diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/args.json b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/args.json new file mode 100644 index 0000000000000000000000000000000000000000..5509b682e36938b87c64e18d8270788cf5e8ef09 --- /dev/null +++ b/lr1.75e-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/lr1.75e-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": 0.000175, "decay_lr": true, "readout_zero_init": false, "query_zero_init": false, "l1_loss": false, "debugpy": false, "n_embd": 128} \ No newline at end of file diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/dataloader_02500.pt b/lr1.75e-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/lr1.75e-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/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/dataloader_04999.pt b/lr1.75e-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/lr1.75e-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/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/log2.txt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/log2.txt new file mode 100644 index 0000000000000000000000000000000000000000..1859d75e57dd34d597abdc7b8869c41b23400073 --- /dev/null +++ b/lr1.75e-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=1.7500e-04) (hash(x)=22886834) +1 train 11.396555 (lr=1.7500e-04) (hash(x)=26375038) +2 train 11.169489 (lr=1.7500e-04) (hash(x)=30598777) +3 train 11.028533 (lr=1.7500e-04) (hash(x)=27234506) +4 train 10.733047 (lr=1.7500e-04) (hash(x)=27767880) +5 train 10.559708 (lr=1.7500e-04) (hash(x)=23702020) +6 train 10.599311 (lr=1.7500e-04) (hash(x)=31986844) +7 train 10.441170 (lr=1.7500e-04) (hash(x)=20782690) +8 train 10.414865 (lr=1.7500e-04) (hash(x)=25201599) +9 train 10.289166 (lr=1.7500e-04) (hash(x)=23094976) +10 train 10.245318 (lr=1.7500e-04) (hash(x)=23841096) +11 train 10.245503 (lr=1.7500e-04) (hash(x)=26532095) +12 train 10.175285 (lr=1.7500e-04) (hash(x)=24432298) +13 train 10.160977 (lr=1.7500e-04) (hash(x)=27151649) +14 train 10.200006 (lr=1.7500e-04) (hash(x)=24596846) +15 train 9.930424 (lr=1.7500e-04) (hash(x)=23890908) +16 train 9.876884 (lr=1.7500e-04) (hash(x)=28913955) +17 train 9.732286 (lr=1.7500e-04) (hash(x)=25588236) +18 train 9.796841 (lr=1.7500e-04) (hash(x)=23770034) +19 train 9.637856 (lr=1.7499e-04) (hash(x)=24011372) +20 train 9.460370 (lr=1.7499e-04) (hash(x)=25441898) +21 train 9.639175 (lr=1.7499e-04) (hash(x)=28375581) +22 train 9.278931 (lr=1.7499e-04) (hash(x)=24046679) +23 train 9.336289 (lr=1.7499e-04) (hash(x)=24611628) +24 train 9.318339 (lr=1.7499e-04) (hash(x)=26169030) +25 train 9.348361 (lr=1.7499e-04) (hash(x)=30298407) +26 train 9.072040 (lr=1.7499e-04) (hash(x)=23711112) +27 train 8.877810 (lr=1.7499e-04) (hash(x)=19245352) +28 train 8.813415 (lr=1.7499e-04) (hash(x)=21529136) +29 train 9.186362 (lr=1.7499e-04) (hash(x)=28936608) +30 train 8.730496 (lr=1.7499e-04) (hash(x)=24339013) +31 train 8.572330 (lr=1.7499e-04) (hash(x)=25767553) +32 train 8.734408 (lr=1.7499e-04) (hash(x)=26439905) +33 train 8.907145 (lr=1.7498e-04) (hash(x)=31093473) +34 train 8.500969 (lr=1.7498e-04) (hash(x)=25450374) +35 train 8.381739 (lr=1.7498e-04) (hash(x)=24809873) +36 train 8.534350 (lr=1.7498e-04) (hash(x)=23253252) +37 train 8.614918 (lr=1.7498e-04) (hash(x)=27852919) +38 train 8.349433 (lr=1.7498e-04) (hash(x)=23327497) +39 train 8.207426 (lr=1.7498e-04) (hash(x)=22512166) +40 train 8.340344 (lr=1.7498e-04) (hash(x)=22859419) +41 train 8.286136 (lr=1.7498e-04) (hash(x)=27620338) +42 train 8.363899 (lr=1.7497e-04) (hash(x)=26397837) +43 train 8.369537 (lr=1.7497e-04) (hash(x)=28092148) +44 train 8.194524 (lr=1.7497e-04) (hash(x)=24662703) +45 train 8.361908 (lr=1.7497e-04) (hash(x)=27938767) +46 train 8.670207 (lr=1.7497e-04) (hash(x)=26037988) +47 train 8.054297 (lr=1.7497e-04) (hash(x)=24732833) +48 train 8.169591 (lr=1.7497e-04) (hash(x)=25259526) +49 train 8.143176 (lr=1.7496e-04) (hash(x)=23200230) +50 val loss 8.0872 +50 val perplexity 3252.4224 +50 train 8.152373 (lr=1.7496e-04) (hash(x)=26721357) +51 train 7.966598 (lr=1.7496e-04) (hash(x)=22694718) +52 train 8.063544 (lr=1.7496e-04) (hash(x)=28066766) +53 train 7.996901 (lr=1.7496e-04) (hash(x)=23125151) +54 train 8.005190 (lr=1.7496e-04) (hash(x)=27193725) +55 train 7.887970 (lr=1.7495e-04) (hash(x)=25129410) +56 train 8.008475 (lr=1.7495e-04) (hash(x)=24263988) +57 train 7.812988 (lr=1.7495e-04) (hash(x)=23059154) +58 train 8.038404 (lr=1.7495e-04) (hash(x)=26063864) +59 train 8.296872 (lr=1.7495e-04) (hash(x)=27858570) +60 train 7.999905 (lr=1.7495e-04) (hash(x)=23874620) +61 train 7.858231 (lr=1.7494e-04) (hash(x)=22402617) +62 train 7.975471 (lr=1.7494e-04) (hash(x)=23600822) +63 train 7.855655 (lr=1.7494e-04) (hash(x)=26582391) +64 train 7.838850 (lr=1.7494e-04) (hash(x)=23225283) +65 train 8.184184 (lr=1.7494e-04) (hash(x)=26075451) +66 train 7.862728 (lr=1.7493e-04) (hash(x)=24723419) +67 train 8.026367 (lr=1.7493e-04) (hash(x)=27279806) +68 train 7.816944 (lr=1.7493e-04) (hash(x)=25870391) +69 train 8.036019 (lr=1.7493e-04) (hash(x)=26188136) +70 train 8.153365 (lr=1.7493e-04) (hash(x)=30373443) +71 train 8.077964 (lr=1.7492e-04) (hash(x)=26472336) +72 train 7.843703 (lr=1.7492e-04) (hash(x)=26651572) +73 train 8.008693 (lr=1.7492e-04) (hash(x)=26376212) +74 train 7.971633 (lr=1.7492e-04) (hash(x)=26733350) +75 train 8.120076 (lr=1.7491e-04) (hash(x)=28301589) +76 train 8.008845 (lr=1.7491e-04) (hash(x)=27599559) +77 train 8.004535 (lr=1.7491e-04) (hash(x)=28035221) +78 train 7.980419 (lr=1.7491e-04) (hash(x)=25016783) +79 train 8.041086 (lr=1.7491e-04) (hash(x)=27654289) +80 train 7.866472 (lr=1.7490e-04) (hash(x)=24597558) +81 train 7.654054 (lr=1.7490e-04) (hash(x)=21560904) +82 train 7.642229 (lr=1.7490e-04) (hash(x)=21983837) +83 train 7.817575 (lr=1.7490e-04) (hash(x)=24995715) +84 train 8.136889 (lr=1.7489e-04) (hash(x)=29876413) +85 train 7.749779 (lr=1.7489e-04) (hash(x)=23792508) +86 train 7.724863 (lr=1.7489e-04) (hash(x)=25509120) +87 train 7.952866 (lr=1.7489e-04) (hash(x)=26559876) +88 train 7.886490 (lr=1.7488e-04) (hash(x)=23569647) +89 train 7.891141 (lr=1.7488e-04) (hash(x)=25758852) +90 train 7.734390 (lr=1.7488e-04) (hash(x)=25706298) +91 train 7.921411 (lr=1.7487e-04) (hash(x)=28364895) +92 train 7.752278 (lr=1.7487e-04) (hash(x)=25304663) +93 train 7.819901 (lr=1.7487e-04) (hash(x)=25269299) +94 train 7.963538 (lr=1.7487e-04) (hash(x)=25870566) +95 train 7.570764 (lr=1.7486e-04) (hash(x)=21770329) +96 train 8.050952 (lr=1.7486e-04) (hash(x)=27595900) +97 train 7.960698 (lr=1.7486e-04) (hash(x)=24785397) +98 train 7.655525 (lr=1.7485e-04) (hash(x)=21521480) +99 train 7.778947 (lr=1.7485e-04) (hash(x)=24628606) +100 val loss 7.8260 +100 val perplexity 2504.9033 +100 train 7.892837 (lr=1.7485e-04) (hash(x)=24670150) +101 train 7.801581 (lr=1.7484e-04) (hash(x)=23181910) +102 train 7.761011 (lr=1.7484e-04) (hash(x)=22714991) +103 train 7.721115 (lr=1.7484e-04) (hash(x)=22723459) +104 train 7.684401 (lr=1.7484e-04) (hash(x)=21524316) +105 train 7.868268 (lr=1.7483e-04) (hash(x)=25506632) +106 train 7.580844 (lr=1.7483e-04) (hash(x)=21675672) +107 train 7.681417 (lr=1.7483e-04) (hash(x)=22897919) +108 train 7.701056 (lr=1.7482e-04) (hash(x)=23321631) +109 train 7.881905 (lr=1.7482e-04) (hash(x)=26546719) +110 train 8.914940 (lr=1.7482e-04) (hash(x)=31962348) +111 train 8.203730 (lr=1.7481e-04) (hash(x)=30338342) +112 train 7.790801 (lr=1.7481e-04) (hash(x)=23724471) +113 train 7.966930 (lr=1.7481e-04) (hash(x)=29175888) +114 train 7.980336 (lr=1.7480e-04) (hash(x)=23256716) +115 train 8.052502 (lr=1.7480e-04) (hash(x)=27063280) +116 train 8.063972 (lr=1.7479e-04) (hash(x)=31057659) +117 train 8.254948 (lr=1.7479e-04) (hash(x)=32915097) +118 train 8.094237 (lr=1.7479e-04) (hash(x)=28842717) +119 train 7.785554 (lr=1.7478e-04) (hash(x)=25678059) +120 train 7.621109 (lr=1.7478e-04) (hash(x)=21593510) +121 train 7.572883 (lr=1.7478e-04) (hash(x)=20083773) +122 train 7.733767 (lr=1.7477e-04) (hash(x)=23002820) +123 train 7.576381 (lr=1.7477e-04) (hash(x)=21853028) +124 train 7.840051 (lr=1.7476e-04) (hash(x)=26985625) +125 train 7.577403 (lr=1.7476e-04) (hash(x)=21808483) +126 train 7.962700 (lr=1.7476e-04) (hash(x)=28873251) +127 train 7.853195 (lr=1.7475e-04) (hash(x)=26109335) +128 train 8.023256 (lr=1.7475e-04) (hash(x)=26334674) +129 train 7.889067 (lr=1.7475e-04) (hash(x)=24916754) +130 train 7.821057 (lr=1.7474e-04) (hash(x)=25449624) +131 train 7.902266 (lr=1.7474e-04) (hash(x)=25334848) +132 train 8.162299 (lr=1.7473e-04) (hash(x)=27484863) +133 train 7.754035 (lr=1.7473e-04) (hash(x)=24917705) +134 train 7.734760 (lr=1.7473e-04) (hash(x)=25143449) +135 train 7.756658 (lr=1.7472e-04) (hash(x)=25044885) +136 train 7.969326 (lr=1.7472e-04) (hash(x)=27821028) +137 train 7.957092 (lr=1.7471e-04) (hash(x)=28747022) +138 train 7.907323 (lr=1.7471e-04) (hash(x)=27182888) +139 train 7.693546 (lr=1.7470e-04) (hash(x)=23678349) +140 train 7.811037 (lr=1.7470e-04) (hash(x)=23593235) +141 train 8.101305 (lr=1.7470e-04) (hash(x)=28529813) +142 train 8.435539 (lr=1.7469e-04) (hash(x)=32074661) +143 train 8.016937 (lr=1.7469e-04) (hash(x)=28870690) +144 train 7.946822 (lr=1.7468e-04) (hash(x)=27307705) +145 train 7.779462 (lr=1.7468e-04) (hash(x)=25044834) +146 train 7.839299 (lr=1.7467e-04) (hash(x)=23712023) +147 train 8.359694 (lr=1.7467e-04) (hash(x)=32982615) +148 train 8.132773 (lr=1.7466e-04) (hash(x)=30113660) +149 train 7.599622 (lr=1.7466e-04) (hash(x)=20970960) +150 val loss 7.8100 +150 val perplexity 2465.1433 +150 train 7.780923 (lr=1.7466e-04) (hash(x)=23132684) +151 train 9.543010 (lr=1.7465e-04) (hash(x)=35279941) +152 train 8.695432 (lr=1.7465e-04) (hash(x)=31227444) +153 train 7.770088 (lr=1.7464e-04) (hash(x)=25529472) +154 train 7.865277 (lr=1.7464e-04) (hash(x)=24350409) +155 train 8.130317 (lr=1.7463e-04) (hash(x)=26400041) +156 train 7.830638 (lr=1.7463e-04) (hash(x)=25262621) +157 train 7.860763 (lr=1.7462e-04) (hash(x)=24656138) +158 train 8.058945 (lr=1.7462e-04) (hash(x)=26803414) +159 train 7.948021 (lr=1.7461e-04) (hash(x)=25015923) +160 train 7.645093 (lr=1.7461e-04) (hash(x)=23581172) +161 train 7.785440 (lr=1.7460e-04) (hash(x)=22924885) +162 train 7.721250 (lr=1.7460e-04) (hash(x)=23414296) +163 train 7.900876 (lr=1.7459e-04) (hash(x)=24853586) +164 train 7.955055 (lr=1.7459e-04) (hash(x)=25000130) +165 train 7.851189 (lr=1.7458e-04) (hash(x)=27004780) +166 train 7.854474 (lr=1.7458e-04) (hash(x)=26148573) +167 train 7.824045 (lr=1.7457e-04) (hash(x)=26740855) +168 train 7.504669 (lr=1.7457e-04) (hash(x)=20965419) +169 train 7.739319 (lr=1.7456e-04) (hash(x)=23950114) +170 train 7.667787 (lr=1.7456e-04) (hash(x)=24951982) +171 train 7.790421 (lr=1.7455e-04) (hash(x)=24584116) +172 train 7.731378 (lr=1.7455e-04) (hash(x)=24378759) +173 train 7.753147 (lr=1.7454e-04) (hash(x)=25718516) +174 train 7.894591 (lr=1.7454e-04) (hash(x)=28424396) +175 train 7.688443 (lr=1.7453e-04) (hash(x)=22262151) +176 train 7.940148 (lr=1.7452e-04) (hash(x)=26438412) +177 train 7.720050 (lr=1.7452e-04) (hash(x)=23025303) +178 train 7.774031 (lr=1.7451e-04) (hash(x)=24190770) +179 train 7.941785 (lr=1.7451e-04) (hash(x)=26627860) +180 train 7.730278 (lr=1.7450e-04) (hash(x)=23663439) +181 train 7.610779 (lr=1.7450e-04) (hash(x)=23700532) +182 train 7.649209 (lr=1.7449e-04) (hash(x)=23075676) +183 train 7.879300 (lr=1.7449e-04) (hash(x)=26621834) +184 train 7.942420 (lr=1.7448e-04) (hash(x)=29426269) +185 train 7.578841 (lr=1.7447e-04) (hash(x)=21821465) +186 train 7.779805 (lr=1.7447e-04) (hash(x)=26506130) +187 train 8.067710 (lr=1.7446e-04) (hash(x)=26930630) +188 train 7.572441 (lr=1.7446e-04) (hash(x)=22993793) +189 train 7.438159 (lr=1.7445e-04) (hash(x)=19557946) +190 train 7.773891 (lr=1.7445e-04) (hash(x)=23572891) +191 train 7.598814 (lr=1.7444e-04) (hash(x)=23234741) +192 train 7.707263 (lr=1.7443e-04) (hash(x)=25547951) +193 train 7.799011 (lr=1.7443e-04) (hash(x)=26713563) +194 train 7.798592 (lr=1.7442e-04) (hash(x)=25913622) +195 train 8.066778 (lr=1.7442e-04) (hash(x)=28102443) +196 train 7.754258 (lr=1.7441e-04) (hash(x)=23093351) +197 train 8.493168 (lr=1.7440e-04) (hash(x)=31689122) +198 train 8.336148 (lr=1.7440e-04) (hash(x)=32252517) +199 train 7.908590 (lr=1.7439e-04) (hash(x)=25470563) +200 val loss 7.8466 +200 val perplexity 2556.9844 +200 train 7.930885 (lr=1.7438e-04) (hash(x)=25597614) +201 train 7.976495 (lr=1.7438e-04) (hash(x)=23757479) +202 train 7.792275 (lr=1.7437e-04) (hash(x)=25140048) +203 train 7.979885 (lr=1.7437e-04) (hash(x)=28282861) +204 train 7.768813 (lr=1.7436e-04) (hash(x)=24754885) +205 train 7.977855 (lr=1.7435e-04) (hash(x)=26731964) +206 train 8.048716 (lr=1.7435e-04) (hash(x)=26660561) +207 train 7.623612 (lr=1.7434e-04) (hash(x)=21799102) +208 train 7.870569 (lr=1.7433e-04) (hash(x)=27025986) +209 train 7.780632 (lr=1.7433e-04) (hash(x)=24672077) +210 train 7.761182 (lr=1.7432e-04) (hash(x)=25322984) +211 train 7.597787 (lr=1.7432e-04) (hash(x)=23471769) +212 train 7.430183 (lr=1.7431e-04) (hash(x)=20766491) +213 train 7.928021 (lr=1.7430e-04) (hash(x)=24058931) +214 train 7.649218 (lr=1.7430e-04) (hash(x)=23872843) +215 train 7.702681 (lr=1.7429e-04) (hash(x)=23275479) +216 train 7.827011 (lr=1.7428e-04) (hash(x)=24914695) +217 train 7.682507 (lr=1.7428e-04) (hash(x)=24364396) +218 train 7.953691 (lr=1.7427e-04) (hash(x)=27986474) +219 train 7.854942 (lr=1.7426e-04) (hash(x)=24473581) +220 train 7.762842 (lr=1.7426e-04) (hash(x)=22974689) +221 train 7.824081 (lr=1.7425e-04) (hash(x)=23774644) +222 train 7.783777 (lr=1.7424e-04) (hash(x)=23245327) +223 train 7.618785 (lr=1.7423e-04) (hash(x)=22091862) +224 train 7.691323 (lr=1.7423e-04) (hash(x)=24362839) +225 train 7.794711 (lr=1.7422e-04) (hash(x)=25482303) +226 train 7.887190 (lr=1.7421e-04) (hash(x)=24911853) +227 train 7.861350 (lr=1.7421e-04) (hash(x)=26018202) +228 train 7.708853 (lr=1.7420e-04) (hash(x)=26124495) +229 train 7.793570 (lr=1.7419e-04) (hash(x)=24560096) +230 train 7.777099 (lr=1.7419e-04) (hash(x)=24695331) +231 train 7.526441 (lr=1.7418e-04) (hash(x)=17430373) +232 train 7.560233 (lr=1.7417e-04) (hash(x)=21813345) +233 train 7.216257 (lr=1.7416e-04) (hash(x)=20098681) +234 train 7.542993 (lr=1.7416e-04) (hash(x)=25095928) +235 train 7.614746 (lr=1.7415e-04) (hash(x)=24078083) +236 train 7.641324 (lr=1.7414e-04) (hash(x)=22901505) +237 train 7.852441 (lr=1.7414e-04) (hash(x)=26595592) +238 train 7.743184 (lr=1.7413e-04) (hash(x)=27663196) +239 train 7.558328 (lr=1.7412e-04) (hash(x)=22954861) +240 train 8.026108 (lr=1.7411e-04) (hash(x)=30159234) +241 train 7.912441 (lr=1.7411e-04) (hash(x)=29294271) +242 train 7.866205 (lr=1.7410e-04) (hash(x)=23728322) +243 train 7.908715 (lr=1.7409e-04) (hash(x)=28695016) +244 train 8.039566 (lr=1.7408e-04) (hash(x)=26702728) +245 train 7.837396 (lr=1.7408e-04) (hash(x)=27100115) +246 train 7.722054 (lr=1.7407e-04) (hash(x)=25082752) +247 train 8.059526 (lr=1.7406e-04) (hash(x)=26671799) +248 train 7.788976 (lr=1.7405e-04) (hash(x)=23718946) +249 train 8.024436 (lr=1.7405e-04) (hash(x)=28137394) +250 val loss 7.7640 +250 val perplexity 2354.3186 +250 train 8.047542 (lr=1.7404e-04) (hash(x)=23893495) +251 train 7.831608 (lr=1.7403e-04) (hash(x)=23166092) +252 train 7.763182 (lr=1.7402e-04) (hash(x)=25907665) +253 train 7.754422 (lr=1.7401e-04) (hash(x)=25885986) +254 train 7.809732 (lr=1.7401e-04) (hash(x)=25262712) +255 train 7.778827 (lr=1.7400e-04) (hash(x)=26924723) +256 train 7.991334 (lr=1.7399e-04) (hash(x)=28744736) +257 train 7.736571 (lr=1.7398e-04) (hash(x)=26140590) +258 train 7.921256 (lr=1.7398e-04) (hash(x)=25780449) +259 train 7.760522 (lr=1.7397e-04) (hash(x)=25138659) +260 train 8.027438 (lr=1.7396e-04) (hash(x)=27244046) +261 train 7.883366 (lr=1.7395e-04) (hash(x)=27224685) +262 train 8.165726 (lr=1.7394e-04) (hash(x)=28274477) +263 train 7.643592 (lr=1.7393e-04) (hash(x)=23557495) +264 train 7.773327 (lr=1.7393e-04) (hash(x)=24680596) +265 train 7.776016 (lr=1.7392e-04) (hash(x)=23928957) +266 train 7.708124 (lr=1.7391e-04) (hash(x)=23761390) +267 train 7.698740 (lr=1.7390e-04) (hash(x)=25288123) +268 train 7.933923 (lr=1.7389e-04) (hash(x)=28705502) +269 train 7.561710 (lr=1.7389e-04) (hash(x)=23246294) +270 train 7.642728 (lr=1.7388e-04) (hash(x)=28639079) +271 train 7.558940 (lr=1.7387e-04) (hash(x)=27804380) +272 train 7.731531 (lr=1.7386e-04) (hash(x)=24172235) +273 train 7.808888 (lr=1.7385e-04) (hash(x)=23089140) +274 train 8.009119 (lr=1.7384e-04) (hash(x)=27163701) +275 train 8.113873 (lr=1.7384e-04) (hash(x)=26993263) +276 train 7.816741 (lr=1.7383e-04) (hash(x)=28224233) +277 train 8.113441 (lr=1.7382e-04) (hash(x)=27397203) +278 train 8.029041 (lr=1.7381e-04) (hash(x)=27923882) +279 train 7.863509 (lr=1.7380e-04) (hash(x)=26654908) +280 train 7.810573 (lr=1.7379e-04) (hash(x)=24213147) +281 train 7.555615 (lr=1.7378e-04) (hash(x)=21965022) +282 train 7.718161 (lr=1.7378e-04) (hash(x)=25465685) +283 train 7.920265 (lr=1.7377e-04) (hash(x)=27347722) +284 train 7.924663 (lr=1.7376e-04) (hash(x)=26732050) +285 train 8.094680 (lr=1.7375e-04) (hash(x)=28314127) +286 train 7.617670 (lr=1.7374e-04) (hash(x)=21471186) +287 train 7.582524 (lr=1.7373e-04) (hash(x)=23627518) +288 train 7.591252 (lr=1.7372e-04) (hash(x)=20870353) +289 train 7.685608 (lr=1.7371e-04) (hash(x)=25024764) +290 train 7.491338 (lr=1.7370e-04) (hash(x)=20683822) +291 train 7.784687 (lr=1.7370e-04) (hash(x)=21768671) +292 train 7.832518 (lr=1.7369e-04) (hash(x)=25557309) +293 train 7.992012 (lr=1.7368e-04) (hash(x)=25076667) +294 train 7.621557 (lr=1.7367e-04) (hash(x)=23765822) +295 train 7.577800 (lr=1.7366e-04) (hash(x)=21889990) +296 train 7.802870 (lr=1.7365e-04) (hash(x)=26339893) +297 train 7.533460 (lr=1.7364e-04) (hash(x)=20932794) +298 train 7.638429 (lr=1.7363e-04) (hash(x)=21750070) +299 train 7.803270 (lr=1.7362e-04) (hash(x)=23665838) +300 val loss 7.7424 +300 val perplexity 2304.0210 +300 train 8.589043 (lr=1.7361e-04) (hash(x)=32888061) +301 train 8.339806 (lr=1.7360e-04) (hash(x)=30223582) +302 train 8.059770 (lr=1.7360e-04) (hash(x)=26908418) +303 train 7.448003 (lr=1.7359e-04) (hash(x)=22528001) +304 train 7.942928 (lr=1.7358e-04) (hash(x)=27452187) +305 train 7.764313 (lr=1.7357e-04) (hash(x)=25181641) +306 train 7.841452 (lr=1.7356e-04) (hash(x)=25546593) +307 train 7.846060 (lr=1.7355e-04) (hash(x)=22487328) +308 train 7.984592 (lr=1.7354e-04) (hash(x)=27804274) +309 train 8.029194 (lr=1.7353e-04) (hash(x)=26544630) +310 train 8.182826 (lr=1.7352e-04) (hash(x)=27738934) +311 train 7.948241 (lr=1.7351e-04) (hash(x)=29248942) +312 train 7.696936 (lr=1.7350e-04) (hash(x)=25103452) +313 train 7.945674 (lr=1.7349e-04) (hash(x)=25052066) +314 train 7.789101 (lr=1.7348e-04) (hash(x)=24481302) +315 train 7.736866 (lr=1.7347e-04) (hash(x)=23543273) +316 train 7.740406 (lr=1.7346e-04) (hash(x)=25608244) +317 train 7.913547 (lr=1.7345e-04) (hash(x)=27451288) +318 train 7.600976 (lr=1.7344e-04) (hash(x)=22806491) +319 train 7.768054 (lr=1.7343e-04) (hash(x)=25533417) +320 train 7.741526 (lr=1.7342e-04) (hash(x)=24557997) +321 train 7.790613 (lr=1.7341e-04) (hash(x)=24432899) +322 train 8.030486 (lr=1.7340e-04) (hash(x)=27583287) +323 train 7.890707 (lr=1.7339e-04) (hash(x)=25552036) +324 train 7.652790 (lr=1.7338e-04) (hash(x)=24201868) +325 train 7.994648 (lr=1.7337e-04) (hash(x)=28149782) +326 train 7.794409 (lr=1.7336e-04) (hash(x)=25529698) +327 train 7.497393 (lr=1.7335e-04) (hash(x)=20612533) +328 train 7.514148 (lr=1.7334e-04) (hash(x)=20699000) +329 train 7.449034 (lr=1.7333e-04) (hash(x)=19774173) +330 train 7.480042 (lr=1.7332e-04) (hash(x)=21681646) +331 train 7.353205 (lr=1.7331e-04) (hash(x)=20216795) +332 train 8.061246 (lr=1.7330e-04) (hash(x)=27697998) +333 train 7.832365 (lr=1.7329e-04) (hash(x)=25896435) +334 train 7.701253 (lr=1.7328e-04) (hash(x)=21585310) +335 train 7.750276 (lr=1.7327e-04) (hash(x)=24677740) +336 train 7.564297 (lr=1.7326e-04) (hash(x)=22027900) +337 train 7.593524 (lr=1.7325e-04) (hash(x)=21835643) +338 train 7.495752 (lr=1.7324e-04) (hash(x)=20558462) +339 train 7.423111 (lr=1.7323e-04) (hash(x)=16722715) +340 train 7.601300 (lr=1.7322e-04) (hash(x)=20972655) +341 train 8.014445 (lr=1.7321e-04) (hash(x)=26303975) +342 train 7.791023 (lr=1.7320e-04) (hash(x)=22938170) +343 train 7.838764 (lr=1.7319e-04) (hash(x)=25347203) +344 train 7.800667 (lr=1.7318e-04) (hash(x)=27398686) +345 train 7.765141 (lr=1.7317e-04) (hash(x)=25973417) +346 train 7.781550 (lr=1.7316e-04) (hash(x)=26918389) +347 train 7.707930 (lr=1.7315e-04) (hash(x)=24272489) +348 train 7.745309 (lr=1.7313e-04) (hash(x)=25593714) +349 train 7.831882 (lr=1.7312e-04) (hash(x)=29260846) +350 val loss 7.7333 +350 val perplexity 2283.1758 +350 train 7.909003 (lr=1.7311e-04) (hash(x)=27951602) +351 train 7.998094 (lr=1.7310e-04) (hash(x)=28922363) +352 train 7.885281 (lr=1.7309e-04) (hash(x)=27210734) +353 train 7.914483 (lr=1.7308e-04) (hash(x)=26322572) +354 train 7.847205 (lr=1.7307e-04) (hash(x)=27084665) +355 train 7.761766 (lr=1.7306e-04) (hash(x)=25510798) +356 train 7.822083 (lr=1.7305e-04) (hash(x)=24970921) +357 train 7.855182 (lr=1.7304e-04) (hash(x)=24138948) +358 train 7.749948 (lr=1.7303e-04) (hash(x)=24790211) +359 train 7.790964 (lr=1.7302e-04) (hash(x)=25631397) +360 train 7.627702 (lr=1.7300e-04) (hash(x)=23226625) +361 train 7.695503 (lr=1.7299e-04) (hash(x)=24001903) +362 train 7.697701 (lr=1.7298e-04) (hash(x)=24587948) +363 train 7.422899 (lr=1.7297e-04) (hash(x)=21333676) +364 train 7.282773 (lr=1.7296e-04) (hash(x)=23673779) +365 train 8.706145 (lr=1.7295e-04) (hash(x)=30770484) +366 train 7.834387 (lr=1.7294e-04) (hash(x)=26564899) +367 train 7.833821 (lr=1.7293e-04) (hash(x)=26237983) +368 train 7.563832 (lr=1.7291e-04) (hash(x)=23764356) +369 train 7.927665 (lr=1.7290e-04) (hash(x)=26205744) +370 train 7.578205 (lr=1.7289e-04) (hash(x)=19208770) +371 train 7.863225 (lr=1.7288e-04) (hash(x)=25976502) +372 train 7.670959 (lr=1.7287e-04) (hash(x)=23983933) +373 train 7.669758 (lr=1.7286e-04) (hash(x)=24080636) +374 train 7.769682 (lr=1.7285e-04) (hash(x)=24404047) +375 train 7.715887 (lr=1.7283e-04) (hash(x)=24742645) +376 train 7.765916 (lr=1.7282e-04) (hash(x)=24159600) +377 train 8.025882 (lr=1.7281e-04) (hash(x)=28677257) +378 train 7.765920 (lr=1.7280e-04) (hash(x)=25604111) +379 train 7.732085 (lr=1.7279e-04) (hash(x)=27086333) +380 train 7.656908 (lr=1.7278e-04) (hash(x)=25188207) +381 train 7.871381 (lr=1.7277e-04) (hash(x)=27855233) +382 train 7.501935 (lr=1.7275e-04) (hash(x)=19470039) +383 train 7.790317 (lr=1.7274e-04) (hash(x)=26157660) +384 train 7.691547 (lr=1.7273e-04) (hash(x)=25291570) +385 train 7.661691 (lr=1.7272e-04) (hash(x)=25046062) +386 train 7.982584 (lr=1.7271e-04) (hash(x)=27020337) +387 train 7.605611 (lr=1.7269e-04) (hash(x)=23616370) +388 train 7.303632 (lr=1.7268e-04) (hash(x)=19113218) +389 train 7.642372 (lr=1.7267e-04) (hash(x)=24302232) +390 train 7.665117 (lr=1.7266e-04) (hash(x)=22188949) +391 train 7.486634 (lr=1.7265e-04) (hash(x)=22582169) +392 train 7.663542 (lr=1.7263e-04) (hash(x)=24700570) +393 train 7.572067 (lr=1.7262e-04) (hash(x)=22773833) +394 train 7.450897 (lr=1.7261e-04) (hash(x)=21875928) +395 train 7.748446 (lr=1.7260e-04) (hash(x)=26233189) +396 train 7.580586 (lr=1.7259e-04) (hash(x)=24321467) +397 train 7.835193 (lr=1.7257e-04) (hash(x)=26431507) +398 train 7.903639 (lr=1.7256e-04) (hash(x)=28690877) +399 train 7.844455 (lr=1.7255e-04) (hash(x)=26431960) +400 val loss 7.7317 +400 val perplexity 2279.4717 +400 train 7.659444 (lr=1.7254e-04) (hash(x)=24580300) +401 train 7.702548 (lr=1.7252e-04) (hash(x)=25112360) +402 train 7.795244 (lr=1.7251e-04) (hash(x)=27597243) +403 train 8.238673 (lr=1.7250e-04) (hash(x)=30707498) +404 train 7.880013 (lr=1.7249e-04) (hash(x)=28485465) +405 train 7.542764 (lr=1.7248e-04) (hash(x)=22586447) +406 train 7.692449 (lr=1.7246e-04) (hash(x)=23175270) +407 train 7.763775 (lr=1.7245e-04) (hash(x)=25716176) +408 train 7.877638 (lr=1.7244e-04) (hash(x)=26861373) +409 train 7.926186 (lr=1.7243e-04) (hash(x)=25118971) +410 train 7.478725 (lr=1.7241e-04) (hash(x)=19829066) +411 train 7.616515 (lr=1.7240e-04) (hash(x)=26256420) +412 train 7.859428 (lr=1.7239e-04) (hash(x)=27796153) +413 train 7.615915 (lr=1.7238e-04) (hash(x)=22633318) +414 train 7.634809 (lr=1.7236e-04) (hash(x)=22589383) +415 train 8.032348 (lr=1.7235e-04) (hash(x)=28019788) +416 train 7.970695 (lr=1.7234e-04) (hash(x)=28970440) +417 train 7.657157 (lr=1.7232e-04) (hash(x)=27396089) +418 train 7.678916 (lr=1.7231e-04) (hash(x)=21183513) +419 train 7.684370 (lr=1.7230e-04) (hash(x)=23510110) +420 train 7.893769 (lr=1.7229e-04) (hash(x)=28833467) +421 train 7.763696 (lr=1.7227e-04) (hash(x)=23646926) +422 train 7.714902 (lr=1.7226e-04) (hash(x)=24697272) +423 train 7.481171 (lr=1.7225e-04) (hash(x)=20382963) +424 train 7.518236 (lr=1.7223e-04) (hash(x)=23467595) +425 train 7.675297 (lr=1.7222e-04) (hash(x)=24304768) +426 train 7.567133 (lr=1.7221e-04) (hash(x)=21392328) +427 train 7.608932 (lr=1.7219e-04) (hash(x)=25339466) +428 train 7.576016 (lr=1.7218e-04) (hash(x)=22092542) +429 train 7.677460 (lr=1.7217e-04) (hash(x)=22088696) +430 train 7.565517 (lr=1.7216e-04) (hash(x)=22184471) +431 train 7.679065 (lr=1.7214e-04) (hash(x)=24489647) +432 train 7.714014 (lr=1.7213e-04) (hash(x)=26794132) +433 train 7.508265 (lr=1.7212e-04) (hash(x)=22940357) +434 train 7.665579 (lr=1.7210e-04) (hash(x)=23719522) +435 train 7.550014 (lr=1.7209e-04) (hash(x)=22927699) +436 train 7.700386 (lr=1.7208e-04) (hash(x)=26068576) +437 train 7.834134 (lr=1.7206e-04) (hash(x)=27631132) +438 train 7.738332 (lr=1.7205e-04) (hash(x)=26739991) +439 train 7.795399 (lr=1.7204e-04) (hash(x)=25128502) +440 train 7.840559 (lr=1.7202e-04) (hash(x)=25657260) +441 train 7.558877 (lr=1.7201e-04) (hash(x)=23576982) +442 train 7.827602 (lr=1.7199e-04) (hash(x)=27117886) +443 train 7.804658 (lr=1.7198e-04) (hash(x)=25808969) +444 train 7.720032 (lr=1.7197e-04) (hash(x)=24738238) +445 train 7.702527 (lr=1.7195e-04) (hash(x)=23429962) +446 train 7.836176 (lr=1.7194e-04) (hash(x)=25075165) +447 train 7.699222 (lr=1.7193e-04) (hash(x)=25231390) +448 train 7.487280 (lr=1.7191e-04) (hash(x)=22055054) +449 train 7.631782 (lr=1.7190e-04) (hash(x)=25395441) +450 val loss 7.6842 +450 val perplexity 2173.8025 +450 train 7.735890 (lr=1.7189e-04) (hash(x)=25863209) +451 train 7.469426 (lr=1.7187e-04) (hash(x)=21154388) +452 train 7.455403 (lr=1.7186e-04) (hash(x)=21600876) +453 train 7.553179 (lr=1.7184e-04) (hash(x)=24278611) +454 train 7.389606 (lr=1.7183e-04) (hash(x)=23221720) +455 train 7.626018 (lr=1.7182e-04) (hash(x)=22708977) +456 train 8.220588 (lr=1.7180e-04) (hash(x)=23637758) +457 train 7.920697 (lr=1.7179e-04) (hash(x)=28228490) +458 train 7.934947 (lr=1.7177e-04) (hash(x)=28638071) +459 train 7.797401 (lr=1.7176e-04) (hash(x)=27258353) +460 train 7.840794 (lr=1.7175e-04) (hash(x)=26604728) +461 train 7.753331 (lr=1.7173e-04) (hash(x)=23252199) +462 train 7.788560 (lr=1.7172e-04) (hash(x)=26441427) +463 train 7.544712 (lr=1.7170e-04) (hash(x)=24364920) +464 train 7.666885 (lr=1.7169e-04) (hash(x)=25623792) +465 train 7.549783 (lr=1.7168e-04) (hash(x)=23283905) +466 train 7.954480 (lr=1.7166e-04) (hash(x)=26025267) +467 train 7.739128 (lr=1.7165e-04) (hash(x)=27243972) +468 train 8.098508 (lr=1.7163e-04) (hash(x)=30449945) +469 train 7.827196 (lr=1.7162e-04) (hash(x)=28113043) +470 train 7.626039 (lr=1.7160e-04) (hash(x)=25182521) +471 train 7.702005 (lr=1.7159e-04) (hash(x)=24932925) +472 train 7.532129 (lr=1.7158e-04) (hash(x)=20353098) +473 train 7.394516 (lr=1.7156e-04) (hash(x)=19001259) +474 train 7.927387 (lr=1.7155e-04) (hash(x)=27585685) +475 train 7.620605 (lr=1.7153e-04) (hash(x)=26371091) +476 train 7.502351 (lr=1.7152e-04) (hash(x)=24891798) +477 train 7.581167 (lr=1.7150e-04) (hash(x)=24258817) +478 train 7.655509 (lr=1.7149e-04) (hash(x)=24330263) +479 train 7.708557 (lr=1.7147e-04) (hash(x)=26913684) +480 train 7.680834 (lr=1.7146e-04) (hash(x)=26338455) +481 train 7.960994 (lr=1.7144e-04) (hash(x)=27753043) +482 train 7.658624 (lr=1.7143e-04) (hash(x)=26123289) +483 train 7.772823 (lr=1.7141e-04) (hash(x)=29239611) +484 train 7.693556 (lr=1.7140e-04) (hash(x)=26553003) +485 train 7.663454 (lr=1.7139e-04) (hash(x)=22984557) +486 train 7.200506 (lr=1.7137e-04) (hash(x)=16947491) +487 train 7.227184 (lr=1.7136e-04) (hash(x)=18017792) +488 train 7.355157 (lr=1.7134e-04) (hash(x)=19918608) +489 train 7.819198 (lr=1.7133e-04) (hash(x)=23374526) +490 train 7.696960 (lr=1.7131e-04) (hash(x)=25009505) +491 train 7.658465 (lr=1.7130e-04) (hash(x)=27574089) +492 train 7.816208 (lr=1.7128e-04) (hash(x)=24122664) +493 train 7.667684 (lr=1.7127e-04) (hash(x)=26154906) +494 train 7.610103 (lr=1.7125e-04) (hash(x)=25192767) +495 train 7.733609 (lr=1.7124e-04) (hash(x)=28613882) +496 train 7.591617 (lr=1.7122e-04) (hash(x)=23547219) +497 train 7.645131 (lr=1.7121e-04) (hash(x)=25272182) +498 train 7.528992 (lr=1.7119e-04) (hash(x)=24992761) +499 train 7.789845 (lr=1.7117e-04) (hash(x)=26981914) +500 val loss 7.7061 +500 val perplexity 2221.8589 +500 train 7.649126 (lr=1.7116e-04) (hash(x)=22051933) +501 train 7.769662 (lr=1.7114e-04) (hash(x)=24232348) +502 train 7.742719 (lr=1.7113e-04) (hash(x)=23158331) +503 train 7.561477 (lr=1.7111e-04) (hash(x)=22652243) +504 train 7.584028 (lr=1.7110e-04) (hash(x)=23805602) +505 train 7.854129 (lr=1.7108e-04) (hash(x)=25411991) +506 train 7.014644 (lr=1.7107e-04) (hash(x)=18827215) +507 train 6.748708 (lr=1.7105e-04) (hash(x)=15446025) +508 train 7.170787 (lr=1.7104e-04) (hash(x)=20516263) +509 train 7.729671 (lr=1.7102e-04) (hash(x)=27846176) +510 train 7.440770 (lr=1.7101e-04) (hash(x)=23342449) +511 train 7.699422 (lr=1.7099e-04) (hash(x)=27194521) +512 train 7.503419 (lr=1.7097e-04) (hash(x)=23008284) +513 train 7.985180 (lr=1.7096e-04) (hash(x)=29430001) +514 train 7.306821 (lr=1.7094e-04) (hash(x)=22579319) +515 train 7.389650 (lr=1.7093e-04) (hash(x)=25264518) +516 train 7.703105 (lr=1.7091e-04) (hash(x)=25359075) +517 train 7.657325 (lr=1.7090e-04) (hash(x)=25568956) +518 train 7.927648 (lr=1.7088e-04) (hash(x)=32004108) +519 train 7.561370 (lr=1.7086e-04) (hash(x)=24936836) +520 train 7.726158 (lr=1.7085e-04) (hash(x)=27263338) +521 train 7.782262 (lr=1.7083e-04) (hash(x)=27452099) +522 train 7.671266 (lr=1.7082e-04) (hash(x)=25965406) +523 train 7.836361 (lr=1.7080e-04) (hash(x)=28197282) +524 train 7.591905 (lr=1.7078e-04) (hash(x)=22466209) +525 train 7.654347 (lr=1.7077e-04) (hash(x)=22931889) +526 train 7.765845 (lr=1.7075e-04) (hash(x)=26903920) +527 train 7.629089 (lr=1.7074e-04) (hash(x)=24765578) +528 train 7.733003 (lr=1.7072e-04) (hash(x)=27811359) +529 train 7.530898 (lr=1.7070e-04) (hash(x)=25078649) +530 train 7.696617 (lr=1.7069e-04) (hash(x)=25572416) +531 train 7.806718 (lr=1.7067e-04) (hash(x)=27448185) +532 train 7.864983 (lr=1.7066e-04) (hash(x)=25923719) +533 train 7.667541 (lr=1.7064e-04) (hash(x)=24804856) +534 train 7.702312 (lr=1.7062e-04) (hash(x)=23207829) +535 train 7.612689 (lr=1.7061e-04) (hash(x)=23107416) +536 train 7.484493 (lr=1.7059e-04) (hash(x)=26739531) +537 train 7.528342 (lr=1.7057e-04) (hash(x)=24960796) +538 train 7.622751 (lr=1.7056e-04) (hash(x)=24667802) +539 train 7.733106 (lr=1.7054e-04) (hash(x)=26755138) +540 train 7.643434 (lr=1.7053e-04) (hash(x)=25537132) +541 train 7.574795 (lr=1.7051e-04) (hash(x)=24542526) +542 train 7.371025 (lr=1.7049e-04) (hash(x)=21296355) +543 train 7.911609 (lr=1.7048e-04) (hash(x)=29314255) +544 train 7.640558 (lr=1.7046e-04) (hash(x)=26001799) +545 train 7.691895 (lr=1.7044e-04) (hash(x)=27347755) +546 train 7.629002 (lr=1.7043e-04) (hash(x)=25107798) +547 train 7.424648 (lr=1.7041e-04) (hash(x)=22112669) +548 train 7.462233 (lr=1.7039e-04) (hash(x)=21897967) +549 train 7.591046 (lr=1.7038e-04) (hash(x)=25161929) +550 val loss 7.5841 +550 val perplexity 1966.5807 +550 train 7.507680 (lr=1.7036e-04) (hash(x)=27465106) +551 train 7.587856 (lr=1.7034e-04) (hash(x)=24013079) +552 train 7.474368 (lr=1.7033e-04) (hash(x)=23142015) +553 train 7.584139 (lr=1.7031e-04) (hash(x)=26768629) +554 train 7.623979 (lr=1.7029e-04) (hash(x)=26393383) +555 train 7.453664 (lr=1.7028e-04) (hash(x)=22537194) +556 train 7.718634 (lr=1.7026e-04) (hash(x)=24046036) +557 train 7.664890 (lr=1.7024e-04) (hash(x)=24974360) +558 train 7.902299 (lr=1.7022e-04) (hash(x)=28379928) +559 train 7.626058 (lr=1.7021e-04) (hash(x)=25322001) +560 train 7.729413 (lr=1.7019e-04) (hash(x)=26622031) +561 train 7.336664 (lr=1.7017e-04) (hash(x)=20562247) +562 train 7.712505 (lr=1.7016e-04) (hash(x)=27381885) +563 train 7.869229 (lr=1.7014e-04) (hash(x)=27028126) +564 train 7.704971 (lr=1.7012e-04) (hash(x)=28882928) +565 train 7.611508 (lr=1.7010e-04) (hash(x)=25666355) +566 train 7.739873 (lr=1.7009e-04) (hash(x)=24330810) +567 train 7.653133 (lr=1.7007e-04) (hash(x)=26690440) +568 train 7.552001 (lr=1.7005e-04) (hash(x)=22923592) +569 train 7.670110 (lr=1.7004e-04) (hash(x)=27348418) +570 train 7.681656 (lr=1.7002e-04) (hash(x)=28849848) +571 train 7.710593 (lr=1.7000e-04) (hash(x)=26967331) +572 train 7.487844 (lr=1.6998e-04) (hash(x)=22831467) +573 train 7.559330 (lr=1.6997e-04) (hash(x)=24765121) +574 train 7.545160 (lr=1.6995e-04) (hash(x)=24331857) +575 train 7.395290 (lr=1.6993e-04) (hash(x)=22598512) +576 train 7.542222 (lr=1.6991e-04) (hash(x)=25149353) +577 train 7.464290 (lr=1.6990e-04) (hash(x)=23725598) +578 train 7.666541 (lr=1.6988e-04) (hash(x)=26449557) +579 train 7.703638 (lr=1.6986e-04) (hash(x)=24697985) +580 train 7.720712 (lr=1.6984e-04) (hash(x)=26923059) +581 train 7.536916 (lr=1.6983e-04) (hash(x)=25201962) +582 train 7.206291 (lr=1.6981e-04) (hash(x)=20931520) +583 train 7.270576 (lr=1.6979e-04) (hash(x)=18473911) +584 train 7.408415 (lr=1.6977e-04) (hash(x)=21306267) +585 train 7.633405 (lr=1.6976e-04) (hash(x)=25982840) +586 train 7.532704 (lr=1.6974e-04) (hash(x)=25364874) +587 train 7.410273 (lr=1.6972e-04) (hash(x)=23172124) +588 train 7.737956 (lr=1.6970e-04) (hash(x)=27876897) +589 train 8.406670 (lr=1.6968e-04) (hash(x)=34646114) +590 train 8.668195 (lr=1.6967e-04) (hash(x)=35153576) +591 train 7.599439 (lr=1.6965e-04) (hash(x)=22322442) +592 train 7.788786 (lr=1.6963e-04) (hash(x)=27907331) +593 train 7.687905 (lr=1.6961e-04) (hash(x)=26211794) +594 train 7.862542 (lr=1.6959e-04) (hash(x)=29291512) +595 train 8.061687 (lr=1.6958e-04) (hash(x)=29659121) +596 train 7.940942 (lr=1.6956e-04) (hash(x)=29674399) +597 train 7.575829 (lr=1.6954e-04) (hash(x)=23538306) +598 train 7.702114 (lr=1.6952e-04) (hash(x)=21991524) +599 train 7.621414 (lr=1.6950e-04) (hash(x)=26324153) +600 val loss 7.5729 +600 val perplexity 1944.7521 +600 train 7.553630 (lr=1.6949e-04) (hash(x)=23712082) +601 train 7.666122 (lr=1.6947e-04) (hash(x)=24910403) +602 train 7.596001 (lr=1.6945e-04) (hash(x)=26737205) +603 train 7.708271 (lr=1.6943e-04) (hash(x)=26939970) +604 train 7.584507 (lr=1.6941e-04) (hash(x)=27651943) +605 train 7.919538 (lr=1.6939e-04) (hash(x)=27515446) +606 train 7.786603 (lr=1.6938e-04) (hash(x)=26753129) +607 train 7.494380 (lr=1.6936e-04) (hash(x)=23446058) +608 train 7.696716 (lr=1.6934e-04) (hash(x)=27587849) +609 train 7.680509 (lr=1.6932e-04) (hash(x)=25308253) +610 train 7.690723 (lr=1.6930e-04) (hash(x)=26615098) +611 train 7.714059 (lr=1.6928e-04) (hash(x)=29981801) +612 train 7.753197 (lr=1.6927e-04) (hash(x)=29592345) +613 train 7.792211 (lr=1.6925e-04) (hash(x)=23470413) +614 train 7.684556 (lr=1.6923e-04) (hash(x)=24742370) +615 train 7.674659 (lr=1.6921e-04) (hash(x)=24843741) +616 train 7.658852 (lr=1.6919e-04) (hash(x)=25192548) +617 train 7.690370 (lr=1.6917e-04) (hash(x)=27176996) +618 train 7.556009 (lr=1.6915e-04) (hash(x)=23964552) +619 train 7.569061 (lr=1.6914e-04) (hash(x)=22855363) +620 train 7.517128 (lr=1.6912e-04) (hash(x)=26332996) +621 train 7.329161 (lr=1.6910e-04) (hash(x)=22960957) +622 train 7.630544 (lr=1.6908e-04) (hash(x)=22752597) +623 train 7.513095 (lr=1.6906e-04) (hash(x)=23197102) +624 train 7.964963 (lr=1.6904e-04) (hash(x)=27383319) +625 train 7.634252 (lr=1.6902e-04) (hash(x)=26132276) +626 train 7.556001 (lr=1.6900e-04) (hash(x)=19810497) +627 train 7.575159 (lr=1.6898e-04) (hash(x)=25704919) +628 train 7.773848 (lr=1.6897e-04) (hash(x)=27174264) +629 train 7.846680 (lr=1.6895e-04) (hash(x)=22280814) +630 train 8.483221 (lr=1.6893e-04) (hash(x)=24279448) +631 train 8.042871 (lr=1.6891e-04) (hash(x)=23054940) +632 train 8.126512 (lr=1.6889e-04) (hash(x)=23942400) +633 train 8.324437 (lr=1.6887e-04) (hash(x)=24712416) +634 train 7.946527 (lr=1.6885e-04) (hash(x)=24564658) +635 train 7.679066 (lr=1.6883e-04) (hash(x)=24909904) +636 train 7.716318 (lr=1.6881e-04) (hash(x)=23049534) +637 train 7.770227 (lr=1.6879e-04) (hash(x)=24321591) +638 train 7.555995 (lr=1.6877e-04) (hash(x)=26153298) +639 train 7.598354 (lr=1.6875e-04) (hash(x)=27140757) +640 train 7.345821 (lr=1.6874e-04) (hash(x)=25115907) +641 train 7.395468 (lr=1.6872e-04) (hash(x)=26563770) +642 train 7.586716 (lr=1.6870e-04) (hash(x)=28089252) +643 train 7.509132 (lr=1.6868e-04) (hash(x)=25993110) +644 train 7.481664 (lr=1.6866e-04) (hash(x)=25150008) +645 train 7.706712 (lr=1.6864e-04) (hash(x)=28520222) +646 train 7.417392 (lr=1.6862e-04) (hash(x)=21349943) +647 train 7.478909 (lr=1.6860e-04) (hash(x)=25149419) +648 train 7.709747 (lr=1.6858e-04) (hash(x)=25730641) +649 train 7.821548 (lr=1.6856e-04) (hash(x)=26112813) +650 val loss 7.6034 +650 val perplexity 2004.9225 +650 train 7.630792 (lr=1.6854e-04) (hash(x)=25907805) +651 train 7.653378 (lr=1.6852e-04) (hash(x)=27623643) +652 train 7.622992 (lr=1.6850e-04) (hash(x)=26484959) +653 train 7.678977 (lr=1.6848e-04) (hash(x)=29199854) +654 train 7.662229 (lr=1.6846e-04) (hash(x)=28369628) +655 train 7.505983 (lr=1.6844e-04) (hash(x)=24727764) +656 train 7.291176 (lr=1.6842e-04) (hash(x)=22610673) +657 train 7.232911 (lr=1.6840e-04) (hash(x)=22667179) +658 train 7.030835 (lr=1.6838e-04) (hash(x)=18477300) +659 train 7.431774 (lr=1.6836e-04) (hash(x)=23155773) +660 train 7.209151 (lr=1.6834e-04) (hash(x)=19461032) +661 train 7.500302 (lr=1.6832e-04) (hash(x)=23453788) +662 train 7.633580 (lr=1.6830e-04) (hash(x)=24543466) +663 train 7.413016 (lr=1.6828e-04) (hash(x)=21935931) +664 train 7.255435 (lr=1.6826e-04) (hash(x)=19910292) +665 train 7.533066 (lr=1.6824e-04) (hash(x)=24481079) +666 train 7.224051 (lr=1.6822e-04) (hash(x)=18922411) +667 train 7.260936 (lr=1.6820e-04) (hash(x)=20054917) +668 train 7.488603 (lr=1.6818e-04) (hash(x)=24850470) +669 train 7.480787 (lr=1.6816e-04) (hash(x)=25907741) +670 train 7.649709 (lr=1.6814e-04) (hash(x)=26873522) +671 train 7.692540 (lr=1.6812e-04) (hash(x)=27606073) +672 train 7.794535 (lr=1.6810e-04) (hash(x)=26209645) +673 train 7.621584 (lr=1.6808e-04) (hash(x)=25202001) +674 train 7.665254 (lr=1.6806e-04) (hash(x)=25569462) +675 train 7.651745 (lr=1.6804e-04) (hash(x)=26534487) +676 train 7.610924 (lr=1.6802e-04) (hash(x)=26455057) +677 train 7.503952 (lr=1.6800e-04) (hash(x)=24095850) +678 train 7.720999 (lr=1.6798e-04) (hash(x)=25287752) +679 train 7.230752 (lr=1.6796e-04) (hash(x)=22450341) +680 train 7.960777 (lr=1.6794e-04) (hash(x)=29004853) +681 train 7.660071 (lr=1.6792e-04) (hash(x)=27993763) +682 train 7.488374 (lr=1.6790e-04) (hash(x)=26382658) +683 train 7.610485 (lr=1.6788e-04) (hash(x)=25013073) +684 train 7.641692 (lr=1.6786e-04) (hash(x)=30595809) +685 train 7.722819 (lr=1.6784e-04) (hash(x)=30934371) +686 train 8.276461 (lr=1.6782e-04) (hash(x)=33060834) +687 train 7.606578 (lr=1.6779e-04) (hash(x)=25945859) +688 train 7.455864 (lr=1.6777e-04) (hash(x)=23375678) +689 train 7.468615 (lr=1.6775e-04) (hash(x)=25218689) +690 train 7.606434 (lr=1.6773e-04) (hash(x)=28127397) +691 train 7.511131 (lr=1.6771e-04) (hash(x)=24418091) +692 train 7.437290 (lr=1.6769e-04) (hash(x)=22761099) +693 train 7.473785 (lr=1.6767e-04) (hash(x)=24615466) +694 train 7.633185 (lr=1.6765e-04) (hash(x)=24699240) +695 train 7.543184 (lr=1.6763e-04) (hash(x)=21613707) +696 train 7.549602 (lr=1.6761e-04) (hash(x)=24977554) +697 train 7.511810 (lr=1.6759e-04) (hash(x)=24348175) +698 train 7.648186 (lr=1.6757e-04) (hash(x)=25102767) +699 train 7.593495 (lr=1.6754e-04) (hash(x)=26386157) +700 val loss 7.5218 +700 val perplexity 1847.9778 +700 train 7.540180 (lr=1.6752e-04) (hash(x)=26423460) +701 train 7.468405 (lr=1.6750e-04) (hash(x)=25771047) +702 train 7.541837 (lr=1.6748e-04) (hash(x)=26999875) +703 train 7.458771 (lr=1.6746e-04) (hash(x)=24396519) +704 train 7.489187 (lr=1.6744e-04) (hash(x)=22588122) +705 train 7.800856 (lr=1.6742e-04) (hash(x)=25142399) +706 train 7.549587 (lr=1.6740e-04) (hash(x)=20440214) +707 train 7.393986 (lr=1.6738e-04) (hash(x)=23265507) +708 train 7.488028 (lr=1.6735e-04) (hash(x)=24563470) +709 train 7.396094 (lr=1.6733e-04) (hash(x)=22514858) +710 train 7.703182 (lr=1.6731e-04) (hash(x)=26691212) +711 train 7.796618 (lr=1.6729e-04) (hash(x)=29138828) +712 train 7.794467 (lr=1.6727e-04) (hash(x)=28028528) +713 train 7.660353 (lr=1.6725e-04) (hash(x)=20531210) +714 train 7.483003 (lr=1.6723e-04) (hash(x)=25075352) +715 train 7.560220 (lr=1.6720e-04) (hash(x)=24265353) +716 train 7.664344 (lr=1.6718e-04) (hash(x)=24635726) +717 train 7.503359 (lr=1.6716e-04) (hash(x)=24999726) +718 train 7.687459 (lr=1.6714e-04) (hash(x)=27412910) +719 train 7.470769 (lr=1.6712e-04) (hash(x)=24685515) +720 train 7.557620 (lr=1.6710e-04) (hash(x)=23780329) +721 train 7.349244 (lr=1.6708e-04) (hash(x)=25071701) +722 train 7.483665 (lr=1.6705e-04) (hash(x)=23767130) +723 train 7.453444 (lr=1.6703e-04) (hash(x)=24876269) +724 train 7.615274 (lr=1.6701e-04) (hash(x)=26405773) +725 train 8.023891 (lr=1.6699e-04) (hash(x)=31733180) +726 train 7.199684 (lr=1.6697e-04) (hash(x)=21337509) +727 train 7.335159 (lr=1.6694e-04) (hash(x)=22825749) +728 train 7.693813 (lr=1.6692e-04) (hash(x)=28638695) +729 train 7.554590 (lr=1.6690e-04) (hash(x)=26393943) +730 train 7.738434 (lr=1.6688e-04) (hash(x)=27563583) +731 train 7.259729 (lr=1.6686e-04) (hash(x)=21239652) +732 train 7.386590 (lr=1.6684e-04) (hash(x)=23986428) +733 train 7.405290 (lr=1.6681e-04) (hash(x)=24943881) +734 train 7.874538 (lr=1.6679e-04) (hash(x)=29691448) +735 train 7.795741 (lr=1.6677e-04) (hash(x)=28767869) +736 train 7.480484 (lr=1.6675e-04) (hash(x)=23628188) +737 train 7.744102 (lr=1.6673e-04) (hash(x)=29341482) +738 train 7.611113 (lr=1.6670e-04) (hash(x)=30336570) +739 train 7.574006 (lr=1.6668e-04) (hash(x)=25614301) +740 train 7.425485 (lr=1.6666e-04) (hash(x)=24160500) +741 train 7.655931 (lr=1.6664e-04) (hash(x)=26030058) +742 train 8.000786 (lr=1.6661e-04) (hash(x)=29243936) +743 train 7.289008 (lr=1.6659e-04) (hash(x)=21159060) +744 train 7.380889 (lr=1.6657e-04) (hash(x)=23701853) +745 train 7.592304 (lr=1.6655e-04) (hash(x)=24629937) +746 train 7.524654 (lr=1.6653e-04) (hash(x)=25110108) +747 train 7.561784 (lr=1.6650e-04) (hash(x)=26751788) +748 train 7.602077 (lr=1.6648e-04) (hash(x)=26430427) +749 train 7.445156 (lr=1.6646e-04) (hash(x)=26012353) +750 val loss 7.4875 +750 val perplexity 1785.5531 +750 train 7.603195 (lr=1.6644e-04) (hash(x)=22735910) +751 train 7.399797 (lr=1.6641e-04) (hash(x)=25045397) +752 train 7.118898 (lr=1.6639e-04) (hash(x)=21554427) +753 train 7.214206 (lr=1.6637e-04) (hash(x)=23751143) +754 train 8.012798 (lr=1.6635e-04) (hash(x)=28602273) +755 train 8.016159 (lr=1.6632e-04) (hash(x)=29989709) +756 train 7.429690 (lr=1.6630e-04) (hash(x)=22331648) +757 train 7.868466 (lr=1.6628e-04) (hash(x)=31017246) +758 train 7.799127 (lr=1.6626e-04) (hash(x)=29709045) +759 train 7.830525 (lr=1.6623e-04) (hash(x)=25560928) +760 train 7.542446 (lr=1.6621e-04) (hash(x)=25075464) +761 train 7.626328 (lr=1.6619e-04) (hash(x)=27352253) +762 train 7.828561 (lr=1.6616e-04) (hash(x)=28187891) +763 train 7.710147 (lr=1.6614e-04) (hash(x)=26062687) +764 train 7.724283 (lr=1.6612e-04) (hash(x)=27427811) +765 train 7.780849 (lr=1.6610e-04) (hash(x)=27614522) +766 train 7.541995 (lr=1.6607e-04) (hash(x)=26129544) +767 train 8.096749 (lr=1.6605e-04) (hash(x)=28959222) +768 train 7.660695 (lr=1.6603e-04) (hash(x)=26860067) +769 train 7.425540 (lr=1.6600e-04) (hash(x)=25122598) +770 train 7.526683 (lr=1.6598e-04) (hash(x)=25245030) +771 train 7.538703 (lr=1.6596e-04) (hash(x)=25434884) +772 train 7.570259 (lr=1.6594e-04) (hash(x)=27732790) +773 train 7.599145 (lr=1.6591e-04) (hash(x)=27824438) +774 train 7.680089 (lr=1.6589e-04) (hash(x)=27201953) +775 train 7.448864 (lr=1.6587e-04) (hash(x)=21248405) +776 train 7.221904 (lr=1.6584e-04) (hash(x)=22805934) +777 train 7.572129 (lr=1.6582e-04) (hash(x)=26482588) +778 train 7.597101 (lr=1.6580e-04) (hash(x)=24153691) +779 train 7.698977 (lr=1.6577e-04) (hash(x)=25044192) +780 train 7.659685 (lr=1.6575e-04) (hash(x)=25910078) +781 train 7.626626 (lr=1.6573e-04) (hash(x)=28645524) +782 train 7.442429 (lr=1.6570e-04) (hash(x)=24368498) +783 train 7.512348 (lr=1.6568e-04) (hash(x)=25830182) +784 train 7.632493 (lr=1.6566e-04) (hash(x)=29181807) +785 train 7.573059 (lr=1.6563e-04) (hash(x)=25585137) +786 train 7.486371 (lr=1.6561e-04) (hash(x)=24798246) +787 train 7.594591 (lr=1.6559e-04) (hash(x)=26621419) +788 train 7.162850 (lr=1.6556e-04) (hash(x)=21446891) +789 train 7.113585 (lr=1.6554e-04) (hash(x)=22165286) +790 train 7.338057 (lr=1.6552e-04) (hash(x)=23477219) +791 train 7.623451 (lr=1.6549e-04) (hash(x)=25173113) +792 train 7.488034 (lr=1.6547e-04) (hash(x)=25853788) +793 train 7.590883 (lr=1.6545e-04) (hash(x)=27267091) +794 train 7.420794 (lr=1.6542e-04) (hash(x)=23743694) +795 train 7.402954 (lr=1.6540e-04) (hash(x)=24400133) +796 train 7.533077 (lr=1.6537e-04) (hash(x)=23663639) +797 train 7.447380 (lr=1.6535e-04) (hash(x)=23103223) +798 train 7.909343 (lr=1.6533e-04) (hash(x)=28748411) +799 train 7.151742 (lr=1.6530e-04) (hash(x)=23486277) +800 val loss 7.5185 +800 val perplexity 1841.8102 +800 train 7.531682 (lr=1.6528e-04) (hash(x)=25678518) +801 train 7.445371 (lr=1.6526e-04) (hash(x)=23421286) +802 train 7.574960 (lr=1.6523e-04) (hash(x)=26054104) +803 train 7.564831 (lr=1.6521e-04) (hash(x)=25978130) +804 train 7.586180 (lr=1.6518e-04) (hash(x)=26006525) +805 train 7.561704 (lr=1.6516e-04) (hash(x)=25769432) +806 train 7.385475 (lr=1.6514e-04) (hash(x)=22430795) +807 train 7.710637 (lr=1.6511e-04) (hash(x)=28916006) +808 train 7.531792 (lr=1.6509e-04) (hash(x)=25166800) +809 train 7.662449 (lr=1.6506e-04) (hash(x)=24226056) +810 train 7.482005 (lr=1.6504e-04) (hash(x)=25057934) +811 train 8.323267 (lr=1.6502e-04) (hash(x)=33195100) +812 train 7.663054 (lr=1.6499e-04) (hash(x)=26312888) +813 train 7.856395 (lr=1.6497e-04) (hash(x)=27730410) +814 train 7.701010 (lr=1.6494e-04) (hash(x)=27372474) +815 train 7.535217 (lr=1.6492e-04) (hash(x)=25556929) +816 train 7.645708 (lr=1.6489e-04) (hash(x)=26909985) +817 train 7.459621 (lr=1.6487e-04) (hash(x)=25991247) +818 train 7.621148 (lr=1.6485e-04) (hash(x)=27438141) +819 train 7.755214 (lr=1.6482e-04) (hash(x)=29536986) +820 train 7.511189 (lr=1.6480e-04) (hash(x)=24478391) +821 train 7.524165 (lr=1.6477e-04) (hash(x)=26125216) +822 train 7.560154 (lr=1.6475e-04) (hash(x)=26422130) +823 train 7.754314 (lr=1.6472e-04) (hash(x)=29648798) +824 train 7.447057 (lr=1.6470e-04) (hash(x)=21247770) +825 train 7.561218 (lr=1.6468e-04) (hash(x)=23195388) +826 train 7.509686 (lr=1.6465e-04) (hash(x)=25796725) +827 train 7.505176 (lr=1.6463e-04) (hash(x)=23124767) +828 train 7.543225 (lr=1.6460e-04) (hash(x)=25233464) +829 train 7.545990 (lr=1.6458e-04) (hash(x)=25713275) +830 train 7.484965 (lr=1.6455e-04) (hash(x)=25550167) +831 train 7.383452 (lr=1.6453e-04) (hash(x)=24976217) +832 train 7.707669 (lr=1.6450e-04) (hash(x)=28536827) +833 train 7.607892 (lr=1.6448e-04) (hash(x)=27500801) +834 train 7.441223 (lr=1.6445e-04) (hash(x)=25545765) +835 train 7.419234 (lr=1.6443e-04) (hash(x)=23632825) +836 train 7.469600 (lr=1.6440e-04) (hash(x)=25708009) +837 train 7.508559 (lr=1.6438e-04) (hash(x)=24456276) +838 train 7.647976 (lr=1.6435e-04) (hash(x)=29189855) +839 train 7.889197 (lr=1.6433e-04) (hash(x)=31019606) +840 train 7.764383 (lr=1.6430e-04) (hash(x)=26328013) +841 train 7.716259 (lr=1.6428e-04) (hash(x)=25027904) +842 train 7.454724 (lr=1.6425e-04) (hash(x)=23734189) +843 train 7.705731 (lr=1.6423e-04) (hash(x)=28236580) +844 train 7.532227 (lr=1.6420e-04) (hash(x)=26509780) +845 train 7.570244 (lr=1.6418e-04) (hash(x)=25386473) +846 train 7.508692 (lr=1.6415e-04) (hash(x)=24052671) +847 train 7.709054 (lr=1.6413e-04) (hash(x)=28269421) +848 train 7.142276 (lr=1.6410e-04) (hash(x)=22251724) +849 train 7.371574 (lr=1.6408e-04) (hash(x)=24308447) +850 val loss 7.4866 +850 val perplexity 1784.0612 +850 train 7.331468 (lr=1.6405e-04) (hash(x)=24242830) +851 train 7.565172 (lr=1.6403e-04) (hash(x)=25563279) +852 train 7.583412 (lr=1.6400e-04) (hash(x)=26354481) +853 train 7.718692 (lr=1.6398e-04) (hash(x)=26152637) +854 train 7.739292 (lr=1.6395e-04) (hash(x)=28051025) +855 train 7.563675 (lr=1.6393e-04) (hash(x)=24865358) +856 train 7.461678 (lr=1.6390e-04) (hash(x)=24288911) +857 train 7.366504 (lr=1.6388e-04) (hash(x)=22230964) +858 train 7.278816 (lr=1.6385e-04) (hash(x)=21303832) +859 train 7.420568 (lr=1.6383e-04) (hash(x)=22155546) +860 train 7.526079 (lr=1.6380e-04) (hash(x)=25296428) +861 train 7.690960 (lr=1.6378e-04) (hash(x)=29142319) +862 train 7.514522 (lr=1.6375e-04) (hash(x)=25545430) +863 train 7.347717 (lr=1.6372e-04) (hash(x)=26984272) +864 train 7.527632 (lr=1.6370e-04) (hash(x)=25429005) +865 train 7.537784 (lr=1.6367e-04) (hash(x)=27077032) +866 train 7.579631 (lr=1.6365e-04) (hash(x)=26494424) +867 train 7.578036 (lr=1.6362e-04) (hash(x)=23193673) +868 train 7.596115 (lr=1.6360e-04) (hash(x)=25075134) +869 train 7.624629 (lr=1.6357e-04) (hash(x)=27112558) +870 train 7.764678 (lr=1.6355e-04) (hash(x)=27436608) +871 train 7.486610 (lr=1.6352e-04) (hash(x)=24544116) +872 train 7.817731 (lr=1.6349e-04) (hash(x)=31632686) +873 train 7.525221 (lr=1.6347e-04) (hash(x)=25890184) +874 train 7.650350 (lr=1.6344e-04) (hash(x)=22887555) +875 train 7.450786 (lr=1.6342e-04) (hash(x)=24547533) +876 train 7.621775 (lr=1.6339e-04) (hash(x)=26553496) +877 train 7.708786 (lr=1.6337e-04) (hash(x)=27467688) +878 train 7.530434 (lr=1.6334e-04) (hash(x)=24766934) +879 train 7.386558 (lr=1.6331e-04) (hash(x)=22059850) +880 train 7.749704 (lr=1.6329e-04) (hash(x)=22871702) +881 train 7.592374 (lr=1.6326e-04) (hash(x)=23893130) +882 train 7.631525 (lr=1.6324e-04) (hash(x)=25125691) +883 train 7.559972 (lr=1.6321e-04) (hash(x)=25994573) +884 train 7.592220 (lr=1.6318e-04) (hash(x)=26076345) +885 train 7.520643 (lr=1.6316e-04) (hash(x)=26577783) +886 train 7.656459 (lr=1.6313e-04) (hash(x)=27395225) +887 train 7.476480 (lr=1.6310e-04) (hash(x)=23926632) +888 train 7.321009 (lr=1.6308e-04) (hash(x)=21737239) +889 train 7.596588 (lr=1.6305e-04) (hash(x)=23574207) +890 train 7.324202 (lr=1.6303e-04) (hash(x)=24365231) +891 train 7.470100 (lr=1.6300e-04) (hash(x)=27111369) +892 train 7.739818 (lr=1.6297e-04) (hash(x)=27290015) +893 train 7.515734 (lr=1.6295e-04) (hash(x)=23979820) +894 train 7.642330 (lr=1.6292e-04) (hash(x)=26450121) +895 train 7.505913 (lr=1.6289e-04) (hash(x)=27025333) +896 train 7.513898 (lr=1.6287e-04) (hash(x)=23624605) +897 train 7.283052 (lr=1.6284e-04) (hash(x)=22846386) +898 train 7.434056 (lr=1.6282e-04) (hash(x)=22970561) +899 train 7.290615 (lr=1.6279e-04) (hash(x)=16908068) +900 val loss 7.5162 +900 val perplexity 1837.6021 +900 train 7.506527 (lr=1.6276e-04) (hash(x)=24661446) +901 train 7.608014 (lr=1.6274e-04) (hash(x)=25664727) +902 train 7.547587 (lr=1.6271e-04) (hash(x)=25667011) +903 train 7.612103 (lr=1.6268e-04) (hash(x)=29120407) +904 train 7.659546 (lr=1.6266e-04) (hash(x)=23385735) +905 train 7.683500 (lr=1.6263e-04) (hash(x)=25564213) +906 train 7.744595 (lr=1.6260e-04) (hash(x)=25413898) +907 train 7.720903 (lr=1.6258e-04) (hash(x)=27092710) +908 train 7.500722 (lr=1.6255e-04) (hash(x)=25789923) +909 train 7.580841 (lr=1.6252e-04) (hash(x)=28533197) +910 train 7.416808 (lr=1.6250e-04) (hash(x)=22982996) +911 train 7.507459 (lr=1.6247e-04) (hash(x)=23827393) +912 train 7.163081 (lr=1.6244e-04) (hash(x)=21242640) +913 train 7.542972 (lr=1.6242e-04) (hash(x)=24154233) +914 train 7.538432 (lr=1.6239e-04) (hash(x)=24331967) +915 train 7.833225 (lr=1.6236e-04) (hash(x)=32812727) +916 train 7.454770 (lr=1.6234e-04) (hash(x)=23572994) +917 train 7.476584 (lr=1.6231e-04) (hash(x)=26305435) +918 train 7.562161 (lr=1.6228e-04) (hash(x)=26268355) +919 train 7.724558 (lr=1.6225e-04) (hash(x)=27230027) +920 train 7.494199 (lr=1.6223e-04) (hash(x)=23885377) +921 train 7.456717 (lr=1.6220e-04) (hash(x)=23532437) +922 train 7.540047 (lr=1.6217e-04) (hash(x)=25577034) +923 train 7.643505 (lr=1.6215e-04) (hash(x)=25703381) +924 train 7.640468 (lr=1.6212e-04) (hash(x)=27113866) +925 train 7.445508 (lr=1.6209e-04) (hash(x)=26961429) +926 train 7.292661 (lr=1.6206e-04) (hash(x)=21355372) +927 train 7.375381 (lr=1.6204e-04) (hash(x)=24968260) +928 train 7.369956 (lr=1.6201e-04) (hash(x)=25357517) +929 train 7.510784 (lr=1.6198e-04) (hash(x)=24854265) +930 train 7.296494 (lr=1.6196e-04) (hash(x)=21102770) +931 train 7.580588 (lr=1.6193e-04) (hash(x)=25676468) +932 train 7.402042 (lr=1.6190e-04) (hash(x)=22809869) +933 train 7.488356 (lr=1.6187e-04) (hash(x)=25503865) +934 train 7.376518 (lr=1.6185e-04) (hash(x)=24853995) +935 train 7.640663 (lr=1.6182e-04) (hash(x)=27544803) +936 train 7.631387 (lr=1.6179e-04) (hash(x)=25981933) +937 train 7.376755 (lr=1.6176e-04) (hash(x)=24658683) +938 train 7.540275 (lr=1.6174e-04) (hash(x)=23855201) +939 train 7.483755 (lr=1.6171e-04) (hash(x)=24331407) +940 train 7.655124 (lr=1.6168e-04) (hash(x)=29265551) +941 train 7.382093 (lr=1.6165e-04) (hash(x)=21892556) +942 train 7.406184 (lr=1.6163e-04) (hash(x)=27183405) +943 train 7.345998 (lr=1.6160e-04) (hash(x)=26540663) +944 train 7.314014 (lr=1.6157e-04) (hash(x)=25718393) +945 train 7.542317 (lr=1.6154e-04) (hash(x)=26819462) +946 train 7.518352 (lr=1.6152e-04) (hash(x)=27427540) +947 train 7.505463 (lr=1.6149e-04) (hash(x)=25532657) +948 train 7.750957 (lr=1.6146e-04) (hash(x)=27641372) +949 train 7.437451 (lr=1.6143e-04) (hash(x)=26515570) +950 val loss 7.4870 +950 val perplexity 1784.6891 +950 train 7.704948 (lr=1.6141e-04) (hash(x)=26911957) +951 train 7.822721 (lr=1.6138e-04) (hash(x)=25856625) +952 train 7.374082 (lr=1.6135e-04) (hash(x)=25219129) +953 train 7.322886 (lr=1.6132e-04) (hash(x)=25260471) +954 train 7.721279 (lr=1.6129e-04) (hash(x)=29373370) +955 train 7.276630 (lr=1.6127e-04) (hash(x)=23437426) +956 train 7.578755 (lr=1.6124e-04) (hash(x)=23769521) +957 train 7.600711 (lr=1.6121e-04) (hash(x)=25961833) +958 train 7.321590 (lr=1.6118e-04) (hash(x)=23582666) +959 train 7.402974 (lr=1.6115e-04) (hash(x)=23164356) +960 train 7.377799 (lr=1.6113e-04) (hash(x)=24443114) +961 train 7.452770 (lr=1.6110e-04) (hash(x)=25052665) +962 train 7.590169 (lr=1.6107e-04) (hash(x)=27802272) +963 train 7.425342 (lr=1.6104e-04) (hash(x)=25957896) +964 train 7.457003 (lr=1.6101e-04) (hash(x)=26737251) +965 train 7.614133 (lr=1.6099e-04) (hash(x)=24723263) +966 train 7.517410 (lr=1.6096e-04) (hash(x)=24707011) +967 train 7.502805 (lr=1.6093e-04) (hash(x)=25646282) +968 train 7.529751 (lr=1.6090e-04) (hash(x)=27544665) +969 train 7.449417 (lr=1.6087e-04) (hash(x)=25851993) +970 train 7.779367 (lr=1.6084e-04) (hash(x)=29059700) +971 train 7.468147 (lr=1.6082e-04) (hash(x)=21513584) +972 train 7.192997 (lr=1.6079e-04) (hash(x)=23151267) +973 train 7.488306 (lr=1.6076e-04) (hash(x)=26017176) +974 train 7.536991 (lr=1.6073e-04) (hash(x)=26979518) +975 train 7.559088 (lr=1.6070e-04) (hash(x)=23843233) +976 train 7.757612 (lr=1.6067e-04) (hash(x)=24193010) +977 train 7.467737 (lr=1.6065e-04) (hash(x)=21476847) +978 train 7.338660 (lr=1.6062e-04) (hash(x)=21366504) +979 train 7.331302 (lr=1.6059e-04) (hash(x)=23226697) +980 train 7.138587 (lr=1.6056e-04) (hash(x)=19961773) +981 train 7.057422 (lr=1.6053e-04) (hash(x)=19772969) +982 train 7.365714 (lr=1.6050e-04) (hash(x)=23110142) +983 train 7.622861 (lr=1.6047e-04) (hash(x)=24506028) +984 train 7.620534 (lr=1.6045e-04) (hash(x)=25480731) +985 train 7.458694 (lr=1.6042e-04) (hash(x)=21077417) +986 train 7.410868 (lr=1.6039e-04) (hash(x)=23686713) +987 train 7.474028 (lr=1.6036e-04) (hash(x)=26024321) +988 train 7.568300 (lr=1.6033e-04) (hash(x)=27424109) +989 train 7.704710 (lr=1.6030e-04) (hash(x)=27786174) +990 train 7.487047 (lr=1.6027e-04) (hash(x)=25232502) +991 train 7.504478 (lr=1.6024e-04) (hash(x)=22781277) +992 train 7.586558 (lr=1.6022e-04) (hash(x)=26184527) +993 train 7.549100 (lr=1.6019e-04) (hash(x)=24459895) +994 train 7.503152 (lr=1.6016e-04) (hash(x)=25244624) +995 train 7.635563 (lr=1.6013e-04) (hash(x)=24451843) +996 train 7.620337 (lr=1.6010e-04) (hash(x)=22129897) +997 train 7.414026 (lr=1.6007e-04) (hash(x)=21116390) +998 train 7.227712 (lr=1.6004e-04) (hash(x)=20650070) +999 train 7.584451 (lr=1.6001e-04) (hash(x)=24948650) +1000 val loss 7.4659 +1000 val perplexity 1747.3674 +1000 train 7.473845 (lr=1.5998e-04) (hash(x)=25444553) +1001 train 7.435653 (lr=1.5995e-04) (hash(x)=25617781) +1002 train 7.328920 (lr=1.5993e-04) (hash(x)=23862434) +1003 train 7.381687 (lr=1.5990e-04) (hash(x)=25559534) +1004 train 7.576736 (lr=1.5987e-04) (hash(x)=26577585) +1005 train 7.445718 (lr=1.5984e-04) (hash(x)=25546274) +1006 train 7.498747 (lr=1.5981e-04) (hash(x)=26284202) +1007 train 7.544511 (lr=1.5978e-04) (hash(x)=26373991) +1008 train 7.414413 (lr=1.5975e-04) (hash(x)=24612851) +1009 train 7.501488 (lr=1.5972e-04) (hash(x)=26410662) +1010 train 7.575580 (lr=1.5969e-04) (hash(x)=23824841) +1011 train 7.855985 (lr=1.5966e-04) (hash(x)=27756673) +1012 train 7.594907 (lr=1.5963e-04) (hash(x)=25427447) +1013 train 7.624600 (lr=1.5960e-04) (hash(x)=23661686) +1014 train 7.495492 (lr=1.5957e-04) (hash(x)=25129504) +1015 train 7.444737 (lr=1.5954e-04) (hash(x)=23402396) +1016 train 7.673654 (lr=1.5952e-04) (hash(x)=26145557) +1017 train 7.403419 (lr=1.5949e-04) (hash(x)=26547918) +1018 train 7.532598 (lr=1.5946e-04) (hash(x)=26653070) +1019 train 7.554196 (lr=1.5943e-04) (hash(x)=28250354) +1020 train 7.518494 (lr=1.5940e-04) (hash(x)=25437401) +1021 train 7.578462 (lr=1.5937e-04) (hash(x)=25598861) +1022 train 7.388483 (lr=1.5934e-04) (hash(x)=24572587) +1023 train 7.463254 (lr=1.5931e-04) (hash(x)=21562133) +1024 train 7.855025 (lr=1.5928e-04) (hash(x)=27718876) +1025 train 7.435587 (lr=1.5925e-04) (hash(x)=25312391) +1026 train 7.505581 (lr=1.5922e-04) (hash(x)=26579535) +1027 train 7.729965 (lr=1.5919e-04) (hash(x)=27253861) +1028 train 7.608028 (lr=1.5916e-04) (hash(x)=28451867) +1029 train 7.357502 (lr=1.5913e-04) (hash(x)=26795921) +1030 train 7.520952 (lr=1.5910e-04) (hash(x)=26147208) +1031 train 7.525917 (lr=1.5907e-04) (hash(x)=25009210) +1032 train 7.473805 (lr=1.5904e-04) (hash(x)=25213771) +1033 train 7.390420 (lr=1.5901e-04) (hash(x)=26254538) +1034 train 7.423830 (lr=1.5898e-04) (hash(x)=25565614) +1035 train 7.275693 (lr=1.5895e-04) (hash(x)=23052577) +1036 train 8.035327 (lr=1.5892e-04) (hash(x)=29630613) +1037 train 7.312304 (lr=1.5889e-04) (hash(x)=23667224) +1038 train 7.414273 (lr=1.5886e-04) (hash(x)=25740670) +1039 train 7.543345 (lr=1.5883e-04) (hash(x)=27161811) +1040 train 7.667714 (lr=1.5880e-04) (hash(x)=26385663) +1041 train 7.369060 (lr=1.5877e-04) (hash(x)=26313522) +1042 train 7.487323 (lr=1.5874e-04) (hash(x)=26814686) +1043 train 7.600888 (lr=1.5871e-04) (hash(x)=27302459) +1044 train 7.882220 (lr=1.5868e-04) (hash(x)=26758132) +1045 train 7.494872 (lr=1.5865e-04) (hash(x)=26837963) +1046 train 7.276781 (lr=1.5862e-04) (hash(x)=22089547) +1047 train 7.780090 (lr=1.5859e-04) (hash(x)=29515100) +1048 train 7.480432 (lr=1.5856e-04) (hash(x)=25471442) +1049 train 7.485406 (lr=1.5853e-04) (hash(x)=26674478) +1050 val loss 7.4620 +1050 val perplexity 1740.6953 +1050 train 7.422695 (lr=1.5850e-04) (hash(x)=25373386) +1051 train 7.463759 (lr=1.5847e-04) (hash(x)=25318001) +1052 train 7.626789 (lr=1.5844e-04) (hash(x)=27255021) +1053 train 7.544792 (lr=1.5841e-04) (hash(x)=25174043) +1054 train 7.342828 (lr=1.5838e-04) (hash(x)=23857597) +1055 train 7.540933 (lr=1.5835e-04) (hash(x)=25305929) +1056 train 7.582809 (lr=1.5832e-04) (hash(x)=27009246) +1057 train 7.652692 (lr=1.5829e-04) (hash(x)=26175477) +1058 train 7.302975 (lr=1.5826e-04) (hash(x)=22700025) +1059 train 7.439216 (lr=1.5822e-04) (hash(x)=24339043) +1060 train 7.243985 (lr=1.5819e-04) (hash(x)=22139900) +1061 train 8.065089 (lr=1.5816e-04) (hash(x)=25412772) +1062 train 7.496604 (lr=1.5813e-04) (hash(x)=27020849) +1063 train 7.390215 (lr=1.5810e-04) (hash(x)=26808543) +1064 train 7.171906 (lr=1.5807e-04) (hash(x)=23061527) +1065 train 7.414074 (lr=1.5804e-04) (hash(x)=24738650) +1066 train 7.245654 (lr=1.5801e-04) (hash(x)=24036715) +1067 train 7.319173 (lr=1.5798e-04) (hash(x)=25763991) +1068 train 7.601456 (lr=1.5795e-04) (hash(x)=27393753) +1069 train 7.701152 (lr=1.5792e-04) (hash(x)=28182190) +1070 train 7.368790 (lr=1.5789e-04) (hash(x)=23358569) +1071 train 7.553843 (lr=1.5786e-04) (hash(x)=25669509) +1072 train 7.640592 (lr=1.5783e-04) (hash(x)=29139024) +1073 train 7.559270 (lr=1.5779e-04) (hash(x)=25616522) +1074 train 7.403388 (lr=1.5776e-04) (hash(x)=25695789) +1075 train 7.604198 (lr=1.5773e-04) (hash(x)=27676869) +1076 train 7.504892 (lr=1.5770e-04) (hash(x)=25952695) +1077 train 7.497893 (lr=1.5767e-04) (hash(x)=26316170) +1078 train 7.403572 (lr=1.5764e-04) (hash(x)=24081867) +1079 train 7.574364 (lr=1.5761e-04) (hash(x)=28435805) +1080 train 7.478316 (lr=1.5758e-04) (hash(x)=23375063) +1081 train 7.469937 (lr=1.5755e-04) (hash(x)=26869022) +1082 train 7.341271 (lr=1.5752e-04) (hash(x)=25793007) +1083 train 7.280423 (lr=1.5749e-04) (hash(x)=23455211) +1084 train 7.348272 (lr=1.5745e-04) (hash(x)=20441501) +1085 train 7.716411 (lr=1.5742e-04) (hash(x)=29321187) +1086 train 7.860176 (lr=1.5739e-04) (hash(x)=32627505) +1087 train 7.415096 (lr=1.5736e-04) (hash(x)=26482758) +1088 train 7.233391 (lr=1.5733e-04) (hash(x)=21431511) +1089 train 7.476983 (lr=1.5730e-04) (hash(x)=26046639) +1090 train 7.543053 (lr=1.5727e-04) (hash(x)=27464841) +1091 train 7.432384 (lr=1.5724e-04) (hash(x)=27068280) +1092 train 7.266472 (lr=1.5720e-04) (hash(x)=23119133) +1093 train 7.487373 (lr=1.5717e-04) (hash(x)=26782091) +1094 train 7.502931 (lr=1.5714e-04) (hash(x)=26265326) +1095 train 7.513544 (lr=1.5711e-04) (hash(x)=24929929) +1096 train 7.376117 (lr=1.5708e-04) (hash(x)=23158628) +1097 train 7.463060 (lr=1.5705e-04) (hash(x)=25950541) +1098 train 7.268883 (lr=1.5702e-04) (hash(x)=22093912) +1099 train 7.433044 (lr=1.5698e-04) (hash(x)=25373676) +1100 val loss 7.4138 +1100 val perplexity 1658.7947 +1100 train 7.186972 (lr=1.5695e-04) (hash(x)=18986670) +1101 train 7.673818 (lr=1.5692e-04) (hash(x)=27283187) +1102 train 7.419661 (lr=1.5689e-04) (hash(x)=25474743) +1103 train 7.293800 (lr=1.5686e-04) (hash(x)=25043037) +1104 train 7.261394 (lr=1.5683e-04) (hash(x)=23156261) +1105 train 7.664135 (lr=1.5679e-04) (hash(x)=27027534) +1106 train 7.269441 (lr=1.5676e-04) (hash(x)=22733630) +1107 train 7.542550 (lr=1.5673e-04) (hash(x)=27906976) +1108 train 7.460477 (lr=1.5670e-04) (hash(x)=27848655) +1109 train 7.410910 (lr=1.5667e-04) (hash(x)=23889709) +1110 train 8.449869 (lr=1.5664e-04) (hash(x)=33189918) +1111 train 7.993634 (lr=1.5660e-04) (hash(x)=29151257) +1112 train 7.676042 (lr=1.5657e-04) (hash(x)=23881512) +1113 train 7.358562 (lr=1.5654e-04) (hash(x)=21307974) +1114 train 7.395122 (lr=1.5651e-04) (hash(x)=25264524) +1115 train 7.567990 (lr=1.5648e-04) (hash(x)=26405613) +1116 train 7.257022 (lr=1.5645e-04) (hash(x)=21918678) +1117 train 7.332973 (lr=1.5641e-04) (hash(x)=24233887) +1118 train 6.964512 (lr=1.5638e-04) (hash(x)=19490509) +1119 train 7.572392 (lr=1.5635e-04) (hash(x)=26400365) +1120 train 7.803575 (lr=1.5632e-04) (hash(x)=28572086) +1121 train 7.293621 (lr=1.5629e-04) (hash(x)=22293114) +1122 train 7.391803 (lr=1.5625e-04) (hash(x)=26845479) +1123 train 7.258556 (lr=1.5622e-04) (hash(x)=23971905) +1124 train 7.485191 (lr=1.5619e-04) (hash(x)=25639959) +1125 train 7.118883 (lr=1.5616e-04) (hash(x)=20076502) +1126 train 7.495013 (lr=1.5612e-04) (hash(x)=25089255) +1127 train 7.378151 (lr=1.5609e-04) (hash(x)=24098812) +1128 train 7.394510 (lr=1.5606e-04) (hash(x)=23493707) +1129 train 7.612661 (lr=1.5603e-04) (hash(x)=27610410) +1130 train 7.376491 (lr=1.5600e-04) (hash(x)=24540186) +1131 train 7.650877 (lr=1.5596e-04) (hash(x)=29402976) +1132 train 7.279609 (lr=1.5593e-04) (hash(x)=23776025) +1133 train 7.011776 (lr=1.5590e-04) (hash(x)=19032564) +1134 train 7.591229 (lr=1.5587e-04) (hash(x)=26921117) +1135 train 7.196579 (lr=1.5583e-04) (hash(x)=20967666) +1136 train 7.231134 (lr=1.5580e-04) (hash(x)=23394540) +1137 train 7.284767 (lr=1.5577e-04) (hash(x)=22666342) +1138 train 7.418326 (lr=1.5574e-04) (hash(x)=23482498) +1139 train 7.483686 (lr=1.5570e-04) (hash(x)=24287610) +1140 train 7.567793 (lr=1.5567e-04) (hash(x)=24512831) +1141 train 7.833327 (lr=1.5564e-04) (hash(x)=28637634) +1142 train 8.087570 (lr=1.5561e-04) (hash(x)=24107127) +1143 train 7.696984 (lr=1.5557e-04) (hash(x)=28667963) +1144 train 7.542956 (lr=1.5554e-04) (hash(x)=26302492) +1145 train 7.575787 (lr=1.5551e-04) (hash(x)=23621685) +1146 train 7.276294 (lr=1.5548e-04) (hash(x)=23997414) +1147 train 7.375905 (lr=1.5544e-04) (hash(x)=25974316) +1148 train 7.320519 (lr=1.5541e-04) (hash(x)=23464988) +1149 train 7.436657 (lr=1.5538e-04) (hash(x)=24487710) +1150 val loss 7.4092 +1150 val perplexity 1651.1659 +1150 train 7.628940 (lr=1.5535e-04) (hash(x)=29610350) +1151 train 7.761765 (lr=1.5531e-04) (hash(x)=27083417) +1152 train 7.091644 (lr=1.5528e-04) (hash(x)=20666288) +1153 train 7.181053 (lr=1.5525e-04) (hash(x)=22850633) +1154 train 7.375887 (lr=1.5522e-04) (hash(x)=24741872) +1155 train 7.749438 (lr=1.5518e-04) (hash(x)=28605205) +1156 train 7.194124 (lr=1.5515e-04) (hash(x)=22624463) +1157 train 7.426281 (lr=1.5512e-04) (hash(x)=24786468) +1158 train 7.163872 (lr=1.5508e-04) (hash(x)=21365399) +1159 train 7.402701 (lr=1.5505e-04) (hash(x)=23649001) +1160 train 7.461045 (lr=1.5502e-04) (hash(x)=28203982) +1161 train 7.358481 (lr=1.5499e-04) (hash(x)=26473994) +1162 train 7.022513 (lr=1.5495e-04) (hash(x)=19476441) +1163 train 7.312016 (lr=1.5492e-04) (hash(x)=25921700) +1164 train 7.176419 (lr=1.5489e-04) (hash(x)=23064343) +1165 train 7.332989 (lr=1.5485e-04) (hash(x)=24117626) +1166 train 7.315589 (lr=1.5482e-04) (hash(x)=21764556) +1167 train 8.148211 (lr=1.5479e-04) (hash(x)=31338300) +1168 train 7.604364 (lr=1.5475e-04) (hash(x)=27443187) +1169 train 6.996022 (lr=1.5472e-04) (hash(x)=21337692) +1170 train 7.496625 (lr=1.5469e-04) (hash(x)=27845383) +1171 train 7.313218 (lr=1.5465e-04) (hash(x)=23862328) +1172 train 7.543415 (lr=1.5462e-04) (hash(x)=23811014) +1173 train 7.498140 (lr=1.5459e-04) (hash(x)=24380098) +1174 train 7.168062 (lr=1.5455e-04) (hash(x)=22351136) +1175 train 7.486533 (lr=1.5452e-04) (hash(x)=30603174) +1176 train 7.537455 (lr=1.5449e-04) (hash(x)=27924596) +1177 train 7.884208 (lr=1.5445e-04) (hash(x)=30882548) +1178 train 7.313568 (lr=1.5442e-04) (hash(x)=22339464) +1179 train 7.170490 (lr=1.5439e-04) (hash(x)=23603806) +1180 train 7.534819 (lr=1.5435e-04) (hash(x)=24809041) +1181 train 7.360340 (lr=1.5432e-04) (hash(x)=24382442) +1182 train 7.300804 (lr=1.5429e-04) (hash(x)=23134077) +1183 train 7.331239 (lr=1.5425e-04) (hash(x)=24830965) +1184 train 7.397797 (lr=1.5422e-04) (hash(x)=25527259) +1185 train 7.473348 (lr=1.5419e-04) (hash(x)=25547480) +1186 train 7.296936 (lr=1.5415e-04) (hash(x)=24424314) +1187 train 7.722856 (lr=1.5412e-04) (hash(x)=32488729) +1188 train 7.649049 (lr=1.5409e-04) (hash(x)=31168462) +1189 train 7.898040 (lr=1.5405e-04) (hash(x)=31331643) +1190 train 7.545921 (lr=1.5402e-04) (hash(x)=28746633) +1191 train 7.516422 (lr=1.5399e-04) (hash(x)=27269893) +1192 train 7.299188 (lr=1.5395e-04) (hash(x)=23484031) +1193 train 7.317546 (lr=1.5392e-04) (hash(x)=23278725) +1194 train 7.432858 (lr=1.5388e-04) (hash(x)=25440745) +1195 train 7.500047 (lr=1.5385e-04) (hash(x)=25215077) +1196 train 7.527684 (lr=1.5382e-04) (hash(x)=28309266) +1197 train 7.276141 (lr=1.5378e-04) (hash(x)=22442404) +1198 train 7.303334 (lr=1.5375e-04) (hash(x)=20775262) +1199 train 7.350043 (lr=1.5372e-04) (hash(x)=24825041) +1200 val loss 7.4194 +1200 val perplexity 1668.0876 +1200 train 7.539247 (lr=1.5368e-04) (hash(x)=29016896) +1201 train 7.470835 (lr=1.5365e-04) (hash(x)=25590276) +1202 train 7.321052 (lr=1.5361e-04) (hash(x)=22816384) +1203 train 7.481258 (lr=1.5358e-04) (hash(x)=25893804) +1204 train 7.349428 (lr=1.5355e-04) (hash(x)=23983816) +1205 train 7.254286 (lr=1.5351e-04) (hash(x)=22222468) +1206 train 7.297490 (lr=1.5348e-04) (hash(x)=23039141) +1207 train 7.222327 (lr=1.5344e-04) (hash(x)=22724871) +1208 train 7.259358 (lr=1.5341e-04) (hash(x)=25253062) +1209 train 7.272542 (lr=1.5338e-04) (hash(x)=25140744) +1210 train 7.381865 (lr=1.5334e-04) (hash(x)=24717218) +1211 train 7.452858 (lr=1.5331e-04) (hash(x)=27317554) +1212 train 7.131438 (lr=1.5327e-04) (hash(x)=22013236) +1213 train 7.668658 (lr=1.5324e-04) (hash(x)=26692343) +1214 train 7.180640 (lr=1.5321e-04) (hash(x)=19859225) +1215 train 7.121400 (lr=1.5317e-04) (hash(x)=24683717) +1216 train 7.216516 (lr=1.5314e-04) (hash(x)=21932013) +1217 train 7.449590 (lr=1.5310e-04) (hash(x)=26849303) +1218 train 7.509914 (lr=1.5307e-04) (hash(x)=26458000) +1219 train 7.307893 (lr=1.5303e-04) (hash(x)=21584083) +1220 train 7.671968 (lr=1.5300e-04) (hash(x)=23598625) +1221 train 7.373952 (lr=1.5297e-04) (hash(x)=26059939) +1222 train 7.622676 (lr=1.5293e-04) (hash(x)=25481982) +1223 train 7.483064 (lr=1.5290e-04) (hash(x)=26190337) +1224 train 7.649927 (lr=1.5286e-04) (hash(x)=28767755) +1225 train 7.316033 (lr=1.5283e-04) (hash(x)=23663918) +1226 train 7.440271 (lr=1.5279e-04) (hash(x)=21293227) +1227 train 7.436204 (lr=1.5276e-04) (hash(x)=22249019) +1228 train 7.514668 (lr=1.5273e-04) (hash(x)=26886529) +1229 train 7.329820 (lr=1.5269e-04) (hash(x)=25779849) +1230 train 7.450283 (lr=1.5266e-04) (hash(x)=26228964) +1231 train 7.395151 (lr=1.5262e-04) (hash(x)=23086289) +1232 train 7.501368 (lr=1.5259e-04) (hash(x)=23198922) +1233 train 7.495932 (lr=1.5255e-04) (hash(x)=27523941) +1234 train 7.304204 (lr=1.5252e-04) (hash(x)=24293992) +1235 train 8.017365 (lr=1.5248e-04) (hash(x)=28047044) +1236 train 7.494039 (lr=1.5245e-04) (hash(x)=23688671) +1237 train 7.359712 (lr=1.5241e-04) (hash(x)=25125498) +1238 train 7.274240 (lr=1.5238e-04) (hash(x)=21977292) +1239 train 7.354066 (lr=1.5234e-04) (hash(x)=23593875) +1240 train 7.279159 (lr=1.5231e-04) (hash(x)=22659030) +1241 train 7.375356 (lr=1.5227e-04) (hash(x)=25117733) +1242 train 7.408479 (lr=1.5224e-04) (hash(x)=22322808) +1243 train 7.402278 (lr=1.5221e-04) (hash(x)=26059735) +1244 train 7.330055 (lr=1.5217e-04) (hash(x)=22485526) +1245 train 7.250595 (lr=1.5214e-04) (hash(x)=23028679) +1246 train 7.258873 (lr=1.5210e-04) (hash(x)=22906035) +1247 train 7.169994 (lr=1.5207e-04) (hash(x)=22414190) +1248 train 7.436878 (lr=1.5203e-04) (hash(x)=26229624) +1249 train 7.236211 (lr=1.5200e-04) (hash(x)=22223137) +1250 val loss 7.3868 +1250 val perplexity 1614.5826 +1250 train 7.521718 (lr=1.5196e-04) (hash(x)=24911520) +1251 train 7.688907 (lr=1.5193e-04) (hash(x)=24204591) +1252 train 7.227714 (lr=1.5189e-04) (hash(x)=24379601) +1253 train 7.234966 (lr=1.5186e-04) (hash(x)=22922475) +1254 train 7.233139 (lr=1.5182e-04) (hash(x)=23426249) +1255 train 7.512888 (lr=1.5179e-04) (hash(x)=26758114) +1256 train 7.199277 (lr=1.5175e-04) (hash(x)=24027111) +1257 train 7.356938 (lr=1.5172e-04) (hash(x)=25358064) +1258 train 7.252005 (lr=1.5168e-04) (hash(x)=22571285) +1259 train 7.684648 (lr=1.5165e-04) (hash(x)=20084233) +1260 train 7.472848 (lr=1.5161e-04) (hash(x)=18786581) +1261 train 7.397480 (lr=1.5157e-04) (hash(x)=26395104) +1262 train 7.292069 (lr=1.5154e-04) (hash(x)=24212567) +1263 train 7.115512 (lr=1.5150e-04) (hash(x)=21563184) +1264 train 7.389923 (lr=1.5147e-04) (hash(x)=26490150) +1265 train 7.500992 (lr=1.5143e-04) (hash(x)=25207694) +1266 train 7.324358 (lr=1.5140e-04) (hash(x)=23914544) +1267 train 7.345559 (lr=1.5136e-04) (hash(x)=23861489) +1268 train 7.805377 (lr=1.5133e-04) (hash(x)=30714540) +1269 train 7.333426 (lr=1.5129e-04) (hash(x)=23471007) +1270 train 7.311679 (lr=1.5126e-04) (hash(x)=23244293) +1271 train 7.229019 (lr=1.5122e-04) (hash(x)=19218470) +1272 train 7.524076 (lr=1.5119e-04) (hash(x)=26965136) +1273 train 7.281098 (lr=1.5115e-04) (hash(x)=22944035) +1274 train 7.326662 (lr=1.5112e-04) (hash(x)=22002714) +1275 train 7.582010 (lr=1.5108e-04) (hash(x)=28469562) +1276 train 7.639334 (lr=1.5104e-04) (hash(x)=26889992) +1277 train 7.682693 (lr=1.5101e-04) (hash(x)=26452814) +1278 train 7.502457 (lr=1.5097e-04) (hash(x)=28397488) +1279 train 7.549074 (lr=1.5094e-04) (hash(x)=25588469) +1280 train 7.422833 (lr=1.5090e-04) (hash(x)=24833139) +1281 train 7.287665 (lr=1.5087e-04) (hash(x)=24788298) +1282 train 7.521955 (lr=1.5083e-04) (hash(x)=24979383) +1283 train 7.526622 (lr=1.5079e-04) (hash(x)=25236367) +1284 train 7.406352 (lr=1.5076e-04) (hash(x)=22638257) +1285 train 7.210414 (lr=1.5072e-04) (hash(x)=23069067) +1286 train 7.388083 (lr=1.5069e-04) (hash(x)=25133239) +1287 train 7.957331 (lr=1.5065e-04) (hash(x)=30433767) +1288 train 7.990219 (lr=1.5062e-04) (hash(x)=34319079) +1289 train 7.841287 (lr=1.5058e-04) (hash(x)=29268881) +1290 train 7.447751 (lr=1.5054e-04) (hash(x)=24528336) +1291 train 7.610641 (lr=1.5051e-04) (hash(x)=26302626) +1292 train 7.563288 (lr=1.5047e-04) (hash(x)=25479111) +1293 train 7.763779 (lr=1.5044e-04) (hash(x)=24749682) +1294 train 7.377793 (lr=1.5040e-04) (hash(x)=24111393) +1295 train 7.077870 (lr=1.5036e-04) (hash(x)=17851621) +1296 train 7.336449 (lr=1.5033e-04) (hash(x)=26463070) +1297 train 7.401776 (lr=1.5029e-04) (hash(x)=25620741) +1298 train 8.049170 (lr=1.5026e-04) (hash(x)=28225676) +1299 train 7.830363 (lr=1.5022e-04) (hash(x)=27028191) +1300 val loss 7.4017 +1300 val perplexity 1638.8141 +1300 train 7.455875 (lr=1.5018e-04) (hash(x)=29006516) +1301 train 7.579672 (lr=1.5015e-04) (hash(x)=27590299) +1302 train 7.713750 (lr=1.5011e-04) (hash(x)=28678983) +1303 train 7.578960 (lr=1.5008e-04) (hash(x)=25183690) +1304 train 7.117587 (lr=1.5004e-04) (hash(x)=19918097) +1305 train 7.892607 (lr=1.5000e-04) (hash(x)=31114252) +1306 train 7.852413 (lr=1.4997e-04) (hash(x)=30913255) +1307 train 7.448251 (lr=1.4993e-04) (hash(x)=26182243) +1308 train 7.670546 (lr=1.4990e-04) (hash(x)=27420668) +1309 train 7.899461 (lr=1.4986e-04) (hash(x)=30419908) +1310 train 7.787564 (lr=1.4982e-04) (hash(x)=29002281) +1311 train 7.479276 (lr=1.4979e-04) (hash(x)=27040642) +1312 train 7.380646 (lr=1.4975e-04) (hash(x)=26929300) +1313 train 7.474338 (lr=1.4971e-04) (hash(x)=26240761) +1314 train 7.528615 (lr=1.4968e-04) (hash(x)=27161876) +1315 train 7.361095 (lr=1.4964e-04) (hash(x)=24489607) +1316 train 7.774970 (lr=1.4961e-04) (hash(x)=27040115) +1317 train 7.390161 (lr=1.4957e-04) (hash(x)=25012872) +1318 train 7.034988 (lr=1.4953e-04) (hash(x)=20894720) +1319 train 7.107641 (lr=1.4950e-04) (hash(x)=22183303) +1320 train 7.439650 (lr=1.4946e-04) (hash(x)=26291778) +1321 train 7.513040 (lr=1.4942e-04) (hash(x)=27682633) +1322 train 7.276305 (lr=1.4939e-04) (hash(x)=26490892) +1323 train 7.727090 (lr=1.4935e-04) (hash(x)=28844646) +1324 train 8.047603 (lr=1.4931e-04) (hash(x)=29545304) +1325 train 8.215091 (lr=1.4928e-04) (hash(x)=31082070) +1326 train 7.797569 (lr=1.4924e-04) (hash(x)=27486316) +1327 train 7.709564 (lr=1.4920e-04) (hash(x)=27537063) +1328 train 7.472680 (lr=1.4917e-04) (hash(x)=26955557) +1329 train 7.477365 (lr=1.4913e-04) (hash(x)=26125988) +1330 train 7.490618 (lr=1.4909e-04) (hash(x)=22800125) +1331 train 7.642606 (lr=1.4906e-04) (hash(x)=25446686) +1332 train 7.698270 (lr=1.4902e-04) (hash(x)=28743746) +1333 train 7.455223 (lr=1.4898e-04) (hash(x)=19819857) +1334 train 7.193646 (lr=1.4895e-04) (hash(x)=23518628) +1335 train 7.182983 (lr=1.4891e-04) (hash(x)=19492832) +1336 train 7.368671 (lr=1.4887e-04) (hash(x)=24627720) +1337 train 7.306226 (lr=1.4884e-04) (hash(x)=23741214) +1338 train 7.384877 (lr=1.4880e-04) (hash(x)=25837914) +1339 train 7.292658 (lr=1.4876e-04) (hash(x)=25484958) +1340 train 7.294327 (lr=1.4873e-04) (hash(x)=23671284) +1341 train 7.406740 (lr=1.4869e-04) (hash(x)=25525370) +1342 train 7.503080 (lr=1.4865e-04) (hash(x)=26585300) +1343 train 7.543727 (lr=1.4861e-04) (hash(x)=25951629) +1344 train 7.769147 (lr=1.4858e-04) (hash(x)=28743135) +1345 train 7.950655 (lr=1.4854e-04) (hash(x)=28557663) +1346 train 7.257878 (lr=1.4850e-04) (hash(x)=22642751) +1347 train 7.173173 (lr=1.4847e-04) (hash(x)=23462798) +1348 train 7.084384 (lr=1.4843e-04) (hash(x)=24292328) +1349 train 7.426932 (lr=1.4839e-04) (hash(x)=27320280) +1350 val loss 7.3993 +1350 val perplexity 1634.8226 +1350 train 7.605401 (lr=1.4836e-04) (hash(x)=27352812) +1351 train 7.448262 (lr=1.4832e-04) (hash(x)=22408682) +1352 train 7.349602 (lr=1.4828e-04) (hash(x)=23144732) +1353 train 7.213642 (lr=1.4824e-04) (hash(x)=22230799) +1354 train 7.633768 (lr=1.4821e-04) (hash(x)=29747687) +1355 train 7.810034 (lr=1.4817e-04) (hash(x)=31317970) +1356 train 6.996724 (lr=1.4813e-04) (hash(x)=20131758) +1357 train 7.439384 (lr=1.4810e-04) (hash(x)=24020983) +1358 train 7.240242 (lr=1.4806e-04) (hash(x)=23998051) +1359 train 7.364231 (lr=1.4802e-04) (hash(x)=27633457) +1360 train 7.108997 (lr=1.4798e-04) (hash(x)=20155247) +1361 train 7.386079 (lr=1.4795e-04) (hash(x)=23766987) +1362 train 7.259378 (lr=1.4791e-04) (hash(x)=25960383) +1363 train 7.535922 (lr=1.4787e-04) (hash(x)=23729283) +1364 train 7.645210 (lr=1.4783e-04) (hash(x)=27775445) +1365 train 7.504736 (lr=1.4780e-04) (hash(x)=25975834) +1366 train 7.319509 (lr=1.4776e-04) (hash(x)=22765259) +1367 train 7.585331 (lr=1.4772e-04) (hash(x)=27635080) +1368 train 7.319412 (lr=1.4768e-04) (hash(x)=23848542) +1369 train 7.478768 (lr=1.4765e-04) (hash(x)=27181156) +1370 train 7.668689 (lr=1.4761e-04) (hash(x)=28321340) +1371 train 7.372209 (lr=1.4757e-04) (hash(x)=25918780) +1372 train 7.348845 (lr=1.4753e-04) (hash(x)=23338297) +1373 train 7.417761 (lr=1.4750e-04) (hash(x)=22370417) +1374 train 7.396553 (lr=1.4746e-04) (hash(x)=24272668) +1375 train 7.065300 (lr=1.4742e-04) (hash(x)=22287596) +1376 train 7.269707 (lr=1.4738e-04) (hash(x)=25257403) +1377 train 7.198593 (lr=1.4735e-04) (hash(x)=21584419) +1378 train 7.400073 (lr=1.4731e-04) (hash(x)=25318823) +1379 train 7.181337 (lr=1.4727e-04) (hash(x)=22694623) +1380 train 7.316409 (lr=1.4723e-04) (hash(x)=23743406) +1381 train 7.608844 (lr=1.4720e-04) (hash(x)=30820846) +1382 train 8.098662 (lr=1.4716e-04) (hash(x)=34639557) +1383 train 7.991581 (lr=1.4712e-04) (hash(x)=35895440) +1384 train 7.414304 (lr=1.4708e-04) (hash(x)=26304839) +1385 train 7.557826 (lr=1.4704e-04) (hash(x)=27058657) +1386 train 7.440121 (lr=1.4701e-04) (hash(x)=25209529) +1387 train 7.361537 (lr=1.4697e-04) (hash(x)=24298886) +1388 train 7.483954 (lr=1.4693e-04) (hash(x)=26200200) +1389 train 7.402832 (lr=1.4689e-04) (hash(x)=27303061) +1390 train 7.478223 (lr=1.4685e-04) (hash(x)=26531628) +1391 train 7.455566 (lr=1.4682e-04) (hash(x)=25888847) +1392 train 7.604826 (lr=1.4678e-04) (hash(x)=28924067) +1393 train 7.057113 (lr=1.4674e-04) (hash(x)=21267641) +1394 train 7.639089 (lr=1.4670e-04) (hash(x)=29419156) +1395 train 7.889897 (lr=1.4666e-04) (hash(x)=30860646) +1396 train 7.405603 (lr=1.4663e-04) (hash(x)=25744434) +1397 train 7.393079 (lr=1.4659e-04) (hash(x)=26881837) +1398 train 7.358358 (lr=1.4655e-04) (hash(x)=26676176) +1399 train 7.587442 (lr=1.4651e-04) (hash(x)=26518800) +1400 val loss 7.3816 +1400 val perplexity 1606.1206 +1400 train 7.327265 (lr=1.4647e-04) (hash(x)=25043238) +1401 train 7.606696 (lr=1.4644e-04) (hash(x)=25863277) +1402 train 7.253999 (lr=1.4640e-04) (hash(x)=24073623) +1403 train 7.349043 (lr=1.4636e-04) (hash(x)=25385523) +1404 train 7.409641 (lr=1.4632e-04) (hash(x)=24958112) +1405 train 7.300525 (lr=1.4628e-04) (hash(x)=23362519) +1406 train 7.566657 (lr=1.4625e-04) (hash(x)=29262616) +1407 train 7.922555 (lr=1.4621e-04) (hash(x)=37519283) +1408 train 8.168951 (lr=1.4617e-04) (hash(x)=33716930) +1409 train 7.440762 (lr=1.4613e-04) (hash(x)=23392584) +1410 train 7.877061 (lr=1.4609e-04) (hash(x)=22877779) +1411 train 8.201888 (lr=1.4605e-04) (hash(x)=20564397) +1412 train 7.637009 (lr=1.4602e-04) (hash(x)=24366235) +1413 train 7.528592 (lr=1.4598e-04) (hash(x)=27065499) +1414 train 7.348329 (lr=1.4594e-04) (hash(x)=26844114) +1415 train 7.476047 (lr=1.4590e-04) (hash(x)=25141945) +1416 train 7.705274 (lr=1.4586e-04) (hash(x)=28813116) +1417 train 7.485219 (lr=1.4582e-04) (hash(x)=25466598) +1418 train 7.374852 (lr=1.4579e-04) (hash(x)=22800032) +1419 train 7.448831 (lr=1.4575e-04) (hash(x)=22717866) +1420 train 7.940929 (lr=1.4571e-04) (hash(x)=28040763) +1421 train 8.076810 (lr=1.4567e-04) (hash(x)=29648992) +1422 train 8.020041 (lr=1.4563e-04) (hash(x)=31747228) +1423 train 7.464588 (lr=1.4559e-04) (hash(x)=28527939) +1424 train 7.381036 (lr=1.4555e-04) (hash(x)=21563992) +1425 train 7.326375 (lr=1.4552e-04) (hash(x)=25134784) +1426 train 7.537035 (lr=1.4548e-04) (hash(x)=28442823) +1427 train 8.113104 (lr=1.4544e-04) (hash(x)=32757059) +1428 train 7.280023 (lr=1.4540e-04) (hash(x)=24110500) +1429 train 7.380451 (lr=1.4536e-04) (hash(x)=24145729) +1430 train 7.401741 (lr=1.4532e-04) (hash(x)=23541086) +1431 train 7.299554 (lr=1.4528e-04) (hash(x)=21942471) +1432 train 7.393024 (lr=1.4524e-04) (hash(x)=24736836) +1433 train 7.536105 (lr=1.4521e-04) (hash(x)=25325444) +1434 train 7.565142 (lr=1.4517e-04) (hash(x)=25188954) +1435 train 8.089762 (lr=1.4513e-04) (hash(x)=24247339) +1436 train 7.492411 (lr=1.4509e-04) (hash(x)=23773363) +1437 train 7.286351 (lr=1.4505e-04) (hash(x)=24142989) +1438 train 7.274161 (lr=1.4501e-04) (hash(x)=24226952) +1439 train 7.508627 (lr=1.4497e-04) (hash(x)=24955630) +1440 train 7.488322 (lr=1.4493e-04) (hash(x)=24563233) +1441 train 7.580704 (lr=1.4490e-04) (hash(x)=25491335) +1442 train 7.880922 (lr=1.4486e-04) (hash(x)=33253763) +1443 train 7.334389 (lr=1.4482e-04) (hash(x)=21368780) +1444 train 7.361399 (lr=1.4478e-04) (hash(x)=26615500) +1445 train 7.605710 (lr=1.4474e-04) (hash(x)=27146278) +1446 train 7.449844 (lr=1.4470e-04) (hash(x)=25904861) +1447 train 7.309618 (lr=1.4466e-04) (hash(x)=25541230) +1448 train 7.466531 (lr=1.4462e-04) (hash(x)=25434227) +1449 train 7.414937 (lr=1.4458e-04) (hash(x)=25375355) +1450 val loss 7.4020 +1450 val perplexity 1639.3260 +1450 train 7.218420 (lr=1.4454e-04) (hash(x)=21921129) +1451 train 7.221015 (lr=1.4451e-04) (hash(x)=23098806) +1452 train 7.252233 (lr=1.4447e-04) (hash(x)=22000544) +1453 train 7.175858 (lr=1.4443e-04) (hash(x)=22061174) +1454 train 7.289450 (lr=1.4439e-04) (hash(x)=24326286) +1455 train 7.334671 (lr=1.4435e-04) (hash(x)=23501481) +1456 train 7.494937 (lr=1.4431e-04) (hash(x)=26397938) +1457 train 7.443459 (lr=1.4427e-04) (hash(x)=24656430) +1458 train 7.201092 (lr=1.4423e-04) (hash(x)=23494971) +1459 train 7.287453 (lr=1.4419e-04) (hash(x)=23802681) +1460 train 7.265587 (lr=1.4415e-04) (hash(x)=21990153) +1461 train 7.275005 (lr=1.4411e-04) (hash(x)=23496118) +1462 train 7.285678 (lr=1.4407e-04) (hash(x)=24233822) +1463 train 7.595113 (lr=1.4403e-04) (hash(x)=22754988) +1464 train 7.333261 (lr=1.4400e-04) (hash(x)=23116635) +1465 train 7.039969 (lr=1.4396e-04) (hash(x)=21461650) +1466 train 7.160092 (lr=1.4392e-04) (hash(x)=22274473) +1467 train 7.210860 (lr=1.4388e-04) (hash(x)=22183009) +1468 train 7.433721 (lr=1.4384e-04) (hash(x)=24972441) +1469 train 7.265553 (lr=1.4380e-04) (hash(x)=22300616) +1470 train 7.030926 (lr=1.4376e-04) (hash(x)=21443060) +1471 train 7.281987 (lr=1.4372e-04) (hash(x)=23475070) +1472 train 7.189775 (lr=1.4368e-04) (hash(x)=22316810) +1473 train 7.663053 (lr=1.4364e-04) (hash(x)=24508407) +1474 train 7.653170 (lr=1.4360e-04) (hash(x)=24603557) +1475 train 7.294121 (lr=1.4356e-04) (hash(x)=23359061) +1476 train 7.351516 (lr=1.4352e-04) (hash(x)=22950844) +1477 train 7.397207 (lr=1.4348e-04) (hash(x)=22588667) +1478 train 7.491673 (lr=1.4344e-04) (hash(x)=26083526) +1479 train 7.431568 (lr=1.4340e-04) (hash(x)=23609959) +1480 train 7.441867 (lr=1.4336e-04) (hash(x)=24088171) +1481 train 7.423363 (lr=1.4332e-04) (hash(x)=25394852) +1482 train 7.380618 (lr=1.4328e-04) (hash(x)=24503040) +1483 train 7.115622 (lr=1.4324e-04) (hash(x)=22408449) +1484 train 7.355466 (lr=1.4320e-04) (hash(x)=25069325) +1485 train 7.396360 (lr=1.4316e-04) (hash(x)=26947398) +1486 train 6.874043 (lr=1.4312e-04) (hash(x)=17527161) +1487 train 7.280221 (lr=1.4308e-04) (hash(x)=23441847) +1488 train 7.315000 (lr=1.4305e-04) (hash(x)=25592861) +1489 train 7.216486 (lr=1.4301e-04) (hash(x)=23101350) +1490 train 7.173053 (lr=1.4297e-04) (hash(x)=24201380) +1491 train 7.327096 (lr=1.4293e-04) (hash(x)=23676365) +1492 train 7.409801 (lr=1.4289e-04) (hash(x)=26668088) +1493 train 7.511028 (lr=1.4285e-04) (hash(x)=26488811) +1494 train 7.508279 (lr=1.4281e-04) (hash(x)=27248109) +1495 train 7.551595 (lr=1.4277e-04) (hash(x)=23096292) +1496 train 7.452370 (lr=1.4273e-04) (hash(x)=22101981) +1497 train 7.602063 (lr=1.4269e-04) (hash(x)=24512380) +1498 train 7.392681 (lr=1.4265e-04) (hash(x)=25367738) +1499 train 7.446680 (lr=1.4261e-04) (hash(x)=27706294) +1500 val loss 7.3998 +1500 val perplexity 1635.6593 +1500 train 7.526207 (lr=1.4257e-04) (hash(x)=24154026) +1501 train 7.258237 (lr=1.4253e-04) (hash(x)=21892472) +1502 train 7.297569 (lr=1.4249e-04) (hash(x)=23662543) +1503 train 7.381647 (lr=1.4245e-04) (hash(x)=26171093) +1504 train 7.410155 (lr=1.4241e-04) (hash(x)=25974292) +1505 train 7.272162 (lr=1.4237e-04) (hash(x)=23191101) +1506 train 7.489464 (lr=1.4233e-04) (hash(x)=26498861) +1507 train 7.989542 (lr=1.4229e-04) (hash(x)=34946941) +1508 train 7.581809 (lr=1.4225e-04) (hash(x)=25442719) +1509 train 7.461376 (lr=1.4221e-04) (hash(x)=25569942) +1510 train 7.178799 (lr=1.4216e-04) (hash(x)=21265828) +1511 train 7.110265 (lr=1.4212e-04) (hash(x)=20060838) +1512 train 7.302504 (lr=1.4208e-04) (hash(x)=22588251) +1513 train 7.263906 (lr=1.4204e-04) (hash(x)=24581020) +1514 train 7.270723 (lr=1.4200e-04) (hash(x)=21882493) +1515 train 7.188303 (lr=1.4196e-04) (hash(x)=21591702) +1516 train 7.243711 (lr=1.4192e-04) (hash(x)=19813285) +1517 train 7.328041 (lr=1.4188e-04) (hash(x)=21870012) +1518 train 7.336963 (lr=1.4184e-04) (hash(x)=26895498) +1519 train 7.376870 (lr=1.4180e-04) (hash(x)=25451055) +1520 train 7.407493 (lr=1.4176e-04) (hash(x)=25395865) +1521 train 6.904292 (lr=1.4172e-04) (hash(x)=18989695) +1522 train 6.791602 (lr=1.4168e-04) (hash(x)=17040678) +1523 train 6.900119 (lr=1.4164e-04) (hash(x)=18691455) +1524 train 6.977523 (lr=1.4160e-04) (hash(x)=19017167) +1525 train 7.301430 (lr=1.4156e-04) (hash(x)=22406503) +1526 train 7.479417 (lr=1.4152e-04) (hash(x)=23036138) +1527 train 7.333175 (lr=1.4148e-04) (hash(x)=24934792) +1528 train 7.366758 (lr=1.4144e-04) (hash(x)=22843127) +1529 train 7.321172 (lr=1.4140e-04) (hash(x)=24249677) +1530 train 7.239903 (lr=1.4136e-04) (hash(x)=23318555) +1531 train 7.217869 (lr=1.4132e-04) (hash(x)=23864361) +1532 train 7.127464 (lr=1.4128e-04) (hash(x)=20242060) +1533 train 7.290317 (lr=1.4124e-04) (hash(x)=21549554) +1534 train 7.094025 (lr=1.4119e-04) (hash(x)=21642024) +1535 train 7.609004 (lr=1.4115e-04) (hash(x)=25367597) +1536 train 7.766733 (lr=1.4111e-04) (hash(x)=27224144) +1537 train 7.279299 (lr=1.4107e-04) (hash(x)=24409290) +1538 train 7.358284 (lr=1.4103e-04) (hash(x)=24987180) +1539 train 7.275757 (lr=1.4099e-04) (hash(x)=27016702) +1540 train 7.539558 (lr=1.4095e-04) (hash(x)=25819636) +1541 train 7.453778 (lr=1.4091e-04) (hash(x)=25520453) +1542 train 7.229360 (lr=1.4087e-04) (hash(x)=23580496) +1543 train 7.441075 (lr=1.4083e-04) (hash(x)=25022148) +1544 train 7.421784 (lr=1.4079e-04) (hash(x)=25447327) +1545 train 7.416023 (lr=1.4075e-04) (hash(x)=25010319) +1546 train 7.337662 (lr=1.4071e-04) (hash(x)=25511777) +1547 train 7.315914 (lr=1.4066e-04) (hash(x)=24459012) +1548 train 7.361034 (lr=1.4062e-04) (hash(x)=25082785) +1549 train 7.472583 (lr=1.4058e-04) (hash(x)=26528670) +1550 val loss 7.3852 +1550 val perplexity 1611.8702 +1550 train 7.383036 (lr=1.4054e-04) (hash(x)=26684367) +1551 train 7.366609 (lr=1.4050e-04) (hash(x)=25431365) +1552 train 7.361838 (lr=1.4046e-04) (hash(x)=24802747) +1553 train 7.197690 (lr=1.4042e-04) (hash(x)=24229522) +1554 train 7.415332 (lr=1.4038e-04) (hash(x)=24757176) +1555 train 7.536582 (lr=1.4034e-04) (hash(x)=25958785) +1556 train 7.550923 (lr=1.4030e-04) (hash(x)=26810735) +1557 train 7.188891 (lr=1.4026e-04) (hash(x)=22882640) +1558 train 7.637128 (lr=1.4021e-04) (hash(x)=27220057) +1559 train 7.945251 (lr=1.4017e-04) (hash(x)=29307788) +1560 train 7.380236 (lr=1.4013e-04) (hash(x)=25214030) +1561 train 7.227865 (lr=1.4009e-04) (hash(x)=23167825) +1562 train 7.309335 (lr=1.4005e-04) (hash(x)=24658511) +1563 train 7.416421 (lr=1.4001e-04) (hash(x)=24965435) +1564 train 7.207849 (lr=1.3997e-04) (hash(x)=23620579) +1565 train 7.180063 (lr=1.3993e-04) (hash(x)=23772949) +1566 train 7.354115 (lr=1.3989e-04) (hash(x)=23807939) +1567 train 7.631569 (lr=1.3984e-04) (hash(x)=25651929) +1568 train 7.578684 (lr=1.3980e-04) (hash(x)=25549933) +1569 train 7.211101 (lr=1.3976e-04) (hash(x)=23146724) +1570 train 7.339584 (lr=1.3972e-04) (hash(x)=24099275) +1571 train 7.564903 (lr=1.3968e-04) (hash(x)=28451031) +1572 train 7.699568 (lr=1.3964e-04) (hash(x)=25488511) +1573 train 7.483116 (lr=1.3960e-04) (hash(x)=23796771) +1574 train 7.497318 (lr=1.3956e-04) (hash(x)=22642764) +1575 train 7.679776 (lr=1.3951e-04) (hash(x)=26312387) +1576 train 7.444170 (lr=1.3947e-04) (hash(x)=22486223) +1577 train 7.388458 (lr=1.3943e-04) (hash(x)=21257377) +1578 train 7.586707 (lr=1.3939e-04) (hash(x)=24328365) +1579 train 7.667770 (lr=1.3935e-04) (hash(x)=25326650) +1580 train 7.633135 (lr=1.3931e-04) (hash(x)=26484837) +1581 train 7.376204 (lr=1.3927e-04) (hash(x)=24605603) +1582 train 7.475263 (lr=1.3922e-04) (hash(x)=24668537) +1583 train 7.402109 (lr=1.3918e-04) (hash(x)=23804913) +1584 train 7.685543 (lr=1.3914e-04) (hash(x)=23615391) +1585 train 7.665790 (lr=1.3910e-04) (hash(x)=24322926) +1586 train 7.346795 (lr=1.3906e-04) (hash(x)=19753104) +1587 train 7.854593 (lr=1.3902e-04) (hash(x)=25537529) +1588 train 7.249599 (lr=1.3897e-04) (hash(x)=22835476) +1589 train 7.387717 (lr=1.3893e-04) (hash(x)=25707197) +1590 train 7.402559 (lr=1.3889e-04) (hash(x)=24191203) +1591 train 7.712860 (lr=1.3885e-04) (hash(x)=26115519) +1592 train 7.545999 (lr=1.3881e-04) (hash(x)=25781547) +1593 train 7.349330 (lr=1.3877e-04) (hash(x)=24850654) +1594 train 7.249651 (lr=1.3873e-04) (hash(x)=23300928) +1595 train 7.554707 (lr=1.3868e-04) (hash(x)=25494804) +1596 train 7.600279 (lr=1.3864e-04) (hash(x)=28169410) +1597 train 7.279120 (lr=1.3860e-04) (hash(x)=21972022) +1598 train 7.895786 (lr=1.3856e-04) (hash(x)=27687290) +1599 train 7.763127 (lr=1.3852e-04) (hash(x)=23210747) +1600 val loss 7.5128 +1600 val perplexity 1831.3694 +1600 train 7.758560 (lr=1.3847e-04) (hash(x)=20362758) +1601 train 7.508214 (lr=1.3843e-04) (hash(x)=17064773) +1602 train 7.578712 (lr=1.3839e-04) (hash(x)=17173694) +1603 train 7.604581 (lr=1.3835e-04) (hash(x)=15717069) +1604 train 7.675402 (lr=1.3831e-04) (hash(x)=15117973) +1605 train 7.497505 (lr=1.3827e-04) (hash(x)=16189636) +1606 train 7.413803 (lr=1.3822e-04) (hash(x)=16552095) +1607 train 7.256720 (lr=1.3818e-04) (hash(x)=18463712) +1608 train 7.399441 (lr=1.3814e-04) (hash(x)=17572155) +1609 train 7.390090 (lr=1.3810e-04) (hash(x)=19970072) +1610 train 7.380508 (lr=1.3806e-04) (hash(x)=20463871) +1611 train 7.455837 (lr=1.3801e-04) (hash(x)=20705573) +1612 train 7.372308 (lr=1.3797e-04) (hash(x)=24441646) +1613 train 7.571048 (lr=1.3793e-04) (hash(x)=22913147) +1614 train 7.707791 (lr=1.3789e-04) (hash(x)=23081598) +1615 train 7.390848 (lr=1.3785e-04) (hash(x)=23245699) +1616 train 7.404237 (lr=1.3780e-04) (hash(x)=23003072) +1617 train 7.675983 (lr=1.3776e-04) (hash(x)=27121904) +1618 train 7.403881 (lr=1.3772e-04) (hash(x)=25092305) +1619 train 7.438028 (lr=1.3768e-04) (hash(x)=23444521) +1620 train 7.462341 (lr=1.3764e-04) (hash(x)=22130531) +1621 train 7.164456 (lr=1.3759e-04) (hash(x)=20917937) +1622 train 7.336066 (lr=1.3755e-04) (hash(x)=22526838) +1623 train 7.522322 (lr=1.3751e-04) (hash(x)=21770300) +1624 train 8.718825 (lr=1.3747e-04) (hash(x)=22333537) +1625 train 8.733803 (lr=1.3743e-04) (hash(x)=24642519) +1626 train 7.819534 (lr=1.3738e-04) (hash(x)=25199038) +1627 train 7.546631 (lr=1.3734e-04) (hash(x)=23334569) +1628 train 7.413042 (lr=1.3730e-04) (hash(x)=23785360) +1629 train 7.017786 (lr=1.3726e-04) (hash(x)=21796200) +1630 train 7.078978 (lr=1.3721e-04) (hash(x)=22389081) +1631 train 7.438049 (lr=1.3717e-04) (hash(x)=25387532) +1632 train 6.915871 (lr=1.3713e-04) (hash(x)=17247578) +1633 train 7.353748 (lr=1.3709e-04) (hash(x)=22203733) +1634 train 7.600593 (lr=1.3704e-04) (hash(x)=24387455) +1635 train 8.146228 (lr=1.3700e-04) (hash(x)=29466743) +1636 train 7.420878 (lr=1.3696e-04) (hash(x)=25354152) +1637 train 7.512414 (lr=1.3692e-04) (hash(x)=21756102) +1638 train 7.446372 (lr=1.3688e-04) (hash(x)=23544029) +1639 train 7.606544 (lr=1.3683e-04) (hash(x)=27718703) +1640 train 7.561157 (lr=1.3679e-04) (hash(x)=25697138) +1641 train 7.370125 (lr=1.3675e-04) (hash(x)=22978681) +1642 train 8.002187 (lr=1.3671e-04) (hash(x)=29527067) +1643 train 7.055324 (lr=1.3666e-04) (hash(x)=17631973) +1644 train 7.509999 (lr=1.3662e-04) (hash(x)=24860172) +1645 train 7.806194 (lr=1.3658e-04) (hash(x)=27947891) +1646 train 7.495622 (lr=1.3654e-04) (hash(x)=23819556) +1647 train 7.526451 (lr=1.3649e-04) (hash(x)=27661052) +1648 train 7.291294 (lr=1.3645e-04) (hash(x)=23014209) +1649 train 7.203379 (lr=1.3641e-04) (hash(x)=23061452) +1650 val loss 7.4728 +1650 val perplexity 1759.5924 +1650 train 7.333365 (lr=1.3637e-04) (hash(x)=21949051) +1651 train 7.386749 (lr=1.3632e-04) (hash(x)=22244096) +1652 train 7.414212 (lr=1.3628e-04) (hash(x)=25997585) +1653 train 7.473875 (lr=1.3624e-04) (hash(x)=25389713) +1654 train 7.361176 (lr=1.3620e-04) (hash(x)=24390520) +1655 train 7.629933 (lr=1.3615e-04) (hash(x)=26538928) +1656 train 7.571353 (lr=1.3611e-04) (hash(x)=28708088) +1657 train 7.715378 (lr=1.3607e-04) (hash(x)=25685569) +1658 train 7.205423 (lr=1.3602e-04) (hash(x)=22163531) +1659 train 7.397973 (lr=1.3598e-04) (hash(x)=26256802) +1660 train 7.858312 (lr=1.3594e-04) (hash(x)=30016026) +1661 train 7.437068 (lr=1.3590e-04) (hash(x)=24412323) +1662 train 7.486185 (lr=1.3585e-04) (hash(x)=24722307) +1663 train 7.293050 (lr=1.3581e-04) (hash(x)=21772654) +1664 train 7.255020 (lr=1.3577e-04) (hash(x)=24984527) +1665 train 7.443353 (lr=1.3572e-04) (hash(x)=25456825) +1666 train 7.790140 (lr=1.3568e-04) (hash(x)=24383976) +1667 train 7.705901 (lr=1.3564e-04) (hash(x)=25026277) +1668 train 7.610121 (lr=1.3560e-04) (hash(x)=28121715) +1669 train 7.620229 (lr=1.3555e-04) (hash(x)=26855439) +1670 train 7.685052 (lr=1.3551e-04) (hash(x)=33370924) +1671 train 7.517990 (lr=1.3547e-04) (hash(x)=26263254) +1672 train 7.990524 (lr=1.3542e-04) (hash(x)=29958158) +1673 train 7.256316 (lr=1.3538e-04) (hash(x)=21917396) +1674 train 7.440012 (lr=1.3534e-04) (hash(x)=24196295) +1675 train 7.458837 (lr=1.3530e-04) (hash(x)=24726314) +1676 train 7.229211 (lr=1.3525e-04) (hash(x)=22137742) +1677 train 7.346698 (lr=1.3521e-04) (hash(x)=24375100) +1678 train 7.294734 (lr=1.3517e-04) (hash(x)=23965039) +1679 train 7.367982 (lr=1.3512e-04) (hash(x)=23552356) +1680 train 7.331838 (lr=1.3508e-04) (hash(x)=26136969) +1681 train 7.617671 (lr=1.3504e-04) (hash(x)=25343112) +1682 train 7.237329 (lr=1.3499e-04) (hash(x)=22831508) +1683 train 7.563323 (lr=1.3495e-04) (hash(x)=26699819) +1684 train 7.683118 (lr=1.3491e-04) (hash(x)=25435504) +1685 train 7.855708 (lr=1.3487e-04) (hash(x)=25218858) +1686 train 8.567866 (lr=1.3482e-04) (hash(x)=25664448) +1687 train 7.500726 (lr=1.3478e-04) (hash(x)=22707141) +1688 train 7.687224 (lr=1.3474e-04) (hash(x)=28001383) +1689 train 7.930885 (lr=1.3469e-04) (hash(x)=29168269) +1690 train 7.880753 (lr=1.3465e-04) (hash(x)=29637522) +1691 train 7.890341 (lr=1.3461e-04) (hash(x)=25676149) +1692 train 7.311974 (lr=1.3456e-04) (hash(x)=20919831) +1693 train 7.467350 (lr=1.3452e-04) (hash(x)=24324401) +1694 train 7.551843 (lr=1.3448e-04) (hash(x)=26862625) +1695 train 7.948521 (lr=1.3443e-04) (hash(x)=34234481) +1696 train 7.540195 (lr=1.3439e-04) (hash(x)=27415195) +1697 train 7.295190 (lr=1.3435e-04) (hash(x)=24511386) +1698 train 7.472528 (lr=1.3430e-04) (hash(x)=26904299) +1699 train 7.313019 (lr=1.3426e-04) (hash(x)=25401624) +1700 val loss 7.4565 +1700 val perplexity 1731.0804 +1700 train 7.395326 (lr=1.3422e-04) (hash(x)=26498489) +1701 train 7.383740 (lr=1.3417e-04) (hash(x)=22340685) +1702 train 7.487051 (lr=1.3413e-04) (hash(x)=26396757) +1703 train 8.088147 (lr=1.3409e-04) (hash(x)=35008670) +1704 train 7.861502 (lr=1.3404e-04) (hash(x)=31782020) +1705 train 7.712422 (lr=1.3400e-04) (hash(x)=29662286) +1706 train 7.889362 (lr=1.3396e-04) (hash(x)=34215782) +1707 train 7.395456 (lr=1.3391e-04) (hash(x)=25682280) +1708 train 7.672348 (lr=1.3387e-04) (hash(x)=27109048) +1709 train 7.707414 (lr=1.3383e-04) (hash(x)=27686498) +1710 train 7.536659 (lr=1.3378e-04) (hash(x)=24247565) +1711 train 7.525104 (lr=1.3374e-04) (hash(x)=25891543) +1712 train 7.611343 (lr=1.3370e-04) (hash(x)=26436778) +1713 train 7.243785 (lr=1.3365e-04) (hash(x)=22538881) +1714 train 7.168606 (lr=1.3361e-04) (hash(x)=21993512) +1715 train 7.694753 (lr=1.3356e-04) (hash(x)=25962407) +1716 train 7.456436 (lr=1.3352e-04) (hash(x)=24130284) +1717 train 7.332945 (lr=1.3348e-04) (hash(x)=24819073) +1718 train 7.191045 (lr=1.3343e-04) (hash(x)=23496648) +1719 train 7.253601 (lr=1.3339e-04) (hash(x)=21971224) +1720 train 7.153931 (lr=1.3335e-04) (hash(x)=21498081) +1721 train 7.190876 (lr=1.3330e-04) (hash(x)=20951317) +1722 train 7.774101 (lr=1.3326e-04) (hash(x)=28848134) +1723 train 7.795555 (lr=1.3322e-04) (hash(x)=30838142) +1724 train 7.750778 (lr=1.3317e-04) (hash(x)=28844392) +1725 train 7.328674 (lr=1.3313e-04) (hash(x)=23102419) +1726 train 7.349519 (lr=1.3308e-04) (hash(x)=22374479) +1727 train 7.647438 (lr=1.3304e-04) (hash(x)=27312186) +1728 train 7.956415 (lr=1.3300e-04) (hash(x)=34362559) +1729 train 7.851657 (lr=1.3295e-04) (hash(x)=30920030) +1730 train 7.267101 (lr=1.3291e-04) (hash(x)=23684126) +1731 train 7.496730 (lr=1.3287e-04) (hash(x)=23657081) +1732 train 7.661594 (lr=1.3282e-04) (hash(x)=28463299) +1733 train 7.921983 (lr=1.3278e-04) (hash(x)=35351214) +1734 train 7.523563 (lr=1.3273e-04) (hash(x)=28855662) +1735 train 7.062561 (lr=1.3269e-04) (hash(x)=22163749) +1736 train 7.055109 (lr=1.3265e-04) (hash(x)=22024585) +1737 train 7.286463 (lr=1.3260e-04) (hash(x)=24629160) +1738 train 7.377766 (lr=1.3256e-04) (hash(x)=25220941) +1739 train 7.344894 (lr=1.3251e-04) (hash(x)=24829818) +1740 train 7.643913 (lr=1.3247e-04) (hash(x)=28453898) +1741 train 7.667316 (lr=1.3243e-04) (hash(x)=25424550) +1742 train 7.320118 (lr=1.3238e-04) (hash(x)=23437814) +1743 train 7.381351 (lr=1.3234e-04) (hash(x)=25942888) +1744 train 7.384551 (lr=1.3229e-04) (hash(x)=24503801) +1745 train 7.709043 (lr=1.3225e-04) (hash(x)=26418501) +1746 train 7.575682 (lr=1.3221e-04) (hash(x)=27177691) +1747 train 7.286253 (lr=1.3216e-04) (hash(x)=23785671) +1748 train 7.705902 (lr=1.3212e-04) (hash(x)=27362772) +1749 train 7.506738 (lr=1.3207e-04) (hash(x)=25097859) +1750 val loss 7.4489 +1750 val perplexity 1718.0481 +1750 train 7.409838 (lr=1.3203e-04) (hash(x)=24662466) +1751 train 7.336954 (lr=1.3199e-04) (hash(x)=25493916) +1752 train 7.432468 (lr=1.3194e-04) (hash(x)=24655868) +1753 train 7.721800 (lr=1.3190e-04) (hash(x)=19819210) +1754 train 7.295093 (lr=1.3185e-04) (hash(x)=21377155) +1755 train 8.136368 (lr=1.3181e-04) (hash(x)=28618702) +1756 train 8.020695 (lr=1.3177e-04) (hash(x)=27324953) +1757 train 7.733412 (lr=1.3172e-04) (hash(x)=29707907) +1758 train 7.486028 (lr=1.3168e-04) (hash(x)=24485921) +1759 train 7.597549 (lr=1.3163e-04) (hash(x)=24289951) +1760 train 7.297372 (lr=1.3159e-04) (hash(x)=22496716) +1761 train 7.442400 (lr=1.3154e-04) (hash(x)=25147026) +1762 train 7.529433 (lr=1.3150e-04) (hash(x)=26851828) +1763 train 7.504590 (lr=1.3146e-04) (hash(x)=26331486) +1764 train 7.314538 (lr=1.3141e-04) (hash(x)=24383054) +1765 train 7.596138 (lr=1.3137e-04) (hash(x)=25885126) +1766 train 7.483125 (lr=1.3132e-04) (hash(x)=25848470) +1767 train 7.299249 (lr=1.3128e-04) (hash(x)=23648671) +1768 train 7.264209 (lr=1.3123e-04) (hash(x)=23168674) +1769 train 7.130929 (lr=1.3119e-04) (hash(x)=20252079) +1770 train 7.340314 (lr=1.3115e-04) (hash(x)=23914287) +1771 train 7.694432 (lr=1.3110e-04) (hash(x)=27292797) +1772 train 6.868396 (lr=1.3106e-04) (hash(x)=16175151) +1773 train 6.993863 (lr=1.3101e-04) (hash(x)=18317379) +1774 train 7.370420 (lr=1.3097e-04) (hash(x)=24464271) +1775 train 7.296094 (lr=1.3092e-04) (hash(x)=24992055) +1776 train 8.032245 (lr=1.3088e-04) (hash(x)=26032451) +1777 train 7.762984 (lr=1.3083e-04) (hash(x)=24734221) +1778 train 7.702712 (lr=1.3079e-04) (hash(x)=25413430) +1779 train 7.551206 (lr=1.3075e-04) (hash(x)=24398330) +1780 train 7.401190 (lr=1.3070e-04) (hash(x)=24568049) +1781 train 7.259307 (lr=1.3066e-04) (hash(x)=23573984) +1782 train 7.499181 (lr=1.3061e-04) (hash(x)=27338410) +1783 train 7.469513 (lr=1.3057e-04) (hash(x)=26005549) +1784 train 7.303758 (lr=1.3052e-04) (hash(x)=24332331) +1785 train 7.154575 (lr=1.3048e-04) (hash(x)=22583878) +1786 train 7.323323 (lr=1.3043e-04) (hash(x)=24599113) +1787 train 7.766295 (lr=1.3039e-04) (hash(x)=30259737) +1788 train 7.566220 (lr=1.3035e-04) (hash(x)=26504237) +1789 train 7.413300 (lr=1.3030e-04) (hash(x)=25196470) +1790 train 7.316645 (lr=1.3026e-04) (hash(x)=23607871) +1791 train 7.209989 (lr=1.3021e-04) (hash(x)=21046554) +1792 train 7.478430 (lr=1.3017e-04) (hash(x)=27285635) +1793 train 7.453479 (lr=1.3012e-04) (hash(x)=25454371) +1794 train 7.533142 (lr=1.3008e-04) (hash(x)=26486575) +1795 train 7.028943 (lr=1.3003e-04) (hash(x)=18773877) +1796 train 7.170099 (lr=1.2999e-04) (hash(x)=22506761) +1797 train 7.481285 (lr=1.2994e-04) (hash(x)=24645168) +1798 train 7.539289 (lr=1.2990e-04) (hash(x)=25046236) +1799 train 7.607147 (lr=1.2985e-04) (hash(x)=26321539) +1800 val loss 7.4412 +1800 val perplexity 1704.8505 +1800 train 7.392766 (lr=1.2981e-04) (hash(x)=24602494) +1801 train 7.521611 (lr=1.2976e-04) (hash(x)=25722713) +1802 train 7.286321 (lr=1.2972e-04) (hash(x)=23711219) +1803 train 7.379313 (lr=1.2967e-04) (hash(x)=22850804) +1804 train 7.719003 (lr=1.2963e-04) (hash(x)=25829388) +1805 train 7.233034 (lr=1.2958e-04) (hash(x)=22503524) +1806 train 7.540718 (lr=1.2954e-04) (hash(x)=26669453) +1807 train 7.418415 (lr=1.2950e-04) (hash(x)=27807872) +1808 train 7.450583 (lr=1.2945e-04) (hash(x)=23543560) +1809 train 7.558151 (lr=1.2941e-04) (hash(x)=25845590) +1810 train 7.347009 (lr=1.2936e-04) (hash(x)=23026635) +1811 train 7.300540 (lr=1.2932e-04) (hash(x)=25545137) +1812 train 7.813961 (lr=1.2927e-04) (hash(x)=27746841) +1813 train 7.194411 (lr=1.2923e-04) (hash(x)=25471231) +1814 train 7.326602 (lr=1.2918e-04) (hash(x)=24333204) +1815 train 7.148338 (lr=1.2914e-04) (hash(x)=21555364) +1816 train 7.362077 (lr=1.2909e-04) (hash(x)=26317977) +1817 train 7.458373 (lr=1.2905e-04) (hash(x)=24474988) +1818 train 7.109764 (lr=1.2900e-04) (hash(x)=21975953) +1819 train 7.783544 (lr=1.2896e-04) (hash(x)=27243798) +1820 train 7.358251 (lr=1.2891e-04) (hash(x)=25097367) +1821 train 7.275454 (lr=1.2887e-04) (hash(x)=24419085) +1822 train 7.223833 (lr=1.2882e-04) (hash(x)=23058837) +1823 train 7.380766 (lr=1.2878e-04) (hash(x)=26325324) +1824 train 7.097527 (lr=1.2873e-04) (hash(x)=20581023) +1825 train 7.424585 (lr=1.2869e-04) (hash(x)=24822111) +1826 train 7.196410 (lr=1.2864e-04) (hash(x)=24336304) +1827 train 7.387208 (lr=1.2860e-04) (hash(x)=26228728) +1828 train 7.528440 (lr=1.2855e-04) (hash(x)=26445781) +1829 train 7.572623 (lr=1.2850e-04) (hash(x)=24707042) +1830 train 7.852676 (lr=1.2846e-04) (hash(x)=27882744) +1831 train 7.346957 (lr=1.2841e-04) (hash(x)=24956294) +1832 train 7.149955 (lr=1.2837e-04) (hash(x)=20984728) +1833 train 7.202185 (lr=1.2832e-04) (hash(x)=23424737) +1834 train 7.558321 (lr=1.2828e-04) (hash(x)=26207120) +1835 train 7.617296 (lr=1.2823e-04) (hash(x)=25592289) +1836 train 7.248993 (lr=1.2819e-04) (hash(x)=24326649) +1837 train 7.382863 (lr=1.2814e-04) (hash(x)=26826109) +1838 train 7.367568 (lr=1.2810e-04) (hash(x)=24759294) +1839 train 7.375408 (lr=1.2805e-04) (hash(x)=24429389) +1840 train 7.334877 (lr=1.2801e-04) (hash(x)=25537519) +1841 train 7.304898 (lr=1.2796e-04) (hash(x)=24747421) +1842 train 7.206577 (lr=1.2792e-04) (hash(x)=23079065) +1843 train 7.619887 (lr=1.2787e-04) (hash(x)=28733708) +1844 train 7.366482 (lr=1.2783e-04) (hash(x)=23937742) +1845 train 7.649822 (lr=1.2778e-04) (hash(x)=29704803) +1846 train 7.827521 (lr=1.2774e-04) (hash(x)=34617155) +1847 train 7.551628 (lr=1.2769e-04) (hash(x)=27929846) +1848 train 7.888748 (lr=1.2764e-04) (hash(x)=28280878) +1849 train 6.926709 (lr=1.2760e-04) (hash(x)=18961171) +1850 val loss 7.3999 +1850 val perplexity 1635.7412 +1850 train 7.450670 (lr=1.2755e-04) (hash(x)=27146015) +1851 train 7.263853 (lr=1.2751e-04) (hash(x)=22417476) +1852 train 7.429771 (lr=1.2746e-04) (hash(x)=24583152) +1853 train 7.475824 (lr=1.2742e-04) (hash(x)=26364120) +1854 train 7.627858 (lr=1.2737e-04) (hash(x)=25946767) +1855 train 7.494011 (lr=1.2733e-04) (hash(x)=25282897) +1856 train 7.419560 (lr=1.2728e-04) (hash(x)=25154557) +1857 train 7.119820 (lr=1.2724e-04) (hash(x)=22082503) +1858 train 7.151616 (lr=1.2719e-04) (hash(x)=23974606) +1859 train 7.273813 (lr=1.2714e-04) (hash(x)=22278062) +1860 train 7.218425 (lr=1.2710e-04) (hash(x)=19509639) +1861 train 7.480034 (lr=1.2705e-04) (hash(x)=24271468) +1862 train 7.104110 (lr=1.2701e-04) (hash(x)=21943809) +1863 train 7.311009 (lr=1.2696e-04) (hash(x)=26802508) +1864 train 7.861012 (lr=1.2692e-04) (hash(x)=34178409) +1865 train 8.006653 (lr=1.2687e-04) (hash(x)=33468379) +1866 train 7.246926 (lr=1.2683e-04) (hash(x)=22109262) +1867 train 6.971401 (lr=1.2678e-04) (hash(x)=22094832) +1868 train 7.245398 (lr=1.2673e-04) (hash(x)=24016953) +1869 train 7.516101 (lr=1.2669e-04) (hash(x)=26759850) +1870 train 7.314701 (lr=1.2664e-04) (hash(x)=23570779) +1871 train 7.791498 (lr=1.2660e-04) (hash(x)=28390416) +1872 train 7.793832 (lr=1.2655e-04) (hash(x)=26215770) +1873 train 7.648577 (lr=1.2651e-04) (hash(x)=22727956) +1874 train 7.449919 (lr=1.2646e-04) (hash(x)=21304587) +1875 train 7.776413 (lr=1.2641e-04) (hash(x)=26379331) +1876 train 7.873510 (lr=1.2637e-04) (hash(x)=25252419) +1877 train 7.690436 (lr=1.2632e-04) (hash(x)=25048158) +1878 train 7.590439 (lr=1.2628e-04) (hash(x)=23588991) +1879 train 7.606351 (lr=1.2623e-04) (hash(x)=26292451) +1880 train 7.474908 (lr=1.2619e-04) (hash(x)=23617086) +1881 train 7.360271 (lr=1.2614e-04) (hash(x)=23336031) +1882 train 7.380903 (lr=1.2609e-04) (hash(x)=19198742) +1883 train 8.087051 (lr=1.2605e-04) (hash(x)=26301866) +1884 train 7.988297 (lr=1.2600e-04) (hash(x)=30114703) +1885 train 7.487477 (lr=1.2596e-04) (hash(x)=26687040) +1886 train 7.330170 (lr=1.2591e-04) (hash(x)=25810717) +1887 train 7.141123 (lr=1.2587e-04) (hash(x)=22915344) +1888 train 7.485368 (lr=1.2582e-04) (hash(x)=27046189) +1889 train 7.107167 (lr=1.2577e-04) (hash(x)=19831900) +1890 train 7.514509 (lr=1.2573e-04) (hash(x)=27786987) +1891 train 7.333086 (lr=1.2568e-04) (hash(x)=25448318) +1892 train 7.361098 (lr=1.2564e-04) (hash(x)=25166953) +1893 train 7.326496 (lr=1.2559e-04) (hash(x)=24993116) +1894 train 7.403059 (lr=1.2554e-04) (hash(x)=25748002) +1895 train 7.632479 (lr=1.2550e-04) (hash(x)=24744383) +1896 train 7.360042 (lr=1.2545e-04) (hash(x)=25560120) +1897 train 7.178867 (lr=1.2541e-04) (hash(x)=23731849) +1898 train 7.223453 (lr=1.2536e-04) (hash(x)=24115851) +1899 train 7.282697 (lr=1.2531e-04) (hash(x)=22835201) +1900 val loss 7.3988 +1900 val perplexity 1634.0231 +1900 train 7.058782 (lr=1.2527e-04) (hash(x)=21927896) +1901 train 7.438712 (lr=1.2522e-04) (hash(x)=24652361) +1902 train 7.599507 (lr=1.2518e-04) (hash(x)=27332405) +1903 train 7.404964 (lr=1.2513e-04) (hash(x)=26284678) +1904 train 7.333180 (lr=1.2508e-04) (hash(x)=23441305) +1905 train 7.433540 (lr=1.2504e-04) (hash(x)=27522881) +1906 train 7.486556 (lr=1.2499e-04) (hash(x)=25521191) +1907 train 7.272209 (lr=1.2495e-04) (hash(x)=24745936) +1908 train 7.170990 (lr=1.2490e-04) (hash(x)=21653364) +1909 train 7.210524 (lr=1.2485e-04) (hash(x)=21973969) +1910 train 7.214540 (lr=1.2481e-04) (hash(x)=24318192) +1911 train 7.150622 (lr=1.2476e-04) (hash(x)=21654269) +1912 train 7.210755 (lr=1.2472e-04) (hash(x)=24142904) +1913 train 7.131275 (lr=1.2467e-04) (hash(x)=21708739) +1914 train 7.348971 (lr=1.2462e-04) (hash(x)=22937923) +1915 train 7.882193 (lr=1.2458e-04) (hash(x)=32387999) +1916 train 8.075658 (lr=1.2453e-04) (hash(x)=28958671) +1917 train 8.107440 (lr=1.2448e-04) (hash(x)=32662682) +1918 train 8.016494 (lr=1.2444e-04) (hash(x)=31364539) +1919 train 8.131250 (lr=1.2439e-04) (hash(x)=29466268) +1920 train 8.096156 (lr=1.2435e-04) (hash(x)=31407564) +1921 train 7.976552 (lr=1.2430e-04) (hash(x)=28372973) +1922 train 8.076553 (lr=1.2425e-04) (hash(x)=28620993) +1923 train 8.110916 (lr=1.2421e-04) (hash(x)=30736727) +1924 train 8.007712 (lr=1.2416e-04) (hash(x)=30370374) +1925 train 7.955924 (lr=1.2411e-04) (hash(x)=29935562) +1926 train 7.932941 (lr=1.2407e-04) (hash(x)=30528627) +1927 train 8.003509 (lr=1.2402e-04) (hash(x)=32616762) +1928 train 7.836560 (lr=1.2398e-04) (hash(x)=29150044) +1929 train 7.985418 (lr=1.2393e-04) (hash(x)=32861403) +1930 train 7.923763 (lr=1.2388e-04) (hash(x)=31053918) +1931 train 7.843915 (lr=1.2384e-04) (hash(x)=29358578) +1932 train 7.960120 (lr=1.2379e-04) (hash(x)=31521292) +1933 train 7.879478 (lr=1.2374e-04) (hash(x)=31218966) +1934 train 7.888797 (lr=1.2370e-04) (hash(x)=31811872) +1935 train 8.089240 (lr=1.2365e-04) (hash(x)=32201138) +1936 train 7.787080 (lr=1.2360e-04) (hash(x)=28631348) +1937 train 7.890153 (lr=1.2356e-04) (hash(x)=30545133) +1938 train 7.945061 (lr=1.2351e-04) (hash(x)=32136080) +1939 train 8.005196 (lr=1.2347e-04) (hash(x)=30041621) +1940 train 7.790315 (lr=1.2342e-04) (hash(x)=30537181) +1941 train 7.790654 (lr=1.2337e-04) (hash(x)=30371023) +1942 train 7.937543 (lr=1.2333e-04) (hash(x)=30734634) +1943 train 7.876827 (lr=1.2328e-04) (hash(x)=33683468) +1944 train 7.936390 (lr=1.2323e-04) (hash(x)=30472451) +1945 train 7.783542 (lr=1.2319e-04) (hash(x)=29809830) +1946 train 7.656366 (lr=1.2314e-04) (hash(x)=26077593) +1947 train 7.645034 (lr=1.2309e-04) (hash(x)=26837755) +1948 train 7.606746 (lr=1.2305e-04) (hash(x)=23910920) +1949 train 7.563732 (lr=1.2300e-04) (hash(x)=26084089) +1950 val loss 7.5113 +1950 val perplexity 1828.5012 +1950 train 7.701028 (lr=1.2295e-04) (hash(x)=26963533) +1951 train 7.590087 (lr=1.2291e-04) (hash(x)=27498125) +1952 train 7.748844 (lr=1.2286e-04) (hash(x)=29512508) +1953 train 8.048329 (lr=1.2281e-04) (hash(x)=34478395) +1954 train 7.643875 (lr=1.2277e-04) (hash(x)=25357046) +1955 train 7.457434 (lr=1.2272e-04) (hash(x)=22372507) +1956 train 7.401696 (lr=1.2267e-04) (hash(x)=24501779) +1957 train 7.491759 (lr=1.2263e-04) (hash(x)=25638879) +1958 train 7.296669 (lr=1.2258e-04) (hash(x)=24243109) +1959 train 7.236905 (lr=1.2253e-04) (hash(x)=25164318) +1960 train 7.401086 (lr=1.2249e-04) (hash(x)=24139533) +1961 train 7.428868 (lr=1.2244e-04) (hash(x)=27271900) +1962 train 7.260924 (lr=1.2239e-04) (hash(x)=24869232) +1963 train 7.484505 (lr=1.2235e-04) (hash(x)=26562947) +1964 train 7.380402 (lr=1.2230e-04) (hash(x)=26477326) +1965 train 7.480206 (lr=1.2225e-04) (hash(x)=24917192) +1966 train 7.277405 (lr=1.2221e-04) (hash(x)=23110147) +1967 train 7.357511 (lr=1.2216e-04) (hash(x)=25690221) +1968 train 7.775455 (lr=1.2211e-04) (hash(x)=26999273) +1969 train 7.443129 (lr=1.2207e-04) (hash(x)=24807841) +1970 train 7.333606 (lr=1.2202e-04) (hash(x)=23918831) +1971 train 7.242178 (lr=1.2197e-04) (hash(x)=21947305) +1972 train 7.340309 (lr=1.2193e-04) (hash(x)=22874486) +1973 train 7.249237 (lr=1.2188e-04) (hash(x)=22195089) +1974 train 7.346650 (lr=1.2183e-04) (hash(x)=25345359) +1975 train 7.484455 (lr=1.2179e-04) (hash(x)=29031550) +1976 train 7.472374 (lr=1.2174e-04) (hash(x)=29947423) +1977 train 7.646382 (lr=1.2169e-04) (hash(x)=29395823) +1978 train 7.392028 (lr=1.2165e-04) (hash(x)=26968216) +1979 train 7.468187 (lr=1.2160e-04) (hash(x)=26551589) +1980 train 7.439298 (lr=1.2155e-04) (hash(x)=25657210) +1981 train 7.383871 (lr=1.2151e-04) (hash(x)=23689487) +1982 train 7.490170 (lr=1.2146e-04) (hash(x)=25744240) +1983 train 7.509051 (lr=1.2141e-04) (hash(x)=24094093) +1984 train 7.218770 (lr=1.2137e-04) (hash(x)=21724872) +1985 train 7.253622 (lr=1.2132e-04) (hash(x)=24106453) +1986 train 7.305767 (lr=1.2127e-04) (hash(x)=25004577) +1987 train 7.322614 (lr=1.2122e-04) (hash(x)=23639076) +1988 train 7.619757 (lr=1.2118e-04) (hash(x)=29408797) +1989 train 7.269443 (lr=1.2113e-04) (hash(x)=25107314) +1990 train 9.949356 (lr=1.2108e-04) (hash(x)=49896019) +1991 train 11.542602 (lr=1.2104e-04) (hash(x)=61455960) +1992 train 11.286455 (lr=1.2099e-04) (hash(x)=63788199) +1993 train 11.394973 (lr=1.2094e-04) (hash(x)=63899424) +1994 train 11.144141 (lr=1.2090e-04) (hash(x)=66412689) +1995 train 10.779576 (lr=1.2085e-04) (hash(x)=65636572) +1996 train 10.973929 (lr=1.2080e-04) (hash(x)=69649789) +1997 train 10.753806 (lr=1.2075e-04) (hash(x)=71578682) +1998 train 9.812780 (lr=1.2071e-04) (hash(x)=58341730) +1999 train 9.802730 (lr=1.2066e-04) (hash(x)=61104710) +2000 val loss 8.0526 +2000 val perplexity 3141.8782 +2000 train 9.306664 (lr=1.2061e-04) (hash(x)=52865322) +2001 train 8.220149 (lr=1.2057e-04) (hash(x)=23633693) +2002 train 8.187070 (lr=1.2052e-04) (hash(x)=25297571) +2003 train 8.413324 (lr=1.2047e-04) (hash(x)=24123821) +2004 train 7.909628 (lr=1.2043e-04) (hash(x)=20161517) +2005 train 7.834507 (lr=1.2038e-04) (hash(x)=19919984) +2006 train 7.750820 (lr=1.2033e-04) (hash(x)=18626507) +2007 train 7.946389 (lr=1.2028e-04) (hash(x)=20881126) +2008 train 7.989460 (lr=1.2024e-04) (hash(x)=26261448) +2009 train 7.926423 (lr=1.2019e-04) (hash(x)=27528050) +2010 train 7.921710 (lr=1.2014e-04) (hash(x)=26692097) +2011 train 7.592655 (lr=1.2010e-04) (hash(x)=23209969) +2012 train 7.494826 (lr=1.2005e-04) (hash(x)=26083446) +2013 train 7.655351 (lr=1.2000e-04) (hash(x)=28426467) +2014 train 7.404489 (lr=1.1995e-04) (hash(x)=26158154) +2015 train 7.537801 (lr=1.1991e-04) (hash(x)=26920243) +2016 train 7.239837 (lr=1.1986e-04) (hash(x)=21365321) +2017 train 7.360719 (lr=1.1981e-04) (hash(x)=25730699) +2018 train 7.470044 (lr=1.1976e-04) (hash(x)=25177106) +2019 train 7.372135 (lr=1.1972e-04) (hash(x)=26127756) +2020 train 6.938480 (lr=1.1967e-04) (hash(x)=19770037) +2021 train 7.424585 (lr=1.1962e-04) (hash(x)=26479346) +2022 train 7.465941 (lr=1.1958e-04) (hash(x)=25967643) +2023 train 7.373924 (lr=1.1953e-04) (hash(x)=21970343) +2024 train 7.583850 (lr=1.1948e-04) (hash(x)=26449648) +2025 train 7.489036 (lr=1.1943e-04) (hash(x)=24874094) +2026 train 7.102686 (lr=1.1939e-04) (hash(x)=21399697) +2027 train 7.323089 (lr=1.1934e-04) (hash(x)=24097897) +2028 train 7.382786 (lr=1.1929e-04) (hash(x)=24453548) +2029 train 7.463880 (lr=1.1924e-04) (hash(x)=26692093) +2030 train 7.275343 (lr=1.1920e-04) (hash(x)=27217002) +2031 train 7.675113 (lr=1.1915e-04) (hash(x)=31676352) +2032 train 7.291791 (lr=1.1910e-04) (hash(x)=23396350) +2033 train 7.340946 (lr=1.1906e-04) (hash(x)=26245173) +2034 train 7.388924 (lr=1.1901e-04) (hash(x)=24821033) +2035 train 7.425491 (lr=1.1896e-04) (hash(x)=23908053) +2036 train 7.208651 (lr=1.1891e-04) (hash(x)=23469373) +2037 train 7.269548 (lr=1.1887e-04) (hash(x)=24102198) +2038 train 7.287850 (lr=1.1882e-04) (hash(x)=24712135) +2039 train 7.510498 (lr=1.1877e-04) (hash(x)=25600562) +2040 train 7.438406 (lr=1.1872e-04) (hash(x)=23193393) +2041 train 7.418170 (lr=1.1868e-04) (hash(x)=24776954) +2042 train 7.533496 (lr=1.1863e-04) (hash(x)=28066546) +2043 train 7.163535 (lr=1.1858e-04) (hash(x)=23549168) +2044 train 7.181635 (lr=1.1853e-04) (hash(x)=22681487) +2045 train 7.356014 (lr=1.1849e-04) (hash(x)=26663184) +2046 train 7.293700 (lr=1.1844e-04) (hash(x)=23320809) +2047 train 7.178641 (lr=1.1839e-04) (hash(x)=22022924) +2048 train 7.520982 (lr=1.1834e-04) (hash(x)=27960930) +2049 train 7.309903 (lr=1.1830e-04) (hash(x)=24899178) +2050 val loss 7.3352 +2050 val perplexity 1533.2896 +2050 train 7.209395 (lr=1.1825e-04) (hash(x)=24450711) +2051 train 7.167496 (lr=1.1820e-04) (hash(x)=23294980) +2052 train 7.085396 (lr=1.1815e-04) (hash(x)=23243665) +2053 train 6.911988 (lr=1.1811e-04) (hash(x)=21004461) +2054 train 7.294080 (lr=1.1806e-04) (hash(x)=24493583) +2055 train 7.225885 (lr=1.1801e-04) (hash(x)=22777085) +2056 train 7.169281 (lr=1.1796e-04) (hash(x)=25169889) +2057 train 7.811318 (lr=1.1792e-04) (hash(x)=28395880) +2058 train 7.695889 (lr=1.1787e-04) (hash(x)=29603726) +2059 train 7.367224 (lr=1.1782e-04) (hash(x)=26271115) +2060 train 7.348320 (lr=1.1777e-04) (hash(x)=25616212) +2061 train 7.440451 (lr=1.1773e-04) (hash(x)=26398325) +2062 train 7.136413 (lr=1.1768e-04) (hash(x)=23836586) +2063 train 7.054823 (lr=1.1763e-04) (hash(x)=21727744) +2064 train 7.300041 (lr=1.1758e-04) (hash(x)=25183195) +2065 train 7.417516 (lr=1.1753e-04) (hash(x)=27108132) +2066 train 7.134691 (lr=1.1749e-04) (hash(x)=20987812) +2067 train 7.399458 (lr=1.1744e-04) (hash(x)=22729318) +2068 train 7.255379 (lr=1.1739e-04) (hash(x)=23129709) +2069 train 7.739522 (lr=1.1734e-04) (hash(x)=32820084) +2070 train 7.812113 (lr=1.1730e-04) (hash(x)=33763489) +2071 train 7.302408 (lr=1.1725e-04) (hash(x)=20701998) +2072 train 7.517972 (lr=1.1720e-04) (hash(x)=27765988) +2073 train 7.278484 (lr=1.1715e-04) (hash(x)=24157446) +2074 train 7.202180 (lr=1.1711e-04) (hash(x)=22014978) +2075 train 7.682591 (lr=1.1706e-04) (hash(x)=27928398) +2076 train 7.531793 (lr=1.1701e-04) (hash(x)=27880142) +2077 train 7.844205 (lr=1.1696e-04) (hash(x)=34991795) +2078 train 7.411548 (lr=1.1691e-04) (hash(x)=25944128) +2079 train 7.145509 (lr=1.1687e-04) (hash(x)=20863982) +2080 train 7.560058 (lr=1.1682e-04) (hash(x)=28036097) +2081 train 7.590222 (lr=1.1677e-04) (hash(x)=25813615) +2082 train 7.045640 (lr=1.1672e-04) (hash(x)=22862316) +2083 train 7.122804 (lr=1.1668e-04) (hash(x)=22827054) +2084 train 7.202445 (lr=1.1663e-04) (hash(x)=23996531) +2085 train 7.305871 (lr=1.1658e-04) (hash(x)=25756087) +2086 train 7.357044 (lr=1.1653e-04) (hash(x)=23165889) +2087 train 7.536689 (lr=1.1648e-04) (hash(x)=25084926) +2088 train 7.352387 (lr=1.1644e-04) (hash(x)=26063862) +2089 train 7.400733 (lr=1.1639e-04) (hash(x)=27843638) +2090 train 7.680723 (lr=1.1634e-04) (hash(x)=27375554) +2091 train 7.430448 (lr=1.1629e-04) (hash(x)=25540961) +2092 train 7.186869 (lr=1.1625e-04) (hash(x)=22933785) +2093 train 7.351390 (lr=1.1620e-04) (hash(x)=23996956) +2094 train 7.060870 (lr=1.1615e-04) (hash(x)=22915854) +2095 train 7.321771 (lr=1.1610e-04) (hash(x)=24412897) +2096 train 7.352748 (lr=1.1605e-04) (hash(x)=25152336) +2097 train 7.655238 (lr=1.1601e-04) (hash(x)=29525589) +2098 train 7.493663 (lr=1.1596e-04) (hash(x)=26435656) +2099 train 7.373641 (lr=1.1591e-04) (hash(x)=26269869) +2100 val loss 7.3139 +2100 val perplexity 1500.9711 +2100 train 7.149227 (lr=1.1586e-04) (hash(x)=23856783) +2101 train 7.389931 (lr=1.1581e-04) (hash(x)=26039611) +2102 train 7.137444 (lr=1.1577e-04) (hash(x)=25048861) +2103 train 7.254253 (lr=1.1572e-04) (hash(x)=25434913) +2104 train 7.415753 (lr=1.1567e-04) (hash(x)=24203891) +2105 train 7.322093 (lr=1.1562e-04) (hash(x)=26016998) +2106 train 7.406722 (lr=1.1557e-04) (hash(x)=23986767) +2107 train 7.339376 (lr=1.1553e-04) (hash(x)=25157653) +2108 train 7.485444 (lr=1.1548e-04) (hash(x)=30193751) +2109 train 7.336739 (lr=1.1543e-04) (hash(x)=22630574) +2110 train 7.199359 (lr=1.1538e-04) (hash(x)=23475467) +2111 train 7.495331 (lr=1.1533e-04) (hash(x)=26302544) +2112 train 7.306159 (lr=1.1529e-04) (hash(x)=21276592) +2113 train 7.521991 (lr=1.1524e-04) (hash(x)=27566393) +2114 train 7.268010 (lr=1.1519e-04) (hash(x)=25028015) +2115 train 7.080284 (lr=1.1514e-04) (hash(x)=22010703) +2116 train 7.381982 (lr=1.1509e-04) (hash(x)=23711709) +2117 train 7.404045 (lr=1.1505e-04) (hash(x)=26105026) +2118 train 7.795345 (lr=1.1500e-04) (hash(x)=34433894) +2119 train 7.861372 (lr=1.1495e-04) (hash(x)=34976197) +2120 train 7.384628 (lr=1.1490e-04) (hash(x)=27690727) +2121 train 7.244698 (lr=1.1485e-04) (hash(x)=24368234) +2122 train 7.232124 (lr=1.1481e-04) (hash(x)=25095726) +2123 train 7.412169 (lr=1.1476e-04) (hash(x)=28248301) +2124 train 7.166321 (lr=1.1471e-04) (hash(x)=23322302) +2125 train 7.577474 (lr=1.1466e-04) (hash(x)=26416200) +2126 train 7.276305 (lr=1.1461e-04) (hash(x)=26577567) +2127 train 7.333945 (lr=1.1457e-04) (hash(x)=23870805) +2128 train 7.251992 (lr=1.1452e-04) (hash(x)=25440544) +2129 train 7.377918 (lr=1.1447e-04) (hash(x)=25795021) +2130 train 7.200855 (lr=1.1442e-04) (hash(x)=20896402) +2131 train 7.232948 (lr=1.1437e-04) (hash(x)=24457252) +2132 train 7.333456 (lr=1.1432e-04) (hash(x)=25926760) +2133 train 7.202816 (lr=1.1428e-04) (hash(x)=23503725) +2134 train 7.740757 (lr=1.1423e-04) (hash(x)=28728828) +2135 train 7.253618 (lr=1.1418e-04) (hash(x)=25041103) +2136 train 7.287871 (lr=1.1413e-04) (hash(x)=22863770) +2137 train 7.110768 (lr=1.1408e-04) (hash(x)=23037755) +2138 train 7.337102 (lr=1.1404e-04) (hash(x)=25848413) +2139 train 7.398061 (lr=1.1399e-04) (hash(x)=25998487) +2140 train 7.248137 (lr=1.1394e-04) (hash(x)=22754440) +2141 train 7.489685 (lr=1.1389e-04) (hash(x)=27705382) +2142 train 7.527550 (lr=1.1384e-04) (hash(x)=27629095) +2143 train 7.387195 (lr=1.1379e-04) (hash(x)=26041745) +2144 train 7.161585 (lr=1.1375e-04) (hash(x)=21909712) +2145 train 7.345705 (lr=1.1370e-04) (hash(x)=24353905) +2146 train 7.278668 (lr=1.1365e-04) (hash(x)=24482587) +2147 train 7.401955 (lr=1.1360e-04) (hash(x)=27249810) +2148 train 7.520940 (lr=1.1355e-04) (hash(x)=26709938) +2149 train 7.183228 (lr=1.1350e-04) (hash(x)=23831457) +2150 val loss 7.3046 +2150 val perplexity 1487.0913 +2150 train 7.536704 (lr=1.1346e-04) (hash(x)=29776243) +2151 train 7.076866 (lr=1.1341e-04) (hash(x)=24068619) +2152 train 7.259680 (lr=1.1336e-04) (hash(x)=22208671) +2153 train 7.432359 (lr=1.1331e-04) (hash(x)=26680905) +2154 train 7.290951 (lr=1.1326e-04) (hash(x)=23567808) +2155 train 7.562811 (lr=1.1321e-04) (hash(x)=26359528) +2156 train 7.352531 (lr=1.1317e-04) (hash(x)=23787652) +2157 train 7.587067 (lr=1.1312e-04) (hash(x)=28347177) +2158 train 7.307547 (lr=1.1307e-04) (hash(x)=25266519) +2159 train 7.219675 (lr=1.1302e-04) (hash(x)=25441262) +2160 train 7.129336 (lr=1.1297e-04) (hash(x)=23959943) +2161 train 7.377540 (lr=1.1292e-04) (hash(x)=27888093) +2162 train 7.281451 (lr=1.1288e-04) (hash(x)=25547833) +2163 train 7.206340 (lr=1.1283e-04) (hash(x)=24413659) +2164 train 8.758769 (lr=1.1278e-04) (hash(x)=34397626) +2165 train 7.138364 (lr=1.1273e-04) (hash(x)=21159323) +2166 train 7.349518 (lr=1.1268e-04) (hash(x)=25360269) +2167 train 7.400070 (lr=1.1263e-04) (hash(x)=29181867) +2168 train 7.233453 (lr=1.1259e-04) (hash(x)=22501613) +2169 train 7.285730 (lr=1.1254e-04) (hash(x)=26469077) +2170 train 7.262543 (lr=1.1249e-04) (hash(x)=26665118) +2171 train 7.917629 (lr=1.1244e-04) (hash(x)=31551575) +2172 train 7.243369 (lr=1.1239e-04) (hash(x)=24803935) +2173 train 7.121759 (lr=1.1234e-04) (hash(x)=20896465) +2174 train 7.569281 (lr=1.1230e-04) (hash(x)=25702284) +2175 train 7.562070 (lr=1.1225e-04) (hash(x)=27093757) +2176 train 7.351360 (lr=1.1220e-04) (hash(x)=26024255) +2177 train 7.466856 (lr=1.1215e-04) (hash(x)=26443521) +2178 train 7.423017 (lr=1.1210e-04) (hash(x)=25478467) +2179 train 7.281690 (lr=1.1205e-04) (hash(x)=23624298) +2180 train 7.369253 (lr=1.1200e-04) (hash(x)=27304178) +2181 train 7.116141 (lr=1.1196e-04) (hash(x)=23016570) +2182 train 7.109212 (lr=1.1191e-04) (hash(x)=21073756) +2183 train 7.212877 (lr=1.1186e-04) (hash(x)=25150275) +2184 train 7.039461 (lr=1.1181e-04) (hash(x)=21004187) +2185 train 7.264980 (lr=1.1176e-04) (hash(x)=25876062) +2186 train 7.203856 (lr=1.1171e-04) (hash(x)=24221275) +2187 train 7.477991 (lr=1.1166e-04) (hash(x)=26239886) +2188 train 7.212440 (lr=1.1162e-04) (hash(x)=23299261) +2189 train 7.669928 (lr=1.1157e-04) (hash(x)=31024703) +2190 train 7.760218 (lr=1.1152e-04) (hash(x)=30084774) +2191 train 8.008981 (lr=1.1147e-04) (hash(x)=33457102) +2192 train 7.234512 (lr=1.1142e-04) (hash(x)=22423723) +2193 train 7.292769 (lr=1.1137e-04) (hash(x)=21989055) +2194 train 7.304212 (lr=1.1133e-04) (hash(x)=23286499) +2195 train 7.262523 (lr=1.1128e-04) (hash(x)=17499738) +2196 train 7.305567 (lr=1.1123e-04) (hash(x)=25329557) +2197 train 7.191104 (lr=1.1118e-04) (hash(x)=24195578) +2198 train 7.453983 (lr=1.1113e-04) (hash(x)=26646383) +2199 train 7.349950 (lr=1.1108e-04) (hash(x)=25755322) +2200 val loss 7.3180 +2200 val perplexity 1507.2532 +2200 train 7.386237 (lr=1.1103e-04) (hash(x)=27592223) +2201 train 7.541412 (lr=1.1098e-04) (hash(x)=26164625) +2202 train 7.400960 (lr=1.1094e-04) (hash(x)=21856341) +2203 train 7.282146 (lr=1.1089e-04) (hash(x)=23722795) +2204 train 7.340753 (lr=1.1084e-04) (hash(x)=25409645) +2205 train 7.287686 (lr=1.1079e-04) (hash(x)=23415339) +2206 train 7.273851 (lr=1.1074e-04) (hash(x)=24147928) +2207 train 7.182907 (lr=1.1069e-04) (hash(x)=23630794) +2208 train 7.292389 (lr=1.1064e-04) (hash(x)=27361452) +2209 train 7.297563 (lr=1.1060e-04) (hash(x)=25632158) +2210 train 7.139165 (lr=1.1055e-04) (hash(x)=21159789) +2211 train 7.266291 (lr=1.1050e-04) (hash(x)=23374168) +2212 train 7.284470 (lr=1.1045e-04) (hash(x)=24844739) +2213 train 7.197047 (lr=1.1040e-04) (hash(x)=23461285) +2214 train 7.259972 (lr=1.1035e-04) (hash(x)=27958481) +2215 train 7.158321 (lr=1.1030e-04) (hash(x)=25167987) +2216 train 7.347531 (lr=1.1026e-04) (hash(x)=22873204) +2217 train 7.900414 (lr=1.1021e-04) (hash(x)=31038116) +2218 train 7.401456 (lr=1.1016e-04) (hash(x)=28883155) +2219 train 7.287552 (lr=1.1011e-04) (hash(x)=30941010) +2220 train 7.279431 (lr=1.1006e-04) (hash(x)=24947521) +2221 train 7.317787 (lr=1.1001e-04) (hash(x)=22703293) +2222 train 7.265318 (lr=1.0996e-04) (hash(x)=23976007) +2223 train 7.197218 (lr=1.0991e-04) (hash(x)=24043224) +2224 train 7.109660 (lr=1.0987e-04) (hash(x)=23981093) +2225 train 7.271749 (lr=1.0982e-04) (hash(x)=26445994) +2226 train 7.560768 (lr=1.0977e-04) (hash(x)=27252393) +2227 train 7.558995 (lr=1.0972e-04) (hash(x)=29736627) +2228 train 7.452909 (lr=1.0967e-04) (hash(x)=24698933) +2229 train 7.124405 (lr=1.0962e-04) (hash(x)=24357840) +2230 train 7.268390 (lr=1.0957e-04) (hash(x)=25384498) +2231 train 7.426605 (lr=1.0952e-04) (hash(x)=24665411) +2232 train 7.276497 (lr=1.0948e-04) (hash(x)=24646352) +2233 train 7.280076 (lr=1.0943e-04) (hash(x)=25670741) +2234 train 7.304737 (lr=1.0938e-04) (hash(x)=26648242) +2235 train 7.568280 (lr=1.0933e-04) (hash(x)=27916043) +2236 train 7.278471 (lr=1.0928e-04) (hash(x)=25963100) +2237 train 7.373731 (lr=1.0923e-04) (hash(x)=27357379) +2238 train 7.170691 (lr=1.0918e-04) (hash(x)=21852360) +2239 train 7.087087 (lr=1.0913e-04) (hash(x)=17321657) +2240 train 7.044689 (lr=1.0908e-04) (hash(x)=18446645) +2241 train 6.879594 (lr=1.0904e-04) (hash(x)=17550988) +2242 train 7.258698 (lr=1.0899e-04) (hash(x)=27052347) +2243 train 7.149225 (lr=1.0894e-04) (hash(x)=23829833) +2244 train 7.384102 (lr=1.0889e-04) (hash(x)=27267264) +2245 train 7.572813 (lr=1.0884e-04) (hash(x)=24673611) +2246 train 7.513181 (lr=1.0879e-04) (hash(x)=25248507) +2247 train 7.770597 (lr=1.0874e-04) (hash(x)=27932591) +2248 train 7.591170 (lr=1.0869e-04) (hash(x)=26078877) +2249 train 7.646901 (lr=1.0864e-04) (hash(x)=26067367) +2250 val loss 7.3113 +2250 val perplexity 1497.1105 +2250 train 7.636363 (lr=1.0860e-04) (hash(x)=29143527) +2251 train 7.631584 (lr=1.0855e-04) (hash(x)=28206079) +2252 train 8.166498 (lr=1.0850e-04) (hash(x)=28894494) +2253 train 7.672963 (lr=1.0845e-04) (hash(x)=27977422) +2254 train 7.334089 (lr=1.0840e-04) (hash(x)=26446420) +2255 train 7.545297 (lr=1.0835e-04) (hash(x)=29447954) +2256 train 7.407478 (lr=1.0830e-04) (hash(x)=22181789) +2257 train 7.391194 (lr=1.0825e-04) (hash(x)=24976337) +2258 train 7.343924 (lr=1.0820e-04) (hash(x)=23277532) +2259 train 7.482488 (lr=1.0816e-04) (hash(x)=25935364) +2260 train 7.633377 (lr=1.0811e-04) (hash(x)=26988889) +2261 train 7.391391 (lr=1.0806e-04) (hash(x)=26887303) +2262 train 7.346706 (lr=1.0801e-04) (hash(x)=25021426) +2263 train 7.306571 (lr=1.0796e-04) (hash(x)=24621816) +2264 train 7.192894 (lr=1.0791e-04) (hash(x)=22132007) +2265 train 7.093327 (lr=1.0786e-04) (hash(x)=22648602) +2266 train 7.454796 (lr=1.0781e-04) (hash(x)=23132242) +2267 train 7.477035 (lr=1.0776e-04) (hash(x)=24070405) +2268 train 7.054442 (lr=1.0772e-04) (hash(x)=21412906) +2269 train 7.778325 (lr=1.0767e-04) (hash(x)=27547292) +2270 train 7.518985 (lr=1.0762e-04) (hash(x)=27740500) +2271 train 7.248186 (lr=1.0757e-04) (hash(x)=24682294) +2272 train 7.684737 (lr=1.0752e-04) (hash(x)=27969424) +2273 train 7.338478 (lr=1.0747e-04) (hash(x)=22172182) +2274 train 7.343350 (lr=1.0742e-04) (hash(x)=26485905) +2275 train 7.203163 (lr=1.0737e-04) (hash(x)=24050209) +2276 train 7.399271 (lr=1.0732e-04) (hash(x)=28802650) +2277 train 7.158321 (lr=1.0727e-04) (hash(x)=23644616) +2278 train 7.337922 (lr=1.0723e-04) (hash(x)=25409768) +2279 train 7.524517 (lr=1.0718e-04) (hash(x)=28057095) +2280 train 7.973941 (lr=1.0713e-04) (hash(x)=31689723) +2281 train 7.157600 (lr=1.0708e-04) (hash(x)=22252427) +2282 train 7.415732 (lr=1.0703e-04) (hash(x)=24142092) +2283 train 7.334573 (lr=1.0698e-04) (hash(x)=22523232) +2284 train 7.524946 (lr=1.0693e-04) (hash(x)=26017294) +2285 train 7.402893 (lr=1.0688e-04) (hash(x)=25025388) +2286 train 7.207108 (lr=1.0683e-04) (hash(x)=23819479) +2287 train 7.372359 (lr=1.0678e-04) (hash(x)=24547536) +2288 train 7.144987 (lr=1.0674e-04) (hash(x)=22622789) +2289 train 7.112816 (lr=1.0669e-04) (hash(x)=23874051) +2290 train 7.461832 (lr=1.0664e-04) (hash(x)=25015641) +2291 train 7.358411 (lr=1.0659e-04) (hash(x)=24978712) +2292 train 7.446784 (lr=1.0654e-04) (hash(x)=25311986) +2293 train 7.186790 (lr=1.0649e-04) (hash(x)=24298295) +2294 train 7.276405 (lr=1.0644e-04) (hash(x)=26481527) +2295 train 7.001653 (lr=1.0639e-04) (hash(x)=18987545) +2296 train 7.233529 (lr=1.0634e-04) (hash(x)=24617990) +2297 train 7.210586 (lr=1.0629e-04) (hash(x)=23903200) +2298 train 7.544482 (lr=1.0624e-04) (hash(x)=26278697) +2299 train 7.292929 (lr=1.0620e-04) (hash(x)=24092784) +2300 val loss 7.3220 +2300 val perplexity 1513.2491 +2300 train 7.233611 (lr=1.0615e-04) (hash(x)=22894919) +2301 train 7.309150 (lr=1.0610e-04) (hash(x)=24253964) +2302 train 7.235856 (lr=1.0605e-04) (hash(x)=23750610) +2303 train 7.293518 (lr=1.0600e-04) (hash(x)=26745063) +2304 train 7.108038 (lr=1.0595e-04) (hash(x)=21407001) +2305 train 7.487014 (lr=1.0590e-04) (hash(x)=26680082) +2306 train 7.371640 (lr=1.0585e-04) (hash(x)=26722122) +2307 train 7.237364 (lr=1.0580e-04) (hash(x)=22539112) +2308 train 7.027031 (lr=1.0575e-04) (hash(x)=19927356) +2309 train 7.139426 (lr=1.0570e-04) (hash(x)=21431267) +2310 train 7.097478 (lr=1.0566e-04) (hash(x)=21073487) +2311 train 7.120754 (lr=1.0561e-04) (hash(x)=21447406) +2312 train 7.127939 (lr=1.0556e-04) (hash(x)=22667253) +2313 train 7.094464 (lr=1.0551e-04) (hash(x)=20849089) +2314 train 7.071590 (lr=1.0546e-04) (hash(x)=19168351) +2315 train 7.114862 (lr=1.0541e-04) (hash(x)=21082139) +2316 train 7.105730 (lr=1.0536e-04) (hash(x)=21493530) +2317 train 7.019781 (lr=1.0531e-04) (hash(x)=19506447) +2318 train 7.132599 (lr=1.0526e-04) (hash(x)=23128797) +2319 train 7.206066 (lr=1.0521e-04) (hash(x)=24650655) +2320 train 6.987004 (lr=1.0516e-04) (hash(x)=21833080) +2321 train 7.496532 (lr=1.0511e-04) (hash(x)=26355512) +2322 train 7.696668 (lr=1.0507e-04) (hash(x)=26746363) +2323 train 7.124781 (lr=1.0502e-04) (hash(x)=22130721) +2324 train 7.470838 (lr=1.0497e-04) (hash(x)=28301752) +2325 train 7.302316 (lr=1.0492e-04) (hash(x)=26444359) +2326 train 7.664496 (lr=1.0487e-04) (hash(x)=24836130) +2327 train 8.123477 (lr=1.0482e-04) (hash(x)=26519976) +2328 train 9.735964 (lr=1.0477e-04) (hash(x)=35558906) +2329 train 7.743376 (lr=1.0472e-04) (hash(x)=30877729) +2330 train 7.536867 (lr=1.0467e-04) (hash(x)=28028485) +2331 train 7.681123 (lr=1.0462e-04) (hash(x)=25582440) +2332 train 8.004551 (lr=1.0457e-04) (hash(x)=29402491) +2333 train 7.320992 (lr=1.0452e-04) (hash(x)=25200284) +2334 train 7.350935 (lr=1.0448e-04) (hash(x)=26288480) +2335 train 7.096036 (lr=1.0443e-04) (hash(x)=20106514) +2336 train 7.137357 (lr=1.0438e-04) (hash(x)=22522123) +2337 train 7.157389 (lr=1.0433e-04) (hash(x)=23362041) +2338 train 7.266852 (lr=1.0428e-04) (hash(x)=26003099) +2339 train 7.284696 (lr=1.0423e-04) (hash(x)=25695510) +2340 train 7.297181 (lr=1.0418e-04) (hash(x)=27225904) +2341 train 7.061573 (lr=1.0413e-04) (hash(x)=21573008) +2342 train 7.492156 (lr=1.0408e-04) (hash(x)=21386628) +2343 train 7.291629 (lr=1.0403e-04) (hash(x)=20117808) +2344 train 7.412985 (lr=1.0398e-04) (hash(x)=21592790) +2345 train 7.326389 (lr=1.0393e-04) (hash(x)=19909192) +2346 train 7.409863 (lr=1.0388e-04) (hash(x)=22529262) +2347 train 7.424721 (lr=1.0383e-04) (hash(x)=24501900) +2348 train 7.215894 (lr=1.0379e-04) (hash(x)=25912171) +2349 train 7.327963 (lr=1.0374e-04) (hash(x)=25606665) +2350 val loss 7.3110 +2350 val perplexity 1496.7101 +2350 train 7.245853 (lr=1.0369e-04) (hash(x)=24487351) +2351 train 7.495865 (lr=1.0364e-04) (hash(x)=25510334) +2352 train 7.422475 (lr=1.0359e-04) (hash(x)=25357989) +2353 train 7.050682 (lr=1.0354e-04) (hash(x)=24656801) +2354 train 7.150414 (lr=1.0349e-04) (hash(x)=23312772) +2355 train 7.002464 (lr=1.0344e-04) (hash(x)=22099158) +2356 train 7.060455 (lr=1.0339e-04) (hash(x)=26507898) +2357 train 7.389934 (lr=1.0334e-04) (hash(x)=28351614) +2358 train 7.397283 (lr=1.0329e-04) (hash(x)=27489567) +2359 train 7.391796 (lr=1.0324e-04) (hash(x)=25749120) +2360 train 7.722074 (lr=1.0319e-04) (hash(x)=31711338) +2361 train 7.822601 (lr=1.0315e-04) (hash(x)=29645018) +2362 train 7.794780 (lr=1.0310e-04) (hash(x)=29713268) +2363 train 7.012723 (lr=1.0305e-04) (hash(x)=21720691) +2364 train 7.117563 (lr=1.0300e-04) (hash(x)=24316633) +2365 train 7.046164 (lr=1.0295e-04) (hash(x)=21597124) +2366 train 7.076411 (lr=1.0290e-04) (hash(x)=22520345) +2367 train 7.107065 (lr=1.0285e-04) (hash(x)=24357241) +2368 train 7.239170 (lr=1.0280e-04) (hash(x)=24085450) +2369 train 7.175167 (lr=1.0275e-04) (hash(x)=25136495) +2370 train 7.648232 (lr=1.0270e-04) (hash(x)=26073986) +2371 train 7.575603 (lr=1.0265e-04) (hash(x)=28911272) +2372 train 7.381182 (lr=1.0260e-04) (hash(x)=26667356) +2373 train 7.209825 (lr=1.0255e-04) (hash(x)=25225894) +2374 train 7.250383 (lr=1.0250e-04) (hash(x)=24404081) +2375 train 7.319426 (lr=1.0245e-04) (hash(x)=25584945) +2376 train 7.130812 (lr=1.0241e-04) (hash(x)=23831571) +2377 train 7.179891 (lr=1.0236e-04) (hash(x)=23521916) +2378 train 7.168489 (lr=1.0231e-04) (hash(x)=25318634) +2379 train 7.028289 (lr=1.0226e-04) (hash(x)=21847287) +2380 train 7.421619 (lr=1.0221e-04) (hash(x)=23877060) +2381 train 7.211985 (lr=1.0216e-04) (hash(x)=24069020) +2382 train 6.976928 (lr=1.0211e-04) (hash(x)=21724290) +2383 train 7.249127 (lr=1.0206e-04) (hash(x)=25198897) +2384 train 7.120395 (lr=1.0201e-04) (hash(x)=24109958) +2385 train 6.983623 (lr=1.0196e-04) (hash(x)=20122390) +2386 train 7.290308 (lr=1.0191e-04) (hash(x)=24062305) +2387 train 7.034729 (lr=1.0186e-04) (hash(x)=22436833) +2388 train 7.335562 (lr=1.0181e-04) (hash(x)=26013214) +2389 train 7.717421 (lr=1.0176e-04) (hash(x)=27691436) +2390 train 7.806259 (lr=1.0171e-04) (hash(x)=30802878) +2391 train 6.989099 (lr=1.0166e-04) (hash(x)=23475891) +2392 train 6.968858 (lr=1.0162e-04) (hash(x)=23118133) +2393 train 6.878657 (lr=1.0157e-04) (hash(x)=21469159) +2394 train 7.266791 (lr=1.0152e-04) (hash(x)=26444484) +2395 train 7.121036 (lr=1.0147e-04) (hash(x)=25083992) +2396 train 7.472103 (lr=1.0142e-04) (hash(x)=23461229) +2397 train 7.320540 (lr=1.0137e-04) (hash(x)=20441653) +2398 train 7.425817 (lr=1.0132e-04) (hash(x)=28024211) +2399 train 7.238829 (lr=1.0127e-04) (hash(x)=23644804) +2400 val loss 7.2884 +2400 val perplexity 1463.2600 +2400 train 7.056143 (lr=1.0122e-04) (hash(x)=26685301) +2401 train 6.934734 (lr=1.0117e-04) (hash(x)=20820913) +2402 train 7.119127 (lr=1.0112e-04) (hash(x)=22178190) +2403 train 7.676351 (lr=1.0107e-04) (hash(x)=31377168) +2404 train 7.891690 (lr=1.0102e-04) (hash(x)=33795307) +2405 train 8.039536 (lr=1.0097e-04) (hash(x)=34450341) +2406 train 7.278975 (lr=1.0092e-04) (hash(x)=25834183) +2407 train 7.498369 (lr=1.0087e-04) (hash(x)=25629584) +2408 train 7.304672 (lr=1.0083e-04) (hash(x)=25080123) +2409 train 7.166351 (lr=1.0078e-04) (hash(x)=21975628) +2410 train 7.692632 (lr=1.0073e-04) (hash(x)=27430197) +2411 train 7.850388 (lr=1.0068e-04) (hash(x)=29285135) +2412 train 7.582783 (lr=1.0063e-04) (hash(x)=24640105) +2413 train 7.590416 (lr=1.0058e-04) (hash(x)=29628864) +2414 train 7.805554 (lr=1.0053e-04) (hash(x)=30096444) +2415 train 7.627150 (lr=1.0048e-04) (hash(x)=29797280) +2416 train 7.006454 (lr=1.0043e-04) (hash(x)=22686143) +2417 train 7.591099 (lr=1.0038e-04) (hash(x)=28346842) +2418 train 7.586154 (lr=1.0033e-04) (hash(x)=28167937) +2419 train 7.791968 (lr=1.0028e-04) (hash(x)=33122326) +2420 train 7.861008 (lr=1.0023e-04) (hash(x)=33044913) +2421 train 7.636394 (lr=1.0018e-04) (hash(x)=31250981) +2422 train 7.845342 (lr=1.0013e-04) (hash(x)=29827111) +2423 train 7.772851 (lr=1.0008e-04) (hash(x)=30026394) +2424 train 7.847391 (lr=1.0003e-04) (hash(x)=26998238) +2425 train 7.837002 (lr=9.9985e-05) (hash(x)=24850684) +2426 train 8.077603 (lr=9.9936e-05) (hash(x)=36659853) +2427 train 7.977544 (lr=9.9886e-05) (hash(x)=34353164) +2428 train 7.312812 (lr=9.9837e-05) (hash(x)=23630644) +2429 train 7.243691 (lr=9.9787e-05) (hash(x)=24528186) +2430 train 7.165831 (lr=9.9738e-05) (hash(x)=22665222) +2431 train 7.291509 (lr=9.9688e-05) (hash(x)=26594177) +2432 train 7.632038 (lr=9.9639e-05) (hash(x)=29300546) +2433 train 7.087665 (lr=9.9590e-05) (hash(x)=21331715) +2434 train 7.368417 (lr=9.9540e-05) (hash(x)=26290885) +2435 train 7.287563 (lr=9.9491e-05) (hash(x)=25554738) +2436 train 7.522662 (lr=9.9441e-05) (hash(x)=26744311) +2437 train 7.471392 (lr=9.9392e-05) (hash(x)=26872344) +2438 train 7.535461 (lr=9.9342e-05) (hash(x)=27636081) +2439 train 7.299127 (lr=9.9293e-05) (hash(x)=23766256) +2440 train 7.430432 (lr=9.9243e-05) (hash(x)=24434438) +2441 train 7.218071 (lr=9.9194e-05) (hash(x)=22992618) +2442 train 7.115789 (lr=9.9145e-05) (hash(x)=22393467) +2443 train 7.365973 (lr=9.9095e-05) (hash(x)=26853444) +2444 train 7.293790 (lr=9.9046e-05) (hash(x)=25101020) +2445 train 7.213644 (lr=9.8996e-05) (hash(x)=24705456) +2446 train 7.499831 (lr=9.8947e-05) (hash(x)=26798611) +2447 train 7.177829 (lr=9.8897e-05) (hash(x)=24250150) +2448 train 7.240410 (lr=9.8848e-05) (hash(x)=24494331) +2449 train 7.239694 (lr=9.8798e-05) (hash(x)=27579257) +2450 val loss 7.3153 +2450 val perplexity 1503.1686 +2450 train 7.042346 (lr=9.8749e-05) (hash(x)=22377407) +2451 train 7.333530 (lr=9.8699e-05) (hash(x)=26289588) +2452 train 7.228556 (lr=9.8650e-05) (hash(x)=25871900) +2453 train 7.143661 (lr=9.8600e-05) (hash(x)=23437197) +2454 train 7.409769 (lr=9.8551e-05) (hash(x)=23557786) +2455 train 7.311377 (lr=9.8501e-05) (hash(x)=26108817) +2456 train 7.253470 (lr=9.8452e-05) (hash(x)=26440482) +2457 train 7.251709 (lr=9.8403e-05) (hash(x)=24583191) +2458 train 7.265224 (lr=9.8353e-05) (hash(x)=23756440) +2459 train 7.131270 (lr=9.8304e-05) (hash(x)=23814987) +2460 train 7.519786 (lr=9.8254e-05) (hash(x)=28508433) +2461 train 7.160165 (lr=9.8205e-05) (hash(x)=25692442) +2462 train 7.160742 (lr=9.8155e-05) (hash(x)=24699197) +2463 train 6.816491 (lr=9.8106e-05) (hash(x)=18582688) +2464 train 7.165488 (lr=9.8056e-05) (hash(x)=23266625) +2465 train 7.479352 (lr=9.8007e-05) (hash(x)=26565489) +2466 train 6.948242 (lr=9.7957e-05) (hash(x)=21686599) +2467 train 7.224091 (lr=9.7908e-05) (hash(x)=25558792) +2468 train 7.016033 (lr=9.7858e-05) (hash(x)=25110035) +2469 train 7.393585 (lr=9.7809e-05) (hash(x)=26263661) +2470 train 7.132955 (lr=9.7759e-05) (hash(x)=22282189) +2471 train 7.076564 (lr=9.7710e-05) (hash(x)=23272705) +2472 train 7.186180 (lr=9.7660e-05) (hash(x)=25300067) +2473 train 7.365206 (lr=9.7611e-05) (hash(x)=26802369) +2474 train 7.100234 (lr=9.7561e-05) (hash(x)=24646471) +2475 train 7.072205 (lr=9.7512e-05) (hash(x)=24709241) +2476 train 7.155180 (lr=9.7462e-05) (hash(x)=26747197) +2477 train 7.209817 (lr=9.7413e-05) (hash(x)=25201108) +2478 train 7.302311 (lr=9.7363e-05) (hash(x)=24962427) +2479 train 7.148007 (lr=9.7314e-05) (hash(x)=24793412) +2480 train 7.218513 (lr=9.7265e-05) (hash(x)=24452301) +2481 train 7.234670 (lr=9.7215e-05) (hash(x)=25177251) +2482 train 7.131822 (lr=9.7166e-05) (hash(x)=25801499) +2483 train 7.317085 (lr=9.7116e-05) (hash(x)=27256707) +2484 train 7.573667 (lr=9.7067e-05) (hash(x)=25303237) +2485 train 7.144380 (lr=9.7017e-05) (hash(x)=21641481) +2486 train 7.141740 (lr=9.6968e-05) (hash(x)=23818831) +2487 train 6.919755 (lr=9.6918e-05) (hash(x)=19280989) +2488 train 7.259688 (lr=9.6869e-05) (hash(x)=24075167) +2489 train 7.292676 (lr=9.6819e-05) (hash(x)=26651546) +2490 train 7.227251 (lr=9.6770e-05) (hash(x)=25367186) +2491 train 7.176755 (lr=9.6720e-05) (hash(x)=26508642) +2492 train 7.268864 (lr=9.6671e-05) (hash(x)=25294182) +2493 train 7.171968 (lr=9.6621e-05) (hash(x)=23916886) +2494 train 7.044254 (lr=9.6572e-05) (hash(x)=21189910) +2495 train 7.136364 (lr=9.6522e-05) (hash(x)=22751150) +2496 train 7.574794 (lr=9.6473e-05) (hash(x)=26608502) +2497 train 7.951603 (lr=9.6423e-05) (hash(x)=25372010) +2498 train 7.210066 (lr=9.6374e-05) (hash(x)=22006251) +2499 train 7.180009 (lr=9.6324e-05) (hash(x)=23880160) +2500 val loss 7.2913 +2500 val perplexity 1467.5154 +2500 train 7.106008 (lr=9.6275e-05) (hash(x)=23225337) +2501 train 7.246079 (lr=9.6225e-05) (hash(x)=24932950) +2502 train 7.011023 (lr=9.6176e-05) (hash(x)=20022340) +2503 train 7.407283 (lr=9.6126e-05) (hash(x)=23537942) +2504 train 7.286410 (lr=9.6077e-05) (hash(x)=24884288) +2505 train 6.940853 (lr=9.6027e-05) (hash(x)=21296580) +2506 train 7.173378 (lr=9.5978e-05) (hash(x)=23001455) +2507 train 7.474010 (lr=9.5928e-05) (hash(x)=26975313) +2508 train 7.464351 (lr=9.5879e-05) (hash(x)=26029962) +2509 train 7.151608 (lr=9.5829e-05) (hash(x)=24302204) +2510 train 6.870306 (lr=9.5780e-05) (hash(x)=22997203) +2511 train 7.016388 (lr=9.5730e-05) (hash(x)=23748375) +2512 train 7.216550 (lr=9.5681e-05) (hash(x)=24453191) +2513 train 6.904937 (lr=9.5631e-05) (hash(x)=22026776) +2514 train 7.000350 (lr=9.5582e-05) (hash(x)=19934168) +2515 train 7.323900 (lr=9.5532e-05) (hash(x)=25541754) +2516 train 7.669880 (lr=9.5483e-05) (hash(x)=26604471) +2517 train 7.654857 (lr=9.5433e-05) (hash(x)=27900386) +2518 train 7.592056 (lr=9.5384e-05) (hash(x)=26403431) +2519 train 7.591712 (lr=9.5334e-05) (hash(x)=27413825) +2520 train 7.697164 (lr=9.5285e-05) (hash(x)=28332637) +2521 train 7.487805 (lr=9.5235e-05) (hash(x)=27223027) +2522 train 7.505731 (lr=9.5186e-05) (hash(x)=23843387) +2523 train 7.540174 (lr=9.5137e-05) (hash(x)=27075951) +2524 train 7.741029 (lr=9.5087e-05) (hash(x)=29300154) +2525 train 7.375992 (lr=9.5038e-05) (hash(x)=28100582) +2526 train 7.412825 (lr=9.4988e-05) (hash(x)=28051084) +2527 train 7.180785 (lr=9.4939e-05) (hash(x)=21682445) +2528 train 7.311410 (lr=9.4889e-05) (hash(x)=24062589) +2529 train 7.521362 (lr=9.4840e-05) (hash(x)=29616079) +2530 train 7.462122 (lr=9.4790e-05) (hash(x)=25170523) +2531 train 7.041107 (lr=9.4741e-05) (hash(x)=23361504) +2532 train 7.222620 (lr=9.4691e-05) (hash(x)=24444462) +2533 train 7.237766 (lr=9.4642e-05) (hash(x)=24035993) +2534 train 7.183345 (lr=9.4592e-05) (hash(x)=24696651) +2535 train 7.198630 (lr=9.4543e-05) (hash(x)=22040184) +2536 train 7.094459 (lr=9.4493e-05) (hash(x)=27400103) +2537 train 7.441097 (lr=9.4444e-05) (hash(x)=27383080) +2538 train 7.219758 (lr=9.4394e-05) (hash(x)=24212212) +2539 train 7.082506 (lr=9.4345e-05) (hash(x)=23727731) +2540 train 7.238138 (lr=9.4295e-05) (hash(x)=24149487) +2541 train 6.993626 (lr=9.4246e-05) (hash(x)=23794649) +2542 train 7.175949 (lr=9.4196e-05) (hash(x)=26147774) +2543 train 7.308895 (lr=9.4147e-05) (hash(x)=24463229) +2544 train 7.356009 (lr=9.4097e-05) (hash(x)=26361238) +2545 train 7.016717 (lr=9.4048e-05) (hash(x)=18891545) +2546 train 7.571207 (lr=9.3999e-05) (hash(x)=30380438) +2547 train 7.788568 (lr=9.3949e-05) (hash(x)=32663792) +2548 train 7.202663 (lr=9.3900e-05) (hash(x)=25175499) +2549 train 7.394043 (lr=9.3850e-05) (hash(x)=26702407) +2550 val loss 7.2843 +2550 val perplexity 1457.1808 +2550 train 7.196979 (lr=9.3801e-05) (hash(x)=24578061) +2551 train 7.201573 (lr=9.3751e-05) (hash(x)=24091954) +2552 train 7.256598 (lr=9.3702e-05) (hash(x)=23041778) +2553 train 7.002996 (lr=9.3652e-05) (hash(x)=23686239) +2554 train 7.143591 (lr=9.3603e-05) (hash(x)=22745355) +2555 train 7.203815 (lr=9.3553e-05) (hash(x)=23599013) +2556 train 7.100481 (lr=9.3504e-05) (hash(x)=26033088) +2557 train 7.176983 (lr=9.3454e-05) (hash(x)=21634218) +2558 train 7.112183 (lr=9.3405e-05) (hash(x)=20985281) +2559 train 7.397197 (lr=9.3355e-05) (hash(x)=26670219) +2560 train 7.148970 (lr=9.3306e-05) (hash(x)=26499936) +2561 train 7.250712 (lr=9.3257e-05) (hash(x)=23547908) +2562 train 7.104912 (lr=9.3207e-05) (hash(x)=22306373) +2563 train 7.248360 (lr=9.3158e-05) (hash(x)=24380893) +2564 train 7.187500 (lr=9.3108e-05) (hash(x)=23726190) +2565 train 7.217265 (lr=9.3059e-05) (hash(x)=26967512) +2566 train 7.278197 (lr=9.3009e-05) (hash(x)=23414576) +2567 train 7.516862 (lr=9.2960e-05) (hash(x)=25558986) +2568 train 7.391609 (lr=9.2910e-05) (hash(x)=27057505) +2569 train 7.377501 (lr=9.2861e-05) (hash(x)=26048135) +2570 train 7.323930 (lr=9.2812e-05) (hash(x)=26991032) +2571 train 7.413593 (lr=9.2762e-05) (hash(x)=25729492) +2572 train 6.956959 (lr=9.2713e-05) (hash(x)=20611723) +2573 train 7.057569 (lr=9.2663e-05) (hash(x)=24563606) +2574 train 7.129852 (lr=9.2614e-05) (hash(x)=23330043) +2575 train 7.157897 (lr=9.2564e-05) (hash(x)=19218943) +2576 train 7.511680 (lr=9.2515e-05) (hash(x)=20985122) +2577 train 7.112688 (lr=9.2465e-05) (hash(x)=24133609) +2578 train 7.473042 (lr=9.2416e-05) (hash(x)=28368610) +2579 train 7.149739 (lr=9.2367e-05) (hash(x)=23952206) +2580 train 7.092910 (lr=9.2317e-05) (hash(x)=23068957) +2581 train 7.182659 (lr=9.2268e-05) (hash(x)=25365277) +2582 train 7.528610 (lr=9.2218e-05) (hash(x)=24721184) +2583 train 7.235541 (lr=9.2169e-05) (hash(x)=24551402) +2584 train 6.977142 (lr=9.2119e-05) (hash(x)=20469327) +2585 train 7.379395 (lr=9.2070e-05) (hash(x)=24966478) +2586 train 7.095017 (lr=9.2021e-05) (hash(x)=18626184) +2587 train 7.141086 (lr=9.1971e-05) (hash(x)=24007642) +2588 train 7.110756 (lr=9.1922e-05) (hash(x)=23521875) +2589 train 7.324743 (lr=9.1872e-05) (hash(x)=25204207) +2590 train 7.113883 (lr=9.1823e-05) (hash(x)=25449801) +2591 train 7.297634 (lr=9.1774e-05) (hash(x)=25229281) +2592 train 7.160254 (lr=9.1724e-05) (hash(x)=23202696) +2593 train 7.047174 (lr=9.1675e-05) (hash(x)=22435944) +2594 train 7.046815 (lr=9.1625e-05) (hash(x)=20787439) +2595 train 6.605931 (lr=9.1576e-05) (hash(x)=18214283) +2596 train 6.833168 (lr=9.1527e-05) (hash(x)=20851477) +2597 train 6.815183 (lr=9.1477e-05) (hash(x)=20609675) +2598 train 6.931296 (lr=9.1428e-05) (hash(x)=20061218) +2599 train 6.963207 (lr=9.1378e-05) (hash(x)=21251127) +2600 val loss 7.2786 +2600 val perplexity 1448.9950 +2600 train 7.464593 (lr=9.1329e-05) (hash(x)=30948038) +2601 train 7.716879 (lr=9.1280e-05) (hash(x)=32279160) +2602 train 7.368330 (lr=9.1230e-05) (hash(x)=26607151) +2603 train 7.223308 (lr=9.1181e-05) (hash(x)=25097619) +2604 train 6.849856 (lr=9.1131e-05) (hash(x)=20892421) +2605 train 7.016165 (lr=9.1082e-05) (hash(x)=22212821) +2606 train 7.325673 (lr=9.1033e-05) (hash(x)=24720588) +2607 train 7.317976 (lr=9.0983e-05) (hash(x)=25800857) +2608 train 7.123479 (lr=9.0934e-05) (hash(x)=22901279) +2609 train 7.015022 (lr=9.0884e-05) (hash(x)=20921910) +2610 train 7.213456 (lr=9.0835e-05) (hash(x)=24846267) +2611 train 7.107011 (lr=9.0786e-05) (hash(x)=22918428) +2612 train 7.078366 (lr=9.0736e-05) (hash(x)=22805901) +2613 train 7.229917 (lr=9.0687e-05) (hash(x)=24345816) +2614 train 7.068241 (lr=9.0638e-05) (hash(x)=22962012) +2615 train 7.324013 (lr=9.0588e-05) (hash(x)=25836189) +2616 train 7.366664 (lr=9.0539e-05) (hash(x)=27922916) +2617 train 7.128012 (lr=9.0490e-05) (hash(x)=21697866) +2618 train 7.102986 (lr=9.0440e-05) (hash(x)=24283369) +2619 train 7.009983 (lr=9.0391e-05) (hash(x)=24504567) +2620 train 7.109537 (lr=9.0342e-05) (hash(x)=25557725) +2621 train 7.166635 (lr=9.0292e-05) (hash(x)=23135849) +2622 train 7.120267 (lr=9.0243e-05) (hash(x)=22888908) +2623 train 7.305341 (lr=9.0193e-05) (hash(x)=25999255) +2624 train 7.159476 (lr=9.0144e-05) (hash(x)=24446851) +2625 train 6.897486 (lr=9.0095e-05) (hash(x)=21137520) +2626 train 7.208097 (lr=9.0045e-05) (hash(x)=26245754) +2627 train 7.531111 (lr=8.9996e-05) (hash(x)=27308968) +2628 train 7.265526 (lr=8.9947e-05) (hash(x)=23961169) +2629 train 7.230190 (lr=8.9897e-05) (hash(x)=25924731) +2630 train 7.329492 (lr=8.9848e-05) (hash(x)=25782315) +2631 train 7.360800 (lr=8.9799e-05) (hash(x)=20149394) +2632 train 7.418690 (lr=8.9749e-05) (hash(x)=23801981) +2633 train 7.199128 (lr=8.9700e-05) (hash(x)=23830286) +2634 train 7.132105 (lr=8.9651e-05) (hash(x)=25325236) +2635 train 7.126816 (lr=8.9602e-05) (hash(x)=24498556) +2636 train 7.096548 (lr=8.9552e-05) (hash(x)=23693078) +2637 train 7.274852 (lr=8.9503e-05) (hash(x)=25484922) +2638 train 6.931360 (lr=8.9454e-05) (hash(x)=22645025) +2639 train 6.927725 (lr=8.9404e-05) (hash(x)=21999338) +2640 train 7.165341 (lr=8.9355e-05) (hash(x)=21758019) +2641 train 7.087839 (lr=8.9306e-05) (hash(x)=24064168) +2642 train 7.122556 (lr=8.9256e-05) (hash(x)=26847292) +2643 train 6.988991 (lr=8.9207e-05) (hash(x)=23280568) +2644 train 6.978539 (lr=8.9158e-05) (hash(x)=21749161) +2645 train 7.612235 (lr=8.9109e-05) (hash(x)=30082352) +2646 train 7.510972 (lr=8.9059e-05) (hash(x)=28334297) +2647 train 7.623560 (lr=8.9010e-05) (hash(x)=27611302) +2648 train 7.968849 (lr=8.8961e-05) (hash(x)=31007436) +2649 train 6.951497 (lr=8.8911e-05) (hash(x)=22356183) +2650 val loss 7.2822 +2650 val perplexity 1454.1537 +2650 train 7.001928 (lr=8.8862e-05) (hash(x)=23071731) +2651 train 7.042172 (lr=8.8813e-05) (hash(x)=23982308) +2652 train 7.347631 (lr=8.8764e-05) (hash(x)=25673823) +2653 train 7.134749 (lr=8.8714e-05) (hash(x)=22973788) +2654 train 7.299660 (lr=8.8665e-05) (hash(x)=25386647) +2655 train 7.055870 (lr=8.8616e-05) (hash(x)=22778356) +2656 train 7.258537 (lr=8.8567e-05) (hash(x)=26669130) +2657 train 6.992363 (lr=8.8517e-05) (hash(x)=23542930) +2658 train 7.143090 (lr=8.8468e-05) (hash(x)=23307871) +2659 train 7.116880 (lr=8.8419e-05) (hash(x)=23467046) +2660 train 7.228953 (lr=8.8370e-05) (hash(x)=24728872) +2661 train 7.815590 (lr=8.8320e-05) (hash(x)=29719902) +2662 train 7.122860 (lr=8.8271e-05) (hash(x)=25114165) +2663 train 7.052633 (lr=8.8222e-05) (hash(x)=24195959) +2664 train 7.262425 (lr=8.8173e-05) (hash(x)=26938509) +2665 train 7.442392 (lr=8.8123e-05) (hash(x)=27168434) +2666 train 7.559408 (lr=8.8074e-05) (hash(x)=27488221) +2667 train 8.261341 (lr=8.8025e-05) (hash(x)=32710438) +2668 train 7.362936 (lr=8.7976e-05) (hash(x)=25073185) +2669 train 7.359956 (lr=8.7927e-05) (hash(x)=26951664) +2670 train 7.548425 (lr=8.7877e-05) (hash(x)=24886228) +2671 train 6.984874 (lr=8.7828e-05) (hash(x)=19127465) +2672 train 7.266870 (lr=8.7779e-05) (hash(x)=27134917) +2673 train 7.196320 (lr=8.7730e-05) (hash(x)=25673955) +2674 train 7.730793 (lr=8.7680e-05) (hash(x)=27111776) +2675 train 7.635961 (lr=8.7631e-05) (hash(x)=28962580) +2676 train 7.193649 (lr=8.7582e-05) (hash(x)=25593381) +2677 train 7.232100 (lr=8.7533e-05) (hash(x)=25238916) +2678 train 7.128471 (lr=8.7484e-05) (hash(x)=27453574) +2679 train 7.141651 (lr=8.7435e-05) (hash(x)=22426274) +2680 train 7.141727 (lr=8.7385e-05) (hash(x)=22974780) +2681 train 7.166600 (lr=8.7336e-05) (hash(x)=24668644) +2682 train 7.175765 (lr=8.7287e-05) (hash(x)=26182084) +2683 train 7.372783 (lr=8.7238e-05) (hash(x)=25606512) +2684 train 7.204877 (lr=8.7189e-05) (hash(x)=24885252) +2685 train 6.992389 (lr=8.7140e-05) (hash(x)=21290254) +2686 train 6.938416 (lr=8.7090e-05) (hash(x)=21367078) +2687 train 7.140883 (lr=8.7041e-05) (hash(x)=23785205) +2688 train 7.040797 (lr=8.6992e-05) (hash(x)=24640056) +2689 train 7.508720 (lr=8.6943e-05) (hash(x)=27083886) +2690 train 7.187035 (lr=8.6894e-05) (hash(x)=23603571) +2691 train 7.295790 (lr=8.6845e-05) (hash(x)=24779414) +2692 train 6.984136 (lr=8.6796e-05) (hash(x)=22200693) +2693 train 7.322534 (lr=8.6746e-05) (hash(x)=26907868) +2694 train 7.637966 (lr=8.6697e-05) (hash(x)=32034827) +2695 train 7.501626 (lr=8.6648e-05) (hash(x)=28505676) +2696 train 7.110904 (lr=8.6599e-05) (hash(x)=23805750) +2697 train 7.442554 (lr=8.6550e-05) (hash(x)=29804750) +2698 train 7.700716 (lr=8.6501e-05) (hash(x)=28443583) +2699 train 7.617406 (lr=8.6452e-05) (hash(x)=29156288) +2700 val loss 7.2899 +2700 val perplexity 1465.4414 +2700 train 7.324156 (lr=8.6403e-05) (hash(x)=25895743) +2701 train 6.934135 (lr=8.6353e-05) (hash(x)=21173795) +2702 train 6.848325 (lr=8.6304e-05) (hash(x)=20790866) +2703 train 7.424274 (lr=8.6255e-05) (hash(x)=27706477) +2704 train 7.537274 (lr=8.6206e-05) (hash(x)=30358985) +2705 train 7.111615 (lr=8.6157e-05) (hash(x)=23548492) +2706 train 7.249528 (lr=8.6108e-05) (hash(x)=25879696) +2707 train 7.135613 (lr=8.6059e-05) (hash(x)=23711800) +2708 train 7.619934 (lr=8.6010e-05) (hash(x)=28763123) +2709 train 7.263283 (lr=8.5961e-05) (hash(x)=23327642) +2710 train 7.296059 (lr=8.5912e-05) (hash(x)=25634166) +2711 train 7.208327 (lr=8.5863e-05) (hash(x)=28684175) +2712 train 7.323938 (lr=8.5814e-05) (hash(x)=23996278) +2713 train 6.944099 (lr=8.5765e-05) (hash(x)=21795980) +2714 train 7.278722 (lr=8.5716e-05) (hash(x)=24840769) +2715 train 7.225730 (lr=8.5667e-05) (hash(x)=25225466) +2716 train 7.510985 (lr=8.5617e-05) (hash(x)=27500471) +2717 train 7.176994 (lr=8.5568e-05) (hash(x)=24703036) +2718 train 7.307013 (lr=8.5519e-05) (hash(x)=24294293) +2719 train 7.286287 (lr=8.5470e-05) (hash(x)=28003600) +2720 train 7.000175 (lr=8.5421e-05) (hash(x)=22822962) +2721 train 6.917851 (lr=8.5372e-05) (hash(x)=24189246) +2722 train 7.020351 (lr=8.5323e-05) (hash(x)=22608951) +2723 train 7.715230 (lr=8.5274e-05) (hash(x)=27989890) +2724 train 7.365302 (lr=8.5225e-05) (hash(x)=24175838) +2725 train 7.222098 (lr=8.5176e-05) (hash(x)=24781792) +2726 train 7.071835 (lr=8.5127e-05) (hash(x)=23413276) +2727 train 7.440989 (lr=8.5078e-05) (hash(x)=27586845) +2728 train 7.260968 (lr=8.5029e-05) (hash(x)=27336264) +2729 train 7.316760 (lr=8.4980e-05) (hash(x)=26808464) +2730 train 7.133188 (lr=8.4931e-05) (hash(x)=22312009) +2731 train 7.201115 (lr=8.4882e-05) (hash(x)=22373927) +2732 train 7.151989 (lr=8.4833e-05) (hash(x)=23428834) +2733 train 7.149568 (lr=8.4784e-05) (hash(x)=25304441) +2734 train 7.163881 (lr=8.4736e-05) (hash(x)=24798164) +2735 train 6.963146 (lr=8.4687e-05) (hash(x)=21176405) +2736 train 7.055589 (lr=8.4638e-05) (hash(x)=22343075) +2737 train 7.136636 (lr=8.4589e-05) (hash(x)=23825332) +2738 train 7.162351 (lr=8.4540e-05) (hash(x)=24191865) +2739 train 6.978343 (lr=8.4491e-05) (hash(x)=23806052) +2740 train 7.013591 (lr=8.4442e-05) (hash(x)=21764591) +2741 train 7.185741 (lr=8.4393e-05) (hash(x)=25548695) +2742 train 7.378273 (lr=8.4344e-05) (hash(x)=26847535) +2743 train 7.092270 (lr=8.4295e-05) (hash(x)=25888433) +2744 train 7.062103 (lr=8.4246e-05) (hash(x)=24327454) +2745 train 6.961892 (lr=8.4197e-05) (hash(x)=22543301) +2746 train 7.413574 (lr=8.4148e-05) (hash(x)=24593022) +2747 train 8.036551 (lr=8.4099e-05) (hash(x)=27797727) +2748 train 7.468097 (lr=8.4051e-05) (hash(x)=28067682) +2749 train 7.118494 (lr=8.4002e-05) (hash(x)=25278538) +2750 val loss 7.2655 +2750 val perplexity 1430.1156 +2750 train 7.048595 (lr=8.3953e-05) (hash(x)=23875731) +2751 train 7.249267 (lr=8.3904e-05) (hash(x)=27916982) +2752 train 7.221465 (lr=8.3855e-05) (hash(x)=25726799) +2753 train 7.061220 (lr=8.3806e-05) (hash(x)=25227141) +2754 train 7.312902 (lr=8.3757e-05) (hash(x)=27679212) +2755 train 7.026624 (lr=8.3708e-05) (hash(x)=24621793) +2756 train 6.930038 (lr=8.3660e-05) (hash(x)=21962296) +2757 train 7.277921 (lr=8.3611e-05) (hash(x)=24899679) +2758 train 6.983484 (lr=8.3562e-05) (hash(x)=21452158) +2759 train 7.090379 (lr=8.3513e-05) (hash(x)=24334708) +2760 train 7.347064 (lr=8.3464e-05) (hash(x)=25523041) +2761 train 7.483788 (lr=8.3415e-05) (hash(x)=30389813) +2762 train 6.995290 (lr=8.3367e-05) (hash(x)=22426014) +2763 train 7.087603 (lr=8.3318e-05) (hash(x)=24419143) +2764 train 7.163115 (lr=8.3269e-05) (hash(x)=24850536) +2765 train 7.254009 (lr=8.3220e-05) (hash(x)=24181393) +2766 train 6.770076 (lr=8.3171e-05) (hash(x)=18882503) +2767 train 7.248352 (lr=8.3122e-05) (hash(x)=25617709) +2768 train 7.183702 (lr=8.3074e-05) (hash(x)=24076662) +2769 train 7.099742 (lr=8.3025e-05) (hash(x)=21656802) +2770 train 7.047185 (lr=8.2976e-05) (hash(x)=21014265) +2771 train 7.203346 (lr=8.2927e-05) (hash(x)=24556034) +2772 train 6.953527 (lr=8.2879e-05) (hash(x)=22046665) +2773 train 7.234010 (lr=8.2830e-05) (hash(x)=26761579) +2774 train 8.725023 (lr=8.2781e-05) (hash(x)=41414315) +2775 train 7.126132 (lr=8.2732e-05) (hash(x)=25152362) +2776 train 7.311121 (lr=8.2684e-05) (hash(x)=25567641) +2777 train 7.252527 (lr=8.2635e-05) (hash(x)=25427935) +2778 train 7.323091 (lr=8.2586e-05) (hash(x)=25824457) +2779 train 7.243925 (lr=8.2537e-05) (hash(x)=24326376) +2780 train 7.264577 (lr=8.2489e-05) (hash(x)=27447230) +2781 train 7.135345 (lr=8.2440e-05) (hash(x)=24003710) +2782 train 7.056125 (lr=8.2391e-05) (hash(x)=24157390) +2783 train 7.142271 (lr=8.2342e-05) (hash(x)=24276512) +2784 train 6.974298 (lr=8.2294e-05) (hash(x)=21503752) +2785 train 6.879288 (lr=8.2245e-05) (hash(x)=20031488) +2786 train 6.938700 (lr=8.2196e-05) (hash(x)=21788715) +2787 train 7.116457 (lr=8.2148e-05) (hash(x)=24344695) +2788 train 7.155447 (lr=8.2099e-05) (hash(x)=22927763) +2789 train 7.046761 (lr=8.2050e-05) (hash(x)=23710755) +2790 train 7.277585 (lr=8.2002e-05) (hash(x)=26924620) +2791 train 7.594749 (lr=8.1953e-05) (hash(x)=26776133) +2792 train 7.066049 (lr=8.1904e-05) (hash(x)=19936770) +2793 train 7.208864 (lr=8.1856e-05) (hash(x)=25440959) +2794 train 7.157657 (lr=8.1807e-05) (hash(x)=25146097) +2795 train 6.963511 (lr=8.1758e-05) (hash(x)=21847282) +2796 train 7.150505 (lr=8.1710e-05) (hash(x)=25639784) +2797 train 6.932321 (lr=8.1661e-05) (hash(x)=21199921) +2798 train 7.125380 (lr=8.1612e-05) (hash(x)=22360806) +2799 train 6.585087 (lr=8.1564e-05) (hash(x)=20254159) +2800 val loss 7.2445 +2800 val perplexity 1400.4038 +2800 train 6.758412 (lr=8.1515e-05) (hash(x)=23348345) +2801 train 7.334805 (lr=8.1466e-05) (hash(x)=24908033) +2802 train 7.094120 (lr=8.1418e-05) (hash(x)=23350309) +2803 train 7.178707 (lr=8.1369e-05) (hash(x)=25044762) +2804 train 7.067691 (lr=8.1321e-05) (hash(x)=24071026) +2805 train 6.875372 (lr=8.1272e-05) (hash(x)=22169363) +2806 train 7.154972 (lr=8.1224e-05) (hash(x)=23757564) +2807 train 7.539099 (lr=8.1175e-05) (hash(x)=27873855) +2808 train 7.345676 (lr=8.1126e-05) (hash(x)=26577893) +2809 train 7.377014 (lr=8.1078e-05) (hash(x)=27001634) +2810 train 7.179375 (lr=8.1029e-05) (hash(x)=24796541) +2811 train 7.053343 (lr=8.0981e-05) (hash(x)=22575615) +2812 train 7.168199 (lr=8.0932e-05) (hash(x)=25876475) +2813 train 7.164619 (lr=8.0884e-05) (hash(x)=24765155) +2814 train 7.094872 (lr=8.0835e-05) (hash(x)=25785699) +2815 train 7.308908 (lr=8.0787e-05) (hash(x)=25113614) +2816 train 7.162610 (lr=8.0738e-05) (hash(x)=24415748) +2817 train 7.247430 (lr=8.0689e-05) (hash(x)=25140622) +2818 train 7.164212 (lr=8.0641e-05) (hash(x)=24845866) +2819 train 7.619698 (lr=8.0592e-05) (hash(x)=28062905) +2820 train 7.130528 (lr=8.0544e-05) (hash(x)=22041086) +2821 train 7.242959 (lr=8.0495e-05) (hash(x)=24957184) +2822 train 7.174989 (lr=8.0447e-05) (hash(x)=24360380) +2823 train 7.291291 (lr=8.0399e-05) (hash(x)=26192886) +2824 train 7.193603 (lr=8.0350e-05) (hash(x)=25001858) +2825 train 7.131510 (lr=8.0302e-05) (hash(x)=24721193) +2826 train 7.210164 (lr=8.0253e-05) (hash(x)=26186227) +2827 train 7.162053 (lr=8.0205e-05) (hash(x)=25770338) +2828 train 7.245432 (lr=8.0156e-05) (hash(x)=25920767) +2829 train 7.175865 (lr=8.0108e-05) (hash(x)=25060684) +2830 train 6.865067 (lr=8.0059e-05) (hash(x)=22933946) +2831 train 7.022978 (lr=8.0011e-05) (hash(x)=24614912) +2832 train 6.772675 (lr=7.9962e-05) (hash(x)=19955522) +2833 train 6.848190 (lr=7.9914e-05) (hash(x)=21111215) +2834 train 7.695271 (lr=7.9866e-05) (hash(x)=28817924) +2835 train 7.228500 (lr=7.9817e-05) (hash(x)=26934071) +2836 train 7.154758 (lr=7.9769e-05) (hash(x)=24768851) +2837 train 7.143777 (lr=7.9720e-05) (hash(x)=25706447) +2838 train 6.923439 (lr=7.9672e-05) (hash(x)=19579834) +2839 train 7.172708 (lr=7.9624e-05) (hash(x)=25397093) +2840 train 7.615564 (lr=7.9575e-05) (hash(x)=27902141) +2841 train 7.223973 (lr=7.9527e-05) (hash(x)=25383069) +2842 train 7.014044 (lr=7.9479e-05) (hash(x)=22007373) +2843 train 7.099154 (lr=7.9430e-05) (hash(x)=25925963) +2844 train 7.169384 (lr=7.9382e-05) (hash(x)=25711128) +2845 train 6.875932 (lr=7.9334e-05) (hash(x)=21881216) +2846 train 7.080669 (lr=7.9285e-05) (hash(x)=20277075) +2847 train 7.142330 (lr=7.9237e-05) (hash(x)=19811802) +2848 train 7.023715 (lr=7.9189e-05) (hash(x)=23878906) +2849 train 7.284020 (lr=7.9140e-05) (hash(x)=25034966) +2850 val loss 7.2462 +2850 val perplexity 1402.7462 +2850 train 7.300495 (lr=7.9092e-05) (hash(x)=24359507) +2851 train 7.064081 (lr=7.9044e-05) (hash(x)=23248423) +2852 train 7.046906 (lr=7.8995e-05) (hash(x)=21782773) +2853 train 7.199821 (lr=7.8947e-05) (hash(x)=23804418) +2854 train 7.214554 (lr=7.8899e-05) (hash(x)=22525078) +2855 train 7.217566 (lr=7.8851e-05) (hash(x)=25579655) +2856 train 7.316776 (lr=7.8802e-05) (hash(x)=27048876) +2857 train 7.477225 (lr=7.8754e-05) (hash(x)=26468479) +2858 train 7.117659 (lr=7.8706e-05) (hash(x)=23854933) +2859 train 7.517868 (lr=7.8658e-05) (hash(x)=25537603) +2860 train 6.942726 (lr=7.8609e-05) (hash(x)=20979252) +2861 train 7.477115 (lr=7.8561e-05) (hash(x)=26504374) +2862 train 7.276851 (lr=7.8513e-05) (hash(x)=27561842) +2863 train 7.261560 (lr=7.8465e-05) (hash(x)=26096514) +2864 train 7.276897 (lr=7.8416e-05) (hash(x)=25926899) +2865 train 7.308393 (lr=7.8368e-05) (hash(x)=26058348) +2866 train 7.307574 (lr=7.8320e-05) (hash(x)=29802259) +2867 train 7.231240 (lr=7.8272e-05) (hash(x)=24132888) +2868 train 6.954043 (lr=7.8224e-05) (hash(x)=23369410) +2869 train 7.119308 (lr=7.8176e-05) (hash(x)=25387506) +2870 train 7.300440 (lr=7.8127e-05) (hash(x)=27375344) +2871 train 7.040932 (lr=7.8079e-05) (hash(x)=22589633) +2872 train 7.211360 (lr=7.8031e-05) (hash(x)=23250237) +2873 train 7.093208 (lr=7.7983e-05) (hash(x)=25511322) +2874 train 6.790097 (lr=7.7935e-05) (hash(x)=18356418) +2875 train 7.205760 (lr=7.7887e-05) (hash(x)=27781566) +2876 train 7.071491 (lr=7.7839e-05) (hash(x)=24878173) +2877 train 7.549407 (lr=7.7790e-05) (hash(x)=30018637) +2878 train 7.374261 (lr=7.7742e-05) (hash(x)=27168416) +2879 train 7.366536 (lr=7.7694e-05) (hash(x)=26757147) +2880 train 7.400805 (lr=7.7646e-05) (hash(x)=26637081) +2881 train 7.243814 (lr=7.7598e-05) (hash(x)=24795024) +2882 train 7.510901 (lr=7.7550e-05) (hash(x)=29787745) +2883 train 7.354616 (lr=7.7502e-05) (hash(x)=26649864) +2884 train 7.214290 (lr=7.7454e-05) (hash(x)=27306612) +2885 train 7.305849 (lr=7.7406e-05) (hash(x)=27568311) +2886 train 7.336774 (lr=7.7358e-05) (hash(x)=27440150) +2887 train 7.065598 (lr=7.7310e-05) (hash(x)=24963730) +2888 train 7.070259 (lr=7.7262e-05) (hash(x)=23619807) +2889 train 7.573325 (lr=7.7214e-05) (hash(x)=29447356) +2890 train 7.084429 (lr=7.7166e-05) (hash(x)=25144675) +2891 train 7.010863 (lr=7.7118e-05) (hash(x)=25249959) +2892 train 7.045126 (lr=7.7070e-05) (hash(x)=26608712) +2893 train 7.061609 (lr=7.7022e-05) (hash(x)=26333258) +2894 train 6.853191 (lr=7.6974e-05) (hash(x)=20682182) +2895 train 7.288971 (lr=7.6926e-05) (hash(x)=27703124) +2896 train 7.090152 (lr=7.6878e-05) (hash(x)=23228180) +2897 train 6.958008 (lr=7.6830e-05) (hash(x)=25252411) +2898 train 6.940531 (lr=7.6782e-05) (hash(x)=22879178) +2899 train 7.244934 (lr=7.6734e-05) (hash(x)=26459082) +2900 val loss 7.2368 +2900 val perplexity 1389.6774 +2900 train 7.072170 (lr=7.6686e-05) (hash(x)=24569501) +2901 train 6.872340 (lr=7.6638e-05) (hash(x)=19803884) +2902 train 6.908760 (lr=7.6590e-05) (hash(x)=18799747) +2903 train 7.210325 (lr=7.6542e-05) (hash(x)=24781713) +2904 train 7.333446 (lr=7.6494e-05) (hash(x)=25016590) +2905 train 7.523705 (lr=7.6446e-05) (hash(x)=29006906) +2906 train 7.261623 (lr=7.6398e-05) (hash(x)=24069959) +2907 train 7.410556 (lr=7.6350e-05) (hash(x)=26597693) +2908 train 7.042221 (lr=7.6303e-05) (hash(x)=25014146) +2909 train 7.273302 (lr=7.6255e-05) (hash(x)=24943747) +2910 train 7.191306 (lr=7.6207e-05) (hash(x)=27847542) +2911 train 7.135271 (lr=7.6159e-05) (hash(x)=24720476) +2912 train 6.991139 (lr=7.6111e-05) (hash(x)=24388804) +2913 train 7.105176 (lr=7.6063e-05) (hash(x)=23567535) +2914 train 7.421548 (lr=7.6015e-05) (hash(x)=29673625) +2915 train 7.156063 (lr=7.5968e-05) (hash(x)=23691295) +2916 train 7.519980 (lr=7.5920e-05) (hash(x)=26572819) +2917 train 7.165109 (lr=7.5872e-05) (hash(x)=23237812) +2918 train 7.455571 (lr=7.5824e-05) (hash(x)=26531016) +2919 train 6.966783 (lr=7.5776e-05) (hash(x)=23481301) +2920 train 7.264051 (lr=7.5729e-05) (hash(x)=24839184) +2921 train 7.125577 (lr=7.5681e-05) (hash(x)=23327755) +2922 train 7.362827 (lr=7.5633e-05) (hash(x)=26347114) +2923 train 7.036602 (lr=7.5585e-05) (hash(x)=23295676) +2924 train 7.089124 (lr=7.5538e-05) (hash(x)=24557178) +2925 train 7.148159 (lr=7.5490e-05) (hash(x)=26067788) +2926 train 7.100811 (lr=7.5442e-05) (hash(x)=25694982) +2927 train 7.180452 (lr=7.5394e-05) (hash(x)=25641033) +2928 train 7.240599 (lr=7.5347e-05) (hash(x)=24906422) +2929 train 7.411507 (lr=7.5299e-05) (hash(x)=27803515) +2930 train 7.377812 (lr=7.5251e-05) (hash(x)=26208803) +2931 train 6.873065 (lr=7.5204e-05) (hash(x)=22441379) +2932 train 7.128537 (lr=7.5156e-05) (hash(x)=24741626) +2933 train 7.019507 (lr=7.5108e-05) (hash(x)=24595257) +2934 train 7.053673 (lr=7.5060e-05) (hash(x)=23939167) +2935 train 7.324837 (lr=7.5013e-05) (hash(x)=27369437) +2936 train 6.984540 (lr=7.4965e-05) (hash(x)=21409783) +2937 train 7.259927 (lr=7.4918e-05) (hash(x)=25923735) +2938 train 7.266501 (lr=7.4870e-05) (hash(x)=29559511) +2939 train 7.134374 (lr=7.4822e-05) (hash(x)=24482272) +2940 train 7.131546 (lr=7.4775e-05) (hash(x)=24767658) +2941 train 7.306473 (lr=7.4727e-05) (hash(x)=26425020) +2942 train 7.646623 (lr=7.4679e-05) (hash(x)=27444868) +2943 train 7.124422 (lr=7.4632e-05) (hash(x)=24760900) +2944 train 7.173539 (lr=7.4584e-05) (hash(x)=25605407) +2945 train 7.053967 (lr=7.4537e-05) (hash(x)=22886951) +2946 train 7.361217 (lr=7.4489e-05) (hash(x)=26112205) +2947 train 7.169116 (lr=7.4442e-05) (hash(x)=23919156) +2948 train 7.149082 (lr=7.4394e-05) (hash(x)=23729312) +2949 train 7.428178 (lr=7.4346e-05) (hash(x)=30440878) +2950 val loss 7.2464 +2950 val perplexity 1403.1102 +2950 train 6.904855 (lr=7.4299e-05) (hash(x)=20004041) +2951 train 6.858503 (lr=7.4251e-05) (hash(x)=21692546) +2952 train 6.923130 (lr=7.4204e-05) (hash(x)=23021681) +2953 train 7.279266 (lr=7.4156e-05) (hash(x)=26663597) +2954 train 7.129912 (lr=7.4109e-05) (hash(x)=23727385) +2955 train 7.111631 (lr=7.4061e-05) (hash(x)=27692087) +2956 train 7.165038 (lr=7.4014e-05) (hash(x)=24003378) +2957 train 7.813458 (lr=7.3966e-05) (hash(x)=29534673) +2958 train 7.052186 (lr=7.3919e-05) (hash(x)=22875068) +2959 train 7.026322 (lr=7.3872e-05) (hash(x)=22720391) +2960 train 6.823126 (lr=7.3824e-05) (hash(x)=17997400) +2961 train 7.036035 (lr=7.3777e-05) (hash(x)=22853822) +2962 train 7.116028 (lr=7.3729e-05) (hash(x)=25238004) +2963 train 7.228072 (lr=7.3682e-05) (hash(x)=26146560) +2964 train 7.340086 (lr=7.3634e-05) (hash(x)=21894867) +2965 train 7.316949 (lr=7.3587e-05) (hash(x)=23001150) +2966 train 7.051181 (lr=7.3540e-05) (hash(x)=23392923) +2967 train 7.100591 (lr=7.3492e-05) (hash(x)=24376979) +2968 train 7.078317 (lr=7.3445e-05) (hash(x)=23781449) +2969 train 7.224434 (lr=7.3397e-05) (hash(x)=25315495) +2970 train 7.360393 (lr=7.3350e-05) (hash(x)=27165470) +2971 train 7.189303 (lr=7.3303e-05) (hash(x)=22917712) +2972 train 7.485588 (lr=7.3255e-05) (hash(x)=27928456) +2973 train 6.906110 (lr=7.3208e-05) (hash(x)=19890855) +2974 train 6.881412 (lr=7.3161e-05) (hash(x)=21318134) +2975 train 7.032167 (lr=7.3113e-05) (hash(x)=22244509) +2976 train 6.934082 (lr=7.3066e-05) (hash(x)=21293137) +2977 train 7.055307 (lr=7.3019e-05) (hash(x)=23465789) +2978 train 7.019048 (lr=7.2972e-05) (hash(x)=21169753) +2979 train 7.362480 (lr=7.2924e-05) (hash(x)=25243385) +2980 train 7.413460 (lr=7.2877e-05) (hash(x)=27465812) +2981 train 7.125650 (lr=7.2830e-05) (hash(x)=24615492) +2982 train 7.058158 (lr=7.2783e-05) (hash(x)=23081307) +2983 train 6.825589 (lr=7.2735e-05) (hash(x)=21831960) +2984 train 6.953378 (lr=7.2688e-05) (hash(x)=23242850) +2985 train 7.055161 (lr=7.2641e-05) (hash(x)=24308188) +2986 train 7.252616 (lr=7.2594e-05) (hash(x)=28541601) +2987 train 7.163673 (lr=7.2546e-05) (hash(x)=24842373) +2988 train 6.881099 (lr=7.2499e-05) (hash(x)=21967126) +2989 train 7.093812 (lr=7.2452e-05) (hash(x)=22951616) +2990 train 7.207868 (lr=7.2405e-05) (hash(x)=24325714) +2991 train 6.996349 (lr=7.2358e-05) (hash(x)=24921535) +2992 train 7.239929 (lr=7.2311e-05) (hash(x)=25937112) +2993 train 6.890308 (lr=7.2263e-05) (hash(x)=20716218) +2994 train 7.205686 (lr=7.2216e-05) (hash(x)=25450724) +2995 train 7.148690 (lr=7.2169e-05) (hash(x)=24344615) +2996 train 6.894394 (lr=7.2122e-05) (hash(x)=20299058) +2997 train 7.103622 (lr=7.2075e-05) (hash(x)=23859426) +2998 train 7.100668 (lr=7.2028e-05) (hash(x)=23094397) +2999 train 7.378500 (lr=7.1981e-05) (hash(x)=25381251) +3000 val loss 7.2400 +3000 val perplexity 1394.0936 +3000 train 7.137064 (lr=7.1934e-05) (hash(x)=23586527) +3001 train 7.016431 (lr=7.1887e-05) (hash(x)=24220410) +3002 train 6.915086 (lr=7.1840e-05) (hash(x)=20597347) +3003 train 6.995281 (lr=7.1793e-05) (hash(x)=22887303) +3004 train 7.312374 (lr=7.1746e-05) (hash(x)=25869462) +3005 train 7.036348 (lr=7.1699e-05) (hash(x)=22098530) +3006 train 7.335091 (lr=7.1651e-05) (hash(x)=26246291) +3007 train 7.242556 (lr=7.1604e-05) (hash(x)=25687352) +3008 train 7.007677 (lr=7.1557e-05) (hash(x)=25425646) +3009 train 7.183434 (lr=7.1510e-05) (hash(x)=26021124) +3010 train 7.224548 (lr=7.1464e-05) (hash(x)=25392057) +3011 train 7.323465 (lr=7.1417e-05) (hash(x)=27791412) +3012 train 7.135858 (lr=7.1370e-05) (hash(x)=23181098) +3013 train 7.139219 (lr=7.1323e-05) (hash(x)=25521889) +3014 train 6.959722 (lr=7.1276e-05) (hash(x)=21685795) +3015 train 7.103055 (lr=7.1229e-05) (hash(x)=25221654) +3016 train 7.309937 (lr=7.1182e-05) (hash(x)=24888744) +3017 train 7.193233 (lr=7.1135e-05) (hash(x)=24200150) +3018 train 7.119599 (lr=7.1088e-05) (hash(x)=26943942) +3019 train 7.111903 (lr=7.1041e-05) (hash(x)=23243731) +3020 train 6.957119 (lr=7.0994e-05) (hash(x)=21068284) +3021 train 7.143114 (lr=7.0947e-05) (hash(x)=23876902) +3022 train 7.271657 (lr=7.0901e-05) (hash(x)=25337639) +3023 train 7.191866 (lr=7.0854e-05) (hash(x)=24469863) +3024 train 7.615872 (lr=7.0807e-05) (hash(x)=27850876) +3025 train 7.468712 (lr=7.0760e-05) (hash(x)=20515778) +3026 train 7.229370 (lr=7.0713e-05) (hash(x)=29019173) +3027 train 6.893331 (lr=7.0666e-05) (hash(x)=22484936) +3028 train 7.051132 (lr=7.0620e-05) (hash(x)=24639400) +3029 train 7.215103 (lr=7.0573e-05) (hash(x)=26835174) +3030 train 7.341422 (lr=7.0526e-05) (hash(x)=29843763) +3031 train 7.066621 (lr=7.0479e-05) (hash(x)=25291413) +3032 train 7.033599 (lr=7.0432e-05) (hash(x)=24590244) +3033 train 7.277445 (lr=7.0386e-05) (hash(x)=28880142) +3034 train 6.999025 (lr=7.0339e-05) (hash(x)=23372199) +3035 train 7.002515 (lr=7.0292e-05) (hash(x)=23952225) +3036 train 7.149316 (lr=7.0246e-05) (hash(x)=24589186) +3037 train 7.096971 (lr=7.0199e-05) (hash(x)=23260323) +3038 train 7.259407 (lr=7.0152e-05) (hash(x)=25824498) +3039 train 7.199721 (lr=7.0105e-05) (hash(x)=25744274) +3040 train 7.168518 (lr=7.0059e-05) (hash(x)=21610247) +3041 train 7.280410 (lr=7.0012e-05) (hash(x)=25079786) +3042 train 6.926687 (lr=6.9965e-05) (hash(x)=23219195) +3043 train 6.851724 (lr=6.9919e-05) (hash(x)=22616739) +3044 train 7.144592 (lr=6.9872e-05) (hash(x)=24908480) +3045 train 6.984775 (lr=6.9826e-05) (hash(x)=22293489) +3046 train 7.022012 (lr=6.9779e-05) (hash(x)=23557651) +3047 train 7.081725 (lr=6.9732e-05) (hash(x)=24246963) +3048 train 7.216133 (lr=6.9686e-05) (hash(x)=24490083) +3049 train 7.184059 (lr=6.9639e-05) (hash(x)=22372895) +3050 val loss 7.2248 +3050 val perplexity 1373.0209 +3050 train 6.909472 (lr=6.9593e-05) (hash(x)=21759470) +3051 train 6.799283 (lr=6.9546e-05) (hash(x)=19407094) +3052 train 7.172381 (lr=6.9499e-05) (hash(x)=23957047) +3053 train 7.259843 (lr=6.9453e-05) (hash(x)=24719318) +3054 train 7.047113 (lr=6.9406e-05) (hash(x)=20719314) +3055 train 7.011814 (lr=6.9360e-05) (hash(x)=19724058) +3056 train 6.813692 (lr=6.9313e-05) (hash(x)=14407266) +3057 train 6.663932 (lr=6.9267e-05) (hash(x)=12468292) +3058 train 6.959165 (lr=6.9220e-05) (hash(x)=16098279) +3059 train 7.052383 (lr=6.9174e-05) (hash(x)=18836491) +3060 train 6.885153 (lr=6.9127e-05) (hash(x)=19132277) +3061 train 7.020581 (lr=6.9081e-05) (hash(x)=22814208) +3062 train 7.077110 (lr=6.9034e-05) (hash(x)=24838508) +3063 train 6.987632 (lr=6.8988e-05) (hash(x)=20705649) +3064 train 7.955265 (lr=6.8942e-05) (hash(x)=29416914) +3065 train 7.434797 (lr=6.8895e-05) (hash(x)=25972430) +3066 train 6.788118 (lr=6.8849e-05) (hash(x)=23705805) +3067 train 6.879768 (lr=6.8802e-05) (hash(x)=21325875) +3068 train 7.086683 (lr=6.8756e-05) (hash(x)=23526506) +3069 train 7.560318 (lr=6.8710e-05) (hash(x)=27282337) +3070 train 7.414407 (lr=6.8663e-05) (hash(x)=27968043) +3071 train 7.218063 (lr=6.8617e-05) (hash(x)=24938685) +3072 train 7.418813 (lr=6.8571e-05) (hash(x)=26942737) +3073 train 7.325157 (lr=6.8524e-05) (hash(x)=23506879) +3074 train 7.007521 (lr=6.8478e-05) (hash(x)=23589913) +3075 train 7.210196 (lr=6.8432e-05) (hash(x)=25152403) +3076 train 7.325203 (lr=6.8385e-05) (hash(x)=23425868) +3077 train 7.492658 (lr=6.8339e-05) (hash(x)=23966181) +3078 train 7.539795 (lr=6.8293e-05) (hash(x)=27312570) +3079 train 7.155611 (lr=6.8247e-05) (hash(x)=21707000) +3080 train 7.093803 (lr=6.8200e-05) (hash(x)=25600427) +3081 train 7.216015 (lr=6.8154e-05) (hash(x)=24270631) +3082 train 7.303684 (lr=6.8108e-05) (hash(x)=25199537) +3083 train 6.573837 (lr=6.8062e-05) (hash(x)=17952018) +3084 train 6.688937 (lr=6.8015e-05) (hash(x)=18733143) +3085 train 7.334252 (lr=6.7969e-05) (hash(x)=26946100) +3086 train 7.165386 (lr=6.7923e-05) (hash(x)=25547515) +3087 train 7.107728 (lr=6.7877e-05) (hash(x)=24948980) +3088 train 8.339597 (lr=6.7831e-05) (hash(x)=35461645) +3089 train 7.369094 (lr=6.7785e-05) (hash(x)=28330877) +3090 train 7.267433 (lr=6.7738e-05) (hash(x)=27687861) +3091 train 7.393584 (lr=6.7692e-05) (hash(x)=28012110) +3092 train 7.233634 (lr=6.7646e-05) (hash(x)=24684480) +3093 train 7.201790 (lr=6.7600e-05) (hash(x)=26225786) +3094 train 6.884593 (lr=6.7554e-05) (hash(x)=23098156) +3095 train 7.517803 (lr=6.7508e-05) (hash(x)=30773958) +3096 train 7.792931 (lr=6.7462e-05) (hash(x)=28640406) +3097 train 7.699715 (lr=6.7416e-05) (hash(x)=28201086) +3098 train 8.051143 (lr=6.7370e-05) (hash(x)=35002344) +3099 train 7.580839 (lr=6.7324e-05) (hash(x)=29481068) +3100 val loss 7.2426 +3100 val perplexity 1397.7820 +3100 train 7.127288 (lr=6.7278e-05) (hash(x)=26374528) +3101 train 7.122060 (lr=6.7232e-05) (hash(x)=24153602) +3102 train 7.171944 (lr=6.7186e-05) (hash(x)=25478746) +3103 train 7.453982 (lr=6.7140e-05) (hash(x)=26769046) +3104 train 7.086713 (lr=6.7094e-05) (hash(x)=21841970) +3105 train 7.342696 (lr=6.7048e-05) (hash(x)=27693052) +3106 train 6.848405 (lr=6.7002e-05) (hash(x)=20689448) +3107 train 7.154228 (lr=6.6956e-05) (hash(x)=26755048) +3108 train 7.202185 (lr=6.6910e-05) (hash(x)=24431904) +3109 train 7.062569 (lr=6.6864e-05) (hash(x)=21009792) +3110 train 7.121327 (lr=6.6818e-05) (hash(x)=21909003) +3111 train 7.176582 (lr=6.6772e-05) (hash(x)=18849656) +3112 train 7.284333 (lr=6.6726e-05) (hash(x)=22223376) +3113 train 7.571507 (lr=6.6680e-05) (hash(x)=25652491) +3114 train 7.478256 (lr=6.6635e-05) (hash(x)=23521434) +3115 train 7.506807 (lr=6.6589e-05) (hash(x)=25449800) +3116 train 7.825079 (lr=6.6543e-05) (hash(x)=27655847) +3117 train 7.901149 (lr=6.6497e-05) (hash(x)=29878248) +3118 train 7.946772 (lr=6.6451e-05) (hash(x)=30444094) +3119 train 7.578621 (lr=6.6405e-05) (hash(x)=24624950) +3120 train 6.883935 (lr=6.6360e-05) (hash(x)=20798511) +3121 train 7.294782 (lr=6.6314e-05) (hash(x)=26581679) +3122 train 7.192272 (lr=6.6268e-05) (hash(x)=25333422) +3123 train 7.231777 (lr=6.6222e-05) (hash(x)=26174069) +3124 train 7.301602 (lr=6.6177e-05) (hash(x)=25219475) +3125 train 7.204364 (lr=6.6131e-05) (hash(x)=20919061) +3126 train 7.153150 (lr=6.6085e-05) (hash(x)=23828688) +3127 train 7.672241 (lr=6.6039e-05) (hash(x)=27299605) +3128 train 7.034186 (lr=6.5994e-05) (hash(x)=23797514) +3129 train 7.277701 (lr=6.5948e-05) (hash(x)=23601883) +3130 train 7.473778 (lr=6.5902e-05) (hash(x)=31003964) +3131 train 7.231320 (lr=6.5857e-05) (hash(x)=24777273) +3132 train 7.109904 (lr=6.5811e-05) (hash(x)=25403249) +3133 train 7.313007 (lr=6.5765e-05) (hash(x)=28913150) +3134 train 7.261182 (lr=6.5720e-05) (hash(x)=26541508) +3135 train 7.239206 (lr=6.5674e-05) (hash(x)=24113445) +3136 train 7.043807 (lr=6.5629e-05) (hash(x)=25464565) +3137 train 7.272860 (lr=6.5583e-05) (hash(x)=26581432) +3138 train 7.119508 (lr=6.5537e-05) (hash(x)=23074513) +3139 train 6.976985 (lr=6.5492e-05) (hash(x)=23970384) +3140 train 7.219126 (lr=6.5446e-05) (hash(x)=26694495) +3141 train 7.190346 (lr=6.5401e-05) (hash(x)=26883445) +3142 train 7.350296 (lr=6.5355e-05) (hash(x)=28632211) +3143 train 7.765839 (lr=6.5310e-05) (hash(x)=32644465) +3144 train 7.518328 (lr=6.5264e-05) (hash(x)=27490443) +3145 train 7.072849 (lr=6.5219e-05) (hash(x)=23814853) +3146 train 7.518961 (lr=6.5173e-05) (hash(x)=29664236) +3147 train 7.814092 (lr=6.5128e-05) (hash(x)=29951548) +3148 train 7.568578 (lr=6.5082e-05) (hash(x)=28426503) +3149 train 6.964276 (lr=6.5037e-05) (hash(x)=23727657) +3150 val loss 7.2289 +3150 val perplexity 1378.7701 +3150 train 7.120033 (lr=6.4991e-05) (hash(x)=21430659) +3151 train 7.186920 (lr=6.4946e-05) (hash(x)=25829219) +3152 train 7.370422 (lr=6.4901e-05) (hash(x)=29735208) +3153 train 7.362239 (lr=6.4855e-05) (hash(x)=28173447) +3154 train 7.087656 (lr=6.4810e-05) (hash(x)=22909641) +3155 train 7.255344 (lr=6.4764e-05) (hash(x)=20556094) +3156 train 6.990785 (lr=6.4719e-05) (hash(x)=24013769) +3157 train 7.004132 (lr=6.4674e-05) (hash(x)=22525971) +3158 train 7.079631 (lr=6.4628e-05) (hash(x)=25492728) +3159 train 7.110924 (lr=6.4583e-05) (hash(x)=25194550) +3160 train 7.226157 (lr=6.4538e-05) (hash(x)=25610603) +3161 train 7.190436 (lr=6.4492e-05) (hash(x)=23848640) +3162 train 7.025434 (lr=6.4447e-05) (hash(x)=24082226) +3163 train 7.392819 (lr=6.4402e-05) (hash(x)=28482186) +3164 train 7.304203 (lr=6.4357e-05) (hash(x)=27542978) +3165 train 7.042340 (lr=6.4311e-05) (hash(x)=22540954) +3166 train 7.209557 (lr=6.4266e-05) (hash(x)=26103641) +3167 train 7.148616 (lr=6.4221e-05) (hash(x)=25941804) +3168 train 7.175654 (lr=6.4176e-05) (hash(x)=25965921) +3169 train 7.421231 (lr=6.4131e-05) (hash(x)=25631269) +3170 train 7.002936 (lr=6.4085e-05) (hash(x)=23471525) +3171 train 7.223062 (lr=6.4040e-05) (hash(x)=27049208) +3172 train 7.244462 (lr=6.3995e-05) (hash(x)=27074992) +3173 train 7.191185 (lr=6.3950e-05) (hash(x)=25712617) +3174 train 7.131336 (lr=6.3905e-05) (hash(x)=25884917) +3175 train 7.168618 (lr=6.3860e-05) (hash(x)=24075727) +3176 train 7.041097 (lr=6.3815e-05) (hash(x)=23681759) +3177 train 7.309785 (lr=6.3770e-05) (hash(x)=25786577) +3178 train 7.287771 (lr=6.3724e-05) (hash(x)=27307614) +3179 train 7.328613 (lr=6.3679e-05) (hash(x)=25082806) +3180 train 7.309564 (lr=6.3634e-05) (hash(x)=26098308) +3181 train 7.091155 (lr=6.3589e-05) (hash(x)=24080140) +3182 train 7.298416 (lr=6.3544e-05) (hash(x)=26399395) +3183 train 7.358885 (lr=6.3499e-05) (hash(x)=23104539) +3184 train 6.991872 (lr=6.3454e-05) (hash(x)=23356930) +3185 train 7.245395 (lr=6.3409e-05) (hash(x)=27972420) +3186 train 6.913473 (lr=6.3364e-05) (hash(x)=21338924) +3187 train 7.343587 (lr=6.3319e-05) (hash(x)=25351113) +3188 train 7.279359 (lr=6.3274e-05) (hash(x)=26019439) +3189 train 7.335065 (lr=6.3229e-05) (hash(x)=30149312) +3190 train 7.036655 (lr=6.3185e-05) (hash(x)=23028152) +3191 train 7.396297 (lr=6.3140e-05) (hash(x)=23018983) +3192 train 7.044217 (lr=6.3095e-05) (hash(x)=23190787) +3193 train 7.440151 (lr=6.3050e-05) (hash(x)=27798543) +3194 train 7.233933 (lr=6.3005e-05) (hash(x)=25193663) +3195 train 7.035012 (lr=6.2960e-05) (hash(x)=25302106) +3196 train 7.195107 (lr=6.2915e-05) (hash(x)=24325364) +3197 train 7.217416 (lr=6.2870e-05) (hash(x)=25399101) +3198 train 7.054439 (lr=6.2826e-05) (hash(x)=23606439) +3199 train 7.079405 (lr=6.2781e-05) (hash(x)=24422929) +3200 val loss 7.2181 +3200 val perplexity 1363.9617 +3200 train 7.273642 (lr=6.2736e-05) (hash(x)=24760381) +3201 train 6.929501 (lr=6.2691e-05) (hash(x)=23278576) +3202 train 7.156085 (lr=6.2646e-05) (hash(x)=24897511) +3203 train 7.469859 (lr=6.2602e-05) (hash(x)=29052117) +3204 train 7.202099 (lr=6.2557e-05) (hash(x)=25772923) +3205 train 7.338848 (lr=6.2512e-05) (hash(x)=25885977) +3206 train 7.137119 (lr=6.2468e-05) (hash(x)=21985272) +3207 train 7.072191 (lr=6.2423e-05) (hash(x)=23389696) +3208 train 6.974292 (lr=6.2378e-05) (hash(x)=25299042) +3209 train 7.216855 (lr=6.2333e-05) (hash(x)=23703987) +3210 train 7.111212 (lr=6.2289e-05) (hash(x)=23362342) +3211 train 7.175630 (lr=6.2244e-05) (hash(x)=23962503) +3212 train 7.100005 (lr=6.2200e-05) (hash(x)=21216023) +3213 train 7.176328 (lr=6.2155e-05) (hash(x)=25841931) +3214 train 7.029823 (lr=6.2110e-05) (hash(x)=23631428) +3215 train 7.430075 (lr=6.2066e-05) (hash(x)=29102969) +3216 train 7.161858 (lr=6.2021e-05) (hash(x)=25782766) +3217 train 7.428073 (lr=6.1977e-05) (hash(x)=28825867) +3218 train 7.353284 (lr=6.1932e-05) (hash(x)=24609499) +3219 train 7.323111 (lr=6.1888e-05) (hash(x)=24948166) +3220 train 7.366832 (lr=6.1843e-05) (hash(x)=26919841) +3221 train 7.226196 (lr=6.1798e-05) (hash(x)=27236198) +3222 train 6.994850 (lr=6.1754e-05) (hash(x)=24029305) +3223 train 7.555684 (lr=6.1709e-05) (hash(x)=28359859) +3224 train 7.367603 (lr=6.1665e-05) (hash(x)=24886008) +3225 train 7.162773 (lr=6.1621e-05) (hash(x)=27159867) +3226 train 7.439823 (lr=6.1576e-05) (hash(x)=20672023) +3227 train 7.124362 (lr=6.1532e-05) (hash(x)=22360298) +3228 train 7.564490 (lr=6.1487e-05) (hash(x)=27478658) +3229 train 7.338804 (lr=6.1443e-05) (hash(x)=26575886) +3230 train 7.529354 (lr=6.1398e-05) (hash(x)=26890615) +3231 train 7.148349 (lr=6.1354e-05) (hash(x)=24630955) +3232 train 7.448886 (lr=6.1310e-05) (hash(x)=27016054) +3233 train 7.638959 (lr=6.1265e-05) (hash(x)=28444407) +3234 train 7.040070 (lr=6.1221e-05) (hash(x)=24053336) +3235 train 7.345057 (lr=6.1177e-05) (hash(x)=26897402) +3236 train 7.514679 (lr=6.1132e-05) (hash(x)=29451214) +3237 train 7.270786 (lr=6.1088e-05) (hash(x)=27268677) +3238 train 7.434552 (lr=6.1044e-05) (hash(x)=27494000) +3239 train 7.086983 (lr=6.1000e-05) (hash(x)=22969113) +3240 train 7.036760 (lr=6.0955e-05) (hash(x)=21944576) +3241 train 7.250162 (lr=6.0911e-05) (hash(x)=21671079) +3242 train 7.137022 (lr=6.0867e-05) (hash(x)=23912980) +3243 train 7.111852 (lr=6.0823e-05) (hash(x)=25205781) +3244 train 7.087683 (lr=6.0779e-05) (hash(x)=25654244) +3245 train 7.040136 (lr=6.0734e-05) (hash(x)=23335929) +3246 train 7.406106 (lr=6.0690e-05) (hash(x)=27953926) +3247 train 7.190828 (lr=6.0646e-05) (hash(x)=27004415) +3248 train 6.897163 (lr=6.0602e-05) (hash(x)=20471566) +3249 train 7.097276 (lr=6.0558e-05) (hash(x)=25797941) +3250 val loss 7.2107 +3250 val perplexity 1353.8733 +3250 train 6.993199 (lr=6.0514e-05) (hash(x)=21787064) +3251 train 7.010049 (lr=6.0470e-05) (hash(x)=22974875) +3252 train 7.210670 (lr=6.0426e-05) (hash(x)=28431267) +3253 train 7.139832 (lr=6.0381e-05) (hash(x)=25584910) +3254 train 6.908988 (lr=6.0337e-05) (hash(x)=23888922) +3255 train 7.141323 (lr=6.0293e-05) (hash(x)=22265063) +3256 train 6.766060 (lr=6.0249e-05) (hash(x)=21926624) +3257 train 7.058704 (lr=6.0205e-05) (hash(x)=23073191) +3258 train 7.068039 (lr=6.0161e-05) (hash(x)=24409183) +3259 train 7.127982 (lr=6.0117e-05) (hash(x)=23312114) +3260 train 7.040035 (lr=6.0073e-05) (hash(x)=21001289) +3261 train 7.229677 (lr=6.0029e-05) (hash(x)=25514824) +3262 train 7.018485 (lr=5.9985e-05) (hash(x)=22526800) +3263 train 7.399165 (lr=5.9942e-05) (hash(x)=26905990) +3264 train 7.106347 (lr=5.9898e-05) (hash(x)=24469631) +3265 train 6.945472 (lr=5.9854e-05) (hash(x)=21149081) +3266 train 7.144478 (lr=5.9810e-05) (hash(x)=24696215) +3267 train 7.463152 (lr=5.9766e-05) (hash(x)=27089280) +3268 train 7.021649 (lr=5.9722e-05) (hash(x)=23100446) +3269 train 7.204575 (lr=5.9678e-05) (hash(x)=25061229) +3270 train 7.127393 (lr=5.9635e-05) (hash(x)=24337543) +3271 train 7.188961 (lr=5.9591e-05) (hash(x)=24047679) +3272 train 7.251082 (lr=5.9547e-05) (hash(x)=27616773) +3273 train 7.176685 (lr=5.9503e-05) (hash(x)=25315110) +3274 train 7.239217 (lr=5.9459e-05) (hash(x)=28354645) +3275 train 7.078146 (lr=5.9416e-05) (hash(x)=25034684) +3276 train 7.121864 (lr=5.9372e-05) (hash(x)=23550342) +3277 train 7.803229 (lr=5.9328e-05) (hash(x)=28661487) +3278 train 7.358760 (lr=5.9284e-05) (hash(x)=24724622) +3279 train 7.311634 (lr=5.9241e-05) (hash(x)=26905582) +3280 train 7.398046 (lr=5.9197e-05) (hash(x)=26838818) +3281 train 7.132726 (lr=5.9153e-05) (hash(x)=23949017) +3282 train 6.638460 (lr=5.9110e-05) (hash(x)=18846300) +3283 train 7.009592 (lr=5.9066e-05) (hash(x)=21406950) +3284 train 6.810133 (lr=5.9023e-05) (hash(x)=21157696) +3285 train 6.936020 (lr=5.8979e-05) (hash(x)=21440152) +3286 train 7.107849 (lr=5.8935e-05) (hash(x)=26749182) +3287 train 7.275707 (lr=5.8892e-05) (hash(x)=29018970) +3288 train 7.222505 (lr=5.8848e-05) (hash(x)=27577517) +3289 train 6.860040 (lr=5.8805e-05) (hash(x)=19190537) +3290 train 6.888661 (lr=5.8761e-05) (hash(x)=21957991) +3291 train 6.942026 (lr=5.8718e-05) (hash(x)=20853530) +3292 train 6.856590 (lr=5.8674e-05) (hash(x)=22291731) +3293 train 7.044633 (lr=5.8631e-05) (hash(x)=23786853) +3294 train 7.179392 (lr=5.8587e-05) (hash(x)=25740147) +3295 train 7.339123 (lr=5.8544e-05) (hash(x)=24503315) +3296 train 7.029916 (lr=5.8500e-05) (hash(x)=22541728) +3297 train 7.349687 (lr=5.8457e-05) (hash(x)=27067328) +3298 train 7.017522 (lr=5.8413e-05) (hash(x)=22600715) +3299 train 7.010675 (lr=5.8370e-05) (hash(x)=23080074) +3300 val loss 7.1949 +3300 val perplexity 1332.6584 +3300 train 6.819519 (lr=5.8327e-05) (hash(x)=22097758) +3301 train 7.024705 (lr=5.8283e-05) (hash(x)=24105430) +3302 train 6.881567 (lr=5.8240e-05) (hash(x)=23343775) +3303 train 7.153464 (lr=5.8197e-05) (hash(x)=22607537) +3304 train 7.206671 (lr=5.8153e-05) (hash(x)=26501182) +3305 train 7.447367 (lr=5.8110e-05) (hash(x)=26063650) +3306 train 7.061372 (lr=5.8067e-05) (hash(x)=23486602) +3307 train 8.046544 (lr=5.8023e-05) (hash(x)=32179773) +3308 train 11.381185 (lr=5.7980e-05) (hash(x)=66155855) +3309 train 8.508234 (lr=5.7937e-05) (hash(x)=37724427) +3310 train 7.527798 (lr=5.7894e-05) (hash(x)=28861610) +3311 train 7.489536 (lr=5.7850e-05) (hash(x)=26690225) +3312 train 7.075803 (lr=5.7807e-05) (hash(x)=24136450) +3313 train 7.249899 (lr=5.7764e-05) (hash(x)=23702010) +3314 train 7.534610 (lr=5.7721e-05) (hash(x)=28761762) +3315 train 6.862091 (lr=5.7678e-05) (hash(x)=22109609) +3316 train 7.236879 (lr=5.7635e-05) (hash(x)=25168631) +3317 train 7.118688 (lr=5.7591e-05) (hash(x)=24503786) +3318 train 7.120059 (lr=5.7548e-05) (hash(x)=23698606) +3319 train 7.182920 (lr=5.7505e-05) (hash(x)=24226255) +3320 train 7.773427 (lr=5.7462e-05) (hash(x)=31110577) +3321 train 7.137897 (lr=5.7419e-05) (hash(x)=24752754) +3322 train 6.983284 (lr=5.7376e-05) (hash(x)=21135610) +3323 train 6.944409 (lr=5.7333e-05) (hash(x)=23013573) +3324 train 6.712566 (lr=5.7290e-05) (hash(x)=20289715) +3325 train 6.963033 (lr=5.7247e-05) (hash(x)=22700287) +3326 train 7.047826 (lr=5.7204e-05) (hash(x)=21320362) +3327 train 7.148551 (lr=5.7161e-05) (hash(x)=23622702) +3328 train 7.414872 (lr=5.7118e-05) (hash(x)=27435461) +3329 train 7.144133 (lr=5.7075e-05) (hash(x)=25435452) +3330 train 7.176145 (lr=5.7032e-05) (hash(x)=27952557) +3331 train 6.859272 (lr=5.6989e-05) (hash(x)=21517429) +3332 train 6.972177 (lr=5.6946e-05) (hash(x)=24288985) +3333 train 7.146355 (lr=5.6904e-05) (hash(x)=23374788) +3334 train 6.996359 (lr=5.6861e-05) (hash(x)=22042499) +3335 train 7.229048 (lr=5.6818e-05) (hash(x)=23910425) +3336 train 7.524100 (lr=5.6775e-05) (hash(x)=28118508) +3337 train 7.313844 (lr=5.6732e-05) (hash(x)=26737440) +3338 train 7.061828 (lr=5.6689e-05) (hash(x)=24472271) +3339 train 7.013869 (lr=5.6647e-05) (hash(x)=24407484) +3340 train 7.609227 (lr=5.6604e-05) (hash(x)=27908937) +3341 train 7.727225 (lr=5.6561e-05) (hash(x)=29038937) +3342 train 7.470714 (lr=5.6518e-05) (hash(x)=24802580) +3343 train 7.462399 (lr=5.6476e-05) (hash(x)=27213318) +3344 train 7.514598 (lr=5.6433e-05) (hash(x)=28693458) +3345 train 6.807258 (lr=5.6390e-05) (hash(x)=20332324) +3346 train 7.224149 (lr=5.6348e-05) (hash(x)=26726007) +3347 train 7.118761 (lr=5.6305e-05) (hash(x)=25524191) +3348 train 7.212106 (lr=5.6262e-05) (hash(x)=25553293) +3349 train 7.132817 (lr=5.6220e-05) (hash(x)=25614848) +3350 val loss 7.2143 +3350 val perplexity 1358.7743 +3350 train 7.235881 (lr=5.6177e-05) (hash(x)=25747903) +3351 train 7.202619 (lr=5.6134e-05) (hash(x)=26701577) +3352 train 6.959686 (lr=5.6092e-05) (hash(x)=21964135) +3353 train 7.087266 (lr=5.6049e-05) (hash(x)=24461007) +3354 train 7.102153 (lr=5.6007e-05) (hash(x)=25818495) +3355 train 6.951759 (lr=5.5964e-05) (hash(x)=22091266) +3356 train 6.923349 (lr=5.5922e-05) (hash(x)=24476213) +3357 train 7.315687 (lr=5.5879e-05) (hash(x)=24500423) +3358 train 7.086473 (lr=5.5837e-05) (hash(x)=21754841) +3359 train 7.405019 (lr=5.5794e-05) (hash(x)=26216794) +3360 train 6.875835 (lr=5.5752e-05) (hash(x)=24267249) +3361 train 7.205919 (lr=5.5709e-05) (hash(x)=23143515) +3362 train 7.086183 (lr=5.5667e-05) (hash(x)=24120302) +3363 train 7.263710 (lr=5.5625e-05) (hash(x)=20817340) +3364 train 7.218263 (lr=5.5582e-05) (hash(x)=22285847) +3365 train 7.515916 (lr=5.5540e-05) (hash(x)=28151597) +3366 train 7.916824 (lr=5.5497e-05) (hash(x)=31593285) +3367 train 7.576744 (lr=5.5455e-05) (hash(x)=27579623) +3368 train 7.182189 (lr=5.5413e-05) (hash(x)=24995988) +3369 train 6.821977 (lr=5.5370e-05) (hash(x)=22166810) +3370 train 7.091444 (lr=5.5328e-05) (hash(x)=23948298) +3371 train 6.971420 (lr=5.5286e-05) (hash(x)=21532187) +3372 train 7.038832 (lr=5.5244e-05) (hash(x)=23571652) +3373 train 7.445541 (lr=5.5201e-05) (hash(x)=26911513) +3374 train 7.363045 (lr=5.5159e-05) (hash(x)=24011329) +3375 train 7.552573 (lr=5.5117e-05) (hash(x)=26086198) +3376 train 7.133705 (lr=5.5075e-05) (hash(x)=22844402) +3377 train 7.095689 (lr=5.5033e-05) (hash(x)=21817762) +3378 train 7.148906 (lr=5.4990e-05) (hash(x)=23903232) +3379 train 7.124669 (lr=5.4948e-05) (hash(x)=23911729) +3380 train 7.081380 (lr=5.4906e-05) (hash(x)=24485288) +3381 train 7.293079 (lr=5.4864e-05) (hash(x)=27955492) +3382 train 6.995415 (lr=5.4822e-05) (hash(x)=25884586) +3383 train 7.201940 (lr=5.4780e-05) (hash(x)=24863441) +3384 train 7.483665 (lr=5.4738e-05) (hash(x)=22045992) +3385 train 7.610704 (lr=5.4696e-05) (hash(x)=29174796) +3386 train 7.863654 (lr=5.4654e-05) (hash(x)=32589942) +3387 train 7.495286 (lr=5.4612e-05) (hash(x)=28856978) +3388 train 6.997187 (lr=5.4570e-05) (hash(x)=21667904) +3389 train 6.988480 (lr=5.4528e-05) (hash(x)=23431801) +3390 train 6.765741 (lr=5.4486e-05) (hash(x)=20877285) +3391 train 7.036884 (lr=5.4444e-05) (hash(x)=25236385) +3392 train 7.250081 (lr=5.4402e-05) (hash(x)=25373071) +3393 train 7.403234 (lr=5.4360e-05) (hash(x)=25713464) +3394 train 7.406813 (lr=5.4318e-05) (hash(x)=25713475) +3395 train 7.251784 (lr=5.4276e-05) (hash(x)=24278687) +3396 train 7.353741 (lr=5.4234e-05) (hash(x)=27491349) +3397 train 7.255924 (lr=5.4192e-05) (hash(x)=24513692) +3398 train 7.375070 (lr=5.4151e-05) (hash(x)=26853415) +3399 train 7.445525 (lr=5.4109e-05) (hash(x)=25330803) +3400 val loss 7.1921 +3400 val perplexity 1328.8783 +3400 train 7.419564 (lr=5.4067e-05) (hash(x)=26578066) +3401 train 7.430095 (lr=5.4025e-05) (hash(x)=26811522) +3402 train 7.137393 (lr=5.3983e-05) (hash(x)=25611092) +3403 train 6.930048 (lr=5.3942e-05) (hash(x)=21568545) +3404 train 6.925817 (lr=5.3900e-05) (hash(x)=22756484) +3405 train 7.214581 (lr=5.3858e-05) (hash(x)=27927608) +3406 train 7.226524 (lr=5.3817e-05) (hash(x)=27497018) +3407 train 7.030354 (lr=5.3775e-05) (hash(x)=22508532) +3408 train 7.465077 (lr=5.3733e-05) (hash(x)=26673287) +3409 train 7.163327 (lr=5.3692e-05) (hash(x)=23675869) +3410 train 7.078180 (lr=5.3650e-05) (hash(x)=25496948) +3411 train 7.054714 (lr=5.3608e-05) (hash(x)=24850662) +3412 train 7.327854 (lr=5.3567e-05) (hash(x)=29790167) +3413 train 6.943730 (lr=5.3525e-05) (hash(x)=24193434) +3414 train 7.317924 (lr=5.3484e-05) (hash(x)=25310919) +3415 train 7.029998 (lr=5.3442e-05) (hash(x)=21799261) +3416 train 7.298563 (lr=5.3400e-05) (hash(x)=26620074) +3417 train 7.249564 (lr=5.3359e-05) (hash(x)=26719309) +3418 train 7.576612 (lr=5.3317e-05) (hash(x)=23190530) +3419 train 7.221990 (lr=5.3276e-05) (hash(x)=24884891) +3420 train 7.213035 (lr=5.3235e-05) (hash(x)=25545849) +3421 train 7.145230 (lr=5.3193e-05) (hash(x)=26021405) +3422 train 7.111375 (lr=5.3152e-05) (hash(x)=23887343) +3423 train 7.200555 (lr=5.3110e-05) (hash(x)=26311168) +3424 train 6.886667 (lr=5.3069e-05) (hash(x)=21051541) +3425 train 7.220997 (lr=5.3027e-05) (hash(x)=23553179) +3426 train 7.082036 (lr=5.2986e-05) (hash(x)=24345540) +3427 train 7.593369 (lr=5.2945e-05) (hash(x)=27549895) +3428 train 6.892030 (lr=5.2903e-05) (hash(x)=22559753) +3429 train 6.855897 (lr=5.2862e-05) (hash(x)=21647642) +3430 train 6.750479 (lr=5.2821e-05) (hash(x)=20130901) +3431 train 6.911317 (lr=5.2780e-05) (hash(x)=20977430) +3432 train 6.904522 (lr=5.2738e-05) (hash(x)=21356429) +3433 train 6.898557 (lr=5.2697e-05) (hash(x)=23494380) +3434 train 7.161405 (lr=5.2656e-05) (hash(x)=23805501) +3435 train 7.121549 (lr=5.2615e-05) (hash(x)=23448855) +3436 train 7.460272 (lr=5.2573e-05) (hash(x)=26000319) +3437 train 6.956760 (lr=5.2532e-05) (hash(x)=21760032) +3438 train 7.071691 (lr=5.2491e-05) (hash(x)=24424886) +3439 train 7.448303 (lr=5.2450e-05) (hash(x)=26941617) +3440 train 7.459411 (lr=5.2409e-05) (hash(x)=26798528) +3441 train 7.485338 (lr=5.2368e-05) (hash(x)=27464193) +3442 train 7.376505 (lr=5.2327e-05) (hash(x)=25649118) +3443 train 7.396654 (lr=5.2286e-05) (hash(x)=26953192) +3444 train 7.256361 (lr=5.2245e-05) (hash(x)=22224958) +3445 train 7.042247 (lr=5.2204e-05) (hash(x)=24044587) +3446 train 7.478899 (lr=5.2163e-05) (hash(x)=29584466) +3447 train 7.863863 (lr=5.2122e-05) (hash(x)=30008957) +3448 train 7.775261 (lr=5.2081e-05) (hash(x)=26059290) +3449 train 6.733341 (lr=5.2040e-05) (hash(x)=19733965) +3450 val loss 7.1977 +3450 val perplexity 1336.3243 +3450 train 7.248384 (lr=5.1999e-05) (hash(x)=23960200) +3451 train 7.434157 (lr=5.1958e-05) (hash(x)=27069893) +3452 train 7.056519 (lr=5.1917e-05) (hash(x)=23947772) +3453 train 7.162739 (lr=5.1876e-05) (hash(x)=22707406) +3454 train 7.335963 (lr=5.1835e-05) (hash(x)=27832550) +3455 train 7.204399 (lr=5.1794e-05) (hash(x)=27125962) +3456 train 7.077760 (lr=5.1753e-05) (hash(x)=24510254) +3457 train 6.875890 (lr=5.1712e-05) (hash(x)=23545652) +3458 train 6.951335 (lr=5.1672e-05) (hash(x)=23554751) +3459 train 7.088357 (lr=5.1631e-05) (hash(x)=23341415) +3460 train 7.255683 (lr=5.1590e-05) (hash(x)=21784583) +3461 train 7.034307 (lr=5.1549e-05) (hash(x)=22214769) +3462 train 7.097373 (lr=5.1509e-05) (hash(x)=24206922) +3463 train 7.196761 (lr=5.1468e-05) (hash(x)=25888358) +3464 train 7.039293 (lr=5.1427e-05) (hash(x)=22689666) +3465 train 7.153098 (lr=5.1387e-05) (hash(x)=24918697) +3466 train 7.407881 (lr=5.1346e-05) (hash(x)=28237214) +3467 train 7.500284 (lr=5.1305e-05) (hash(x)=26761645) +3468 train 7.154020 (lr=5.1265e-05) (hash(x)=26979307) +3469 train 7.092229 (lr=5.1224e-05) (hash(x)=23553754) +3470 train 7.245990 (lr=5.1183e-05) (hash(x)=25256849) +3471 train 7.093730 (lr=5.1143e-05) (hash(x)=21725719) +3472 train 7.191670 (lr=5.1102e-05) (hash(x)=24897801) +3473 train 7.144077 (lr=5.1062e-05) (hash(x)=26175307) +3474 train 6.943777 (lr=5.1021e-05) (hash(x)=23309218) +3475 train 7.019525 (lr=5.0981e-05) (hash(x)=25746493) +3476 train 7.339047 (lr=5.0940e-05) (hash(x)=27169613) +3477 train 7.021698 (lr=5.0900e-05) (hash(x)=22937341) +3478 train 7.147842 (lr=5.0859e-05) (hash(x)=24250636) +3479 train 6.963932 (lr=5.0819e-05) (hash(x)=21669704) +3480 train 6.978476 (lr=5.0778e-05) (hash(x)=24431839) +3481 train 7.021366 (lr=5.0738e-05) (hash(x)=22763387) +3482 train 6.982685 (lr=5.0698e-05) (hash(x)=20489446) +3483 train 6.941478 (lr=5.0657e-05) (hash(x)=21167493) +3484 train 6.959509 (lr=5.0617e-05) (hash(x)=23465087) +3485 train 7.173908 (lr=5.0577e-05) (hash(x)=26175023) +3486 train 7.292043 (lr=5.0536e-05) (hash(x)=24986207) +3487 train 6.857204 (lr=5.0496e-05) (hash(x)=23166993) +3488 train 7.148384 (lr=5.0456e-05) (hash(x)=25281216) +3489 train 6.947344 (lr=5.0416e-05) (hash(x)=21824285) +3490 train 6.988634 (lr=5.0375e-05) (hash(x)=22352750) +3491 train 7.231561 (lr=5.0335e-05) (hash(x)=23947208) +3492 train 7.264563 (lr=5.0295e-05) (hash(x)=26257363) +3493 train 7.120730 (lr=5.0255e-05) (hash(x)=25103214) +3494 train 7.173972 (lr=5.0215e-05) (hash(x)=25267583) +3495 train 7.251596 (lr=5.0174e-05) (hash(x)=26235974) +3496 train 7.431044 (lr=5.0134e-05) (hash(x)=26430769) +3497 train 7.827596 (lr=5.0094e-05) (hash(x)=28282027) +3498 train 7.731135 (lr=5.0054e-05) (hash(x)=28386462) +3499 train 7.342611 (lr=5.0014e-05) (hash(x)=29822604) +3500 val loss 7.1962 +3500 val perplexity 1334.3619 +3500 train 7.246381 (lr=4.9974e-05) (hash(x)=29225386) +3501 train 7.118948 (lr=4.9934e-05) (hash(x)=25249294) +3502 train 6.879978 (lr=4.9894e-05) (hash(x)=20020741) +3503 train 7.023261 (lr=4.9854e-05) (hash(x)=25426430) +3504 train 6.996387 (lr=4.9814e-05) (hash(x)=25720411) +3505 train 7.043732 (lr=4.9774e-05) (hash(x)=25602639) +3506 train 7.128609 (lr=4.9734e-05) (hash(x)=26724388) +3507 train 7.069627 (lr=4.9694e-05) (hash(x)=26043735) +3508 train 7.017046 (lr=4.9654e-05) (hash(x)=24955163) +3509 train 6.976862 (lr=4.9614e-05) (hash(x)=20936107) +3510 train 6.970367 (lr=4.9574e-05) (hash(x)=20317378) +3511 train 6.989446 (lr=4.9535e-05) (hash(x)=22966314) +3512 train 7.336441 (lr=4.9495e-05) (hash(x)=25870930) +3513 train 7.172544 (lr=4.9455e-05) (hash(x)=24656635) +3514 train 7.439269 (lr=4.9415e-05) (hash(x)=28576810) +3515 train 7.338232 (lr=4.9375e-05) (hash(x)=27944619) +3516 train 7.194267 (lr=4.9336e-05) (hash(x)=27421509) +3517 train 6.936025 (lr=4.9296e-05) (hash(x)=20844620) +3518 train 7.126718 (lr=4.9256e-05) (hash(x)=28569406) +3519 train 7.018177 (lr=4.9216e-05) (hash(x)=23448505) +3520 train 7.177303 (lr=4.9177e-05) (hash(x)=24852577) +3521 train 7.071256 (lr=4.9137e-05) (hash(x)=23963103) +3522 train 6.982721 (lr=4.9097e-05) (hash(x)=24816516) +3523 train 7.172799 (lr=4.9058e-05) (hash(x)=24205942) +3524 train 6.738277 (lr=4.9018e-05) (hash(x)=20988660) +3525 train 6.855917 (lr=4.8979e-05) (hash(x)=21631366) +3526 train 7.062824 (lr=4.8939e-05) (hash(x)=23499370) +3527 train 7.164754 (lr=4.8899e-05) (hash(x)=26330693) +3528 train 6.804511 (lr=4.8860e-05) (hash(x)=23937176) +3529 train 7.105081 (lr=4.8820e-05) (hash(x)=27345885) +3530 train 6.808062 (lr=4.8781e-05) (hash(x)=21104610) +3531 train 7.184422 (lr=4.8741e-05) (hash(x)=24844466) +3532 train 6.542542 (lr=4.8702e-05) (hash(x)=21055483) +3533 train 6.887506 (lr=4.8663e-05) (hash(x)=23229414) +3534 train 7.181415 (lr=4.8623e-05) (hash(x)=26676920) +3535 train 7.144044 (lr=4.8584e-05) (hash(x)=29550596) +3536 train 6.925622 (lr=4.8544e-05) (hash(x)=22231942) +3537 train 7.091101 (lr=4.8505e-05) (hash(x)=25843852) +3538 train 7.257465 (lr=4.8466e-05) (hash(x)=27110533) +3539 train 6.810075 (lr=4.8426e-05) (hash(x)=20506540) +3540 train 6.956198 (lr=4.8387e-05) (hash(x)=21599346) +3541 train 7.119138 (lr=4.8348e-05) (hash(x)=26395519) +3542 train 7.077579 (lr=4.8308e-05) (hash(x)=25892512) +3543 train 7.138269 (lr=4.8269e-05) (hash(x)=22124892) +3544 train 7.002063 (lr=4.8230e-05) (hash(x)=21882567) +3545 train 7.072814 (lr=4.8191e-05) (hash(x)=24316212) +3546 train 7.020700 (lr=4.8152e-05) (hash(x)=24296310) +3547 train 7.111610 (lr=4.8112e-05) (hash(x)=24867036) +3548 train 7.078773 (lr=4.8073e-05) (hash(x)=23351896) +3549 train 7.070351 (lr=4.8034e-05) (hash(x)=21576408) +3550 val loss 7.1842 +3550 val perplexity 1318.4540 +3550 train 7.201770 (lr=4.7995e-05) (hash(x)=26377338) +3551 train 7.004710 (lr=4.7956e-05) (hash(x)=25607640) +3552 train 7.331261 (lr=4.7917e-05) (hash(x)=27619776) +3553 train 6.834957 (lr=4.7878e-05) (hash(x)=23454533) +3554 train 7.032865 (lr=4.7839e-05) (hash(x)=22542519) +3555 train 7.090941 (lr=4.7800e-05) (hash(x)=26176930) +3556 train 6.901422 (lr=4.7761e-05) (hash(x)=22815181) +3557 train 6.878011 (lr=4.7722e-05) (hash(x)=21821757) +3558 train 6.908092 (lr=4.7683e-05) (hash(x)=23988293) +3559 train 6.831440 (lr=4.7644e-05) (hash(x)=23795894) +3560 train 6.795912 (lr=4.7605e-05) (hash(x)=22898969) +3561 train 6.809906 (lr=4.7566e-05) (hash(x)=21510825) +3562 train 6.739813 (lr=4.7527e-05) (hash(x)=22499317) +3563 train 6.771614 (lr=4.7488e-05) (hash(x)=23756298) +3564 train 6.817979 (lr=4.7449e-05) (hash(x)=23964512) +3565 train 6.914020 (lr=4.7410e-05) (hash(x)=23262803) +3566 train 7.109334 (lr=4.7372e-05) (hash(x)=23347279) +3567 train 7.007320 (lr=4.7333e-05) (hash(x)=24165449) +3568 train 7.094187 (lr=4.7294e-05) (hash(x)=25503946) +3569 train 7.074735 (lr=4.7255e-05) (hash(x)=26532839) +3570 train 6.776089 (lr=4.7217e-05) (hash(x)=21889816) +3571 train 7.075243 (lr=4.7178e-05) (hash(x)=26643739) +3572 train 7.237659 (lr=4.7139e-05) (hash(x)=26826130) +3573 train 7.259904 (lr=4.7100e-05) (hash(x)=25810624) +3574 train 7.128316 (lr=4.7062e-05) (hash(x)=23080331) +3575 train 7.267269 (lr=4.7023e-05) (hash(x)=24697756) +3576 train 7.097142 (lr=4.6985e-05) (hash(x)=25158900) +3577 train 7.258541 (lr=4.6946e-05) (hash(x)=25793633) +3578 train 6.806551 (lr=4.6907e-05) (hash(x)=21468493) +3579 train 7.153296 (lr=4.6869e-05) (hash(x)=24431101) +3580 train 7.011858 (lr=4.6830e-05) (hash(x)=27314357) +3581 train 7.240307 (lr=4.6792e-05) (hash(x)=26286249) +3582 train 7.438919 (lr=4.6753e-05) (hash(x)=25954856) +3583 train 7.329776 (lr=4.6715e-05) (hash(x)=27218899) +3584 train 7.117943 (lr=4.6676e-05) (hash(x)=24249114) +3585 train 6.998218 (lr=4.6638e-05) (hash(x)=23659934) +3586 train 7.009621 (lr=4.6599e-05) (hash(x)=25995600) +3587 train 6.997801 (lr=4.6561e-05) (hash(x)=29462219) +3588 train 7.095726 (lr=4.6523e-05) (hash(x)=23346714) +3589 train 7.220049 (lr=4.6484e-05) (hash(x)=27168432) +3590 train 7.023899 (lr=4.6446e-05) (hash(x)=23954240) +3591 train 7.000520 (lr=4.6408e-05) (hash(x)=24748522) +3592 train 7.166439 (lr=4.6369e-05) (hash(x)=24887007) +3593 train 6.960590 (lr=4.6331e-05) (hash(x)=25539383) +3594 train 6.880954 (lr=4.6293e-05) (hash(x)=20104613) +3595 train 7.379539 (lr=4.6254e-05) (hash(x)=24843486) +3596 train 7.386939 (lr=4.6216e-05) (hash(x)=24357864) +3597 train 7.089906 (lr=4.6178e-05) (hash(x)=23873745) +3598 train 7.218482 (lr=4.6140e-05) (hash(x)=25142829) +3599 train 7.305612 (lr=4.6102e-05) (hash(x)=24965317) +3600 val loss 7.1827 +3600 val perplexity 1316.5059 +3600 train 6.785892 (lr=4.6064e-05) (hash(x)=18505205) +3601 train 6.831631 (lr=4.6025e-05) (hash(x)=23632877) +3602 train 7.050966 (lr=4.5987e-05) (hash(x)=23704554) +3603 train 7.205788 (lr=4.5949e-05) (hash(x)=26584754) +3604 train 6.823963 (lr=4.5911e-05) (hash(x)=20667709) +3605 train 6.707281 (lr=4.5873e-05) (hash(x)=20573248) +3606 train 6.862656 (lr=4.5835e-05) (hash(x)=23998997) +3607 train 7.035695 (lr=4.5797e-05) (hash(x)=22031210) +3608 train 7.078941 (lr=4.5759e-05) (hash(x)=24124536) +3609 train 6.992104 (lr=4.5721e-05) (hash(x)=22650144) +3610 train 7.070837 (lr=4.5683e-05) (hash(x)=23796998) +3611 train 7.122121 (lr=4.5645e-05) (hash(x)=24860582) +3612 train 6.672425 (lr=4.5607e-05) (hash(x)=20591300) +3613 train 7.068506 (lr=4.5569e-05) (hash(x)=23447130) +3614 train 7.056747 (lr=4.5532e-05) (hash(x)=26237963) +3615 train 7.184551 (lr=4.5494e-05) (hash(x)=25877990) +3616 train 6.965784 (lr=4.5456e-05) (hash(x)=24808003) +3617 train 7.175668 (lr=4.5418e-05) (hash(x)=24103543) +3618 train 7.073250 (lr=4.5380e-05) (hash(x)=24877184) +3619 train 7.192598 (lr=4.5343e-05) (hash(x)=24970646) +3620 train 7.130170 (lr=4.5305e-05) (hash(x)=25764524) +3621 train 7.313782 (lr=4.5267e-05) (hash(x)=25313591) +3622 train 7.147742 (lr=4.5229e-05) (hash(x)=23260940) +3623 train 7.077979 (lr=4.5192e-05) (hash(x)=24382381) +3624 train 7.016501 (lr=4.5154e-05) (hash(x)=24618902) +3625 train 7.201437 (lr=4.5116e-05) (hash(x)=25074871) +3626 train 6.892317 (lr=4.5079e-05) (hash(x)=24472251) +3627 train 7.039488 (lr=4.5041e-05) (hash(x)=25221746) +3628 train 7.123659 (lr=4.5003e-05) (hash(x)=27448790) +3629 train 7.087596 (lr=4.4966e-05) (hash(x)=25221431) +3630 train 6.713431 (lr=4.4928e-05) (hash(x)=22034366) +3631 train 7.255394 (lr=4.4891e-05) (hash(x)=24551999) +3632 train 6.956830 (lr=4.4853e-05) (hash(x)=24330217) +3633 train 7.055747 (lr=4.4816e-05) (hash(x)=22792380) +3634 train 6.863157 (lr=4.4778e-05) (hash(x)=22393767) +3635 train 7.184703 (lr=4.4741e-05) (hash(x)=28151378) +3636 train 7.211906 (lr=4.4704e-05) (hash(x)=26999341) +3637 train 7.213459 (lr=4.4666e-05) (hash(x)=27251870) +3638 train 7.152469 (lr=4.4629e-05) (hash(x)=23439462) +3639 train 7.258005 (lr=4.4591e-05) (hash(x)=25765516) +3640 train 7.107645 (lr=4.4554e-05) (hash(x)=24720171) +3641 train 7.297498 (lr=4.4517e-05) (hash(x)=23927187) +3642 train 7.082357 (lr=4.4479e-05) (hash(x)=23879561) +3643 train 7.206876 (lr=4.4442e-05) (hash(x)=25630696) +3644 train 6.803420 (lr=4.4405e-05) (hash(x)=22030016) +3645 train 7.274385 (lr=4.4368e-05) (hash(x)=28781600) +3646 train 7.242418 (lr=4.4330e-05) (hash(x)=26668019) +3647 train 7.269556 (lr=4.4293e-05) (hash(x)=25204247) +3648 train 7.515949 (lr=4.4256e-05) (hash(x)=31261394) +3649 train 7.298472 (lr=4.4219e-05) (hash(x)=26193103) +3650 val loss 7.1907 +3650 val perplexity 1326.9983 +3650 train 7.122910 (lr=4.4182e-05) (hash(x)=23872456) +3651 train 7.023029 (lr=4.4145e-05) (hash(x)=26326447) +3652 train 7.021651 (lr=4.4107e-05) (hash(x)=26449631) +3653 train 7.289605 (lr=4.4070e-05) (hash(x)=26373461) +3654 train 7.148575 (lr=4.4033e-05) (hash(x)=24882768) +3655 train 7.219947 (lr=4.3996e-05) (hash(x)=26321813) +3656 train 7.241632 (lr=4.3959e-05) (hash(x)=27056428) +3657 train 7.216407 (lr=4.3922e-05) (hash(x)=24583976) +3658 train 6.929770 (lr=4.3885e-05) (hash(x)=22259624) +3659 train 7.058157 (lr=4.3848e-05) (hash(x)=25400396) +3660 train 6.913112 (lr=4.3811e-05) (hash(x)=21095507) +3661 train 7.146817 (lr=4.3775e-05) (hash(x)=27231042) +3662 train 6.970300 (lr=4.3738e-05) (hash(x)=27292771) +3663 train 7.373654 (lr=4.3701e-05) (hash(x)=25528323) +3664 train 7.131690 (lr=4.3664e-05) (hash(x)=24374502) +3665 train 6.909359 (lr=4.3627e-05) (hash(x)=22463800) +3666 train 7.215986 (lr=4.3590e-05) (hash(x)=25413960) +3667 train 7.125385 (lr=4.3554e-05) (hash(x)=24035353) +3668 train 7.067186 (lr=4.3517e-05) (hash(x)=24815852) +3669 train 6.938909 (lr=4.3480e-05) (hash(x)=22995856) +3670 train 7.223283 (lr=4.3443e-05) (hash(x)=28128238) +3671 train 7.244550 (lr=4.3407e-05) (hash(x)=25114729) +3672 train 7.004422 (lr=4.3370e-05) (hash(x)=19337726) +3673 train 7.412964 (lr=4.3333e-05) (hash(x)=26674420) +3674 train 6.914458 (lr=4.3297e-05) (hash(x)=22553270) +3675 train 6.753729 (lr=4.3260e-05) (hash(x)=21634962) +3676 train 6.967944 (lr=4.3223e-05) (hash(x)=23362669) +3677 train 7.141234 (lr=4.3187e-05) (hash(x)=24781824) +3678 train 6.681252 (lr=4.3150e-05) (hash(x)=17909688) +3679 train 7.849530 (lr=4.3114e-05) (hash(x)=31341964) +3680 train 7.374732 (lr=4.3077e-05) (hash(x)=29071335) +3681 train 6.797774 (lr=4.3041e-05) (hash(x)=19486640) +3682 train 6.948203 (lr=4.3004e-05) (hash(x)=24301133) +3683 train 7.141959 (lr=4.2968e-05) (hash(x)=29172813) +3684 train 7.679863 (lr=4.2931e-05) (hash(x)=31501337) +3685 train 7.281561 (lr=4.2895e-05) (hash(x)=27377840) +3686 train 7.053371 (lr=4.2859e-05) (hash(x)=24499761) +3687 train 7.074909 (lr=4.2822e-05) (hash(x)=26326024) +3688 train 7.027213 (lr=4.2786e-05) (hash(x)=23179996) +3689 train 6.724153 (lr=4.2749e-05) (hash(x)=20963675) +3690 train 7.017198 (lr=4.2713e-05) (hash(x)=26650521) +3691 train 6.705914 (lr=4.2677e-05) (hash(x)=20140071) +3692 train 6.770499 (lr=4.2641e-05) (hash(x)=21734340) +3693 train 7.076898 (lr=4.2604e-05) (hash(x)=23848422) +3694 train 7.112320 (lr=4.2568e-05) (hash(x)=27499953) +3695 train 7.352825 (lr=4.2532e-05) (hash(x)=27273311) +3696 train 7.288513 (lr=4.2496e-05) (hash(x)=25741091) +3697 train 7.019185 (lr=4.2460e-05) (hash(x)=22010794) +3698 train 7.101833 (lr=4.2424e-05) (hash(x)=24616138) +3699 train 7.480585 (lr=4.2387e-05) (hash(x)=31276487) +3700 val loss 7.1834 +3700 val perplexity 1317.3177 +3700 train 7.141845 (lr=4.2351e-05) (hash(x)=24042922) +3701 train 6.925346 (lr=4.2315e-05) (hash(x)=21985431) +3702 train 6.776956 (lr=4.2279e-05) (hash(x)=21336316) +3703 train 6.619938 (lr=4.2243e-05) (hash(x)=17819313) +3704 train 7.258002 (lr=4.2207e-05) (hash(x)=27033851) +3705 train 7.246461 (lr=4.2171e-05) (hash(x)=27260043) +3706 train 7.356305 (lr=4.2135e-05) (hash(x)=26847649) +3707 train 7.272401 (lr=4.2099e-05) (hash(x)=25843618) +3708 train 7.276772 (lr=4.2063e-05) (hash(x)=25828009) +3709 train 7.314786 (lr=4.2027e-05) (hash(x)=24960960) +3710 train 7.417793 (lr=4.1992e-05) (hash(x)=24852741) +3711 train 6.850202 (lr=4.1956e-05) (hash(x)=23769243) +3712 train 7.070760 (lr=4.1920e-05) (hash(x)=27110690) +3713 train 7.105661 (lr=4.1884e-05) (hash(x)=22817285) +3714 train 6.775583 (lr=4.1848e-05) (hash(x)=19618355) +3715 train 7.317005 (lr=4.1812e-05) (hash(x)=28731298) +3716 train 7.082478 (lr=4.1777e-05) (hash(x)=23091196) +3717 train 7.617923 (lr=4.1741e-05) (hash(x)=28825233) +3718 train 7.162597 (lr=4.1705e-05) (hash(x)=25778506) +3719 train 7.110206 (lr=4.1670e-05) (hash(x)=23788738) +3720 train 6.495972 (lr=4.1634e-05) (hash(x)=16684794) +3721 train 6.989947 (lr=4.1598e-05) (hash(x)=24755102) +3722 train 7.272420 (lr=4.1563e-05) (hash(x)=26839238) +3723 train 7.307904 (lr=4.1527e-05) (hash(x)=26599031) +3724 train 7.162531 (lr=4.1491e-05) (hash(x)=25945650) +3725 train 7.380304 (lr=4.1456e-05) (hash(x)=27434751) +3726 train 7.080181 (lr=4.1420e-05) (hash(x)=24814591) +3727 train 7.065030 (lr=4.1385e-05) (hash(x)=24818744) +3728 train 7.123528 (lr=4.1349e-05) (hash(x)=25649817) +3729 train 7.023088 (lr=4.1314e-05) (hash(x)=24987021) +3730 train 6.989604 (lr=4.1278e-05) (hash(x)=24667779) +3731 train 6.957613 (lr=4.1243e-05) (hash(x)=23053871) +3732 train 6.682079 (lr=4.1208e-05) (hash(x)=19264856) +3733 train 7.236932 (lr=4.1172e-05) (hash(x)=23718117) +3734 train 6.959434 (lr=4.1137e-05) (hash(x)=21904779) +3735 train 7.136176 (lr=4.1102e-05) (hash(x)=23472795) +3736 train 7.362471 (lr=4.1066e-05) (hash(x)=24650440) +3737 train 7.441543 (lr=4.1031e-05) (hash(x)=25243911) +3738 train 7.822722 (lr=4.0996e-05) (hash(x)=30423616) +3739 train 7.824387 (lr=4.0960e-05) (hash(x)=29748225) +3740 train 7.218564 (lr=4.0925e-05) (hash(x)=25180684) +3741 train 7.235089 (lr=4.0890e-05) (hash(x)=25619065) +3742 train 7.638414 (lr=4.0855e-05) (hash(x)=31847002) +3743 train 7.150642 (lr=4.0820e-05) (hash(x)=24991832) +3744 train 7.106984 (lr=4.0784e-05) (hash(x)=23836263) +3745 train 6.996336 (lr=4.0749e-05) (hash(x)=24651902) +3746 train 7.532978 (lr=4.0714e-05) (hash(x)=22936538) +3747 train 7.522061 (lr=4.0679e-05) (hash(x)=23681545) +3748 train 6.948046 (lr=4.0644e-05) (hash(x)=21140825) +3749 train 7.115454 (lr=4.0609e-05) (hash(x)=24932453) +3750 val loss 7.1900 +3750 val perplexity 1326.1520 +3750 train 7.268346 (lr=4.0574e-05) (hash(x)=25919062) +3751 train 7.036663 (lr=4.0539e-05) (hash(x)=22424066) +3752 train 7.112950 (lr=4.0504e-05) (hash(x)=23542210) +3753 train 6.978139 (lr=4.0469e-05) (hash(x)=22113561) +3754 train 6.896810 (lr=4.0434e-05) (hash(x)=24892794) +3755 train 7.357338 (lr=4.0399e-05) (hash(x)=25262748) +3756 train 7.148335 (lr=4.0364e-05) (hash(x)=24477975) +3757 train 6.930925 (lr=4.0330e-05) (hash(x)=24681189) +3758 train 6.993342 (lr=4.0295e-05) (hash(x)=24052603) +3759 train 7.205666 (lr=4.0260e-05) (hash(x)=26474878) +3760 train 7.765649 (lr=4.0225e-05) (hash(x)=28228836) +3761 train 7.258718 (lr=4.0190e-05) (hash(x)=23832522) +3762 train 7.213629 (lr=4.0156e-05) (hash(x)=24416789) +3763 train 7.010637 (lr=4.0121e-05) (hash(x)=23930593) +3764 train 7.055681 (lr=4.0086e-05) (hash(x)=23895092) +3765 train 7.001997 (lr=4.0052e-05) (hash(x)=26865287) +3766 train 7.078607 (lr=4.0017e-05) (hash(x)=21330722) +3767 train 7.103343 (lr=3.9982e-05) (hash(x)=22704349) +3768 train 7.232401 (lr=3.9948e-05) (hash(x)=27740886) +3769 train 7.219707 (lr=3.9913e-05) (hash(x)=24935936) +3770 train 7.093698 (lr=3.9879e-05) (hash(x)=23497487) +3771 train 7.254252 (lr=3.9844e-05) (hash(x)=24801048) +3772 train 7.024242 (lr=3.9809e-05) (hash(x)=25490486) +3773 train 7.037417 (lr=3.9775e-05) (hash(x)=21166466) +3774 train 7.236494 (lr=3.9740e-05) (hash(x)=23225244) +3775 train 7.020726 (lr=3.9706e-05) (hash(x)=22293673) +3776 train 7.350315 (lr=3.9672e-05) (hash(x)=25700016) +3777 train 6.903752 (lr=3.9637e-05) (hash(x)=22370207) +3778 train 7.214284 (lr=3.9603e-05) (hash(x)=25224849) +3779 train 7.108631 (lr=3.9568e-05) (hash(x)=23311934) +3780 train 6.860434 (lr=3.9534e-05) (hash(x)=19627124) +3781 train 7.420624 (lr=3.9500e-05) (hash(x)=27132838) +3782 train 7.299123 (lr=3.9465e-05) (hash(x)=27242104) +3783 train 6.840089 (lr=3.9431e-05) (hash(x)=21785487) +3784 train 7.147720 (lr=3.9397e-05) (hash(x)=25798262) +3785 train 7.046754 (lr=3.9363e-05) (hash(x)=24806937) +3786 train 6.875745 (lr=3.9328e-05) (hash(x)=24098756) +3787 train 6.907768 (lr=3.9294e-05) (hash(x)=22981456) +3788 train 7.339405 (lr=3.9260e-05) (hash(x)=22441908) +3789 train 7.212027 (lr=3.9226e-05) (hash(x)=25867804) +3790 train 7.155902 (lr=3.9192e-05) (hash(x)=22835586) +3791 train 7.366193 (lr=3.9158e-05) (hash(x)=25251063) +3792 train 7.171190 (lr=3.9124e-05) (hash(x)=27059729) +3793 train 7.170243 (lr=3.9090e-05) (hash(x)=23819311) +3794 train 6.874576 (lr=3.9056e-05) (hash(x)=21345757) +3795 train 7.093807 (lr=3.9022e-05) (hash(x)=25796422) +3796 train 6.819843 (lr=3.8988e-05) (hash(x)=21414971) +3797 train 7.072694 (lr=3.8954e-05) (hash(x)=26120920) +3798 train 7.026283 (lr=3.8920e-05) (hash(x)=22008247) +3799 train 7.099942 (lr=3.8886e-05) (hash(x)=22722211) +3800 val loss 7.1768 +3800 val perplexity 1308.7745 +3800 train 6.837937 (lr=3.8852e-05) (hash(x)=24484513) +3801 train 7.161025 (lr=3.8818e-05) (hash(x)=24463866) +3802 train 7.169200 (lr=3.8784e-05) (hash(x)=26470775) +3803 train 7.205867 (lr=3.8750e-05) (hash(x)=24296755) +3804 train 7.175217 (lr=3.8716e-05) (hash(x)=24381309) +3805 train 7.372783 (lr=3.8683e-05) (hash(x)=26781262) +3806 train 6.908595 (lr=3.8649e-05) (hash(x)=23563137) +3807 train 7.075138 (lr=3.8615e-05) (hash(x)=24522269) +3808 train 6.915830 (lr=3.8582e-05) (hash(x)=22871995) +3809 train 7.231212 (lr=3.8548e-05) (hash(x)=24751946) +3810 train 7.058259 (lr=3.8514e-05) (hash(x)=19879741) +3811 train 7.124179 (lr=3.8481e-05) (hash(x)=25617184) +3812 train 6.830957 (lr=3.8447e-05) (hash(x)=21776722) +3813 train 6.924488 (lr=3.8413e-05) (hash(x)=22663402) +3814 train 7.270801 (lr=3.8380e-05) (hash(x)=26072046) +3815 train 6.925121 (lr=3.8346e-05) (hash(x)=23329475) +3816 train 7.022139 (lr=3.8313e-05) (hash(x)=25519031) +3817 train 6.995195 (lr=3.8279e-05) (hash(x)=22846270) +3818 train 7.010687 (lr=3.8246e-05) (hash(x)=20299429) +3819 train 7.455532 (lr=3.8212e-05) (hash(x)=30652062) +3820 train 6.767060 (lr=3.8179e-05) (hash(x)=19824665) +3821 train 7.311952 (lr=3.8145e-05) (hash(x)=26698904) +3822 train 7.154123 (lr=3.8112e-05) (hash(x)=27612163) +3823 train 6.964978 (lr=3.8079e-05) (hash(x)=24735165) +3824 train 6.692295 (lr=3.8045e-05) (hash(x)=19965890) +3825 train 6.873614 (lr=3.8012e-05) (hash(x)=23518594) +3826 train 6.865976 (lr=3.7979e-05) (hash(x)=22388460) +3827 train 6.945079 (lr=3.7945e-05) (hash(x)=23795686) +3828 train 6.849337 (lr=3.7912e-05) (hash(x)=24470150) +3829 train 6.543816 (lr=3.7879e-05) (hash(x)=19483392) +3830 train 6.955916 (lr=3.7846e-05) (hash(x)=23304516) +3831 train 7.257605 (lr=3.7812e-05) (hash(x)=27002892) +3832 train 7.001092 (lr=3.7779e-05) (hash(x)=22114813) +3833 train 7.178607 (lr=3.7746e-05) (hash(x)=26221916) +3834 train 6.781589 (lr=3.7713e-05) (hash(x)=27261960) +3835 train 7.005981 (lr=3.7680e-05) (hash(x)=21189101) +3836 train 6.675491 (lr=3.7647e-05) (hash(x)=20638173) +3837 train 7.144145 (lr=3.7614e-05) (hash(x)=25497439) +3838 train 6.649392 (lr=3.7581e-05) (hash(x)=20460499) +3839 train 7.028909 (lr=3.7548e-05) (hash(x)=23499349) +3840 train 7.909438 (lr=3.7515e-05) (hash(x)=22671939) +3841 train 7.917803 (lr=3.7482e-05) (hash(x)=26809295) +3842 train 7.159240 (lr=3.7449e-05) (hash(x)=28094504) +3843 train 7.118495 (lr=3.7416e-05) (hash(x)=26807896) +3844 train 7.208249 (lr=3.7383e-05) (hash(x)=24749334) +3845 train 7.099168 (lr=3.7350e-05) (hash(x)=25031330) +3846 train 7.006996 (lr=3.7317e-05) (hash(x)=23008126) +3847 train 6.931774 (lr=3.7285e-05) (hash(x)=22461589) +3848 train 7.245302 (lr=3.7252e-05) (hash(x)=24959391) +3849 train 7.115712 (lr=3.7219e-05) (hash(x)=24239512) +3850 val loss 7.1742 +3850 val perplexity 1305.3391 +3850 train 6.987297 (lr=3.7186e-05) (hash(x)=24760422) +3851 train 7.449787 (lr=3.7154e-05) (hash(x)=26904123) +3852 train 6.577751 (lr=3.7121e-05) (hash(x)=17986444) +3853 train 6.943462 (lr=3.7088e-05) (hash(x)=21618533) +3854 train 7.013159 (lr=3.7056e-05) (hash(x)=27107027) +3855 train 7.276090 (lr=3.7023e-05) (hash(x)=26415040) +3856 train 7.837273 (lr=3.6990e-05) (hash(x)=28682703) +3857 train 6.987117 (lr=3.6958e-05) (hash(x)=22824767) +3858 train 7.134851 (lr=3.6925e-05) (hash(x)=24540450) +3859 train 7.109522 (lr=3.6893e-05) (hash(x)=24463181) +3860 train 7.015851 (lr=3.6860e-05) (hash(x)=22832558) +3861 train 7.218095 (lr=3.6828e-05) (hash(x)=26582384) +3862 train 7.868562 (lr=3.6795e-05) (hash(x)=32327364) +3863 train 7.256990 (lr=3.6763e-05) (hash(x)=26349465) +3864 train 7.000246 (lr=3.6730e-05) (hash(x)=23079414) +3865 train 7.042345 (lr=3.6698e-05) (hash(x)=23464639) +3866 train 6.880023 (lr=3.6666e-05) (hash(x)=21406620) +3867 train 6.764614 (lr=3.6633e-05) (hash(x)=21205988) +3868 train 6.789348 (lr=3.6601e-05) (hash(x)=22742634) +3869 train 6.863806 (lr=3.6569e-05) (hash(x)=24868938) +3870 train 7.197958 (lr=3.6536e-05) (hash(x)=28095283) +3871 train 6.928053 (lr=3.6504e-05) (hash(x)=21596677) +3872 train 7.121234 (lr=3.6472e-05) (hash(x)=26884381) +3873 train 7.197298 (lr=3.6440e-05) (hash(x)=26410272) +3874 train 6.994840 (lr=3.6407e-05) (hash(x)=22915785) +3875 train 6.978796 (lr=3.6375e-05) (hash(x)=23575666) +3876 train 6.961826 (lr=3.6343e-05) (hash(x)=25313223) +3877 train 6.370875 (lr=3.6311e-05) (hash(x)=16319719) +3878 train 7.052266 (lr=3.6279e-05) (hash(x)=23227579) +3879 train 6.984299 (lr=3.6247e-05) (hash(x)=24117012) +3880 train 7.063320 (lr=3.6215e-05) (hash(x)=24681517) +3881 train 6.990865 (lr=3.6183e-05) (hash(x)=23186527) +3882 train 6.985116 (lr=3.6151e-05) (hash(x)=23472784) +3883 train 6.972656 (lr=3.6119e-05) (hash(x)=26013014) +3884 train 7.207903 (lr=3.6087e-05) (hash(x)=25952206) +3885 train 7.318466 (lr=3.6055e-05) (hash(x)=23897834) +3886 train 7.022279 (lr=3.6023e-05) (hash(x)=26350364) +3887 train 7.053388 (lr=3.5991e-05) (hash(x)=24105761) +3888 train 7.146928 (lr=3.5959e-05) (hash(x)=22801707) +3889 train 6.960968 (lr=3.5928e-05) (hash(x)=21821937) +3890 train 6.965856 (lr=3.5896e-05) (hash(x)=24264640) +3891 train 6.930166 (lr=3.5864e-05) (hash(x)=20369133) +3892 train 6.896144 (lr=3.5832e-05) (hash(x)=24313506) +3893 train 6.901123 (lr=3.5800e-05) (hash(x)=22104086) +3894 train 7.100417 (lr=3.5769e-05) (hash(x)=25312602) +3895 train 7.192307 (lr=3.5737e-05) (hash(x)=25725049) +3896 train 6.980462 (lr=3.5705e-05) (hash(x)=22981231) +3897 train 6.872873 (lr=3.5674e-05) (hash(x)=18021467) +3898 train 6.843729 (lr=3.5642e-05) (hash(x)=17960254) +3899 train 7.028195 (lr=3.5611e-05) (hash(x)=19808118) +3900 val loss 7.1722 +3900 val perplexity 1302.6946 +3900 train 6.778148 (lr=3.5579e-05) (hash(x)=21022829) +3901 train 6.955606 (lr=3.5547e-05) (hash(x)=22434663) +3902 train 6.713666 (lr=3.5516e-05) (hash(x)=20208091) +3903 train 6.843987 (lr=3.5484e-05) (hash(x)=22892776) +3904 train 6.955170 (lr=3.5453e-05) (hash(x)=21554367) +3905 train 7.085878 (lr=3.5422e-05) (hash(x)=23704875) +3906 train 7.054265 (lr=3.5390e-05) (hash(x)=21690340) +3907 train 6.974857 (lr=3.5359e-05) (hash(x)=23736780) +3908 train 6.846792 (lr=3.5327e-05) (hash(x)=21060920) +3909 train 6.811299 (lr=3.5296e-05) (hash(x)=20091559) +3910 train 7.073396 (lr=3.5265e-05) (hash(x)=22147974) +3911 train 7.016679 (lr=3.5233e-05) (hash(x)=21630383) +3912 train 7.284371 (lr=3.5202e-05) (hash(x)=28339385) +3913 train 7.048247 (lr=3.5171e-05) (hash(x)=25355505) +3914 train 6.922247 (lr=3.5140e-05) (hash(x)=20843914) +3915 train 7.430972 (lr=3.5108e-05) (hash(x)=25397467) +3916 train 7.105847 (lr=3.5077e-05) (hash(x)=23587501) +3917 train 6.701302 (lr=3.5046e-05) (hash(x)=19036533) +3918 train 6.898215 (lr=3.5015e-05) (hash(x)=29749389) +3919 train 6.803071 (lr=3.4984e-05) (hash(x)=24727094) +3920 train 6.805683 (lr=3.4953e-05) (hash(x)=22723450) +3921 train 7.016060 (lr=3.4922e-05) (hash(x)=24424680) +3922 train 7.163550 (lr=3.4891e-05) (hash(x)=25817917) +3923 train 6.947683 (lr=3.4860e-05) (hash(x)=23951182) +3924 train 6.949103 (lr=3.4829e-05) (hash(x)=21177944) +3925 train 6.815098 (lr=3.4798e-05) (hash(x)=23533768) +3926 train 7.043949 (lr=3.4767e-05) (hash(x)=24263615) +3927 train 6.846870 (lr=3.4736e-05) (hash(x)=22835000) +3928 train 7.065799 (lr=3.4705e-05) (hash(x)=26076156) +3929 train 7.029093 (lr=3.4674e-05) (hash(x)=25171508) +3930 train 7.035698 (lr=3.4643e-05) (hash(x)=22021396) +3931 train 7.357393 (lr=3.4613e-05) (hash(x)=28767849) +3932 train 7.287506 (lr=3.4582e-05) (hash(x)=29497606) +3933 train 6.933349 (lr=3.4551e-05) (hash(x)=22723124) +3934 train 7.183200 (lr=3.4520e-05) (hash(x)=27106616) +3935 train 7.020232 (lr=3.4489e-05) (hash(x)=22839049) +3936 train 7.054216 (lr=3.4459e-05) (hash(x)=25101923) +3937 train 7.038217 (lr=3.4428e-05) (hash(x)=25945975) +3938 train 7.166788 (lr=3.4397e-05) (hash(x)=25382013) +3939 train 6.735760 (lr=3.4367e-05) (hash(x)=19930900) +3940 train 6.862489 (lr=3.4336e-05) (hash(x)=22202373) +3941 train 7.049191 (lr=3.4306e-05) (hash(x)=24592992) +3942 train 6.929086 (lr=3.4275e-05) (hash(x)=25002271) +3943 train 6.826585 (lr=3.4245e-05) (hash(x)=20654136) +3944 train 6.903838 (lr=3.4214e-05) (hash(x)=20061590) +3945 train 6.833211 (lr=3.4184e-05) (hash(x)=21441361) +3946 train 7.021794 (lr=3.4153e-05) (hash(x)=20055468) +3947 train 7.709697 (lr=3.4123e-05) (hash(x)=28495621) +3948 train 7.141019 (lr=3.4092e-05) (hash(x)=25959236) +3949 train 7.448102 (lr=3.4062e-05) (hash(x)=26750193) +3950 val loss 7.1737 +3950 val perplexity 1304.6185 +3950 train 7.305647 (lr=3.4032e-05) (hash(x)=25882605) +3951 train 7.352591 (lr=3.4001e-05) (hash(x)=26776000) +3952 train 6.924046 (lr=3.3971e-05) (hash(x)=24155107) +3953 train 7.049678 (lr=3.3941e-05) (hash(x)=23441845) +3954 train 6.952766 (lr=3.3911e-05) (hash(x)=22860915) +3955 train 6.754227 (lr=3.3880e-05) (hash(x)=21584429) +3956 train 6.342115 (lr=3.3850e-05) (hash(x)=16535556) +3957 train 6.425462 (lr=3.3820e-05) (hash(x)=17946180) +3958 train 6.982387 (lr=3.3790e-05) (hash(x)=25367610) +3959 train 6.848867 (lr=3.3760e-05) (hash(x)=22560658) +3960 train 7.136069 (lr=3.3730e-05) (hash(x)=23809585) +3961 train 7.401456 (lr=3.3699e-05) (hash(x)=20438213) +3962 train 7.733855 (lr=3.3669e-05) (hash(x)=30520037) +3963 train 7.382137 (lr=3.3639e-05) (hash(x)=25276565) +3964 train 7.087899 (lr=3.3609e-05) (hash(x)=26796532) +3965 train 6.886343 (lr=3.3579e-05) (hash(x)=22850475) +3966 train 7.360591 (lr=3.3549e-05) (hash(x)=25983698) +3967 train 7.270021 (lr=3.3519e-05) (hash(x)=25995933) +3968 train 7.476215 (lr=3.3490e-05) (hash(x)=25319339) +3969 train 7.090495 (lr=3.3460e-05) (hash(x)=25066892) +3970 train 7.280837 (lr=3.3430e-05) (hash(x)=26931819) +3971 train 7.233256 (lr=3.3400e-05) (hash(x)=24163910) +3972 train 7.144386 (lr=3.3370e-05) (hash(x)=25359634) +3973 train 7.071704 (lr=3.3340e-05) (hash(x)=24323444) +3974 train 7.214034 (lr=3.3311e-05) (hash(x)=26529231) +3975 train 7.219573 (lr=3.3281e-05) (hash(x)=24635394) +3976 train 7.514939 (lr=3.3251e-05) (hash(x)=24783093) +3977 train 7.629091 (lr=3.3222e-05) (hash(x)=26710509) +3978 train 7.070703 (lr=3.3192e-05) (hash(x)=25396630) +3979 train 6.966899 (lr=3.3162e-05) (hash(x)=22556381) +3980 train 7.286233 (lr=3.3133e-05) (hash(x)=26912161) +3981 train 6.848285 (lr=3.3103e-05) (hash(x)=22268078) +3982 train 7.876395 (lr=3.3073e-05) (hash(x)=30430328) +3983 train 7.474355 (lr=3.3044e-05) (hash(x)=27537228) +3984 train 6.928590 (lr=3.3014e-05) (hash(x)=24468603) +3985 train 7.250168 (lr=3.2985e-05) (hash(x)=27006663) +3986 train 7.459911 (lr=3.2956e-05) (hash(x)=27014728) +3987 train 6.929551 (lr=3.2926e-05) (hash(x)=20883633) +3988 train 7.033086 (lr=3.2897e-05) (hash(x)=23361791) +3989 train 7.147584 (lr=3.2867e-05) (hash(x)=26775925) +3990 train 7.703598 (lr=3.2838e-05) (hash(x)=30648934) +3991 train 7.180601 (lr=3.2809e-05) (hash(x)=26496730) +3992 train 7.008154 (lr=3.2779e-05) (hash(x)=25942897) +3993 train 7.029714 (lr=3.2750e-05) (hash(x)=24887111) +3994 train 6.911684 (lr=3.2721e-05) (hash(x)=22908550) +3995 train 6.669662 (lr=3.2692e-05) (hash(x)=20342150) +3996 train 6.922985 (lr=3.2662e-05) (hash(x)=22261760) +3997 train 6.973303 (lr=3.2633e-05) (hash(x)=22731641) +3998 train 6.888272 (lr=3.2604e-05) (hash(x)=20669749) +3999 train 6.827359 (lr=3.2575e-05) (hash(x)=16533310) +4000 val loss 7.1684 +4000 val perplexity 1297.7434 +4000 train 7.020638 (lr=3.2546e-05) (hash(x)=23661341) +4001 train 6.988931 (lr=3.2517e-05) (hash(x)=24644301) +4002 train 6.799538 (lr=3.2488e-05) (hash(x)=22938438) +4003 train 6.934835 (lr=3.2459e-05) (hash(x)=24315862) +4004 train 7.144414 (lr=3.2430e-05) (hash(x)=25169315) +4005 train 7.089912 (lr=3.2401e-05) (hash(x)=24752796) +4006 train 7.079114 (lr=3.2372e-05) (hash(x)=23103706) +4007 train 7.162639 (lr=3.2343e-05) (hash(x)=24881176) +4008 train 7.036368 (lr=3.2314e-05) (hash(x)=23971947) +4009 train 7.371805 (lr=3.2285e-05) (hash(x)=27741054) +4010 train 7.723969 (lr=3.2256e-05) (hash(x)=30956251) +4011 train 7.103767 (lr=3.2227e-05) (hash(x)=23649686) +4012 train 6.968915 (lr=3.2198e-05) (hash(x)=23344798) +4013 train 7.585593 (lr=3.2170e-05) (hash(x)=29529498) +4014 train 7.113300 (lr=3.2141e-05) (hash(x)=24688359) +4015 train 7.065473 (lr=3.2112e-05) (hash(x)=25593613) +4016 train 7.188774 (lr=3.2083e-05) (hash(x)=25674488) +4017 train 6.648178 (lr=3.2055e-05) (hash(x)=21345346) +4018 train 6.992354 (lr=3.2026e-05) (hash(x)=21978324) +4019 train 6.969480 (lr=3.1997e-05) (hash(x)=23669244) +4020 train 6.865433 (lr=3.1969e-05) (hash(x)=22479613) +4021 train 6.887267 (lr=3.1940e-05) (hash(x)=22855256) +4022 train 7.267500 (lr=3.1912e-05) (hash(x)=19759826) +4023 train 7.171669 (lr=3.1883e-05) (hash(x)=22886646) +4024 train 7.094232 (lr=3.1855e-05) (hash(x)=25553008) +4025 train 6.964749 (lr=3.1826e-05) (hash(x)=25487028) +4026 train 7.534088 (lr=3.1798e-05) (hash(x)=26799246) +4027 train 7.861894 (lr=3.1769e-05) (hash(x)=30728540) +4028 train 7.278380 (lr=3.1741e-05) (hash(x)=23966676) +4029 train 6.994543 (lr=3.1713e-05) (hash(x)=22118783) +4030 train 7.121690 (lr=3.1684e-05) (hash(x)=24744703) +4031 train 7.121187 (lr=3.1656e-05) (hash(x)=21407676) +4032 train 7.050508 (lr=3.1628e-05) (hash(x)=20623349) +4033 train 6.824330 (lr=3.1599e-05) (hash(x)=24723788) +4034 train 7.148706 (lr=3.1571e-05) (hash(x)=25030709) +4035 train 7.154890 (lr=3.1543e-05) (hash(x)=26326164) +4036 train 7.042183 (lr=3.1515e-05) (hash(x)=23754475) +4037 train 7.681609 (lr=3.1487e-05) (hash(x)=30112933) +4038 train 7.399130 (lr=3.1458e-05) (hash(x)=27474299) +4039 train 6.874167 (lr=3.1430e-05) (hash(x)=21720304) +4040 train 7.292461 (lr=3.1402e-05) (hash(x)=25142674) +4041 train 7.529216 (lr=3.1374e-05) (hash(x)=25284552) +4042 train 7.413320 (lr=3.1346e-05) (hash(x)=24554942) +4043 train 7.157326 (lr=3.1318e-05) (hash(x)=23773870) +4044 train 6.926261 (lr=3.1290e-05) (hash(x)=23896338) +4045 train 7.774524 (lr=3.1262e-05) (hash(x)=34984911) +4046 train 7.011110 (lr=3.1234e-05) (hash(x)=23854263) +4047 train 7.304627 (lr=3.1206e-05) (hash(x)=27263416) +4048 train 6.987849 (lr=3.1178e-05) (hash(x)=24989642) +4049 train 7.002268 (lr=3.1151e-05) (hash(x)=24492055) +4050 val loss 7.1741 +4050 val perplexity 1305.1394 +4050 train 6.901991 (lr=3.1123e-05) (hash(x)=21579916) +4051 train 7.135396 (lr=3.1095e-05) (hash(x)=25274710) +4052 train 7.034059 (lr=3.1067e-05) (hash(x)=24701947) +4053 train 7.028069 (lr=3.1039e-05) (hash(x)=25477340) +4054 train 6.924684 (lr=3.1012e-05) (hash(x)=23774195) +4055 train 7.184518 (lr=3.0984e-05) (hash(x)=25840801) +4056 train 7.398988 (lr=3.0956e-05) (hash(x)=27972529) +4057 train 7.159145 (lr=3.0929e-05) (hash(x)=26952458) +4058 train 6.715990 (lr=3.0901e-05) (hash(x)=22683653) +4059 train 6.731208 (lr=3.0873e-05) (hash(x)=20984129) +4060 train 6.921195 (lr=3.0846e-05) (hash(x)=22816482) +4061 train 7.163460 (lr=3.0818e-05) (hash(x)=24285302) +4062 train 7.581512 (lr=3.0791e-05) (hash(x)=31517950) +4063 train 7.827863 (lr=3.0763e-05) (hash(x)=31424568) +4064 train 7.556729 (lr=3.0736e-05) (hash(x)=29497876) +4065 train 7.416851 (lr=3.0708e-05) (hash(x)=27277376) +4066 train 7.129987 (lr=3.0681e-05) (hash(x)=26832588) +4067 train 6.975881 (lr=3.0653e-05) (hash(x)=25149712) +4068 train 6.977132 (lr=3.0626e-05) (hash(x)=23728457) +4069 train 6.876388 (lr=3.0599e-05) (hash(x)=25265136) +4070 train 7.405270 (lr=3.0571e-05) (hash(x)=25241681) +4071 train 7.115927 (lr=3.0544e-05) (hash(x)=23403065) +4072 train 7.049295 (lr=3.0517e-05) (hash(x)=25808207) +4073 train 6.983891 (lr=3.0490e-05) (hash(x)=23904844) +4074 train 6.666116 (lr=3.0462e-05) (hash(x)=18865309) +4075 train 7.136308 (lr=3.0435e-05) (hash(x)=23531744) +4076 train 7.171622 (lr=3.0408e-05) (hash(x)=25784275) +4077 train 6.903614 (lr=3.0381e-05) (hash(x)=22417529) +4078 train 6.909477 (lr=3.0354e-05) (hash(x)=23095491) +4079 train 7.049211 (lr=3.0327e-05) (hash(x)=22656033) +4080 train 7.058372 (lr=3.0300e-05) (hash(x)=25865435) +4081 train 7.163684 (lr=3.0273e-05) (hash(x)=25699377) +4082 train 7.168669 (lr=3.0246e-05) (hash(x)=20854084) +4083 train 6.708473 (lr=3.0219e-05) (hash(x)=18950799) +4084 train 6.957265 (lr=3.0192e-05) (hash(x)=22633739) +4085 train 7.881065 (lr=3.0165e-05) (hash(x)=34054446) +4086 train 7.278562 (lr=3.0138e-05) (hash(x)=27599387) +4087 train 7.139278 (lr=3.0111e-05) (hash(x)=26869295) +4088 train 7.121047 (lr=3.0084e-05) (hash(x)=24075139) +4089 train 7.553365 (lr=3.0057e-05) (hash(x)=29784110) +4090 train 7.853604 (lr=3.0030e-05) (hash(x)=34273918) +4091 train 8.250628 (lr=3.0004e-05) (hash(x)=34472685) +4092 train 7.589641 (lr=2.9977e-05) (hash(x)=30113791) +4093 train 6.852891 (lr=2.9950e-05) (hash(x)=22366381) +4094 train 7.109755 (lr=2.9924e-05) (hash(x)=24922935) +4095 train 7.278357 (lr=2.9897e-05) (hash(x)=25504151) +4096 train 7.266734 (lr=2.9870e-05) (hash(x)=24517375) +4097 train 7.957103 (lr=2.9844e-05) (hash(x)=25871651) +4098 train 6.993360 (lr=2.9817e-05) (hash(x)=23480225) +4099 train 6.865331 (lr=2.9790e-05) (hash(x)=22559978) +4100 val loss 7.1863 +4100 val perplexity 1321.2545 +4100 train 7.266523 (lr=2.9764e-05) (hash(x)=25795272) +4101 train 7.246355 (lr=2.9737e-05) (hash(x)=25440399) +4102 train 6.947689 (lr=2.9711e-05) (hash(x)=21581806) +4103 train 6.965576 (lr=2.9684e-05) (hash(x)=25781518) +4104 train 7.113392 (lr=2.9658e-05) (hash(x)=24682372) +4105 train 6.904526 (lr=2.9632e-05) (hash(x)=22440094) +4106 train 7.092720 (lr=2.9605e-05) (hash(x)=23661032) +4107 train 7.336844 (lr=2.9579e-05) (hash(x)=26966012) +4108 train 7.365677 (lr=2.9553e-05) (hash(x)=26232227) +4109 train 7.013433 (lr=2.9526e-05) (hash(x)=24110656) +4110 train 7.271245 (lr=2.9500e-05) (hash(x)=25938621) +4111 train 7.104642 (lr=2.9474e-05) (hash(x)=26432850) +4112 train 7.086965 (lr=2.9448e-05) (hash(x)=25387672) +4113 train 6.876378 (lr=2.9421e-05) (hash(x)=22740017) +4114 train 7.250833 (lr=2.9395e-05) (hash(x)=26384190) +4115 train 6.949780 (lr=2.9369e-05) (hash(x)=24725583) +4116 train 7.083980 (lr=2.9343e-05) (hash(x)=23986700) +4117 train 7.092168 (lr=2.9317e-05) (hash(x)=18529900) +4118 train 7.103954 (lr=2.9291e-05) (hash(x)=22236257) +4119 train 6.773761 (lr=2.9265e-05) (hash(x)=20155894) +4120 train 6.581085 (lr=2.9239e-05) (hash(x)=17423813) +4121 train 6.523201 (lr=2.9213e-05) (hash(x)=18905183) +4122 train 6.903554 (lr=2.9187e-05) (hash(x)=22534398) +4123 train 7.537609 (lr=2.9161e-05) (hash(x)=25247868) +4124 train 7.101531 (lr=2.9135e-05) (hash(x)=23994188) +4125 train 6.936922 (lr=2.9109e-05) (hash(x)=22929754) +4126 train 6.844649 (lr=2.9083e-05) (hash(x)=22485897) +4127 train 6.885022 (lr=2.9057e-05) (hash(x)=22270169) +4128 train 6.855049 (lr=2.9032e-05) (hash(x)=23638027) +4129 train 7.179794 (lr=2.9006e-05) (hash(x)=23821210) +4130 train 7.013379 (lr=2.8980e-05) (hash(x)=25021512) +4131 train 7.108882 (lr=2.8954e-05) (hash(x)=25240141) +4132 train 7.060534 (lr=2.8929e-05) (hash(x)=22833160) +4133 train 6.982135 (lr=2.8903e-05) (hash(x)=22909944) +4134 train 7.236003 (lr=2.8877e-05) (hash(x)=26163558) +4135 train 6.994522 (lr=2.8852e-05) (hash(x)=22108461) +4136 train 6.937796 (lr=2.8826e-05) (hash(x)=22549232) +4137 train 7.126794 (lr=2.8801e-05) (hash(x)=24701302) +4138 train 7.278745 (lr=2.8775e-05) (hash(x)=25206013) +4139 train 7.212949 (lr=2.8750e-05) (hash(x)=27896130) +4140 train 6.920564 (lr=2.8724e-05) (hash(x)=24106243) +4141 train 7.533105 (lr=2.8699e-05) (hash(x)=27158651) +4142 train 7.109233 (lr=2.8673e-05) (hash(x)=23841147) +4143 train 7.088109 (lr=2.8648e-05) (hash(x)=24802848) +4144 train 7.369373 (lr=2.8623e-05) (hash(x)=24911295) +4145 train 7.133433 (lr=2.8597e-05) (hash(x)=26473900) +4146 train 7.191375 (lr=2.8572e-05) (hash(x)=26785092) +4147 train 7.489502 (lr=2.8547e-05) (hash(x)=30188532) +4148 train 6.977872 (lr=2.8521e-05) (hash(x)=25010649) +4149 train 6.958486 (lr=2.8496e-05) (hash(x)=22409016) +4150 val loss 7.1717 +4150 val perplexity 1302.1034 +4150 train 7.762474 (lr=2.8471e-05) (hash(x)=31675024) +4151 train 7.017767 (lr=2.8446e-05) (hash(x)=25086604) +4152 train 7.039593 (lr=2.8421e-05) (hash(x)=24429343) +4153 train 7.214803 (lr=2.8395e-05) (hash(x)=25014232) +4154 train 7.122056 (lr=2.8370e-05) (hash(x)=25366275) +4155 train 7.606313 (lr=2.8345e-05) (hash(x)=24031473) +4156 train 7.122125 (lr=2.8320e-05) (hash(x)=26651059) +4157 train 7.210831 (lr=2.8295e-05) (hash(x)=26069721) +4158 train 7.370011 (lr=2.8270e-05) (hash(x)=28114382) +4159 train 7.363217 (lr=2.8245e-05) (hash(x)=26983186) +4160 train 6.708889 (lr=2.8220e-05) (hash(x)=21944670) +4161 train 7.439502 (lr=2.8195e-05) (hash(x)=28155702) +4162 train 6.879288 (lr=2.8170e-05) (hash(x)=24765002) +4163 train 7.125145 (lr=2.8146e-05) (hash(x)=26492636) +4164 train 7.077806 (lr=2.8121e-05) (hash(x)=24063705) +4165 train 7.372922 (lr=2.8096e-05) (hash(x)=27079573) +4166 train 7.039465 (lr=2.8071e-05) (hash(x)=24912201) +4167 train 7.133076 (lr=2.8046e-05) (hash(x)=27208507) +4168 train 7.079069 (lr=2.8022e-05) (hash(x)=25824320) +4169 train 7.597638 (lr=2.7997e-05) (hash(x)=29641677) +4170 train 7.281412 (lr=2.7972e-05) (hash(x)=26275614) +4171 train 7.127857 (lr=2.7948e-05) (hash(x)=25227725) +4172 train 7.211806 (lr=2.7923e-05) (hash(x)=27417375) +4173 train 7.405782 (lr=2.7898e-05) (hash(x)=25581973) +4174 train 7.645927 (lr=2.7874e-05) (hash(x)=30360417) +4175 train 6.929166 (lr=2.7849e-05) (hash(x)=23862845) +4176 train 7.053732 (lr=2.7825e-05) (hash(x)=25415130) +4177 train 7.029283 (lr=2.7800e-05) (hash(x)=23111123) +4178 train 7.005340 (lr=2.7776e-05) (hash(x)=24022804) +4179 train 7.020187 (lr=2.7751e-05) (hash(x)=25148490) +4180 train 7.247495 (lr=2.7727e-05) (hash(x)=22792092) +4181 train 7.342979 (lr=2.7703e-05) (hash(x)=24779698) +4182 train 7.232643 (lr=2.7678e-05) (hash(x)=24870844) +4183 train 6.950963 (lr=2.7654e-05) (hash(x)=22664494) +4184 train 6.995612 (lr=2.7630e-05) (hash(x)=22599729) +4185 train 7.190102 (lr=2.7605e-05) (hash(x)=24707078) +4186 train 6.986673 (lr=2.7581e-05) (hash(x)=23823945) +4187 train 6.701859 (lr=2.7557e-05) (hash(x)=22219856) +4188 train 7.379122 (lr=2.7533e-05) (hash(x)=27061401) +4189 train 7.100472 (lr=2.7509e-05) (hash(x)=23398766) +4190 train 7.183150 (lr=2.7484e-05) (hash(x)=27916730) +4191 train 7.112651 (lr=2.7460e-05) (hash(x)=24092927) +4192 train 7.132293 (lr=2.7436e-05) (hash(x)=24723657) +4193 train 7.183784 (lr=2.7412e-05) (hash(x)=24676155) +4194 train 7.052562 (lr=2.7388e-05) (hash(x)=23455369) +4195 train 6.994473 (lr=2.7364e-05) (hash(x)=21999890) +4196 train 6.924262 (lr=2.7340e-05) (hash(x)=23385567) +4197 train 7.137536 (lr=2.7316e-05) (hash(x)=25120814) +4198 train 6.815273 (lr=2.7292e-05) (hash(x)=21308113) +4199 train 7.144073 (lr=2.7269e-05) (hash(x)=27213812) +4200 val loss 7.1651 +4200 val perplexity 1293.4430 +4200 train 6.715153 (lr=2.7245e-05) (hash(x)=19675382) +4201 train 7.004940 (lr=2.7221e-05) (hash(x)=23882161) +4202 train 7.005310 (lr=2.7197e-05) (hash(x)=24338567) +4203 train 7.284709 (lr=2.7173e-05) (hash(x)=27649723) +4204 train 7.107687 (lr=2.7149e-05) (hash(x)=27563514) +4205 train 7.095798 (lr=2.7126e-05) (hash(x)=23128552) +4206 train 7.003973 (lr=2.7102e-05) (hash(x)=26203283) +4207 train 7.042184 (lr=2.7078e-05) (hash(x)=23929955) +4208 train 6.740062 (lr=2.7055e-05) (hash(x)=20978691) +4209 train 7.037160 (lr=2.7031e-05) (hash(x)=21875178) +4210 train 7.082490 (lr=2.7008e-05) (hash(x)=23563293) +4211 train 7.256484 (lr=2.6984e-05) (hash(x)=25538503) +4212 train 7.254057 (lr=2.6960e-05) (hash(x)=24171014) +4213 train 7.097307 (lr=2.6937e-05) (hash(x)=22306665) +4214 train 7.041039 (lr=2.6913e-05) (hash(x)=26082318) +4215 train 6.833409 (lr=2.6890e-05) (hash(x)=23025790) +4216 train 6.918279 (lr=2.6867e-05) (hash(x)=21146597) +4217 train 7.283771 (lr=2.6843e-05) (hash(x)=27470230) +4218 train 7.037552 (lr=2.6820e-05) (hash(x)=22691005) +4219 train 6.806961 (lr=2.6797e-05) (hash(x)=21550313) +4220 train 6.916182 (lr=2.6773e-05) (hash(x)=20618443) +4221 train 7.004982 (lr=2.6750e-05) (hash(x)=25260787) +4222 train 7.082439 (lr=2.6727e-05) (hash(x)=25249873) +4223 train 6.716652 (lr=2.6703e-05) (hash(x)=20452272) +4224 train 6.973187 (lr=2.6680e-05) (hash(x)=25649764) +4225 train 6.877509 (lr=2.6657e-05) (hash(x)=19589460) +4226 train 7.278594 (lr=2.6634e-05) (hash(x)=26477595) +4227 train 7.430156 (lr=2.6611e-05) (hash(x)=27585442) +4228 train 7.294494 (lr=2.6588e-05) (hash(x)=25821343) +4229 train 7.205481 (lr=2.6565e-05) (hash(x)=24549919) +4230 train 7.115468 (lr=2.6542e-05) (hash(x)=26124522) +4231 train 7.405327 (lr=2.6519e-05) (hash(x)=26473464) +4232 train 7.386964 (lr=2.6496e-05) (hash(x)=28883028) +4233 train 7.322005 (lr=2.6473e-05) (hash(x)=29611296) +4234 train 7.226398 (lr=2.6450e-05) (hash(x)=29059941) +4235 train 7.090954 (lr=2.6427e-05) (hash(x)=26368203) +4236 train 7.096345 (lr=2.6404e-05) (hash(x)=27021360) +4237 train 7.068626 (lr=2.6381e-05) (hash(x)=26135379) +4238 train 6.849567 (lr=2.6358e-05) (hash(x)=25862549) +4239 train 7.244414 (lr=2.6335e-05) (hash(x)=28276603) +4240 train 6.824509 (lr=2.6313e-05) (hash(x)=22170090) +4241 train 7.163136 (lr=2.6290e-05) (hash(x)=22625589) +4242 train 7.197557 (lr=2.6267e-05) (hash(x)=25751475) +4243 train 7.072968 (lr=2.6245e-05) (hash(x)=25836838) +4244 train 7.038311 (lr=2.6222e-05) (hash(x)=23938214) +4245 train 6.967641 (lr=2.6199e-05) (hash(x)=22759365) +4246 train 6.923139 (lr=2.6177e-05) (hash(x)=24964628) +4247 train 6.654418 (lr=2.6154e-05) (hash(x)=21480367) +4248 train 7.201080 (lr=2.6132e-05) (hash(x)=25974694) +4249 train 7.542343 (lr=2.6109e-05) (hash(x)=29830546) +4250 val loss 7.1618 +4250 val perplexity 1289.1875 +4250 train 7.239713 (lr=2.6087e-05) (hash(x)=26283200) +4251 train 7.218222 (lr=2.6064e-05) (hash(x)=25605672) +4252 train 6.894034 (lr=2.6042e-05) (hash(x)=21439107) +4253 train 6.805910 (lr=2.6019e-05) (hash(x)=22626883) +4254 train 7.189528 (lr=2.5997e-05) (hash(x)=25627150) +4255 train 7.305637 (lr=2.5975e-05) (hash(x)=24658642) +4256 train 7.408746 (lr=2.5952e-05) (hash(x)=29755505) +4257 train 7.104598 (lr=2.5930e-05) (hash(x)=22750846) +4258 train 7.012531 (lr=2.5908e-05) (hash(x)=21892651) +4259 train 7.086185 (lr=2.5885e-05) (hash(x)=22487960) +4260 train 7.135628 (lr=2.5863e-05) (hash(x)=24059869) +4261 train 6.925906 (lr=2.5841e-05) (hash(x)=21090180) +4262 train 7.040120 (lr=2.5819e-05) (hash(x)=22716452) +4263 train 7.271910 (lr=2.5797e-05) (hash(x)=26854801) +4264 train 7.068863 (lr=2.5775e-05) (hash(x)=23815428) +4265 train 6.931807 (lr=2.5753e-05) (hash(x)=23368704) +4266 train 6.985970 (lr=2.5731e-05) (hash(x)=24301098) +4267 train 7.188298 (lr=2.5709e-05) (hash(x)=25025039) +4268 train 6.929054 (lr=2.5687e-05) (hash(x)=25425736) +4269 train 7.152741 (lr=2.5665e-05) (hash(x)=27439380) +4270 train 6.601134 (lr=2.5643e-05) (hash(x)=18682756) +4271 train 6.745520 (lr=2.5621e-05) (hash(x)=17862226) +4272 train 7.345575 (lr=2.5599e-05) (hash(x)=29946491) +4273 train 6.597159 (lr=2.5577e-05) (hash(x)=21392062) +4274 train 7.177114 (lr=2.5555e-05) (hash(x)=25195556) +4275 train 7.157839 (lr=2.5533e-05) (hash(x)=26682036) +4276 train 7.090610 (lr=2.5512e-05) (hash(x)=21235260) +4277 train 6.882549 (lr=2.5490e-05) (hash(x)=22118984) +4278 train 6.912717 (lr=2.5468e-05) (hash(x)=24094510) +4279 train 7.436036 (lr=2.5447e-05) (hash(x)=28519182) +4280 train 7.081069 (lr=2.5425e-05) (hash(x)=26652859) +4281 train 6.995386 (lr=2.5403e-05) (hash(x)=24463139) +4282 train 6.992995 (lr=2.5382e-05) (hash(x)=23281870) +4283 train 7.201768 (lr=2.5360e-05) (hash(x)=29181174) +4284 train 6.898213 (lr=2.5339e-05) (hash(x)=24797417) +4285 train 7.252098 (lr=2.5317e-05) (hash(x)=29026537) +4286 train 7.033525 (lr=2.5296e-05) (hash(x)=23045165) +4287 train 6.952358 (lr=2.5274e-05) (hash(x)=25193694) +4288 train 7.013215 (lr=2.5253e-05) (hash(x)=23475407) +4289 train 7.128354 (lr=2.5231e-05) (hash(x)=24875410) +4290 train 7.054090 (lr=2.5210e-05) (hash(x)=26328101) +4291 train 7.310187 (lr=2.5189e-05) (hash(x)=26273661) +4292 train 7.023746 (lr=2.5167e-05) (hash(x)=23271891) +4293 train 6.994016 (lr=2.5146e-05) (hash(x)=23300732) +4294 train 7.102846 (lr=2.5125e-05) (hash(x)=24243693) +4295 train 7.174139 (lr=2.5104e-05) (hash(x)=25642620) +4296 train 7.214729 (lr=2.5082e-05) (hash(x)=27730411) +4297 train 6.975203 (lr=2.5061e-05) (hash(x)=25485335) +4298 train 6.846146 (lr=2.5040e-05) (hash(x)=25268789) +4299 train 7.304098 (lr=2.5019e-05) (hash(x)=28917143) +4300 val loss 7.1642 +4300 val perplexity 1292.2845 +4300 train 7.452035 (lr=2.4998e-05) (hash(x)=28987991) +4301 train 7.199249 (lr=2.4977e-05) (hash(x)=25989151) +4302 train 7.080194 (lr=2.4956e-05) (hash(x)=25658195) +4303 train 7.046636 (lr=2.4935e-05) (hash(x)=25765909) +4304 train 7.051883 (lr=2.4914e-05) (hash(x)=25704261) +4305 train 7.071060 (lr=2.4893e-05) (hash(x)=24438198) +4306 train 6.861427 (lr=2.4872e-05) (hash(x)=22871710) +4307 train 6.716444 (lr=2.4851e-05) (hash(x)=20160896) +4308 train 7.270164 (lr=2.4830e-05) (hash(x)=24218641) +4309 train 6.707456 (lr=2.4809e-05) (hash(x)=22073751) +4310 train 7.030088 (lr=2.4788e-05) (hash(x)=26434959) +4311 train 6.711710 (lr=2.4768e-05) (hash(x)=20750531) +4312 train 6.836921 (lr=2.4747e-05) (hash(x)=22232293) +4313 train 7.174309 (lr=2.4726e-05) (hash(x)=27324521) +4314 train 6.839248 (lr=2.4706e-05) (hash(x)=22217862) +4315 train 7.304715 (lr=2.4685e-05) (hash(x)=25741958) +4316 train 7.012127 (lr=2.4664e-05) (hash(x)=22738456) +4317 train 7.078299 (lr=2.4644e-05) (hash(x)=25387302) +4318 train 7.029720 (lr=2.4623e-05) (hash(x)=24669014) +4319 train 7.140244 (lr=2.4602e-05) (hash(x)=24917098) +4320 train 7.076515 (lr=2.4582e-05) (hash(x)=26698227) +4321 train 6.894354 (lr=2.4561e-05) (hash(x)=23518293) +4322 train 6.862102 (lr=2.4541e-05) (hash(x)=23643971) +4323 train 7.037637 (lr=2.4521e-05) (hash(x)=25659505) +4324 train 6.888574 (lr=2.4500e-05) (hash(x)=22697720) +4325 train 7.341504 (lr=2.4480e-05) (hash(x)=25082178) +4326 train 6.895230 (lr=2.4459e-05) (hash(x)=24166546) +4327 train 7.035352 (lr=2.4439e-05) (hash(x)=24499766) +4328 train 7.174877 (lr=2.4419e-05) (hash(x)=24338607) +4329 train 6.938739 (lr=2.4398e-05) (hash(x)=23225420) +4330 train 7.099464 (lr=2.4378e-05) (hash(x)=25907032) +4331 train 6.920203 (lr=2.4358e-05) (hash(x)=24634979) +4332 train 6.996936 (lr=2.4338e-05) (hash(x)=22161377) +4333 train 7.132775 (lr=2.4318e-05) (hash(x)=22559939) +4334 train 6.901997 (lr=2.4298e-05) (hash(x)=20840022) +4335 train 7.204076 (lr=2.4277e-05) (hash(x)=25067358) +4336 train 6.887979 (lr=2.4257e-05) (hash(x)=23432626) +4337 train 7.043813 (lr=2.4237e-05) (hash(x)=23820385) +4338 train 7.825330 (lr=2.4217e-05) (hash(x)=31594930) +4339 train 7.258937 (lr=2.4197e-05) (hash(x)=27138750) +4340 train 7.430312 (lr=2.4177e-05) (hash(x)=30031341) +4341 train 6.984726 (lr=2.4157e-05) (hash(x)=24602807) +4342 train 6.797209 (lr=2.4138e-05) (hash(x)=21584976) +4343 train 7.181388 (lr=2.4118e-05) (hash(x)=27479796) +4344 train 6.849988 (lr=2.4098e-05) (hash(x)=22746241) +4345 train 7.014144 (lr=2.4078e-05) (hash(x)=19728452) +4346 train 6.863596 (lr=2.4058e-05) (hash(x)=24502020) +4347 train 7.320863 (lr=2.4038e-05) (hash(x)=28225954) +4348 train 6.960877 (lr=2.4019e-05) (hash(x)=23893447) +4349 train 7.255334 (lr=2.3999e-05) (hash(x)=25654586) +4350 val loss 7.1609 +4350 val perplexity 1288.1288 +4350 train 7.126781 (lr=2.3979e-05) (hash(x)=23856469) +4351 train 7.057448 (lr=2.3960e-05) (hash(x)=23136080) +4352 train 7.156116 (lr=2.3940e-05) (hash(x)=26532918) +4353 train 7.061087 (lr=2.3921e-05) (hash(x)=25461947) +4354 train 7.070301 (lr=2.3901e-05) (hash(x)=26590231) +4355 train 6.812468 (lr=2.3881e-05) (hash(x)=21441985) +4356 train 7.084570 (lr=2.3862e-05) (hash(x)=26507941) +4357 train 7.354355 (lr=2.3842e-05) (hash(x)=26245238) +4358 train 7.178718 (lr=2.3823e-05) (hash(x)=24879059) +4359 train 7.419588 (lr=2.3804e-05) (hash(x)=29810074) +4360 train 6.847061 (lr=2.3784e-05) (hash(x)=24258069) +4361 train 6.976657 (lr=2.3765e-05) (hash(x)=25229360) +4362 train 7.168872 (lr=2.3746e-05) (hash(x)=25440206) +4363 train 7.036991 (lr=2.3726e-05) (hash(x)=23222125) +4364 train 6.884211 (lr=2.3707e-05) (hash(x)=23353186) +4365 train 7.093869 (lr=2.3688e-05) (hash(x)=26995240) +4366 train 7.027840 (lr=2.3669e-05) (hash(x)=24135899) +4367 train 7.071379 (lr=2.3649e-05) (hash(x)=24765539) +4368 train 7.097089 (lr=2.3630e-05) (hash(x)=26051004) +4369 train 6.844991 (lr=2.3611e-05) (hash(x)=22559142) +4370 train 6.761299 (lr=2.3592e-05) (hash(x)=20364388) +4371 train 7.254933 (lr=2.3573e-05) (hash(x)=25938817) +4372 train 7.287769 (lr=2.3554e-05) (hash(x)=26060945) +4373 train 7.175432 (lr=2.3535e-05) (hash(x)=27866714) +4374 train 7.125856 (lr=2.3516e-05) (hash(x)=27104972) +4375 train 6.804203 (lr=2.3497e-05) (hash(x)=22216309) +4376 train 6.883866 (lr=2.3478e-05) (hash(x)=20781533) +4377 train 6.762741 (lr=2.3459e-05) (hash(x)=18784350) +4378 train 6.905374 (lr=2.3440e-05) (hash(x)=21102897) +4379 train 7.191278 (lr=2.3421e-05) (hash(x)=25647489) +4380 train 6.981655 (lr=2.3403e-05) (hash(x)=24486462) +4381 train 7.234869 (lr=2.3384e-05) (hash(x)=26539114) +4382 train 6.878098 (lr=2.3365e-05) (hash(x)=20026045) +4383 train 7.165933 (lr=2.3346e-05) (hash(x)=20613861) +4384 train 6.891656 (lr=2.3328e-05) (hash(x)=20676237) +4385 train 7.097630 (lr=2.3309e-05) (hash(x)=24893163) +4386 train 6.652410 (lr=2.3290e-05) (hash(x)=17299395) +4387 train 6.829257 (lr=2.3272e-05) (hash(x)=19580191) +4388 train 6.999936 (lr=2.3253e-05) (hash(x)=25588218) +4389 train 7.141155 (lr=2.3234e-05) (hash(x)=26433063) +4390 train 7.200443 (lr=2.3216e-05) (hash(x)=24917693) +4391 train 6.879495 (lr=2.3197e-05) (hash(x)=23462447) +4392 train 7.080202 (lr=2.3179e-05) (hash(x)=27185416) +4393 train 7.224898 (lr=2.3161e-05) (hash(x)=24109010) +4394 train 6.990262 (lr=2.3142e-05) (hash(x)=21486000) +4395 train 6.869000 (lr=2.3124e-05) (hash(x)=22230006) +4396 train 7.281803 (lr=2.3105e-05) (hash(x)=26092311) +4397 train 7.015491 (lr=2.3087e-05) (hash(x)=24112426) +4398 train 6.889942 (lr=2.3069e-05) (hash(x)=21881373) +4399 train 7.019756 (lr=2.3051e-05) (hash(x)=26739455) +4400 val loss 7.1610 +4400 val perplexity 1288.2129 +4400 train 6.877595 (lr=2.3032e-05) (hash(x)=22873602) +4401 train 6.985584 (lr=2.3014e-05) (hash(x)=26748712) +4402 train 7.195428 (lr=2.2996e-05) (hash(x)=26306618) +4403 train 7.415958 (lr=2.2978e-05) (hash(x)=26898808) +4404 train 7.027500 (lr=2.2960e-05) (hash(x)=25067751) +4405 train 7.105083 (lr=2.2942e-05) (hash(x)=25397145) +4406 train 7.228775 (lr=2.2923e-05) (hash(x)=24796962) +4407 train 7.026076 (lr=2.2905e-05) (hash(x)=23222996) +4408 train 7.031998 (lr=2.2887e-05) (hash(x)=24820189) +4409 train 7.389752 (lr=2.2869e-05) (hash(x)=27669038) +4410 train 6.970872 (lr=2.2852e-05) (hash(x)=24283976) +4411 train 7.230464 (lr=2.2834e-05) (hash(x)=25018789) +4412 train 7.104051 (lr=2.2816e-05) (hash(x)=26247064) +4413 train 7.145299 (lr=2.2798e-05) (hash(x)=22942904) +4414 train 7.039543 (lr=2.2780e-05) (hash(x)=23918746) +4415 train 7.142919 (lr=2.2762e-05) (hash(x)=26489285) +4416 train 6.128908 (lr=2.2744e-05) (hash(x)=14942495) +4417 train 6.929239 (lr=2.2727e-05) (hash(x)=23908505) +4418 train 7.202457 (lr=2.2709e-05) (hash(x)=25854036) +4419 train 7.067282 (lr=2.2691e-05) (hash(x)=27522868) +4420 train 6.955757 (lr=2.2674e-05) (hash(x)=26549205) +4421 train 6.843640 (lr=2.2656e-05) (hash(x)=24565522) +4422 train 7.199033 (lr=2.2638e-05) (hash(x)=23919123) +4423 train 7.034994 (lr=2.2621e-05) (hash(x)=25185942) +4424 train 7.029889 (lr=2.2603e-05) (hash(x)=24818969) +4425 train 7.149156 (lr=2.2586e-05) (hash(x)=26750372) +4426 train 7.129754 (lr=2.2568e-05) (hash(x)=25621536) +4427 train 7.571426 (lr=2.2551e-05) (hash(x)=28037060) +4428 train 7.629743 (lr=2.2533e-05) (hash(x)=30829517) +4429 train 7.183527 (lr=2.2516e-05) (hash(x)=28728766) +4430 train 7.105224 (lr=2.2499e-05) (hash(x)=25936895) +4431 train 7.241005 (lr=2.2481e-05) (hash(x)=27476158) +4432 train 7.010671 (lr=2.2464e-05) (hash(x)=23297921) +4433 train 6.992489 (lr=2.2447e-05) (hash(x)=23201299) +4434 train 6.912378 (lr=2.2430e-05) (hash(x)=22681766) +4435 train 6.879936 (lr=2.2412e-05) (hash(x)=23217512) +4436 train 7.352688 (lr=2.2395e-05) (hash(x)=29322443) +4437 train 6.933005 (lr=2.2378e-05) (hash(x)=23502072) +4438 train 7.063896 (lr=2.2361e-05) (hash(x)=28873527) +4439 train 7.086777 (lr=2.2344e-05) (hash(x)=23653175) +4440 train 6.874628 (lr=2.2327e-05) (hash(x)=21635879) +4441 train 6.911270 (lr=2.2310e-05) (hash(x)=22201854) +4442 train 6.860280 (lr=2.2293e-05) (hash(x)=23101164) +4443 train 7.267185 (lr=2.2276e-05) (hash(x)=25475122) +4444 train 7.018336 (lr=2.2259e-05) (hash(x)=25124825) +4445 train 7.112869 (lr=2.2242e-05) (hash(x)=26883852) +4446 train 6.915431 (lr=2.2225e-05) (hash(x)=24731829) +4447 train 6.935210 (lr=2.2208e-05) (hash(x)=22405076) +4448 train 7.074863 (lr=2.2191e-05) (hash(x)=27633869) +4449 train 7.129602 (lr=2.2174e-05) (hash(x)=25162594) +4450 val loss 7.1525 +4450 val perplexity 1277.3350 +4450 train 7.134515 (lr=2.2157e-05) (hash(x)=26438149) +4451 train 7.152543 (lr=2.2141e-05) (hash(x)=26748800) +4452 train 6.899246 (lr=2.2124e-05) (hash(x)=22971620) +4453 train 7.022634 (lr=2.2107e-05) (hash(x)=25886430) +4454 train 6.810449 (lr=2.2091e-05) (hash(x)=21084137) +4455 train 6.979898 (lr=2.2074e-05) (hash(x)=25673545) +4456 train 7.671514 (lr=2.2057e-05) (hash(x)=29389002) +4457 train 6.727635 (lr=2.2041e-05) (hash(x)=21676076) +4458 train 6.807730 (lr=2.2024e-05) (hash(x)=22616647) +4459 train 7.195224 (lr=2.2008e-05) (hash(x)=22771197) +4460 train 7.133905 (lr=2.1991e-05) (hash(x)=26393514) +4461 train 7.357389 (lr=2.1975e-05) (hash(x)=24996433) +4462 train 6.994244 (lr=2.1958e-05) (hash(x)=19594028) +4463 train 7.141448 (lr=2.1942e-05) (hash(x)=22675428) +4464 train 7.137864 (lr=2.1926e-05) (hash(x)=26566551) +4465 train 7.166157 (lr=2.1909e-05) (hash(x)=22469290) +4466 train 7.627697 (lr=2.1893e-05) (hash(x)=29821654) +4467 train 7.140884 (lr=2.1877e-05) (hash(x)=26305388) +4468 train 6.963957 (lr=2.1860e-05) (hash(x)=21998506) +4469 train 7.370683 (lr=2.1844e-05) (hash(x)=23953315) +4470 train 7.026277 (lr=2.1828e-05) (hash(x)=23985456) +4471 train 7.408008 (lr=2.1812e-05) (hash(x)=28168456) +4472 train 7.067128 (lr=2.1796e-05) (hash(x)=25126411) +4473 train 6.888662 (lr=2.1780e-05) (hash(x)=24619336) +4474 train 7.081375 (lr=2.1764e-05) (hash(x)=24467798) +4475 train 7.903151 (lr=2.1747e-05) (hash(x)=31673254) +4476 train 7.714555 (lr=2.1731e-05) (hash(x)=29929610) +4477 train 7.436769 (lr=2.1715e-05) (hash(x)=29412572) +4478 train 7.587738 (lr=2.1699e-05) (hash(x)=31910006) +4479 train 7.201798 (lr=2.1684e-05) (hash(x)=26072586) +4480 train 7.171495 (lr=2.1668e-05) (hash(x)=25782825) +4481 train 6.997300 (lr=2.1652e-05) (hash(x)=21131363) +4482 train 7.130318 (lr=2.1636e-05) (hash(x)=25071223) +4483 train 7.745676 (lr=2.1620e-05) (hash(x)=32249577) +4484 train 6.958993 (lr=2.1604e-05) (hash(x)=24752808) +4485 train 6.999694 (lr=2.1589e-05) (hash(x)=24970539) +4486 train 6.927686 (lr=2.1573e-05) (hash(x)=24191005) +4487 train 7.142776 (lr=2.1557e-05) (hash(x)=24974331) +4488 train 7.313228 (lr=2.1542e-05) (hash(x)=27043409) +4489 train 6.764851 (lr=2.1526e-05) (hash(x)=11320385) +4490 train 6.742721 (lr=2.1510e-05) (hash(x)=11919565) +4491 train 6.790916 (lr=2.1495e-05) (hash(x)=10404694) +4492 train 6.830202 (lr=2.1479e-05) (hash(x)=12393159) +4493 train 6.734787 (lr=2.1464e-05) (hash(x)=11843609) +4494 train 6.775108 (lr=2.1448e-05) (hash(x)=12632729) +4495 train 7.034351 (lr=2.1433e-05) (hash(x)=21951984) +4496 train 7.706038 (lr=2.1417e-05) (hash(x)=19411544) +4497 train 7.647664 (lr=2.1402e-05) (hash(x)=21000228) +4498 train 7.235216 (lr=2.1386e-05) (hash(x)=26018207) +4499 train 7.249315 (lr=2.1371e-05) (hash(x)=24659058) +4500 val loss 7.1584 +4500 val perplexity 1284.8579 +4500 train 7.428071 (lr=2.1356e-05) (hash(x)=27919597) +4501 train 7.021804 (lr=2.1341e-05) (hash(x)=26232596) +4502 train 7.155968 (lr=2.1325e-05) (hash(x)=26248912) +4503 train 7.055959 (lr=2.1310e-05) (hash(x)=25403751) +4504 train 6.961488 (lr=2.1295e-05) (hash(x)=21096637) +4505 train 7.133231 (lr=2.1280e-05) (hash(x)=26560941) +4506 train 7.132107 (lr=2.1265e-05) (hash(x)=24942406) +4507 train 7.180844 (lr=2.1249e-05) (hash(x)=24405748) +4508 train 7.065147 (lr=2.1234e-05) (hash(x)=22975455) +4509 train 6.982889 (lr=2.1219e-05) (hash(x)=26358820) +4510 train 6.988679 (lr=2.1204e-05) (hash(x)=24211938) +4511 train 7.184099 (lr=2.1189e-05) (hash(x)=26396012) +4512 train 6.894177 (lr=2.1174e-05) (hash(x)=22534410) +4513 train 6.971757 (lr=2.1159e-05) (hash(x)=23855025) +4514 train 6.882310 (lr=2.1145e-05) (hash(x)=22722345) +4515 train 6.871576 (lr=2.1130e-05) (hash(x)=22779251) +4516 train 7.143126 (lr=2.1115e-05) (hash(x)=23973078) +4517 train 6.995565 (lr=2.1100e-05) (hash(x)=19886228) +4518 train 7.095584 (lr=2.1085e-05) (hash(x)=23849694) +4519 train 7.509407 (lr=2.1071e-05) (hash(x)=24827190) +4520 train 7.037824 (lr=2.1056e-05) (hash(x)=25111498) +4521 train 7.869687 (lr=2.1041e-05) (hash(x)=29752556) +4522 train 7.301584 (lr=2.1026e-05) (hash(x)=25606805) +4523 train 7.072012 (lr=2.1012e-05) (hash(x)=22209714) +4524 train 6.839563 (lr=2.0997e-05) (hash(x)=24991834) +4525 train 7.107002 (lr=2.0983e-05) (hash(x)=27808158) +4526 train 7.005745 (lr=2.0968e-05) (hash(x)=23041199) +4527 train 7.093779 (lr=2.0954e-05) (hash(x)=24847458) +4528 train 7.038232 (lr=2.0939e-05) (hash(x)=25091787) +4529 train 7.965465 (lr=2.0925e-05) (hash(x)=29745551) +4530 train 6.761758 (lr=2.0910e-05) (hash(x)=20447167) +4531 train 6.949306 (lr=2.0896e-05) (hash(x)=20720911) +4532 train 7.136519 (lr=2.0882e-05) (hash(x)=24803353) +4533 train 7.185192 (lr=2.0867e-05) (hash(x)=23780724) +4534 train 7.210659 (lr=2.0853e-05) (hash(x)=23423120) +4535 train 6.874063 (lr=2.0839e-05) (hash(x)=22159088) +4536 train 7.057496 (lr=2.0824e-05) (hash(x)=25820304) +4537 train 6.870130 (lr=2.0810e-05) (hash(x)=22813612) +4538 train 7.161979 (lr=2.0796e-05) (hash(x)=27827979) +4539 train 7.198555 (lr=2.0782e-05) (hash(x)=25737179) +4540 train 7.383486 (lr=2.0768e-05) (hash(x)=23401504) +4541 train 7.032677 (lr=2.0754e-05) (hash(x)=25071988) +4542 train 7.071210 (lr=2.0740e-05) (hash(x)=22844541) +4543 train 6.844779 (lr=2.0726e-05) (hash(x)=22140034) +4544 train 7.114537 (lr=2.0712e-05) (hash(x)=26522091) +4545 train 7.134865 (lr=2.0698e-05) (hash(x)=24099725) +4546 train 6.732584 (lr=2.0684e-05) (hash(x)=19127182) +4547 train 6.842903 (lr=2.0670e-05) (hash(x)=18992693) +4548 train 7.862253 (lr=2.0656e-05) (hash(x)=26723015) +4549 train 7.653963 (lr=2.0642e-05) (hash(x)=30389969) +4550 val loss 7.1599 +4550 val perplexity 1286.8273 +4550 train 6.963272 (lr=2.0628e-05) (hash(x)=24065654) +4551 train 6.760255 (lr=2.0614e-05) (hash(x)=19044797) +4552 train 7.193148 (lr=2.0601e-05) (hash(x)=24919665) +4553 train 7.220592 (lr=2.0587e-05) (hash(x)=22780968) +4554 train 6.953418 (lr=2.0573e-05) (hash(x)=24549699) +4555 train 6.868831 (lr=2.0559e-05) (hash(x)=21374811) +4556 train 6.986064 (lr=2.0546e-05) (hash(x)=25225950) +4557 train 7.109788 (lr=2.0532e-05) (hash(x)=25691882) +4558 train 7.004279 (lr=2.0519e-05) (hash(x)=24685235) +4559 train 6.854942 (lr=2.0505e-05) (hash(x)=23932794) +4560 train 7.452475 (lr=2.0492e-05) (hash(x)=28152043) +4561 train 6.939416 (lr=2.0478e-05) (hash(x)=23417051) +4562 train 7.026419 (lr=2.0465e-05) (hash(x)=26250211) +4563 train 7.226589 (lr=2.0451e-05) (hash(x)=25428813) +4564 train 7.391867 (lr=2.0438e-05) (hash(x)=27477379) +4565 train 7.160032 (lr=2.0424e-05) (hash(x)=23015212) +4566 train 6.900615 (lr=2.0411e-05) (hash(x)=22837608) +4567 train 6.999622 (lr=2.0398e-05) (hash(x)=25256890) +4568 train 6.915287 (lr=2.0384e-05) (hash(x)=22742827) +4569 train 7.313323 (lr=2.0371e-05) (hash(x)=30167922) +4570 train 6.990808 (lr=2.0358e-05) (hash(x)=24540265) +4571 train 7.316322 (lr=2.0345e-05) (hash(x)=26752941) +4572 train 7.119156 (lr=2.0332e-05) (hash(x)=25094026) +4573 train 7.785932 (lr=2.0318e-05) (hash(x)=28508785) +4574 train 7.206268 (lr=2.0305e-05) (hash(x)=26501871) +4575 train 7.008306 (lr=2.0292e-05) (hash(x)=24161711) +4576 train 6.933560 (lr=2.0279e-05) (hash(x)=24313695) +4577 train 7.342537 (lr=2.0266e-05) (hash(x)=28248933) +4578 train 7.520264 (lr=2.0253e-05) (hash(x)=28445722) +4579 train 7.099182 (lr=2.0240e-05) (hash(x)=24589015) +4580 train 7.279048 (lr=2.0227e-05) (hash(x)=26192193) +4581 train 6.916862 (lr=2.0214e-05) (hash(x)=25131316) +4582 train 7.023609 (lr=2.0202e-05) (hash(x)=26631504) +4583 train 6.868750 (lr=2.0189e-05) (hash(x)=22036817) +4584 train 7.478893 (lr=2.0176e-05) (hash(x)=28361254) +4585 train 7.083777 (lr=2.0163e-05) (hash(x)=24828340) +4586 train 6.787062 (lr=2.0150e-05) (hash(x)=24067304) +4587 train 6.588646 (lr=2.0138e-05) (hash(x)=20733289) +4588 train 6.484398 (lr=2.0125e-05) (hash(x)=19526622) +4589 train 6.878900 (lr=2.0112e-05) (hash(x)=22148688) +4590 train 7.107031 (lr=2.0100e-05) (hash(x)=24141800) +4591 train 7.149702 (lr=2.0087e-05) (hash(x)=26663208) +4592 train 6.817208 (lr=2.0075e-05) (hash(x)=22536305) +4593 train 7.050134 (lr=2.0062e-05) (hash(x)=23608185) +4594 train 6.939942 (lr=2.0049e-05) (hash(x)=23348495) +4595 train 7.118546 (lr=2.0037e-05) (hash(x)=25409759) +4596 train 7.078122 (lr=2.0025e-05) (hash(x)=25572131) +4597 train 7.072134 (lr=2.0012e-05) (hash(x)=21782039) +4598 train 7.034226 (lr=2.0000e-05) (hash(x)=24643923) +4599 train 6.991114 (lr=1.9987e-05) (hash(x)=24072213) +4600 val loss 7.1533 +4600 val perplexity 1278.3330 +4600 train 6.919612 (lr=1.9975e-05) (hash(x)=23925612) +4601 train 7.015619 (lr=1.9963e-05) (hash(x)=23315415) +4602 train 7.015011 (lr=1.9951e-05) (hash(x)=21793800) +4603 train 6.949677 (lr=1.9938e-05) (hash(x)=24921200) +4604 train 7.232107 (lr=1.9926e-05) (hash(x)=27226113) +4605 train 6.999820 (lr=1.9914e-05) (hash(x)=22920960) +4606 train 6.964476 (lr=1.9902e-05) (hash(x)=21947750) +4607 train 7.028184 (lr=1.9890e-05) (hash(x)=22766044) +4608 train 7.414138 (lr=1.9878e-05) (hash(x)=28237005) +4609 train 6.863442 (lr=1.9865e-05) (hash(x)=24922621) +4610 train 7.057550 (lr=1.9853e-05) (hash(x)=24899830) +4611 train 7.482184 (lr=1.9841e-05) (hash(x)=32920298) +4612 train 6.945969 (lr=1.9830e-05) (hash(x)=25083835) +4613 train 6.981515 (lr=1.9818e-05) (hash(x)=22863054) +4614 train 7.027010 (lr=1.9806e-05) (hash(x)=24841464) +4615 train 7.314749 (lr=1.9794e-05) (hash(x)=27871153) +4616 train 7.355373 (lr=1.9782e-05) (hash(x)=28025163) +4617 train 6.972188 (lr=1.9770e-05) (hash(x)=24659561) +4618 train 7.049862 (lr=1.9758e-05) (hash(x)=25067194) +4619 train 7.078722 (lr=1.9747e-05) (hash(x)=22731460) +4620 train 7.000540 (lr=1.9735e-05) (hash(x)=20445873) +4621 train 7.096260 (lr=1.9723e-05) (hash(x)=26033948) +4622 train 6.947003 (lr=1.9712e-05) (hash(x)=22473213) +4623 train 7.509834 (lr=1.9700e-05) (hash(x)=24037280) +4624 train 7.886610 (lr=1.9688e-05) (hash(x)=25624131) +4625 train 7.601987 (lr=1.9677e-05) (hash(x)=26799867) +4626 train 7.096793 (lr=1.9665e-05) (hash(x)=27187602) +4627 train 7.034329 (lr=1.9654e-05) (hash(x)=23277695) +4628 train 7.058336 (lr=1.9642e-05) (hash(x)=24748234) +4629 train 7.166420 (lr=1.9631e-05) (hash(x)=26103104) +4630 train 7.090641 (lr=1.9619e-05) (hash(x)=24327389) +4631 train 7.198956 (lr=1.9608e-05) (hash(x)=24121850) +4632 train 7.050308 (lr=1.9597e-05) (hash(x)=23714590) +4633 train 7.083936 (lr=1.9585e-05) (hash(x)=22379412) +4634 train 7.335739 (lr=1.9574e-05) (hash(x)=24454713) +4635 train 6.997949 (lr=1.9563e-05) (hash(x)=22966977) +4636 train 6.989888 (lr=1.9551e-05) (hash(x)=23764884) +4637 train 6.831676 (lr=1.9540e-05) (hash(x)=23827429) +4638 train 7.062869 (lr=1.9529e-05) (hash(x)=24088592) +4639 train 7.038564 (lr=1.9518e-05) (hash(x)=24380031) +4640 train 7.137593 (lr=1.9507e-05) (hash(x)=26065050) +4641 train 7.066509 (lr=1.9496e-05) (hash(x)=24442902) +4642 train 6.648297 (lr=1.9485e-05) (hash(x)=18548782) +4643 train 7.145227 (lr=1.9474e-05) (hash(x)=26957303) +4644 train 7.103574 (lr=1.9463e-05) (hash(x)=25032727) +4645 train 7.007405 (lr=1.9452e-05) (hash(x)=27224706) +4646 train 7.181607 (lr=1.9441e-05) (hash(x)=27508476) +4647 train 6.880424 (lr=1.9430e-05) (hash(x)=23055215) +4648 train 7.029758 (lr=1.9419e-05) (hash(x)=24496194) +4649 train 8.568713 (lr=1.9408e-05) (hash(x)=13982941) +4650 val loss 7.1547 +4650 val perplexity 1280.0775 +4650 train 7.616273 (lr=1.9397e-05) (hash(x)=16721547) +4651 train 7.035066 (lr=1.9387e-05) (hash(x)=22929154) +4652 train 6.970832 (lr=1.9376e-05) (hash(x)=23323994) +4653 train 7.305054 (lr=1.9365e-05) (hash(x)=24877951) +4654 train 7.152838 (lr=1.9354e-05) (hash(x)=24096183) +4655 train 6.983275 (lr=1.9344e-05) (hash(x)=25329724) +4656 train 6.960845 (lr=1.9333e-05) (hash(x)=23877337) +4657 train 6.599439 (lr=1.9322e-05) (hash(x)=20923083) +4658 train 6.931736 (lr=1.9312e-05) (hash(x)=23807996) +4659 train 7.010017 (lr=1.9301e-05) (hash(x)=24370475) +4660 train 7.390445 (lr=1.9291e-05) (hash(x)=28202255) +4661 train 7.120577 (lr=1.9280e-05) (hash(x)=26142119) +4662 train 6.909049 (lr=1.9270e-05) (hash(x)=21387743) +4663 train 7.027033 (lr=1.9260e-05) (hash(x)=25662408) +4664 train 7.091812 (lr=1.9249e-05) (hash(x)=23962815) +4665 train 7.004466 (lr=1.9239e-05) (hash(x)=23987677) +4666 train 7.290906 (lr=1.9228e-05) (hash(x)=26554284) +4667 train 7.330061 (lr=1.9218e-05) (hash(x)=25991817) +4668 train 7.039463 (lr=1.9208e-05) (hash(x)=24256966) +4669 train 6.842253 (lr=1.9198e-05) (hash(x)=22187158) +4670 train 7.124480 (lr=1.9187e-05) (hash(x)=26295320) +4671 train 7.139341 (lr=1.9177e-05) (hash(x)=26346814) +4672 train 7.406493 (lr=1.9167e-05) (hash(x)=26594196) +4673 train 7.171607 (lr=1.9157e-05) (hash(x)=24322101) +4674 train 7.259644 (lr=1.9147e-05) (hash(x)=27274566) +4675 train 7.083081 (lr=1.9137e-05) (hash(x)=24505725) +4676 train 7.213466 (lr=1.9127e-05) (hash(x)=26167371) +4677 train 7.344097 (lr=1.9117e-05) (hash(x)=28062311) +4678 train 7.087422 (lr=1.9107e-05) (hash(x)=23476009) +4679 train 7.154922 (lr=1.9097e-05) (hash(x)=25283256) +4680 train 6.876260 (lr=1.9087e-05) (hash(x)=22033246) +4681 train 6.919816 (lr=1.9077e-05) (hash(x)=22716214) +4682 train 7.058094 (lr=1.9067e-05) (hash(x)=25672672) +4683 train 6.920656 (lr=1.9058e-05) (hash(x)=22979072) +4684 train 7.132855 (lr=1.9048e-05) (hash(x)=27439204) +4685 train 7.062463 (lr=1.9038e-05) (hash(x)=24857737) +4686 train 7.332487 (lr=1.9028e-05) (hash(x)=29615897) +4687 train 6.917439 (lr=1.9019e-05) (hash(x)=24021771) +4688 train 7.052686 (lr=1.9009e-05) (hash(x)=27410807) +4689 train 6.879033 (lr=1.8999e-05) (hash(x)=22850411) +4690 train 7.155837 (lr=1.8990e-05) (hash(x)=24949696) +4691 train 6.940491 (lr=1.8980e-05) (hash(x)=22956381) +4692 train 7.450494 (lr=1.8971e-05) (hash(x)=28193458) +4693 train 6.963210 (lr=1.8961e-05) (hash(x)=25596844) +4694 train 6.941177 (lr=1.8952e-05) (hash(x)=22101377) +4695 train 6.864598 (lr=1.8942e-05) (hash(x)=23576840) +4696 train 6.862434 (lr=1.8933e-05) (hash(x)=21849758) +4697 train 7.062538 (lr=1.8923e-05) (hash(x)=26431349) +4698 train 7.159090 (lr=1.8914e-05) (hash(x)=22960758) +4699 train 7.040746 (lr=1.8905e-05) (hash(x)=23243097) +4700 val loss 7.1487 +4700 val perplexity 1272.5142 +4700 train 6.955532 (lr=1.8895e-05) (hash(x)=23715370) +4701 train 7.582362 (lr=1.8886e-05) (hash(x)=30678293) +4702 train 7.717052 (lr=1.8877e-05) (hash(x)=32481620) +4703 train 7.225805 (lr=1.8868e-05) (hash(x)=26414858) +4704 train 7.129322 (lr=1.8859e-05) (hash(x)=24768691) +4705 train 6.785524 (lr=1.8849e-05) (hash(x)=21627762) +4706 train 6.884700 (lr=1.8840e-05) (hash(x)=21024917) +4707 train 6.834733 (lr=1.8831e-05) (hash(x)=23570951) +4708 train 6.973481 (lr=1.8822e-05) (hash(x)=23729185) +4709 train 7.269924 (lr=1.8813e-05) (hash(x)=25933754) +4710 train 6.803331 (lr=1.8804e-05) (hash(x)=23091014) +4711 train 6.864072 (lr=1.8795e-05) (hash(x)=20099261) +4712 train 7.061684 (lr=1.8786e-05) (hash(x)=26807297) +4713 train 6.925758 (lr=1.8777e-05) (hash(x)=25332115) +4714 train 6.947091 (lr=1.8769e-05) (hash(x)=23247605) +4715 train 6.822343 (lr=1.8760e-05) (hash(x)=23786549) +4716 train 6.903441 (lr=1.8751e-05) (hash(x)=23981166) +4717 train 7.053746 (lr=1.8742e-05) (hash(x)=25967754) +4718 train 6.936125 (lr=1.8733e-05) (hash(x)=23659116) +4719 train 6.969452 (lr=1.8725e-05) (hash(x)=22453718) +4720 train 6.912797 (lr=1.8716e-05) (hash(x)=22597951) +4721 train 7.142975 (lr=1.8707e-05) (hash(x)=25284885) +4722 train 7.093750 (lr=1.8699e-05) (hash(x)=24748569) +4723 train 6.720160 (lr=1.8690e-05) (hash(x)=19448608) +4724 train 7.051158 (lr=1.8682e-05) (hash(x)=24888040) +4725 train 6.942542 (lr=1.8673e-05) (hash(x)=23203503) +4726 train 6.697057 (lr=1.8665e-05) (hash(x)=20387787) +4727 train 6.772598 (lr=1.8656e-05) (hash(x)=22529445) +4728 train 7.075966 (lr=1.8648e-05) (hash(x)=22455471) +4729 train 7.056343 (lr=1.8639e-05) (hash(x)=25661132) +4730 train 7.044615 (lr=1.8631e-05) (hash(x)=24997711) +4731 train 7.147024 (lr=1.8623e-05) (hash(x)=22575521) +4732 train 6.928291 (lr=1.8614e-05) (hash(x)=22640285) +4733 train 6.793128 (lr=1.8606e-05) (hash(x)=18637357) +4734 train 6.929952 (lr=1.8598e-05) (hash(x)=22845826) +4735 train 7.121814 (lr=1.8590e-05) (hash(x)=24484543) +4736 train 6.970346 (lr=1.8581e-05) (hash(x)=23352320) +4737 train 6.802672 (lr=1.8573e-05) (hash(x)=21544758) +4738 train 6.595823 (lr=1.8565e-05) (hash(x)=18292136) +4739 train 7.259033 (lr=1.8557e-05) (hash(x)=24893614) +4740 train 7.081960 (lr=1.8549e-05) (hash(x)=28103443) +4741 train 6.900394 (lr=1.8541e-05) (hash(x)=22233356) +4742 train 6.763242 (lr=1.8533e-05) (hash(x)=21133541) +4743 train 7.041290 (lr=1.8525e-05) (hash(x)=24043998) +4744 train 7.339697 (lr=1.8517e-05) (hash(x)=24801185) +4745 train 7.110215 (lr=1.8509e-05) (hash(x)=23858358) +4746 train 7.124023 (lr=1.8501e-05) (hash(x)=23926989) +4747 train 7.202384 (lr=1.8493e-05) (hash(x)=24813708) +4748 train 6.989429 (lr=1.8485e-05) (hash(x)=26339467) +4749 train 6.869309 (lr=1.8478e-05) (hash(x)=21850656) +4750 val loss 7.1504 +4750 val perplexity 1274.5879 +4750 train 6.858900 (lr=1.8470e-05) (hash(x)=21475802) +4751 train 7.056554 (lr=1.8462e-05) (hash(x)=24301906) +4752 train 6.891533 (lr=1.8455e-05) (hash(x)=22748495) +4753 train 7.029508 (lr=1.8447e-05) (hash(x)=25649256) +4754 train 6.944332 (lr=1.8439e-05) (hash(x)=23934346) +4755 train 7.060710 (lr=1.8432e-05) (hash(x)=26332892) +4756 train 6.942540 (lr=1.8424e-05) (hash(x)=23279389) +4757 train 6.988191 (lr=1.8416e-05) (hash(x)=23146858) +4758 train 7.335804 (lr=1.8409e-05) (hash(x)=26892932) +4759 train 6.878088 (lr=1.8401e-05) (hash(x)=26328881) +4760 train 6.985627 (lr=1.8394e-05) (hash(x)=24394655) +4761 train 6.940471 (lr=1.8387e-05) (hash(x)=22122308) +4762 train 7.100854 (lr=1.8379e-05) (hash(x)=24200369) +4763 train 7.226200 (lr=1.8372e-05) (hash(x)=26841776) +4764 train 7.189889 (lr=1.8365e-05) (hash(x)=27196641) +4765 train 6.934551 (lr=1.8357e-05) (hash(x)=24912822) +4766 train 7.204144 (lr=1.8350e-05) (hash(x)=25946055) +4767 train 6.790367 (lr=1.8343e-05) (hash(x)=23101508) +4768 train 6.956035 (lr=1.8336e-05) (hash(x)=24287798) +4769 train 7.041848 (lr=1.8328e-05) (hash(x)=22798964) +4770 train 6.975488 (lr=1.8321e-05) (hash(x)=24164479) +4771 train 7.028544 (lr=1.8314e-05) (hash(x)=24946464) +4772 train 7.166470 (lr=1.8307e-05) (hash(x)=25154423) +4773 train 6.839554 (lr=1.8300e-05) (hash(x)=23173476) +4774 train 7.113248 (lr=1.8293e-05) (hash(x)=25373559) +4775 train 7.064832 (lr=1.8286e-05) (hash(x)=23527176) +4776 train 7.063232 (lr=1.8279e-05) (hash(x)=24865403) +4777 train 6.984804 (lr=1.8272e-05) (hash(x)=24451067) +4778 train 7.624443 (lr=1.8265e-05) (hash(x)=28187162) +4779 train 7.789590 (lr=1.8258e-05) (hash(x)=31163350) +4780 train 8.113876 (lr=1.8251e-05) (hash(x)=33563280) +4781 train 8.164210 (lr=1.8245e-05) (hash(x)=34939183) +4782 train 7.647565 (lr=1.8238e-05) (hash(x)=30263543) +4783 train 6.939984 (lr=1.8231e-05) (hash(x)=22705673) +4784 train 6.804006 (lr=1.8224e-05) (hash(x)=21415023) +4785 train 7.037738 (lr=1.8218e-05) (hash(x)=26079097) +4786 train 7.339375 (lr=1.8211e-05) (hash(x)=25503836) +4787 train 7.209549 (lr=1.8204e-05) (hash(x)=24705721) +4788 train 7.065052 (lr=1.8198e-05) (hash(x)=24384657) +4789 train 6.991937 (lr=1.8191e-05) (hash(x)=22550579) +4790 train 7.040812 (lr=1.8185e-05) (hash(x)=22452164) +4791 train 7.320451 (lr=1.8178e-05) (hash(x)=28664796) +4792 train 7.679042 (lr=1.8172e-05) (hash(x)=26139280) +4793 train 7.324711 (lr=1.8165e-05) (hash(x)=23862341) +4794 train 6.902489 (lr=1.8159e-05) (hash(x)=23784757) +4795 train 6.771314 (lr=1.8153e-05) (hash(x)=22659441) +4796 train 7.540242 (lr=1.8146e-05) (hash(x)=29744216) +4797 train 7.430611 (lr=1.8140e-05) (hash(x)=25822591) +4798 train 6.852343 (lr=1.8134e-05) (hash(x)=22370895) +4799 train 7.286415 (lr=1.8127e-05) (hash(x)=27102890) +4800 val loss 7.1511 +4800 val perplexity 1275.4458 +4800 train 7.321741 (lr=1.8121e-05) (hash(x)=27014625) +4801 train 7.092616 (lr=1.8115e-05) (hash(x)=25755963) +4802 train 7.321092 (lr=1.8109e-05) (hash(x)=29675278) +4803 train 7.407994 (lr=1.8103e-05) (hash(x)=26660930) +4804 train 7.333527 (lr=1.8097e-05) (hash(x)=24557060) +4805 train 7.460745 (lr=1.8091e-05) (hash(x)=24622741) +4806 train 7.529977 (lr=1.8085e-05) (hash(x)=23952601) +4807 train 7.169206 (lr=1.8079e-05) (hash(x)=26787259) +4808 train 7.416883 (lr=1.8073e-05) (hash(x)=28919605) +4809 train 7.748601 (lr=1.8067e-05) (hash(x)=37061654) +4810 train 7.495042 (lr=1.8061e-05) (hash(x)=30379739) +4811 train 7.276213 (lr=1.8055e-05) (hash(x)=26097180) +4812 train 7.435229 (lr=1.8049e-05) (hash(x)=26327092) +4813 train 7.215508 (lr=1.8043e-05) (hash(x)=23258030) +4814 train 7.256788 (lr=1.8037e-05) (hash(x)=25582015) +4815 train 6.960809 (lr=1.8032e-05) (hash(x)=23396088) +4816 train 6.936810 (lr=1.8026e-05) (hash(x)=21904146) +4817 train 7.158607 (lr=1.8020e-05) (hash(x)=26281676) +4818 train 6.896091 (lr=1.8015e-05) (hash(x)=23140470) +4819 train 7.214405 (lr=1.8009e-05) (hash(x)=24611098) +4820 train 7.008325 (lr=1.8003e-05) (hash(x)=23832642) +4821 train 7.223244 (lr=1.7998e-05) (hash(x)=21439671) +4822 train 7.063960 (lr=1.7992e-05) (hash(x)=25128845) +4823 train 7.009664 (lr=1.7987e-05) (hash(x)=24911831) +4824 train 7.157695 (lr=1.7981e-05) (hash(x)=26051723) +4825 train 7.192488 (lr=1.7976e-05) (hash(x)=26479565) +4826 train 7.294137 (lr=1.7970e-05) (hash(x)=26228987) +4827 train 7.177581 (lr=1.7965e-05) (hash(x)=25131300) +4828 train 6.906559 (lr=1.7960e-05) (hash(x)=19921978) +4829 train 6.925866 (lr=1.7954e-05) (hash(x)=23173449) +4830 train 7.237764 (lr=1.7949e-05) (hash(x)=24791832) +4831 train 6.949071 (lr=1.7944e-05) (hash(x)=23453491) +4832 train 7.122764 (lr=1.7938e-05) (hash(x)=22564139) +4833 train 6.953519 (lr=1.7933e-05) (hash(x)=21659918) +4834 train 7.080358 (lr=1.7928e-05) (hash(x)=22956076) +4835 train 7.132821 (lr=1.7923e-05) (hash(x)=22237612) +4836 train 7.279538 (lr=1.7918e-05) (hash(x)=24736427) +4837 train 7.387492 (lr=1.7913e-05) (hash(x)=24939751) +4838 train 7.181423 (lr=1.7908e-05) (hash(x)=25059298) +4839 train 7.121275 (lr=1.7903e-05) (hash(x)=23453396) +4840 train 6.641262 (lr=1.7898e-05) (hash(x)=17919338) +4841 train 7.123566 (lr=1.7893e-05) (hash(x)=23428815) +4842 train 7.396320 (lr=1.7888e-05) (hash(x)=27042659) +4843 train 7.493503 (lr=1.7883e-05) (hash(x)=25161278) +4844 train 7.247271 (lr=1.7878e-05) (hash(x)=24113253) +4845 train 7.360651 (lr=1.7873e-05) (hash(x)=26139263) +4846 train 7.409798 (lr=1.7869e-05) (hash(x)=27787006) +4847 train 7.147344 (lr=1.7864e-05) (hash(x)=23869612) +4848 train 7.300643 (lr=1.7859e-05) (hash(x)=26092193) +4849 train 7.311353 (lr=1.7854e-05) (hash(x)=29351182) +4850 val loss 7.1447 +4850 val perplexity 1267.3518 +4850 train 7.469739 (lr=1.7850e-05) (hash(x)=28773463) +4851 train 7.411942 (lr=1.7845e-05) (hash(x)=28207741) +4852 train 6.952565 (lr=1.7840e-05) (hash(x)=23280878) +4853 train 7.394353 (lr=1.7836e-05) (hash(x)=26742336) +4854 train 7.189581 (lr=1.7831e-05) (hash(x)=23543321) +4855 train 7.547338 (lr=1.7827e-05) (hash(x)=26581590) +4856 train 7.024205 (lr=1.7822e-05) (hash(x)=22728668) +4857 train 6.850644 (lr=1.7818e-05) (hash(x)=19854534) +4858 train 7.284222 (lr=1.7813e-05) (hash(x)=26612813) +4859 train 7.397978 (lr=1.7809e-05) (hash(x)=25827863) +4860 train 7.083843 (lr=1.7805e-05) (hash(x)=24574997) +4861 train 7.270009 (lr=1.7800e-05) (hash(x)=26187830) +4862 train 7.184100 (lr=1.7796e-05) (hash(x)=25105823) +4863 train 7.275968 (lr=1.7792e-05) (hash(x)=28056342) +4864 train 7.127423 (lr=1.7787e-05) (hash(x)=21885801) +4865 train 7.331045 (lr=1.7783e-05) (hash(x)=25659043) +4866 train 7.296668 (lr=1.7779e-05) (hash(x)=23852824) +4867 train 7.101653 (lr=1.7775e-05) (hash(x)=23965470) +4868 train 7.103889 (lr=1.7771e-05) (hash(x)=25035012) +4869 train 7.322637 (lr=1.7767e-05) (hash(x)=26639165) +4870 train 7.279197 (lr=1.7763e-05) (hash(x)=29205362) +4871 train 7.152891 (lr=1.7759e-05) (hash(x)=25900866) +4872 train 7.192179 (lr=1.7755e-05) (hash(x)=25636242) +4873 train 7.258564 (lr=1.7751e-05) (hash(x)=25430698) +4874 train 7.226819 (lr=1.7747e-05) (hash(x)=27629981) +4875 train 7.206810 (lr=1.7743e-05) (hash(x)=27682625) +4876 train 7.453700 (lr=1.7739e-05) (hash(x)=27549409) +4877 train 7.184040 (lr=1.7735e-05) (hash(x)=24661627) +4878 train 7.233315 (lr=1.7731e-05) (hash(x)=25196542) +4879 train 7.124252 (lr=1.7728e-05) (hash(x)=24549177) +4880 train 7.089452 (lr=1.7724e-05) (hash(x)=23740600) +4881 train 6.972375 (lr=1.7720e-05) (hash(x)=21460850) +4882 train 7.271595 (lr=1.7716e-05) (hash(x)=27101400) +4883 train 7.262572 (lr=1.7713e-05) (hash(x)=24193076) +4884 train 7.151412 (lr=1.7709e-05) (hash(x)=24582947) +4885 train 7.135329 (lr=1.7706e-05) (hash(x)=25133839) +4886 train 7.134992 (lr=1.7702e-05) (hash(x)=24759454) +4887 train 7.201513 (lr=1.7698e-05) (hash(x)=28239583) +4888 train 7.462689 (lr=1.7695e-05) (hash(x)=29594489) +4889 train 7.148091 (lr=1.7692e-05) (hash(x)=23833431) +4890 train 7.113835 (lr=1.7688e-05) (hash(x)=23139411) +4891 train 7.084714 (lr=1.7685e-05) (hash(x)=20885864) +4892 train 7.536325 (lr=1.7681e-05) (hash(x)=26217418) +4893 train 7.282523 (lr=1.7678e-05) (hash(x)=27321870) +4894 train 6.748435 (lr=1.7675e-05) (hash(x)=19912955) +4895 train 7.064937 (lr=1.7671e-05) (hash(x)=23223554) +4896 train 7.254444 (lr=1.7668e-05) (hash(x)=25667219) +4897 train 7.479455 (lr=1.7665e-05) (hash(x)=28007972) +4898 train 7.296670 (lr=1.7662e-05) (hash(x)=27748764) +4899 train 7.224903 (lr=1.7659e-05) (hash(x)=27425770) +4900 val loss 7.1397 +4900 val perplexity 1261.0596 +4900 train 7.335124 (lr=1.7655e-05) (hash(x)=28394020) +4901 train 7.184177 (lr=1.7652e-05) (hash(x)=24080235) +4902 train 7.061558 (lr=1.7649e-05) (hash(x)=23309527) +4903 train 7.033855 (lr=1.7646e-05) (hash(x)=24793480) +4904 train 7.253640 (lr=1.7643e-05) (hash(x)=25344456) +4905 train 7.201805 (lr=1.7640e-05) (hash(x)=24590670) +4906 train 7.141168 (lr=1.7637e-05) (hash(x)=26937171) +4907 train 7.289913 (lr=1.7634e-05) (hash(x)=26949097) +4908 train 6.979317 (lr=1.7632e-05) (hash(x)=22443915) +4909 train 7.048279 (lr=1.7629e-05) (hash(x)=23814995) +4910 train 7.110296 (lr=1.7626e-05) (hash(x)=26135871) +4911 train 6.938354 (lr=1.7623e-05) (hash(x)=25415570) +4912 train 7.259027 (lr=1.7620e-05) (hash(x)=26756326) +4913 train 7.128275 (lr=1.7618e-05) (hash(x)=22920200) +4914 train 7.198993 (lr=1.7615e-05) (hash(x)=26710977) +4915 train 7.117065 (lr=1.7612e-05) (hash(x)=24985634) +4916 train 7.235167 (lr=1.7610e-05) (hash(x)=26004335) +4917 train 7.156429 (lr=1.7607e-05) (hash(x)=25637457) +4918 train 7.382663 (lr=1.7605e-05) (hash(x)=26645180) +4919 train 7.197618 (lr=1.7602e-05) (hash(x)=24425760) +4920 train 7.447139 (lr=1.7600e-05) (hash(x)=28223544) +4921 train 7.153667 (lr=1.7597e-05) (hash(x)=25538618) +4922 train 7.405924 (lr=1.7595e-05) (hash(x)=26984784) +4923 train 7.421787 (lr=1.7592e-05) (hash(x)=29154578) +4924 train 7.122794 (lr=1.7590e-05) (hash(x)=25308123) +4925 train 7.432576 (lr=1.7587e-05) (hash(x)=27939259) +4926 train 7.039770 (lr=1.7585e-05) (hash(x)=21984545) +4927 train 7.083986 (lr=1.7583e-05) (hash(x)=23707134) +4928 train 7.125785 (lr=1.7581e-05) (hash(x)=27201034) +4929 train 7.512637 (lr=1.7578e-05) (hash(x)=31623877) +4930 train 7.141062 (lr=1.7576e-05) (hash(x)=22162782) +4931 train 7.060783 (lr=1.7574e-05) (hash(x)=20049335) +4932 train 6.999081 (lr=1.7572e-05) (hash(x)=25594665) +4933 train 7.098076 (lr=1.7570e-05) (hash(x)=25265312) +4934 train 7.228491 (lr=1.7568e-05) (hash(x)=27094896) +4935 train 7.591406 (lr=1.7566e-05) (hash(x)=28321697) +4936 train 7.086864 (lr=1.7564e-05) (hash(x)=25006013) +4937 train 7.293965 (lr=1.7562e-05) (hash(x)=24596431) +4938 train 7.327062 (lr=1.7560e-05) (hash(x)=25150510) +4939 train 6.830804 (lr=1.7558e-05) (hash(x)=21497535) +4940 train 7.114172 (lr=1.7556e-05) (hash(x)=25094669) +4941 train 7.004076 (lr=1.7554e-05) (hash(x)=24024557) +4942 train 7.285108 (lr=1.7552e-05) (hash(x)=24370776) +4943 train 7.136915 (lr=1.7551e-05) (hash(x)=23434031) +4944 train 7.124396 (lr=1.7549e-05) (hash(x)=24383517) +4945 train 7.160213 (lr=1.7547e-05) (hash(x)=25858759) +4946 train 6.760328 (lr=1.7545e-05) (hash(x)=20409561) +4947 train 7.429263 (lr=1.7544e-05) (hash(x)=27469117) +4948 train 6.999872 (lr=1.7542e-05) (hash(x)=22086623) +4949 train 7.266406 (lr=1.7540e-05) (hash(x)=25759281) +4950 val loss 7.1368 +4950 val perplexity 1257.4484 +4950 train 7.194244 (lr=1.7539e-05) (hash(x)=27130117) +4951 train 7.061549 (lr=1.7537e-05) (hash(x)=27003481) +4952 train 7.389873 (lr=1.7536e-05) (hash(x)=26725937) +4953 train 7.118698 (lr=1.7534e-05) (hash(x)=22691119) +4954 train 7.170221 (lr=1.7533e-05) (hash(x)=17272898) +4955 train 6.984892 (lr=1.7531e-05) (hash(x)=17850370) +4956 train 6.993810 (lr=1.7530e-05) (hash(x)=18729639) +4957 train 7.201925 (lr=1.7529e-05) (hash(x)=25327160) +4958 train 7.347928 (lr=1.7527e-05) (hash(x)=28709044) +4959 train 6.930244 (lr=1.7526e-05) (hash(x)=22236893) +4960 train 6.865874 (lr=1.7525e-05) (hash(x)=21729251) +4961 train 6.998900 (lr=1.7524e-05) (hash(x)=23852346) +4962 train 7.192775 (lr=1.7522e-05) (hash(x)=23974368) +4963 train 7.128201 (lr=1.7521e-05) (hash(x)=25764691) +4964 train 7.527284 (lr=1.7520e-05) (hash(x)=28341865) +4965 train 7.022400 (lr=1.7519e-05) (hash(x)=23856238) +4966 train 7.263069 (lr=1.7518e-05) (hash(x)=24568904) +4967 train 7.148689 (lr=1.7517e-05) (hash(x)=26857458) +4968 train 7.044899 (lr=1.7516e-05) (hash(x)=20507972) +4969 train 7.225590 (lr=1.7515e-05) (hash(x)=23139455) +4970 train 7.055115 (lr=1.7514e-05) (hash(x)=24853703) +4971 train 7.094002 (lr=1.7513e-05) (hash(x)=25654849) +4972 train 6.920496 (lr=1.7512e-05) (hash(x)=22963710) +4973 train 7.287755 (lr=1.7511e-05) (hash(x)=25652110) +4974 train 7.226144 (lr=1.7511e-05) (hash(x)=24085957) +4975 train 7.442889 (lr=1.7510e-05) (hash(x)=26413122) +4976 train 7.582972 (lr=1.7509e-05) (hash(x)=26989387) +4977 train 7.224648 (lr=1.7508e-05) (hash(x)=22784033) +4978 train 7.586042 (lr=1.7508e-05) (hash(x)=26694945) +4979 train 7.526077 (lr=1.7507e-05) (hash(x)=24507726) +4980 train 7.565468 (lr=1.7506e-05) (hash(x)=26490335) +4981 train 7.512767 (lr=1.7506e-05) (hash(x)=25624751) +4982 train 7.486905 (lr=1.7505e-05) (hash(x)=27846204) +4983 train 7.363484 (lr=1.7504e-05) (hash(x)=27696537) +4984 train 7.240771 (lr=1.7504e-05) (hash(x)=28915842) +4985 train 7.305323 (lr=1.7503e-05) (hash(x)=28274576) +4986 train 7.327507 (lr=1.7503e-05) (hash(x)=28923892) +4987 train 6.946237 (lr=1.7503e-05) (hash(x)=21602520) +4988 train 6.883145 (lr=1.7502e-05) (hash(x)=21061011) +4989 train 7.359058 (lr=1.7502e-05) (hash(x)=28060542) +4990 train 7.154237 (lr=1.7502e-05) (hash(x)=24838134) +4991 train 7.085872 (lr=1.7501e-05) (hash(x)=21950234) +4992 train 7.349414 (lr=1.7501e-05) (hash(x)=27192740) +4993 train 7.326338 (lr=1.7501e-05) (hash(x)=26770105) +4994 train 7.020656 (lr=1.7501e-05) (hash(x)=23721261) +4995 train 7.065309 (lr=1.7500e-05) (hash(x)=26064895) +4996 train 7.278234 (lr=1.7500e-05) (hash(x)=25651075) +4997 train 7.096890 (lr=1.7500e-05) (hash(x)=25029447) +4998 train 7.274466 (lr=1.7500e-05) (hash(x)=26088225) +4999 val loss 7.1381 +4999 val perplexity 1258.9999 +4999 train 7.190485 (lr=1.7500e-05) (hash(x)=24051952) diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/model_02500.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/model_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..32fee17ca84b59a60137c2b2c971ddb939d69b3f --- /dev/null +++ b/lr1.75e-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:defea6a632319118df7d16678f44f86ef66eedefa4ebdc84b96c3f16ecab0128 +size 38587970 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/model_04999.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/model_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..1b0842cfe88b3b6f0057e5c0427d51d6a37e8d6a --- /dev/null +++ b/lr1.75e-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:e45d09d06f3a257f9e8ceba7aa1f548ad247f74be98b06e92d1f3f4709b11e49 +size 38587970 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/optimizer_02500.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/optimizer_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..9b3e57f60cc7202c2bc8ab299fc5f5fec4eadcce --- /dev/null +++ b/lr1.75e-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:b1028f2f978c6d69dfb43fb207733ee04401624506ba0db579dd2eff3cb58676 +size 70895430 diff --git a/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/optimizer_04999.pt b/lr1.75e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1_seed1339/optimizer_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..d82102cb0dcdcb322f0af7d442d9e4c8fac4176c --- /dev/null +++ b/lr1.75e-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 sha256:09694c746d7e3e6c52ba31e8472d2750d52574edb40a2936a52aea6f9512088f +size 70895430