04) (hash(x)=20061218) +2599 train 6.903139 (lr=1.0443e-04) (hash(x)=21251127) +2600 val loss 7.2032 +2600 val perplexity 1343.7800 +2600 train 7.409149 (lr=1.0438e-04) (hash(x)=30948038) +2601 train 7.641306 (lr=1.0432e-04) (hash(x)=32279160) +2602 train 7.303366 (lr=1.0426e-04) (hash(x)=26607151) +2603 train 7.168637 (lr=1.0421e-04) (hash(x)=25097619) +2604 train 6.725616 (lr=1.0415e-04) (hash(x)=20892421) +2605 train 6.924606 (lr=1.0409e-04) (hash(x)=22212821) +2606 train 7.239194 (lr=1.0404e-04) (hash(x)=24720588) +2607 train 7.250048 (lr=1.0398e-04) (hash(x)=25800857) +2608 train 7.055244 (lr=1.0392e-04) (hash(x)=22901279) +2609 train 6.927567 (lr=1.0387e-04) (hash(x)=20921910) +2610 train 7.145473 (lr=1.0381e-04) (hash(x)=24846267) +2611 train 7.020809 (lr=1.0376e-04) (hash(x)=22918428) +2612 train 6.974812 (lr=1.0370e-04) (hash(x)=22805901) +2613 train 7.121680 (lr=1.0364e-04) (hash(x)=24345816) +2614 train 6.990854 (lr=1.0359e-04) (hash(x)=22962012) +2615 train 7.254408 (lr=1.0353e-04) (hash(x)=25836189) +2616 train 7.291272 (lr=1.0347e-04) (hash(x)=27922916) +2617 train 7.021300 (lr=1.0342e-04) (hash(x)=21697866) +2618 train 7.010198 (lr=1.0336e-04) (hash(x)=24283369) +2619 train 6.914517 (lr=1.0330e-04) (hash(x)=24504567) +2620 train 7.024674 (lr=1.0325e-04) (hash(x)=25557725) +2621 train 7.044109 (lr=1.0319e-04) (hash(x)=23135849) +2622 train 7.014408 (lr=1.0313e-04) (hash(x)=22888908) +2623 train 7.197855 (lr=1.0308e-04) (hash(x)=25999255) +2624 train 7.078842 (lr=1.0302e-04) (hash(x)=24446851) +2625 train 6.798505 (lr=1.0297e-04) (hash(x)=21137520) +2626 train 7.137570 (lr=1.0291e-04) (hash(x)=26245754) +2627 train 7.459302 (lr=1.0285e-04) (hash(x)=27308968) +2628 train 7.219986 (lr=1.0280e-04) (hash(x)=23961169) +2629 train 7.164972 (lr=1.0274e-04) (hash(x)=25924731) +2630 train 7.240833 (lr=1.0268e-04) (hash(x)=25782315) +2631 train 7.272516 (lr=1.0263e-04) (hash(x)=20149394) +2632 train 7.357873 (lr=1.0257e-04) (hash(x)=23801981) +2633 train 7.152792 (lr=1.0251e-04) (hash(x)=23830286) +2634 train 7.083138 (lr=1.0246e-04) (hash(x)=25325236) +2635 train 7.091211 (lr=1.0240e-04) (hash(x)=24498556) +2636 train 7.026100 (lr=1.0235e-04) (hash(x)=23693078) +2637 train 7.204004 (lr=1.0229e-04) (hash(x)=25484922) +2638 train 6.884106 (lr=1.0223e-04) (hash(x)=22645025) +2639 train 6.857882 (lr=1.0218e-04) (hash(x)=21999338) +2640 train 7.089731 (lr=1.0212e-04) (hash(x)=21758019) +2641 train 7.033823 (lr=1.0206e-04) (hash(x)=24064168) +2642 train 7.063499 (lr=1.0201e-04) (hash(x)=26847292) +2643 train 6.899045 (lr=1.0195e-04) (hash(x)=23280568) +2644 train 6.897546 (lr=1.0189e-04) (hash(x)=21749161) +2645 train 7.565166 (lr=1.0184e-04) (hash(x)=30082352) +2646 train 7.402505 (lr=1.0178e-04) (hash(x)=28334297) +2647 train 7.562306 (lr=1.0173e-04) (hash(x)=27611302) +2648 train 7.931721 (lr=1.0167e-04) (hash(x)=31007436) +2649 train 6.874591 (lr=1.0161e-04) (hash(x)=22356183) +2650 val loss 7.2205 +2650 val perplexity 1367.1588 +2650 train 6.937912 (lr=1.0156e-04) (hash(x)=23071731) +2651 train 6.970105 (lr=1.0150e-04) (hash(x)=23982308) +2652 train 7.297099 (lr=1.0144e-04) (hash(x)=25673823) +2653 train 7.055547 (lr=1.0139e-04) (hash(x)=22973788) +2654 train 7.227604 (lr=1.0133e-04) (hash(x)=25386647) +2655 train 6.970677 (lr=1.0128e-04) (hash(x)=22778356) +2656 train 7.163686 (lr=1.0122e-04) (hash(x)=26669130) +2657 train 6.894702 (lr=1.0116e-04) (hash(x)=23542930) +2658 train 7.026738 (lr=1.0111e-04) (hash(x)=23307871) +2659 train 6.997864 (lr=1.0105e-04) (hash(x)=23467046) +2660 train 7.156261 (lr=1.0099e-04) (hash(x)=24728872) +2661 train 7.766335 (lr=1.0094e-04) (hash(x)=29719902) +2662 train 7.073440 (lr=1.0088e-04) (hash(x)=25114165) +2663 train 6.985969 (lr=1.0082e-04) (hash(x)=24195959) +2664 train 7.211459 (lr=1.0077e-04) (hash(x)=26938509) +2665 train 7.370064 (lr=1.0071e-04) (hash(x)=27168434) +2666 train 7.519571 (lr=1.0066e-04) (hash(x)=27488221) +2667 train 8.256703 (lr=1.0060e-04) (hash(x)=32710438) +2668 train 7.299870 (lr=1.0054e-04) (hash(x)=25073185) +2669 train 7.314610 (lr=1.0049e-04) (hash(x)=26951664) +2670 train 7.469655 (lr=1.0043e-04) (hash(x)=24886228) +2671 train 6.926219 (lr=1.0037e-04) (hash(x)=19127465) +2672 train 7.193517 (lr=1.0032e-04) (hash(x)=27134917) +2673 train 7.134315 (lr=1.0026e-04) (hash(x)=25673955) +2674 train 7.647813 (lr=1.0021e-04) (hash(x)=27111776) +2675 train 7.603536 (lr=1.0015e-04) (hash(x)=28962580) +2676 train 7.160582 (lr=1.0009e-04) (hash(x)=25593381) +2677 train 7.210249 (lr=1.0004e-04) (hash(x)=25238916) +2678 train 7.100108 (lr=9.9981e-05) (hash(x)=27453574) +2679 train 7.086475 (lr=9.9925e-05) (hash(x)=22426274) +2680 train 7.104028 (lr=9.9869e-05) (hash(x)=22974780) +2681 train 7.128102 (lr=9.9813e-05) (hash(x)=24668644) +2682 train 7.144733 (lr=9.9757e-05) (hash(x)=26182084) +2683 train 7.341775 (lr=9.9700e-05) (hash(x)=25606512) +2684 train 7.154840 (lr=9.9644e-05) (hash(x)=24885252) +2685 train 6.975379 (lr=9.9588e-05) (hash(x)=21290254) +2686 train 6.869725 (lr=9.9532e-05) (hash(x)=21367078) +2687 train 7.048206 (lr=9.9476e-05) (hash(x)=23785205) +2688 train 6.962667 (lr=9.9420e-05) (hash(x)=24640056) +2689 train 7.414619 (lr=9.9363e-05) (hash(x)=27083886) +2690 train 7.083827 (lr=9.9307e-05) (hash(x)=23603571) +2691 train 7.166759 (lr=9.9251e-05) (hash(x)=24779414) +2692 train 6.868989 (lr=9.9195e-05) (hash(x)=22200693) +2693 train 7.204937 (lr=9.9139e-05) (hash(x)=26907868) +2694 train 7.553904 (lr=9.9083e-05) (hash(x)=32034827) +2695 train 7.418617 (lr=9.9026e-05) (hash(x)=28505676) +2696 train 6.992651 (lr=9.8970e-05) (hash(x)=23805750) +2697 train 7.323051 (lr=9.8914e-05) (hash(x)=29804750) +2698 train 7.635855 (lr=9.8858e-05) (hash(x)=28443583) +2699 train 7.523936 (lr=9.8802e-05) (hash(x)=29156288) +2700 val loss 7.2054 +2700 val perplexity 1346.6608 +2700 train 7.230487 (lr=9.8746e-05) (hash(x)=25895743) +2701 train 6.860673 (lr=9.8690e-05) (hash(x)=21173795) +2702 train 6.775688 (lr=9.8634e-05) (hash(x)=20790866) +2703 train 7.367387 (lr=9.8577e-05) (hash(x)=27706477) +2704 train 7.439308 (lr=9.8521e-05) (hash(x)=30358985) +2705 train 7.027663 (lr=9.8465e-05) (hash(x)=23548492) +2706 train 7.167641 (lr=9.8409e-05) (hash(x)=25879696) +2707 train 7.018669 (lr=9.8353e-05) (hash(x)=23711800) +2708 train 7.533452 (lr=9.8297e-05) (hash(x)=28763123) +2709 train 7.170747 (lr=9.8241e-05) (hash(x)=23327642) +2710 train 7.227098 (lr=9.8185e-05) (hash(x)=25634166) +2711 train 7.143014 (lr=9.8129e-05) (hash(x)=28684175) +2712 train 7.244722 (lr=9.8073e-05) (hash(x)=23996278) +2713 train 6.825353 (lr=9.8017e-05) (hash(x)=21795980) +2714 train 7.189477 (lr=9.7961e-05) (hash(x)=24840769) +2715 train 7.117911 (lr=9.7905e-05) (hash(x)=25225466) +2716 train 7.422370 (lr=9.7849e-05) (hash(x)=27500471) +2717 train 7.092969 (lr=9.7793e-05) (hash(x)=24703036) +2718 train 7.246736 (lr=9.7736e-05) (hash(x)=24294293) +2719 train 7.188610 (lr=9.7680e-05) (hash(x)=28003600) +2720 train 6.929035 (lr=9.7624e-05) (hash(x)=22822962) +2721 train 6.828830 (lr=9.7568e-05) (hash(x)=24189246) +2722 train 6.953877 (lr=9.7512e-05) (hash(x)=22608951) +2723 train 7.650821 (lr=9.7456e-05) (hash(x)=27989890) +2724 train 7.298763 (lr=9.7400e-05) (hash(x)=24175838) +2725 train 7.153365 (lr=9.7344e-05) (hash(x)=24781792) +2726 train 6.971520 (lr=9.7288e-05) (hash(x)=23413276) +2727 train 7.419375 (lr=9.7232e-05) (hash(x)=27586845) +2728 train 7.201634 (lr=9.7176e-05) (hash(x)=27336264) +2729 train 7.272972 (lr=9.7120e-05) (hash(x)=26808464) +2730 train 7.078252 (lr=9.7064e-05) (hash(x)=22312009) +2731 train 7.165832 (lr=9.7008e-05) (hash(x)=22373927) +2732 train 7.085408 (lr=9.6953e-05) (hash(x)=23428834) +2733 train 7.080468 (lr=9.6897e-05) (hash(x)=25304441) +2734 train 7.114609 (lr=9.6841e-05) (hash(x)=24798164) +2735 train 6.902794 (lr=9.6785e-05) (hash(x)=21176405) +2736 train 6.996667 (lr=9.6729e-05) (hash(x)=22343075) +2737 train 7.064546 (lr=9.6673e-05) (hash(x)=23825332) +2738 train 7.126379 (lr=9.6617e-05) (hash(x)=24191865) +2739 train 6.952397 (lr=9.6561e-05) (hash(x)=23806052) +2740 train 6.954067 (lr=9.6505e-05) (hash(x)=21764591) +2741 train 7.110752 (lr=9.6449e-05) (hash(x)=25548695) +2742 train 7.327796 (lr=9.6393e-05) (hash(x)=26847535) +2743 train 7.024452 (lr=9.6337e-05) (hash(x)=25888433) +2744 train 7.003119 (lr=9.6281e-05) (hash(x)=24327454) +2745 train 6.902156 (lr=9.6225e-05) (hash(x)=22543301) +2746 train 7.341554 (lr=9.6170e-05) (hash(x)=24593022) +2747 train 8.009270 (lr=9.6114e-05) (hash(x)=27797727) +2748 train 7.400344 (lr=9.6058e-05) (hash(x)=28067682) +2749 train 7.016249 (lr=9.6002e-05) (hash(x)=25278538) +2750 val loss 7.2057 +2750 val perplexity 1347.0724 +2750 train 6.967373 (lr=9.5946e-05) (hash(x)=23875731) +2751 train 7.179241 (lr=9.5890e-05) (hash(x)=27916982) +2752 train 7.158867 (lr=9.5834e-05) (hash(x)=25726799) +2753 train 6.992433 (lr=9.5778e-05) (hash(x)=25227141) +2754 train 7.255193 (lr=9.5723e-05) (hash(x)=27679212) +2755 train 6.969810 (lr=9.5667e-05) (hash(x)=24621793) +2756 train 6.896138 (lr=9.5611e-05) (hash(x)=21962296) +2757 train 7.261617 (lr=9.5555e-05) (hash(x)=24899679) +2758 train 6.953455 (lr=9.5499e-05) (hash(x)=21452158) +2759 train 7.051512 (lr=9.5443e-05) (hash(x)=24334708) +2760 train 7.300485 (lr=9.5388e-05) (hash(x)=25523041) +2761 train 7.406200 (lr=9.5332e-05) (hash(x)=30389813) +2762 train 6.935153 (lr=9.5276e-05) (hash(x)=22426014) +2763 train 7.027785 (lr=9.5220e-05) (hash(x)=24419143) +2764 train 7.108822 (lr=9.5164e-05) (hash(x)=24850536) +2765 train 7.183289 (lr=9.5109e-05) (hash(x)=24181393) +2766 train 6.670503 (lr=9.5053e-05) (hash(x)=18882503) +2767 train 7.169927 (lr=9.4997e-05) (hash(x)=25617709) +2768 train 7.093395 (lr=9.4941e-05) (hash(x)=24076662) +2769 train 7.029537 (lr=9.4886e-05) (hash(x)=21656802) +2770 train 6.970911 (lr=9.4830e-05) (hash(x)=21014265) +2771 train 7.119943 (lr=9.4774e-05) (hash(x)=24556034) +2772 train 6.846186 (lr=9.4718e-05) (hash(x)=22046665) +2773 train 7.163053 (lr=9.4663e-05) (hash(x)=26761579) +2774 train 8.654129 (lr=9.4607e-05) (hash(x)=41414315) +2775 train 7.052145 (lr=9.4551e-05) (hash(x)=25152362) +2776 train 7.234444 (lr=9.4495e-05) (hash(x)=25567641) +2777 train 7.162091 (lr=9.4440e-05) (hash(x)=25427935) +2778 train 7.242917 (lr=9.4384e-05) (hash(x)=25824457) +2779 train 7.153008 (lr=9.4328e-05) (hash(x)=24326376) +2780 train 7.187564 (lr=9.4273e-05) (hash(x)=27447230) +2781 train 7.038532 (lr=9.4217e-05) (hash(x)=24003710) +2782 train 6.953729 (lr=9.4161e-05) (hash(x)=24157390) +2783 train 7.062073 (lr=9.4106e-05) (hash(x)=24276512) +2784 train 6.898367 (lr=9.4050e-05) (hash(x)=21503752) +2785 train 6.813426 (lr=9.3994e-05) (hash(x)=20031488) +2786 train 6.847070 (lr=9.3939e-05) (hash(x)=21788715) +2787 train 7.051805 (lr=9.3883e-05) (hash(x)=24344695) +2788 train 7.101118 (lr=9.3827e-05) (hash(x)=22927763) +2789 train 6.975717 (lr=9.3772e-05) (hash(x)=23710755) +2790 train 7.216472 (lr=9.3716e-05) (hash(x)=26924620) +2791 train 7.547610 (lr=9.3660e-05) (hash(x)=26776133) +2792 train 6.987712 (lr=9.3605e-05) (hash(x)=19936770) +2793 train 7.144169 (lr=9.3549e-05) (hash(x)=25440959) +2794 train 7.070710 (lr=9.3494e-05) (hash(x)=25146097) +2795 train 6.887347 (lr=9.3438e-05) (hash(x)=21847282) +2796 train 7.077828 (lr=9.3382e-05) (hash(x)=25639784) +2797 train 6.851848 (lr=9.3327e-05) (hash(x)=21199921) +2798 train 7.036348 (lr=9.3271e-05) (hash(x)=22360806) +2799 train 6.496257 (lr=9.3216e-05) (hash(x)=20254159) +2800 val loss 7.1767 +2800 val perplexity 1308.5287 +2800 train 6.643735 (lr=9.3160e-05) (hash(x)=23348345) +2801 train 7.288287 (lr=9.3105e-05) (hash(x)=24908033) +2802 train 7.025843 (lr=9.3049e-05) (hash(x)=23350309) +2803 train 7.090271 (lr=9.2993e-05) (hash(x)=25044762) +2804 train 6.972955 (lr=9.2938e-05) (hash(x)=24071026) +2805 train 6.766529 (lr=9.2882e-05) (hash(x)=22169363) +2806 train 7.061532 (lr=9.2827e-05) (hash(x)=23757564) +2807 train 7.523654 (lr=9.2771e-05) (hash(x)=27873855) +2808 train 7.278263 (lr=9.2716e-05) (hash(x)=26577893) +2809 train 7.325772 (lr=9.2660e-05) (hash(x)=27001634) +2810 train 7.101457 (lr=9.2605e-05) (hash(x)=24796541) +2811 train 6.961546 (lr=9.2549e-05) (hash(x)=22575615) +2812 train 7.087873 (lr=9.2494e-05) (hash(x)=25876475) +2813 train 7.074483 (lr=9.2438e-05) (hash(x)=24765155) +2814 train 7.007343 (lr=9.2383e-05) (hash(x)=25785699) +2815 train 7.222487 (lr=9.2327e-05) (hash(x)=25113614) +2816 train 7.088452 (lr=9.2272e-05) (hash(x)=24415748) +2817 train 7.199740 (lr=9.2217e-05) (hash(x)=25140622) +2818 train 7.094041 (lr=9.2161e-05) (hash(x)=24845866) +2819 train 7.548055 (lr=9.2106e-05) (hash(x)=28062905) +2820 train 7.060037 (lr=9.2050e-05) (hash(x)=22041086) +2821 train 7.202384 (lr=9.1995e-05) (hash(x)=24957184) +2822 train 7.102462 (lr=9.1939e-05) (hash(x)=24360380) +2823 train 7.231786 (lr=9.1884e-05) (hash(x)=26192886) +2824 train 7.107095 (lr=9.1829e-05) (hash(x)=25001858) +2825 train 7.064833 (lr=9.1773e-05) (hash(x)=24721193) +2826 train 7.143823 (lr=9.1718e-05) (hash(x)=26186227) +2827 train 7.082238 (lr=9.1662e-05) (hash(x)=25770338) +2828 train 7.162062 (lr=9.1607e-05) (hash(x)=25920767) +2829 train 7.088340 (lr=9.1552e-05) (hash(x)=25060684) +2830 train 6.778377 (lr=9.1496e-05) (hash(x)=22933946) +2831 train 6.952808 (lr=9.1441e-05) (hash(x)=24614912) +2832 train 6.674225 (lr=9.1386e-05) (hash(x)=19955522) +2833 train 6.736076 (lr=9.1330e-05) (hash(x)=21111215) +2834 train 7.617973 (lr=9.1275e-05) (hash(x)=28817924) +2835 train 7.157726 (lr=9.1220e-05) (hash(x)=26934071) +2836 train 7.095294 (lr=9.1164e-05) (hash(x)=24768851) +2837 train 7.059707 (lr=9.1109e-05) (hash(x)=25706447) +2838 train 6.821700 (lr=9.1054e-05) (hash(x)=19579834) +2839 train 7.086296 (lr=9.0999e-05) (hash(x)=25397093) +2840 train 7.494766 (lr=9.0943e-05) (hash(x)=27902141) +2841 train 7.148703 (lr=9.0888e-05) (hash(x)=25383069) +2842 train 6.928432 (lr=9.0833e-05) (hash(x)=22007373) +2843 train 7.012108 (lr=9.0777e-05) (hash(x)=25925963) +2844 train 7.095910 (lr=9.0722e-05) (hash(x)=25711128) +2845 train 6.807018 (lr=9.0667e-05) (hash(x)=21881216) +2846 train 7.009067 (lr=9.0612e-05) (hash(x)=20277075) +2847 train 7.054604 (lr=9.0556e-05) (hash(x)=19811802) +2848 train 6.946233 (lr=9.0501e-05) (hash(x)=23878906) +2849 train 7.176021 (lr=9.0446e-05) (hash(x)=25034966) +2850 val loss 7.1649 +2850 val perplexity 1293.2062 +2850 train 7.205697 (lr=9.0391e-05) (hash(x)=24359507) +2851 train 6.959938 (lr=9.0336e-05) (hash(x)=23248423) +2852 train 6.938147 (lr=9.0280e-05) (hash(x)=21782773) +2853 train 7.085319 (lr=9.0225e-05) (hash(x)=23804418) +2854 train 7.132198 (lr=9.0170e-05) (hash(x)=22525078) +2855 train 7.124324 (lr=9.0115e-05) (hash(x)=25579655) +2856 train 7.223608 (lr=9.0060e-05) (hash(x)=27048876) +2857 train 7.359679 (lr=9.0005e-05) (hash(x)=26468479) +2858 train 7.015209 (lr=8.9949e-05) (hash(x)=23854933) +2859 train 7.421357 (lr=8.9894e-05) (hash(x)=25537603) +2860 train 6.815482 (lr=8.9839e-05) (hash(x)=20979252) +2861 train 7.417116 (lr=8.9784e-05) (hash(x)=26504374) +2862 train 7.189862 (lr=8.9729e-05) (hash(x)=27561842) +2863 train 7.182642 (lr=8.9674e-05) (hash(x)=26096514) +2864 train 7.203798 (lr=8.9619e-05) (hash(x)=25926899) +2865 train 7.222855 (lr=8.9564e-05) (hash(x)=26058348) +2866 train 7.237741 (lr=8.9509e-05) (hash(x)=29802259) +2867 train 7.136564 (lr=8.9454e-05) (hash(x)=24132888) +2868 train 6.848473 (lr=8.9398e-05) (hash(x)=23369410) +2869 train 7.008232 (lr=8.9343e-05) (hash(x)=25387506) +2870 train 7.214580 (lr=8.9288e-05) (hash(x)=27375344) +2871 train 6.959816 (lr=8.9233e-05) (hash(x)=22589633) +2872 train 7.127092 (lr=8.9178e-05) (hash(x)=23250237) +2873 train 6.995740 (lr=8.9123e-05) (hash(x)=25511322) +2874 train 6.656879 (lr=8.9068e-05) (hash(x)=18356418) +2875 train 7.140980 (lr=8.9013e-05) (hash(x)=27781566) +2876 train 7.000202 (lr=8.8958e-05) (hash(x)=24878173) +2877 train 7.479630 (lr=8.8903e-05) (hash(x)=30018637) +2878 train 7.307374 (lr=8.8848e-05) (hash(x)=27168416) +2879 train 7.276610 (lr=8.8793e-05) (hash(x)=26757147) +2880 train 7.311679 (lr=8.8738e-05) (hash(x)=26637081) +2881 train 7.199468 (lr=8.8683e-05) (hash(x)=24795024) +2882 train 7.469504 (lr=8.8628e-05) (hash(x)=29787745) +2883 train 7.295295 (lr=8.8574e-05) (hash(x)=26649864) +2884 train 7.133996 (lr=8.8519e-05) (hash(x)=27306612) +2885 train 7.207045 (lr=8.8464e-05) (hash(x)=27568311) +2886 train 7.248517 (lr=8.8409e-05) (hash(x)=27440150) +2887 train 6.968790 (lr=8.8354e-05) (hash(x)=24963730) +2888 train 7.003647 (lr=8.8299e-05) (hash(x)=23619807) +2889 train 7.499007 (lr=8.8244e-05) (hash(x)=29447356) +2890 train 6.989004 (lr=8.8189e-05) (hash(x)=25144675) +2891 train 6.925255 (lr=8.8134e-05) (hash(x)=25249959) +2892 train 6.941324 (lr=8.8079e-05) (hash(x)=26608712) +2893 train 6.961823 (lr=8.8025e-05) (hash(x)=26333258) +2894 train 6.761563 (lr=8.7970e-05) (hash(x)=20682182) +2895 train 7.206534 (lr=8.7915e-05) (hash(x)=27703124) +2896 train 6.977796 (lr=8.7860e-05) (hash(x)=23228180) +2897 train 6.852069 (lr=8.7805e-05) (hash(x)=25252411) +2898 train 6.856346 (lr=8.7751e-05) (hash(x)=22879178) +2899 train 7.159900 (lr=8.7696e-05) (hash(x)=26459082) +2900 val loss 7.1534 +2900 val perplexity 1278.4373 +2900 train 6.977220 (lr=8.7641e-05) (hash(x)=24569501) +2901 train 6.760848 (lr=8.7586e-05) (hash(x)=19803884) +2902 train 6.821086 (lr=8.7531e-05) (hash(x)=18799747) +2903 train 7.123434 (lr=8.7477e-05) (hash(x)=24781713) +2904 train 7.252386 (lr=8.7422e-05) (hash(x)=25016590) +2905 train 7.467927 (lr=8.7367e-05) (hash(x)=29006906) +2906 train 7.210988 (lr=8.7312e-05) (hash(x)=24069959) +2907 train 7.373193 (lr=8.7258e-05) (hash(x)=26597693) +2908 train 6.971643 (lr=8.7203e-05) (hash(x)=25014146) +2909 train 7.199134 (lr=8.7148e-05) (hash(x)=24943747) +2910 train 7.108594 (lr=8.7093e-05) (hash(x)=27847542) +2911 train 7.037418 (lr=8.7039e-05) (hash(x)=24720476) +2912 train 6.897274 (lr=8.6984e-05) (hash(x)=24388804) +2913 train 7.027965 (lr=8.6929e-05) (hash(x)=23567535) +2914 train 7.335101 (lr=8.6875e-05) (hash(x)=29673625) +2915 train 7.049057 (lr=8.6820e-05) (hash(x)=23691295) +2916 train 7.431395 (lr=8.6765e-05) (hash(x)=26572819) +2917 train 7.058900 (lr=8.6711e-05) (hash(x)=23237812) +2918 train 7.327466 (lr=8.6656e-05) (hash(x)=26531016) +2919 train 6.859156 (lr=8.6602e-05) (hash(x)=23481301) +2920 train 7.152159 (lr=8.6547e-05) (hash(x)=24839184) +2921 train 6.979542 (lr=8.6492e-05) (hash(x)=23327755) +2922 train 7.248521 (lr=8.6438e-05) (hash(x)=26347114) +2923 train 6.897554 (lr=8.6383e-05) (hash(x)=23295676) +2924 train 6.970200 (lr=8.6329e-05) (hash(x)=24557178) +2925 train 7.049873 (lr=8.6274e-05) (hash(x)=26067788) +2926 train 7.002670 (lr=8.6220e-05) (hash(x)=25694982) +2927 train 7.089809 (lr=8.6165e-05) (hash(x)=25641033) +2928 train 7.128597 (lr=8.6110e-05) (hash(x)=24906422) +2929 train 7.303705 (lr=8.6056e-05) (hash(x)=27803515) +2930 train 7.269086 (lr=8.6001e-05) (hash(x)=26208803) +2931 train 6.750279 (lr=8.5947e-05) (hash(x)=22441379) +2932 train 7.040462 (lr=8.5892e-05) (hash(x)=24741626) +2933 train 6.897245 (lr=8.5838e-05) (hash(x)=24595257) +2934 train 6.945546 (lr=8.5783e-05) (hash(x)=23939167) +2935 train 7.230810 (lr=8.5729e-05) (hash(x)=27369437) +2936 train 6.879611 (lr=8.5674e-05) (hash(x)=21409783) +2937 train 7.163809 (lr=8.5620e-05) (hash(x)=25923735) +2938 train 7.158760 (lr=8.5566e-05) (hash(x)=29559511) +2939 train 7.029041 (lr=8.5511e-05) (hash(x)=24482272) +2940 train 7.012814 (lr=8.5457e-05) (hash(x)=24767658) +2941 train 7.193494 (lr=8.5402e-05) (hash(x)=26425020) +2942 train 7.575049 (lr=8.5348e-05) (hash(x)=27444868) +2943 train 7.017246 (lr=8.5294e-05) (hash(x)=24760900) +2944 train 7.099385 (lr=8.5239e-05) (hash(x)=25605407) +2945 train 6.921889 (lr=8.5185e-05) (hash(x)=22886951) +2946 train 7.282585 (lr=8.5130e-05) (hash(x)=26112205) +2947 train 7.087907 (lr=8.5076e-05) (hash(x)=23919156) +2948 train 7.046566 (lr=8.5022e-05) (hash(x)=23729312) +2949 train 7.354171 (lr=8.4967e-05) (hash(x)=30440878) +2950 val loss 7.1547 +2950 val perplexity 1280.0531 +2950 train 6.783347 (lr=8.4913e-05) (hash(x)=20004041) +2951 train 6.748262 (lr=8.4859e-05) (hash(x)=21692546) +2952 train 6.831712 (lr=8.4804e-05) (hash(x)=23021681) +2953 train 7.172836 (lr=8.4750e-05) (hash(x)=26663597) +2954 train 7.045488 (lr=8.4696e-05) (hash(x)=23727385) +2955 train 7.056890 (lr=8.4642e-05) (hash(x)=27692087) +2956 train 7.070634 (lr=8.4587e-05) (hash(x)=24003378) +2957 train 7.747757 (lr=8.4533e-05) (hash(x)=29534673) +2958 train 6.968878 (lr=8.4479e-05) (hash(x)=22875068) +2959 train 6.948290 (lr=8.4425e-05) (hash(x)=22720391) +2960 train 6.744920 (lr=8.4370e-05) (hash(x)=17997400) +2961 train 6.958833 (lr=8.4316e-05) (hash(x)=22853822) +2962 train 7.034196 (lr=8.4262e-05) (hash(x)=25238004) +2963 train 7.146581 (lr=8.4208e-05) (hash(x)=26146560) +2964 train 7.280248 (lr=8.4154e-05) (hash(x)=21894867) +2965 train 7.257003 (lr=8.4099e-05) (hash(x)=23001150) +2966 train 6.934973 (lr=8.4045e-05) (hash(x)=23392923) +2967 train 7.025679 (lr=8.3991e-05) (hash(x)=24376979) +2968 train 7.017137 (lr=8.3937e-05) (hash(x)=23781449) +2969 train 7.173502 (lr=8.3883e-05) (hash(x)=25315495) +2970 train 7.286349 (lr=8.3829e-05) (hash(x)=27165470) +2971 train 7.089392 (lr=8.3775e-05) (hash(x)=22917712) +2972 train 7.427917 (lr=8.3721e-05) (hash(x)=27928456) +2973 train 6.807666 (lr=8.3666e-05) (hash(x)=19890855) +2974 train 6.802159 (lr=8.3612e-05) (hash(x)=21318134) +2975 train 6.938262 (lr=8.3558e-05) (hash(x)=22244509) +2976 train 6.887685 (lr=8.3504e-05) (hash(x)=21293137) +2977 train 6.976944 (lr=8.3450e-05) (hash(x)=23465789) +2978 train 6.938939 (lr=8.3396e-05) (hash(x)=21169753) +2979 train 7.289977 (lr=8.3342e-05) (hash(x)=25243385) +2980 train 7.323598 (lr=8.3288e-05) (hash(x)=27465812) +2981 train 7.048824 (lr=8.3234e-05) (hash(x)=24615492) +2982 train 6.974218 (lr=8.3180e-05) (hash(x)=23081307) +2983 train 6.739566 (lr=8.3126e-05) (hash(x)=21831960) +2984 train 6.863756 (lr=8.3072e-05) (hash(x)=23242850) +2985 train 6.997931 (lr=8.3018e-05) (hash(x)=24308188) +2986 train 7.179289 (lr=8.2964e-05) (hash(x)=28541601) +2987 train 7.067175 (lr=8.2910e-05) (hash(x)=24842373) +2988 train 6.792589 (lr=8.2856e-05) (hash(x)=21967126) +2989 train 6.968060 (lr=8.2802e-05) (hash(x)=22951616) +2990 train 7.091918 (lr=8.2748e-05) (hash(x)=24325714) +2991 train 6.901151 (lr=8.2695e-05) (hash(x)=24921535) +2992 train 7.140662 (lr=8.2641e-05) (hash(x)=25937112) +2993 train 6.785997 (lr=8.2587e-05) (hash(x)=20716218) +2994 train 7.113208 (lr=8.2533e-05) (hash(x)=25450724) +2995 train 7.059293 (lr=8.2479e-05) (hash(x)=24344615) +2996 train 6.794137 (lr=8.2425e-05) (hash(x)=20299058) +2997 train 7.015251 (lr=8.2371e-05) (hash(x)=23859426) +2998 train 6.987081 (lr=8.2318e-05) (hash(x)=23094397) +2999 train 7.265607 (lr=8.2264e-05) (hash(x)=25381251) +3000 val loss 7.1578 +3000 val perplexity 1284.0409 +3000 train 7.080562 (lr=8.2210e-05) (hash(x)=23586527) +3001 train 6.935278 (lr=8.2156e-05) (hash(x)=24220410) +3002 train 6.804945 (lr=8.2102e-05) (hash(x)=20597347) +3003 train 6.903766 (lr=8.2049e-05) (hash(x)=22887303) +3004 train 7.207101 (lr=8.1995e-05) (hash(x)=25869462) +3005 train 6.917150 (lr=8.1941e-05) (hash(x)=22098530) +3006 train 7.218585 (lr=8.1887e-05) (hash(x)=26246291) +3007 train 7.155776 (lr=8.1834e-05) (hash(x)=25687352) +3008 train 6.904986 (lr=8.1780e-05) (hash(x)=25425646) +3009 train 7.089684 (lr=8.1726e-05) (hash(x)=26021124) +3010 train 7.132224 (lr=8.1673e-05) (hash(x)=25392057) +3011 train 7.236032 (lr=8.1619e-05) (hash(x)=27791412) +3012 train 7.048066 (lr=8.1565e-05) (hash(x)=23181098) +3013 train 7.068741 (lr=8.1512e-05) (hash(x)=25521889) +3014 train 6.875098 (lr=8.1458e-05) (hash(x)=21685795) +3015 train 7.034380 (lr=8.1404e-05) (hash(x)=25221654) +3016 train 7.216364 (lr=8.1351e-05) (hash(x)=24888744) +3017 train 7.108588 (lr=8.1297e-05) (hash(x)=24200150) +3018 train 7.030631 (lr=8.1243e-05) (hash(x)=26943942) +3019 train 6.992735 (lr=8.1190e-05) (hash(x)=23243731) +3020 train 6.853832 (lr=8.1136e-05) (hash(x)=21068284) +3021 train 7.004876 (lr=8.1083e-05) (hash(x)=23876902) +3022 train 7.189565 (lr=8.1029e-05) (hash(x)=25337639) +3023 train 7.084155 (lr=8.0976e-05) (hash(x)=24469863) +3024 train 7.532724 (lr=8.0922e-05) (hash(x)=27850876) +3025 train 7.383879 (lr=8.0869e-05) (hash(x)=20515778) +3026 train 7.134230 (lr=8.0815e-05) (hash(x)=29019173) +3027 train 6.779335 (lr=8.0762e-05) (hash(x)=22484936) +3028 train 6.940042 (lr=8.0708e-05) (hash(x)=24639400) +3029 train 7.125449 (lr=8.0655e-05) (hash(x)=26835174) +3030 train 7.273157 (lr=8.0601e-05) (hash(x)=29843763) +3031 train 6.976856 (lr=8.0548e-05) (hash(x)=25291413) +3032 train 6.917169 (lr=8.0494e-05) (hash(x)=24590244) +3033 train 7.186270 (lr=8.0441e-05) (hash(x)=28880142) +3034 train 6.905188 (lr=8.0387e-05) (hash(x)=23372199) +3035 train 6.897580 (lr=8.0334e-05) (hash(x)=23952225) +3036 train 7.034760 (lr=8.0281e-05) (hash(x)=24589186) +3037 train 7.024448 (lr=8.0227e-05) (hash(x)=23260323) +3038 train 7.156855 (lr=8.0174e-05) (hash(x)=25824498) +3039 train 7.116898 (lr=8.0120e-05) (hash(x)=25744274) +3040 train 7.075350 (lr=8.0067e-05) (hash(x)=21610247) +3041 train 7.191324 (lr=8.0014e-05) (hash(x)=25079786) +3042 train 6.817709 (lr=7.9960e-05) (hash(x)=23219195) +3043 train 6.752647 (lr=7.9907e-05) (hash(x)=22616739) +3044 train 7.064171 (lr=7.9854e-05) (hash(x)=24908480) +3045 train 6.911233 (lr=7.9801e-05) (hash(x)=22293489) +3046 train 6.942983 (lr=7.9747e-05) (hash(x)=23557651) +3047 train 6.988904 (lr=7.9694e-05) (hash(x)=24246963) +3048 train 7.106072 (lr=7.9641e-05) (hash(x)=24490083) +3049 train 7.090022 (lr=7.9588e-05) (hash(x)=22372895) +3050 val loss 7.1446 +3050 val perplexity 1267.2551 +3050 train 6.808017 (lr=7.9534e-05) (hash(x)=21759470) +3051 train 6.722953 (lr=7.9481e-05) (hash(x)=19407094) +3052 train 7.083287 (lr=7.9428e-05) (hash(x)=23957047) +3053 train 7.185909 (lr=7.9375e-05) (hash(x)=24719318) +3054 train 6.965008 (lr=7.9322e-05) (hash(x)=20719314) +3055 train 6.914674 (lr=7.9268e-05) (hash(x)=19724058) +3056 train 6.740253 (lr=7.9215e-05) (hash(x)=14407266) +3057 train 6.608846 (lr=7.9162e-05) (hash(x)=12468292) +3058 train 6.880427 (lr=7.9109e-05) (hash(x)=16098279) +3059 train 6.976261 (lr=7.9056e-05) (hash(x)=18836491) +3060 train 6.803821 (lr=7.9003e-05) (hash(x)=19132277) +3061 train 6.946157 (lr=7.8950e-05) (hash(x)=22814208) +3062 train 6.967248 (lr=7.8897e-05) (hash(x)=24838508) +3063 train 6.851560 (lr=7.8843e-05) (hash(x)=20705649) +3064 train 7.905991 (lr=7.8790e-05) (hash(x)=29416914) +3065 train 7.334003 (lr=7.8737e-05) (hash(x)=25972430) +3066 train 6.702356 (lr=7.8684e-05) (hash(x)=23705805) +3067 train 6.766301 (lr=7.8631e-05) (hash(x)=21325875) +3068 train 7.024220 (lr=7.8578e-05) (hash(x)=23526506) +3069 train 7.571234 (lr=7.8525e-05) (hash(x)=27282337) +3070 train 7.325572 (lr=7.8472e-05) (hash(x)=27968043) +3071 train 7.154155 (lr=7.8419e-05) (hash(x)=24938685) +3072 train 7.341284 (lr=7.8366e-05) (hash(x)=26942737) +3073 train 7.208942 (lr=7.8313e-05) (hash(x)=23506879) +3074 train 6.882061 (lr=7.8261e-05) (hash(x)=23589913) +3075 train 7.099335 (lr=7.8208e-05) (hash(x)=25152403) +3076 train 7.234437 (lr=7.8155e-05) (hash(x)=23425868) +3077 train 7.435378 (lr=7.8102e-05) (hash(x)=23966181) +3078 train 7.449736 (lr=7.8049e-05) (hash(x)=27312570) +3079 train 7.046268 (lr=7.7996e-05) (hash(x)=21707000) +3080 train 7.003305 (lr=7.7943e-05) (hash(x)=25600427) +3081 train 7.124454 (lr=7.7890e-05) (hash(x)=24270631) +3082 train 7.220003 (lr=7.7838e-05) (hash(x)=25199537) +3083 train 6.503464 (lr=7.7785e-05) (hash(x)=17952018) +3084 train 6.592571 (lr=7.7732e-05) (hash(x)=18733143) +3085 train 7.250404 (lr=7.7679e-05) (hash(x)=26946100) +3086 train 7.069122 (lr=7.7626e-05) (hash(x)=25547515) +3087 train 7.040502 (lr=7.7574e-05) (hash(x)=24948980) +3088 train 8.156188 (lr=7.7521e-05) (hash(x)=35461645) +3089 train 7.267641 (lr=7.7468e-05) (hash(x)=28330877) +3090 train 7.178693 (lr=7.7415e-05) (hash(x)=27687861) +3091 train 7.328693 (lr=7.7363e-05) (hash(x)=28012110) +3092 train 7.175909 (lr=7.7310e-05) (hash(x)=24684480) +3093 train 7.142962 (lr=7.7257e-05) (hash(x)=26225786) +3094 train 6.806064 (lr=7.7205e-05) (hash(x)=23098156) +3095 train 7.387653 (lr=7.7152e-05) (hash(x)=30773958) +3096 train 7.683548 (lr=7.7099e-05) (hash(x)=28640406) +3097 train 7.603681 (lr=7.7047e-05) (hash(x)=28201086) +3098 train 7.988112 (lr=7.6994e-05) (hash(x)=35002344) +3099 train 7.484058 (lr=7.6941e-05) (hash(x)=29481068) +3100 val loss 7.1524 +3100 val perplexity 1277.1255 +3100 train 7.052185 (lr=7.6889e-05) (hash(x)=26374528) +3101 train 7.023197 (lr=7.6836e-05) (hash(x)=24153602) +3102 train 7.054790 (lr=7.6784e-05) (hash(x)=25478746) +3103 train 7.359058 (lr=7.6731e-05) (hash(x)=26769046) +3104 train 6.954506 (lr=7.6679e-05) (hash(x)=21841970) +3105 train 7.253504 (lr=7.6626e-05) (hash(x)=27693052) +3106 train 6.721175 (lr=7.6573e-05) (hash(x)=20689448) +3107 train 7.080609 (lr=7.6521e-05) (hash(x)=26755048) +3108 train 7.107933 (lr=7.6468e-05) (hash(x)=24431904) +3109 train 6.954921 (lr=7.6416e-05) (hash(x)=21009792) +3110 train 7.069144 (lr=7.6364e-05) (hash(x)=21909003) +3111 train 7.121676 (lr=7.6311e-05) (hash(x)=18849656) +3112 train 7.219740 (lr=7.6259e-05) (hash(x)=22223376) +3113 train 7.490710 (lr=7.6206e-05) (hash(x)=25652491) +3114 train 7.405484 (lr=7.6154e-05) (hash(x)=23521434) +3115 train 7.448803 (lr=7.6101e-05) (hash(x)=25449800) +3116 train 7.809506 (lr=7.6049e-05) (hash(x)=27655847) +3117 train 7.876248 (lr=7.5997e-05) (hash(x)=29878248) +3118 train 7.896832 (lr=7.5944e-05) (hash(x)=30444094) +3119 train 7.488561 (lr=7.5892e-05) (hash(x)=24624950) +3120 train 6.820879 (lr=7.5840e-05) (hash(x)=20798511) +3121 train 7.224196 (lr=7.5787e-05) (hash(x)=26581679) +3122 train 7.112259 (lr=7.5735e-05) (hash(x)=25333422) +3123 train 7.194838 (lr=7.5683e-05) (hash(x)=26174069) +3124 train 7.228757 (lr=7.5630e-05) (hash(x)=25219475) +3125 train 7.140087 (lr=7.5578e-05) (hash(x)=20919061) +3126 train 7.102612 (lr=7.5526e-05) (hash(x)=23828688) +3127 train 7.580045 (lr=7.5474e-05) (hash(x)=27299605) +3128 train 6.985208 (lr=7.5421e-05) (hash(x)=23797514) +3129 train 7.216844 (lr=7.5369e-05) (hash(x)=23601883) +3130 train 7.408063 (lr=7.5317e-05) (hash(x)=31003964) +3131 train 7.141562 (lr=7.5265e-05) (hash(x)=24777273) +3132 train 6.998997 (lr=7.5213e-05) (hash(x)=25403249) +3133 train 7.242671 (lr=7.5160e-05) (hash(x)=28913150) +3134 train 7.200215 (lr=7.5108e-05) (hash(x)=26541508) +3135 train 7.151371 (lr=7.5056e-05) (hash(x)=24113445) +3136 train 6.940050 (lr=7.5004e-05) (hash(x)=25464565) +3137 train 7.204956 (lr=7.4952e-05) (hash(x)=26581432) +3138 train 7.036477 (lr=7.4900e-05) (hash(x)=23074513) +3139 train 6.908182 (lr=7.4848e-05) (hash(x)=23970384) +3140 train 7.146459 (lr=7.4796e-05) (hash(x)=26694495) +3141 train 7.103019 (lr=7.4744e-05) (hash(x)=26883445) +3142 train 7.295512 (lr=7.4692e-05) (hash(x)=28632211) +3143 train 7.703585 (lr=7.4640e-05) (hash(x)=32644465) +3144 train 7.429758 (lr=7.4588e-05) (hash(x)=27490443) +3145 train 6.998853 (lr=7.4536e-05) (hash(x)=23814853) +3146 train 7.446900 (lr=7.4484e-05) (hash(x)=29664236) +3147 train 7.731407 (lr=7.4432e-05) (hash(x)=29951548) +3148 train 7.489096 (lr=7.4380e-05) (hash(x)=28426503) +3149 train 6.882092 (lr=7.4328e-05) (hash(x)=23727657) +3150 val loss 7.1547 +3150 val perplexity 1280.1307 +3150 train 7.036691 (lr=7.4276e-05) (hash(x)=21430659) +3151 train 7.095170 (lr=7.4224e-05) (hash(x)=25829219) +3152 train 7.257765 (lr=7.4172e-05) (hash(x)=29735208) +3153 train 7.302515 (lr=7.4120e-05) (hash(x)=28173447) +3154 train 6.999974 (lr=7.4068e-05) (hash(x)=22909641) +3155 train 7.165375 (lr=7.4017e-05) (hash(x)=20556094) +3156 train 6.902143 (lr=7.3965e-05) (hash(x)=24013769) +3157 train 6.889801 (lr=7.3913e-05) (hash(x)=22525971) +3158 train 6.982718 (lr=7.3861e-05) (hash(x)=25492728) +3159 train 7.038734 (lr=7.3809e-05) (hash(x)=25194550) +3160 train 7.148134 (lr=7.3757e-05) (hash(x)=25610603) +3161 train 7.107976 (lr=7.3706e-05) (hash(x)=23848640) +3162 train 6.946270 (lr=7.3654e-05) (hash(x)=24082226) +3163 train 7.343803 (lr=7.3602e-05) (hash(x)=28482186) +3164 train 7.246509 (lr=7.3551e-05) (hash(x)=27542978) +3165 train 6.981555 (lr=7.3499e-05) (hash(x)=22540954) +3166 train 7.126653 (lr=7.3447e-05) (hash(x)=26103641) +3167 train 7.086510 (lr=7.3395e-05) (hash(x)=25941804) +3168 train 7.122146 (lr=7.3344e-05) (hash(x)=25965921) +3169 train 7.325566 (lr=7.3292e-05) (hash(x)=25631269) +3170 train 6.910439 (lr=7.3240e-05) (hash(x)=23471525) +3171 train 7.154762 (lr=7.3189e-05) (hash(x)=27049208) +3172 train 7.147083 (lr=7.3137e-05) (hash(x)=27074992) +3173 train 7.105968 (lr=7.3086e-05) (hash(x)=25712617) +3174 train 7.072780 (lr=7.3034e-05) (hash(x)=25884917) +3175 train 7.081439 (lr=7.2983e-05) (hash(x)=24075727) +3176 train 6.974671 (lr=7.2931e-05) (hash(x)=23681759) +3177 train 7.232503 (lr=7.2879e-05) (hash(x)=25786577) +3178 train 7.207021 (lr=7.2828e-05) (hash(x)=27307614) +3179 train 7.245570 (lr=7.2776e-05) (hash(x)=25082806) +3180 train 7.236572 (lr=7.2725e-05) (hash(x)=26098308) +3181 train 7.019280 (lr=7.2673e-05) (hash(x)=24080140) +3182 train 7.252561 (lr=7.2622e-05) (hash(x)=26399395) +3183 train 7.254498 (lr=7.2571e-05) (hash(x)=23104539) +3184 train 6.921365 (lr=7.2519e-05) (hash(x)=23356930) +3185 train 7.172680 (lr=7.2468e-05) (hash(x)=27972420) +3186 train 6.848673 (lr=7.2416e-05) (hash(x)=21338924) +3187 train 7.260465 (lr=7.2365e-05) (hash(x)=25351113) +3188 train 7.202690 (lr=7.2314e-05) (hash(x)=26019439) +3189 train 7.267658 (lr=7.2262e-05) (hash(x)=30149312) +3190 train 6.954445 (lr=7.2211e-05) (hash(x)=23028152) +3191 train 7.299638 (lr=7.2160e-05) (hash(x)=23018983) +3192 train 6.947834 (lr=7.2108e-05) (hash(x)=23190787) +3193 train 7.359277 (lr=7.2057e-05) (hash(x)=27798543) +3194 train 7.149220 (lr=7.2006e-05) (hash(x)=25193663) +3195 train 6.934401 (lr=7.1954e-05) (hash(x)=25302106) +3196 train 7.093972 (lr=7.1903e-05) (hash(x)=24325364) +3197 train 7.110837 (lr=7.1852e-05) (hash(x)=25399101) +3198 train 6.952515 (lr=7.1801e-05) (hash(x)=23606439) +3199 train 6.983016 (lr=7.1749e-05) (hash(x)=24422929) +3200 val loss 7.1366 +3200 val perplexity 1257.1726 +3200 train 7.190646 (lr=7.1698e-05) (hash(x)=24760381) +3201 train 6.848760 (lr=7.1647e-05) (hash(x)=23278576) +3202 train 7.068833 (lr=7.1596e-05) (hash(x)=24897511) +3203 train 7.365549 (lr=7.1545e-05) (hash(x)=29052117) +3204 train 7.109229 (lr=7.1494e-05) (hash(x)=25772923) +3205 train 7.250070 (lr=7.1443e-05) (hash(x)=25885977) +3206 train 7.034459 (lr=7.1391e-05) (hash(x)=21985272) +3207 train 6.967660 (lr=7.1340e-05) (hash(x)=23389696) +3208 train 6.872875 (lr=7.1289e-05) (hash(x)=25299042) +3209 train 7.155050 (lr=7.1238e-05) (hash(x)=23703987) +3210 train 7.038357 (lr=7.1187e-05) (hash(x)=23362342) +3211 train 7.107825 (lr=7.1136e-05) (hash(x)=23962503) +3212 train 6.989128 (lr=7.1085e-05) (hash(x)=21216023) +3213 train 7.104440 (lr=7.1034e-05) (hash(x)=25841931) +3214 train 6.944633 (lr=7.0983e-05) (hash(x)=23631428) +3215 train 7.348595 (lr=7.0932e-05) (hash(x)=29102969) +3216 train 7.132143 (lr=7.0881e-05) (hash(x)=25782766) +3217 train 7.346443 (lr=7.0830e-05) (hash(x)=28825867) +3218 train 7.300532 (lr=7.0779e-05) (hash(x)=24609499) +3219 train 7.213304 (lr=7.0729e-05) (hash(x)=24948166) +3220 train 7.318918 (lr=7.0678e-05) (hash(x)=26919841) +3221 train 7.137917 (lr=7.0627e-05) (hash(x)=27236198) +3222 train 6.947801 (lr=7.0576e-05) (hash(x)=24029305) +3223 train 7.527407 (lr=7.0525e-05) (hash(x)=28359859) +3224 train 7.289922 (lr=7.0474e-05) (hash(x)=24886008) +3225 train 7.090303 (lr=7.0424e-05) (hash(x)=27159867) +3226 train 7.366998 (lr=7.0373e-05) (hash(x)=20672023) +3227 train 7.038139 (lr=7.0322e-05) (hash(x)=22360298) +3228 train 7.463918 (lr=7.0271e-05) (hash(x)=27478658) +3229 train 7.250615 (lr=7.0220e-05) (hash(x)=26575886) +3230 train 7.430675 (lr=7.0170e-05) (hash(x)=26890615) +3231 train 7.034078 (lr=7.0119e-05) (hash(x)=24630955) +3232 train 7.339412 (lr=7.0068e-05) (hash(x)=27016054) +3233 train 7.530252 (lr=7.0018e-05) (hash(x)=28444407) +3234 train 6.968494 (lr=6.9967e-05) (hash(x)=24053336) +3235 train 7.278553 (lr=6.9916e-05) (hash(x)=26897402) +3236 train 7.435476 (lr=6.9866e-05) (hash(x)=29451214) +3237 train 7.200147 (lr=6.9815e-05) (hash(x)=27268677) +3238 train 7.338275 (lr=6.9764e-05) (hash(x)=27494000) +3239 train 6.985529 (lr=6.9714e-05) (hash(x)=22969113) +3240 train 6.949473 (lr=6.9663e-05) (hash(x)=21944576) +3241 train 7.193584 (lr=6.9613e-05) (hash(x)=21671079) +3242 train 7.063211 (lr=6.9562e-05) (hash(x)=23912980) +3243 train 7.013173 (lr=6.9512e-05) (hash(x)=25205781) +3244 train 7.015600 (lr=6.9461e-05) (hash(x)=25654244) +3245 train 6.954291 (lr=6.9411e-05) (hash(x)=23335929) +3246 train 7.302320 (lr=6.9360e-05) (hash(x)=27953926) +3247 train 7.135385 (lr=6.9310e-05) (hash(x)=27004415) +3248 train 6.798503 (lr=6.9259e-05) (hash(x)=20471566) +3249 train 7.007288 (lr=6.9209e-05) (hash(x)=25797941) +3250 val loss 7.1377 +3250 val perplexity 1258.5612 +3250 train 6.919747 (lr=6.9158e-05) (hash(x)=21787064) +3251 train 6.906613 (lr=6.9108e-05) (hash(x)=22974875) +3252 train 7.153723 (lr=6.9058e-05) (hash(x)=28431267) +3253 train 7.042160 (lr=6.9007e-05) (hash(x)=25584910) +3254 train 6.849483 (lr=6.8957e-05) (hash(x)=23888922) +3255 train 7.064500 (lr=6.8907e-05) (hash(x)=22265063) +3256 train 6.664356 (lr=6.8856e-05) (hash(x)=21926624) +3257 train 6.949941 (lr=6.8806e-05) (hash(x)=23073191) +3258 train 6.965390 (lr=6.8756e-05) (hash(x)=24409183) +3259 train 7.041254 (lr=6.8706e-05) (hash(x)=23312114) +3260 train 6.926037 (lr=6.8655e-05) (hash(x)=21001289) +3261 train 7.151942 (lr=6.8605e-05) (hash(x)=25514824) +3262 train 6.911163 (lr=6.8555e-05) (hash(x)=22526800) +3263 train 7.313732 (lr=6.8505e-05) (hash(x)=26905990) +3264 train 7.001199 (lr=6.8454e-05) (hash(x)=24469631) +3265 train 6.855864 (lr=6.8404e-05) (hash(x)=21149081) +3266 train 7.044656 (lr=6.8354e-05) (hash(x)=24696215) +3267 train 7.440369 (lr=6.8304e-05) (hash(x)=27089280) +3268 train 6.935016 (lr=6.8254e-05) (hash(x)=23100446) +3269 train 7.168924 (lr=6.8204e-05) (hash(x)=25061229) +3270 train 7.040823 (lr=6.8154e-05) (hash(x)=24337543) +3271 train 7.111454 (lr=6.8104e-05) (hash(x)=24047679) +3272 train 7.184386 (lr=6.8054e-05) (hash(x)=27616773) +3273 train 7.081543 (lr=6.8004e-05) (hash(x)=25315110) +3274 train 7.176787 (lr=6.7954e-05) (hash(x)=28354645) +3275 train 7.011859 (lr=6.7904e-05) (hash(x)=25034684) +3276 train 7.041989 (lr=6.7854e-05) (hash(x)=23550342) +3277 train 7.731790 (lr=6.7804e-05) (hash(x)=28661487) +3278 train 7.289820 (lr=6.7754e-05) (hash(x)=24724622) +3279 train 7.212642 (lr=6.7704e-05) (hash(x)=26905582) +3280 train 7.304851 (lr=6.7654e-05) (hash(x)=26838818) +3281 train 7.046454 (lr=6.7604e-05) (hash(x)=23949017) +3282 train 6.518039 (lr=6.7554e-05) (hash(x)=18846300) +3283 train 6.887520 (lr=6.7504e-05) (hash(x)=21406950) +3284 train 6.720936 (lr=6.7454e-05) (hash(x)=21157696) +3285 train 6.839273 (lr=6.7404e-05) (hash(x)=21440152) +3286 train 7.019020 (lr=6.7355e-05) (hash(x)=26749182) +3287 train 7.216375 (lr=6.7305e-05) (hash(x)=29018970) +3288 train 7.154440 (lr=6.7255e-05) (hash(x)=27577517) +3289 train 6.793610 (lr=6.7205e-05) (hash(x)=19190537) +3290 train 6.798946 (lr=6.7156e-05) (hash(x)=21957991) +3291 train 6.852104 (lr=6.7106e-05) (hash(x)=20853530) +3292 train 6.778101 (lr=6.7056e-05) (hash(x)=22291731) +3293 train 6.978031 (lr=6.7006e-05) (hash(x)=23786853) +3294 train 7.123405 (lr=6.6957e-05) (hash(x)=25740147) +3295 train 7.225235 (lr=6.6907e-05) (hash(x)=24503315) +3296 train 6.973717 (lr=6.6857e-05) (hash(x)=22541728) +3297 train 7.291694 (lr=6.6808e-05) (hash(x)=27067328) +3298 train 6.931962 (lr=6.6758e-05) (hash(x)=22600715) +3299 train 6.954924 (lr=6.6709e-05) (hash(x)=23080074) +3300 val loss 7.1235 +3300 val perplexity 1240.7375 +3300 train 6.761415 (lr=6.6659e-05) (hash(x)=22097758) +3301 train 6.939818 (lr=6.6609e-05) (hash(x)=24105430) +3302 train 6.793222 (lr=6.6560e-05) (hash(x)=23343775) +3303 train 7.039399 (lr=6.6510e-05) (hash(x)=22607537) +3304 train 7.116545 (lr=6.6461e-05) (hash(x)=26501182) +3305 train 7.388014 (lr=6.6411e-05) (hash(x)=26063650) +3306 train 6.980515 (lr=6.6362e-05) (hash(x)=23486602) +3307 train 7.967564 (lr=6.6312e-05) (hash(x)=32179773) +3308 train 11.381427 (lr=6.6263e-05) (hash(x)=66155855) +3309 train 8.473784 (lr=6.6214e-05) (hash(x)=37724427) +3310 train 7.473982 (lr=6.6164e-05) (hash(x)=28861610) +3311 train 7.411247 (lr=6.6115e-05) (hash(x)=26690225) +3312 train 7.000736 (lr=6.6065e-05) (hash(x)=24136450) +3313 train 7.185027 (lr=6.6016e-05) (hash(x)=23702010) +3314 train 7.436176 (lr=6.5967e-05) (hash(x)=28761762) +3315 train 6.780599 (lr=6.5917e-05) (hash(x)=22109609) +3316 train 7.126541 (lr=6.5868e-05) (hash(x)=25168631) +3317 train 7.021764 (lr=6.5819e-05) (hash(x)=24503786) +3318 train 7.032814 (lr=6.5770e-05) (hash(x)=23698606) +3319 train 7.096002 (lr=6.5720e-05) (hash(x)=24226255) +3320 train 7.681532 (lr=6.5671e-05) (hash(x)=31110577) +3321 train 7.053751 (lr=6.5622e-05) (hash(x)=24752754) +3322 train 6.915009 (lr=6.5573e-05) (hash(x)=21135610) +3323 train 6.859446 (lr=6.5523e-05) (hash(x)=23013573) +3324 train 6.603628 (lr=6.5474e-05) (hash(x)=20289715) +3325 train 6.879695 (lr=6.5425e-05) (hash(x)=22700287) +3326 train 6.959878 (lr=6.5376e-05) (hash(x)=21320362) +3327 train 7.080900 (lr=6.5327e-05) (hash(x)=23622702) +3328 train 7.328134 (lr=6.5278e-05) (hash(x)=27435461) +3329 train 7.099178 (lr=6.5229e-05) (hash(x)=25435452) +3330 train 7.102132 (lr=6.5180e-05) (hash(x)=27952557) +3331 train 6.755461 (lr=6.5131e-05) (hash(x)=21517429) +3332 train 6.889482 (lr=6.5082e-05) (hash(x)=24288985) +3333 train 7.073331 (lr=6.5033e-05) (hash(x)=23374788) +3334 train 6.871071 (lr=6.4984e-05) (hash(x)=22042499) +3335 train 7.140004 (lr=6.4935e-05) (hash(x)=23910425) +3336 train 7.469339 (lr=6.4886e-05) (hash(x)=28118508) +3337 train 7.231558 (lr=6.4837e-05) (hash(x)=26737440) +3338 train 6.988744 (lr=6.4788e-05) (hash(x)=24472271) +3339 train 6.929541 (lr=6.4739e-05) (hash(x)=24407484) +3340 train 7.502034 (lr=6.4690e-05) (hash(x)=27908937) +3341 train 7.636569 (lr=6.4641e-05) (hash(x)=29038937) +3342 train 7.402420 (lr=6.4592e-05) (hash(x)=24802580) +3343 train 7.388381 (lr=6.4544e-05) (hash(x)=27213318) +3344 train 7.459335 (lr=6.4495e-05) (hash(x)=28693458) +3345 train 6.741581 (lr=6.4446e-05) (hash(x)=20332324) +3346 train 7.137976 (lr=6.4397e-05) (hash(x)=26726007) +3347 train 7.022866 (lr=6.4348e-05) (hash(x)=25524191) +3348 train 7.128697 (lr=6.4300e-05) (hash(x)=25553293) +3349 train 7.055780 (lr=6.4251e-05) (hash(x)=25614848) +3350 val loss 7.1404 +3350 val perplexity 1261.8788 +3350 train 7.168868 (lr=6.4202e-05) (hash(x)=25747903) +3351 train 7.133882 (lr=6.4154e-05) (hash(x)=26701577) +3352 train 6.874597 (lr=6.4105e-05) (hash(x)=21964135) +3353 train 6.990105 (lr=6.4056e-05) (hash(x)=24461007) +3354 train 7.036818 (lr=6.4008e-05) (hash(x)=25818495) +3355 train 6.860537 (lr=6.3959e-05) (hash(x)=22091266) +3356 train 6.841660 (lr=6.3911e-05) (hash(x)=24476213) +3357 train 7.221990 (lr=6.3862e-05) (hash(x)=24500423) +3358 train 6.992358 (lr=6.3813e-05) (hash(x)=21754841) +3359 train 7.308739 (lr=6.3765e-05) (hash(x)=26216794) +3360 train 6.795928 (lr=6.3716e-05) (hash(x)=24267249) +3361 train 7.123514 (lr=6.3668e-05) (hash(x)=23143515) +3362 train 6.991369 (lr=6.3619e-05) (hash(x)=24120302) +3363 train 7.182474 (lr=6.3571e-05) (hash(x)=20817340) +3364 train 7.150755 (lr=6.3522e-05) (hash(x)=22285847) +3365 train 7.435031 (lr=6.3474e-05) (hash(x)=28151597) +3366 train 7.864653 (lr=6.3426e-05) (hash(x)=31593285) +3367 train 7.494623 (lr=6.3377e-05) (hash(x)=27579623) +3368 train 7.115264 (lr=6.3329e-05) (hash(x)=24995988) +3369 train 6.723477 (lr=6.3281e-05) (hash(x)=22166810) +3370 train 6.988903 (lr=6.3232e-05) (hash(x)=23948298) +3371 train 6.867771 (lr=6.3184e-05) (hash(x)=21532187) +3372 train 6.975110 (lr=6.3136e-05) (hash(x)=23571652) +3373 train 7.372972 (lr=6.3087e-05) (hash(x)=26911513) +3374 train 7.302200 (lr=6.3039e-05) (hash(x)=24011329) +3375 train 7.492723 (lr=6.2991e-05) (hash(x)=26086198) +3376 train 7.067785 (lr=6.2943e-05) (hash(x)=22844402) +3377 train 7.029401 (lr=6.2894e-05) (hash(x)=21817762) +3378 train 7.063873 (lr=6.2846e-05) (hash(x)=23903232) +3379 train 7.052910 (lr=6.2798e-05) (hash(x)=23911729) +3380 train 7.050874 (lr=6.2750e-05) (hash(x)=24485288) +3381 train 7.223987 (lr=6.2702e-05) (hash(x)=27955492) +3382 train 6.917134 (lr=6.2654e-05) (hash(x)=25884586) +3383 train 7.145415 (lr=6.2606e-05) (hash(x)=24863441) +3384 train 7.422491 (lr=6.2557e-05) (hash(x)=22045992) +3385 train 7.547006 (lr=6.2509e-05) (hash(x)=29174796) +3386 train 7.820518 (lr=6.2461e-05) (hash(x)=32589942) +3387 train 7.426489 (lr=6.2413e-05) (hash(x)=28856978) +3388 train 6.884891 (lr=6.2365e-05) (hash(x)=21667904) +3389 train 6.903732 (lr=6.2317e-05) (hash(x)=23431801) +3390 train 6.701974 (lr=6.2269e-05) (hash(x)=20877285) +3391 train 6.966258 (lr=6.2221e-05) (hash(x)=25236385) +3392 train 7.181122 (lr=6.2174e-05) (hash(x)=25373071) +3393 train 7.318935 (lr=6.2126e-05) (hash(x)=25713464) +3394 train 7.295931 (lr=6.2078e-05) (hash(x)=25713475) +3395 train 7.155277 (lr=6.2030e-05) (hash(x)=24278687) +3396 train 7.263828 (lr=6.1982e-05) (hash(x)=27491349) +3397 train 7.165322 (lr=6.1934e-05) (hash(x)=24513692) +3398 train 7.271137 (lr=6.1886e-05) (hash(x)=26853415) +3399 train 7.340990 (lr=6.1839e-05) (hash(x)=25330803) +3400 val loss 7.1174 +3400 val perplexity 1233.1794 +3400 train 7.303411 (lr=6.1791e-05) (hash(x)=26578066) +3401 train 7.350752 (lr=6.1743e-05) (hash(x)=26811522) +3402 train 7.032146 (lr=6.1695e-05) (hash(x)=25611092) +3403 train 6.843778 (lr=6.1648e-05) (hash(x)=21568545) +3404 train 6.852277 (lr=6.1600e-05) (hash(x)=22756484) +3405 train 7.133625 (lr=6.1552e-05) (hash(x)=27927608) +3406 train 7.151462 (lr=6.1505e-05) (hash(x)=27497018) +3407 train 6.954147 (lr=6.1457e-05) (hash(x)=22508532) +3408 train 7.392793 (lr=6.1409e-05) (hash(x)=26673287) +3409 train 7.047146 (lr=6.1362e-05) (hash(x)=23675869) +3410 train 6.977672 (lr=6.1314e-05) (hash(x)=25496948) +3411 train 6.973389 (lr=6.1267e-05) (hash(x)=24850662) +3412 train 7.233255 (lr=6.1219e-05) (hash(x)=29790167) +3413 train 6.879702 (lr=6.1172e-05) (hash(x)=24193434) +3414 train 7.248301 (lr=6.1124e-05) (hash(x)=25310919) +3415 train 6.947469 (lr=6.1077e-05) (hash(x)=21799261) +3416 train 7.257054 (lr=6.1029e-05) (hash(x)=26620074) +3417 train 7.214849 (lr=6.0982e-05) (hash(x)=26719309) +3418 train 7.560681 (lr=6.0934e-05) (hash(x)=23190530) +3419 train 7.139218 (lr=6.0887e-05) (hash(x)=24884891) +3420 train 7.128007 (lr=6.0839e-05) (hash(x)=25545849) +3421 train 7.093727 (lr=6.0792e-05) (hash(x)=26021405) +3422 train 7.029350 (lr=6.0745e-05) (hash(x)=23887343) +3423 train 7.118079 (lr=6.0697e-05) (hash(x)=26311168) +3424 train 6.789440 (lr=6.0650e-05) (hash(x)=21051541) +3425 train 7.150314 (lr=6.0603e-05) (hash(x)=23553179) +3426 train 7.015531 (lr=6.0556e-05) (hash(x)=24345540) +3427 train 7.451400 (lr=6.0508e-05) (hash(x)=27549895) +3428 train 6.800299 (lr=6.0461e-05) (hash(x)=22559753) +3429 train 6.756075 (lr=6.0414e-05) (hash(x)=21647642) +3430 train 6.648134 (lr=6.0367e-05) (hash(x)=20130901) +3431 train 6.809034 (lr=6.0320e-05) (hash(x)=20977430) +3432 train 6.792105 (lr=6.0272e-05) (hash(x)=21356429) +3433 train 6.798291 (lr=6.0225e-05) (hash(x)=23494380) +3434 train 7.062082 (lr=6.0178e-05) (hash(x)=23805501) +3435 train 7.019948 (lr=6.0131e-05) (hash(x)=23448855) +3436 train 7.370993 (lr=6.0084e-05) (hash(x)=26000319) +3437 train 6.858217 (lr=6.0037e-05) (hash(x)=21760032) +3438 train 6.993489 (lr=5.9990e-05) (hash(x)=24424886) +3439 train 7.403548 (lr=5.9943e-05) (hash(x)=26941617) +3440 train 7.378870 (lr=5.9896e-05) (hash(x)=26798528) +3441 train 7.416928 (lr=5.9849e-05) (hash(x)=27464193) +3442 train 7.305092 (lr=5.9802e-05) (hash(x)=25649118) +3443 train 7.328668 (lr=5.9755e-05) (hash(x)=26953192) +3444 train 7.159015 (lr=5.9708e-05) (hash(x)=22224958) +3445 train 6.964789 (lr=5.9661e-05) (hash(x)=24044587) +3446 train 7.427846 (lr=5.9614e-05) (hash(x)=29584466) +3447 train 7.826430 (lr=5.9567e-05) (hash(x)=30008957) +3448 train 7.697886 (lr=5.9521e-05) (hash(x)=26059290) +3449 train 6.664094 (lr=5.9474e-05) (hash(x)=19733965) +3450 val loss 7.1384 +3450 val perplexity 1259.3884 +3450 train 7.170514 (lr=5.9427e-05) (hash(x)=23960200) +3451 train 7.332956 (lr=5.9380e-05) (hash(x)=27069893) +3452 train 6.998229 (lr=5.9333e-05) (hash(x)=23947772) +3453 train 7.073467 (lr=5.9287e-05) (hash(x)=22707406) +3454 train 7.226898 (lr=5.9240e-05) (hash(x)=27832550) +3455 train 7.113556 (lr=5.9193e-05) (hash(x)=27125962) +3456 train 6.985584 (lr=5.9147e-05) (hash(x)=24510254) +3457 train 6.787145 (lr=5.9100e-05) (hash(x)=23545652) +3458 train 6.863473 (lr=5.9053e-05) (hash(x)=23554751) +3459 train 7.007847 (lr=5.9007e-05) (hash(x)=23341415) +3460 train 7.165324 (lr=5.8960e-05) (hash(x)=21784583) +3461 train 6.937100 (lr=5.8914e-05) (hash(x)=22214769) +3462 train 7.014643 (lr=5.8867e-05) (hash(x)=24206922) +3463 train 7.127789 (lr=5.8820e-05) (hash(x)=25888358) +3464 train 6.932414 (lr=5.8774e-05) (hash(x)=22689666) +3465 train 7.069801 (lr=5.8727e-05) (hash(x)=24918697) +3466 train 7.359544 (lr=5.8681e-05) (hash(x)=28237214) +3467 train 7.431041 (lr=5.8635e-05) (hash(x)=26761645) +3468 train 7.093057 (lr=5.8588e-05) (hash(x)=26979307) +3469 train 7.017439 (lr=5.8542e-05) (hash(x)=23553754) +3470 train 7.161584 (lr=5.8495e-05) (hash(x)=25256849) +3471 train 6.987869 (lr=5.8449e-05) (hash(x)=21725719) +3472 train 7.102475 (lr=5.8403e-05) (hash(x)=24897801) +3473 train 7.044076 (lr=5.8356e-05) (hash(x)=26175307) +3474 train 6.851785 (lr=5.8310e-05) (hash(x)=23309218) +3475 train 6.942183 (lr=5.8264e-05) (hash(x)=25746493) +3476 train 7.255794 (lr=5.8217e-05) (hash(x)=27169613) +3477 train 6.951718 (lr=5.8171e-05) (hash(x)=22937341) +3478 train 7.044981 (lr=5.8125e-05) (hash(x)=24250636) +3479 train 6.880301 (lr=5.8079e-05) (hash(x)=21669704) +3480 train 6.904047 (lr=5.8032e-05) (hash(x)=24431839) +3481 train 6.914331 (lr=5.7986e-05) (hash(x)=22763387) +3482 train 6.904382 (lr=5.7940e-05) (hash(x)=20489446) +3483 train 6.874206 (lr=5.7894e-05) (hash(x)=21167493) +3484 train 6.895117 (lr=5.7848e-05) (hash(x)=23465087) +3485 train 7.110462 (lr=5.7802e-05) (hash(x)=26175023) +3486 train 7.191982 (lr=5.7756e-05) (hash(x)=24986207) +3487 train 6.763570 (lr=5.7710e-05) (hash(x)=23166993) +3488 train 7.060716 (lr=5.7664e-05) (hash(x)=25281216) +3489 train 6.843430 (lr=5.7618e-05) (hash(x)=21824285) +3490 train 6.885262 (lr=5.7572e-05) (hash(x)=22352750) +3491 train 7.145956 (lr=5.7526e-05) (hash(x)=23947208) +3492 train 7.197818 (lr=5.7480e-05) (hash(x)=26257363) +3493 train 7.030522 (lr=5.7434e-05) (hash(x)=25103214) +3494 train 7.076901 (lr=5.7388e-05) (hash(x)=25267583) +3495 train 7.133260 (lr=5.7342e-05) (hash(x)=26235974) +3496 train 7.347522 (lr=5.7296e-05) (hash(x)=26430769) +3497 train 7.741718 (lr=5.7250e-05) (hash(x)=28282027) +3498 train 7.641948 (lr=5.7205e-05) (hash(x)=28386462) +3499 train 7.240474 (lr=5.7159e-05) (hash(x)=29822604) +3500 val loss 7.1226 +3500 val perplexity 1239.6536 +3500 train 7.143575 (lr=5.7113e-05) (hash(x)=29225386) +3501 train 7.043247 (lr=5.7067e-05) (hash(x)=25249294) +3502 train 6.801129 (lr=5.7022e-05) (hash(x)=20020741) +3503 train 6.961115 (lr=5.6976e-05) (hash(x)=25426430) +3504 train 6.925502 (lr=5.6930e-05) (hash(x)=25720411) +3505 train 6.968417 (lr=5.6884e-05) (hash(x)=25602639) +3506 train 7.057599 (lr=5.6839e-05) (hash(x)=26724388) +3507 train 6.981787 (lr=5.6793e-05) (hash(x)=26043735) +3508 train 6.957069 (lr=5.6748e-05) (hash(x)=24955163) +3509 train 6.911157 (lr=5.6702e-05) (hash(x)=20936107) +3510 train 6.897719 (lr=5.6656e-05) (hash(x)=20317378) +3511 train 6.921356 (lr=5.6611e-05) (hash(x)=22966314) +3512 train 7.262389 (lr=5.6565e-05) (hash(x)=25870930) +3513 train 7.104887 (lr=5.6520e-05) (hash(x)=24656635) +3514 train 7.368011 (lr=5.6474e-05) (hash(x)=28576810) +3515 train 7.278364 (lr=5.6429e-05) (hash(x)=27944619) +3516 train 7.116209 (lr=5.6384e-05) (hash(x)=27421509) +3517 train 6.849337 (lr=5.6338e-05) (hash(x)=20844620) +3518 train 7.067998 (lr=5.6293e-05) (hash(x)=28569406) +3519 train 6.946813 (lr=5.6247e-05) (hash(x)=23448505) +3520 train 7.125846 (lr=5.6202e-05) (hash(x)=24852577) +3521 train 7.020425 (lr=5.6157e-05) (hash(x)=23963103) +3522 train 6.897206 (lr=5.6111e-05) (hash(x)=24816516) +3523 train 7.092529 (lr=5.6066e-05) (hash(x)=24205942) +3524 train 6.664173 (lr=5.6021e-05) (hash(x)=20988660) +3525 train 6.754619 (lr=5.5976e-05) (hash(x)=21631366) +3526 train 6.952188 (lr=5.5930e-05) (hash(x)=23499370) +3527 train 7.083072 (lr=5.5885e-05) (hash(x)=26330693) +3528 train 6.704967 (lr=5.5840e-05) (hash(x)=23937176) +3529 train 7.032383 (lr=5.5795e-05) (hash(x)=27345885) +3530 train 6.702667 (lr=5.5750e-05) (hash(x)=21104610) +3531 train 7.096806 (lr=5.5704e-05) (hash(x)=24844466) +3532 train 6.446675 (lr=5.5659e-05) (hash(x)=21055483) +3533 train 6.788758 (lr=5.5614e-05) (hash(x)=23229414) +3534 train 7.121053 (lr=5.5569e-05) (hash(x)=26676920) +3535 train 7.070135 (lr=5.5524e-05) (hash(x)=29550596) +3536 train 6.836232 (lr=5.5479e-05) (hash(x)=22231942) +3537 train 7.019872 (lr=5.5434e-05) (hash(x)=25843852) +3538 train 7.171552 (lr=5.5389e-05) (hash(x)=27110533) +3539 train 6.692473 (lr=5.5344e-05) (hash(x)=20506540) +3540 train 6.820686 (lr=5.5299e-05) (hash(x)=21599346) +3541 train 7.036655 (lr=5.5254e-05) (hash(x)=26395519) +3542 train 6.997228 (lr=5.5210e-05) (hash(x)=25892512) +3543 train 7.056850 (lr=5.5165e-05) (hash(x)=22124892) +3544 train 6.933423 (lr=5.5120e-05) (hash(x)=21882567) +3545 train 7.014021 (lr=5.5075e-05) (hash(x)=24316212) +3546 train 6.929475 (lr=5.5030e-05) (hash(x)=24296310) +3547 train 7.031747 (lr=5.4986e-05) (hash(x)=24867036) +3548 train 7.011091 (lr=5.4941e-05) (hash(x)=23351896) +3549 train 6.979256 (lr=5.4896e-05) (hash(x)=21576408) +3550 val loss 7.1087 +3550 val perplexity 1222.5383 +3550 train 7.120179 (lr=5.4851e-05) (hash(x)=26377338) +3551 train 6.948299 (lr=5.4807e-05) (hash(x)=25607640) +3552 train 7.253869 (lr=5.4762e-05) (hash(x)=27619776) +3553 train 6.760242 (lr=5.4717e-05) (hash(x)=23454533) +3554 train 6.953031 (lr=5.4673e-05) (hash(x)=22542519) +3555 train 7.011720 (lr=5.4628e-05) (hash(x)=26176930) +3556 train 6.800060 (lr=5.4584e-05) (hash(x)=22815181) +3557 train 6.798984 (lr=5.4539e-05) (hash(x)=21821757) +3558 train 6.838315 (lr=5.4494e-05) (hash(x)=23988293) +3559 train 6.752194 (lr=5.4450e-05) (hash(x)=23795894) +3560 train 6.706029 (lr=5.4405e-05) (hash(x)=22898969) +3561 train 6.726742 (lr=5.4361e-05) (hash(x)=21510825) +3562 train 6.652547 (lr=5.4317e-05) (hash(x)=22499317) +3563 train 6.664512 (lr=5.4272e-05) (hash(x)=23756298) +3564 train 6.719833 (lr=5.4228e-05) (hash(x)=23964512) +3565 train 6.819001 (lr=5.4183e-05) (hash(x)=23262803) +3566 train 7.015667 (lr=5.4139e-05) (hash(x)=23347279) +3567 train 6.914861 (lr=5.4095e-05) (hash(x)=24165449) +3568 train 7.034593 (lr=5.4050e-05) (hash(x)=25503946) +3569 train 7.013870 (lr=5.4006e-05) (hash(x)=26532839) +3570 train 6.667861 (lr=5.3962e-05) (hash(x)=21889816) +3571 train 6.960443 (lr=5.3918e-05) (hash(x)=26643739) +3572 train 7.176727 (lr=5.3873e-05) (hash(x)=26826130) +3573 train 7.169515 (lr=5.3829e-05) (hash(x)=25810624) +3574 train 7.036121 (lr=5.3785e-05) (hash(x)=23080331) +3575 train 7.170986 (lr=5.3741e-05) (hash(x)=24697756) +3576 train 7.028348 (lr=5.3697e-05) (hash(x)=25158900) +3577 train 7.154454 (lr=5.3652e-05) (hash(x)=25793633) +3578 train 6.707489 (lr=5.3608e-05) (hash(x)=21468493) +3579 train 7.079447 (lr=5.3564e-05) (hash(x)=24431101) +3580 train 6.943408 (lr=5.3520e-05) (hash(x)=27314357) +3581 train 7.153852 (lr=5.3476e-05) (hash(x)=26286249) +3582 train 7.371181 (lr=5.3432e-05) (hash(x)=25954856) +3583 train 7.247802 (lr=5.3388e-05) (hash(x)=27218899) +3584 train 7.045213 (lr=5.3344e-05) (hash(x)=24249114) +3585 train 6.926231 (lr=5.3300e-05) (hash(x)=23659934) +3586 train 6.915803 (lr=5.3256e-05) (hash(x)=25995600) +3587 train 6.890531 (lr=5.3213e-05) (hash(x)=29462219) +3588 train 7.014607 (lr=5.3169e-05) (hash(x)=23346714) +3589 train 7.119308 (lr=5.3125e-05) (hash(x)=27168432) +3590 train 6.936012 (lr=5.3081e-05) (hash(x)=23954240) +3591 train 6.910948 (lr=5.3037e-05) (hash(x)=24748522) +3592 train 7.095757 (lr=5.2993e-05) (hash(x)=24887007) +3593 train 6.867828 (lr=5.2950e-05) (hash(x)=25539383) +3594 train 6.774467 (lr=5.2906e-05) (hash(x)=20104613) +3595 train 7.307753 (lr=5.2862e-05) (hash(x)=24843486) +3596 train 7.294258 (lr=5.2819e-05) (hash(x)=24357864) +3597 train 6.989465 (lr=5.2775e-05) (hash(x)=23873745) +3598 train 7.130965 (lr=5.2731e-05) (hash(x)=25142829) +3599 train 7.217069 (lr=5.2688e-05) (hash(x)=24965317) +3600 val loss 7.0953 +3600 val perplexity 1206.2539 +3600 train 6.656059 (lr=5.2644e-05) (hash(x)=18505205) +3601 train 6.701268 (lr=5.2600e-05) (hash(x)=23632877) +3602 train 6.954048 (lr=5.2557e-05) (hash(x)=23704554) +3603 train 7.105755 (lr=5.2513e-05) (hash(x)=26584754) +3604 train 6.729775 (lr=5.2470e-05) (hash(x)=20667709) +3605 train 6.601678 (lr=5.2426e-05) (hash(x)=20573248) +3606 train 6.762630 (lr=5.2383e-05) (hash(x)=23998997) +3607 train 6.936317 (lr=5.2339e-05) (hash(x)=22031210) +3608 train 7.016468 (lr=5.2296e-05) (hash(x)=24124536) +3609 train 6.906371 (lr=5.2253e-05) (hash(x)=22650144) +3610 train 6.977163 (lr=5.2209e-05) (hash(x)=23796998) +3611 train 7.040189 (lr=5.2166e-05) (hash(x)=24860582) +3612 train 6.558614 (lr=5.2123e-05) (hash(x)=20591300) +3613 train 6.979147 (lr=5.2079e-05) (hash(x)=23447130) +3614 train 6.990274 (lr=5.2036e-05) (hash(x)=26237963) +3615 train 7.102047 (lr=5.1993e-05) (hash(x)=25877990) +3616 train 6.872406 (lr=5.1950e-05) (hash(x)=24808003) +3617 train 7.078603 (lr=5.1906e-05) (hash(x)=24103543) +3618 train 6.987171 (lr=5.1863e-05) (hash(x)=24877184) +3619 train 7.068091 (lr=5.1820e-05) (hash(x)=24970646) +3620 train 7.032666 (lr=5.1777e-05) (hash(x)=25764524) +3621 train 7.217117 (lr=5.1734e-05) (hash(x)=25313591) +3622 train 7.066620 (lr=5.1691e-05) (hash(x)=23260940) +3623 train 6.975691 (lr=5.1648e-05) (hash(x)=24382381) +3624 train 6.937982 (lr=5.1605e-05) (hash(x)=24618902) +3625 train 7.108724 (lr=5.1562e-05) (hash(x)=25074871) +3626 train 6.798194 (lr=5.1519e-05) (hash(x)=24472251) +3627 train 6.936564 (lr=5.1476e-05) (hash(x)=25221746) +3628 train 7.043478 (lr=5.1433e-05) (hash(x)=27448790) +3629 train 7.046954 (lr=5.1390e-05) (hash(x)=25221431) +3630 train 6.602681 (lr=5.1347e-05) (hash(x)=22034366) +3631 train 7.170327 (lr=5.1304e-05) (hash(x)=24551999) +3632 train 6.848349 (lr=5.1261e-05) (hash(x)=24330217) +3633 train 6.972655 (lr=5.1218e-05) (hash(x)=22792380) +3634 train 6.769287 (lr=5.1175e-05) (hash(x)=22393767) +3635 train 7.090984 (lr=5.1133e-05) (hash(x)=28151378) +3636 train 7.125993 (lr=5.1090e-05) (hash(x)=26999341) +3637 train 7.096141 (lr=5.1047e-05) (hash(x)=27251870) +3638 train 7.059551 (lr=5.1004e-05) (hash(x)=23439462) +3639 train 7.165660 (lr=5.0962e-05) (hash(x)=25765516) +3640 train 7.016300 (lr=5.0919e-05) (hash(x)=24720171) +3641 train 7.191517 (lr=5.0876e-05) (hash(x)=23927187) +3642 train 6.968964 (lr=5.0834e-05) (hash(x)=23879561) +3643 train 7.101719 (lr=5.0791e-05) (hash(x)=25630696) +3644 train 6.700916 (lr=5.0748e-05) (hash(x)=22030016) +3645 train 7.157104 (lr=5.0706e-05) (hash(x)=28781600) +3646 train 7.152255 (lr=5.0663e-05) (hash(x)=26668019) +3647 train 7.190684 (lr=5.0621e-05) (hash(x)=25204247) +3648 train 7.430368 (lr=5.0578e-05) (hash(x)=31261394) +3649 train 7.198736 (lr=5.0536e-05) (hash(x)=26193103) +3650 val loss 7.1035 +3650 val perplexity 1216.1635 +3650 train 7.036748 (lr=5.0493e-05) (hash(x)=23872456) +3651 train 6.942176 (lr=5.0451e-05) (hash(x)=26326447) +3652 train 6.927716 (lr=5.0409e-05) (hash(x)=26449631) +3653 train 7.184312 (lr=5.0366e-05) (hash(x)=26373461) +3654 train 7.043766 (lr=5.0324e-05) (hash(x)=24882768) +3655 train 7.130669 (lr=5.0282e-05) (hash(x)=26321813) +3656 train 7.138513 (lr=5.0239e-05) (hash(x)=27056428) +3657 train 7.121913 (lr=5.0197e-05) (hash(x)=24583976) +3658 train 6.832155 (lr=5.0155e-05) (hash(x)=22259624) +3659 train 6.952775 (lr=5.0112e-05) (hash(x)=25400396) +3660 train 6.830419 (lr=5.0070e-05) (hash(x)=21095507) +3661 train 7.057298 (lr=5.0028e-05) (hash(x)=27231042) +3662 train 6.855663 (lr=4.9986e-05) (hash(x)=27292771) +3663 train 7.265492 (lr=4.9944e-05) (hash(x)=25528323) +3664 train 7.045364 (lr=4.9902e-05) (hash(x)=24374502) +3665 train 6.820806 (lr=4.9860e-05) (hash(x)=22463800) +3666 train 7.116286 (lr=4.9817e-05) (hash(x)=25413960) +3667 train 7.033077 (lr=4.9775e-05) (hash(x)=24035353) +3668 train 6.967783 (lr=4.9733e-05) (hash(x)=24815852) +3669 train 6.847517 (lr=4.9691e-05) (hash(x)=22995856) +3670 train 7.121884 (lr=4.9649e-05) (hash(x)=28128238) +3671 train 7.130292 (lr=4.9608e-05) (hash(x)=25114729) +3672 train 6.878857 (lr=4.9566e-05) (hash(x)=19337726) +3673 train 7.310966 (lr=4.9524e-05) (hash(x)=26674420) +3674 train 6.827402 (lr=4.9482e-05) (hash(x)=22553270) +3675 train 6.674661 (lr=4.9440e-05) (hash(x)=21634962) +3676 train 6.869205 (lr=4.9398e-05) (hash(x)=23362669) +3677 train 7.030382 (lr=4.9356e-05) (hash(x)=24781824) +3678 train 6.530483 (lr=4.9315e-05) (hash(x)=17909688) +3679 train 7.783731 (lr=4.9273e-05) (hash(x)=31341964) +3680 train 7.285529 (lr=4.9231e-05) (hash(x)=29071335) +3681 train 6.701497 (lr=4.9189e-05) (hash(x)=19486640) +3682 train 6.868552 (lr=4.9148e-05) (hash(x)=24301133) +3683 train 7.053269 (lr=4.9106e-05) (hash(x)=29172813) +3684 train 7.587152 (lr=4.9064e-05) (hash(x)=31501337) +3685 train 7.188068 (lr=4.9023e-05) (hash(x)=27377840) +3686 train 6.969838 (lr=4.8981e-05) (hash(x)=24499761) +3687 train 6.967233 (lr=4.8940e-05) (hash(x)=26326024) +3688 train 6.960197 (lr=4.8898e-05) (hash(x)=23179996) +3689 train 6.630077 (lr=4.8857e-05) (hash(x)=20963675) +3690 train 6.944138 (lr=4.8815e-05) (hash(x)=26650521) +3691 train 6.655207 (lr=4.8774e-05) (hash(x)=20140071) +3692 train 6.684345 (lr=4.8732e-05) (hash(x)=21734340) +3693 train 6.972554 (lr=4.8691e-05) (hash(x)=23848422) +3694 train 7.028812 (lr=4.8649e-05) (hash(x)=27499953) +3695 train 7.271405 (lr=4.8608e-05) (hash(x)=27273311) +3696 train 7.196232 (lr=4.8567e-05) (hash(x)=25741091) +3697 train 6.916246 (lr=4.8525e-05) (hash(x)=22010794) +3698 train 7.039707 (lr=4.8484e-05) (hash(x)=24616138) +3699 train 7.408128 (lr=4.8443e-05) (hash(x)=31276487) +3700 val loss 7.1019 +3700 val perplexity 1214.2924 +3700 train 7.040924 (lr=4.8401e-05) (hash(x)=24042922) +3701 train 6.804964 (lr=4.8360e-05) (hash(x)=21985431) +3702 train 6.665517 (lr=4.8319e-05) (hash(x)=21336316) +3703 train 6.507131 (lr=4.8278e-05) (hash(x)=17819313) +3704 train 7.179425 (lr=4.8237e-05) (hash(x)=27033851) +3705 train 7.186991 (lr=4.8196e-05) (hash(x)=27260043) +3706 train 7.248747 (lr=4.8154e-05) (hash(x)=26847649) +3707 train 7.178084 (lr=4.8113e-05) (hash(x)=25843618) +3708 train 7.162881 (lr=4.8072e-05) (hash(x)=25828009) +3709 train 7.224145 (lr=4.8031e-05) (hash(x)=24960960) +3710 train 7.303833 (lr=4.7990e-05) (hash(x)=24852741) +3711 train 6.786285 (lr=4.7949e-05) (hash(x)=23769243) +3712 train 6.997776 (lr=4.7908e-05) (hash(x)=27110690) +3713 train 6.980096 (lr=4.7867e-05) (hash(x)=22817285) +3714 train 6.673269 (lr=4.7827e-05) (hash(x)=19618355) +3715 train 7.268684 (lr=4.7786e-05) (hash(x)=28731298) +3716 train 6.981859 (lr=4.7745e-05) (hash(x)=23091196) +3717 train 7.531285 (lr=4.7704e-05) (hash(x)=28825233) +3718 train 7.083013 (lr=4.7663e-05) (hash(x)=25778506) +3719 train 7.043663 (lr=4.7622e-05) (hash(x)=23788738) +3720 train 6.352144 (lr=4.7582e-05) (hash(x)=16684794) +3721 train 6.874713 (lr=4.7541e-05) (hash(x)=24755102) +3722 train 7.188213 (lr=4.7500e-05) (hash(x)=26839238) +3723 train 7.222164 (lr=4.7460e-05) (hash(x)=26599031) +3724 train 7.047443 (lr=4.7419e-05) (hash(x)=25945650) +3725 train 7.258283 (lr=4.7378e-05) (hash(x)=27434751) +3726 train 6.976257 (lr=4.7338e-05) (hash(x)=24814591) +3727 train 6.946407 (lr=4.7297e-05) (hash(x)=24818744) +3728 train 7.037641 (lr=4.7256e-05) (hash(x)=25649817) +3729 train 6.938594 (lr=4.7216e-05) (hash(x)=24987021) +3730 train 6.880712 (lr=4.7175e-05) (hash(x)=24667779) +3731 train 6.865073 (lr=4.7135e-05) (hash(x)=23053871) +3732 train 6.566541 (lr=4.7094e-05) (hash(x)=19264856) +3733 train 7.158261 (lr=4.7054e-05) (hash(x)=23718117) +3734 train 6.875234 (lr=4.7014e-05) (hash(x)=21904779) +3735 train 7.058122 (lr=4.6973e-05) (hash(x)=23472795) +3736 train 7.290699 (lr=4.6933e-05) (hash(x)=24650440) +3737 train 7.344112 (lr=4.6893e-05) (hash(x)=25243911) +3738 train 7.734987 (lr=4.6852e-05) (hash(x)=30423616) +3739 train 7.741172 (lr=4.6812e-05) (hash(x)=29748225) +3740 train 7.125444 (lr=4.6772e-05) (hash(x)=25180684) +3741 train 7.157187 (lr=4.6731e-05) (hash(x)=25619065) +3742 train 7.511363 (lr=4.6691e-05) (hash(x)=31847002) +3743 train 7.061914 (lr=4.6651e-05) (hash(x)=24991832) +3744 train 7.012665 (lr=4.6611e-05) (hash(x)=23836263) +3745 train 6.873955 (lr=4.6571e-05) (hash(x)=24651902) +3746 train 7.439448 (lr=4.6531e-05) (hash(x)=22936538) +3747 train 7.414540 (lr=4.6491e-05) (hash(x)=23681545) +3748 train 6.845905 (lr=4.6450e-05) (hash(x)=21140825) +3749 train 7.017743 (lr=4.6410e-05) (hash(x)=24932453) +3750 val loss 7.1103 +3750 val perplexity 1224.4846 +3750 train 7.170448 (lr=4.6370e-05) (hash(x)=25919062) +3751 train 6.967718 (lr=4.6330e-05) (hash(x)=22424066) +3752 train 7.007515 (lr=4.6290e-05) (hash(x)=23542210) +3753 train 6.893889 (lr=4.6251e-05) (hash(x)=22113561) +3754 train 6.800858 (lr=4.6211e-05) (hash(x)=24892794) +3755 train 7.278446 (lr=4.6171e-05) (hash(x)=25262748) +3756 train 7.059308 (lr=4.6131e-05) (hash(x)=24477975) +3757 train 6.854448 (lr=4.6091e-05) (hash(x)=24681189) +3758 train 6.890843 (lr=4.6051e-05) (hash(x)=24052603) +3759 train 7.118306 (lr=4.6011e-05) (hash(x)=26474878) +3760 train 7.675099 (lr=4.5972e-05) (hash(x)=28228836) +3761 train 7.197241 (lr=4.5932e-05) (hash(x)=23832522) +3762 train 7.135274 (lr=4.5892e-05) (hash(x)=24416789) +3763 train 6.902349 (lr=4.5853e-05) (hash(x)=23930593) +3764 train 6.942853 (lr=4.5813e-05) (hash(x)=23895092) +3765 train 6.909672 (lr=4.5773e-05) (hash(x)=26865287) +3766 train 6.915930 (lr=4.5734e-05) (hash(x)=21330722) +3767 train 7.017463 (lr=4.5694e-05) (hash(x)=22704349) +3768 train 7.143519 (lr=4.5654e-05) (hash(x)=27740886) +3769 train 7.114095 (lr=4.5615e-05) (hash(x)=24935936) +3770 train 6.983740 (lr=4.5575e-05) (hash(x)=23497487) +3771 train 7.177302 (lr=4.5536e-05) (hash(x)=24801048) +3772 train 6.934674 (lr=4.5496e-05) (hash(x)=25490486) +3773 train 6.951388 (lr=4.5457e-05) (hash(x)=21166466) +3774 train 7.136951 (lr=4.5418e-05) (hash(x)=23225244) +3775 train 6.928411 (lr=4.5378e-05) (hash(x)=22293673) +3776 train 7.228926 (lr=4.5339e-05) (hash(x)=25700016) +3777 train 6.781581 (lr=4.5300e-05) (hash(x)=22370207) +3778 train 7.108845 (lr=4.5260e-05) (hash(x)=25224849) +3779 train 7.011074 (lr=4.5221e-05) (hash(x)=23311934) +3780 train 6.722885 (lr=4.5182e-05) (hash(x)=19627124) +3781 train 7.291686 (lr=4.5143e-05) (hash(x)=27132838) +3782 train 7.232997 (lr=4.5103e-05) (hash(x)=27242104) +3783 train 6.725170 (lr=4.5064e-05) (hash(x)=21785487) +3784 train 7.044966 (lr=4.5025e-05) (hash(x)=25798262) +3785 train 6.944482 (lr=4.4986e-05) (hash(x)=24806937) +3786 train 6.770303 (lr=4.4947e-05) (hash(x)=24098756) +3787 train 6.795043 (lr=4.4908e-05) (hash(x)=22981456) +3788 train 7.238454 (lr=4.4869e-05) (hash(x)=22441908) +3789 train 7.105759 (lr=4.4830e-05) (hash(x)=25867804) +3790 train 7.066152 (lr=4.4791e-05) (hash(x)=22835586) +3791 train 7.249055 (lr=4.4752e-05) (hash(x)=25251063) +3792 train 7.132482 (lr=4.4713e-05) (hash(x)=27059729) +3793 train 7.065801 (lr=4.4674e-05) (hash(x)=23819311) +3794 train 6.756040 (lr=4.4635e-05) (hash(x)=21345757) +3795 train 6.988245 (lr=4.4596e-05) (hash(x)=25796422) +3796 train 6.689575 (lr=4.4557e-05) (hash(x)=21414971) +3797 train 6.990537 (lr=4.4518e-05) (hash(x)=26120920) +3798 train 6.919858 (lr=4.4480e-05) (hash(x)=22008247) +3799 train 7.000957 (lr=4.4441e-05) (hash(x)=22722211) +3800 val loss 7.0972 +3800 val perplexity 1208.5436 +3800 train 6.740930 (lr=4.4402e-05) (hash(x)=24484513) +3801 train 7.084457 (lr=4.4363e-05) (hash(x)=24463866) +3802 train 7.082417 (lr=4.4325e-05) (hash(x)=26470775) +3803 train 7.100566 (lr=4.4286e-05) (hash(x)=24296755) +3804 train 7.094449 (lr=4.4247e-05) (hash(x)=24381309) +3805 train 7.292244 (lr=4.4209e-05) (hash(x)=26781262) +3806 train 6.801267 (lr=4.4170e-05) (hash(x)=23563137) +3807 train 6.991428 (lr=4.4132e-05) (hash(x)=24522269) +3808 train 6.803634 (lr=4.4093e-05) (hash(x)=22871995) +3809 train 7.148352 (lr=4.4055e-05) (hash(x)=24751946) +3810 train 6.945254 (lr=4.4016e-05) (hash(x)=19879741) +3811 train 7.059276 (lr=4.3978e-05) (hash(x)=25617184) +3812 train 6.706757 (lr=4.3939e-05) (hash(x)=21776722) +3813 train 6.824240 (lr=4.3901e-05) (hash(x)=22663402) +3814 train 7.191467 (lr=4.3863e-05) (hash(x)=26072046) +3815 train 6.843803 (lr=4.3824e-05) (hash(x)=23329475) +3816 train 6.934354 (lr=4.3786e-05) (hash(x)=25519031) +3817 train 6.924315 (lr=4.3748e-05) (hash(x)=22846270) +3818 train 6.906410 (lr=4.3709e-05) (hash(x)=20299429) +3819 train 7.350363 (lr=4.3671e-05) (hash(x)=30652062) +3820 train 6.693794 (lr=4.3633e-05) (hash(x)=19824665) +3821 train 7.247463 (lr=4.3595e-05) (hash(x)=26698904) +3822 train 7.068306 (lr=4.3556e-05) (hash(x)=27612163) +3823 train 6.860847 (lr=4.3518e-05) (hash(x)=24735165) +3824 train 6.616693 (lr=4.3480e-05) (hash(x)=19965890) +3825 train 6.764807 (lr=4.3442e-05) (hash(x)=23518594) +3826 train 6.776901 (lr=4.3404e-05) (hash(x)=22388460) +3827 train 6.836887 (lr=4.3366e-05) (hash(x)=23795686) +3828 train 6.737148 (lr=4.3328e-05) (hash(x)=24470150) +3829 train 6.409370 (lr=4.3290e-05) (hash(x)=19483392) +3830 train 6.864007 (lr=4.3252e-05) (hash(x)=23304516) +3831 train 7.202943 (lr=4.3214e-05) (hash(x)=27002892) +3832 train 6.921038 (lr=4.3176e-05) (hash(x)=22114813) +3833 train 7.073500 (lr=4.3138e-05) (hash(x)=26221916) +3834 train 6.626514 (lr=4.3101e-05) (hash(x)=27261960) +3835 train 6.904678 (lr=4.3063e-05) (hash(x)=21189101) +3836 train 6.563249 (lr=4.3025e-05) (hash(x)=20638173) +3837 train 7.026826 (lr=4.2987e-05) (hash(x)=25497439) +3838 train 6.486773 (lr=4.2949e-05) (hash(x)=20460499) +3839 train 6.945578 (lr=4.2912e-05) (hash(x)=23499349) +3840 train 7.793741 (lr=4.2874e-05) (hash(x)=22671939) +3841 train 7.811124 (lr=4.2836e-05) (hash(x)=26809295) +3842 train 7.048923 (lr=4.2799e-05) (hash(x)=28094504) +3843 train 7.022931 (lr=4.2761e-05) (hash(x)=26807896) +3844 train 7.092772 (lr=4.2724e-05) (hash(x)=24749334) +3845 train 7.021413 (lr=4.2686e-05) (hash(x)=25031330) +3846 train 6.895947 (lr=4.2648e-05) (hash(x)=23008126) +3847 train 6.880334 (lr=4.2611e-05) (hash(x)=22461589) +3848 train 7.155920 (lr=4.2573e-05) (hash(x)=24959391) +3849 train 7.038997 (lr=4.2536e-05) (hash(x)=24239512) +3850 val loss 7.0913 +3850 val perplexity 1201.5249 +3850 train 6.879350 (lr=4.2499e-05) (hash(x)=24760422) +3851 train 7.376833 (lr=4.2461e-05) (hash(x)=26904123) +3852 train 6.480432 (lr=4.2424e-05) (hash(x)=17986444) +3853 train 6.831412 (lr=4.2386e-05) (hash(x)=21618533) +3854 train 6.918859 (lr=4.2349e-05) (hash(x)=27107027) +3855 train 7.187974 (lr=4.2312e-05) (hash(x)=26415040) +3856 train 7.717396 (lr=4.2275e-05) (hash(x)=28682703) +3857 train 6.872472 (lr=4.2237e-05) (hash(x)=22824767) +3858 train 7.033785 (lr=4.2200e-05) (hash(x)=24540450) +3859 train 7.012916 (lr=4.2163e-05) (hash(x)=24463181) +3860 train 6.914983 (lr=4.2126e-05) (hash(x)=22832558) +3861 train 7.147830 (lr=4.2089e-05) (hash(x)=26582384) +3862 train 7.826620 (lr=4.2052e-05) (hash(x)=32327364) +3863 train 7.174859 (lr=4.2015e-05) (hash(x)=26349465) +3864 train 6.885663 (lr=4.1977e-05) (hash(x)=23079414) +3865 train 6.945513 (lr=4.1940e-05) (hash(x)=23464639) +3866 train 6.789298 (lr=4.1903e-05) (hash(x)=21406620) +3867 train 6.599151 (lr=4.1867e-05) (hash(x)=21205988) +3868 train 6.681763 (lr=4.1830e-05) (hash(x)=22742634) +3869 train 6.727718 (lr=4.1793e-05) (hash(x)=24868938) +3870 train 7.114411 (lr=4.1756e-05) (hash(x)=28095283) +3871 train 6.830667 (lr=4.1719e-05) (hash(x)=21596677) +3872 train 7.030396 (lr=4.1682e-05) (hash(x)=26884381) +3873 train 7.116437 (lr=4.1645e-05) (hash(x)=26410272) +3874 train 6.896211 (lr=4.1608e-05) (hash(x)=22915785) +3875 train 6.881177 (lr=4.1572e-05) (hash(x)=23575666) +3876 train 6.858800 (lr=4.1535e-05) (hash(x)=25313223) +3877 train 6.303793 (lr=4.1498e-05) (hash(x)=16319719) +3878 train 6.971049 (lr=4.1462e-05) (hash(x)=23227579) +3879 train 6.892227 (lr=4.1425e-05) (hash(x)=24117012) +3880 train 6.958858 (lr=4.1388e-05) (hash(x)=24681517) +3881 train 6.905365 (lr=4.1352e-05) (hash(x)=23186527) +3882 train 6.884302 (lr=4.1315e-05) (hash(x)=23472784) +3883 train 6.899841 (lr=4.1279e-05) (hash(x)=26013014) +3884 train 7.085501 (lr=4.1242e-05) (hash(x)=25952206) +3885 train 7.221396 (lr=4.1206e-05) (hash(x)=23897834) +3886 train 6.971179 (lr=4.1169e-05) (hash(x)=26350364) +3887 train 6.986577 (lr=4.1133e-05) (hash(x)=24105761) +3888 train 7.093977 (lr=4.1096e-05) (hash(x)=22801707) +3889 train 6.914353 (lr=4.1060e-05) (hash(x)=21821937) +3890 train 6.862930 (lr=4.1024e-05) (hash(x)=24264640) +3891 train 6.804466 (lr=4.0987e-05) (hash(x)=20369133) +3892 train 6.793848 (lr=4.0951e-05) (hash(x)=24313506) +3893 train 6.792732 (lr=4.0915e-05) (hash(x)=22104086) +3894 train 7.005882 (lr=4.0879e-05) (hash(x)=25312602) +3895 train 7.077891 (lr=4.0842e-05) (hash(x)=25725049) +3896 train 6.891983 (lr=4.0806e-05) (hash(x)=22981231) +3897 train 6.746707 (lr=4.0770e-05) (hash(x)=18021467) +3898 train 6.717653 (lr=4.0734e-05) (hash(x)=17960254) +3899 train 6.888462 (lr=4.0698e-05) (hash(x)=19808118) +3900 val loss 7.0860 +3900 val perplexity 1195.1211 +3900 train 6.676276 (lr=4.0662e-05) (hash(x)=21022829) +3901 train 6.845274 (lr=4.0626e-05) (hash(x)=22434663) +3902 train 6.585988 (lr=4.0590e-05) (hash(x)=20208091) +3903 train 6.725816 (lr=4.0554e-05) (hash(x)=22892776) +3904 train 6.833320 (lr=4.0518e-05) (hash(x)=21554367) +3905 train 6.977235 (lr=4.0482e-05) (hash(x)=23704875) +3906 train 6.921810 (lr=4.0446e-05) (hash(x)=21690340) +3907 train 6.886640 (lr=4.0410e-05) (hash(x)=23736780) +3908 train 6.729270 (lr=4.0374e-05) (hash(x)=21060920) +3909 train 6.690009 (lr=4.0338e-05) (hash(x)=20091559) +3910 train 6.945065 (lr=4.0303e-05) (hash(x)=22147974) +3911 train 6.915951 (lr=4.0267e-05) (hash(x)=21630383) +3912 train 7.189642 (lr=4.0231e-05) (hash(x)=28339385) +3913 train 6.945735 (lr=4.0195e-05) (hash(x)=25355505) +3914 train 6.813164 (lr=4.0160e-05) (hash(x)=20843914) +3915 train 7.316727 (lr=4.0124e-05) (hash(x)=25397467) +3916 train 7.015252 (lr=4.0088e-05) (hash(x)=23587501) +3917 train 6.577348 (lr=4.0053e-05) (hash(x)=19036533) +3918 train 6.802860 (lr=4.0017e-05) (hash(x)=29749389) +3919 train 6.708946 (lr=3.9982e-05) (hash(x)=24727094) +3920 train 6.730785 (lr=3.9946e-05) (hash(x)=22723450) +3921 train 6.908502 (lr=3.9911e-05) (hash(x)=24424680) +3922 train 7.052457 (lr=3.9875e-05) (hash(x)=25817917) +3923 train 6.851558 (lr=3.9840e-05) (hash(x)=23951182) +3924 train 6.848976 (lr=3.9804e-05) (hash(x)=21177944) +3925 train 6.706249 (lr=3.9769e-05) (hash(x)=23533768) +3926 train 6.941531 (lr=3.9734e-05) (hash(x)=24263615) +3927 train 6.740150 (lr=3.9698e-05) (hash(x)=22835000) +3928 train 6.994737 (lr=3.9663e-05) (hash(x)=26076156) +3929 train 6.942333 (lr=3.9628e-05) (hash(x)=25171508) +3930 train 6.966165 (lr=3.9592e-05) (hash(x)=22021396) +3931 train 7.249464 (lr=3.9557e-05) (hash(x)=28767849) +3932 train 7.159122 (lr=3.9522e-05) (hash(x)=29497606) +3933 train 6.805063 (lr=3.9487e-05) (hash(x)=22723124) +3934 train 7.091175 (lr=3.9452e-05) (hash(x)=27106616) +3935 train 6.931251 (lr=3.9417e-05) (hash(x)=22839049) +3936 train 6.985150 (lr=3.9381e-05) (hash(x)=25101923) +3937 train 6.947185 (lr=3.9346e-05) (hash(x)=25945975) +3938 train 7.080953 (lr=3.9311e-05) (hash(x)=25382013) +3939 train 6.616675 (lr=3.9276e-05) (hash(x)=19930900) +3940 train 6.787116 (lr=3.9241e-05) (hash(x)=22202373) +3941 train 6.947821 (lr=3.9207e-05) (hash(x)=24592992) +3942 train 6.869969 (lr=3.9172e-05) (hash(x)=25002271) +3943 train 6.723577 (lr=3.9137e-05) (hash(x)=20654136) +3944 train 6.784276 (lr=3.9102e-05) (hash(x)=20061590) +3945 train 6.710520 (lr=3.9067e-05) (hash(x)=21441361) +3946 train 6.926120 (lr=3.9032e-05) (hash(x)=20055468) +3947 train 7.617731 (lr=3.8997e-05) (hash(x)=28495621) +3948 train 7.065480 (lr=3.8963e-05) (hash(x)=25959236) +3949 train 7.385073 (lr=3.8928e-05) (hash(x)=26750193) +3950 val loss 7.0879 +3950 val perplexity 1197.3320 +3950 train 7.204398 (lr=3.8893e-05) (hash(x)=25882605) +3951 train 7.266149 (lr=3.8859e-05) (hash(x)=26776000) +3952 train 6.815132 (lr=3.8824e-05) (hash(x)=24155107) +3953 train 6.931833 (lr=3.8789e-05) (hash(x)=23441845) +3954 train 6.862424 (lr=3.8755e-05) (hash(x)=22860915) +3955 train 6.633386 (lr=3.8720e-05) (hash(x)=21584429) +3956 train 6.237511 (lr=3.8686e-05) (hash(x)=16535556) +3957 train 6.325554 (lr=3.8651e-05) (hash(x)=17946180) +3958 train 6.880334 (lr=3.8617e-05) (hash(x)=25367610) +3959 train 6.752028 (lr=3.8582e-05) (hash(x)=22560658) +3960 train 7.034280 (lr=3.8548e-05) (hash(x)=23809585) +3961 train 7.283151 (lr=3.8514e-05) (hash(x)=20438213) +3962 train 7.651062 (lr=3.8479e-05) (hash(x)=30520037) +3963 train 7.299339 (lr=3.8445e-05) (hash(x)=25276565) +3964 train 7.002742 (lr=3.8411e-05) (hash(x)=26796532) +3965 train 6.782256 (lr=3.8376e-05) (hash(x)=22850475) +3966 train 7.301967 (lr=3.8342e-05) (hash(x)=25983698) +3967 train 7.189988 (lr=3.8308e-05) (hash(x)=25995933) +3968 train 7.372821 (lr=3.8274e-05) (hash(x)=25319339) +3969 train 7.001022 (lr=3.8240e-05) (hash(x)=25066892) +3970 train 7.203403 (lr=3.8206e-05) (hash(x)=26931819) +3971 train 7.137294 (lr=3.8171e-05) (hash(x)=24163910) +3972 train 7.057064 (lr=3.8137e-05) (hash(x)=25359634) +3973 train 6.938461 (lr=3.8103e-05) (hash(x)=24323444) +3974 train 7.124256 (lr=3.8069e-05) (hash(x)=26529231) +3975 train 7.131728 (lr=3.8035e-05) (hash(x)=24635394) +3976 train 7.438963 (lr=3.8001e-05) (hash(x)=24783093) +3977 train 7.560403 (lr=3.7967e-05) (hash(x)=26710509) +3978 train 6.970912 (lr=3.7934e-05) (hash(x)=25396630) +3979 train 6.869212 (lr=3.7900e-05) (hash(x)=22556381) +3980 train 7.177295 (lr=3.7866e-05) (hash(x)=26912161) +3981 train 6.740639 (lr=3.7832e-05) (hash(x)=22268078) +3982 train 7.753641 (lr=3.7798e-05) (hash(x)=30430328) +3983 train 7.391172 (lr=3.7765e-05) (hash(x)=27537228) +3984 train 6.810091 (lr=3.7731e-05) (hash(x)=24468603) +3985 train 7.142652 (lr=3.7697e-05) (hash(x)=27006663) +3986 train 7.377176 (lr=3.7663e-05) (hash(x)=27014728) +3987 train 6.794893 (lr=3.7630e-05) (hash(x)=20883633) +3988 train 6.909039 (lr=3.7596e-05) (hash(x)=23361791) +3989 train 7.042009 (lr=3.7563e-05) (hash(x)=26775925) +3990 train 7.558104 (lr=3.7529e-05) (hash(x)=30648934) +3991 train 7.112600 (lr=3.7496e-05) (hash(x)=26496730) +3992 train 6.910691 (lr=3.7462e-05) (hash(x)=25942897) +3993 train 6.923119 (lr=3.7429e-05) (hash(x)=24887111) +3994 train 6.824731 (lr=3.7395e-05) (hash(x)=22908550) +3995 train 6.560268 (lr=3.7362e-05) (hash(x)=20342150) +3996 train 6.823410 (lr=3.7328e-05) (hash(x)=22261760) +3997 train 6.890182 (lr=3.7295e-05) (hash(x)=22731641) +3998 train 6.776760 (lr=3.7262e-05) (hash(x)=20669749) +3999 train 6.743426 (lr=3.7228e-05) (hash(x)=16533310) +4000 val loss 7.0806 +4000 val perplexity 1188.6609 +4000 train 6.909359 (lr=3.7195e-05) (hash(x)=23661341) +4001 train 6.910778 (lr=3.7162e-05) (hash(x)=24644301) +4002 train 6.728598 (lr=3.7129e-05) (hash(x)=22938438) +4003 train 6.825287 (lr=3.7095e-05) (hash(x)=24315862) +4004 train 7.036860 (lr=3.7062e-05) (hash(x)=25169315) +4005 train 7.022533 (lr=3.7029e-05) (hash(x)=24752796) +4006 train 6.969747 (lr=3.6996e-05) (hash(x)=23103706) +4007 train 7.092238 (lr=3.6963e-05) (hash(x)=24881176) +4008 train 6.951124 (lr=3.6930e-05) (hash(x)=23971947) +4009 train 7.260506 (lr=3.6897e-05) (hash(x)=27741054) +4010 train 7.650122 (lr=3.6864e-05) (hash(x)=30956251) +4011 train 7.022889 (lr=3.6831e-05) (hash(x)=23649686) +4012 train 6.864447 (lr=3.6798e-05) (hash(x)=23344798) +4013 train 7.504256 (lr=3.6765e-05) (hash(x)=29529498) +4014 train 7.018583 (lr=3.6732e-05) (hash(x)=24688359) +4015 train 6.992079 (lr=3.6700e-05) (hash(x)=25593613) +4016 train 7.095094 (lr=3.6667e-05) (hash(x)=25674488) +4017 train 6.538861 (lr=3.6634e-05) (hash(x)=21345346) +4018 train 6.859381 (lr=3.6601e-05) (hash(x)=21978324) +4019 train 6.895346 (lr=3.6569e-05) (hash(x)=23669244) +4020 train 6.747086 (lr=3.6536e-05) (hash(x)=22479613) +4021 train 6.749799 (lr=3.6503e-05) (hash(x)=22855256) +4022 train 7.144155 (lr=3.6471e-05) (hash(x)=19759826) +4023 train 7.052364 (lr=3.6438e-05) (hash(x)=22886646) +4024 train 7.027084 (lr=3.6405e-05) (hash(x)=25553008) +4025 train 6.872808 (lr=3.6373e-05) (hash(x)=25487028) +4026 train 7.441547 (lr=3.6340e-05) (hash(x)=26799246) +4027 train 7.786036 (lr=3.6308e-05) (hash(x)=30728540) +4028 train 7.178947 (lr=3.6275e-05) (hash(x)=23966676) +4029 train 6.867062 (lr=3.6243e-05) (hash(x)=22118783) +4030 train 7.009564 (lr=3.6211e-05) (hash(x)=24744703) +4031 train 7.034757 (lr=3.6178e-05) (hash(x)=21407676) +4032 train 6.929987 (lr=3.6146e-05) (hash(x)=20623349) +4033 train 6.719878 (lr=3.6114e-05) (hash(x)=24723788) +4034 train 7.067198 (lr=3.6081e-05) (hash(x)=25030709) +4035 train 7.081435 (lr=3.6049e-05) (hash(x)=26326164) +4036 train 6.929524 (lr=3.6017e-05) (hash(x)=23754475) +4037 train 7.559456 (lr=3.5985e-05) (hash(x)=30112933) +4038 train 7.300214 (lr=3.5952e-05) (hash(x)=27474299) +4039 train 6.774765 (lr=3.5920e-05) (hash(x)=21720304) +4040 train 7.168248 (lr=3.5888e-05) (hash(x)=25142674) +4041 train 7.429101 (lr=3.5856e-05) (hash(x)=25284552) +4042 train 7.329258 (lr=3.5824e-05) (hash(x)=24554942) +4043 train 7.077924 (lr=3.5792e-05) (hash(x)=23773870) +4044 train 6.827428 (lr=3.5760e-05) (hash(x)=23896338) +4045 train 7.659289 (lr=3.5728e-05) (hash(x)=34984911) +4046 train 6.899963 (lr=3.5696e-05) (hash(x)=23854263) +4047 train 7.199817 (lr=3.5664e-05) (hash(x)=27263416) +4048 train 6.883781 (lr=3.5632e-05) (hash(x)=24989642) +4049 train 6.917876 (lr=3.5601e-05) (hash(x)=24492055) +4050 val loss 7.0864 +4050 val perplexity 1195.5748 +4050 train 6.798225 (lr=3.5569e-05) (hash(x)=21579916) +4051 train 7.048139 (lr=3.5537e-05) (hash(x)=25274710) +4052 train 6.940981 (lr=3.5505e-05) (hash(x)=24701947) +4053 train 6.942075 (lr=3.5474e-05) (hash(x)=25477340) +4054 train 6.861054 (lr=3.5442e-05) (hash(x)=23774195) +4055 train 7.088887 (lr=3.5410e-05) (hash(x)=25840801) +4056 train 7.287960 (lr=3.5379e-05) (hash(x)=27972529) +4057 train 7.060909 (lr=3.5347e-05) (hash(x)=26952458) +4058 train 6.567091 (lr=3.5315e-05) (hash(x)=22683653) +4059 train 6.617838 (lr=3.5284e-05) (hash(x)=20984129) +4060 train 6.800520 (lr=3.5252e-05) (hash(x)=22816482) +4061 train 7.070400 (lr=3.5221e-05) (hash(x)=24285302) +4062 train 7.517169 (lr=3.5189e-05) (hash(x)=31517950) +4063 train 7.701001 (lr=3.5158e-05) (hash(x)=31424568) +4064 train 7.435772 (lr=3.5127e-05) (hash(x)=29497876) +4065 train 7.299622 (lr=3.5095e-05) (hash(x)=27277376) +4066 train 7.025548 (lr=3.5064e-05) (hash(x)=26832588) +4067 train 6.868025 (lr=3.5032e-05) (hash(x)=25149712) +4068 train 6.880872 (lr=3.5001e-05) (hash(x)=23728457) +4069 train 6.766026 (lr=3.4970e-05) (hash(x)=25265136) +4070 train 7.310603 (lr=3.4939e-05) (hash(x)=25241681) +4071 train 7.018531 (lr=3.4908e-05) (hash(x)=23403065) +4072 train 6.955627 (lr=3.4876e-05) (hash(x)=25808207) +4073 train 6.867652 (lr=3.4845e-05) (hash(x)=23904844) +4074 train 6.548193 (lr=3.4814e-05) (hash(x)=18865309) +4075 train 7.038349 (lr=3.4783e-05) (hash(x)=23531744) +4076 train 7.054225 (lr=3.4752e-05) (hash(x)=25784275) +4077 train 6.810422 (lr=3.4721e-05) (hash(x)=22417529) +4078 train 6.795909 (lr=3.4690e-05) (hash(x)=23095491) +4079 train 6.921556 (lr=3.4659e-05) (hash(x)=22656033) +4080 train 6.928997 (lr=3.4628e-05) (hash(x)=25865435) +4081 train 7.057716 (lr=3.4597e-05) (hash(x)=25699377) +4082 train 7.071819 (lr=3.4566e-05) (hash(x)=20854084) +4083 train 6.618174 (lr=3.4536e-05) (hash(x)=18950799) +4084 train 6.850379 (lr=3.4505e-05) (hash(x)=22633739) +4085 train 7.687173 (lr=3.4474e-05) (hash(x)=34054446) +4086 train 7.223068 (lr=3.4443e-05) (hash(x)=27599387) +4087 train 7.053775 (lr=3.4413e-05) (hash(x)=26869295) +4088 train 7.000375 (lr=3.4382e-05) (hash(x)=24075139) +4089 train 7.439510 (lr=3.4351e-05) (hash(x)=29784110) +4090 train 7.762856 (lr=3.4321e-05) (hash(x)=34273918) +4091 train 8.147902 (lr=3.4290e-05) (hash(x)=34472685) +4092 train 7.484506 (lr=3.4259e-05) (hash(x)=30113791) +4093 train 6.745757 (lr=3.4229e-05) (hash(x)=22366381) +4094 train 6.984703 (lr=3.4198e-05) (hash(x)=24922935) +4095 train 7.203291 (lr=3.4168e-05) (hash(x)=25504151) +4096 train 7.161512 (lr=3.4137e-05) (hash(x)=24517375) +4097 train 7.834634 (lr=3.4107e-05) (hash(x)=25871651) +4098 train 6.883208 (lr=3.4077e-05) (hash(x)=23480225) +4099 train 6.707985 (lr=3.4046e-05) (hash(x)=22559978) +4100 val loss 7.0805 +4100 val perplexity 1188.5498 +4100 train 7.170644 (lr=3.4016e-05) (hash(x)=25795272) +4101 train 7.142980 (lr=3.3986e-05) (hash(x)=25440399) +4102 train 6.794289 (lr=3.3955e-05) (hash(x)=21581806) +4103 train 6.847696 (lr=3.3925e-05) (hash(x)=25781518) +4104 train 6.946256 (lr=3.3895e-05) (hash(x)=24682372) +4105 train 6.822675 (lr=3.3865e-05) (hash(x)=22440094) +4106 train 6.970027 (lr=3.3835e-05) (hash(x)=23661032) +4107 train 7.228694 (lr=3.3804e-05) (hash(x)=26966012) +4108 train 7.265499 (lr=3.3774e-05) (hash(x)=26232227) +4109 train 6.907218 (lr=3.3744e-05) (hash(x)=24110656) +4110 train 7.166963 (lr=3.3714e-05) (hash(x)=25938621) +4111 train 6.999200 (lr=3.3684e-05) (hash(x)=26432850) +4112 train 6.985675 (lr=3.3654e-05) (hash(x)=25387672) +4113 train 6.743852 (lr=3.3624e-05) (hash(x)=22740017) +4114 train 7.150362 (lr=3.3595e-05) (hash(x)=26384190) +4115 train 6.844583 (lr=3.3565e-05) (hash(x)=24725583) +4116 train 6.966831 (lr=3.3535e-05) (hash(x)=23986700) +4117 train 6.979354 (lr=3.3505e-05) (hash(x)=18529900) +4118 train 7.000397 (lr=3.3475e-05) (hash(x)=22236257) +4119 train 6.622490 (lr=3.3445e-05) (hash(x)=20155894) +4120 train 6.431282 (lr=3.3416e-05) (hash(x)=17423813) +4121 train 6.395330 (lr=3.3386e-05) (hash(x)=18905183) +4122 train 6.751611 (lr=3.3356e-05) (hash(x)=22534398) +4123 train 7.451343 (lr=3.3327e-05) (hash(x)=25247868) +4124 train 6.975821 (lr=3.3297e-05) (hash(x)=23994188) +4125 train 6.836983 (lr=3.3268e-05) (hash(x)=22929754) +4126 train 6.712934 (lr=3.3238e-05) (hash(x)=22485897) +4127 train 6.769234 (lr=3.3209e-05) (hash(x)=22270169) +4128 train 6.768806 (lr=3.3179e-05) (hash(x)=23638027) +4129 train 7.062748 (lr=3.3150e-05) (hash(x)=23821210) +4130 train 6.907997 (lr=3.3120e-05) (hash(x)=25021512) +4131 train 6.998081 (lr=3.3091e-05) (hash(x)=25240141) +4132 train 6.962515 (lr=3.3061e-05) (hash(x)=22833160) +4133 train 6.873160 (lr=3.3032e-05) (hash(x)=22909944) +4134 train 7.142989 (lr=3.3003e-05) (hash(x)=26163558) +4135 train 6.864242 (lr=3.2973e-05) (hash(x)=22108461) +4136 train 6.820114 (lr=3.2944e-05) (hash(x)=22549232) +4137 train 7.048514 (lr=3.2915e-05) (hash(x)=24701302) +4138 train 7.140520 (lr=3.2886e-05) (hash(x)=25206013) +4139 train 7.105886 (lr=3.2857e-05) (hash(x)=27896130) +4140 train 6.826662 (lr=3.2828e-05) (hash(x)=24106243) +4141 train 7.457333 (lr=3.2799e-05) (hash(x)=27158651) +4142 train 7.009188 (lr=3.2769e-05) (hash(x)=23841147) +4143 train 6.924063 (lr=3.2740e-05) (hash(x)=24802848) +4144 train 7.228988 (lr=3.2711e-05) (hash(x)=24911295) +4145 train 7.018022 (lr=3.2682e-05) (hash(x)=26473900) +4146 train 7.101033 (lr=3.2654e-05) (hash(x)=26785092) +4147 train 7.373260 (lr=3.2625e-05) (hash(x)=30188532) +4148 train 6.904675 (lr=3.2596e-05) (hash(x)=25010649) +4149 train 6.881721 (lr=3.2567e-05) (hash(x)=22409016) +4150 val loss 7.0792 +4150 val perplexity 1187.0715 +4150 train 7.657560 (lr=3.2538e-05) (hash(x)=31675024) +4151 train 6.929103 (lr=3.2509e-05) (hash(x)=25086604) +4152 train 6.948221 (lr=3.2481e-05) (hash(x)=24429343) +4153 train 7.127687 (lr=3.2452e-05) (hash(x)=25014232) +4154 train 7.032735 (lr=3.2423e-05) (hash(x)=25366275) +4155 train 7.463302 (lr=3.2395e-05) (hash(x)=24031473) +4156 train 7.015224 (lr=3.2366e-05) (hash(x)=26651059) +4157 train 7.122519 (lr=3.2337e-05) (hash(x)=26069721) +4158 train 7.279682 (lr=3.2309e-05) (hash(x)=28114382) +4159 train 7.266376 (lr=3.2280e-05) (hash(x)=26983186) +4160 train 6.619188 (lr=3.2252e-05) (hash(x)=21944670) +4161 train 7.354534 (lr=3.2223e-05) (hash(x)=28155702) +4162 train 6.810387 (lr=3.2195e-05) (hash(x)=24765002) +4163 train 7.043907 (lr=3.2166e-05) (hash(x)=26492636) +4164 train 7.002539 (lr=3.2138e-05) (hash(x)=24063705) +4165 train 7.278770 (lr=3.2110e-05) (hash(x)=27079573) +4166 train 6.941715 (lr=3.2081e-05) (hash(x)=24912201) +4167 train 7.059824 (lr=3.2053e-05) (hash(x)=27208507) +4168 train 6.955986 (lr=3.2025e-05) (hash(x)=25824320) +4169 train 7.484273 (lr=3.1997e-05) (hash(x)=29641677) +4170 train 7.206998 (lr=3.1968e-05) (hash(x)=26275614) +4171 train 7.033331 (lr=3.1940e-05) (hash(x)=25227725) +4172 train 7.150510 (lr=3.1912e-05) (hash(x)=27417375) +4173 train 7.331233 (lr=3.1884e-05) (hash(x)=25581973) +4174 train 7.557495 (lr=3.1856e-05) (hash(x)=30360417) +4175 train 6.853576 (lr=3.1828e-05) (hash(x)=23862845) +4176 train 6.946329 (lr=3.1800e-05) (hash(x)=25415130) +4177 train 6.932614 (lr=3.1772e-05) (hash(x)=23111123) +4178 train 6.886714 (lr=3.1744e-05) (hash(x)=24022804) +4179 train 6.930955 (lr=3.1716e-05) (hash(x)=25148490) +4180 train 7.137893 (lr=3.1688e-05) (hash(x)=22792092) +4181 train 7.206874 (lr=3.1660e-05) (hash(x)=24779698) +4182 train 7.120445 (lr=3.1632e-05) (hash(x)=24870844) +4183 train 6.819213 (lr=3.1605e-05) (hash(x)=22664494) +4184 train 6.859429 (lr=3.1577e-05) (hash(x)=22599729) +4185 train 7.088121 (lr=3.1549e-05) (hash(x)=24707078) +4186 train 6.864481 (lr=3.1521e-05) (hash(x)=23823945) +4187 train 6.554780 (lr=3.1494e-05) (hash(x)=22219856) +4188 train 7.275620 (lr=3.1466e-05) (hash(x)=27061401) +4189 train 7.009382 (lr=3.1438e-05) (hash(x)=23398766) +4190 train 7.103337 (lr=3.1411e-05) (hash(x)=27916730) +4191 train 6.991493 (lr=3.1383e-05) (hash(x)=24092927) +4192 train 7.040860 (lr=3.1356e-05) (hash(x)=24723657) +4193 train 7.058192 (lr=3.1328e-05) (hash(x)=24676155) +4194 train 6.948853 (lr=3.1301e-05) (hash(x)=23455369) +4195 train 6.892944 (lr=3.1273e-05) (hash(x)=21999890) +4196 train 6.800209 (lr=3.1246e-05) (hash(x)=23385567) +4197 train 7.033435 (lr=3.1219e-05) (hash(x)=25120814) +4198 train 6.745878 (lr=3.1191e-05) (hash(x)=21308113) +4199 train 7.049162 (lr=3.1164e-05) (hash(x)=27213812) +4200 val loss 7.0694 +4200 val perplexity 1175.4379 +4200 train 6.597994 (lr=3.1137e-05) (hash(x)=19675382) +4201 train 6.923416 (lr=3.1110e-05) (hash(x)=23882161) +4202 train 6.885355 (lr=3.1082e-05) (hash(x)=24338567) +4203 train 7.198392 (lr=3.1055e-05) (hash(x)=27649723) +4204 train 7.009956 (lr=3.1028e-05) (hash(x)=27563514) +4205 train 6.980316 (lr=3.1001e-05) (hash(x)=23128552) +4206 train 6.918950 (lr=3.0974e-05) (hash(x)=26203283) +4207 train 6.936353 (lr=3.0947e-05) (hash(x)=23929955) +4208 train 6.603183 (lr=3.0920e-05) (hash(x)=20978691) +4209 train 6.940103 (lr=3.0893e-05) (hash(x)=21875178) +4210 train 6.995248 (lr=3.0866e-05) (hash(x)=23563293) +4211 train 7.150801 (lr=3.0839e-05) (hash(x)=25538503) +4212 train 7.194234 (lr=3.0812e-05) (hash(x)=24171014) +4213 train 7.008218 (lr=3.0785e-05) (hash(x)=22306665) +4214 train 6.941908 (lr=3.0758e-05) (hash(x)=26082318) +4215 train 6.727153 (lr=3.0731e-05) (hash(x)=23025790) +4216 train 6.810021 (lr=3.0705e-05) (hash(x)=21146597) +4217 train 7.175666 (lr=3.0678e-05) (hash(x)=27470230) +4218 train 6.909416 (lr=3.0651e-05) (hash(x)=22691005) +4219 train 6.694664 (lr=3.0625e-05) (hash(x)=21550313) +4220 train 6.819692 (lr=3.0598e-05) (hash(x)=20618443) +4221 train 6.893510 (lr=3.0571e-05) (hash(x)=25260787) +4222 train 6.985139 (lr=3.0545e-05) (hash(x)=25249873) +4223 train 6.574049 (lr=3.0518e-05) (hash(x)=20452272) +4224 train 6.907894 (lr=3.0492e-05) (hash(x)=25649764) +4225 train 6.775080 (lr=3.0465e-05) (hash(x)=19589460) +4226 train 7.169672 (lr=3.0439e-05) (hash(x)=26477595) +4227 train 7.380388 (lr=3.0412e-05) (hash(x)=27585442) +4228 train 7.198114 (lr=3.0386e-05) (hash(x)=25821343) +4229 train 7.103593 (lr=3.0360e-05) (hash(x)=24549919) +4230 train 7.003893 (lr=3.0333e-05) (hash(x)=26124522) +4231 train 7.310826 (lr=3.0307e-05) (hash(x)=26473464) +4232 train 7.296260 (lr=3.0281e-05) (hash(x)=28883028) +4233 train 7.242921 (lr=3.0254e-05) (hash(x)=29611296) +4234 train 7.159639 (lr=3.0228e-05) (hash(x)=29059941) +4235 train 6.996088 (lr=3.0202e-05) (hash(x)=26368203) +4236 train 7.019069 (lr=3.0176e-05) (hash(x)=27021360) +4237 train 6.962777 (lr=3.0150e-05) (hash(x)=26135379) +4238 train 6.774734 (lr=3.0124e-05) (hash(x)=25862549) +4239 train 7.174659 (lr=3.0098e-05) (hash(x)=28276603) +4240 train 6.730068 (lr=3.0072e-05) (hash(x)=22170090) +4241 train 7.060204 (lr=3.0046e-05) (hash(x)=22625589) +4242 train 7.085964 (lr=3.0020e-05) (hash(x)=25751475) +4243 train 6.977470 (lr=2.9994e-05) (hash(x)=25836838) +4244 train 6.920813 (lr=2.9968e-05) (hash(x)=23938214) +4245 train 6.860301 (lr=2.9942e-05) (hash(x)=22759365) +4246 train 6.831674 (lr=2.9916e-05) (hash(x)=24964628) +4247 train 6.544405 (lr=2.9890e-05) (hash(x)=21480367) +4248 train 7.081450 (lr=2.9865e-05) (hash(x)=25974694) +4249 train 7.432155 (lr=2.9839e-05) (hash(x)=29830546) +4250 val loss 7.0692 +4250 val perplexity 1175.1582 +4250 train 7.091908 (lr=2.9813e-05) (hash(x)=26283200) +4251 train 7.141323 (lr=2.9788e-05) (hash(x)=25605672) +4252 train 6.782593 (lr=2.9762e-05) (hash(x)=21439107) +4253 train 6.686184 (lr=2.9736e-05) (hash(x)=22626883) +4254 train 7.062076 (lr=2.9711e-05) (hash(x)=25627150) +4255 train 7.224469 (lr=2.9685e-05) (hash(x)=24658642) +4256 train 7.284633 (lr=2.9660e-05) (hash(x)=29755505) +4257 train 7.045261 (lr=2.9634e-05) (hash(x)=22750846) +4258 train 6.979662 (lr=2.9609e-05) (hash(x)=21892651) +4259 train 7.002754 (lr=2.9583e-05) (hash(x)=22487960) +4260 train 7.077644 (lr=2.9558e-05) (hash(x)=24059869) +4261 train 6.854373 (lr=2.9533e-05) (hash(x)=21090180) +4262 train 6.971781 (lr=2.9507e-05) (hash(x)=22716452) +4263 train 7.206819 (lr=2.9482e-05) (hash(x)=26854801) +4264 train 6.967667 (lr=2.9457e-05) (hash(x)=23815428) +4265 train 6.806311 (lr=2.9432e-05) (hash(x)=23368704) +4266 train 6.857246 (lr=2.9406e-05) (hash(x)=24301098) +4267 train 7.084058 (lr=2.9381e-05) (hash(x)=25025039) +4268 train 6.828346 (lr=2.9356e-05) (hash(x)=25425736) +4269 train 7.072136 (lr=2.9331e-05) (hash(x)=27439380) +4270 train 6.479631 (lr=2.9306e-05) (hash(x)=18682756) +4271 train 6.613190 (lr=2.9281e-05) (hash(x)=17862226) +4272 train 7.251636 (lr=2.9256e-05) (hash(x)=29946491) +4273 train 6.479324 (lr=2.9231e-05) (hash(x)=21392062) +4274 train 7.055748 (lr=2.9206e-05) (hash(x)=25195556) +4275 train 7.041782 (lr=2.9181e-05) (hash(x)=26682036) +4276 train 6.965440 (lr=2.9156e-05) (hash(x)=21235260) +4277 train 6.762537 (lr=2.9131e-05) (hash(x)=22118984) +4278 train 6.800676 (lr=2.9107e-05) (hash(x)=24094510) +4279 train 7.333943 (lr=2.9082e-05) (hash(x)=28519182) +4280 train 7.018174 (lr=2.9057e-05) (hash(x)=26652859) +4281 train 6.889990 (lr=2.9032e-05) (hash(x)=24463139) +4282 train 6.868638 (lr=2.9008e-05) (hash(x)=23281870) +4283 train 7.110489 (lr=2.8983e-05) (hash(x)=29181174) +4284 train 6.795967 (lr=2.8958e-05) (hash(x)=24797417) +4285 train 7.148380 (lr=2.8934e-05) (hash(x)=29026537) +4286 train 6.917699 (lr=2.8909e-05) (hash(x)=23045165) +4287 train 6.878269 (lr=2.8885e-05) (hash(x)=25193694) +4288 train 6.929776 (lr=2.8860e-05) (hash(x)=23475407) +4289 train 7.040637 (lr=2.8836e-05) (hash(x)=24875410) +4290 train 6.939047 (lr=2.8811e-05) (hash(x)=26328101) +4291 train 7.220404 (lr=2.8787e-05) (hash(x)=26273661) +4292 train 6.949803 (lr=2.8763e-05) (hash(x)=23271891) +4293 train 6.901350 (lr=2.8738e-05) (hash(x)=23300732) +4294 train 7.017119 (lr=2.8714e-05) (hash(x)=24243693) +4295 train 7.096785 (lr=2.8690e-05) (hash(x)=25642620) +4296 train 7.109439 (lr=2.8666e-05) (hash(x)=27730411) +4297 train 6.869865 (lr=2.8641e-05) (hash(x)=25485335) +4298 train 6.735546 (lr=2.8617e-05) (hash(x)=25268789) +4299 train 7.192207 (lr=2.8593e-05) (hash(x)=28917143) +4300 val loss 7.0661 +4300 val perplexity 1171.5640 +4300 train 7.330959 (lr=2.8569e-05) (hash(x)=28987991) +4301 train 7.088979 (lr=2.8545e-05) (hash(x)=25989151) +4302 train 6.973660 (lr=2.8521e-05) (hash(x)=25658195) +4303 train 6.957344 (lr=2.8497e-05) (hash(x)=25765909) +4304 train 6.948822 (lr=2.8473e-05) (hash(x)=25704261) +4305 train 6.959836 (lr=2.8449e-05) (hash(x)=24438198) +4306 train 6.775707 (lr=2.8425e-05) (hash(x)=22871710) +4307 train 6.586168 (lr=2.8401e-05) (hash(x)=20160896) +4308 train 7.190435 (lr=2.8377e-05) (hash(x)=24218641) +4309 train 6.562177 (lr=2.8353e-05) (hash(x)=22073751) +4310 train 6.904728 (lr=2.8330e-05) (hash(x)=26434959) +4311 train 6.622350 (lr=2.8306e-05) (hash(x)=20750531) +4312 train 6.752983 (lr=2.8282e-05) (hash(x)=22232293) +4313 train 7.075067 (lr=2.8259e-05) (hash(x)=27324521) +4314 train 6.721776 (lr=2.8235e-05) (hash(x)=22217862) +4315 train 7.163269 (lr=2.8211e-05) (hash(x)=25741958) +4316 train 6.903207 (lr=2.8188e-05) (hash(x)=22738456) +4317 train 6.975833 (lr=2.8164e-05) (hash(x)=25387302) +4318 train 6.923350 (lr=2.8141e-05) (hash(x)=24669014) +4319 train 7.049043 (lr=2.8117e-05) (hash(x)=24917098) +4320 train 6.998120 (lr=2.8094e-05) (hash(x)=26698227) +4321 train 6.788494 (lr=2.8070e-05) (hash(x)=23518293) +4322 train 6.729740 (lr=2.8047e-05) (hash(x)=23643971) +4323 train 6.949932 (lr=2.8023e-05) (hash(x)=25659505) +4324 train 6.743320 (lr=2.8000e-05) (hash(x)=22697720) +4325 train 7.219971 (lr=2.7977e-05) (hash(x)=25082178) +4326 train 6.781854 (lr=2.7954e-05) (hash(x)=24166546) +4327 train 6.925065 (lr=2.7930e-05) (hash(x)=24499766) +4328 train 7.037320 (lr=2.7907e-05) (hash(x)=24338607) +4329 train 6.824122 (lr=2.7884e-05) (hash(x)=23225420) +4330 train 6.988014 (lr=2.7861e-05) (hash(x)=25907032) +4331 train 6.783315 (lr=2.7838e-05) (hash(x)=24634979) +4332 train 6.896226 (lr=2.7815e-05) (hash(x)=22161377) +4333 train 7.020678 (lr=2.7792e-05) (hash(x)=22559939) +4334 train 6.788779 (lr=2.7769e-05) (hash(x)=20840022) +4335 train 7.098550 (lr=2.7746e-05) (hash(x)=25067358) +4336 train 6.740467 (lr=2.7723e-05) (hash(x)=23432626) +4337 train 6.943394 (lr=2.7700e-05) (hash(x)=23820385) +4338 train 7.716868 (lr=2.7677e-05) (hash(x)=31594930) +4339 train 7.135948 (lr=2.7654e-05) (hash(x)=27138750) +4340 train 7.336644 (lr=2.7631e-05) (hash(x)=30031341) +4341 train 6.882221 (lr=2.7609e-05) (hash(x)=24602807) +4342 train 6.650090 (lr=2.7586e-05) (hash(x)=21584976) +4343 train 7.088829 (lr=2.7563e-05) (hash(x)=27479796) +4344 train 6.757437 (lr=2.7540e-05) (hash(x)=22746241) +4345 train 6.934532 (lr=2.7518e-05) (hash(x)=19728452) +4346 train 6.717037 (lr=2.7495e-05) (hash(x)=24502020) +4347 train 7.243801 (lr=2.7473e-05) (hash(x)=28225954) +4348 train 6.861049 (lr=2.7450e-05) (hash(x)=23893447) +4349 train 7.166818 (lr=2.7427e-05) (hash(x)=25654586) +4350 val loss 7.0641 +4350 val perplexity 1169.1915 +4350 train 7.018715 (lr=2.7405e-05) (hash(x)=23856469) +4351 train 6.902424 (lr=2.7383e-05) (hash(x)=23136080) +4352 train 7.059848 (lr=2.7360e-05) (hash(x)=26532918) +4353 train 6.966666 (lr=2.7338e-05) (hash(x)=25461947) +4354 train 6.979183 (lr=2.7315e-05) (hash(x)=26590231) +4355 train 6.694070 (lr=2.7293e-05) (hash(x)=21441985) +4356 train 6.991258 (lr=2.7271e-05) (hash(x)=26507941) +4357 train 7.271607 (lr=2.7249e-05) (hash(x)=26245238) +4358 train 7.035262 (lr=2.7226e-05) (hash(x)=24879059) +4359 train 7.311844 (lr=2.7204e-05) (hash(x)=29810074) +4360 train 6.720218 (lr=2.7182e-05) (hash(x)=24258069) +4361 train 6.860500 (lr=2.7160e-05) (hash(x)=25229360) +4362 train 7.051280 (lr=2.7138e-05) (hash(x)=25440206) +4363 train 6.913774 (lr=2.7116e-05) (hash(x)=23222125) +4364 train 6.752783 (lr=2.7094e-05) (hash(x)=23353186) +4365 train 6.991811 (lr=2.7072e-05) (hash(x)=26995240) +4366 train 6.919739 (lr=2.7050e-05) (hash(x)=24135899) +4367 train 6.968655 (lr=2.7028e-05) (hash(x)=24765539) +4368 train 7.008192 (lr=2.7006e-05) (hash(x)=26051004) +4369 train 6.739067 (lr=2.6984e-05) (hash(x)=22559142) +4370 train 6.664000 (lr=2.6962e-05) (hash(x)=20364388) +4371 train 7.152287 (lr=2.6940e-05) (hash(x)=25938817) +4372 train 7.189838 (lr=2.6919e-05) (hash(x)=26060945) +4373 train 7.094737 (lr=2.6897e-05) (hash(x)=27866714) +4374 train 7.029103 (lr=2.6875e-05) (hash(x)=27104972) +4375 train 6.704404 (lr=2.6854e-05) (hash(x)=22216309) +4376 train 6.755797 (lr=2.6832e-05) (hash(x)=20781533) +4377 train 6.690465 (lr=2.6810e-05) (hash(x)=18784350) +4378 train 6.810385 (lr=2.6789e-05) (hash(x)=21102897) +4379 train 7.085506 (lr=2.6767e-05) (hash(x)=25647489) +4380 train 6.880895 (lr=2.6746e-05) (hash(x)=24486462) +4381 train 7.142017 (lr=2.6724e-05) (hash(x)=26539114) +4382 train 6.813675 (lr=2.6703e-05) (hash(x)=20026045) +4383 train 7.096504 (lr=2.6681e-05) (hash(x)=20613861) +4384 train 6.775453 (lr=2.6660e-05) (hash(x)=20676237) +4385 train 6.989386 (lr=2.6639e-05) (hash(x)=24893163) +4386 train 6.538387 (lr=2.6617e-05) (hash(x)=17299395) +4387 train 6.688141 (lr=2.6596e-05) (hash(x)=19580191) +4388 train 6.891198 (lr=2.6575e-05) (hash(x)=25588218) +4389 train 7.032070 (lr=2.6554e-05) (hash(x)=26433063) +4390 train 7.087490 (lr=2.6533e-05) (hash(x)=24917693) +4391 train 6.771847 (lr=2.6511e-05) (hash(x)=23462447) +4392 train 7.019561 (lr=2.6490e-05) (hash(x)=27185416) +4393 train 7.121900 (lr=2.6469e-05) (hash(x)=24109010) +4394 train 6.888147 (lr=2.6448e-05) (hash(x)=21486000) +4395 train 6.749245 (lr=2.6427e-05) (hash(x)=22230006) +4396 train 7.204769 (lr=2.6406e-05) (hash(x)=26092311) +4397 train 6.918537 (lr=2.6385e-05) (hash(x)=24112426) +4398 train 6.773825 (lr=2.6364e-05) (hash(x)=21881373) +4399 train 6.909657 (lr=2.6343e-05) (hash(x)=26739455) +4400 val loss 7.0649 +4400 val perplexity 1170.1230 +4400 train 6.776479 (lr=2.6323e-05) (hash(x)=22873602) +4401 train 6.852139 (lr=2.6302e-05) (hash(x)=26748712) +4402 train 7.028759 (lr=2.6281e-05) (hash(x)=26306618) +4403 train 7.185349 (lr=2.6260e-05) (hash(x)=26898808) +4404 train 6.940344 (lr=2.6240e-05) (hash(x)=25067751) +4405 train 6.984441 (lr=2.6219e-05) (hash(x)=25397145) +4406 train 7.150342 (lr=2.6198e-05) (hash(x)=24796962) +4407 train 6.949226 (lr=2.6178e-05) (hash(x)=23222996) +4408 train 6.919727 (lr=2.6157e-05) (hash(x)=24820189) +4409 train 7.322747 (lr=2.6137e-05) (hash(x)=27669038) +4410 train 6.891860 (lr=2.6116e-05) (hash(x)=24283976) +4411 train 7.116406 (lr=2.6096e-05) (hash(x)=25018789) +4412 train 7.017724 (lr=2.6075e-05) (hash(x)=26247064) +4413 train 7.044231 (lr=2.6055e-05) (hash(x)=22942904) +4414 train 6.927591 (lr=2.6034e-05) (hash(x)=23918746) +4415 train 7.061867 (lr=2.6014e-05) (hash(x)=26489285) +4416 train 6.000033 (lr=2.5994e-05) (hash(x)=14942495) +4417 train 6.837271 (lr=2.5973e-05) (hash(x)=23908505) +4418 train 7.105679 (lr=2.5953e-05) (hash(x)=25854036) +4419 train 6.976350 (lr=2.5933e-05) (hash(x)=27522868) +4420 train 6.880308 (lr=2.5913e-05) (hash(x)=26549205) +4421 train 6.744153 (lr=2.5893e-05) (hash(x)=24565522) +4422 train 7.094978 (lr=2.5872e-05) (hash(x)=23919123) +4423 train 6.920415 (lr=2.5852e-05) (hash(x)=25185942) +4424 train 6.928917 (lr=2.5832e-05) (hash(x)=24818969) +4425 train 7.029941 (lr=2.5812e-05) (hash(x)=26750372) +4426 train 7.038281 (lr=2.5792e-05) (hash(x)=25621536) +4427 train 7.466130 (lr=2.5772e-05) (hash(x)=28037060) +4428 train 7.482831 (lr=2.5752e-05) (hash(x)=30829517) +4429 train 7.065979 (lr=2.5733e-05) (hash(x)=28728766) +4430 train 7.009519 (lr=2.5713e-05) (hash(x)=25936895) +4431 train 7.171228 (lr=2.5693e-05) (hash(x)=27476158) +4432 train 6.891431 (lr=2.5673e-05) (hash(x)=23297921) +4433 train 6.893064 (lr=2.5653e-05) (hash(x)=23201299) +4434 train 6.805588 (lr=2.5634e-05) (hash(x)=22681766) +4435 train 6.814067 (lr=2.5614e-05) (hash(x)=23217512) +4436 train 7.281406 (lr=2.5594e-05) (hash(x)=29322443) +4437 train 6.873419 (lr=2.5575e-05) (hash(x)=23502072) +4438 train 6.976584 (lr=2.5555e-05) (hash(x)=28873527) +4439 train 6.992105 (lr=2.5536e-05) (hash(x)=23653175) +4440 train 6.789540 (lr=2.5516e-05) (hash(x)=21635879) +4441 train 6.863027 (lr=2.5497e-05) (hash(x)=22201854) +4442 train 6.773027 (lr=2.5477e-05) (hash(x)=23101164) +4443 train 7.190808 (lr=2.5458e-05) (hash(x)=25475122) +4444 train 6.921932 (lr=2.5438e-05) (hash(x)=25124825) +4445 train 7.031058 (lr=2.5419e-05) (hash(x)=26883852) +4446 train 6.845980 (lr=2.5400e-05) (hash(x)=24731829) +4447 train 6.799982 (lr=2.5380e-05) (hash(x)=22405076) +4448 train 6.982071 (lr=2.5361e-05) (hash(x)=27633869) +4449 train 7.048061 (lr=2.5342e-05) (hash(x)=25162594) +4450 val loss 7.0594 +4450 val perplexity 1163.7812 +4450 train 7.045536 (lr=2.5323e-05) (hash(x)=26438149) +4451 train 7.055212 (lr=2.5304e-05) (hash(x)=26748800) +4452 train 6.783162 (lr=2.5285e-05) (hash(x)=22971620) +4453 train 6.956274 (lr=2.5266e-05) (hash(x)=25886430) +4454 train 6.686460 (lr=2.5246e-05) (hash(x)=21084137) +4455 train 6.902967 (lr=2.5227e-05) (hash(x)=25673545) +4456 train 7.527004 (lr=2.5208e-05) (hash(x)=29389002) +4457 train 6.632697 (lr=2.5190e-05) (hash(x)=21676076) +4458 train 6.691377 (lr=2.5171e-05) (hash(x)=22616647) +4459 train 7.103006 (lr=2.5152e-05) (hash(x)=22771197) +4460 train 7.026525 (lr=2.5133e-05) (hash(x)=26393514) +4461 train 7.244072 (lr=2.5114e-05) (hash(x)=24996433) +4462 train 6.877904 (lr=2.5095e-05) (hash(x)=19594028) +4463 train 7.036220 (lr=2.5077e-05) (hash(x)=22675428) +4464 train 7.064330 (lr=2.5058e-05) (hash(x)=26566551) +4465 train 7.035605 (lr=2.5039e-05) (hash(x)=22469290) +4466 train 7.491998 (lr=2.5021e-05) (hash(x)=29821654) +4467 train 7.026271 (lr=2.5002e-05) (hash(x)=26305388) +4468 train 6.866391 (lr=2.4983e-05) (hash(x)=21998506) +4469 train 7.305683 (lr=2.4965e-05) (hash(x)=23953315) +4470 train 6.902747 (lr=2.4946e-05) (hash(x)=23985456) +4471 train 7.327215 (lr=2.4928e-05) (hash(x)=28168456) +4472 train 6.972028 (lr=2.4909e-05) (hash(x)=25126411) +4473 train 6.781601 (lr=2.4891e-05) (hash(x)=24619336) +4474 train 6.957008 (lr=2.4873e-05) (hash(x)=24467798) +4475 train 7.785276 (lr=2.4854e-05) (hash(x)=31673254) +4476 train 7.580556 (lr=2.4836e-05) (hash(x)=29929610) +4477 train 7.330480 (lr=2.4818e-05) (hash(x)=29412572) +4478 train 7.465230 (lr=2.4799e-05) (hash(x)=31910006) +4479 train 7.126946 (lr=2.4781e-05) (hash(x)=26072586) +4480 train 7.067616 (lr=2.4763e-05) (hash(x)=25782825) +4481 train 6.894263 (lr=2.4745e-05) (hash(x)=21131363) +4482 train 7.007660 (lr=2.4727e-05) (hash(x)=25071223) +4483 train 7.623643 (lr=2.4709e-05) (hash(x)=32249577) +4484 train 6.849472 (lr=2.4691e-05) (hash(x)=24752808) +4485 train 6.906816 (lr=2.4673e-05) (hash(x)=24970539) +4486 train 6.854015 (lr=2.4655e-05) (hash(x)=24191005) +4487 train 7.053641 (lr=2.4637e-05) (hash(x)=24974331) +4488 train 7.192899 (lr=2.4619e-05) (hash(x)=27043409) +4489 train 6.661504 (lr=2.4601e-05) (hash(x)=11320385) +4490 train 6.623017 (lr=2.4583e-05) (hash(x)=11919565) +4491 train 6.674376 (lr=2.4565e-05) (hash(x)=10404694) +4492 train 6.737144 (lr=2.4548e-05) (hash(x)=12393159) +4493 train 6.607121 (lr=2.4530e-05) (hash(x)=11843609) +4494 train 6.661137 (lr=2.4512e-05) (hash(x)=12632729) +4495 train 6.905118 (lr=2.4494e-05) (hash(x)=21951984) +4496 train 7.624794 (lr=2.4477e-05) (hash(x)=19411544) +4497 train 7.566987 (lr=2.4459e-05) (hash(x)=21000228) +4498 train 7.150426 (lr=2.4442e-05) (hash(x)=26018207) +4499 train 7.164445 (lr=2.4424e-05) (hash(x)=24659058) +4500 val loss 7.0604 +4500 val perplexity 1164.8600 +4500 train 7.336205 (lr=2.4407e-05) (hash(x)=27919597) +4501 train 6.904180 (lr=2.4389e-05) (hash(x)=26232596) +4502 train 7.068405 (lr=2.4372e-05) (hash(x)=26248912) +4503 train 6.934586 (lr=2.4354e-05) (hash(x)=25403751) +4504 train 6.792890 (lr=2.4337e-05) (hash(x)=21096637) +4505 train 7.012134 (lr=2.4320e-05) (hash(x)=26560941) +4506 train 7.024721 (lr=2.4302e-05) (hash(x)=24942406) +4507 train 7.070061 (lr=2.4285e-05) (hash(x)=24405748) +4508 train 6.968353 (lr=2.4268e-05) (hash(x)=22975455) +4509 train 6.916760 (lr=2.4251e-05) (hash(x)=26358820) +4510 train 6.906796 (lr=2.4234e-05) (hash(x)=24211938) +4511 train 7.069495 (lr=2.4216e-05) (hash(x)=26396012) +4512 train 6.762718 (lr=2.4199e-05) (hash(x)=22534410) +4513 train 6.880040 (lr=2.4182e-05) (hash(x)=23855025) +4514 train 6.788204 (lr=2.4165e-05) (hash(x)=22722345) +4515 train 6.760945 (lr=2.4148e-05) (hash(x)=22779251) +4516 train 7.044024 (lr=2.4131e-05) (hash(x)=23973078) +4517 train 6.895819 (lr=2.4114e-05) (hash(x)=19886228) +4518 train 6.991639 (lr=2.4097e-05) (hash(x)=23849694) +4519 train 7.375694 (lr=2.4081e-05) (hash(x)=24827190) +4520 train 6.956081 (lr=2.4064e-05) (hash(x)=25111498) +4521 train 7.769554 (lr=2.4047e-05) (hash(x)=29752556) +4522 train 7.200632 (lr=2.4030e-05) (hash(x)=25606805) +4523 train 6.959423 (lr=2.4014e-05) (hash(x)=22209714) +4524 train 6.730782 (lr=2.3997e-05) (hash(x)=24991834) +4525 train 6.990902 (lr=2.3980e-05) (hash(x)=27808158) +4526 train 6.912862 (lr=2.3964e-05) (hash(x)=23041199) +4527 train 6.971329 (lr=2.3947e-05) (hash(x)=24847458) +4528 train 6.901654 (lr=2.3930e-05) (hash(x)=25091787) +4529 train 7.847951 (lr=2.3914e-05) (hash(x)=29745551) +4530 train 6.616773 (lr=2.3897e-05) (hash(x)=20447167) +4531 train 6.824396 (lr=2.3881e-05) (hash(x)=20720911) +4532 train 6.989037 (lr=2.3865e-05) (hash(x)=24803353) +4533 train 7.075237 (lr=2.3848e-05) (hash(x)=23780724) +4534 train 7.092346 (lr=2.3832e-05) (hash(x)=23423120) +4535 train 6.724561 (lr=2.3816e-05) (hash(x)=22159088) +4536 train 6.939981 (lr=2.3799e-05) (hash(x)=25820304) +4537 train 6.753874 (lr=2.3783e-05) (hash(x)=22813612) +4538 train 7.070677 (lr=2.3767e-05) (hash(x)=27827979) +4539 train 7.078857 (lr=2.3751e-05) (hash(x)=25737179) +4540 train 7.309124 (lr=2.3735e-05) (hash(x)=23401504) +4541 train 6.913269 (lr=2.3718e-05) (hash(x)=25071988) +4542 train 6.959605 (lr=2.3702e-05) (hash(x)=22844541) +4543 train 6.720259 (lr=2.3686e-05) (hash(x)=22140034) +4544 train 6.987109 (lr=2.3670e-05) (hash(x)=26522091) +4545 train 6.984012 (lr=2.3654e-05) (hash(x)=24099725) +4546 train 6.599637 (lr=2.3638e-05) (hash(x)=19127182) +4547 train 6.725810 (lr=2.3622e-05) (hash(x)=18992693) +4548 train 7.717385 (lr=2.3607e-05) (hash(x)=26723015) +4549 train 7.502084 (lr=2.3591e-05) (hash(x)=30389969) +4550 val loss 7.0542 +4550 val perplexity 1157.6692 +4550 train 6.830537 (lr=2.3575e-05) (hash(x)=24065654) +4551 train 6.636968 (lr=2.3559e-05) (hash(x)=19044797) +4552 train 7.080427 (lr=2.3543e-05) (hash(x)=24919665) +4553 train 7.096611 (lr=2.3528e-05) (hash(x)=22780968) +4554 train 6.859481 (lr=2.3512e-05) (hash(x)=24549699) +4555 train 6.727820 (lr=2.3497e-05) (hash(x)=21374811) +4556 train 6.880096 (lr=2.3481e-05) (hash(x)=25225950) +4557 train 6.991162 (lr=2.3465e-05) (hash(x)=25691882) +4558 train 6.893299 (lr=2.3450e-05) (hash(x)=24685235) +4559 train 6.742971 (lr=2.3434e-05) (hash(x)=23932794) +4560 train 7.319667 (lr=2.3419e-05) (hash(x)=28152043) +4561 train 6.818582 (lr=2.3403e-05) (hash(x)=23417051) +4562 train 6.902988 (lr=2.3388e-05) (hash(x)=26250211) +4563 train 7.142559 (lr=2.3373e-05) (hash(x)=25428813) +4564 train 7.270663 (lr=2.3357e-05) (hash(x)=27477379) +4565 train 7.070994 (lr=2.3342e-05) (hash(x)=23015212) +4566 train 6.798975 (lr=2.3327e-05) (hash(x)=22837608) +4567 train 6.899025 (lr=2.3312e-05) (hash(x)=25256890) +4568 train 6.792412 (lr=2.3296e-05) (hash(x)=22742827) +4569 train 7.220022 (lr=2.3281e-05) (hash(x)=30167922) +4570 train 6.876390 (lr=2.3266e-05) (hash(x)=24540265) +4571 train 7.198172 (lr=2.3251e-05) (hash(x)=26752941) +4572 train 7.019664 (lr=2.3236e-05) (hash(x)=25094026) +4573 train 7.705734 (lr=2.3221e-05) (hash(x)=28508785) +4574 train 7.121004 (lr=2.3206e-05) (hash(x)=26501871) +4575 train 6.888823 (lr=2.3191e-05) (hash(x)=24161711) +4576 train 6.838544 (lr=2.3176e-05) (hash(x)=24313695) +4577 train 7.264735 (lr=2.3161e-05) (hash(x)=28248933) +4578 train 7.421266 (lr=2.3146e-05) (hash(x)=28445722) +4579 train 6.985803 (lr=2.3132e-05) (hash(x)=24589015) +4580 train 7.216770 (lr=2.3117e-05) (hash(x)=26192193) +4581 train 6.815567 (lr=2.3102e-05) (hash(x)=25131316) +4582 train 6.926597 (lr=2.3087e-05) (hash(x)=26631504) +4583 train 6.738036 (lr=2.3073e-05) (hash(x)=22036817) +4584 train 7.387535 (lr=2.3058e-05) (hash(x)=28361254) +4585 train 6.986195 (lr=2.3044e-05) (hash(x)=24828340) +4586 train 6.667457 (lr=2.3029e-05) (hash(x)=24067304) +4587 train 6.486755 (lr=2.3014e-05) (hash(x)=20733289) +4588 train 6.370675 (lr=2.3000e-05) (hash(x)=19526622) +4589 train 6.782222 (lr=2.2985e-05) (hash(x)=22148688) +4590 train 6.997241 (lr=2.2971e-05) (hash(x)=24141800) +4591 train 7.061389 (lr=2.2957e-05) (hash(x)=26663208) +4592 train 6.696364 (lr=2.2942e-05) (hash(x)=22536305) +4593 train 6.947572 (lr=2.2928e-05) (hash(x)=23608185) +4594 train 6.830077 (lr=2.2914e-05) (hash(x)=23348495) +4595 train 6.975191 (lr=2.2899e-05) (hash(x)=25409759) +4596 train 6.987617 (lr=2.2885e-05) (hash(x)=25572131) +4597 train 6.938574 (lr=2.2871e-05) (hash(x)=21782039) +4598 train 6.930234 (lr=2.2857e-05) (hash(x)=24643923) +4599 train 6.877899 (lr=2.2843e-05) (hash(x)=24072213) +4600 val loss 7.0596 +4600 val perplexity 1163.9500 +4600 train 6.808519 (lr=2.2829e-05) (hash(x)=23925612) +4601 train 6.924998 (lr=2.2815e-05) (hash(x)=23315415) +4602 train 6.901459 (lr=2.2801e-05) (hash(x)=21793800) +4603 train 6.840013 (lr=2.2787e-05) (hash(x)=24921200) +4604 train 7.114348 (lr=2.2773e-05) (hash(x)=27226113) +4605 train 6.900595 (lr=2.2759e-05) (hash(x)=22920960) +4606 train 6.845960 (lr=2.2745e-05) (hash(x)=21947750) +4607 train 6.911307 (lr=2.2731e-05) (hash(x)=22766044) +4608 train 7.308421 (lr=2.2717e-05) (hash(x)=28237005) +4609 train 6.742368 (lr=2.2703e-05) (hash(x)=24922621) +4610 train 6.972447 (lr=2.2690e-05) (hash(x)=24899830) +4611 train 7.380620 (lr=2.2676e-05) (hash(x)=32920298) +4612 train 6.828978 (lr=2.2662e-05) (hash(x)=25083835) +4613 train 6.880989 (lr=2.2649e-05) (hash(x)=22863054) +4614 train 6.901179 (lr=2.2635e-05) (hash(x)=24841464) +4615 train 7.182836 (lr=2.2621e-05) (hash(x)=27871153) +4616 train 7.208848 (lr=2.2608e-05) (hash(x)=28025163) +4617 train 6.850784 (lr=2.2594e-05) (hash(x)=24659561) +4618 train 6.957804 (lr=2.2581e-05) (hash(x)=25067194) +4619 train 6.931717 (lr=2.2568e-05) (hash(x)=22731460) +4620 train 6.910097 (lr=2.2554e-05) (hash(x)=20445873) +4621 train 6.976105 (lr=2.2541e-05) (hash(x)=26033948) +4622 train 6.821355 (lr=2.2527e-05) (hash(x)=22473213) +4623 train 7.374607 (lr=2.2514e-05) (hash(x)=24037280) +4624 train 7.811035 (lr=2.2501e-05) (hash(x)=25624131) +4625 train 7.431783 (lr=2.2488e-05) (hash(x)=26799867) +4626 train 6.998749 (lr=2.2475e-05) (hash(x)=27187602) +4627 train 6.932888 (lr=2.2461e-05) (hash(x)=23277695) +4628 train 6.955176 (lr=2.2448e-05) (hash(x)=24748234) +4629 train 7.041477 (lr=2.2435e-05) (hash(x)=26103104) +4630 train 6.969677 (lr=2.2422e-05) (hash(x)=24327389) +4631 train 7.084156 (lr=2.2409e-05) (hash(x)=24121850) +4632 train 6.927361 (lr=2.2396e-05) (hash(x)=23714590) +4633 train 6.989130 (lr=2.2383e-05) (hash(x)=22379412) +4634 train 7.226803 (lr=2.2370e-05) (hash(x)=24454713) +4635 train 6.888129 (lr=2.2357e-05) (hash(x)=22966977) +4636 train 6.875549 (lr=2.2345e-05) (hash(x)=23764884) +4637 train 6.748376 (lr=2.2332e-05) (hash(x)=23827429) +4638 train 6.950522 (lr=2.2319e-05) (hash(x)=24088592) +4639 train 6.934497 (lr=2.2306e-05) (hash(x)=24380031) +4640 train 7.036782 (lr=2.2293e-05) (hash(x)=26065050) +4641 train 6.949655 (lr=2.2281e-05) (hash(x)=24442902) +4642 train 6.564272 (lr=2.2268e-05) (hash(x)=18548782) +4643 train 7.029004 (lr=2.2256e-05) (hash(x)=26957303) +4644 train 7.029509 (lr=2.2243e-05) (hash(x)=25032727) +4645 train 6.939133 (lr=2.2230e-05) (hash(x)=27224706) +4646 train 7.066907 (lr=2.2218e-05) (hash(x)=27508476) +4647 train 6.763650 (lr=2.2206e-05) (hash(x)=23055215) +4648 train 6.932739 (lr=2.2193e-05) (hash(x)=24496194) +4649 train 8.128159 (lr=2.2181e-05) (hash(x)=13982941) +4650 val loss 7.0571 +4650 val perplexity 1161.0851 +4650 train 7.369452 (lr=2.2168e-05) (hash(x)=16721547) +4651 train 6.922415 (lr=2.2156e-05) (hash(x)=22929154) +4652 train 6.852532 (lr=2.2144e-05) (hash(x)=23323994) +4653 train 7.210570 (lr=2.2131e-05) (hash(x)=24877951) +4654 train 7.065827 (lr=2.2119e-05) (hash(x)=24096183) +4655 train 6.878747 (lr=2.2107e-05) (hash(x)=25329724) +4656 train 6.844214 (lr=2.2095e-05) (hash(x)=23877337) +4657 train 6.463959 (lr=2.2083e-05) (hash(x)=20923083) +4658 train 6.806021 (lr=2.2071e-05) (hash(x)=23807996) +4659 train 6.887759 (lr=2.2059e-05) (hash(x)=24370475) +4660 train 7.289089 (lr=2.2047e-05) (hash(x)=28202255) +4661 train 7.004226 (lr=2.2035e-05) (hash(x)=26142119) +4662 train 6.770473 (lr=2.2023e-05) (hash(x)=21387743) +4663 train 6.924708 (lr=2.2011e-05) (hash(x)=25662408) +4664 train 6.974173 (lr=2.1999e-05) (hash(x)=23962815) +4665 train 6.904494 (lr=2.1987e-05) (hash(x)=23987677) +4666 train 7.185635 (lr=2.1975e-05) (hash(x)=26554284) +4667 train 7.243459 (lr=2.1964e-05) (hash(x)=25991817) +4668 train 6.947702 (lr=2.1952e-05) (hash(x)=24256966) +4669 train 6.718888 (lr=2.1940e-05) (hash(x)=22187158) +4670 train 6.992026 (lr=2.1928e-05) (hash(x)=26295320) +4671 train 7.028871 (lr=2.1917e-05) (hash(x)=26346814) +4672 train 7.271211 (lr=2.1905e-05) (hash(x)=26594196) +4673 train 7.040532 (lr=2.1894e-05) (hash(x)=24322101) +4674 train 7.157824 (lr=2.1882e-05) (hash(x)=27274566) +4675 train 6.982916 (lr=2.1871e-05) (hash(x)=24505725) +4676 train 7.147966 (lr=2.1859e-05) (hash(x)=26167371) +4677 train 7.239706 (lr=2.1848e-05) (hash(x)=28062311) +4678 train 6.962337 (lr=2.1836e-05) (hash(x)=23476009) +4679 train 7.058740 (lr=2.1825e-05) (hash(x)=25283256) +4680 train 6.773311 (lr=2.1814e-05) (hash(x)=22033246) +4681 train 6.805192 (lr=2.1802e-05) (hash(x)=22716214) +4682 train 6.966693 (lr=2.1791e-05) (hash(x)=25672672) +4683 train 6.860503 (lr=2.1780e-05) (hash(x)=22979072) +4684 train 7.050117 (lr=2.1769e-05) (hash(x)=27439204) +4685 train 6.919405 (lr=2.1758e-05) (hash(x)=24857737) +4686 train 7.224020 (lr=2.1747e-05) (hash(x)=29615897) +4687 train 6.799901 (lr=2.1736e-05) (hash(x)=24021771) +4688 train 6.940948 (lr=2.1725e-05) (hash(x)=27410807) +4689 train 6.754753 (lr=2.1713e-05) (hash(x)=22850411) +4690 train 7.057407 (lr=2.1703e-05) (hash(x)=24949696) +4691 train 6.836101 (lr=2.1692e-05) (hash(x)=22956381) +4692 train 7.329645 (lr=2.1681e-05) (hash(x)=28193458) +4693 train 6.857884 (lr=2.1670e-05) (hash(x)=25596844) +4694 train 6.819917 (lr=2.1659e-05) (hash(x)=22101377) +4695 train 6.747400 (lr=2.1648e-05) (hash(x)=23576840) +4696 train 6.745268 (lr=2.1637e-05) (hash(x)=21849758) +4697 train 6.932886 (lr=2.1627e-05) (hash(x)=26431349) +4698 train 7.046182 (lr=2.1616e-05) (hash(x)=22960758) +4699 train 6.937413 (lr=2.1605e-05) (hash(x)=23243097) +4700 val loss 7.0523 +4700 val perplexity 1155.4913 +4700 train 6.858510 (lr=2.1595e-05) (hash(x)=23715370) +4701 train 7.512084 (lr=2.1584e-05) (hash(x)=30678293) +4702 train 7.592770 (lr=2.1574e-05) (hash(x)=32481620) +4703 train 7.136013 (lr=2.1563e-05) (hash(x)=26414858) +4704 train 7.005015 (lr=2.1553e-05) (hash(x)=24768691) +4705 train 6.666608 (lr=2.1542e-05) (hash(x)=21627762) +4706 train 6.771503 (lr=2.1532e-05) (hash(x)=21024917) +4707 train 6.728154 (lr=2.1521e-05) (hash(x)=23570951) +4708 train 6.847403 (lr=2.1511e-05) (hash(x)=23729185) +4709 train 7.180257 (lr=2.1501e-05) (hash(x)=25933754) +4710 train 6.658575 (lr=2.1491e-05) (hash(x)=23091014) +4711 train 6.757465 (lr=2.1480e-05) (hash(x)=20099261) +4712 train 6.921431 (lr=2.1470e-05) (hash(x)=26807297) +4713 train 6.809167 (lr=2.1460e-05) (hash(x)=25332115) +4714 train 6.824165 (lr=2.1450e-05) (hash(x)=23247605) +4715 train 6.714652 (lr=2.1440e-05) (hash(x)=23786549) +4716 train 6.811179 (lr=2.1430e-05) (hash(x)=23981166) +4717 train 6.964558 (lr=2.1420e-05) (hash(x)=25967754) +4718 train 6.824749 (lr=2.1410e-05) (hash(x)=23659116) +4719 train 6.858624 (lr=2.1400e-05) (hash(x)=22453718) +4720 train 6.819760 (lr=2.1390e-05) (hash(x)=22597951) +4721 train 7.038930 (lr=2.1380e-05) (hash(x)=25284885) +4722 train 6.989922 (lr=2.1370e-05) (hash(x)=24748569) +4723 train 6.597750 (lr=2.1360e-05) (hash(x)=19448608) +4724 train 6.945013 (lr=2.1350e-05) (hash(x)=24888040) +4725 train 6.833818 (lr=2.1341e-05) (hash(x)=23203503) +4726 train 6.586975 (lr=2.1331e-05) (hash(x)=20387787) +4727 train 6.668482 (lr=2.1321e-05) (hash(x)=22529445) +4728 train 6.967752 (lr=2.1312e-05) (hash(x)=22455471) +4729 train 6.943413 (lr=2.1302e-05) (hash(x)=25661132) +4730 train 6.931340 (lr=2.1293e-05) (hash(x)=24997711) +4731 train 7.045332 (lr=2.1283e-05) (hash(x)=22575521) +4732 train 6.824548 (lr=2.1273e-05) (hash(x)=22640285) +4733 train 6.677812 (lr=2.1264e-05) (hash(x)=18637357) +4734 train 6.818816 (lr=2.1255e-05) (hash(x)=22845826) +4735 train 7.033162 (lr=2.1245e-05) (hash(x)=24484543) +4736 train 6.863969 (lr=2.1236e-05) (hash(x)=23352320) +4737 train 6.692725 (lr=2.1227e-05) (hash(x)=21544758) +4738 train 6.472330 (lr=2.1217e-05) (hash(x)=18292136) +4739 train 7.132041 (lr=2.1208e-05) (hash(x)=24893614) +4740 train 6.998928 (lr=2.1199e-05) (hash(x)=28103443) +4741 train 6.783705 (lr=2.1190e-05) (hash(x)=22233356) +4742 train 6.661655 (lr=2.1180e-05) (hash(x)=21133541) +4743 train 6.942408 (lr=2.1171e-05) (hash(x)=24043998) +4744 train 7.226996 (lr=2.1162e-05) (hash(x)=24801185) +4745 train 6.995575 (lr=2.1153e-05) (hash(x)=23858358) +4746 train 7.012098 (lr=2.1144e-05) (hash(x)=23926989) +4747 train 7.077411 (lr=2.1135e-05) (hash(x)=24813708) +4748 train 6.901106 (lr=2.1126e-05) (hash(x)=26339467) +4749 train 6.741702 (lr=2.1117e-05) (hash(x)=21850656) +4750 val loss 7.0501 +4750 val perplexity 1152.9458 +4750 train 6.732001 (lr=2.1108e-05) (hash(x)=21475802) +4751 train 6.946807 (lr=2.1100e-05) (hash(x)=24301906) +4752 train 6.761426 (lr=2.1091e-05) (hash(x)=22748495) +4753 train 6.939968 (lr=2.1082e-05) (hash(x)=25649256) +4754 train 6.841129 (lr=2.1073e-05) (hash(x)=23934346) +4755 train 6.959776 (lr=2.1065e-05) (hash(x)=26332892) +4756 train 6.823593 (lr=2.1056e-05) (hash(x)=23279389) +4757 train 6.885849 (lr=2.1047e-05) (hash(x)=23146858) +4758 train 7.258716 (lr=2.1039e-05) (hash(x)=26892932) +4759 train 6.750474 (lr=2.1030e-05) (hash(x)=26328881) +4760 train 6.869104 (lr=2.1022e-05) (hash(x)=24394655) +4761 train 6.843584 (lr=2.1013e-05) (hash(x)=22122308) +4762 train 7.016392 (lr=2.1005e-05) (hash(x)=24200369) +4763 train 7.117186 (lr=2.0996e-05) (hash(x)=26841776) +4764 train 7.082376 (lr=2.0988e-05) (hash(x)=27196641) +4765 train 6.826642 (lr=2.0980e-05) (hash(x)=24912822) +4766 train 7.089668 (lr=2.0971e-05) (hash(x)=25946055) +4767 train 6.679953 (lr=2.0963e-05) (hash(x)=23101508) +4768 train 6.843723 (lr=2.0955e-05) (hash(x)=24287798) +4769 train 6.938585 (lr=2.0947e-05) (hash(x)=22798964) +4770 train 6.862647 (lr=2.0939e-05) (hash(x)=24164479) +4771 train 6.911826 (lr=2.0930e-05) (hash(x)=24946464) +4772 train 7.041081 (lr=2.0922e-05) (hash(x)=25154423) +4773 train 6.742923 (lr=2.0914e-05) (hash(x)=23173476) +4774 train 7.000484 (lr=2.0906e-05) (hash(x)=25373559) +4775 train 6.972904 (lr=2.0898e-05) (hash(x)=23527176) +4776 train 6.925415 (lr=2.0890e-05) (hash(x)=24865403) +4777 train 6.861012 (lr=2.0882e-05) (hash(x)=24451067) +4778 train 7.515499 (lr=2.0874e-05) (hash(x)=28187162) +4779 train 7.670222 (lr=2.0867e-05) (hash(x)=31163350) +4780 train 7.994597 (lr=2.0859e-05) (hash(x)=33563280) +4781 train 8.050925 (lr=2.0851e-05) (hash(x)=34939183) +4782 train 7.526334 (lr=2.0843e-05) (hash(x)=30263543) +4783 train 6.813100 (lr=2.0836e-05) (hash(x)=22705673) +4784 train 6.710958 (lr=2.0828e-05) (hash(x)=21415023) +4785 train 6.939400 (lr=2.0820e-05) (hash(x)=26079097) +4786 train 7.266760 (lr=2.0813e-05) (hash(x)=25503836) +4787 train 7.102166 (lr=2.0805e-05) (hash(x)=24705721) +4788 train 6.973627 (lr=2.0798e-05) (hash(x)=24384657) +4789 train 6.881668 (lr=2.0790e-05) (hash(x)=22550579) +4790 train 6.949705 (lr=2.0783e-05) (hash(x)=22452164) +4791 train 7.215284 (lr=2.0775e-05) (hash(x)=28664796) +4792 train 7.567465 (lr=2.0768e-05) (hash(x)=26139280) +4793 train 7.232520 (lr=2.0760e-05) (hash(x)=23862341) +4794 train 6.775206 (lr=2.0753e-05) (hash(x)=23784757) +4795 train 6.642473 (lr=2.0746e-05) (hash(x)=22659441) +4796 train 7.425055 (lr=2.0739e-05) (hash(x)=29744216) +4797 train 7.310657 (lr=2.0731e-05) (hash(x)=25822591) +4798 train 6.739431 (lr=2.0724e-05) (hash(x)=22370895) +4799 train 7.182725 (lr=2.0717e-05) (hash(x)=27102890) +4800 val loss 7.0499 +4800 val perplexity 1152.7892 +4800 train 7.236328 (lr=2.0710e-05) (hash(x)=27014625) +4801 train 6.986424 (lr=2.0703e-05) (hash(x)=25755963) +4802 train 7.231141 (lr=2.0696e-05) (hash(x)=29675278) +4803 train 7.357839 (lr=2.0689e-05) (hash(x)=26660930) +4804 train 7.273388 (lr=2.0682e-05) (hash(x)=24557060) +4805 train 7.415939 (lr=2.0675e-05) (hash(x)=24622741) +4806 train 7.455686 (lr=2.0668e-05) (hash(x)=23952601) +4807 train 7.061226 (lr=2.0661e-05) (hash(x)=26787259) +4808 train 7.297729 (lr=2.0654e-05) (hash(x)=28919605) +4809 train 7.644696 (lr=2.0648e-05) (hash(x)=37061654) +4810 train 7.414094 (lr=2.0641e-05) (hash(x)=30379739) +4811 train 7.171903 (lr=2.0634e-05) (hash(x)=26097180) +4812 train 7.344755 (lr=2.0627e-05) (hash(x)=26327092) +4813 train 7.090932 (lr=2.0621e-05) (hash(x)=23258030) +4814 train 7.148643 (lr=2.0614e-05) (hash(x)=25582015) +4815 train 6.842813 (lr=2.0608e-05) (hash(x)=23396088) +4816 train 6.815907 (lr=2.0601e-05) (hash(x)=21904146) +4817 train 7.034708 (lr=2.0595e-05) (hash(x)=26281676) +4818 train 6.771539 (lr=2.0588e-05) (hash(x)=23140470) +4819 train 7.104492 (lr=2.0582e-05) (hash(x)=24611098) +4820 train 6.917427 (lr=2.0575e-05) (hash(x)=23832642) +4821 train 7.101959 (lr=2.0569e-05) (hash(x)=21439671) +4822 train 6.954273 (lr=2.0563e-05) (hash(x)=25128845) +4823 train 6.908896 (lr=2.0556e-05) (hash(x)=24911831) +4824 train 7.061580 (lr=2.0550e-05) (hash(x)=26051723) +4825 train 7.085388 (lr=2.0544e-05) (hash(x)=26479565) +4826 train 7.182396 (lr=2.0538e-05) (hash(x)=26228987) +4827 train 7.069623 (lr=2.0531e-05) (hash(x)=25131300) +4828 train 6.789140 (lr=2.0525e-05) (hash(x)=19921978) +4829 train 6.800167 (lr=2.0519e-05) (hash(x)=23173449) +4830 train 7.131239 (lr=2.0513e-05) (hash(x)=24791832) +4831 train 6.853048 (lr=2.0507e-05) (hash(x)=23453491) +4832 train 6.992917 (lr=2.0501e-05) (hash(x)=22564139) +4833 train 6.812351 (lr=2.0495e-05) (hash(x)=21659918) +4834 train 6.935024 (lr=2.0489e-05) (hash(x)=22956076) +4835 train 7.047150 (lr=2.0483e-05) (hash(x)=22237612) +4836 train 7.151935 (lr=2.0478e-05) (hash(x)=24736427) +4837 train 7.253217 (lr=2.0472e-05) (hash(x)=24939751) +4838 train 7.080099 (lr=2.0466e-05) (hash(x)=25059298) +4839 train 6.985178 (lr=2.0460e-05) (hash(x)=23453396) +4840 train 6.498339 (lr=2.0455e-05) (hash(x)=17919338) +4841 train 7.020661 (lr=2.0449e-05) (hash(x)=23428815) +4842 train 7.291719 (lr=2.0443e-05) (hash(x)=27042659) +4843 train 7.369102 (lr=2.0438e-05) (hash(x)=25161278) +4844 train 7.143215 (lr=2.0432e-05) (hash(x)=24113253) +4845 train 7.280033 (lr=2.0427e-05) (hash(x)=26139263) +4846 train 7.294458 (lr=2.0421e-05) (hash(x)=27787006) +4847 train 7.035744 (lr=2.0416e-05) (hash(x)=23869612) +4848 train 7.165134 (lr=2.0410e-05) (hash(x)=26092193) +4849 train 7.197397 (lr=2.0405e-05) (hash(x)=29351182) +4850 val loss 7.0414 +4850 val perplexity 1143.0018 +4850 train 7.405325 (lr=2.0400e-05) (hash(x)=28773463) +4851 train 7.305812 (lr=2.0394e-05) (hash(x)=28207741) +4852 train 6.846499 (lr=2.0389e-05) (hash(x)=23280878) +4853 train 7.312439 (lr=2.0384e-05) (hash(x)=26742336) +4854 train 7.078151 (lr=2.0379e-05) (hash(x)=23543321) +4855 train 7.463478 (lr=2.0373e-05) (hash(x)=26581590) +4856 train 6.912457 (lr=2.0368e-05) (hash(x)=22728668) +4857 train 6.732494 (lr=2.0363e-05) (hash(x)=19854534) +4858 train 7.184772 (lr=2.0358e-05) (hash(x)=26612813) +4859 train 7.282388 (lr=2.0353e-05) (hash(x)=25827863) +4860 train 6.984677 (lr=2.0348e-05) (hash(x)=24574997) +4861 train 7.152147 (lr=2.0343e-05) (hash(x)=26187830) +4862 train 7.098167 (lr=2.0338e-05) (hash(x)=25105823) +4863 train 7.153999 (lr=2.0333e-05) (hash(x)=28056342) +4864 train 7.020147 (lr=2.0329e-05) (hash(x)=21885801) +4865 train 7.238182 (lr=2.0324e-05) (hash(x)=25659043) +4866 train 7.177330 (lr=2.0319e-05) (hash(x)=23852824) +4867 train 6.989183 (lr=2.0314e-05) (hash(x)=23965470) +4868 train 6.977815 (lr=2.0309e-05) (hash(x)=25035012) +4869 train 7.200046 (lr=2.0305e-05) (hash(x)=26639165) +4870 train 7.148146 (lr=2.0300e-05) (hash(x)=29205362) +4871 train 6.983613 (lr=2.0296e-05) (hash(x)=25900866) +4872 train 7.050435 (lr=2.0291e-05) (hash(x)=25636242) +4873 train 7.126640 (lr=2.0286e-05) (hash(x)=25430698) +4874 train 7.106996 (lr=2.0282e-05) (hash(x)=27629981) +4875 train 7.083393 (lr=2.0278e-05) (hash(x)=27682625) +4876 train 7.346222 (lr=2.0273e-05) (hash(x)=27549409) +4877 train 7.037572 (lr=2.0269e-05) (hash(x)=24661627) +4878 train 7.140326 (lr=2.0264e-05) (hash(x)=25196542) +4879 train 7.013040 (lr=2.0260e-05) (hash(x)=24549177) +4880 train 6.983034 (lr=2.0256e-05) (hash(x)=23740600) +4881 train 6.873134 (lr=2.0252e-05) (hash(x)=21460850) +4882 train 7.173343 (lr=2.0247e-05) (hash(x)=27101400) +4883 train 7.179771 (lr=2.0243e-05) (hash(x)=24193076) +4884 train 7.060396 (lr=2.0239e-05) (hash(x)=24582947) +4885 train 7.043518 (lr=2.0235e-05) (hash(x)=25133839) +4886 train 7.018242 (lr=2.0231e-05) (hash(x)=24759454) +4887 train 7.091990 (lr=2.0227e-05) (hash(x)=28239583) +4888 train 7.349094 (lr=2.0223e-05) (hash(x)=29594489) +4889 train 7.042489 (lr=2.0219e-05) (hash(x)=23833431) +4890 train 7.028220 (lr=2.0215e-05) (hash(x)=23139411) +4891 train 6.966406 (lr=2.0211e-05) (hash(x)=20885864) +4892 train 7.368356 (lr=2.0207e-05) (hash(x)=26217418) +4893 train 7.148161 (lr=2.0203e-05) (hash(x)=27321870) +4894 train 6.645943 (lr=2.0200e-05) (hash(x)=19912955) +4895 train 6.973163 (lr=2.0196e-05) (hash(x)=23223554) +4896 train 7.130360 (lr=2.0192e-05) (hash(x)=25667219) +4897 train 7.382980 (lr=2.0188e-05) (hash(x)=28007972) +4898 train 7.183275 (lr=2.0185e-05) (hash(x)=27748764) +4899 train 7.122581 (lr=2.0181e-05) (hash(x)=27425770) +4900 val loss 7.0393 +4900 val perplexity 1140.6063 +4900 train 7.250913 (lr=2.0178e-05) (hash(x)=28394020) +4901 train 7.092083 (lr=2.0174e-05) (hash(x)=24080235) +4902 train 6.925556 (lr=2.0171e-05) (hash(x)=23309527) +4903 train 6.950064 (lr=2.0167e-05) (hash(x)=24793480) +4904 train 7.164877 (lr=2.0164e-05) (hash(x)=25344456) +4905 train 7.093628 (lr=2.0160e-05) (hash(x)=24590670) +4906 train 7.067671 (lr=2.0157e-05) (hash(x)=26937171) +4907 train 7.186443 (lr=2.0154e-05) (hash(x)=26949097) +4908 train 6.893215 (lr=2.0150e-05) (hash(x)=22443915) +4909 train 6.981452 (lr=2.0147e-05) (hash(x)=23814995) +4910 train 6.991664 (lr=2.0144e-05) (hash(x)=26135871) +4911 train 6.855831 (lr=2.0141e-05) (hash(x)=25415570) +4912 train 7.151720 (lr=2.0138e-05) (hash(x)=26756326) +4913 train 7.037107 (lr=2.0134e-05) (hash(x)=22920200) +4914 train 7.091981 (lr=2.0131e-05) (hash(x)=26710977) +4915 train 6.989902 (lr=2.0128e-05) (hash(x)=24985634) +4916 train 7.127512 (lr=2.0125e-05) (hash(x)=26004335) +4917 train 7.038444 (lr=2.0122e-05) (hash(x)=25637457) +4918 train 7.284233 (lr=2.0119e-05) (hash(x)=26645180) +4919 train 7.124481 (lr=2.0117e-05) (hash(x)=24425760) +4920 train 7.365210 (lr=2.0114e-05) (hash(x)=28223544) +4921 train 7.034604 (lr=2.0111e-05) (hash(x)=25538618) +4922 train 7.280697 (lr=2.0108e-05) (hash(x)=26984784) +4923 train 7.331925 (lr=2.0105e-05) (hash(x)=29154578) +4924 train 7.013786 (lr=2.0103e-05) (hash(x)=25308123) +4925 train 7.338376 (lr=2.0100e-05) (hash(x)=27939259) +4926 train 6.940901 (lr=2.0097e-05) (hash(x)=21984545) +4927 train 6.974918 (lr=2.0095e-05) (hash(x)=23707134) +4928 train 7.029053 (lr=2.0092e-05) (hash(x)=27201034) +4929 train 7.399883 (lr=2.0090e-05) (hash(x)=31623877) +4930 train 7.024704 (lr=2.0087e-05) (hash(x)=22162782) +4931 train 6.951215 (lr=2.0085e-05) (hash(x)=20049335) +4932 train 6.879496 (lr=2.0082e-05) (hash(x)=25594665) +4933 train 6.999654 (lr=2.0080e-05) (hash(x)=25265312) +4934 train 7.132524 (lr=2.0077e-05) (hash(x)=27094896) +4935 train 7.504952 (lr=2.0075e-05) (hash(x)=28321697) +4936 train 6.981875 (lr=2.0073e-05) (hash(x)=25006013) +4937 train 7.183263 (lr=2.0071e-05) (hash(x)=24596431) +4938 train 7.226139 (lr=2.0068e-05) (hash(x)=25150510) +4939 train 6.716886 (lr=2.0066e-05) (hash(x)=21497535) +4940 train 6.997716 (lr=2.0064e-05) (hash(x)=25094669) +4941 train 6.895864 (lr=2.0062e-05) (hash(x)=24024557) +4942 train 7.186531 (lr=2.0060e-05) (hash(x)=24370776) +4943 train 7.012692 (lr=2.0058e-05) (hash(x)=23434031) +4944 train 7.009854 (lr=2.0056e-05) (hash(x)=24383517) +4945 train 7.045556 (lr=2.0054e-05) (hash(x)=25858759) +4946 train 6.630162 (lr=2.0052e-05) (hash(x)=20409561) +4947 train 7.339978 (lr=2.0050e-05) (hash(x)=27469117) +4948 train 6.868637 (lr=2.0048e-05) (hash(x)=22086623) +4949 train 7.189788 (lr=2.0046e-05) (hash(x)=25759281) +4950 val loss 7.0323 +4950 val perplexity 1132.6721 +4950 train 7.088814 (lr=2.0044e-05) (hash(x)=27130117) +4951 train 6.971602 (lr=2.0043e-05) (hash(x)=27003481) +4952 train 7.271783 (lr=2.0041e-05) (hash(x)=26725937) +4953 train 7.018382 (lr=2.0039e-05) (hash(x)=22691119) +4954 train 7.094114 (lr=2.0038e-05) (hash(x)=17272898) +4955 train 6.899991 (lr=2.0036e-05) (hash(x)=17850370) +4956 train 6.886455 (lr=2.0034e-05) (hash(x)=18729639) +4957 train 7.095670 (lr=2.0033e-05) (hash(x)=25327160) +4958 train 7.224419 (lr=2.0031e-05) (hash(x)=28709044) +4959 train 6.809924 (lr=2.0030e-05) (hash(x)=22236893) +4960 train 6.768777 (lr=2.0028e-05) (hash(x)=21729251) +4961 train 6.876382 (lr=2.0027e-05) (hash(x)=23852346) +4962 train 7.092422 (lr=2.0026e-05) (hash(x)=23974368) +4963 train 7.011176 (lr=2.0024e-05) (hash(x)=25764691) +4964 train 7.411777 (lr=2.0023e-05) (hash(x)=28341865) +4965 train 6.921597 (lr=2.0022e-05) (hash(x)=23856238) +4966 train 7.165676 (lr=2.0021e-05) (hash(x)=24568904) +4967 train 7.056539 (lr=2.0019e-05) (hash(x)=26857458) +4968 train 6.904686 (lr=2.0018e-05) (hash(x)=20507972) +4969 train 7.091471 (lr=2.0017e-05) (hash(x)=23139455) +4970 train 6.937618 (lr=2.0016e-05) (hash(x)=24853703) +4971 train 6.974797 (lr=2.0015e-05) (hash(x)=25654849) +4972 train 6.802204 (lr=2.0014e-05) (hash(x)=22963710) +4973 train 7.205987 (lr=2.0013e-05) (hash(x)=25652110) +4974 train 7.142027 (lr=2.0012e-05) (hash(x)=24085957) +4975 train 7.344255 (lr=2.0011e-05) (hash(x)=26413122) +4976 train 7.478221 (lr=2.0010e-05) (hash(x)=26989387) +4977 train 7.102092 (lr=2.0009e-05) (hash(x)=22784033) +4978 train 7.472764 (lr=2.0009e-05) (hash(x)=26694945) +4979 train 7.414401 (lr=2.0008e-05) (hash(x)=24507726) +4980 train 7.463115 (lr=2.0007e-05) (hash(x)=26490335) +4981 train 7.413246 (lr=2.0006e-05) (hash(x)=25624751) +4982 train 7.371934 (lr=2.0006e-05) (hash(x)=27846204) +4983 train 7.239197 (lr=2.0005e-05) (hash(x)=27696537) +4984 train 7.127348 (lr=2.0005e-05) (hash(x)=28915842) +4985 train 7.195924 (lr=2.0004e-05) (hash(x)=28274576) +4986 train 7.251314 (lr=2.0003e-05) (hash(x)=28923892) +4987 train 6.852051 (lr=2.0003e-05) (hash(x)=21602520) +4988 train 6.799268 (lr=2.0003e-05) (hash(x)=21061011) +4989 train 7.269334 (lr=2.0002e-05) (hash(x)=28060542) +4990 train 7.065526 (lr=2.0002e-05) (hash(x)=24838134) +4991 train 7.022876 (lr=2.0001e-05) (hash(x)=21950234) +4992 train 7.273752 (lr=2.0001e-05) (hash(x)=27192740) +4993 train 7.258007 (lr=2.0001e-05) (hash(x)=26770105) +4994 train 6.932539 (lr=2.0001e-05) (hash(x)=23721261) +4995 train 6.977872 (lr=2.0000e-05) (hash(x)=26064895) +4996 train 7.183889 (lr=2.0000e-05) (hash(x)=25651075) +4997 train 7.037956 (lr=2.0000e-05) (hash(x)=25029447) +4998 train 7.154950 (lr=2.0000e-05) (hash(x)=26088225) +4999 val loss 7.0376 +4999 val perplexity 1138.5984 +4999 train 7.073069 (lr=2.0000e-05) (hash(x)=24051952) diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/model_02500.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/model_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..dfc2e3db732bd8bfd301d323ec68b7fcbc306954 --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/model_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb2d3305cfc1a56b355dec0ec8d3481e675742da1986b55b5884e7263a9cc10f +size 38587970 diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/model_04999.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/model_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..13979da949127f29fc1980bd1f5439b828e3d2bd --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/model_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb6f463bc36f5e16508c16ce5fb3434312128864c25d5c15ecf767ed1aee6b8f +size 38587970 diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/optimizer_02500.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/optimizer_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..2be999125a03aafed3f64992cda73b9b068ea8c4 --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/optimizer_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:591ab9c2c03da446f3186475d9a8ac85f14e5f9e57c40c19539baf5ad2041d6d +size 70895430 diff --git a/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/optimizer_04999.pt b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/optimizer_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..de41d4231c172aa18a44472d09650031ec0d8454 --- /dev/null +++ b/lr2e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/optimizer_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:252b9542a1ebf4bef7089827b586a3048dd9b24cbc92aef45ff231c995948cf8 +size 70895430