diff --git a/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/args.json b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/args.json new file mode 100644 index 0000000000000000000000000000000000000000..e124c14687e2b929b6fb9fc34dfe15789bf419a9 --- /dev/null +++ b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/args.json @@ -0,0 +1 @@ +{"hellaswag": true, "attention_kind": "selective", "log_dir": "proxy_model_sweep_2/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1", "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": 1337, "memory_penalty_epsilon": 0.1, "selection_head_linear_combo": "none", "selection_head_linear_combo_scale": 1.0, "protection_kind": "none", "leaky_relu_alpha": null, "leaky_relu_bias": null, "use_compile": true, "use_mini_model": false, "upload_to_hf": true, "seq_len": 256, "batch_size": 20, "total_batch_size": 5120, "protection_head_scaling_factor": 1.0, "protection_head_bias": 0.0, "n_sliced_masks": null, "n_latent_masks": null, "mask_layernorm": false, "residual_attention_masks": false, "compute_base_shapes": false, "base_shapes_savefile": null, "mup": true, "disable_selection": false, "mup_enable_coord_check_logging": false, "max_lr": 0.00015, "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/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/dataloader_02500.pt b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/dataloader_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..2bc253f8fc6225637fb651d7b45bcde02b1c9ff0 --- /dev/null +++ b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/dataloader_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5f86eba64e08aa3145708d463ef689ecaee47ebe0a97035e6e0aeb59f377344 +size 964 diff --git a/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/dataloader_04999.pt b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/dataloader_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..0618c479f1dc6588bdd52311cf3417cbd843ddd9 --- /dev/null +++ b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/dataloader_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431842dc67f0d83e5eb85cf9c36fd024e295001fe78f3ba5deeae77865394feb +size 964 diff --git a/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/log2.txt b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/log2.txt new file mode 100644 index 0000000000000000000000000000000000000000..b99dfe0c04faf9e80167b5b608fbfccb9123a07c --- /dev/null +++ b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/log2.txt @@ -0,0 +1,5203 @@ +max_steps: 5000 +0 val loss 11.7537 +0 val perplexity 127229.2734 +0 train 11.717543 (lr=1.5000e-04) (hash(x)=22886834) +1 train 11.449745 (lr=1.5000e-04) (hash(x)=26375038) +2 train 11.188172 (lr=1.5000e-04) (hash(x)=30598777) +3 train 10.928001 (lr=1.5000e-04) (hash(x)=27234506) +4 train 10.582264 (lr=1.5000e-04) (hash(x)=27767880) +5 train 10.384743 (lr=1.5000e-04) (hash(x)=23702020) +6 train 10.272396 (lr=1.5000e-04) (hash(x)=31986844) +7 train 10.273900 (lr=1.5000e-04) (hash(x)=20782690) +8 train 10.220820 (lr=1.5000e-04) (hash(x)=25201599) +9 train 10.133653 (lr=1.5000e-04) (hash(x)=23094976) +10 train 10.131841 (lr=1.5000e-04) (hash(x)=23841096) +11 train 10.125864 (lr=1.5000e-04) (hash(x)=26532095) +12 train 10.086505 (lr=1.5000e-04) (hash(x)=24432298) +13 train 9.996949 (lr=1.5000e-04) (hash(x)=27151649) +14 train 9.907729 (lr=1.5000e-04) (hash(x)=24596846) +15 train 9.857966 (lr=1.5000e-04) (hash(x)=23890908) +16 train 9.745456 (lr=1.5000e-04) (hash(x)=28913955) +17 train 9.652389 (lr=1.5000e-04) (hash(x)=25588236) +18 train 9.690753 (lr=1.5000e-04) (hash(x)=23770034) +19 train 9.577331 (lr=1.5000e-04) (hash(x)=24011372) +20 train 9.432587 (lr=1.5000e-04) (hash(x)=25441898) +21 train 9.537116 (lr=1.4999e-04) (hash(x)=28375581) +22 train 9.307190 (lr=1.4999e-04) (hash(x)=24046679) +23 train 9.310228 (lr=1.4999e-04) (hash(x)=24611628) +24 train 9.302257 (lr=1.4999e-04) (hash(x)=26169030) +25 train 9.272554 (lr=1.4999e-04) (hash(x)=30298407) +26 train 9.075752 (lr=1.4999e-04) (hash(x)=23711112) +27 train 8.860987 (lr=1.4999e-04) (hash(x)=19245352) +28 train 8.856618 (lr=1.4999e-04) (hash(x)=21529136) +29 train 9.072310 (lr=1.4999e-04) (hash(x)=28936608) +30 train 8.733021 (lr=1.4999e-04) (hash(x)=24339013) +31 train 8.640947 (lr=1.4999e-04) (hash(x)=25767553) +32 train 8.748743 (lr=1.4999e-04) (hash(x)=26439905) +33 train 8.865047 (lr=1.4999e-04) (hash(x)=31093473) +34 train 8.619982 (lr=1.4999e-04) (hash(x)=25450374) +35 train 8.460970 (lr=1.4998e-04) (hash(x)=24809873) +36 train 8.556502 (lr=1.4998e-04) (hash(x)=23253252) +37 train 8.622515 (lr=1.4998e-04) (hash(x)=27852919) +38 train 8.423113 (lr=1.4998e-04) (hash(x)=23327497) +39 train 8.209340 (lr=1.4998e-04) (hash(x)=22512166) +40 train 8.368276 (lr=1.4998e-04) (hash(x)=22859419) +41 train 8.327362 (lr=1.4998e-04) (hash(x)=27620338) +42 train 8.377607 (lr=1.4998e-04) (hash(x)=26397837) +43 train 8.382814 (lr=1.4998e-04) (hash(x)=28092148) +44 train 8.267346 (lr=1.4998e-04) (hash(x)=24662703) +45 train 8.412930 (lr=1.4997e-04) (hash(x)=27938767) +46 train 8.627540 (lr=1.4997e-04) (hash(x)=26037988) +47 train 8.141090 (lr=1.4997e-04) (hash(x)=24732833) +48 train 8.259777 (lr=1.4997e-04) (hash(x)=25259526) +49 train 8.118059 (lr=1.4997e-04) (hash(x)=23200230) +50 val loss 8.1207 +50 val perplexity 3363.2488 +50 train 8.194348 (lr=1.4997e-04) (hash(x)=26721357) +51 train 7.950954 (lr=1.4997e-04) (hash(x)=22694718) +52 train 8.089219 (lr=1.4997e-04) (hash(x)=28066766) +53 train 8.039243 (lr=1.4996e-04) (hash(x)=23125151) +54 train 8.057176 (lr=1.4996e-04) (hash(x)=27193725) +55 train 7.952835 (lr=1.4996e-04) (hash(x)=25129410) +56 train 8.078397 (lr=1.4996e-04) (hash(x)=24263988) +57 train 7.890144 (lr=1.4996e-04) (hash(x)=23059154) +58 train 8.065635 (lr=1.4996e-04) (hash(x)=26063864) +59 train 8.301065 (lr=1.4996e-04) (hash(x)=27858570) +60 train 8.043921 (lr=1.4995e-04) (hash(x)=23874620) +61 train 7.888758 (lr=1.4995e-04) (hash(x)=22402617) +62 train 8.007558 (lr=1.4995e-04) (hash(x)=23600822) +63 train 7.859239 (lr=1.4995e-04) (hash(x)=26582391) +64 train 7.849569 (lr=1.4995e-04) (hash(x)=23225283) +65 train 8.159182 (lr=1.4995e-04) (hash(x)=26075451) +66 train 7.903023 (lr=1.4994e-04) (hash(x)=24723419) +67 train 8.061716 (lr=1.4994e-04) (hash(x)=27279806) +68 train 7.804330 (lr=1.4994e-04) (hash(x)=25870391) +69 train 8.044005 (lr=1.4994e-04) (hash(x)=26188136) +70 train 8.186656 (lr=1.4994e-04) (hash(x)=30373443) +71 train 8.086164 (lr=1.4993e-04) (hash(x)=26472336) +72 train 7.844152 (lr=1.4993e-04) (hash(x)=26651572) +73 train 7.990186 (lr=1.4993e-04) (hash(x)=26376212) +74 train 7.986334 (lr=1.4993e-04) (hash(x)=26733350) +75 train 8.158873 (lr=1.4993e-04) (hash(x)=28301589) +76 train 8.013915 (lr=1.4993e-04) (hash(x)=27599559) +77 train 8.091038 (lr=1.4992e-04) (hash(x)=28035221) +78 train 8.081654 (lr=1.4992e-04) (hash(x)=25016783) +79 train 8.136855 (lr=1.4992e-04) (hash(x)=27654289) +80 train 7.880769 (lr=1.4992e-04) (hash(x)=24597558) +81 train 7.650593 (lr=1.4991e-04) (hash(x)=21560904) +82 train 7.705293 (lr=1.4991e-04) (hash(x)=21983837) +83 train 7.877603 (lr=1.4991e-04) (hash(x)=24995715) +84 train 8.178294 (lr=1.4991e-04) (hash(x)=29876413) +85 train 7.833679 (lr=1.4991e-04) (hash(x)=23792508) +86 train 7.785636 (lr=1.4990e-04) (hash(x)=25509120) +87 train 7.995310 (lr=1.4990e-04) (hash(x)=26559876) +88 train 7.907106 (lr=1.4990e-04) (hash(x)=23569647) +89 train 7.932432 (lr=1.4990e-04) (hash(x)=25758852) +90 train 7.762944 (lr=1.4989e-04) (hash(x)=25706298) +91 train 7.923802 (lr=1.4989e-04) (hash(x)=28364895) +92 train 7.736430 (lr=1.4989e-04) (hash(x)=25304663) +93 train 7.846682 (lr=1.4989e-04) (hash(x)=25269299) +94 train 8.005923 (lr=1.4988e-04) (hash(x)=25870566) +95 train 7.626163 (lr=1.4988e-04) (hash(x)=21770329) +96 train 8.054964 (lr=1.4988e-04) (hash(x)=27595900) +97 train 8.012576 (lr=1.4988e-04) (hash(x)=24785397) +98 train 7.751987 (lr=1.4987e-04) (hash(x)=21521480) +99 train 7.823746 (lr=1.4987e-04) (hash(x)=24628606) +100 val loss 7.8649 +100 val perplexity 2604.1199 +100 train 7.950781 (lr=1.4987e-04) (hash(x)=24670150) +101 train 7.818568 (lr=1.4987e-04) (hash(x)=23181910) +102 train 7.774436 (lr=1.4986e-04) (hash(x)=22714991) +103 train 7.755230 (lr=1.4986e-04) (hash(x)=22723459) +104 train 7.669784 (lr=1.4986e-04) (hash(x)=21524316) +105 train 7.852880 (lr=1.4986e-04) (hash(x)=25506632) +106 train 7.563298 (lr=1.4985e-04) (hash(x)=21675672) +107 train 7.676385 (lr=1.4985e-04) (hash(x)=22897919) +108 train 7.730563 (lr=1.4985e-04) (hash(x)=23321631) +109 train 7.895413 (lr=1.4984e-04) (hash(x)=26546719) +110 train 8.947970 (lr=1.4984e-04) (hash(x)=31962348) +111 train 8.225661 (lr=1.4984e-04) (hash(x)=30338342) +112 train 7.764711 (lr=1.4984e-04) (hash(x)=23724471) +113 train 7.964827 (lr=1.4983e-04) (hash(x)=29175888) +114 train 7.948242 (lr=1.4983e-04) (hash(x)=23256716) +115 train 8.047610 (lr=1.4983e-04) (hash(x)=27063280) +116 train 8.068652 (lr=1.4982e-04) (hash(x)=31057659) +117 train 8.182228 (lr=1.4982e-04) (hash(x)=32915097) +118 train 8.108629 (lr=1.4982e-04) (hash(x)=28842717) +119 train 7.772812 (lr=1.4981e-04) (hash(x)=25678059) +120 train 7.672110 (lr=1.4981e-04) (hash(x)=21593510) +121 train 7.594989 (lr=1.4981e-04) (hash(x)=20083773) +122 train 7.756026 (lr=1.4980e-04) (hash(x)=23002820) +123 train 7.556547 (lr=1.4980e-04) (hash(x)=21853028) +124 train 7.828617 (lr=1.4980e-04) (hash(x)=26985625) +125 train 7.567029 (lr=1.4980e-04) (hash(x)=21808483) +126 train 7.982755 (lr=1.4979e-04) (hash(x)=28873251) +127 train 7.830045 (lr=1.4979e-04) (hash(x)=26109335) +128 train 8.012469 (lr=1.4979e-04) (hash(x)=26334674) +129 train 7.869732 (lr=1.4978e-04) (hash(x)=24916754) +130 train 7.840656 (lr=1.4978e-04) (hash(x)=25449624) +131 train 7.898620 (lr=1.4977e-04) (hash(x)=25334848) +132 train 8.186091 (lr=1.4977e-04) (hash(x)=27484863) +133 train 7.728710 (lr=1.4977e-04) (hash(x)=24917705) +134 train 7.728064 (lr=1.4976e-04) (hash(x)=25143449) +135 train 7.754248 (lr=1.4976e-04) (hash(x)=25044885) +136 train 7.986412 (lr=1.4976e-04) (hash(x)=27821028) +137 train 7.933585 (lr=1.4975e-04) (hash(x)=28747022) +138 train 7.885177 (lr=1.4975e-04) (hash(x)=27182888) +139 train 7.685065 (lr=1.4975e-04) (hash(x)=23678349) +140 train 7.818594 (lr=1.4974e-04) (hash(x)=23593235) +141 train 8.117517 (lr=1.4974e-04) (hash(x)=28529813) +142 train 8.421246 (lr=1.4974e-04) (hash(x)=32074661) +143 train 8.008388 (lr=1.4973e-04) (hash(x)=28870690) +144 train 7.960413 (lr=1.4973e-04) (hash(x)=27307705) +145 train 7.818922 (lr=1.4972e-04) (hash(x)=25044834) +146 train 7.850137 (lr=1.4972e-04) (hash(x)=23712023) +147 train 8.378838 (lr=1.4972e-04) (hash(x)=32982615) +148 train 8.123743 (lr=1.4971e-04) (hash(x)=30113660) +149 train 7.597496 (lr=1.4971e-04) (hash(x)=20970960) +150 val loss 7.8048 +150 val perplexity 2452.2749 +150 train 7.769884 (lr=1.4970e-04) (hash(x)=23132684) +151 train 9.458873 (lr=1.4970e-04) (hash(x)=35279941) +152 train 8.661997 (lr=1.4970e-04) (hash(x)=31227444) +153 train 7.728529 (lr=1.4969e-04) (hash(x)=25529472) +154 train 7.821088 (lr=1.4969e-04) (hash(x)=24350409) +155 train 8.103908 (lr=1.4968e-04) (hash(x)=26400041) +156 train 7.825366 (lr=1.4968e-04) (hash(x)=25262621) +157 train 7.869161 (lr=1.4968e-04) (hash(x)=24656138) +158 train 8.050176 (lr=1.4967e-04) (hash(x)=26803414) +159 train 7.925382 (lr=1.4967e-04) (hash(x)=25015923) +160 train 7.661005 (lr=1.4966e-04) (hash(x)=23581172) +161 train 7.774169 (lr=1.4966e-04) (hash(x)=22924885) +162 train 7.700211 (lr=1.4965e-04) (hash(x)=23414296) +163 train 7.899374 (lr=1.4965e-04) (hash(x)=24853586) +164 train 7.940408 (lr=1.4965e-04) (hash(x)=25000130) +165 train 7.867344 (lr=1.4964e-04) (hash(x)=27004780) +166 train 7.896037 (lr=1.4964e-04) (hash(x)=26148573) +167 train 7.791429 (lr=1.4963e-04) (hash(x)=26740855) +168 train 7.444880 (lr=1.4963e-04) (hash(x)=20965419) +169 train 7.694580 (lr=1.4962e-04) (hash(x)=23950114) +170 train 7.628789 (lr=1.4962e-04) (hash(x)=24951982) +171 train 7.755184 (lr=1.4962e-04) (hash(x)=24584116) +172 train 7.756471 (lr=1.4961e-04) (hash(x)=24378759) +173 train 7.770818 (lr=1.4961e-04) (hash(x)=25718516) +174 train 7.893043 (lr=1.4960e-04) (hash(x)=28424396) +175 train 7.677720 (lr=1.4960e-04) (hash(x)=22262151) +176 train 7.944101 (lr=1.4959e-04) (hash(x)=26438412) +177 train 7.706961 (lr=1.4959e-04) (hash(x)=23025303) +178 train 7.743351 (lr=1.4958e-04) (hash(x)=24190770) +179 train 7.914459 (lr=1.4958e-04) (hash(x)=26627860) +180 train 7.697755 (lr=1.4957e-04) (hash(x)=23663439) +181 train 7.564656 (lr=1.4957e-04) (hash(x)=23700532) +182 train 7.602947 (lr=1.4956e-04) (hash(x)=23075676) +183 train 7.847310 (lr=1.4956e-04) (hash(x)=26621834) +184 train 7.897359 (lr=1.4955e-04) (hash(x)=29426269) +185 train 7.531845 (lr=1.4955e-04) (hash(x)=21821465) +186 train 7.810959 (lr=1.4954e-04) (hash(x)=26506130) +187 train 8.050649 (lr=1.4954e-04) (hash(x)=26930630) +188 train 7.562398 (lr=1.4953e-04) (hash(x)=22993793) +189 train 7.427866 (lr=1.4953e-04) (hash(x)=19557946) +190 train 7.781157 (lr=1.4952e-04) (hash(x)=23572891) +191 train 7.596422 (lr=1.4952e-04) (hash(x)=23234741) +192 train 7.692013 (lr=1.4951e-04) (hash(x)=25547951) +193 train 7.805183 (lr=1.4951e-04) (hash(x)=26713563) +194 train 7.824105 (lr=1.4950e-04) (hash(x)=25913622) +195 train 8.012078 (lr=1.4950e-04) (hash(x)=28102443) +196 train 7.715631 (lr=1.4949e-04) (hash(x)=23093351) +197 train 8.477735 (lr=1.4949e-04) (hash(x)=31689122) +198 train 8.330497 (lr=1.4948e-04) (hash(x)=32252517) +199 train 7.849759 (lr=1.4948e-04) (hash(x)=25470563) +200 val loss 7.7789 +200 val perplexity 2389.6326 +200 train 7.875510 (lr=1.4947e-04) (hash(x)=25597614) +201 train 7.927465 (lr=1.4947e-04) (hash(x)=23757479) +202 train 7.750752 (lr=1.4946e-04) (hash(x)=25140048) +203 train 7.936891 (lr=1.4946e-04) (hash(x)=28282861) +204 train 7.743253 (lr=1.4945e-04) (hash(x)=24754885) +205 train 7.938084 (lr=1.4945e-04) (hash(x)=26731964) +206 train 8.044270 (lr=1.4944e-04) (hash(x)=26660561) +207 train 7.628529 (lr=1.4944e-04) (hash(x)=21799102) +208 train 7.819742 (lr=1.4943e-04) (hash(x)=27025986) +209 train 7.663166 (lr=1.4942e-04) (hash(x)=24672077) +210 train 7.734651 (lr=1.4942e-04) (hash(x)=25322984) +211 train 7.593422 (lr=1.4941e-04) (hash(x)=23471769) +212 train 7.407043 (lr=1.4941e-04) (hash(x)=20766491) +213 train 7.934471 (lr=1.4940e-04) (hash(x)=24058931) +214 train 7.626890 (lr=1.4940e-04) (hash(x)=23872843) +215 train 7.673436 (lr=1.4939e-04) (hash(x)=23275479) +216 train 7.800083 (lr=1.4938e-04) (hash(x)=24914695) +217 train 7.672620 (lr=1.4938e-04) (hash(x)=24364396) +218 train 7.929593 (lr=1.4937e-04) (hash(x)=27986474) +219 train 7.840177 (lr=1.4937e-04) (hash(x)=24473581) +220 train 7.750533 (lr=1.4936e-04) (hash(x)=22974689) +221 train 7.822598 (lr=1.4936e-04) (hash(x)=23774644) +222 train 7.764998 (lr=1.4935e-04) (hash(x)=23245327) +223 train 7.565843 (lr=1.4934e-04) (hash(x)=22091862) +224 train 7.635672 (lr=1.4934e-04) (hash(x)=24362839) +225 train 7.792778 (lr=1.4933e-04) (hash(x)=25482303) +226 train 7.866559 (lr=1.4933e-04) (hash(x)=24911853) +227 train 7.859332 (lr=1.4932e-04) (hash(x)=26018202) +228 train 7.696514 (lr=1.4931e-04) (hash(x)=26124495) +229 train 7.794731 (lr=1.4931e-04) (hash(x)=24560096) +230 train 7.753813 (lr=1.4930e-04) (hash(x)=24695331) +231 train 7.527973 (lr=1.4930e-04) (hash(x)=17430373) +232 train 7.532865 (lr=1.4929e-04) (hash(x)=21813345) +233 train 7.180052 (lr=1.4928e-04) (hash(x)=20098681) +234 train 7.519736 (lr=1.4928e-04) (hash(x)=25095928) +235 train 7.668890 (lr=1.4927e-04) (hash(x)=24078083) +236 train 7.659992 (lr=1.4927e-04) (hash(x)=22901505) +237 train 7.835056 (lr=1.4926e-04) (hash(x)=26595592) +238 train 7.715095 (lr=1.4925e-04) (hash(x)=27663196) +239 train 7.527754 (lr=1.4925e-04) (hash(x)=22954861) +240 train 8.016423 (lr=1.4924e-04) (hash(x)=30159234) +241 train 7.877300 (lr=1.4923e-04) (hash(x)=29294271) +242 train 7.814717 (lr=1.4923e-04) (hash(x)=23728322) +243 train 7.852026 (lr=1.4922e-04) (hash(x)=28695016) +244 train 8.003356 (lr=1.4921e-04) (hash(x)=26702728) +245 train 7.821697 (lr=1.4921e-04) (hash(x)=27100115) +246 train 7.732025 (lr=1.4920e-04) (hash(x)=25082752) +247 train 8.067335 (lr=1.4919e-04) (hash(x)=26671799) +248 train 7.771851 (lr=1.4919e-04) (hash(x)=23718946) +249 train 7.985445 (lr=1.4918e-04) (hash(x)=28137394) +250 val loss 7.7415 +250 val perplexity 2301.9421 +250 train 8.007240 (lr=1.4918e-04) (hash(x)=23893495) +251 train 7.791451 (lr=1.4917e-04) (hash(x)=23166092) +252 train 7.757320 (lr=1.4916e-04) (hash(x)=25907665) +253 train 7.711971 (lr=1.4916e-04) (hash(x)=25885986) +254 train 7.748691 (lr=1.4915e-04) (hash(x)=25262712) +255 train 7.734017 (lr=1.4914e-04) (hash(x)=26924723) +256 train 7.924997 (lr=1.4914e-04) (hash(x)=28744736) +257 train 7.664627 (lr=1.4913e-04) (hash(x)=26140590) +258 train 7.910863 (lr=1.4912e-04) (hash(x)=25780449) +259 train 7.732630 (lr=1.4911e-04) (hash(x)=25138659) +260 train 8.013224 (lr=1.4911e-04) (hash(x)=27244046) +261 train 7.878150 (lr=1.4910e-04) (hash(x)=27224685) +262 train 8.135266 (lr=1.4909e-04) (hash(x)=28274477) +263 train 7.661950 (lr=1.4909e-04) (hash(x)=23557495) +264 train 7.753516 (lr=1.4908e-04) (hash(x)=24680596) +265 train 7.769690 (lr=1.4907e-04) (hash(x)=23928957) +266 train 7.727622 (lr=1.4907e-04) (hash(x)=23761390) +267 train 7.655271 (lr=1.4906e-04) (hash(x)=25288123) +268 train 7.936949 (lr=1.4905e-04) (hash(x)=28705502) +269 train 7.537912 (lr=1.4904e-04) (hash(x)=23246294) +270 train 7.658318 (lr=1.4904e-04) (hash(x)=28639079) +271 train 7.565242 (lr=1.4903e-04) (hash(x)=27804380) +272 train 7.710048 (lr=1.4902e-04) (hash(x)=24172235) +273 train 7.762514 (lr=1.4902e-04) (hash(x)=23089140) +274 train 7.959376 (lr=1.4901e-04) (hash(x)=27163701) +275 train 8.004837 (lr=1.4900e-04) (hash(x)=26993263) +276 train 7.807713 (lr=1.4899e-04) (hash(x)=28224233) +277 train 8.077944 (lr=1.4899e-04) (hash(x)=27397203) +278 train 8.016140 (lr=1.4898e-04) (hash(x)=27923882) +279 train 7.867609 (lr=1.4897e-04) (hash(x)=26654908) +280 train 7.825643 (lr=1.4897e-04) (hash(x)=24213147) +281 train 7.589232 (lr=1.4896e-04) (hash(x)=21965022) +282 train 7.717130 (lr=1.4895e-04) (hash(x)=25465685) +283 train 7.864354 (lr=1.4894e-04) (hash(x)=27347722) +284 train 7.893753 (lr=1.4894e-04) (hash(x)=26732050) +285 train 8.036913 (lr=1.4893e-04) (hash(x)=28314127) +286 train 7.579836 (lr=1.4892e-04) (hash(x)=21471186) +287 train 7.559683 (lr=1.4891e-04) (hash(x)=23627518) +288 train 7.547288 (lr=1.4891e-04) (hash(x)=20870353) +289 train 7.643585 (lr=1.4890e-04) (hash(x)=25024764) +290 train 7.450634 (lr=1.4889e-04) (hash(x)=20683822) +291 train 7.752773 (lr=1.4888e-04) (hash(x)=21768671) +292 train 7.789880 (lr=1.4887e-04) (hash(x)=25557309) +293 train 7.930876 (lr=1.4887e-04) (hash(x)=25076667) +294 train 7.591608 (lr=1.4886e-04) (hash(x)=23765822) +295 train 7.568439 (lr=1.4885e-04) (hash(x)=21889990) +296 train 7.764296 (lr=1.4884e-04) (hash(x)=26339893) +297 train 7.452592 (lr=1.4884e-04) (hash(x)=20932794) +298 train 7.594254 (lr=1.4883e-04) (hash(x)=21750070) +299 train 7.728221 (lr=1.4882e-04) (hash(x)=23665838) +300 val loss 7.7057 +300 val perplexity 2220.9363 +300 train 8.513722 (lr=1.4881e-04) (hash(x)=32888061) +301 train 8.308314 (lr=1.4880e-04) (hash(x)=30223582) +302 train 8.035825 (lr=1.4880e-04) (hash(x)=26908418) +303 train 7.350452 (lr=1.4879e-04) (hash(x)=22528001) +304 train 7.920204 (lr=1.4878e-04) (hash(x)=27452187) +305 train 7.746215 (lr=1.4877e-04) (hash(x)=25181641) +306 train 7.814965 (lr=1.4876e-04) (hash(x)=25546593) +307 train 7.824028 (lr=1.4876e-04) (hash(x)=22487328) +308 train 7.930591 (lr=1.4875e-04) (hash(x)=27804274) +309 train 8.000463 (lr=1.4874e-04) (hash(x)=26544630) +310 train 8.089847 (lr=1.4873e-04) (hash(x)=27738934) +311 train 7.939228 (lr=1.4872e-04) (hash(x)=29248942) +312 train 7.676836 (lr=1.4871e-04) (hash(x)=25103452) +313 train 7.897283 (lr=1.4871e-04) (hash(x)=25052066) +314 train 7.715486 (lr=1.4870e-04) (hash(x)=24481302) +315 train 7.659557 (lr=1.4869e-04) (hash(x)=23543273) +316 train 7.664093 (lr=1.4868e-04) (hash(x)=25608244) +317 train 7.844120 (lr=1.4867e-04) (hash(x)=27451288) +318 train 7.511899 (lr=1.4866e-04) (hash(x)=22806491) +319 train 7.675893 (lr=1.4866e-04) (hash(x)=25533417) +320 train 7.708164 (lr=1.4865e-04) (hash(x)=24557997) +321 train 7.760266 (lr=1.4864e-04) (hash(x)=24432899) +322 train 8.005823 (lr=1.4863e-04) (hash(x)=27583287) +323 train 7.942682 (lr=1.4862e-04) (hash(x)=25552036) +324 train 7.672922 (lr=1.4861e-04) (hash(x)=24201868) +325 train 7.948427 (lr=1.4861e-04) (hash(x)=28149782) +326 train 7.747396 (lr=1.4860e-04) (hash(x)=25529698) +327 train 7.433190 (lr=1.4859e-04) (hash(x)=20612533) +328 train 7.533573 (lr=1.4858e-04) (hash(x)=20699000) +329 train 7.451627 (lr=1.4857e-04) (hash(x)=19774173) +330 train 7.496673 (lr=1.4856e-04) (hash(x)=21681646) +331 train 7.334692 (lr=1.4855e-04) (hash(x)=20216795) +332 train 7.981381 (lr=1.4854e-04) (hash(x)=27697998) +333 train 7.768819 (lr=1.4854e-04) (hash(x)=25896435) +334 train 7.608739 (lr=1.4853e-04) (hash(x)=21585310) +335 train 7.684246 (lr=1.4852e-04) (hash(x)=24677740) +336 train 7.499364 (lr=1.4851e-04) (hash(x)=22027900) +337 train 7.516608 (lr=1.4850e-04) (hash(x)=21835643) +338 train 7.403911 (lr=1.4849e-04) (hash(x)=20558462) +339 train 7.268262 (lr=1.4848e-04) (hash(x)=16722715) +340 train 7.461830 (lr=1.4847e-04) (hash(x)=20972655) +341 train 7.955135 (lr=1.4846e-04) (hash(x)=26303975) +342 train 7.693222 (lr=1.4846e-04) (hash(x)=22938170) +343 train 7.762953 (lr=1.4845e-04) (hash(x)=25347203) +344 train 7.728309 (lr=1.4844e-04) (hash(x)=27398686) +345 train 7.711396 (lr=1.4843e-04) (hash(x)=25973417) +346 train 7.733438 (lr=1.4842e-04) (hash(x)=26918389) +347 train 7.678778 (lr=1.4841e-04) (hash(x)=24272489) +348 train 7.748832 (lr=1.4840e-04) (hash(x)=25593714) +349 train 7.792583 (lr=1.4839e-04) (hash(x)=29260846) +350 val loss 7.7078 +350 val perplexity 2225.6338 +350 train 7.877184 (lr=1.4838e-04) (hash(x)=27951602) +351 train 8.007668 (lr=1.4837e-04) (hash(x)=28922363) +352 train 7.849016 (lr=1.4836e-04) (hash(x)=27210734) +353 train 7.828178 (lr=1.4836e-04) (hash(x)=26322572) +354 train 7.779027 (lr=1.4835e-04) (hash(x)=27084665) +355 train 7.661740 (lr=1.4834e-04) (hash(x)=25510798) +356 train 7.771037 (lr=1.4833e-04) (hash(x)=24970921) +357 train 7.803056 (lr=1.4832e-04) (hash(x)=24138948) +358 train 7.725297 (lr=1.4831e-04) (hash(x)=24790211) +359 train 7.760247 (lr=1.4830e-04) (hash(x)=25631397) +360 train 7.644540 (lr=1.4829e-04) (hash(x)=23226625) +361 train 7.693800 (lr=1.4828e-04) (hash(x)=24001903) +362 train 7.679296 (lr=1.4827e-04) (hash(x)=24587948) +363 train 7.343377 (lr=1.4826e-04) (hash(x)=21333676) +364 train 7.240807 (lr=1.4825e-04) (hash(x)=23673779) +365 train 8.619347 (lr=1.4824e-04) (hash(x)=30770484) +366 train 7.829124 (lr=1.4823e-04) (hash(x)=26564899) +367 train 7.806951 (lr=1.4822e-04) (hash(x)=26237983) +368 train 7.502786 (lr=1.4821e-04) (hash(x)=23764356) +369 train 7.883371 (lr=1.4820e-04) (hash(x)=26205744) +370 train 7.539861 (lr=1.4819e-04) (hash(x)=19208770) +371 train 7.792879 (lr=1.4818e-04) (hash(x)=25976502) +372 train 7.662261 (lr=1.4817e-04) (hash(x)=23983933) +373 train 7.642102 (lr=1.4816e-04) (hash(x)=24080636) +374 train 7.766391 (lr=1.4815e-04) (hash(x)=24404047) +375 train 7.725557 (lr=1.4814e-04) (hash(x)=24742645) +376 train 7.743272 (lr=1.4813e-04) (hash(x)=24159600) +377 train 7.985721 (lr=1.4812e-04) (hash(x)=28677257) +378 train 7.731008 (lr=1.4811e-04) (hash(x)=25604111) +379 train 7.669014 (lr=1.4810e-04) (hash(x)=27086333) +380 train 7.641449 (lr=1.4809e-04) (hash(x)=25188207) +381 train 7.861434 (lr=1.4808e-04) (hash(x)=27855233) +382 train 7.433304 (lr=1.4807e-04) (hash(x)=19470039) +383 train 7.754332 (lr=1.4806e-04) (hash(x)=26157660) +384 train 7.684457 (lr=1.4805e-04) (hash(x)=25291570) +385 train 7.656105 (lr=1.4804e-04) (hash(x)=25046062) +386 train 7.964204 (lr=1.4803e-04) (hash(x)=27020337) +387 train 7.590582 (lr=1.4802e-04) (hash(x)=23616370) +388 train 7.279488 (lr=1.4801e-04) (hash(x)=19113218) +389 train 7.655087 (lr=1.4800e-04) (hash(x)=24302232) +390 train 7.656223 (lr=1.4799e-04) (hash(x)=22188949) +391 train 7.475032 (lr=1.4798e-04) (hash(x)=22582169) +392 train 7.694927 (lr=1.4797e-04) (hash(x)=24700570) +393 train 7.564618 (lr=1.4796e-04) (hash(x)=22773833) +394 train 7.411373 (lr=1.4795e-04) (hash(x)=21875928) +395 train 7.682716 (lr=1.4794e-04) (hash(x)=26233189) +396 train 7.535445 (lr=1.4793e-04) (hash(x)=24321467) +397 train 7.817251 (lr=1.4792e-04) (hash(x)=26431507) +398 train 7.882171 (lr=1.4791e-04) (hash(x)=28690877) +399 train 7.839720 (lr=1.4790e-04) (hash(x)=26431960) +400 val loss 7.7047 +400 val perplexity 2218.6543 +400 train 7.645214 (lr=1.4789e-04) (hash(x)=24580300) +401 train 7.680650 (lr=1.4788e-04) (hash(x)=25112360) +402 train 7.777102 (lr=1.4787e-04) (hash(x)=27597243) +403 train 8.231940 (lr=1.4786e-04) (hash(x)=30707498) +404 train 7.898536 (lr=1.4785e-04) (hash(x)=28485465) +405 train 7.573686 (lr=1.4784e-04) (hash(x)=22586447) +406 train 7.710407 (lr=1.4783e-04) (hash(x)=23175270) +407 train 7.795531 (lr=1.4781e-04) (hash(x)=25716176) +408 train 7.892705 (lr=1.4780e-04) (hash(x)=26861373) +409 train 7.970829 (lr=1.4779e-04) (hash(x)=25118971) +410 train 7.480538 (lr=1.4778e-04) (hash(x)=19829066) +411 train 7.610892 (lr=1.4777e-04) (hash(x)=26256420) +412 train 7.878195 (lr=1.4776e-04) (hash(x)=27796153) +413 train 7.606740 (lr=1.4775e-04) (hash(x)=22633318) +414 train 7.625586 (lr=1.4774e-04) (hash(x)=22589383) +415 train 8.056075 (lr=1.4773e-04) (hash(x)=28019788) +416 train 7.973621 (lr=1.4772e-04) (hash(x)=28970440) +417 train 7.634521 (lr=1.4771e-04) (hash(x)=27396089) +418 train 7.641159 (lr=1.4770e-04) (hash(x)=21183513) +419 train 7.676067 (lr=1.4768e-04) (hash(x)=23510110) +420 train 7.866998 (lr=1.4767e-04) (hash(x)=28833467) +421 train 7.727502 (lr=1.4766e-04) (hash(x)=23646926) +422 train 7.686347 (lr=1.4765e-04) (hash(x)=24697272) +423 train 7.486105 (lr=1.4764e-04) (hash(x)=20382963) +424 train 7.511536 (lr=1.4763e-04) (hash(x)=23467595) +425 train 7.667883 (lr=1.4762e-04) (hash(x)=24304768) +426 train 7.601967 (lr=1.4761e-04) (hash(x)=21392328) +427 train 7.655090 (lr=1.4760e-04) (hash(x)=25339466) +428 train 7.563606 (lr=1.4758e-04) (hash(x)=22092542) +429 train 7.691397 (lr=1.4757e-04) (hash(x)=22088696) +430 train 7.572116 (lr=1.4756e-04) (hash(x)=22184471) +431 train 7.700461 (lr=1.4755e-04) (hash(x)=24489647) +432 train 7.724527 (lr=1.4754e-04) (hash(x)=26794132) +433 train 7.471294 (lr=1.4753e-04) (hash(x)=22940357) +434 train 7.669872 (lr=1.4752e-04) (hash(x)=23719522) +435 train 7.560545 (lr=1.4750e-04) (hash(x)=22927699) +436 train 7.728710 (lr=1.4749e-04) (hash(x)=26068576) +437 train 7.840143 (lr=1.4748e-04) (hash(x)=27631132) +438 train 7.712683 (lr=1.4747e-04) (hash(x)=26739991) +439 train 7.784821 (lr=1.4746e-04) (hash(x)=25128502) +440 train 7.858197 (lr=1.4745e-04) (hash(x)=25657260) +441 train 7.585297 (lr=1.4744e-04) (hash(x)=23576982) +442 train 7.841949 (lr=1.4742e-04) (hash(x)=27117886) +443 train 7.791556 (lr=1.4741e-04) (hash(x)=25808969) +444 train 7.739902 (lr=1.4740e-04) (hash(x)=24738238) +445 train 7.708515 (lr=1.4739e-04) (hash(x)=23429962) +446 train 7.844491 (lr=1.4738e-04) (hash(x)=25075165) +447 train 7.728916 (lr=1.4737e-04) (hash(x)=25231390) +448 train 7.516403 (lr=1.4735e-04) (hash(x)=22055054) +449 train 7.753242 (lr=1.4734e-04) (hash(x)=25395441) +450 val loss 7.7476 +450 val perplexity 2316.0627 +450 train 7.809142 (lr=1.4733e-04) (hash(x)=25863209) +451 train 7.477870 (lr=1.4732e-04) (hash(x)=21154388) +452 train 7.509123 (lr=1.4731e-04) (hash(x)=21600876) +453 train 7.619253 (lr=1.4730e-04) (hash(x)=24278611) +454 train 7.455945 (lr=1.4728e-04) (hash(x)=23221720) +455 train 7.620503 (lr=1.4727e-04) (hash(x)=22708977) +456 train 8.231061 (lr=1.4726e-04) (hash(x)=23637758) +457 train 7.979585 (lr=1.4725e-04) (hash(x)=28228490) +458 train 7.997533 (lr=1.4724e-04) (hash(x)=28638071) +459 train 7.805446 (lr=1.4722e-04) (hash(x)=27258353) +460 train 7.833398 (lr=1.4721e-04) (hash(x)=26604728) +461 train 7.723561 (lr=1.4720e-04) (hash(x)=23252199) +462 train 7.822732 (lr=1.4719e-04) (hash(x)=26441427) +463 train 7.581055 (lr=1.4717e-04) (hash(x)=24364920) +464 train 7.745107 (lr=1.4716e-04) (hash(x)=25623792) +465 train 7.640326 (lr=1.4715e-04) (hash(x)=23283905) +466 train 8.017758 (lr=1.4714e-04) (hash(x)=26025267) +467 train 7.824347 (lr=1.4713e-04) (hash(x)=27243972) +468 train 8.144702 (lr=1.4711e-04) (hash(x)=30449945) +469 train 7.861143 (lr=1.4710e-04) (hash(x)=28113043) +470 train 7.655298 (lr=1.4709e-04) (hash(x)=25182521) +471 train 7.693610 (lr=1.4708e-04) (hash(x)=24932925) +472 train 7.526479 (lr=1.4706e-04) (hash(x)=20353098) +473 train 7.444595 (lr=1.4705e-04) (hash(x)=19001259) +474 train 8.007924 (lr=1.4704e-04) (hash(x)=27585685) +475 train 7.713174 (lr=1.4703e-04) (hash(x)=26371091) +476 train 7.548456 (lr=1.4701e-04) (hash(x)=24891798) +477 train 7.609823 (lr=1.4700e-04) (hash(x)=24258817) +478 train 7.687566 (lr=1.4699e-04) (hash(x)=24330263) +479 train 7.768383 (lr=1.4698e-04) (hash(x)=26913684) +480 train 7.756372 (lr=1.4696e-04) (hash(x)=26338455) +481 train 8.028411 (lr=1.4695e-04) (hash(x)=27753043) +482 train 7.736370 (lr=1.4694e-04) (hash(x)=26123289) +483 train 7.821954 (lr=1.4693e-04) (hash(x)=29239611) +484 train 7.735396 (lr=1.4691e-04) (hash(x)=26553003) +485 train 7.693170 (lr=1.4690e-04) (hash(x)=22984557) +486 train 7.234809 (lr=1.4689e-04) (hash(x)=16947491) +487 train 7.232943 (lr=1.4688e-04) (hash(x)=18017792) +488 train 7.404491 (lr=1.4686e-04) (hash(x)=19918608) +489 train 7.880988 (lr=1.4685e-04) (hash(x)=23374526) +490 train 7.759851 (lr=1.4684e-04) (hash(x)=25009505) +491 train 7.736375 (lr=1.4682e-04) (hash(x)=27574089) +492 train 7.915822 (lr=1.4681e-04) (hash(x)=24122664) +493 train 7.750761 (lr=1.4680e-04) (hash(x)=26154906) +494 train 7.742531 (lr=1.4679e-04) (hash(x)=25192767) +495 train 7.929889 (lr=1.4677e-04) (hash(x)=28613882) +496 train 7.760162 (lr=1.4676e-04) (hash(x)=23547219) +497 train 7.788445 (lr=1.4675e-04) (hash(x)=25272182) +498 train 7.672788 (lr=1.4673e-04) (hash(x)=24992761) +499 train 7.930615 (lr=1.4672e-04) (hash(x)=26981914) +500 val loss 7.7860 +500 val perplexity 2406.6860 +500 train 7.707555 (lr=1.4671e-04) (hash(x)=22051933) +501 train 7.891806 (lr=1.4670e-04) (hash(x)=24232348) +502 train 7.881341 (lr=1.4668e-04) (hash(x)=23158331) +503 train 7.704439 (lr=1.4667e-04) (hash(x)=22652243) +504 train 7.764348 (lr=1.4666e-04) (hash(x)=23805602) +505 train 8.049147 (lr=1.4664e-04) (hash(x)=25411991) +506 train 7.357214 (lr=1.4663e-04) (hash(x)=18827215) +507 train 7.071234 (lr=1.4662e-04) (hash(x)=15446025) +508 train 7.377969 (lr=1.4660e-04) (hash(x)=20516263) +509 train 7.844813 (lr=1.4659e-04) (hash(x)=27846176) +510 train 7.599332 (lr=1.4658e-04) (hash(x)=23342449) +511 train 7.832024 (lr=1.4656e-04) (hash(x)=27194521) +512 train 7.628772 (lr=1.4655e-04) (hash(x)=23008284) +513 train 8.129699 (lr=1.4654e-04) (hash(x)=29430001) +514 train 7.404077 (lr=1.4652e-04) (hash(x)=22579319) +515 train 7.461443 (lr=1.4651e-04) (hash(x)=25264518) +516 train 7.803221 (lr=1.4650e-04) (hash(x)=25359075) +517 train 7.785425 (lr=1.4648e-04) (hash(x)=25568956) +518 train 8.101542 (lr=1.4647e-04) (hash(x)=32004108) +519 train 7.715839 (lr=1.4645e-04) (hash(x)=24936836) +520 train 7.875461 (lr=1.4644e-04) (hash(x)=27263338) +521 train 7.925940 (lr=1.4643e-04) (hash(x)=27452099) +522 train 7.790104 (lr=1.4641e-04) (hash(x)=25965406) +523 train 7.968022 (lr=1.4640e-04) (hash(x)=28197282) +524 train 7.698882 (lr=1.4639e-04) (hash(x)=22466209) +525 train 7.725531 (lr=1.4637e-04) (hash(x)=22931889) +526 train 7.854450 (lr=1.4636e-04) (hash(x)=26903920) +527 train 7.717886 (lr=1.4635e-04) (hash(x)=24765578) +528 train 7.851387 (lr=1.4633e-04) (hash(x)=27811359) +529 train 7.642228 (lr=1.4632e-04) (hash(x)=25078649) +530 train 7.804775 (lr=1.4630e-04) (hash(x)=25572416) +531 train 7.928859 (lr=1.4629e-04) (hash(x)=27448185) +532 train 7.975317 (lr=1.4628e-04) (hash(x)=25923719) +533 train 7.772896 (lr=1.4626e-04) (hash(x)=24804856) +534 train 7.876968 (lr=1.4625e-04) (hash(x)=23207829) +535 train 7.760067 (lr=1.4623e-04) (hash(x)=23107416) +536 train 7.647531 (lr=1.4622e-04) (hash(x)=26739531) +537 train 7.643085 (lr=1.4621e-04) (hash(x)=24960796) +538 train 7.779240 (lr=1.4619e-04) (hash(x)=24667802) +539 train 7.863643 (lr=1.4618e-04) (hash(x)=26755138) +540 train 7.749553 (lr=1.4616e-04) (hash(x)=25537132) +541 train 7.649120 (lr=1.4615e-04) (hash(x)=24542526) +542 train 7.449980 (lr=1.4614e-04) (hash(x)=21296355) +543 train 8.012706 (lr=1.4612e-04) (hash(x)=29314255) +544 train 7.736169 (lr=1.4611e-04) (hash(x)=26001799) +545 train 7.765523 (lr=1.4609e-04) (hash(x)=27347755) +546 train 7.749732 (lr=1.4608e-04) (hash(x)=25107798) +547 train 7.538445 (lr=1.4607e-04) (hash(x)=22112669) +548 train 7.555351 (lr=1.4605e-04) (hash(x)=21897967) +549 train 7.673372 (lr=1.4604e-04) (hash(x)=25161929) +550 val loss 7.7060 +550 val perplexity 2221.6587 +550 train 7.613876 (lr=1.4602e-04) (hash(x)=27465106) +551 train 7.701908 (lr=1.4601e-04) (hash(x)=24013079) +552 train 7.637723 (lr=1.4599e-04) (hash(x)=23142015) +553 train 7.717027 (lr=1.4598e-04) (hash(x)=26768629) +554 train 7.724785 (lr=1.4596e-04) (hash(x)=26393383) +555 train 7.554108 (lr=1.4595e-04) (hash(x)=22537194) +556 train 7.807941 (lr=1.4594e-04) (hash(x)=24046036) +557 train 7.756172 (lr=1.4592e-04) (hash(x)=24974360) +558 train 8.002805 (lr=1.4591e-04) (hash(x)=28379928) +559 train 7.739588 (lr=1.4589e-04) (hash(x)=25322001) +560 train 7.844222 (lr=1.4588e-04) (hash(x)=26622031) +561 train 7.481650 (lr=1.4586e-04) (hash(x)=20562247) +562 train 7.886060 (lr=1.4585e-04) (hash(x)=27381885) +563 train 8.009897 (lr=1.4583e-04) (hash(x)=27028126) +564 train 7.836770 (lr=1.4582e-04) (hash(x)=28882928) +565 train 7.777337 (lr=1.4580e-04) (hash(x)=25666355) +566 train 7.932212 (lr=1.4579e-04) (hash(x)=24330810) +567 train 7.796767 (lr=1.4577e-04) (hash(x)=26690440) +568 train 7.675705 (lr=1.4576e-04) (hash(x)=22923592) +569 train 7.792974 (lr=1.4575e-04) (hash(x)=27348418) +570 train 7.850613 (lr=1.4573e-04) (hash(x)=28849848) +571 train 7.859719 (lr=1.4572e-04) (hash(x)=26967331) +572 train 7.630348 (lr=1.4570e-04) (hash(x)=22831467) +573 train 7.706242 (lr=1.4569e-04) (hash(x)=24765121) +574 train 7.678986 (lr=1.4567e-04) (hash(x)=24331857) +575 train 7.509037 (lr=1.4566e-04) (hash(x)=22598512) +576 train 7.704048 (lr=1.4564e-04) (hash(x)=25149353) +577 train 7.521355 (lr=1.4563e-04) (hash(x)=23725598) +578 train 7.797897 (lr=1.4561e-04) (hash(x)=26449557) +579 train 7.818717 (lr=1.4560e-04) (hash(x)=24697985) +580 train 7.866724 (lr=1.4558e-04) (hash(x)=26923059) +581 train 7.652629 (lr=1.4557e-04) (hash(x)=25201962) +582 train 7.305058 (lr=1.4555e-04) (hash(x)=20931520) +583 train 7.340206 (lr=1.4554e-04) (hash(x)=18473911) +584 train 7.486394 (lr=1.4552e-04) (hash(x)=21306267) +585 train 7.799485 (lr=1.4550e-04) (hash(x)=25982840) +586 train 7.673679 (lr=1.4549e-04) (hash(x)=25364874) +587 train 7.575531 (lr=1.4547e-04) (hash(x)=23172124) +588 train 7.882668 (lr=1.4546e-04) (hash(x)=27876897) +589 train 8.526174 (lr=1.4544e-04) (hash(x)=34646114) +590 train 8.878194 (lr=1.4543e-04) (hash(x)=35153576) +591 train 7.624401 (lr=1.4541e-04) (hash(x)=22322442) +592 train 7.905471 (lr=1.4540e-04) (hash(x)=27907331) +593 train 7.816013 (lr=1.4538e-04) (hash(x)=26211794) +594 train 8.078948 (lr=1.4537e-04) (hash(x)=29291512) +595 train 8.265976 (lr=1.4535e-04) (hash(x)=29659121) +596 train 8.101048 (lr=1.4534e-04) (hash(x)=29674399) +597 train 7.715024 (lr=1.4532e-04) (hash(x)=23538306) +598 train 7.805770 (lr=1.4530e-04) (hash(x)=21991524) +599 train 7.755527 (lr=1.4529e-04) (hash(x)=26324153) +600 val loss 7.7193 +600 val perplexity 2251.4673 +600 train 7.713402 (lr=1.4527e-04) (hash(x)=23712082) +601 train 7.722871 (lr=1.4526e-04) (hash(x)=24910403) +602 train 7.717433 (lr=1.4524e-04) (hash(x)=26737205) +603 train 7.852911 (lr=1.4523e-04) (hash(x)=26939970) +604 train 7.734730 (lr=1.4521e-04) (hash(x)=27651943) +605 train 8.042534 (lr=1.4520e-04) (hash(x)=27515446) +606 train 7.959049 (lr=1.4518e-04) (hash(x)=26753129) +607 train 7.603940 (lr=1.4516e-04) (hash(x)=23446058) +608 train 7.962791 (lr=1.4515e-04) (hash(x)=27587849) +609 train 7.788603 (lr=1.4513e-04) (hash(x)=25308253) +610 train 7.818405 (lr=1.4512e-04) (hash(x)=26615098) +611 train 7.871590 (lr=1.4510e-04) (hash(x)=29981801) +612 train 7.921756 (lr=1.4508e-04) (hash(x)=29592345) +613 train 7.932448 (lr=1.4507e-04) (hash(x)=23470413) +614 train 7.831871 (lr=1.4505e-04) (hash(x)=24742370) +615 train 7.871526 (lr=1.4504e-04) (hash(x)=24843741) +616 train 7.749996 (lr=1.4502e-04) (hash(x)=25192548) +617 train 7.845225 (lr=1.4500e-04) (hash(x)=27176996) +618 train 7.648774 (lr=1.4499e-04) (hash(x)=23964552) +619 train 7.641798 (lr=1.4497e-04) (hash(x)=22855363) +620 train 7.641428 (lr=1.4496e-04) (hash(x)=26332996) +621 train 7.459761 (lr=1.4494e-04) (hash(x)=22960957) +622 train 7.794389 (lr=1.4492e-04) (hash(x)=22752597) +623 train 7.686199 (lr=1.4491e-04) (hash(x)=23197102) +624 train 8.212353 (lr=1.4489e-04) (hash(x)=27383319) +625 train 7.718253 (lr=1.4488e-04) (hash(x)=26132276) +626 train 7.548662 (lr=1.4486e-04) (hash(x)=19810497) +627 train 7.673100 (lr=1.4484e-04) (hash(x)=25704919) +628 train 7.865495 (lr=1.4483e-04) (hash(x)=27174264) +629 train 8.048166 (lr=1.4481e-04) (hash(x)=22280814) +630 train 8.764112 (lr=1.4479e-04) (hash(x)=24279448) +631 train 8.217171 (lr=1.4478e-04) (hash(x)=23054940) +632 train 8.310630 (lr=1.4476e-04) (hash(x)=23942400) +633 train 8.579284 (lr=1.4475e-04) (hash(x)=24712416) +634 train 8.127933 (lr=1.4473e-04) (hash(x)=24564658) +635 train 7.818642 (lr=1.4471e-04) (hash(x)=24909904) +636 train 7.834619 (lr=1.4470e-04) (hash(x)=23049534) +637 train 7.892263 (lr=1.4468e-04) (hash(x)=24321591) +638 train 7.701969 (lr=1.4466e-04) (hash(x)=26153298) +639 train 7.711498 (lr=1.4465e-04) (hash(x)=27140757) +640 train 7.494254 (lr=1.4463e-04) (hash(x)=25115907) +641 train 7.532982 (lr=1.4461e-04) (hash(x)=26563770) +642 train 7.744682 (lr=1.4460e-04) (hash(x)=28089252) +643 train 7.640328 (lr=1.4458e-04) (hash(x)=25993110) +644 train 7.614560 (lr=1.4456e-04) (hash(x)=25150008) +645 train 7.876760 (lr=1.4455e-04) (hash(x)=28520222) +646 train 7.504116 (lr=1.4453e-04) (hash(x)=21349943) +647 train 7.593759 (lr=1.4451e-04) (hash(x)=25149419) +648 train 7.785549 (lr=1.4450e-04) (hash(x)=25730641) +649 train 7.955877 (lr=1.4448e-04) (hash(x)=26112813) +650 val loss 7.7080 +650 val perplexity 2226.1890 +650 train 7.775341 (lr=1.4446e-04) (hash(x)=25907805) +651 train 7.823639 (lr=1.4445e-04) (hash(x)=27623643) +652 train 7.747394 (lr=1.4443e-04) (hash(x)=26484959) +653 train 7.818579 (lr=1.4441e-04) (hash(x)=29199854) +654 train 7.814574 (lr=1.4440e-04) (hash(x)=28369628) +655 train 7.664993 (lr=1.4438e-04) (hash(x)=24727764) +656 train 7.400728 (lr=1.4436e-04) (hash(x)=22610673) +657 train 7.343473 (lr=1.4434e-04) (hash(x)=22667179) +658 train 7.141391 (lr=1.4433e-04) (hash(x)=18477300) +659 train 7.565006 (lr=1.4431e-04) (hash(x)=23155773) +660 train 7.330542 (lr=1.4429e-04) (hash(x)=19461032) +661 train 7.593301 (lr=1.4428e-04) (hash(x)=23453788) +662 train 7.738658 (lr=1.4426e-04) (hash(x)=24543466) +663 train 7.508839 (lr=1.4424e-04) (hash(x)=21935931) +664 train 7.364263 (lr=1.4423e-04) (hash(x)=19910292) +665 train 7.667639 (lr=1.4421e-04) (hash(x)=24481079) +666 train 7.308708 (lr=1.4419e-04) (hash(x)=18922411) +667 train 7.354385 (lr=1.4417e-04) (hash(x)=20054917) +668 train 7.601341 (lr=1.4416e-04) (hash(x)=24850470) +669 train 7.618703 (lr=1.4414e-04) (hash(x)=25907741) +670 train 7.788878 (lr=1.4412e-04) (hash(x)=26873522) +671 train 7.820630 (lr=1.4410e-04) (hash(x)=27606073) +672 train 7.975829 (lr=1.4409e-04) (hash(x)=26209645) +673 train 7.773911 (lr=1.4407e-04) (hash(x)=25202001) +674 train 7.904382 (lr=1.4405e-04) (hash(x)=25569462) +675 train 7.850766 (lr=1.4403e-04) (hash(x)=26534487) +676 train 7.801198 (lr=1.4402e-04) (hash(x)=26455057) +677 train 7.685829 (lr=1.4400e-04) (hash(x)=24095850) +678 train 7.911312 (lr=1.4398e-04) (hash(x)=25287752) +679 train 7.382202 (lr=1.4396e-04) (hash(x)=22450341) +680 train 8.090725 (lr=1.4395e-04) (hash(x)=29004853) +681 train 7.808594 (lr=1.4393e-04) (hash(x)=27993763) +682 train 7.652979 (lr=1.4391e-04) (hash(x)=26382658) +683 train 7.763160 (lr=1.4389e-04) (hash(x)=25013073) +684 train 7.846857 (lr=1.4388e-04) (hash(x)=30595809) +685 train 7.927670 (lr=1.4386e-04) (hash(x)=30934371) +686 train 8.471172 (lr=1.4384e-04) (hash(x)=33060834) +687 train 7.765402 (lr=1.4382e-04) (hash(x)=25945859) +688 train 7.547844 (lr=1.4381e-04) (hash(x)=23375678) +689 train 7.653690 (lr=1.4379e-04) (hash(x)=25218689) +690 train 7.758957 (lr=1.4377e-04) (hash(x)=28127397) +691 train 7.696489 (lr=1.4375e-04) (hash(x)=24418091) +692 train 7.592286 (lr=1.4373e-04) (hash(x)=22761099) +693 train 7.624845 (lr=1.4372e-04) (hash(x)=24615466) +694 train 7.740659 (lr=1.4370e-04) (hash(x)=24699240) +695 train 7.636981 (lr=1.4368e-04) (hash(x)=21613707) +696 train 7.692319 (lr=1.4366e-04) (hash(x)=24977554) +697 train 7.629449 (lr=1.4365e-04) (hash(x)=24348175) +698 train 7.838844 (lr=1.4363e-04) (hash(x)=25102767) +699 train 7.770848 (lr=1.4361e-04) (hash(x)=26386157) +700 val loss 7.6736 +700 val perplexity 2150.8591 +700 train 7.703762 (lr=1.4359e-04) (hash(x)=26423460) +701 train 7.671975 (lr=1.4357e-04) (hash(x)=25771047) +702 train 7.728197 (lr=1.4356e-04) (hash(x)=26999875) +703 train 7.623288 (lr=1.4354e-04) (hash(x)=24396519) +704 train 7.668520 (lr=1.4352e-04) (hash(x)=22588122) +705 train 7.953977 (lr=1.4350e-04) (hash(x)=25142399) +706 train 7.648675 (lr=1.4348e-04) (hash(x)=20440214) +707 train 7.538855 (lr=1.4346e-04) (hash(x)=23265507) +708 train 7.632303 (lr=1.4345e-04) (hash(x)=24563470) +709 train 7.547748 (lr=1.4343e-04) (hash(x)=22514858) +710 train 7.928351 (lr=1.4341e-04) (hash(x)=26691212) +711 train 7.975771 (lr=1.4339e-04) (hash(x)=29138828) +712 train 7.930944 (lr=1.4337e-04) (hash(x)=28028528) +713 train 7.757930 (lr=1.4335e-04) (hash(x)=20531210) +714 train 7.648873 (lr=1.4334e-04) (hash(x)=25075352) +715 train 7.712643 (lr=1.4332e-04) (hash(x)=24265353) +716 train 7.804831 (lr=1.4330e-04) (hash(x)=24635726) +717 train 7.678027 (lr=1.4328e-04) (hash(x)=24999726) +718 train 7.874841 (lr=1.4326e-04) (hash(x)=27412910) +719 train 7.620931 (lr=1.4324e-04) (hash(x)=24685515) +720 train 7.702114 (lr=1.4323e-04) (hash(x)=23780329) +721 train 7.527591 (lr=1.4321e-04) (hash(x)=25071701) +722 train 7.677078 (lr=1.4319e-04) (hash(x)=23767130) +723 train 7.640019 (lr=1.4317e-04) (hash(x)=24876269) +724 train 7.771196 (lr=1.4315e-04) (hash(x)=26405773) +725 train 8.150878 (lr=1.4313e-04) (hash(x)=31733180) +726 train 7.385278 (lr=1.4311e-04) (hash(x)=21337509) +727 train 7.537970 (lr=1.4310e-04) (hash(x)=22825749) +728 train 7.894341 (lr=1.4308e-04) (hash(x)=28638695) +729 train 7.783372 (lr=1.4306e-04) (hash(x)=26393943) +730 train 7.916861 (lr=1.4304e-04) (hash(x)=27563583) +731 train 7.455204 (lr=1.4302e-04) (hash(x)=21239652) +732 train 7.551785 (lr=1.4300e-04) (hash(x)=23986428) +733 train 7.503508 (lr=1.4298e-04) (hash(x)=24943881) +734 train 8.038424 (lr=1.4296e-04) (hash(x)=29691448) +735 train 7.968265 (lr=1.4295e-04) (hash(x)=28767869) +736 train 7.672003 (lr=1.4293e-04) (hash(x)=23628188) +737 train 7.965344 (lr=1.4291e-04) (hash(x)=29341482) +738 train 7.785732 (lr=1.4289e-04) (hash(x)=30336570) +739 train 7.751135 (lr=1.4287e-04) (hash(x)=25614301) +740 train 7.619747 (lr=1.4285e-04) (hash(x)=24160500) +741 train 7.840811 (lr=1.4283e-04) (hash(x)=26030058) +742 train 8.202105 (lr=1.4281e-04) (hash(x)=29243936) +743 train 7.458683 (lr=1.4279e-04) (hash(x)=21159060) +744 train 7.548186 (lr=1.4277e-04) (hash(x)=23701853) +745 train 7.742705 (lr=1.4276e-04) (hash(x)=24629937) +746 train 7.642414 (lr=1.4274e-04) (hash(x)=25110108) +747 train 7.706216 (lr=1.4272e-04) (hash(x)=26751788) +748 train 7.768895 (lr=1.4270e-04) (hash(x)=26430427) +749 train 7.616390 (lr=1.4268e-04) (hash(x)=26012353) +750 val loss 7.6660 +750 val perplexity 2134.5972 +750 train 7.762496 (lr=1.4266e-04) (hash(x)=22735910) +751 train 7.576378 (lr=1.4264e-04) (hash(x)=25045397) +752 train 7.344393 (lr=1.4262e-04) (hash(x)=21554427) +753 train 7.549475 (lr=1.4260e-04) (hash(x)=23751143) +754 train 8.238507 (lr=1.4258e-04) (hash(x)=28602273) +755 train 8.284055 (lr=1.4256e-04) (hash(x)=29989709) +756 train 7.716809 (lr=1.4254e-04) (hash(x)=22331648) +757 train 8.114349 (lr=1.4252e-04) (hash(x)=31017246) +758 train 8.044535 (lr=1.4250e-04) (hash(x)=29709045) +759 train 8.083686 (lr=1.4249e-04) (hash(x)=25560928) +760 train 7.756667 (lr=1.4247e-04) (hash(x)=25075464) +761 train 7.801924 (lr=1.4245e-04) (hash(x)=27352253) +762 train 8.016040 (lr=1.4243e-04) (hash(x)=28187891) +763 train 7.836861 (lr=1.4241e-04) (hash(x)=26062687) +764 train 7.838263 (lr=1.4239e-04) (hash(x)=27427811) +765 train 7.905557 (lr=1.4237e-04) (hash(x)=27614522) +766 train 7.671173 (lr=1.4235e-04) (hash(x)=26129544) +767 train 8.249498 (lr=1.4233e-04) (hash(x)=28959222) +768 train 7.805914 (lr=1.4231e-04) (hash(x)=26860067) +769 train 7.584749 (lr=1.4229e-04) (hash(x)=25122598) +770 train 7.645131 (lr=1.4227e-04) (hash(x)=25245030) +771 train 7.678217 (lr=1.4225e-04) (hash(x)=25434884) +772 train 7.762344 (lr=1.4223e-04) (hash(x)=27732790) +773 train 7.784074 (lr=1.4221e-04) (hash(x)=27824438) +774 train 7.846556 (lr=1.4219e-04) (hash(x)=27201953) +775 train 7.572565 (lr=1.4217e-04) (hash(x)=21248405) +776 train 7.406563 (lr=1.4215e-04) (hash(x)=22805934) +777 train 7.685555 (lr=1.4213e-04) (hash(x)=26482588) +778 train 7.769348 (lr=1.4211e-04) (hash(x)=24153691) +779 train 7.873095 (lr=1.4209e-04) (hash(x)=25044192) +780 train 7.797877 (lr=1.4207e-04) (hash(x)=25910078) +781 train 7.808774 (lr=1.4205e-04) (hash(x)=28645524) +782 train 7.621247 (lr=1.4203e-04) (hash(x)=24368498) +783 train 7.688313 (lr=1.4201e-04) (hash(x)=25830182) +784 train 7.804124 (lr=1.4199e-04) (hash(x)=29181807) +785 train 7.714498 (lr=1.4197e-04) (hash(x)=25585137) +786 train 7.674037 (lr=1.4195e-04) (hash(x)=24798246) +787 train 7.765409 (lr=1.4193e-04) (hash(x)=26621419) +788 train 7.300244 (lr=1.4191e-04) (hash(x)=21446891) +789 train 7.265003 (lr=1.4189e-04) (hash(x)=22165286) +790 train 7.511681 (lr=1.4187e-04) (hash(x)=23477219) +791 train 7.770008 (lr=1.4185e-04) (hash(x)=25173113) +792 train 7.633588 (lr=1.4183e-04) (hash(x)=25853788) +793 train 7.763045 (lr=1.4181e-04) (hash(x)=27267091) +794 train 7.574979 (lr=1.4179e-04) (hash(x)=23743694) +795 train 7.577387 (lr=1.4177e-04) (hash(x)=24400133) +796 train 7.656859 (lr=1.4175e-04) (hash(x)=23663639) +797 train 7.530245 (lr=1.4173e-04) (hash(x)=23103223) +798 train 8.077842 (lr=1.4171e-04) (hash(x)=28748411) +799 train 7.340757 (lr=1.4169e-04) (hash(x)=23486277) +800 val loss 7.6548 +800 val perplexity 2110.7639 +800 train 7.651160 (lr=1.4167e-04) (hash(x)=25678518) +801 train 7.570298 (lr=1.4165e-04) (hash(x)=23421286) +802 train 7.729589 (lr=1.4163e-04) (hash(x)=26054104) +803 train 7.735549 (lr=1.4161e-04) (hash(x)=25978130) +804 train 7.744800 (lr=1.4159e-04) (hash(x)=26006525) +805 train 7.703043 (lr=1.4157e-04) (hash(x)=25769432) +806 train 7.485672 (lr=1.4154e-04) (hash(x)=22430795) +807 train 7.910715 (lr=1.4152e-04) (hash(x)=28916006) +808 train 7.677457 (lr=1.4150e-04) (hash(x)=25166800) +809 train 7.811365 (lr=1.4148e-04) (hash(x)=24226056) +810 train 7.655392 (lr=1.4146e-04) (hash(x)=25057934) +811 train 8.479352 (lr=1.4144e-04) (hash(x)=33195100) +812 train 7.829038 (lr=1.4142e-04) (hash(x)=26312888) +813 train 7.999777 (lr=1.4140e-04) (hash(x)=27730410) +814 train 7.851729 (lr=1.4138e-04) (hash(x)=27372474) +815 train 7.677207 (lr=1.4136e-04) (hash(x)=25556929) +816 train 7.771154 (lr=1.4134e-04) (hash(x)=26909985) +817 train 7.596490 (lr=1.4132e-04) (hash(x)=25991247) +818 train 7.790929 (lr=1.4130e-04) (hash(x)=27438141) +819 train 7.925261 (lr=1.4128e-04) (hash(x)=29536986) +820 train 7.648610 (lr=1.4125e-04) (hash(x)=24478391) +821 train 7.634750 (lr=1.4123e-04) (hash(x)=26125216) +822 train 7.684626 (lr=1.4121e-04) (hash(x)=26422130) +823 train 7.916700 (lr=1.4119e-04) (hash(x)=29648798) +824 train 7.601608 (lr=1.4117e-04) (hash(x)=21247770) +825 train 7.693764 (lr=1.4115e-04) (hash(x)=23195388) +826 train 7.656593 (lr=1.4113e-04) (hash(x)=25796725) +827 train 7.687807 (lr=1.4111e-04) (hash(x)=23124767) +828 train 7.712522 (lr=1.4109e-04) (hash(x)=25233464) +829 train 7.714866 (lr=1.4107e-04) (hash(x)=25713275) +830 train 7.615356 (lr=1.4104e-04) (hash(x)=25550167) +831 train 7.543266 (lr=1.4102e-04) (hash(x)=24976217) +832 train 7.876051 (lr=1.4100e-04) (hash(x)=28536827) +833 train 7.759174 (lr=1.4098e-04) (hash(x)=27500801) +834 train 7.564863 (lr=1.4096e-04) (hash(x)=25545765) +835 train 7.571390 (lr=1.4094e-04) (hash(x)=23632825) +836 train 7.594762 (lr=1.4092e-04) (hash(x)=25708009) +837 train 7.648507 (lr=1.4090e-04) (hash(x)=24456276) +838 train 7.784146 (lr=1.4088e-04) (hash(x)=29189855) +839 train 8.018643 (lr=1.4085e-04) (hash(x)=31019606) +840 train 7.910203 (lr=1.4083e-04) (hash(x)=26328013) +841 train 7.827875 (lr=1.4081e-04) (hash(x)=25027904) +842 train 7.557538 (lr=1.4079e-04) (hash(x)=23734189) +843 train 7.842227 (lr=1.4077e-04) (hash(x)=28236580) +844 train 7.647516 (lr=1.4075e-04) (hash(x)=26509780) +845 train 7.717665 (lr=1.4073e-04) (hash(x)=25386473) +846 train 7.663845 (lr=1.4070e-04) (hash(x)=24052671) +847 train 7.839928 (lr=1.4068e-04) (hash(x)=28269421) +848 train 7.245613 (lr=1.4066e-04) (hash(x)=22251724) +849 train 7.528917 (lr=1.4064e-04) (hash(x)=24308447) +850 val loss 7.6351 +850 val perplexity 2069.6201 +850 train 7.487192 (lr=1.4062e-04) (hash(x)=24242830) +851 train 7.681333 (lr=1.4060e-04) (hash(x)=25563279) +852 train 7.700551 (lr=1.4057e-04) (hash(x)=26354481) +853 train 7.836998 (lr=1.4055e-04) (hash(x)=26152637) +854 train 7.871250 (lr=1.4053e-04) (hash(x)=28051025) +855 train 7.671550 (lr=1.4051e-04) (hash(x)=24865358) +856 train 7.588682 (lr=1.4049e-04) (hash(x)=24288911) +857 train 7.472717 (lr=1.4047e-04) (hash(x)=22230964) +858 train 7.359967 (lr=1.4044e-04) (hash(x)=21303832) +859 train 7.530908 (lr=1.4042e-04) (hash(x)=22155546) +860 train 7.639212 (lr=1.4040e-04) (hash(x)=25296428) +861 train 7.836887 (lr=1.4038e-04) (hash(x)=29142319) +862 train 7.617191 (lr=1.4036e-04) (hash(x)=25545430) +863 train 7.481653 (lr=1.4034e-04) (hash(x)=26984272) +864 train 7.671692 (lr=1.4031e-04) (hash(x)=25429005) +865 train 7.697468 (lr=1.4029e-04) (hash(x)=27077032) +866 train 7.705853 (lr=1.4027e-04) (hash(x)=26494424) +867 train 7.673267 (lr=1.4025e-04) (hash(x)=23193673) +868 train 7.709592 (lr=1.4023e-04) (hash(x)=25075134) +869 train 7.771623 (lr=1.4020e-04) (hash(x)=27112558) +870 train 7.904607 (lr=1.4018e-04) (hash(x)=27436608) +871 train 7.615514 (lr=1.4016e-04) (hash(x)=24544116) +872 train 7.959479 (lr=1.4014e-04) (hash(x)=31632686) +873 train 7.647528 (lr=1.4012e-04) (hash(x)=25890184) +874 train 7.702989 (lr=1.4009e-04) (hash(x)=22887555) +875 train 7.596185 (lr=1.4007e-04) (hash(x)=24547533) +876 train 7.710664 (lr=1.4005e-04) (hash(x)=26553496) +877 train 7.820693 (lr=1.4003e-04) (hash(x)=27467688) +878 train 7.584599 (lr=1.4000e-04) (hash(x)=24766934) +879 train 7.458513 (lr=1.3998e-04) (hash(x)=22059850) +880 train 7.848017 (lr=1.3996e-04) (hash(x)=22871702) +881 train 7.658584 (lr=1.3994e-04) (hash(x)=23893130) +882 train 7.736698 (lr=1.3992e-04) (hash(x)=25125691) +883 train 7.649982 (lr=1.3989e-04) (hash(x)=25994573) +884 train 7.698059 (lr=1.3987e-04) (hash(x)=26076345) +885 train 7.657745 (lr=1.3985e-04) (hash(x)=26577783) +886 train 7.769025 (lr=1.3983e-04) (hash(x)=27395225) +887 train 7.602864 (lr=1.3980e-04) (hash(x)=23926632) +888 train 7.458431 (lr=1.3978e-04) (hash(x)=21737239) +889 train 7.724512 (lr=1.3976e-04) (hash(x)=23574207) +890 train 7.367203 (lr=1.3974e-04) (hash(x)=24365231) +891 train 7.521137 (lr=1.3971e-04) (hash(x)=27111369) +892 train 7.856251 (lr=1.3969e-04) (hash(x)=27290015) +893 train 7.612775 (lr=1.3967e-04) (hash(x)=23979820) +894 train 7.716612 (lr=1.3965e-04) (hash(x)=26450121) +895 train 7.616145 (lr=1.3962e-04) (hash(x)=27025333) +896 train 7.618399 (lr=1.3960e-04) (hash(x)=23624605) +897 train 7.389144 (lr=1.3958e-04) (hash(x)=22846386) +898 train 7.510175 (lr=1.3956e-04) (hash(x)=22970561) +899 train 7.314232 (lr=1.3953e-04) (hash(x)=16908068) +900 val loss 7.6148 +900 val perplexity 2028.0597 +900 train 7.589421 (lr=1.3951e-04) (hash(x)=24661446) +901 train 7.705941 (lr=1.3949e-04) (hash(x)=25664727) +902 train 7.640824 (lr=1.3947e-04) (hash(x)=25667011) +903 train 7.706102 (lr=1.3944e-04) (hash(x)=29120407) +904 train 7.716695 (lr=1.3942e-04) (hash(x)=23385735) +905 train 7.782131 (lr=1.3940e-04) (hash(x)=25564213) +906 train 7.862382 (lr=1.3937e-04) (hash(x)=25413898) +907 train 7.787511 (lr=1.3935e-04) (hash(x)=27092710) +908 train 7.541244 (lr=1.3933e-04) (hash(x)=25789923) +909 train 7.638367 (lr=1.3931e-04) (hash(x)=28533197) +910 train 7.480510 (lr=1.3928e-04) (hash(x)=22982996) +911 train 7.584424 (lr=1.3926e-04) (hash(x)=23827393) +912 train 7.261079 (lr=1.3924e-04) (hash(x)=21242640) +913 train 7.666373 (lr=1.3921e-04) (hash(x)=24154233) +914 train 7.666690 (lr=1.3919e-04) (hash(x)=24331967) +915 train 7.950882 (lr=1.3917e-04) (hash(x)=32812727) +916 train 7.559229 (lr=1.3914e-04) (hash(x)=23572994) +917 train 7.574124 (lr=1.3912e-04) (hash(x)=26305435) +918 train 7.630431 (lr=1.3910e-04) (hash(x)=26268355) +919 train 7.796937 (lr=1.3908e-04) (hash(x)=27230027) +920 train 7.608138 (lr=1.3905e-04) (hash(x)=23885377) +921 train 7.501895 (lr=1.3903e-04) (hash(x)=23532437) +922 train 7.597859 (lr=1.3901e-04) (hash(x)=25577034) +923 train 7.729820 (lr=1.3898e-04) (hash(x)=25703381) +924 train 7.757100 (lr=1.3896e-04) (hash(x)=27113866) +925 train 7.570621 (lr=1.3894e-04) (hash(x)=26961429) +926 train 7.375728 (lr=1.3891e-04) (hash(x)=21355372) +927 train 7.519284 (lr=1.3889e-04) (hash(x)=24968260) +928 train 7.537370 (lr=1.3887e-04) (hash(x)=25357517) +929 train 7.589176 (lr=1.3884e-04) (hash(x)=24854265) +930 train 7.367210 (lr=1.3882e-04) (hash(x)=21102770) +931 train 7.658353 (lr=1.3880e-04) (hash(x)=25676468) +932 train 7.576852 (lr=1.3877e-04) (hash(x)=22809869) +933 train 7.703037 (lr=1.3875e-04) (hash(x)=25503865) +934 train 7.552258 (lr=1.3873e-04) (hash(x)=24853995) +935 train 7.732830 (lr=1.3870e-04) (hash(x)=27544803) +936 train 7.761856 (lr=1.3868e-04) (hash(x)=25981933) +937 train 7.445153 (lr=1.3866e-04) (hash(x)=24658683) +938 train 7.629202 (lr=1.3863e-04) (hash(x)=23855201) +939 train 7.574050 (lr=1.3861e-04) (hash(x)=24331407) +940 train 7.822721 (lr=1.3858e-04) (hash(x)=29265551) +941 train 7.493208 (lr=1.3856e-04) (hash(x)=21892556) +942 train 7.563811 (lr=1.3854e-04) (hash(x)=27183405) +943 train 7.522004 (lr=1.3851e-04) (hash(x)=26540663) +944 train 7.434268 (lr=1.3849e-04) (hash(x)=25718393) +945 train 7.651257 (lr=1.3847e-04) (hash(x)=26819462) +946 train 7.655763 (lr=1.3844e-04) (hash(x)=27427540) +947 train 7.628227 (lr=1.3842e-04) (hash(x)=25532657) +948 train 7.857942 (lr=1.3839e-04) (hash(x)=27641372) +949 train 7.594234 (lr=1.3837e-04) (hash(x)=26515570) +950 val loss 7.6032 +950 val perplexity 2004.5295 +950 train 7.842155 (lr=1.3835e-04) (hash(x)=26911957) +951 train 7.977689 (lr=1.3832e-04) (hash(x)=25856625) +952 train 7.486057 (lr=1.3830e-04) (hash(x)=25219129) +953 train 7.465619 (lr=1.3828e-04) (hash(x)=25260471) +954 train 7.814037 (lr=1.3825e-04) (hash(x)=29373370) +955 train 7.396421 (lr=1.3823e-04) (hash(x)=23437426) +956 train 7.691822 (lr=1.3820e-04) (hash(x)=23769521) +957 train 7.721507 (lr=1.3818e-04) (hash(x)=25961833) +958 train 7.462274 (lr=1.3816e-04) (hash(x)=23582666) +959 train 7.533142 (lr=1.3813e-04) (hash(x)=23164356) +960 train 7.513992 (lr=1.3811e-04) (hash(x)=24443114) +961 train 7.549909 (lr=1.3808e-04) (hash(x)=25052665) +962 train 7.693492 (lr=1.3806e-04) (hash(x)=27802272) +963 train 7.537313 (lr=1.3804e-04) (hash(x)=25957896) +964 train 7.594818 (lr=1.3801e-04) (hash(x)=26737251) +965 train 7.717982 (lr=1.3799e-04) (hash(x)=24723263) +966 train 7.656665 (lr=1.3796e-04) (hash(x)=24707011) +967 train 7.623613 (lr=1.3794e-04) (hash(x)=25646282) +968 train 7.617224 (lr=1.3791e-04) (hash(x)=27544665) +969 train 7.572166 (lr=1.3789e-04) (hash(x)=25851993) +970 train 7.892766 (lr=1.3787e-04) (hash(x)=29059700) +971 train 7.563137 (lr=1.3784e-04) (hash(x)=21513584) +972 train 7.313602 (lr=1.3782e-04) (hash(x)=23151267) +973 train 7.578110 (lr=1.3779e-04) (hash(x)=26017176) +974 train 7.667178 (lr=1.3777e-04) (hash(x)=26979518) +975 train 7.655369 (lr=1.3774e-04) (hash(x)=23843233) +976 train 7.817558 (lr=1.3772e-04) (hash(x)=24193010) +977 train 7.566135 (lr=1.3770e-04) (hash(x)=21476847) +978 train 7.420307 (lr=1.3767e-04) (hash(x)=21366504) +979 train 7.437955 (lr=1.3765e-04) (hash(x)=23226697) +980 train 7.294384 (lr=1.3762e-04) (hash(x)=19961773) +981 train 7.148386 (lr=1.3760e-04) (hash(x)=19772969) +982 train 7.454338 (lr=1.3757e-04) (hash(x)=23110142) +983 train 7.746372 (lr=1.3755e-04) (hash(x)=24506028) +984 train 7.695303 (lr=1.3752e-04) (hash(x)=25480731) +985 train 7.498700 (lr=1.3750e-04) (hash(x)=21077417) +986 train 7.481094 (lr=1.3748e-04) (hash(x)=23686713) +987 train 7.553417 (lr=1.3745e-04) (hash(x)=26024321) +988 train 7.671665 (lr=1.3743e-04) (hash(x)=27424109) +989 train 7.785118 (lr=1.3740e-04) (hash(x)=27786174) +990 train 7.583102 (lr=1.3738e-04) (hash(x)=25232502) +991 train 7.578929 (lr=1.3735e-04) (hash(x)=22781277) +992 train 7.623016 (lr=1.3733e-04) (hash(x)=26184527) +993 train 7.618810 (lr=1.3730e-04) (hash(x)=24459895) +994 train 7.601055 (lr=1.3728e-04) (hash(x)=25244624) +995 train 7.697408 (lr=1.3725e-04) (hash(x)=24451843) +996 train 7.676912 (lr=1.3723e-04) (hash(x)=22129897) +997 train 7.493824 (lr=1.3720e-04) (hash(x)=21116390) +998 train 7.337273 (lr=1.3718e-04) (hash(x)=20650070) +999 train 7.748166 (lr=1.3715e-04) (hash(x)=24948650) +1000 val loss 7.5640 +1000 val perplexity 1927.5093 +1000 train 7.574645 (lr=1.3713e-04) (hash(x)=25444553) +1001 train 7.534134 (lr=1.3710e-04) (hash(x)=25617781) +1002 train 7.420804 (lr=1.3708e-04) (hash(x)=23862434) +1003 train 7.459018 (lr=1.3705e-04) (hash(x)=25559534) +1004 train 7.665733 (lr=1.3703e-04) (hash(x)=26577585) +1005 train 7.512191 (lr=1.3700e-04) (hash(x)=25546274) +1006 train 7.613945 (lr=1.3698e-04) (hash(x)=26284202) +1007 train 7.610025 (lr=1.3695e-04) (hash(x)=26373991) +1008 train 7.514053 (lr=1.3693e-04) (hash(x)=24612851) +1009 train 7.590736 (lr=1.3690e-04) (hash(x)=26410662) +1010 train 7.650468 (lr=1.3688e-04) (hash(x)=23824841) +1011 train 7.937522 (lr=1.3685e-04) (hash(x)=27756673) +1012 train 7.672373 (lr=1.3683e-04) (hash(x)=25427447) +1013 train 7.696445 (lr=1.3680e-04) (hash(x)=23661686) +1014 train 7.583431 (lr=1.3678e-04) (hash(x)=25129504) +1015 train 7.491857 (lr=1.3675e-04) (hash(x)=23402396) +1016 train 7.744293 (lr=1.3673e-04) (hash(x)=26145557) +1017 train 7.527713 (lr=1.3670e-04) (hash(x)=26547918) +1018 train 7.618215 (lr=1.3668e-04) (hash(x)=26653070) +1019 train 7.626329 (lr=1.3665e-04) (hash(x)=28250354) +1020 train 7.615791 (lr=1.3663e-04) (hash(x)=25437401) +1021 train 7.672232 (lr=1.3660e-04) (hash(x)=25598861) +1022 train 7.484257 (lr=1.3658e-04) (hash(x)=24572587) +1023 train 7.533443 (lr=1.3655e-04) (hash(x)=21562133) +1024 train 7.950314 (lr=1.3652e-04) (hash(x)=27718876) +1025 train 7.547974 (lr=1.3650e-04) (hash(x)=25312391) +1026 train 7.630908 (lr=1.3647e-04) (hash(x)=26579535) +1027 train 7.850259 (lr=1.3645e-04) (hash(x)=27253861) +1028 train 7.729715 (lr=1.3642e-04) (hash(x)=28451867) +1029 train 7.445741 (lr=1.3640e-04) (hash(x)=26795921) +1030 train 7.595217 (lr=1.3637e-04) (hash(x)=26147208) +1031 train 7.654935 (lr=1.3635e-04) (hash(x)=25009210) +1032 train 7.561206 (lr=1.3632e-04) (hash(x)=25213771) +1033 train 7.468550 (lr=1.3629e-04) (hash(x)=26254538) +1034 train 7.510411 (lr=1.3627e-04) (hash(x)=25565614) +1035 train 7.340894 (lr=1.3624e-04) (hash(x)=23052577) +1036 train 8.111941 (lr=1.3622e-04) (hash(x)=29630613) +1037 train 7.403548 (lr=1.3619e-04) (hash(x)=23667224) +1038 train 7.540875 (lr=1.3617e-04) (hash(x)=25740670) +1039 train 7.625060 (lr=1.3614e-04) (hash(x)=27161811) +1040 train 7.740257 (lr=1.3611e-04) (hash(x)=26385663) +1041 train 7.435144 (lr=1.3609e-04) (hash(x)=26313522) +1042 train 7.561578 (lr=1.3606e-04) (hash(x)=26814686) +1043 train 7.678205 (lr=1.3604e-04) (hash(x)=27302459) +1044 train 7.956020 (lr=1.3601e-04) (hash(x)=26758132) +1045 train 7.598311 (lr=1.3599e-04) (hash(x)=26837963) +1046 train 7.382121 (lr=1.3596e-04) (hash(x)=22089547) +1047 train 7.884258 (lr=1.3593e-04) (hash(x)=29515100) +1048 train 7.566444 (lr=1.3591e-04) (hash(x)=25471442) +1049 train 7.585145 (lr=1.3588e-04) (hash(x)=26674478) +1050 val loss 7.5538 +1050 val perplexity 1907.9576 +1050 train 7.533145 (lr=1.3586e-04) (hash(x)=25373386) +1051 train 7.522246 (lr=1.3583e-04) (hash(x)=25318001) +1052 train 7.687829 (lr=1.3580e-04) (hash(x)=27255021) +1053 train 7.641295 (lr=1.3578e-04) (hash(x)=25174043) +1054 train 7.385275 (lr=1.3575e-04) (hash(x)=23857597) +1055 train 7.601245 (lr=1.3573e-04) (hash(x)=25305929) +1056 train 7.681435 (lr=1.3570e-04) (hash(x)=27009246) +1057 train 7.734197 (lr=1.3567e-04) (hash(x)=26175477) +1058 train 7.452455 (lr=1.3565e-04) (hash(x)=22700025) +1059 train 7.521625 (lr=1.3562e-04) (hash(x)=24339043) +1060 train 7.329329 (lr=1.3560e-04) (hash(x)=22139900) +1061 train 8.183154 (lr=1.3557e-04) (hash(x)=25412772) +1062 train 7.600906 (lr=1.3554e-04) (hash(x)=27020849) +1063 train 7.484609 (lr=1.3552e-04) (hash(x)=26808543) +1064 train 7.339824 (lr=1.3549e-04) (hash(x)=23061527) +1065 train 7.525746 (lr=1.3546e-04) (hash(x)=24738650) +1066 train 7.366748 (lr=1.3544e-04) (hash(x)=24036715) +1067 train 7.428292 (lr=1.3541e-04) (hash(x)=25763991) +1068 train 7.677661 (lr=1.3538e-04) (hash(x)=27393753) +1069 train 7.798822 (lr=1.3536e-04) (hash(x)=28182190) +1070 train 7.448925 (lr=1.3533e-04) (hash(x)=23358569) +1071 train 7.626542 (lr=1.3531e-04) (hash(x)=25669509) +1072 train 7.747528 (lr=1.3528e-04) (hash(x)=29139024) +1073 train 7.630504 (lr=1.3525e-04) (hash(x)=25616522) +1074 train 7.550705 (lr=1.3523e-04) (hash(x)=25695789) +1075 train 7.747047 (lr=1.3520e-04) (hash(x)=27676869) +1076 train 7.593613 (lr=1.3517e-04) (hash(x)=25952695) +1077 train 7.580128 (lr=1.3515e-04) (hash(x)=26316170) +1078 train 7.492101 (lr=1.3512e-04) (hash(x)=24081867) +1079 train 7.708713 (lr=1.3509e-04) (hash(x)=28435805) +1080 train 7.567260 (lr=1.3507e-04) (hash(x)=23375063) +1081 train 7.569048 (lr=1.3504e-04) (hash(x)=26869022) +1082 train 7.459199 (lr=1.3501e-04) (hash(x)=25793007) +1083 train 7.437397 (lr=1.3499e-04) (hash(x)=23455211) +1084 train 7.423065 (lr=1.3496e-04) (hash(x)=20441501) +1085 train 7.827101 (lr=1.3493e-04) (hash(x)=29321187) +1086 train 7.994789 (lr=1.3491e-04) (hash(x)=32627505) +1087 train 7.481256 (lr=1.3488e-04) (hash(x)=26482758) +1088 train 7.337524 (lr=1.3485e-04) (hash(x)=21431511) +1089 train 7.583581 (lr=1.3483e-04) (hash(x)=26046639) +1090 train 7.671319 (lr=1.3480e-04) (hash(x)=27464841) +1091 train 7.542797 (lr=1.3477e-04) (hash(x)=27068280) +1092 train 7.427791 (lr=1.3475e-04) (hash(x)=23119133) +1093 train 7.593180 (lr=1.3472e-04) (hash(x)=26782091) +1094 train 7.602220 (lr=1.3469e-04) (hash(x)=26265326) +1095 train 7.622809 (lr=1.3467e-04) (hash(x)=24929929) +1096 train 7.493257 (lr=1.3464e-04) (hash(x)=23158628) +1097 train 7.579556 (lr=1.3461e-04) (hash(x)=25950541) +1098 train 7.384553 (lr=1.3458e-04) (hash(x)=22093912) +1099 train 7.551892 (lr=1.3456e-04) (hash(x)=25373676) +1100 val loss 7.5407 +1100 val perplexity 1883.1010 +1100 train 7.265135 (lr=1.3453e-04) (hash(x)=18986670) +1101 train 7.754144 (lr=1.3450e-04) (hash(x)=27283187) +1102 train 7.535921 (lr=1.3448e-04) (hash(x)=25474743) +1103 train 7.494709 (lr=1.3445e-04) (hash(x)=25043037) +1104 train 7.383271 (lr=1.3442e-04) (hash(x)=23156261) +1105 train 7.805627 (lr=1.3440e-04) (hash(x)=27027534) +1106 train 7.416646 (lr=1.3437e-04) (hash(x)=22733630) +1107 train 7.689794 (lr=1.3434e-04) (hash(x)=27906976) +1108 train 7.574020 (lr=1.3431e-04) (hash(x)=27848655) +1109 train 7.535294 (lr=1.3429e-04) (hash(x)=23889709) +1110 train 8.525962 (lr=1.3426e-04) (hash(x)=33189918) +1111 train 8.096976 (lr=1.3423e-04) (hash(x)=29151257) +1112 train 7.815672 (lr=1.3420e-04) (hash(x)=23881512) +1113 train 7.559192 (lr=1.3418e-04) (hash(x)=21307974) +1114 train 7.594129 (lr=1.3415e-04) (hash(x)=25264524) +1115 train 7.754294 (lr=1.3412e-04) (hash(x)=26405613) +1116 train 7.463235 (lr=1.3410e-04) (hash(x)=21918678) +1117 train 7.451543 (lr=1.3407e-04) (hash(x)=24233887) +1118 train 7.108521 (lr=1.3404e-04) (hash(x)=19490509) +1119 train 7.702447 (lr=1.3401e-04) (hash(x)=26400365) +1120 train 7.919592 (lr=1.3399e-04) (hash(x)=28572086) +1121 train 7.374069 (lr=1.3396e-04) (hash(x)=22293114) +1122 train 7.501968 (lr=1.3393e-04) (hash(x)=26845479) +1123 train 7.386968 (lr=1.3390e-04) (hash(x)=23971905) +1124 train 7.621689 (lr=1.3388e-04) (hash(x)=25639959) +1125 train 7.215116 (lr=1.3385e-04) (hash(x)=20076502) +1126 train 7.630672 (lr=1.3382e-04) (hash(x)=25089255) +1127 train 7.506526 (lr=1.3379e-04) (hash(x)=24098812) +1128 train 7.524045 (lr=1.3377e-04) (hash(x)=23493707) +1129 train 7.749037 (lr=1.3374e-04) (hash(x)=27610410) +1130 train 7.497199 (lr=1.3371e-04) (hash(x)=24540186) +1131 train 7.793244 (lr=1.3368e-04) (hash(x)=29402976) +1132 train 7.368482 (lr=1.3366e-04) (hash(x)=23776025) +1133 train 7.178232 (lr=1.3363e-04) (hash(x)=19032564) +1134 train 7.703083 (lr=1.3360e-04) (hash(x)=26921117) +1135 train 7.340399 (lr=1.3357e-04) (hash(x)=20967666) +1136 train 7.369779 (lr=1.3354e-04) (hash(x)=23394540) +1137 train 7.429031 (lr=1.3352e-04) (hash(x)=22666342) +1138 train 7.602257 (lr=1.3349e-04) (hash(x)=23482498) +1139 train 7.636687 (lr=1.3346e-04) (hash(x)=24287610) +1140 train 7.664464 (lr=1.3343e-04) (hash(x)=24512831) +1141 train 7.879526 (lr=1.3341e-04) (hash(x)=28637634) +1142 train 8.134658 (lr=1.3338e-04) (hash(x)=24107127) +1143 train 7.765766 (lr=1.3335e-04) (hash(x)=28667963) +1144 train 7.654773 (lr=1.3332e-04) (hash(x)=26302492) +1145 train 7.644989 (lr=1.3329e-04) (hash(x)=23621685) +1146 train 7.417816 (lr=1.3327e-04) (hash(x)=23997414) +1147 train 7.510887 (lr=1.3324e-04) (hash(x)=25974316) +1148 train 7.459860 (lr=1.3321e-04) (hash(x)=23464988) +1149 train 7.560771 (lr=1.3318e-04) (hash(x)=24487710) +1150 val loss 7.5109 +1150 val perplexity 1827.9476 +1150 train 7.774063 (lr=1.3315e-04) (hash(x)=29610350) +1151 train 7.842784 (lr=1.3313e-04) (hash(x)=27083417) +1152 train 7.205356 (lr=1.3310e-04) (hash(x)=20666288) +1153 train 7.305922 (lr=1.3307e-04) (hash(x)=22850633) +1154 train 7.477474 (lr=1.3304e-04) (hash(x)=24741872) +1155 train 7.857971 (lr=1.3301e-04) (hash(x)=28605205) +1156 train 7.315708 (lr=1.3299e-04) (hash(x)=22624463) +1157 train 7.573302 (lr=1.3296e-04) (hash(x)=24786468) +1158 train 7.320096 (lr=1.3293e-04) (hash(x)=21365399) +1159 train 7.529681 (lr=1.3290e-04) (hash(x)=23649001) +1160 train 7.594575 (lr=1.3287e-04) (hash(x)=28203982) +1161 train 7.518419 (lr=1.3284e-04) (hash(x)=26473994) +1162 train 7.170504 (lr=1.3282e-04) (hash(x)=19476441) +1163 train 7.453590 (lr=1.3279e-04) (hash(x)=25921700) +1164 train 7.281642 (lr=1.3276e-04) (hash(x)=23064343) +1165 train 7.453954 (lr=1.3273e-04) (hash(x)=24117626) +1166 train 7.384861 (lr=1.3270e-04) (hash(x)=21764556) +1167 train 8.236251 (lr=1.3267e-04) (hash(x)=31338300) +1168 train 7.691583 (lr=1.3265e-04) (hash(x)=27443187) +1169 train 7.118280 (lr=1.3262e-04) (hash(x)=21337692) +1170 train 7.655772 (lr=1.3259e-04) (hash(x)=27845383) +1171 train 7.485230 (lr=1.3256e-04) (hash(x)=23862328) +1172 train 7.638042 (lr=1.3253e-04) (hash(x)=23811014) +1173 train 7.595374 (lr=1.3250e-04) (hash(x)=24380098) +1174 train 7.315637 (lr=1.3248e-04) (hash(x)=22351136) +1175 train 7.591435 (lr=1.3245e-04) (hash(x)=30603174) +1176 train 7.610485 (lr=1.3242e-04) (hash(x)=27924596) +1177 train 7.952805 (lr=1.3239e-04) (hash(x)=30882548) +1178 train 7.429936 (lr=1.3236e-04) (hash(x)=22339464) +1179 train 7.298704 (lr=1.3233e-04) (hash(x)=23603806) +1180 train 7.618423 (lr=1.3230e-04) (hash(x)=24809041) +1181 train 7.447435 (lr=1.3228e-04) (hash(x)=24382442) +1182 train 7.423818 (lr=1.3225e-04) (hash(x)=23134077) +1183 train 7.446184 (lr=1.3222e-04) (hash(x)=24830965) +1184 train 7.562974 (lr=1.3219e-04) (hash(x)=25527259) +1185 train 7.568181 (lr=1.3216e-04) (hash(x)=25547480) +1186 train 7.454095 (lr=1.3213e-04) (hash(x)=24424314) +1187 train 7.828369 (lr=1.3210e-04) (hash(x)=32488729) +1188 train 7.712151 (lr=1.3207e-04) (hash(x)=31168462) +1189 train 7.982491 (lr=1.3205e-04) (hash(x)=31331643) +1190 train 7.666425 (lr=1.3202e-04) (hash(x)=28746633) +1191 train 7.645804 (lr=1.3199e-04) (hash(x)=27269893) +1192 train 7.472334 (lr=1.3196e-04) (hash(x)=23484031) +1193 train 7.453909 (lr=1.3193e-04) (hash(x)=23278725) +1194 train 7.575677 (lr=1.3190e-04) (hash(x)=25440745) +1195 train 7.595694 (lr=1.3187e-04) (hash(x)=25215077) +1196 train 7.641562 (lr=1.3184e-04) (hash(x)=28309266) +1197 train 7.340873 (lr=1.3181e-04) (hash(x)=22442404) +1198 train 7.368016 (lr=1.3179e-04) (hash(x)=20775262) +1199 train 7.480364 (lr=1.3176e-04) (hash(x)=24825041) +1200 val loss 7.4949 +1200 val perplexity 1798.7827 +1200 train 7.638412 (lr=1.3173e-04) (hash(x)=29016896) +1201 train 7.565865 (lr=1.3170e-04) (hash(x)=25590276) +1202 train 7.441487 (lr=1.3167e-04) (hash(x)=22816384) +1203 train 7.551698 (lr=1.3164e-04) (hash(x)=25893804) +1204 train 7.427523 (lr=1.3161e-04) (hash(x)=23983816) +1205 train 7.327976 (lr=1.3158e-04) (hash(x)=22222468) +1206 train 7.382107 (lr=1.3155e-04) (hash(x)=23039141) +1207 train 7.350933 (lr=1.3152e-04) (hash(x)=22724871) +1208 train 7.404624 (lr=1.3149e-04) (hash(x)=25253062) +1209 train 7.367748 (lr=1.3147e-04) (hash(x)=25140744) +1210 train 7.450803 (lr=1.3144e-04) (hash(x)=24717218) +1211 train 7.568512 (lr=1.3141e-04) (hash(x)=27317554) +1212 train 7.196546 (lr=1.3138e-04) (hash(x)=22013236) +1213 train 7.750740 (lr=1.3135e-04) (hash(x)=26692343) +1214 train 7.226196 (lr=1.3132e-04) (hash(x)=19859225) +1215 train 7.235083 (lr=1.3129e-04) (hash(x)=24683717) +1216 train 7.269361 (lr=1.3126e-04) (hash(x)=21932013) +1217 train 7.515419 (lr=1.3123e-04) (hash(x)=26849303) +1218 train 7.626953 (lr=1.3120e-04) (hash(x)=26458000) +1219 train 7.367565 (lr=1.3117e-04) (hash(x)=21584083) +1220 train 7.724025 (lr=1.3114e-04) (hash(x)=23598625) +1221 train 7.458486 (lr=1.3111e-04) (hash(x)=26059939) +1222 train 7.703897 (lr=1.3108e-04) (hash(x)=25481982) +1223 train 7.567249 (lr=1.3105e-04) (hash(x)=26190337) +1224 train 7.738960 (lr=1.3103e-04) (hash(x)=28767755) +1225 train 7.365200 (lr=1.3100e-04) (hash(x)=23663918) +1226 train 7.498558 (lr=1.3097e-04) (hash(x)=21293227) +1227 train 7.509052 (lr=1.3094e-04) (hash(x)=22249019) +1228 train 7.604898 (lr=1.3091e-04) (hash(x)=26886529) +1229 train 7.449604 (lr=1.3088e-04) (hash(x)=25779849) +1230 train 7.554985 (lr=1.3085e-04) (hash(x)=26228964) +1231 train 7.459255 (lr=1.3082e-04) (hash(x)=23086289) +1232 train 7.581958 (lr=1.3079e-04) (hash(x)=23198922) +1233 train 7.615787 (lr=1.3076e-04) (hash(x)=27523941) +1234 train 7.375274 (lr=1.3073e-04) (hash(x)=24293992) +1235 train 8.140546 (lr=1.3070e-04) (hash(x)=28047044) +1236 train 7.575788 (lr=1.3067e-04) (hash(x)=23688671) +1237 train 7.431643 (lr=1.3064e-04) (hash(x)=25125498) +1238 train 7.318893 (lr=1.3061e-04) (hash(x)=21977292) +1239 train 7.385817 (lr=1.3058e-04) (hash(x)=23593875) +1240 train 7.334045 (lr=1.3055e-04) (hash(x)=22659030) +1241 train 7.463547 (lr=1.3052e-04) (hash(x)=25117733) +1242 train 7.451679 (lr=1.3049e-04) (hash(x)=22322808) +1243 train 7.487434 (lr=1.3046e-04) (hash(x)=26059735) +1244 train 7.451084 (lr=1.3043e-04) (hash(x)=22485526) +1245 train 7.335564 (lr=1.3040e-04) (hash(x)=23028679) +1246 train 7.333740 (lr=1.3037e-04) (hash(x)=22906035) +1247 train 7.275941 (lr=1.3034e-04) (hash(x)=22414190) +1248 train 7.555494 (lr=1.3031e-04) (hash(x)=26229624) +1249 train 7.335992 (lr=1.3028e-04) (hash(x)=22223137) +1250 val loss 7.4741 +1250 val perplexity 1761.7979 +1250 train 7.600411 (lr=1.3025e-04) (hash(x)=24911520) +1251 train 7.743656 (lr=1.3022e-04) (hash(x)=24204591) +1252 train 7.358792 (lr=1.3019e-04) (hash(x)=24379601) +1253 train 7.295045 (lr=1.3016e-04) (hash(x)=22922475) +1254 train 7.332663 (lr=1.3013e-04) (hash(x)=23426249) +1255 train 7.639954 (lr=1.3010e-04) (hash(x)=26758114) +1256 train 7.298345 (lr=1.3007e-04) (hash(x)=24027111) +1257 train 7.442404 (lr=1.3004e-04) (hash(x)=25358064) +1258 train 7.360042 (lr=1.3001e-04) (hash(x)=22571285) +1259 train 7.741319 (lr=1.2998e-04) (hash(x)=20084233) +1260 train 7.541828 (lr=1.2995e-04) (hash(x)=18786581) +1261 train 7.491212 (lr=1.2992e-04) (hash(x)=26395104) +1262 train 7.362049 (lr=1.2989e-04) (hash(x)=24212567) +1263 train 7.214110 (lr=1.2986e-04) (hash(x)=21563184) +1264 train 7.485656 (lr=1.2983e-04) (hash(x)=26490150) +1265 train 7.551824 (lr=1.2980e-04) (hash(x)=25207694) +1266 train 7.390506 (lr=1.2977e-04) (hash(x)=23914544) +1267 train 7.409345 (lr=1.2974e-04) (hash(x)=23861489) +1268 train 7.853926 (lr=1.2971e-04) (hash(x)=30714540) +1269 train 7.391518 (lr=1.2968e-04) (hash(x)=23471007) +1270 train 7.399113 (lr=1.2965e-04) (hash(x)=23244293) +1271 train 7.318292 (lr=1.2962e-04) (hash(x)=19218470) +1272 train 7.584255 (lr=1.2959e-04) (hash(x)=26965136) +1273 train 7.358087 (lr=1.2956e-04) (hash(x)=22944035) +1274 train 7.362814 (lr=1.2953e-04) (hash(x)=22002714) +1275 train 7.668336 (lr=1.2950e-04) (hash(x)=28469562) +1276 train 7.766516 (lr=1.2947e-04) (hash(x)=26889992) +1277 train 7.814234 (lr=1.2944e-04) (hash(x)=26452814) +1278 train 7.604598 (lr=1.2941e-04) (hash(x)=28397488) +1279 train 7.666069 (lr=1.2937e-04) (hash(x)=25588469) +1280 train 7.521314 (lr=1.2934e-04) (hash(x)=24833139) +1281 train 7.417786 (lr=1.2931e-04) (hash(x)=24788298) +1282 train 7.611594 (lr=1.2928e-04) (hash(x)=24979383) +1283 train 7.606006 (lr=1.2925e-04) (hash(x)=25236367) +1284 train 7.445798 (lr=1.2922e-04) (hash(x)=22638257) +1285 train 7.291461 (lr=1.2919e-04) (hash(x)=23069067) +1286 train 7.445301 (lr=1.2916e-04) (hash(x)=25133239) +1287 train 8.000525 (lr=1.2913e-04) (hash(x)=30433767) +1288 train 8.043902 (lr=1.2910e-04) (hash(x)=34319079) +1289 train 7.922290 (lr=1.2907e-04) (hash(x)=29268881) +1290 train 7.545432 (lr=1.2904e-04) (hash(x)=24528336) +1291 train 7.716236 (lr=1.2901e-04) (hash(x)=26302626) +1292 train 7.713660 (lr=1.2898e-04) (hash(x)=25479111) +1293 train 7.815369 (lr=1.2895e-04) (hash(x)=24749682) +1294 train 7.453630 (lr=1.2891e-04) (hash(x)=24111393) +1295 train 7.193377 (lr=1.2888e-04) (hash(x)=17851621) +1296 train 7.421811 (lr=1.2885e-04) (hash(x)=26463070) +1297 train 7.459898 (lr=1.2882e-04) (hash(x)=25620741) +1298 train 8.145876 (lr=1.2879e-04) (hash(x)=28225676) +1299 train 7.972266 (lr=1.2876e-04) (hash(x)=27028191) +1300 val loss 7.5231 +1300 val perplexity 1850.2421 +1300 train 7.654576 (lr=1.2873e-04) (hash(x)=29006516) +1301 train 7.711158 (lr=1.2870e-04) (hash(x)=27590299) +1302 train 7.859169 (lr=1.2867e-04) (hash(x)=28678983) +1303 train 7.675820 (lr=1.2864e-04) (hash(x)=25183690) +1304 train 7.173515 (lr=1.2861e-04) (hash(x)=19918097) +1305 train 7.991430 (lr=1.2858e-04) (hash(x)=31114252) +1306 train 7.948857 (lr=1.2854e-04) (hash(x)=30913255) +1307 train 7.518649 (lr=1.2851e-04) (hash(x)=26182243) +1308 train 7.751298 (lr=1.2848e-04) (hash(x)=27420668) +1309 train 8.022731 (lr=1.2845e-04) (hash(x)=30419908) +1310 train 7.880400 (lr=1.2842e-04) (hash(x)=29002281) +1311 train 7.582936 (lr=1.2839e-04) (hash(x)=27040642) +1312 train 7.479641 (lr=1.2836e-04) (hash(x)=26929300) +1313 train 7.571809 (lr=1.2833e-04) (hash(x)=26240761) +1314 train 7.606322 (lr=1.2830e-04) (hash(x)=27161876) +1315 train 7.459178 (lr=1.2826e-04) (hash(x)=24489607) +1316 train 7.793868 (lr=1.2823e-04) (hash(x)=27040115) +1317 train 7.491776 (lr=1.2820e-04) (hash(x)=25012872) +1318 train 7.179414 (lr=1.2817e-04) (hash(x)=20894720) +1319 train 7.264232 (lr=1.2814e-04) (hash(x)=22183303) +1320 train 7.493855 (lr=1.2811e-04) (hash(x)=26291778) +1321 train 7.599909 (lr=1.2808e-04) (hash(x)=27682633) +1322 train 7.397918 (lr=1.2805e-04) (hash(x)=26490892) +1323 train 7.882854 (lr=1.2801e-04) (hash(x)=28844646) +1324 train 8.209308 (lr=1.2798e-04) (hash(x)=29545304) +1325 train 8.269450 (lr=1.2795e-04) (hash(x)=31082070) +1326 train 7.867200 (lr=1.2792e-04) (hash(x)=27486316) +1327 train 7.820882 (lr=1.2789e-04) (hash(x)=27537063) +1328 train 7.533969 (lr=1.2786e-04) (hash(x)=26955557) +1329 train 7.554943 (lr=1.2783e-04) (hash(x)=26125988) +1330 train 7.558179 (lr=1.2779e-04) (hash(x)=22800125) +1331 train 7.753798 (lr=1.2776e-04) (hash(x)=25446686) +1332 train 7.797052 (lr=1.2773e-04) (hash(x)=28743746) +1333 train 7.549866 (lr=1.2770e-04) (hash(x)=19819857) +1334 train 7.351061 (lr=1.2767e-04) (hash(x)=23518628) +1335 train 7.253480 (lr=1.2764e-04) (hash(x)=19492832) +1336 train 7.510522 (lr=1.2761e-04) (hash(x)=24627720) +1337 train 7.396688 (lr=1.2757e-04) (hash(x)=23741214) +1338 train 7.476325 (lr=1.2754e-04) (hash(x)=25837914) +1339 train 7.413406 (lr=1.2751e-04) (hash(x)=25484958) +1340 train 7.358302 (lr=1.2748e-04) (hash(x)=23671284) +1341 train 7.481877 (lr=1.2745e-04) (hash(x)=25525370) +1342 train 7.541728 (lr=1.2742e-04) (hash(x)=26585300) +1343 train 7.614135 (lr=1.2738e-04) (hash(x)=25951629) +1344 train 7.805704 (lr=1.2735e-04) (hash(x)=28743135) +1345 train 7.977814 (lr=1.2732e-04) (hash(x)=28557663) +1346 train 7.312353 (lr=1.2729e-04) (hash(x)=22642751) +1347 train 7.225528 (lr=1.2726e-04) (hash(x)=23462798) +1348 train 7.083284 (lr=1.2723e-04) (hash(x)=24292328) +1349 train 7.472473 (lr=1.2719e-04) (hash(x)=27320280) +1350 val loss 7.4679 +1350 val perplexity 1750.8604 +1350 train 7.686035 (lr=1.2716e-04) (hash(x)=27352812) +1351 train 7.504184 (lr=1.2713e-04) (hash(x)=22408682) +1352 train 7.421063 (lr=1.2710e-04) (hash(x)=23144732) +1353 train 7.277802 (lr=1.2707e-04) (hash(x)=22230799) +1354 train 7.685529 (lr=1.2703e-04) (hash(x)=29747687) +1355 train 7.869687 (lr=1.2700e-04) (hash(x)=31317970) +1356 train 7.160344 (lr=1.2697e-04) (hash(x)=20131758) +1357 train 7.495320 (lr=1.2694e-04) (hash(x)=24020983) +1358 train 7.374612 (lr=1.2691e-04) (hash(x)=23998051) +1359 train 7.447875 (lr=1.2687e-04) (hash(x)=27633457) +1360 train 7.177670 (lr=1.2684e-04) (hash(x)=20155247) +1361 train 7.458847 (lr=1.2681e-04) (hash(x)=23766987) +1362 train 7.343806 (lr=1.2678e-04) (hash(x)=25960383) +1363 train 7.612692 (lr=1.2675e-04) (hash(x)=23729283) +1364 train 7.719511 (lr=1.2671e-04) (hash(x)=27775445) +1365 train 7.564538 (lr=1.2668e-04) (hash(x)=25975834) +1366 train 7.407933 (lr=1.2665e-04) (hash(x)=22765259) +1367 train 7.667026 (lr=1.2662e-04) (hash(x)=27635080) +1368 train 7.443006 (lr=1.2659e-04) (hash(x)=23848542) +1369 train 7.556142 (lr=1.2655e-04) (hash(x)=27181156) +1370 train 7.704807 (lr=1.2652e-04) (hash(x)=28321340) +1371 train 7.413349 (lr=1.2649e-04) (hash(x)=25918780) +1372 train 7.443821 (lr=1.2646e-04) (hash(x)=23338297) +1373 train 7.580521 (lr=1.2643e-04) (hash(x)=22370417) +1374 train 7.506484 (lr=1.2639e-04) (hash(x)=24272668) +1375 train 7.174581 (lr=1.2636e-04) (hash(x)=22287596) +1376 train 7.366695 (lr=1.2633e-04) (hash(x)=25257403) +1377 train 7.318537 (lr=1.2630e-04) (hash(x)=21584419) +1378 train 7.476871 (lr=1.2626e-04) (hash(x)=25318823) +1379 train 7.294553 (lr=1.2623e-04) (hash(x)=22694623) +1380 train 7.437337 (lr=1.2620e-04) (hash(x)=23743406) +1381 train 7.662335 (lr=1.2617e-04) (hash(x)=30820846) +1382 train 8.165423 (lr=1.2613e-04) (hash(x)=34639557) +1383 train 8.020017 (lr=1.2610e-04) (hash(x)=35895440) +1384 train 7.500337 (lr=1.2607e-04) (hash(x)=26304839) +1385 train 7.647772 (lr=1.2604e-04) (hash(x)=27058657) +1386 train 7.528223 (lr=1.2601e-04) (hash(x)=25209529) +1387 train 7.434654 (lr=1.2597e-04) (hash(x)=24298886) +1388 train 7.553070 (lr=1.2594e-04) (hash(x)=26200200) +1389 train 7.480757 (lr=1.2591e-04) (hash(x)=27303061) +1390 train 7.540256 (lr=1.2588e-04) (hash(x)=26531628) +1391 train 7.553197 (lr=1.2584e-04) (hash(x)=25888847) +1392 train 7.689540 (lr=1.2581e-04) (hash(x)=28924067) +1393 train 7.179214 (lr=1.2578e-04) (hash(x)=21267641) +1394 train 7.694045 (lr=1.2575e-04) (hash(x)=29419156) +1395 train 7.982119 (lr=1.2571e-04) (hash(x)=30860646) +1396 train 7.466710 (lr=1.2568e-04) (hash(x)=25744434) +1397 train 7.490507 (lr=1.2565e-04) (hash(x)=26881837) +1398 train 7.465291 (lr=1.2561e-04) (hash(x)=26676176) +1399 train 7.672143 (lr=1.2558e-04) (hash(x)=26518800) +1400 val loss 7.4795 +1400 val perplexity 1771.4010 +1400 train 7.429488 (lr=1.2555e-04) (hash(x)=25043238) +1401 train 7.691078 (lr=1.2552e-04) (hash(x)=25863277) +1402 train 7.398721 (lr=1.2548e-04) (hash(x)=24073623) +1403 train 7.410266 (lr=1.2545e-04) (hash(x)=25385523) +1404 train 7.461919 (lr=1.2542e-04) (hash(x)=24958112) +1405 train 7.356128 (lr=1.2539e-04) (hash(x)=23362519) +1406 train 7.628532 (lr=1.2535e-04) (hash(x)=29262616) +1407 train 8.006736 (lr=1.2532e-04) (hash(x)=37519283) +1408 train 8.330569 (lr=1.2529e-04) (hash(x)=33716930) +1409 train 7.455211 (lr=1.2525e-04) (hash(x)=23392584) +1410 train 7.910470 (lr=1.2522e-04) (hash(x)=22877779) +1411 train 8.225809 (lr=1.2519e-04) (hash(x)=20564397) +1412 train 7.682816 (lr=1.2516e-04) (hash(x)=24366235) +1413 train 7.564594 (lr=1.2512e-04) (hash(x)=27065499) +1414 train 7.420540 (lr=1.2509e-04) (hash(x)=26844114) +1415 train 7.577461 (lr=1.2506e-04) (hash(x)=25141945) +1416 train 7.767835 (lr=1.2502e-04) (hash(x)=28813116) +1417 train 7.553366 (lr=1.2499e-04) (hash(x)=25466598) +1418 train 7.424534 (lr=1.2496e-04) (hash(x)=22800032) +1419 train 7.493394 (lr=1.2493e-04) (hash(x)=22717866) +1420 train 7.985240 (lr=1.2489e-04) (hash(x)=28040763) +1421 train 8.074435 (lr=1.2486e-04) (hash(x)=29648992) +1422 train 8.008239 (lr=1.2483e-04) (hash(x)=31747228) +1423 train 7.490526 (lr=1.2479e-04) (hash(x)=28527939) +1424 train 7.435132 (lr=1.2476e-04) (hash(x)=21563992) +1425 train 7.382677 (lr=1.2473e-04) (hash(x)=25134784) +1426 train 7.606746 (lr=1.2469e-04) (hash(x)=28442823) +1427 train 8.148188 (lr=1.2466e-04) (hash(x)=32757059) +1428 train 7.316543 (lr=1.2463e-04) (hash(x)=24110500) +1429 train 7.433847 (lr=1.2460e-04) (hash(x)=24145729) +1430 train 7.460632 (lr=1.2456e-04) (hash(x)=23541086) +1431 train 7.309753 (lr=1.2453e-04) (hash(x)=21942471) +1432 train 7.428076 (lr=1.2450e-04) (hash(x)=24736836) +1433 train 7.561157 (lr=1.2446e-04) (hash(x)=25325444) +1434 train 7.546279 (lr=1.2443e-04) (hash(x)=25188954) +1435 train 8.054481 (lr=1.2440e-04) (hash(x)=24247339) +1436 train 7.597104 (lr=1.2436e-04) (hash(x)=23773363) +1437 train 7.334151 (lr=1.2433e-04) (hash(x)=24142989) +1438 train 7.327497 (lr=1.2430e-04) (hash(x)=24226952) +1439 train 7.513501 (lr=1.2426e-04) (hash(x)=24955630) +1440 train 7.476232 (lr=1.2423e-04) (hash(x)=24563233) +1441 train 7.538559 (lr=1.2420e-04) (hash(x)=25491335) +1442 train 7.890892 (lr=1.2416e-04) (hash(x)=33253763) +1443 train 7.357297 (lr=1.2413e-04) (hash(x)=21368780) +1444 train 7.418930 (lr=1.2410e-04) (hash(x)=26615500) +1445 train 7.638195 (lr=1.2406e-04) (hash(x)=27146278) +1446 train 7.475789 (lr=1.2403e-04) (hash(x)=25904861) +1447 train 7.342140 (lr=1.2400e-04) (hash(x)=25541230) +1448 train 7.488896 (lr=1.2396e-04) (hash(x)=25434227) +1449 train 7.475632 (lr=1.2393e-04) (hash(x)=25375355) +1450 val loss 7.4497 +1450 val perplexity 1719.3577 +1450 train 7.299844 (lr=1.2390e-04) (hash(x)=21921129) +1451 train 7.289362 (lr=1.2386e-04) (hash(x)=23098806) +1452 train 7.333805 (lr=1.2383e-04) (hash(x)=22000544) +1453 train 7.275875 (lr=1.2379e-04) (hash(x)=22061174) +1454 train 7.327025 (lr=1.2376e-04) (hash(x)=24326286) +1455 train 7.360738 (lr=1.2373e-04) (hash(x)=23501481) +1456 train 7.526245 (lr=1.2369e-04) (hash(x)=26397938) +1457 train 7.481795 (lr=1.2366e-04) (hash(x)=24656430) +1458 train 7.236509 (lr=1.2363e-04) (hash(x)=23494971) +1459 train 7.275848 (lr=1.2359e-04) (hash(x)=23802681) +1460 train 7.287978 (lr=1.2356e-04) (hash(x)=21990153) +1461 train 7.329021 (lr=1.2353e-04) (hash(x)=23496118) +1462 train 7.344562 (lr=1.2349e-04) (hash(x)=24233822) +1463 train 7.650056 (lr=1.2346e-04) (hash(x)=22754988) +1464 train 7.373658 (lr=1.2342e-04) (hash(x)=23116635) +1465 train 7.103767 (lr=1.2339e-04) (hash(x)=21461650) +1466 train 7.231075 (lr=1.2336e-04) (hash(x)=22274473) +1467 train 7.307344 (lr=1.2332e-04) (hash(x)=22183009) +1468 train 7.523000 (lr=1.2329e-04) (hash(x)=24972441) +1469 train 7.306281 (lr=1.2326e-04) (hash(x)=22300616) +1470 train 7.070076 (lr=1.2322e-04) (hash(x)=21443060) +1471 train 7.324423 (lr=1.2319e-04) (hash(x)=23475070) +1472 train 7.261633 (lr=1.2315e-04) (hash(x)=22316810) +1473 train 7.675745 (lr=1.2312e-04) (hash(x)=24508407) +1474 train 7.659397 (lr=1.2309e-04) (hash(x)=24603557) +1475 train 7.325142 (lr=1.2305e-04) (hash(x)=23359061) +1476 train 7.390945 (lr=1.2302e-04) (hash(x)=22950844) +1477 train 7.455606 (lr=1.2298e-04) (hash(x)=22588667) +1478 train 7.578684 (lr=1.2295e-04) (hash(x)=26083526) +1479 train 7.487926 (lr=1.2292e-04) (hash(x)=23609959) +1480 train 7.498287 (lr=1.2288e-04) (hash(x)=24088171) +1481 train 7.496831 (lr=1.2285e-04) (hash(x)=25394852) +1482 train 7.457328 (lr=1.2281e-04) (hash(x)=24503040) +1483 train 7.242270 (lr=1.2278e-04) (hash(x)=22408449) +1484 train 7.466212 (lr=1.2275e-04) (hash(x)=25069325) +1485 train 7.510275 (lr=1.2271e-04) (hash(x)=26947398) +1486 train 7.062872 (lr=1.2268e-04) (hash(x)=17527161) +1487 train 7.406160 (lr=1.2264e-04) (hash(x)=23441847) +1488 train 7.403385 (lr=1.2261e-04) (hash(x)=25592861) +1489 train 7.309580 (lr=1.2258e-04) (hash(x)=23101350) +1490 train 7.301627 (lr=1.2254e-04) (hash(x)=24201380) +1491 train 7.397308 (lr=1.2251e-04) (hash(x)=23676365) +1492 train 7.454847 (lr=1.2247e-04) (hash(x)=26668088) +1493 train 7.605260 (lr=1.2244e-04) (hash(x)=26488811) +1494 train 7.594619 (lr=1.2241e-04) (hash(x)=27248109) +1495 train 7.591472 (lr=1.2237e-04) (hash(x)=23096292) +1496 train 7.548465 (lr=1.2234e-04) (hash(x)=22101981) +1497 train 7.702590 (lr=1.2230e-04) (hash(x)=24512380) +1498 train 7.506280 (lr=1.2227e-04) (hash(x)=25367738) +1499 train 7.494370 (lr=1.2223e-04) (hash(x)=27706294) +1500 val loss 7.4722 +1500 val perplexity 1758.3962 +1500 train 7.592823 (lr=1.2220e-04) (hash(x)=24154026) +1501 train 7.327135 (lr=1.2217e-04) (hash(x)=21892472) +1502 train 7.415657 (lr=1.2213e-04) (hash(x)=23662543) +1503 train 7.443205 (lr=1.2210e-04) (hash(x)=26171093) +1504 train 7.480358 (lr=1.2206e-04) (hash(x)=25974292) +1505 train 7.308730 (lr=1.2203e-04) (hash(x)=23191101) +1506 train 7.586558 (lr=1.2199e-04) (hash(x)=26498861) +1507 train 8.058908 (lr=1.2196e-04) (hash(x)=34946941) +1508 train 7.693820 (lr=1.2192e-04) (hash(x)=25442719) +1509 train 7.511966 (lr=1.2189e-04) (hash(x)=25569942) +1510 train 7.266237 (lr=1.2186e-04) (hash(x)=21265828) +1511 train 7.187505 (lr=1.2182e-04) (hash(x)=20060838) +1512 train 7.348356 (lr=1.2179e-04) (hash(x)=22588251) +1513 train 7.331012 (lr=1.2175e-04) (hash(x)=24581020) +1514 train 7.281467 (lr=1.2172e-04) (hash(x)=21882493) +1515 train 7.249510 (lr=1.2168e-04) (hash(x)=21591702) +1516 train 7.232923 (lr=1.2165e-04) (hash(x)=19813285) +1517 train 7.327904 (lr=1.2161e-04) (hash(x)=21870012) +1518 train 7.399774 (lr=1.2158e-04) (hash(x)=26895498) +1519 train 7.425437 (lr=1.2154e-04) (hash(x)=25451055) +1520 train 7.467424 (lr=1.2151e-04) (hash(x)=25395865) +1521 train 6.899742 (lr=1.2148e-04) (hash(x)=18989695) +1522 train 6.788860 (lr=1.2144e-04) (hash(x)=17040678) +1523 train 6.906874 (lr=1.2141e-04) (hash(x)=18691455) +1524 train 7.056887 (lr=1.2137e-04) (hash(x)=19017167) +1525 train 7.372702 (lr=1.2134e-04) (hash(x)=22406503) +1526 train 7.506839 (lr=1.2130e-04) (hash(x)=23036138) +1527 train 7.395465 (lr=1.2127e-04) (hash(x)=24934792) +1528 train 7.377582 (lr=1.2123e-04) (hash(x)=22843127) +1529 train 7.330261 (lr=1.2120e-04) (hash(x)=24249677) +1530 train 7.223487 (lr=1.2116e-04) (hash(x)=23318555) +1531 train 7.240599 (lr=1.2113e-04) (hash(x)=23864361) +1532 train 7.183034 (lr=1.2109e-04) (hash(x)=20242060) +1533 train 7.313048 (lr=1.2106e-04) (hash(x)=21549554) +1534 train 7.179416 (lr=1.2102e-04) (hash(x)=21642024) +1535 train 7.637952 (lr=1.2099e-04) (hash(x)=25367597) +1536 train 7.843644 (lr=1.2095e-04) (hash(x)=27224144) +1537 train 7.360222 (lr=1.2092e-04) (hash(x)=24409290) +1538 train 7.359313 (lr=1.2088e-04) (hash(x)=24987180) +1539 train 7.343397 (lr=1.2085e-04) (hash(x)=27016702) +1540 train 7.534710 (lr=1.2081e-04) (hash(x)=25819636) +1541 train 7.506019 (lr=1.2078e-04) (hash(x)=25520453) +1542 train 7.245461 (lr=1.2074e-04) (hash(x)=23580496) +1543 train 7.473608 (lr=1.2071e-04) (hash(x)=25022148) +1544 train 7.488905 (lr=1.2068e-04) (hash(x)=25447327) +1545 train 7.492128 (lr=1.2064e-04) (hash(x)=25010319) +1546 train 7.413443 (lr=1.2061e-04) (hash(x)=25511777) +1547 train 7.382045 (lr=1.2057e-04) (hash(x)=24459012) +1548 train 7.434525 (lr=1.2053e-04) (hash(x)=25082785) +1549 train 7.516553 (lr=1.2050e-04) (hash(x)=26528670) +1550 val loss 7.4579 +1550 val perplexity 1733.4254 +1550 train 7.457628 (lr=1.2046e-04) (hash(x)=26684367) +1551 train 7.413400 (lr=1.2043e-04) (hash(x)=25431365) +1552 train 7.411364 (lr=1.2039e-04) (hash(x)=24802747) +1553 train 7.212354 (lr=1.2036e-04) (hash(x)=24229522) +1554 train 7.436418 (lr=1.2032e-04) (hash(x)=24757176) +1555 train 7.525697 (lr=1.2029e-04) (hash(x)=25958785) +1556 train 7.543770 (lr=1.2025e-04) (hash(x)=26810735) +1557 train 7.198734 (lr=1.2022e-04) (hash(x)=22882640) +1558 train 7.669894 (lr=1.2018e-04) (hash(x)=27220057) +1559 train 7.911297 (lr=1.2015e-04) (hash(x)=29307788) +1560 train 7.357296 (lr=1.2011e-04) (hash(x)=25214030) +1561 train 7.178733 (lr=1.2008e-04) (hash(x)=23167825) +1562 train 7.294126 (lr=1.2004e-04) (hash(x)=24658511) +1563 train 7.446519 (lr=1.2001e-04) (hash(x)=24965435) +1564 train 7.220630 (lr=1.1997e-04) (hash(x)=23620579) +1565 train 7.206296 (lr=1.1994e-04) (hash(x)=23772949) +1566 train 7.373129 (lr=1.1990e-04) (hash(x)=23807939) +1567 train 7.579314 (lr=1.1987e-04) (hash(x)=25651929) +1568 train 7.483930 (lr=1.1983e-04) (hash(x)=25549933) +1569 train 7.227790 (lr=1.1980e-04) (hash(x)=23146724) +1570 train 7.310793 (lr=1.1976e-04) (hash(x)=24099275) +1571 train 7.531650 (lr=1.1972e-04) (hash(x)=28451031) +1572 train 7.567291 (lr=1.1969e-04) (hash(x)=25488511) +1573 train 7.341569 (lr=1.1965e-04) (hash(x)=23796771) +1574 train 7.396407 (lr=1.1962e-04) (hash(x)=22642764) +1575 train 7.508808 (lr=1.1958e-04) (hash(x)=26312387) +1576 train 7.290215 (lr=1.1955e-04) (hash(x)=22486223) +1577 train 7.256326 (lr=1.1951e-04) (hash(x)=21257377) +1578 train 7.431133 (lr=1.1948e-04) (hash(x)=24328365) +1579 train 7.503709 (lr=1.1944e-04) (hash(x)=25326650) +1580 train 7.462721 (lr=1.1941e-04) (hash(x)=26484837) +1581 train 7.239175 (lr=1.1937e-04) (hash(x)=24605603) +1582 train 7.372425 (lr=1.1933e-04) (hash(x)=24668537) +1583 train 7.278952 (lr=1.1930e-04) (hash(x)=23804913) +1584 train 7.526851 (lr=1.1926e-04) (hash(x)=23615391) +1585 train 7.489509 (lr=1.1923e-04) (hash(x)=24322926) +1586 train 7.233762 (lr=1.1919e-04) (hash(x)=19753104) +1587 train 7.718683 (lr=1.1916e-04) (hash(x)=25537529) +1588 train 7.136650 (lr=1.1912e-04) (hash(x)=22835476) +1589 train 7.283039 (lr=1.1909e-04) (hash(x)=25707197) +1590 train 7.300377 (lr=1.1905e-04) (hash(x)=24191203) +1591 train 7.562994 (lr=1.1901e-04) (hash(x)=26115519) +1592 train 7.446285 (lr=1.1898e-04) (hash(x)=25781547) +1593 train 7.243593 (lr=1.1894e-04) (hash(x)=24850654) +1594 train 7.181779 (lr=1.1891e-04) (hash(x)=23300928) +1595 train 7.413176 (lr=1.1887e-04) (hash(x)=25494804) +1596 train 7.421803 (lr=1.1884e-04) (hash(x)=28169410) +1597 train 7.188301 (lr=1.1880e-04) (hash(x)=21972022) +1598 train 7.727203 (lr=1.1876e-04) (hash(x)=27687290) +1599 train 7.647044 (lr=1.1873e-04) (hash(x)=23210747) +1600 val loss 7.4281 +1600 val perplexity 1682.5236 +1600 train 7.635063 (lr=1.1869e-04) (hash(x)=20362758) +1601 train 7.440701 (lr=1.1866e-04) (hash(x)=17064773) +1602 train 7.473512 (lr=1.1862e-04) (hash(x)=17173694) +1603 train 7.500947 (lr=1.1859e-04) (hash(x)=15717069) +1604 train 7.593045 (lr=1.1855e-04) (hash(x)=15117973) +1605 train 7.387643 (lr=1.1851e-04) (hash(x)=16189636) +1606 train 7.338468 (lr=1.1848e-04) (hash(x)=16552095) +1607 train 7.201437 (lr=1.1844e-04) (hash(x)=18463712) +1608 train 7.381720 (lr=1.1841e-04) (hash(x)=17572155) +1609 train 7.350141 (lr=1.1837e-04) (hash(x)=19970072) +1610 train 7.350030 (lr=1.1833e-04) (hash(x)=20463871) +1611 train 7.427113 (lr=1.1830e-04) (hash(x)=20705573) +1612 train 7.241132 (lr=1.1826e-04) (hash(x)=24441646) +1613 train 7.433567 (lr=1.1823e-04) (hash(x)=22913147) +1614 train 7.606598 (lr=1.1819e-04) (hash(x)=23081598) +1615 train 7.313326 (lr=1.1815e-04) (hash(x)=23245699) +1616 train 7.307073 (lr=1.1812e-04) (hash(x)=23003072) +1617 train 7.617618 (lr=1.1808e-04) (hash(x)=27121904) +1618 train 7.339907 (lr=1.1805e-04) (hash(x)=25092305) +1619 train 7.429256 (lr=1.1801e-04) (hash(x)=23444521) +1620 train 7.433240 (lr=1.1797e-04) (hash(x)=22130531) +1621 train 7.210843 (lr=1.1794e-04) (hash(x)=20917937) +1622 train 7.301886 (lr=1.1790e-04) (hash(x)=22526838) +1623 train 7.396553 (lr=1.1787e-04) (hash(x)=21770300) +1624 train 8.536476 (lr=1.1783e-04) (hash(x)=22333537) +1625 train 8.579727 (lr=1.1779e-04) (hash(x)=24642519) +1626 train 7.696256 (lr=1.1776e-04) (hash(x)=25199038) +1627 train 7.453325 (lr=1.1772e-04) (hash(x)=23334569) +1628 train 7.296014 (lr=1.1768e-04) (hash(x)=23785360) +1629 train 6.960581 (lr=1.1765e-04) (hash(x)=21796200) +1630 train 7.033516 (lr=1.1761e-04) (hash(x)=22389081) +1631 train 7.333315 (lr=1.1758e-04) (hash(x)=25387532) +1632 train 6.898769 (lr=1.1754e-04) (hash(x)=17247578) +1633 train 7.259026 (lr=1.1750e-04) (hash(x)=22203733) +1634 train 7.478047 (lr=1.1747e-04) (hash(x)=24387455) +1635 train 7.989321 (lr=1.1743e-04) (hash(x)=29466743) +1636 train 7.345792 (lr=1.1739e-04) (hash(x)=25354152) +1637 train 7.389276 (lr=1.1736e-04) (hash(x)=21756102) +1638 train 7.393373 (lr=1.1732e-04) (hash(x)=23544029) +1639 train 7.507965 (lr=1.1729e-04) (hash(x)=27718703) +1640 train 7.486885 (lr=1.1725e-04) (hash(x)=25697138) +1641 train 7.290452 (lr=1.1721e-04) (hash(x)=22978681) +1642 train 7.851243 (lr=1.1718e-04) (hash(x)=29527067) +1643 train 6.941371 (lr=1.1714e-04) (hash(x)=17631973) +1644 train 7.362671 (lr=1.1710e-04) (hash(x)=24860172) +1645 train 7.697567 (lr=1.1707e-04) (hash(x)=27947891) +1646 train 7.370258 (lr=1.1703e-04) (hash(x)=23819556) +1647 train 7.435410 (lr=1.1699e-04) (hash(x)=27661052) +1648 train 7.212776 (lr=1.1696e-04) (hash(x)=23014209) +1649 train 7.135118 (lr=1.1692e-04) (hash(x)=23061452) +1650 val loss 7.3988 +1650 val perplexity 1634.0044 +1650 train 7.264283 (lr=1.1688e-04) (hash(x)=21949051) +1651 train 7.323706 (lr=1.1685e-04) (hash(x)=22244096) +1652 train 7.305962 (lr=1.1681e-04) (hash(x)=25997585) +1653 train 7.373450 (lr=1.1678e-04) (hash(x)=25389713) +1654 train 7.325694 (lr=1.1674e-04) (hash(x)=24390520) +1655 train 7.560370 (lr=1.1670e-04) (hash(x)=26538928) +1656 train 7.462831 (lr=1.1667e-04) (hash(x)=28708088) +1657 train 7.593943 (lr=1.1663e-04) (hash(x)=25685569) +1658 train 7.151817 (lr=1.1659e-04) (hash(x)=22163531) +1659 train 7.294228 (lr=1.1656e-04) (hash(x)=26256802) +1660 train 7.746788 (lr=1.1652e-04) (hash(x)=30016026) +1661 train 7.342276 (lr=1.1648e-04) (hash(x)=24412323) +1662 train 7.420722 (lr=1.1645e-04) (hash(x)=24722307) +1663 train 7.291154 (lr=1.1641e-04) (hash(x)=21772654) +1664 train 7.228065 (lr=1.1637e-04) (hash(x)=24984527) +1665 train 7.343317 (lr=1.1634e-04) (hash(x)=25456825) +1666 train 7.710681 (lr=1.1630e-04) (hash(x)=24383976) +1667 train 7.637181 (lr=1.1626e-04) (hash(x)=25026277) +1668 train 7.547890 (lr=1.1623e-04) (hash(x)=28121715) +1669 train 7.545713 (lr=1.1619e-04) (hash(x)=26855439) +1670 train 7.620584 (lr=1.1615e-04) (hash(x)=33370924) +1671 train 7.486467 (lr=1.1612e-04) (hash(x)=26263254) +1672 train 7.942975 (lr=1.1608e-04) (hash(x)=29958158) +1673 train 7.200679 (lr=1.1604e-04) (hash(x)=21917396) +1674 train 7.344711 (lr=1.1600e-04) (hash(x)=24196295) +1675 train 7.381232 (lr=1.1597e-04) (hash(x)=24726314) +1676 train 7.224429 (lr=1.1593e-04) (hash(x)=22137742) +1677 train 7.336402 (lr=1.1589e-04) (hash(x)=24375100) +1678 train 7.308540 (lr=1.1586e-04) (hash(x)=23965039) +1679 train 7.363567 (lr=1.1582e-04) (hash(x)=23552356) +1680 train 7.309779 (lr=1.1578e-04) (hash(x)=26136969) +1681 train 7.513225 (lr=1.1575e-04) (hash(x)=25343112) +1682 train 7.242959 (lr=1.1571e-04) (hash(x)=22831508) +1683 train 7.512999 (lr=1.1567e-04) (hash(x)=26699819) +1684 train 7.597174 (lr=1.1564e-04) (hash(x)=25435504) +1685 train 7.764562 (lr=1.1560e-04) (hash(x)=25218858) +1686 train 8.355402 (lr=1.1556e-04) (hash(x)=25664448) +1687 train 7.429765 (lr=1.1552e-04) (hash(x)=22707141) +1688 train 7.589557 (lr=1.1549e-04) (hash(x)=28001383) +1689 train 7.819275 (lr=1.1545e-04) (hash(x)=29168269) +1690 train 7.776939 (lr=1.1541e-04) (hash(x)=29637522) +1691 train 7.794312 (lr=1.1538e-04) (hash(x)=25676149) +1692 train 7.281235 (lr=1.1534e-04) (hash(x)=20919831) +1693 train 7.464008 (lr=1.1530e-04) (hash(x)=24324401) +1694 train 7.513361 (lr=1.1527e-04) (hash(x)=26862625) +1695 train 7.892647 (lr=1.1523e-04) (hash(x)=34234481) +1696 train 7.484833 (lr=1.1519e-04) (hash(x)=27415195) +1697 train 7.294934 (lr=1.1515e-04) (hash(x)=24511386) +1698 train 7.430464 (lr=1.1512e-04) (hash(x)=26904299) +1699 train 7.277593 (lr=1.1508e-04) (hash(x)=25401624) +1700 val loss 7.3968 +1700 val perplexity 1630.6917 +1700 train 7.350231 (lr=1.1504e-04) (hash(x)=26498489) +1701 train 7.340689 (lr=1.1501e-04) (hash(x)=22340685) +1702 train 7.426971 (lr=1.1497e-04) (hash(x)=26396757) +1703 train 8.041110 (lr=1.1493e-04) (hash(x)=35008670) +1704 train 7.802459 (lr=1.1489e-04) (hash(x)=31782020) +1705 train 7.676376 (lr=1.1486e-04) (hash(x)=29662286) +1706 train 7.825070 (lr=1.1482e-04) (hash(x)=34215782) +1707 train 7.274687 (lr=1.1478e-04) (hash(x)=25682280) +1708 train 7.533119 (lr=1.1475e-04) (hash(x)=27109048) +1709 train 7.555225 (lr=1.1471e-04) (hash(x)=27686498) +1710 train 7.342243 (lr=1.1467e-04) (hash(x)=24247565) +1711 train 7.384614 (lr=1.1463e-04) (hash(x)=25891543) +1712 train 7.481702 (lr=1.1460e-04) (hash(x)=26436778) +1713 train 7.135394 (lr=1.1456e-04) (hash(x)=22538881) +1714 train 7.104913 (lr=1.1452e-04) (hash(x)=21993512) +1715 train 7.622174 (lr=1.1448e-04) (hash(x)=25962407) +1716 train 7.392452 (lr=1.1445e-04) (hash(x)=24130284) +1717 train 7.266653 (lr=1.1441e-04) (hash(x)=24819073) +1718 train 7.144164 (lr=1.1437e-04) (hash(x)=23496648) +1719 train 7.211261 (lr=1.1433e-04) (hash(x)=21971224) +1720 train 7.090213 (lr=1.1430e-04) (hash(x)=21498081) +1721 train 7.162414 (lr=1.1426e-04) (hash(x)=20951317) +1722 train 7.665373 (lr=1.1422e-04) (hash(x)=28848134) +1723 train 7.690320 (lr=1.1418e-04) (hash(x)=30838142) +1724 train 7.649536 (lr=1.1415e-04) (hash(x)=28844392) +1725 train 7.307868 (lr=1.1411e-04) (hash(x)=23102419) +1726 train 7.370964 (lr=1.1407e-04) (hash(x)=22374479) +1727 train 7.621452 (lr=1.1403e-04) (hash(x)=27312186) +1728 train 7.978178 (lr=1.1400e-04) (hash(x)=34362559) +1729 train 7.910411 (lr=1.1396e-04) (hash(x)=30920030) +1730 train 7.262294 (lr=1.1392e-04) (hash(x)=23684126) +1731 train 7.491306 (lr=1.1388e-04) (hash(x)=23657081) +1732 train 7.682533 (lr=1.1385e-04) (hash(x)=28463299) +1733 train 7.935516 (lr=1.1381e-04) (hash(x)=35351214) +1734 train 7.518404 (lr=1.1377e-04) (hash(x)=28855662) +1735 train 7.033886 (lr=1.1373e-04) (hash(x)=22163749) +1736 train 7.029210 (lr=1.1370e-04) (hash(x)=22024585) +1737 train 7.205504 (lr=1.1366e-04) (hash(x)=24629160) +1738 train 7.301190 (lr=1.1362e-04) (hash(x)=25220941) +1739 train 7.237943 (lr=1.1358e-04) (hash(x)=24829818) +1740 train 7.609415 (lr=1.1355e-04) (hash(x)=28453898) +1741 train 7.651279 (lr=1.1351e-04) (hash(x)=25424550) +1742 train 7.315097 (lr=1.1347e-04) (hash(x)=23437814) +1743 train 7.386987 (lr=1.1343e-04) (hash(x)=25942888) +1744 train 7.376996 (lr=1.1340e-04) (hash(x)=24503801) +1745 train 7.688953 (lr=1.1336e-04) (hash(x)=26418501) +1746 train 7.531464 (lr=1.1332e-04) (hash(x)=27177691) +1747 train 7.271871 (lr=1.1328e-04) (hash(x)=23785671) +1748 train 7.639530 (lr=1.1324e-04) (hash(x)=27362772) +1749 train 7.447723 (lr=1.1321e-04) (hash(x)=25097859) +1750 val loss 7.4084 +1750 val perplexity 1649.7863 +1750 train 7.356607 (lr=1.1317e-04) (hash(x)=24662466) +1751 train 7.302152 (lr=1.1313e-04) (hash(x)=25493916) +1752 train 7.420320 (lr=1.1309e-04) (hash(x)=24655868) +1753 train 7.654415 (lr=1.1306e-04) (hash(x)=19819210) +1754 train 7.264546 (lr=1.1302e-04) (hash(x)=21377155) +1755 train 8.024286 (lr=1.1298e-04) (hash(x)=28618702) +1756 train 7.955411 (lr=1.1294e-04) (hash(x)=27324953) +1757 train 7.685131 (lr=1.1290e-04) (hash(x)=29707907) +1758 train 7.476586 (lr=1.1287e-04) (hash(x)=24485921) +1759 train 7.522160 (lr=1.1283e-04) (hash(x)=24289951) +1760 train 7.254822 (lr=1.1279e-04) (hash(x)=22496716) +1761 train 7.374768 (lr=1.1275e-04) (hash(x)=25147026) +1762 train 7.470129 (lr=1.1271e-04) (hash(x)=26851828) +1763 train 7.439540 (lr=1.1268e-04) (hash(x)=26331486) +1764 train 7.277170 (lr=1.1264e-04) (hash(x)=24383054) +1765 train 7.527076 (lr=1.1260e-04) (hash(x)=25885126) +1766 train 7.455209 (lr=1.1256e-04) (hash(x)=25848470) +1767 train 7.257661 (lr=1.1252e-04) (hash(x)=23648671) +1768 train 7.237803 (lr=1.1249e-04) (hash(x)=23168674) +1769 train 7.063785 (lr=1.1245e-04) (hash(x)=20252079) +1770 train 7.284022 (lr=1.1241e-04) (hash(x)=23914287) +1771 train 7.606546 (lr=1.1237e-04) (hash(x)=27292797) +1772 train 6.800131 (lr=1.1233e-04) (hash(x)=16175151) +1773 train 6.941550 (lr=1.1230e-04) (hash(x)=18317379) +1774 train 7.323717 (lr=1.1226e-04) (hash(x)=24464271) +1775 train 7.298862 (lr=1.1222e-04) (hash(x)=24992055) +1776 train 7.978066 (lr=1.1218e-04) (hash(x)=26032451) +1777 train 7.713927 (lr=1.1214e-04) (hash(x)=24734221) +1778 train 7.681427 (lr=1.1211e-04) (hash(x)=25413430) +1779 train 7.550447 (lr=1.1207e-04) (hash(x)=24398330) +1780 train 7.364053 (lr=1.1203e-04) (hash(x)=24568049) +1781 train 7.270799 (lr=1.1199e-04) (hash(x)=23573984) +1782 train 7.481663 (lr=1.1195e-04) (hash(x)=27338410) +1783 train 7.409811 (lr=1.1192e-04) (hash(x)=26005549) +1784 train 7.307191 (lr=1.1188e-04) (hash(x)=24332331) +1785 train 7.160624 (lr=1.1184e-04) (hash(x)=22583878) +1786 train 7.309691 (lr=1.1180e-04) (hash(x)=24599113) +1787 train 7.752579 (lr=1.1176e-04) (hash(x)=30259737) +1788 train 7.523580 (lr=1.1172e-04) (hash(x)=26504237) +1789 train 7.378599 (lr=1.1169e-04) (hash(x)=25196470) +1790 train 7.281240 (lr=1.1165e-04) (hash(x)=23607871) +1791 train 7.205208 (lr=1.1161e-04) (hash(x)=21046554) +1792 train 7.471636 (lr=1.1157e-04) (hash(x)=27285635) +1793 train 7.397856 (lr=1.1153e-04) (hash(x)=25454371) +1794 train 7.496049 (lr=1.1149e-04) (hash(x)=26486575) +1795 train 6.948648 (lr=1.1146e-04) (hash(x)=18773877) +1796 train 7.143731 (lr=1.1142e-04) (hash(x)=22506761) +1797 train 7.389463 (lr=1.1138e-04) (hash(x)=24645168) +1798 train 7.475807 (lr=1.1134e-04) (hash(x)=25046236) +1799 train 7.539697 (lr=1.1130e-04) (hash(x)=26321539) +1800 val loss 7.3815 +1800 val perplexity 1605.9622 +1800 train 7.324619 (lr=1.1126e-04) (hash(x)=24602494) +1801 train 7.495004 (lr=1.1123e-04) (hash(x)=25722713) +1802 train 7.248503 (lr=1.1119e-04) (hash(x)=23711219) +1803 train 7.379682 (lr=1.1115e-04) (hash(x)=22850804) +1804 train 7.714680 (lr=1.1111e-04) (hash(x)=25829388) +1805 train 7.232870 (lr=1.1107e-04) (hash(x)=22503524) +1806 train 7.496661 (lr=1.1103e-04) (hash(x)=26669453) +1807 train 7.417316 (lr=1.1100e-04) (hash(x)=27807872) +1808 train 7.427294 (lr=1.1096e-04) (hash(x)=23543560) +1809 train 7.558309 (lr=1.1092e-04) (hash(x)=25845590) +1810 train 7.337902 (lr=1.1088e-04) (hash(x)=23026635) +1811 train 7.305795 (lr=1.1084e-04) (hash(x)=25545137) +1812 train 7.785781 (lr=1.1080e-04) (hash(x)=27746841) +1813 train 7.186246 (lr=1.1076e-04) (hash(x)=25471231) +1814 train 7.329726 (lr=1.1073e-04) (hash(x)=24333204) +1815 train 7.146733 (lr=1.1069e-04) (hash(x)=21555364) +1816 train 7.393655 (lr=1.1065e-04) (hash(x)=26317977) +1817 train 7.418979 (lr=1.1061e-04) (hash(x)=24474988) +1818 train 7.144346 (lr=1.1057e-04) (hash(x)=21975953) +1819 train 7.748178 (lr=1.1053e-04) (hash(x)=27243798) +1820 train 7.351134 (lr=1.1049e-04) (hash(x)=25097367) +1821 train 7.303516 (lr=1.1046e-04) (hash(x)=24419085) +1822 train 7.227935 (lr=1.1042e-04) (hash(x)=23058837) +1823 train 7.381330 (lr=1.1038e-04) (hash(x)=26325324) +1824 train 7.108229 (lr=1.1034e-04) (hash(x)=20581023) +1825 train 7.457311 (lr=1.1030e-04) (hash(x)=24822111) +1826 train 7.266053 (lr=1.1026e-04) (hash(x)=24336304) +1827 train 7.436182 (lr=1.1022e-04) (hash(x)=26228728) +1828 train 7.555428 (lr=1.1019e-04) (hash(x)=26445781) +1829 train 7.570097 (lr=1.1015e-04) (hash(x)=24707042) +1830 train 7.860667 (lr=1.1011e-04) (hash(x)=27882744) +1831 train 7.358232 (lr=1.1007e-04) (hash(x)=24956294) +1832 train 7.196163 (lr=1.1003e-04) (hash(x)=20984728) +1833 train 7.158372 (lr=1.0999e-04) (hash(x)=23424737) +1834 train 7.601148 (lr=1.0995e-04) (hash(x)=26207120) +1835 train 7.597507 (lr=1.0991e-04) (hash(x)=25592289) +1836 train 7.271778 (lr=1.0988e-04) (hash(x)=24326649) +1837 train 7.424682 (lr=1.0984e-04) (hash(x)=26826109) +1838 train 7.397086 (lr=1.0980e-04) (hash(x)=24759294) +1839 train 7.416074 (lr=1.0976e-04) (hash(x)=24429389) +1840 train 7.365057 (lr=1.0972e-04) (hash(x)=25537519) +1841 train 7.370565 (lr=1.0968e-04) (hash(x)=24747421) +1842 train 7.266316 (lr=1.0964e-04) (hash(x)=23079065) +1843 train 7.657660 (lr=1.0960e-04) (hash(x)=28733708) +1844 train 7.385515 (lr=1.0957e-04) (hash(x)=23937742) +1845 train 7.665897 (lr=1.0953e-04) (hash(x)=29704803) +1846 train 7.860957 (lr=1.0949e-04) (hash(x)=34617155) +1847 train 7.563323 (lr=1.0945e-04) (hash(x)=27929846) +1848 train 7.910157 (lr=1.0941e-04) (hash(x)=28280878) +1849 train 6.961854 (lr=1.0937e-04) (hash(x)=18961171) +1850 val loss 7.4319 +1850 val perplexity 1688.9646 +1850 train 7.532724 (lr=1.0933e-04) (hash(x)=27146015) +1851 train 7.305795 (lr=1.0929e-04) (hash(x)=22417476) +1852 train 7.461530 (lr=1.0925e-04) (hash(x)=24583152) +1853 train 7.517107 (lr=1.0922e-04) (hash(x)=26364120) +1854 train 7.672507 (lr=1.0918e-04) (hash(x)=25946767) +1855 train 7.501555 (lr=1.0914e-04) (hash(x)=25282897) +1856 train 7.467746 (lr=1.0910e-04) (hash(x)=25154557) +1857 train 7.168018 (lr=1.0906e-04) (hash(x)=22082503) +1858 train 7.202104 (lr=1.0902e-04) (hash(x)=23974606) +1859 train 7.339479 (lr=1.0898e-04) (hash(x)=22278062) +1860 train 7.246524 (lr=1.0894e-04) (hash(x)=19509639) +1861 train 7.528286 (lr=1.0890e-04) (hash(x)=24271468) +1862 train 7.140715 (lr=1.0886e-04) (hash(x)=21943809) +1863 train 7.346068 (lr=1.0883e-04) (hash(x)=26802508) +1864 train 7.992504 (lr=1.0879e-04) (hash(x)=34178409) +1865 train 8.062012 (lr=1.0875e-04) (hash(x)=33468379) +1866 train 7.212037 (lr=1.0871e-04) (hash(x)=22109262) +1867 train 6.992326 (lr=1.0867e-04) (hash(x)=22094832) +1868 train 7.230770 (lr=1.0863e-04) (hash(x)=24016953) +1869 train 7.520013 (lr=1.0859e-04) (hash(x)=26759850) +1870 train 7.366573 (lr=1.0855e-04) (hash(x)=23570779) +1871 train 7.777990 (lr=1.0851e-04) (hash(x)=28390416) +1872 train 7.775998 (lr=1.0847e-04) (hash(x)=26215770) +1873 train 7.649405 (lr=1.0843e-04) (hash(x)=22727956) +1874 train 7.475442 (lr=1.0839e-04) (hash(x)=21304587) +1875 train 7.752051 (lr=1.0836e-04) (hash(x)=26379331) +1876 train 7.826482 (lr=1.0832e-04) (hash(x)=25252419) +1877 train 7.669914 (lr=1.0828e-04) (hash(x)=25048158) +1878 train 7.615564 (lr=1.0824e-04) (hash(x)=23588991) +1879 train 7.588909 (lr=1.0820e-04) (hash(x)=26292451) +1880 train 7.499691 (lr=1.0816e-04) (hash(x)=23617086) +1881 train 7.346234 (lr=1.0812e-04) (hash(x)=23336031) +1882 train 7.357330 (lr=1.0808e-04) (hash(x)=19198742) +1883 train 8.038634 (lr=1.0804e-04) (hash(x)=26301866) +1884 train 8.009272 (lr=1.0800e-04) (hash(x)=30114703) +1885 train 7.527023 (lr=1.0796e-04) (hash(x)=26687040) +1886 train 7.357300 (lr=1.0792e-04) (hash(x)=25810717) +1887 train 7.174379 (lr=1.0788e-04) (hash(x)=22915344) +1888 train 7.523078 (lr=1.0785e-04) (hash(x)=27046189) +1889 train 7.090252 (lr=1.0781e-04) (hash(x)=19831900) +1890 train 7.515630 (lr=1.0777e-04) (hash(x)=27786987) +1891 train 7.377272 (lr=1.0773e-04) (hash(x)=25448318) +1892 train 7.386625 (lr=1.0769e-04) (hash(x)=25166953) +1893 train 7.360980 (lr=1.0765e-04) (hash(x)=24993116) +1894 train 7.448570 (lr=1.0761e-04) (hash(x)=25748002) +1895 train 7.618996 (lr=1.0757e-04) (hash(x)=24744383) +1896 train 7.380989 (lr=1.0753e-04) (hash(x)=25560120) +1897 train 7.221449 (lr=1.0749e-04) (hash(x)=23731849) +1898 train 7.254494 (lr=1.0745e-04) (hash(x)=24115851) +1899 train 7.253841 (lr=1.0741e-04) (hash(x)=22835201) +1900 val loss 7.3973 +1900 val perplexity 1631.5620 +1900 train 7.050176 (lr=1.0737e-04) (hash(x)=21927896) +1901 train 7.414597 (lr=1.0733e-04) (hash(x)=24652361) +1902 train 7.591608 (lr=1.0729e-04) (hash(x)=27332405) +1903 train 7.418861 (lr=1.0725e-04) (hash(x)=26284678) +1904 train 7.349882 (lr=1.0722e-04) (hash(x)=23441305) +1905 train 7.466425 (lr=1.0718e-04) (hash(x)=27522881) +1906 train 7.509748 (lr=1.0714e-04) (hash(x)=25521191) +1907 train 7.286962 (lr=1.0710e-04) (hash(x)=24745936) +1908 train 7.181015 (lr=1.0706e-04) (hash(x)=21653364) +1909 train 7.238232 (lr=1.0702e-04) (hash(x)=21973969) +1910 train 7.248767 (lr=1.0698e-04) (hash(x)=24318192) +1911 train 7.194219 (lr=1.0694e-04) (hash(x)=21654269) +1912 train 7.248169 (lr=1.0690e-04) (hash(x)=24142904) +1913 train 7.158419 (lr=1.0686e-04) (hash(x)=21708739) +1914 train 7.351564 (lr=1.0682e-04) (hash(x)=22937923) +1915 train 7.946372 (lr=1.0678e-04) (hash(x)=32387999) +1916 train 8.151013 (lr=1.0674e-04) (hash(x)=28958671) +1917 train 8.210380 (lr=1.0670e-04) (hash(x)=32662682) +1918 train 8.108093 (lr=1.0666e-04) (hash(x)=31364539) +1919 train 8.148200 (lr=1.0662e-04) (hash(x)=29466268) +1920 train 8.141627 (lr=1.0658e-04) (hash(x)=31407564) +1921 train 7.959444 (lr=1.0654e-04) (hash(x)=28372973) +1922 train 8.046938 (lr=1.0650e-04) (hash(x)=28620993) +1923 train 8.100509 (lr=1.0646e-04) (hash(x)=30736727) +1924 train 8.011192 (lr=1.0642e-04) (hash(x)=30370374) +1925 train 7.981196 (lr=1.0638e-04) (hash(x)=29935562) +1926 train 7.977039 (lr=1.0634e-04) (hash(x)=30528627) +1927 train 8.019409 (lr=1.0630e-04) (hash(x)=32616762) +1928 train 7.845783 (lr=1.0626e-04) (hash(x)=29150044) +1929 train 8.049548 (lr=1.0623e-04) (hash(x)=32861403) +1930 train 7.986929 (lr=1.0619e-04) (hash(x)=31053918) +1931 train 7.895116 (lr=1.0615e-04) (hash(x)=29358578) +1932 train 7.971628 (lr=1.0611e-04) (hash(x)=31521292) +1933 train 7.913160 (lr=1.0607e-04) (hash(x)=31218966) +1934 train 7.941018 (lr=1.0603e-04) (hash(x)=31811872) +1935 train 8.089554 (lr=1.0599e-04) (hash(x)=32201138) +1936 train 7.839227 (lr=1.0595e-04) (hash(x)=28631348) +1937 train 7.949854 (lr=1.0591e-04) (hash(x)=30545133) +1938 train 8.007855 (lr=1.0587e-04) (hash(x)=32136080) +1939 train 8.108443 (lr=1.0583e-04) (hash(x)=30041621) +1940 train 7.843362 (lr=1.0579e-04) (hash(x)=30537181) +1941 train 7.888524 (lr=1.0575e-04) (hash(x)=30371023) +1942 train 8.040806 (lr=1.0571e-04) (hash(x)=30734634) +1943 train 7.938922 (lr=1.0567e-04) (hash(x)=33683468) +1944 train 7.961653 (lr=1.0563e-04) (hash(x)=30472451) +1945 train 7.797613 (lr=1.0559e-04) (hash(x)=29809830) +1946 train 7.548700 (lr=1.0555e-04) (hash(x)=26077593) +1947 train 7.526877 (lr=1.0551e-04) (hash(x)=26837755) +1948 train 7.482526 (lr=1.0547e-04) (hash(x)=23910920) +1949 train 7.479454 (lr=1.0543e-04) (hash(x)=26084089) +1950 val loss 7.4459 +1950 val perplexity 1712.7975 +1950 train 7.653841 (lr=1.0539e-04) (hash(x)=26963533) +1951 train 7.499066 (lr=1.0535e-04) (hash(x)=27498125) +1952 train 7.719326 (lr=1.0531e-04) (hash(x)=29512508) +1953 train 7.940115 (lr=1.0527e-04) (hash(x)=34478395) +1954 train 7.590965 (lr=1.0523e-04) (hash(x)=25357046) +1955 train 7.379978 (lr=1.0519e-04) (hash(x)=22372507) +1956 train 7.368619 (lr=1.0515e-04) (hash(x)=24501779) +1957 train 7.407952 (lr=1.0511e-04) (hash(x)=25638879) +1958 train 7.281343 (lr=1.0507e-04) (hash(x)=24243109) +1959 train 7.210342 (lr=1.0503e-04) (hash(x)=25164318) +1960 train 7.404003 (lr=1.0499e-04) (hash(x)=24139533) +1961 train 7.376461 (lr=1.0495e-04) (hash(x)=27271900) +1962 train 7.248793 (lr=1.0491e-04) (hash(x)=24869232) +1963 train 7.427904 (lr=1.0487e-04) (hash(x)=26562947) +1964 train 7.345430 (lr=1.0483e-04) (hash(x)=26477326) +1965 train 7.419292 (lr=1.0479e-04) (hash(x)=24917192) +1966 train 7.236721 (lr=1.0475e-04) (hash(x)=23110147) +1967 train 7.289176 (lr=1.0471e-04) (hash(x)=25690221) +1968 train 7.756865 (lr=1.0467e-04) (hash(x)=26999273) +1969 train 7.401392 (lr=1.0463e-04) (hash(x)=24807841) +1970 train 7.286912 (lr=1.0459e-04) (hash(x)=23918831) +1971 train 7.225269 (lr=1.0455e-04) (hash(x)=21947305) +1972 train 7.298510 (lr=1.0451e-04) (hash(x)=22874486) +1973 train 7.209151 (lr=1.0447e-04) (hash(x)=22195089) +1974 train 7.337409 (lr=1.0443e-04) (hash(x)=25345359) +1975 train 7.488609 (lr=1.0439e-04) (hash(x)=29031550) +1976 train 7.460416 (lr=1.0435e-04) (hash(x)=29947423) +1977 train 7.599735 (lr=1.0431e-04) (hash(x)=29395823) +1978 train 7.426038 (lr=1.0427e-04) (hash(x)=26968216) +1979 train 7.448195 (lr=1.0423e-04) (hash(x)=26551589) +1980 train 7.433113 (lr=1.0419e-04) (hash(x)=25657210) +1981 train 7.378788 (lr=1.0415e-04) (hash(x)=23689487) +1982 train 7.479215 (lr=1.0411e-04) (hash(x)=25744240) +1983 train 7.430409 (lr=1.0407e-04) (hash(x)=24094093) +1984 train 7.167535 (lr=1.0403e-04) (hash(x)=21724872) +1985 train 7.250488 (lr=1.0399e-04) (hash(x)=24106453) +1986 train 7.293124 (lr=1.0395e-04) (hash(x)=25004577) +1987 train 7.350998 (lr=1.0391e-04) (hash(x)=23639076) +1988 train 7.595342 (lr=1.0387e-04) (hash(x)=29408797) +1989 train 7.245619 (lr=1.0383e-04) (hash(x)=25107314) +1990 train 9.817937 (lr=1.0379e-04) (hash(x)=49896019) +1991 train 11.302287 (lr=1.0375e-04) (hash(x)=61455960) +1992 train 11.115102 (lr=1.0371e-04) (hash(x)=63788199) +1993 train 11.141125 (lr=1.0367e-04) (hash(x)=63899424) +1994 train 10.773309 (lr=1.0362e-04) (hash(x)=66412689) +1995 train 10.306698 (lr=1.0358e-04) (hash(x)=65636572) +1996 train 10.357950 (lr=1.0354e-04) (hash(x)=69649789) +1997 train 10.044540 (lr=1.0350e-04) (hash(x)=71578682) +1998 train 9.269302 (lr=1.0346e-04) (hash(x)=58341730) +1999 train 9.268562 (lr=1.0342e-04) (hash(x)=61104710) +2000 val loss 8.0997 +2000 val perplexity 3293.3416 +2000 train 8.831749 (lr=1.0338e-04) (hash(x)=52865322) +2001 train 8.235967 (lr=1.0334e-04) (hash(x)=23633693) +2002 train 8.201082 (lr=1.0330e-04) (hash(x)=25297571) +2003 train 8.475847 (lr=1.0326e-04) (hash(x)=24123821) +2004 train 7.940666 (lr=1.0322e-04) (hash(x)=20161517) +2005 train 7.864331 (lr=1.0318e-04) (hash(x)=19919984) +2006 train 7.860757 (lr=1.0314e-04) (hash(x)=18626507) +2007 train 8.078208 (lr=1.0310e-04) (hash(x)=20881126) +2008 train 8.365190 (lr=1.0306e-04) (hash(x)=26261448) +2009 train 8.429162 (lr=1.0302e-04) (hash(x)=27528050) +2010 train 8.436095 (lr=1.0298e-04) (hash(x)=26692097) +2011 train 8.042285 (lr=1.0294e-04) (hash(x)=23209969) +2012 train 8.056134 (lr=1.0290e-04) (hash(x)=26083446) +2013 train 8.165975 (lr=1.0286e-04) (hash(x)=28426467) +2014 train 7.877561 (lr=1.0282e-04) (hash(x)=26158154) +2015 train 7.901224 (lr=1.0278e-04) (hash(x)=26920243) +2016 train 7.580666 (lr=1.0274e-04) (hash(x)=21365321) +2017 train 7.576440 (lr=1.0270e-04) (hash(x)=25730699) +2018 train 7.647831 (lr=1.0266e-04) (hash(x)=25177106) +2019 train 7.529103 (lr=1.0261e-04) (hash(x)=26127756) +2020 train 7.105080 (lr=1.0257e-04) (hash(x)=19770037) +2021 train 7.472258 (lr=1.0253e-04) (hash(x)=26479346) +2022 train 7.483359 (lr=1.0249e-04) (hash(x)=25967643) +2023 train 7.393511 (lr=1.0245e-04) (hash(x)=21970343) +2024 train 7.599912 (lr=1.0241e-04) (hash(x)=26449648) +2025 train 7.511081 (lr=1.0237e-04) (hash(x)=24874094) +2026 train 7.161884 (lr=1.0233e-04) (hash(x)=21399697) +2027 train 7.347304 (lr=1.0229e-04) (hash(x)=24097897) +2028 train 7.399956 (lr=1.0225e-04) (hash(x)=24453548) +2029 train 7.539699 (lr=1.0221e-04) (hash(x)=26692093) +2030 train 7.337989 (lr=1.0217e-04) (hash(x)=27217002) +2031 train 7.708220 (lr=1.0213e-04) (hash(x)=31676352) +2032 train 7.407516 (lr=1.0209e-04) (hash(x)=23396350) +2033 train 7.414946 (lr=1.0205e-04) (hash(x)=26245173) +2034 train 7.451392 (lr=1.0201e-04) (hash(x)=24821033) +2035 train 7.473209 (lr=1.0197e-04) (hash(x)=23908053) +2036 train 7.260132 (lr=1.0193e-04) (hash(x)=23469373) +2037 train 7.320358 (lr=1.0188e-04) (hash(x)=24102198) +2038 train 7.328412 (lr=1.0184e-04) (hash(x)=24712135) +2039 train 7.580695 (lr=1.0180e-04) (hash(x)=25600562) +2040 train 7.492275 (lr=1.0176e-04) (hash(x)=23193393) +2041 train 7.460467 (lr=1.0172e-04) (hash(x)=24776954) +2042 train 7.578928 (lr=1.0168e-04) (hash(x)=28066546) +2043 train 7.168851 (lr=1.0164e-04) (hash(x)=23549168) +2044 train 7.215339 (lr=1.0160e-04) (hash(x)=22681487) +2045 train 7.438732 (lr=1.0156e-04) (hash(x)=26663184) +2046 train 7.353817 (lr=1.0152e-04) (hash(x)=23320809) +2047 train 7.250806 (lr=1.0148e-04) (hash(x)=22022924) +2048 train 7.574075 (lr=1.0144e-04) (hash(x)=27960930) +2049 train 7.365772 (lr=1.0140e-04) (hash(x)=24899178) +2050 val loss 7.3839 +2050 val perplexity 1609.8279 +2050 train 7.284451 (lr=1.0136e-04) (hash(x)=24450711) +2051 train 7.251888 (lr=1.0132e-04) (hash(x)=23294980) +2052 train 7.175945 (lr=1.0127e-04) (hash(x)=23243665) +2053 train 7.078857 (lr=1.0123e-04) (hash(x)=21004461) +2054 train 7.353609 (lr=1.0119e-04) (hash(x)=24493583) +2055 train 7.271080 (lr=1.0115e-04) (hash(x)=22777085) +2056 train 7.215390 (lr=1.0111e-04) (hash(x)=25169889) +2057 train 7.883194 (lr=1.0107e-04) (hash(x)=28395880) +2058 train 7.805892 (lr=1.0103e-04) (hash(x)=29603726) +2059 train 7.430484 (lr=1.0099e-04) (hash(x)=26271115) +2060 train 7.440000 (lr=1.0095e-04) (hash(x)=25616212) +2061 train 7.508661 (lr=1.0091e-04) (hash(x)=26398325) +2062 train 7.216092 (lr=1.0087e-04) (hash(x)=23836586) +2063 train 7.124050 (lr=1.0083e-04) (hash(x)=21727744) +2064 train 7.358833 (lr=1.0078e-04) (hash(x)=25183195) +2065 train 7.489290 (lr=1.0074e-04) (hash(x)=27108132) +2066 train 7.192326 (lr=1.0070e-04) (hash(x)=20987812) +2067 train 7.502805 (lr=1.0066e-04) (hash(x)=22729318) +2068 train 7.295236 (lr=1.0062e-04) (hash(x)=23129709) +2069 train 7.811796 (lr=1.0058e-04) (hash(x)=32820084) +2070 train 7.873712 (lr=1.0054e-04) (hash(x)=33763489) +2071 train 7.325837 (lr=1.0050e-04) (hash(x)=20701998) +2072 train 7.561960 (lr=1.0046e-04) (hash(x)=27765988) +2073 train 7.288904 (lr=1.0042e-04) (hash(x)=24157446) +2074 train 7.249320 (lr=1.0038e-04) (hash(x)=22014978) +2075 train 7.771678 (lr=1.0034e-04) (hash(x)=27928398) +2076 train 7.579604 (lr=1.0029e-04) (hash(x)=27880142) +2077 train 7.892425 (lr=1.0025e-04) (hash(x)=34991795) +2078 train 7.479284 (lr=1.0021e-04) (hash(x)=25944128) +2079 train 7.240251 (lr=1.0017e-04) (hash(x)=20863982) +2080 train 7.598077 (lr=1.0013e-04) (hash(x)=28036097) +2081 train 7.616022 (lr=1.0009e-04) (hash(x)=25813615) +2082 train 7.118700 (lr=1.0005e-04) (hash(x)=22862316) +2083 train 7.136209 (lr=1.0001e-04) (hash(x)=22827054) +2084 train 7.238792 (lr=9.9967e-05) (hash(x)=23996531) +2085 train 7.353986 (lr=9.9926e-05) (hash(x)=25756087) +2086 train 7.384975 (lr=9.9885e-05) (hash(x)=23165889) +2087 train 7.570180 (lr=9.9844e-05) (hash(x)=25084926) +2088 train 7.440250 (lr=9.9803e-05) (hash(x)=26063862) +2089 train 7.469337 (lr=9.9762e-05) (hash(x)=27843638) +2090 train 7.766411 (lr=9.9721e-05) (hash(x)=27375554) +2091 train 7.473115 (lr=9.9680e-05) (hash(x)=25540961) +2092 train 7.192788 (lr=9.9639e-05) (hash(x)=22933785) +2093 train 7.384533 (lr=9.9598e-05) (hash(x)=23996956) +2094 train 7.107382 (lr=9.9557e-05) (hash(x)=22915854) +2095 train 7.359661 (lr=9.9516e-05) (hash(x)=24412897) +2096 train 7.383962 (lr=9.9475e-05) (hash(x)=25152336) +2097 train 7.719757 (lr=9.9434e-05) (hash(x)=29525589) +2098 train 7.527173 (lr=9.9393e-05) (hash(x)=26435656) +2099 train 7.421483 (lr=9.9351e-05) (hash(x)=26269869) +2100 val loss 7.3737 +2100 val perplexity 1593.5312 +2100 train 7.194501 (lr=9.9310e-05) (hash(x)=23856783) +2101 train 7.431853 (lr=9.9269e-05) (hash(x)=26039611) +2102 train 7.186737 (lr=9.9228e-05) (hash(x)=25048861) +2103 train 7.302562 (lr=9.9187e-05) (hash(x)=25434913) +2104 train 7.465055 (lr=9.9146e-05) (hash(x)=24203891) +2105 train 7.344638 (lr=9.9105e-05) (hash(x)=26016998) +2106 train 7.450940 (lr=9.9064e-05) (hash(x)=23986767) +2107 train 7.377656 (lr=9.9023e-05) (hash(x)=25157653) +2108 train 7.528691 (lr=9.8982e-05) (hash(x)=30193751) +2109 train 7.345018 (lr=9.8940e-05) (hash(x)=22630574) +2110 train 7.253259 (lr=9.8899e-05) (hash(x)=23475467) +2111 train 7.565546 (lr=9.8858e-05) (hash(x)=26302544) +2112 train 7.283401 (lr=9.8817e-05) (hash(x)=21276592) +2113 train 7.556133 (lr=9.8776e-05) (hash(x)=27566393) +2114 train 7.323655 (lr=9.8735e-05) (hash(x)=25028015) +2115 train 7.094939 (lr=9.8693e-05) (hash(x)=22010703) +2116 train 7.429109 (lr=9.8652e-05) (hash(x)=23711709) +2117 train 7.490279 (lr=9.8611e-05) (hash(x)=26105026) +2118 train 7.840956 (lr=9.8570e-05) (hash(x)=34433894) +2119 train 7.925472 (lr=9.8529e-05) (hash(x)=34976197) +2120 train 7.423210 (lr=9.8487e-05) (hash(x)=27690727) +2121 train 7.233634 (lr=9.8446e-05) (hash(x)=24368234) +2122 train 7.252357 (lr=9.8405e-05) (hash(x)=25095726) +2123 train 7.448714 (lr=9.8364e-05) (hash(x)=28248301) +2124 train 7.184233 (lr=9.8323e-05) (hash(x)=23322302) +2125 train 7.632222 (lr=9.8281e-05) (hash(x)=26416200) +2126 train 7.294836 (lr=9.8240e-05) (hash(x)=26577567) +2127 train 7.337711 (lr=9.8199e-05) (hash(x)=23870805) +2128 train 7.274705 (lr=9.8158e-05) (hash(x)=25440544) +2129 train 7.381668 (lr=9.8116e-05) (hash(x)=25795021) +2130 train 7.233645 (lr=9.8075e-05) (hash(x)=20896402) +2131 train 7.276221 (lr=9.8034e-05) (hash(x)=24457252) +2132 train 7.371114 (lr=9.7992e-05) (hash(x)=25926760) +2133 train 7.220048 (lr=9.7951e-05) (hash(x)=23503725) +2134 train 7.785652 (lr=9.7910e-05) (hash(x)=28728828) +2135 train 7.291803 (lr=9.7869e-05) (hash(x)=25041103) +2136 train 7.305321 (lr=9.7827e-05) (hash(x)=22863770) +2137 train 7.177789 (lr=9.7786e-05) (hash(x)=23037755) +2138 train 7.407183 (lr=9.7745e-05) (hash(x)=25848413) +2139 train 7.445406 (lr=9.7703e-05) (hash(x)=25998487) +2140 train 7.311095 (lr=9.7662e-05) (hash(x)=22754440) +2141 train 7.556674 (lr=9.7621e-05) (hash(x)=27705382) +2142 train 7.594612 (lr=9.7579e-05) (hash(x)=27629095) +2143 train 7.456097 (lr=9.7538e-05) (hash(x)=26041745) +2144 train 7.211261 (lr=9.7497e-05) (hash(x)=21909712) +2145 train 7.407703 (lr=9.7455e-05) (hash(x)=24353905) +2146 train 7.349496 (lr=9.7414e-05) (hash(x)=24482587) +2147 train 7.455756 (lr=9.7372e-05) (hash(x)=27249810) +2148 train 7.575392 (lr=9.7331e-05) (hash(x)=26709938) +2149 train 7.224176 (lr=9.7290e-05) (hash(x)=23831457) +2150 val loss 7.3500 +2150 val perplexity 1556.1652 +2150 train 7.633470 (lr=9.7248e-05) (hash(x)=29776243) +2151 train 7.097975 (lr=9.7207e-05) (hash(x)=24068619) +2152 train 7.325337 (lr=9.7165e-05) (hash(x)=22208671) +2153 train 7.463154 (lr=9.7124e-05) (hash(x)=26680905) +2154 train 7.326015 (lr=9.7083e-05) (hash(x)=23567808) +2155 train 7.576390 (lr=9.7041e-05) (hash(x)=26359528) +2156 train 7.349449 (lr=9.7000e-05) (hash(x)=23787652) +2157 train 7.650455 (lr=9.6958e-05) (hash(x)=28347177) +2158 train 7.324613 (lr=9.6917e-05) (hash(x)=25266519) +2159 train 7.222434 (lr=9.6875e-05) (hash(x)=25441262) +2160 train 7.170825 (lr=9.6834e-05) (hash(x)=23959943) +2161 train 7.425963 (lr=9.6793e-05) (hash(x)=27888093) +2162 train 7.311347 (lr=9.6751e-05) (hash(x)=25547833) +2163 train 7.277734 (lr=9.6710e-05) (hash(x)=24413659) +2164 train 8.781090 (lr=9.6668e-05) (hash(x)=34397626) +2165 train 7.213409 (lr=9.6627e-05) (hash(x)=21159323) +2166 train 7.441571 (lr=9.6585e-05) (hash(x)=25360269) +2167 train 7.466198 (lr=9.6544e-05) (hash(x)=29181867) +2168 train 7.268466 (lr=9.6502e-05) (hash(x)=22501613) +2169 train 7.366962 (lr=9.6461e-05) (hash(x)=26469077) +2170 train 7.328520 (lr=9.6419e-05) (hash(x)=26665118) +2171 train 7.974164 (lr=9.6378e-05) (hash(x)=31551575) +2172 train 7.258147 (lr=9.6336e-05) (hash(x)=24803935) +2173 train 7.141908 (lr=9.6295e-05) (hash(x)=20896465) +2174 train 7.687595 (lr=9.6253e-05) (hash(x)=25702284) +2175 train 7.640045 (lr=9.6212e-05) (hash(x)=27093757) +2176 train 7.371662 (lr=9.6170e-05) (hash(x)=26024255) +2177 train 7.533809 (lr=9.6129e-05) (hash(x)=26443521) +2178 train 7.464059 (lr=9.6087e-05) (hash(x)=25478467) +2179 train 7.342047 (lr=9.6045e-05) (hash(x)=23624298) +2180 train 7.410832 (lr=9.6004e-05) (hash(x)=27304178) +2181 train 7.172893 (lr=9.5962e-05) (hash(x)=23016570) +2182 train 7.138269 (lr=9.5921e-05) (hash(x)=21073756) +2183 train 7.283362 (lr=9.5879e-05) (hash(x)=25150275) +2184 train 7.046365 (lr=9.5838e-05) (hash(x)=21004187) +2185 train 7.308312 (lr=9.5796e-05) (hash(x)=25876062) +2186 train 7.264206 (lr=9.5754e-05) (hash(x)=24221275) +2187 train 7.529233 (lr=9.5713e-05) (hash(x)=26239886) +2188 train 7.230362 (lr=9.5671e-05) (hash(x)=23299261) +2189 train 7.662032 (lr=9.5630e-05) (hash(x)=31024703) +2190 train 7.797886 (lr=9.5588e-05) (hash(x)=30084774) +2191 train 8.144732 (lr=9.5546e-05) (hash(x)=33457102) +2192 train 7.257282 (lr=9.5505e-05) (hash(x)=22423723) +2193 train 7.288007 (lr=9.5463e-05) (hash(x)=21989055) +2194 train 7.299004 (lr=9.5421e-05) (hash(x)=23286499) +2195 train 7.224607 (lr=9.5380e-05) (hash(x)=17499738) +2196 train 7.295146 (lr=9.5338e-05) (hash(x)=25329557) +2197 train 7.198509 (lr=9.5297e-05) (hash(x)=24195578) +2198 train 7.426316 (lr=9.5255e-05) (hash(x)=26646383) +2199 train 7.323003 (lr=9.5213e-05) (hash(x)=25755322) +2200 val loss 7.3262 +2200 val perplexity 1519.5913 +2200 train 7.402066 (lr=9.5172e-05) (hash(x)=27592223) +2201 train 7.561813 (lr=9.5130e-05) (hash(x)=26164625) +2202 train 7.429832 (lr=9.5088e-05) (hash(x)=21856341) +2203 train 7.257183 (lr=9.5047e-05) (hash(x)=23722795) +2204 train 7.358837 (lr=9.5005e-05) (hash(x)=25409645) +2205 train 7.295764 (lr=9.4963e-05) (hash(x)=23415339) +2206 train 7.271367 (lr=9.4921e-05) (hash(x)=24147928) +2207 train 7.161718 (lr=9.4880e-05) (hash(x)=23630794) +2208 train 7.266727 (lr=9.4838e-05) (hash(x)=27361452) +2209 train 7.296881 (lr=9.4796e-05) (hash(x)=25632158) +2210 train 7.110782 (lr=9.4755e-05) (hash(x)=21159789) +2211 train 7.263683 (lr=9.4713e-05) (hash(x)=23374168) +2212 train 7.278268 (lr=9.4671e-05) (hash(x)=24844739) +2213 train 7.218234 (lr=9.4629e-05) (hash(x)=23461285) +2214 train 7.263088 (lr=9.4588e-05) (hash(x)=27958481) +2215 train 7.207469 (lr=9.4546e-05) (hash(x)=25167987) +2216 train 7.367668 (lr=9.4504e-05) (hash(x)=22873204) +2217 train 8.022154 (lr=9.4463e-05) (hash(x)=31038116) +2218 train 7.433548 (lr=9.4421e-05) (hash(x)=28883155) +2219 train 7.314497 (lr=9.4379e-05) (hash(x)=30941010) +2220 train 7.290611 (lr=9.4337e-05) (hash(x)=24947521) +2221 train 7.310783 (lr=9.4296e-05) (hash(x)=22703293) +2222 train 7.290508 (lr=9.4254e-05) (hash(x)=23976007) +2223 train 7.196926 (lr=9.4212e-05) (hash(x)=24043224) +2224 train 7.161469 (lr=9.4170e-05) (hash(x)=23981093) +2225 train 7.284135 (lr=9.4128e-05) (hash(x)=26445994) +2226 train 7.608019 (lr=9.4087e-05) (hash(x)=27252393) +2227 train 7.547173 (lr=9.4045e-05) (hash(x)=29736627) +2228 train 7.489568 (lr=9.4003e-05) (hash(x)=24698933) +2229 train 7.153025 (lr=9.3961e-05) (hash(x)=24357840) +2230 train 7.289519 (lr=9.3919e-05) (hash(x)=25384498) +2231 train 7.425180 (lr=9.3878e-05) (hash(x)=24665411) +2232 train 7.282482 (lr=9.3836e-05) (hash(x)=24646352) +2233 train 7.288148 (lr=9.3794e-05) (hash(x)=25670741) +2234 train 7.303385 (lr=9.3752e-05) (hash(x)=26648242) +2235 train 7.584207 (lr=9.3710e-05) (hash(x)=27916043) +2236 train 7.346956 (lr=9.3668e-05) (hash(x)=25963100) +2237 train 7.401183 (lr=9.3627e-05) (hash(x)=27357379) +2238 train 7.209015 (lr=9.3585e-05) (hash(x)=21852360) +2239 train 7.142368 (lr=9.3543e-05) (hash(x)=17321657) +2240 train 7.109536 (lr=9.3501e-05) (hash(x)=18446645) +2241 train 6.916439 (lr=9.3459e-05) (hash(x)=17550988) +2242 train 7.279957 (lr=9.3417e-05) (hash(x)=27052347) +2243 train 7.156122 (lr=9.3376e-05) (hash(x)=23829833) +2244 train 7.407574 (lr=9.3334e-05) (hash(x)=27267264) +2245 train 7.601936 (lr=9.3292e-05) (hash(x)=24673611) +2246 train 7.500639 (lr=9.3250e-05) (hash(x)=25248507) +2247 train 7.788402 (lr=9.3208e-05) (hash(x)=27932591) +2248 train 7.630016 (lr=9.3166e-05) (hash(x)=26078877) +2249 train 7.676284 (lr=9.3124e-05) (hash(x)=26067367) +2250 val loss 7.3253 +2250 val perplexity 1518.1935 +2250 train 7.790081 (lr=9.3082e-05) (hash(x)=29143527) +2251 train 7.802234 (lr=9.3040e-05) (hash(x)=28206079) +2252 train 8.305285 (lr=9.2999e-05) (hash(x)=28894494) +2253 train 7.699338 (lr=9.2957e-05) (hash(x)=27977422) +2254 train 7.342037 (lr=9.2915e-05) (hash(x)=26446420) +2255 train 7.589315 (lr=9.2873e-05) (hash(x)=29447954) +2256 train 7.370683 (lr=9.2831e-05) (hash(x)=22181789) +2257 train 7.391310 (lr=9.2789e-05) (hash(x)=24976337) +2258 train 7.333431 (lr=9.2747e-05) (hash(x)=23277532) +2259 train 7.463215 (lr=9.2705e-05) (hash(x)=25935364) +2260 train 7.563143 (lr=9.2663e-05) (hash(x)=26988889) +2261 train 7.369784 (lr=9.2621e-05) (hash(x)=26887303) +2262 train 7.316797 (lr=9.2579e-05) (hash(x)=25021426) +2263 train 7.259927 (lr=9.2537e-05) (hash(x)=24621816) +2264 train 7.144804 (lr=9.2495e-05) (hash(x)=22132007) +2265 train 7.103835 (lr=9.2453e-05) (hash(x)=22648602) +2266 train 7.379387 (lr=9.2412e-05) (hash(x)=23132242) +2267 train 7.429327 (lr=9.2370e-05) (hash(x)=24070405) +2268 train 7.037738 (lr=9.2328e-05) (hash(x)=21412906) +2269 train 7.713051 (lr=9.2286e-05) (hash(x)=27547292) +2270 train 7.490860 (lr=9.2244e-05) (hash(x)=27740500) +2271 train 7.203621 (lr=9.2202e-05) (hash(x)=24682294) +2272 train 7.647092 (lr=9.2160e-05) (hash(x)=27969424) +2273 train 7.329649 (lr=9.2118e-05) (hash(x)=22172182) +2274 train 7.327687 (lr=9.2076e-05) (hash(x)=26485905) +2275 train 7.192684 (lr=9.2034e-05) (hash(x)=24050209) +2276 train 7.346073 (lr=9.1992e-05) (hash(x)=28802650) +2277 train 7.133096 (lr=9.1950e-05) (hash(x)=23644616) +2278 train 7.309087 (lr=9.1908e-05) (hash(x)=25409768) +2279 train 7.494000 (lr=9.1866e-05) (hash(x)=28057095) +2280 train 8.007976 (lr=9.1824e-05) (hash(x)=31689723) +2281 train 7.142209 (lr=9.1782e-05) (hash(x)=22252427) +2282 train 7.349548 (lr=9.1740e-05) (hash(x)=24142092) +2283 train 7.317972 (lr=9.1698e-05) (hash(x)=22523232) +2284 train 7.515724 (lr=9.1656e-05) (hash(x)=26017294) +2285 train 7.369294 (lr=9.1614e-05) (hash(x)=25025388) +2286 train 7.149989 (lr=9.1572e-05) (hash(x)=23819479) +2287 train 7.318544 (lr=9.1530e-05) (hash(x)=24547536) +2288 train 7.100456 (lr=9.1487e-05) (hash(x)=22622789) +2289 train 7.083084 (lr=9.1445e-05) (hash(x)=23874051) +2290 train 7.396549 (lr=9.1403e-05) (hash(x)=25015641) +2291 train 7.285900 (lr=9.1361e-05) (hash(x)=24978712) +2292 train 7.374187 (lr=9.1319e-05) (hash(x)=25311986) +2293 train 7.149069 (lr=9.1277e-05) (hash(x)=24298295) +2294 train 7.257122 (lr=9.1235e-05) (hash(x)=26481527) +2295 train 6.984900 (lr=9.1193e-05) (hash(x)=18987545) +2296 train 7.223653 (lr=9.1151e-05) (hash(x)=24617990) +2297 train 7.215305 (lr=9.1109e-05) (hash(x)=23903200) +2298 train 7.562936 (lr=9.1067e-05) (hash(x)=26278697) +2299 train 7.315683 (lr=9.1025e-05) (hash(x)=24092784) +2300 val loss 7.3328 +2300 val perplexity 1529.6178 +2300 train 7.273451 (lr=9.0983e-05) (hash(x)=22894919) +2301 train 7.322289 (lr=9.0941e-05) (hash(x)=24253964) +2302 train 7.273950 (lr=9.0899e-05) (hash(x)=23750610) +2303 train 7.282364 (lr=9.0856e-05) (hash(x)=26745063) +2304 train 7.099275 (lr=9.0814e-05) (hash(x)=21407001) +2305 train 7.499112 (lr=9.0772e-05) (hash(x)=26680082) +2306 train 7.414653 (lr=9.0730e-05) (hash(x)=26722122) +2307 train 7.262601 (lr=9.0688e-05) (hash(x)=22539112) +2308 train 7.022691 (lr=9.0646e-05) (hash(x)=19927356) +2309 train 7.138454 (lr=9.0604e-05) (hash(x)=21431267) +2310 train 7.063953 (lr=9.0562e-05) (hash(x)=21073487) +2311 train 7.112036 (lr=9.0520e-05) (hash(x)=21447406) +2312 train 7.089050 (lr=9.0477e-05) (hash(x)=22667253) +2313 train 7.058469 (lr=9.0435e-05) (hash(x)=20849089) +2314 train 7.054640 (lr=9.0393e-05) (hash(x)=19168351) +2315 train 7.087581 (lr=9.0351e-05) (hash(x)=21082139) +2316 train 7.064274 (lr=9.0309e-05) (hash(x)=21493530) +2317 train 7.028360 (lr=9.0267e-05) (hash(x)=19506447) +2318 train 7.152364 (lr=9.0225e-05) (hash(x)=23128797) +2319 train 7.242776 (lr=9.0183e-05) (hash(x)=24650655) +2320 train 7.010337 (lr=9.0140e-05) (hash(x)=21833080) +2321 train 7.525362 (lr=9.0098e-05) (hash(x)=26355512) +2322 train 7.661049 (lr=9.0056e-05) (hash(x)=26746363) +2323 train 7.115743 (lr=9.0014e-05) (hash(x)=22130721) +2324 train 7.461629 (lr=8.9972e-05) (hash(x)=28301752) +2325 train 7.318119 (lr=8.9930e-05) (hash(x)=26444359) +2326 train 7.660172 (lr=8.9887e-05) (hash(x)=24836130) +2327 train 8.056076 (lr=8.9845e-05) (hash(x)=26519976) +2328 train 9.399909 (lr=8.9803e-05) (hash(x)=35558906) +2329 train 7.726491 (lr=8.9761e-05) (hash(x)=30877729) +2330 train 7.575983 (lr=8.9719e-05) (hash(x)=28028485) +2331 train 7.700088 (lr=8.9677e-05) (hash(x)=25582440) +2332 train 8.007390 (lr=8.9634e-05) (hash(x)=29402491) +2333 train 7.356626 (lr=8.9592e-05) (hash(x)=25200284) +2334 train 7.401625 (lr=8.9550e-05) (hash(x)=26288480) +2335 train 7.221082 (lr=8.9508e-05) (hash(x)=20106514) +2336 train 7.208189 (lr=8.9466e-05) (hash(x)=22522123) +2337 train 7.191972 (lr=8.9423e-05) (hash(x)=23362041) +2338 train 7.304157 (lr=8.9381e-05) (hash(x)=26003099) +2339 train 7.321941 (lr=8.9339e-05) (hash(x)=25695510) +2340 train 7.277731 (lr=8.9297e-05) (hash(x)=27225904) +2341 train 7.049855 (lr=8.9255e-05) (hash(x)=21573008) +2342 train 7.516798 (lr=8.9212e-05) (hash(x)=21386628) +2343 train 7.276516 (lr=8.9170e-05) (hash(x)=20117808) +2344 train 7.406134 (lr=8.9128e-05) (hash(x)=21592790) +2345 train 7.336549 (lr=8.9086e-05) (hash(x)=19909192) +2346 train 7.442639 (lr=8.9044e-05) (hash(x)=22529262) +2347 train 7.480428 (lr=8.9001e-05) (hash(x)=24501900) +2348 train 7.272637 (lr=8.8959e-05) (hash(x)=25912171) +2349 train 7.365584 (lr=8.8917e-05) (hash(x)=25606665) +2350 val loss 7.3276 +2350 val perplexity 1521.7209 +2350 train 7.256532 (lr=8.8875e-05) (hash(x)=24487351) +2351 train 7.513772 (lr=8.8832e-05) (hash(x)=25510334) +2352 train 7.432376 (lr=8.8790e-05) (hash(x)=25357989) +2353 train 7.085924 (lr=8.8748e-05) (hash(x)=24656801) +2354 train 7.175267 (lr=8.8706e-05) (hash(x)=23312772) +2355 train 7.070400 (lr=8.8664e-05) (hash(x)=22099158) +2356 train 7.125282 (lr=8.8621e-05) (hash(x)=26507898) +2357 train 7.405921 (lr=8.8579e-05) (hash(x)=28351614) +2358 train 7.425323 (lr=8.8537e-05) (hash(x)=27489567) +2359 train 7.417561 (lr=8.8495e-05) (hash(x)=25749120) +2360 train 7.714738 (lr=8.8452e-05) (hash(x)=31711338) +2361 train 7.835194 (lr=8.8410e-05) (hash(x)=29645018) +2362 train 7.872495 (lr=8.8368e-05) (hash(x)=29713268) +2363 train 7.009483 (lr=8.8325e-05) (hash(x)=21720691) +2364 train 7.128115 (lr=8.8283e-05) (hash(x)=24316633) +2365 train 7.031936 (lr=8.8241e-05) (hash(x)=21597124) +2366 train 7.085423 (lr=8.8199e-05) (hash(x)=22520345) +2367 train 7.151067 (lr=8.8156e-05) (hash(x)=24357241) +2368 train 7.279367 (lr=8.8114e-05) (hash(x)=24085450) +2369 train 7.195824 (lr=8.8072e-05) (hash(x)=25136495) +2370 train 7.667818 (lr=8.8030e-05) (hash(x)=26073986) +2371 train 7.671164 (lr=8.7987e-05) (hash(x)=28911272) +2372 train 7.393388 (lr=8.7945e-05) (hash(x)=26667356) +2373 train 7.185985 (lr=8.7903e-05) (hash(x)=25225894) +2374 train 7.222333 (lr=8.7860e-05) (hash(x)=24404081) +2375 train 7.333177 (lr=8.7818e-05) (hash(x)=25584945) +2376 train 7.165294 (lr=8.7776e-05) (hash(x)=23831571) +2377 train 7.156950 (lr=8.7734e-05) (hash(x)=23521916) +2378 train 7.168092 (lr=8.7691e-05) (hash(x)=25318634) +2379 train 7.054399 (lr=8.7649e-05) (hash(x)=21847287) +2380 train 7.413934 (lr=8.7607e-05) (hash(x)=23877060) +2381 train 7.194225 (lr=8.7564e-05) (hash(x)=24069020) +2382 train 7.027722 (lr=8.7522e-05) (hash(x)=21724290) +2383 train 7.271175 (lr=8.7480e-05) (hash(x)=25198897) +2384 train 7.125020 (lr=8.7438e-05) (hash(x)=24109958) +2385 train 6.999056 (lr=8.7395e-05) (hash(x)=20122390) +2386 train 7.272279 (lr=8.7353e-05) (hash(x)=24062305) +2387 train 7.028471 (lr=8.7311e-05) (hash(x)=22436833) +2388 train 7.349043 (lr=8.7268e-05) (hash(x)=26013214) +2389 train 7.723000 (lr=8.7226e-05) (hash(x)=27691436) +2390 train 7.860544 (lr=8.7184e-05) (hash(x)=30802878) +2391 train 6.992222 (lr=8.7141e-05) (hash(x)=23475891) +2392 train 6.959610 (lr=8.7099e-05) (hash(x)=23118133) +2393 train 6.862012 (lr=8.7057e-05) (hash(x)=21469159) +2394 train 7.288458 (lr=8.7014e-05) (hash(x)=26444484) +2395 train 7.128366 (lr=8.6972e-05) (hash(x)=25083992) +2396 train 7.491546 (lr=8.6930e-05) (hash(x)=23461229) +2397 train 7.372113 (lr=8.6887e-05) (hash(x)=20441653) +2398 train 7.439520 (lr=8.6845e-05) (hash(x)=28024211) +2399 train 7.286414 (lr=8.6803e-05) (hash(x)=23644804) +2400 val loss 7.3089 +2400 val perplexity 1493.4990 +2400 train 7.075152 (lr=8.6760e-05) (hash(x)=26685301) +2401 train 6.978427 (lr=8.6718e-05) (hash(x)=20820913) +2402 train 7.142642 (lr=8.6676e-05) (hash(x)=22178190) +2403 train 7.735163 (lr=8.6633e-05) (hash(x)=31377168) +2404 train 7.940034 (lr=8.6591e-05) (hash(x)=33795307) +2405 train 8.098693 (lr=8.6549e-05) (hash(x)=34450341) +2406 train 7.261586 (lr=8.6506e-05) (hash(x)=25834183) +2407 train 7.452162 (lr=8.6464e-05) (hash(x)=25629584) +2408 train 7.230817 (lr=8.6422e-05) (hash(x)=25080123) +2409 train 7.126322 (lr=8.6379e-05) (hash(x)=21975628) +2410 train 7.698873 (lr=8.6337e-05) (hash(x)=27430197) +2411 train 7.885123 (lr=8.6295e-05) (hash(x)=29285135) +2412 train 7.579514 (lr=8.6252e-05) (hash(x)=24640105) +2413 train 7.593259 (lr=8.6210e-05) (hash(x)=29628864) +2414 train 7.835128 (lr=8.6168e-05) (hash(x)=30096444) +2415 train 7.677547 (lr=8.6125e-05) (hash(x)=29797280) +2416 train 7.033594 (lr=8.6083e-05) (hash(x)=22686143) +2417 train 7.614054 (lr=8.6040e-05) (hash(x)=28346842) +2418 train 7.609201 (lr=8.5998e-05) (hash(x)=28167937) +2419 train 7.858008 (lr=8.5956e-05) (hash(x)=33122326) +2420 train 7.892676 (lr=8.5913e-05) (hash(x)=33044913) +2421 train 7.688642 (lr=8.5871e-05) (hash(x)=31250981) +2422 train 7.914698 (lr=8.5829e-05) (hash(x)=29827111) +2423 train 7.836710 (lr=8.5786e-05) (hash(x)=30026394) +2424 train 7.944457 (lr=8.5744e-05) (hash(x)=26998238) +2425 train 7.933895 (lr=8.5702e-05) (hash(x)=24850684) +2426 train 8.117592 (lr=8.5659e-05) (hash(x)=36659853) +2427 train 8.019716 (lr=8.5617e-05) (hash(x)=34353164) +2428 train 7.359402 (lr=8.5574e-05) (hash(x)=23630644) +2429 train 7.285568 (lr=8.5532e-05) (hash(x)=24528186) +2430 train 7.169807 (lr=8.5490e-05) (hash(x)=22665222) +2431 train 7.309508 (lr=8.5447e-05) (hash(x)=26594177) +2432 train 7.674507 (lr=8.5405e-05) (hash(x)=29300546) +2433 train 7.093987 (lr=8.5362e-05) (hash(x)=21331715) +2434 train 7.384387 (lr=8.5320e-05) (hash(x)=26290885) +2435 train 7.314114 (lr=8.5278e-05) (hash(x)=25554738) +2436 train 7.550949 (lr=8.5235e-05) (hash(x)=26744311) +2437 train 7.520259 (lr=8.5193e-05) (hash(x)=26872344) +2438 train 7.565045 (lr=8.5151e-05) (hash(x)=27636081) +2439 train 7.327845 (lr=8.5108e-05) (hash(x)=23766256) +2440 train 7.464228 (lr=8.5066e-05) (hash(x)=24434438) +2441 train 7.233444 (lr=8.5023e-05) (hash(x)=22992618) +2442 train 7.125221 (lr=8.4981e-05) (hash(x)=22393467) +2443 train 7.389452 (lr=8.4939e-05) (hash(x)=26853444) +2444 train 7.338735 (lr=8.4896e-05) (hash(x)=25101020) +2445 train 7.232132 (lr=8.4854e-05) (hash(x)=24705456) +2446 train 7.528071 (lr=8.4811e-05) (hash(x)=26798611) +2447 train 7.198233 (lr=8.4769e-05) (hash(x)=24250150) +2448 train 7.251075 (lr=8.4727e-05) (hash(x)=24494331) +2449 train 7.285443 (lr=8.4684e-05) (hash(x)=27579257) +2450 val loss 7.3128 +2450 val perplexity 1499.3165 +2450 train 7.020586 (lr=8.4642e-05) (hash(x)=22377407) +2451 train 7.349397 (lr=8.4599e-05) (hash(x)=26289588) +2452 train 7.250340 (lr=8.4557e-05) (hash(x)=25871900) +2453 train 7.167877 (lr=8.4515e-05) (hash(x)=23437197) +2454 train 7.438126 (lr=8.4472e-05) (hash(x)=23557786) +2455 train 7.315099 (lr=8.4430e-05) (hash(x)=26108817) +2456 train 7.257152 (lr=8.4387e-05) (hash(x)=26440482) +2457 train 7.265175 (lr=8.4345e-05) (hash(x)=24583191) +2458 train 7.263036 (lr=8.4303e-05) (hash(x)=23756440) +2459 train 7.144949 (lr=8.4260e-05) (hash(x)=23814987) +2460 train 7.498217 (lr=8.4218e-05) (hash(x)=28508433) +2461 train 7.172809 (lr=8.4175e-05) (hash(x)=25692442) +2462 train 7.134538 (lr=8.4133e-05) (hash(x)=24699197) +2463 train 6.877461 (lr=8.4091e-05) (hash(x)=18582688) +2464 train 7.175152 (lr=8.4048e-05) (hash(x)=23266625) +2465 train 7.506031 (lr=8.4006e-05) (hash(x)=26565489) +2466 train 6.993633 (lr=8.3963e-05) (hash(x)=21686599) +2467 train 7.301834 (lr=8.3921e-05) (hash(x)=25558792) +2468 train 7.058616 (lr=8.3879e-05) (hash(x)=25110035) +2469 train 7.397111 (lr=8.3836e-05) (hash(x)=26263661) +2470 train 7.151050 (lr=8.3794e-05) (hash(x)=22282189) +2471 train 7.124303 (lr=8.3751e-05) (hash(x)=23272705) +2472 train 7.224201 (lr=8.3709e-05) (hash(x)=25300067) +2473 train 7.391287 (lr=8.3666e-05) (hash(x)=26802369) +2474 train 7.097579 (lr=8.3624e-05) (hash(x)=24646471) +2475 train 7.062553 (lr=8.3582e-05) (hash(x)=24709241) +2476 train 7.158559 (lr=8.3539e-05) (hash(x)=26747197) +2477 train 7.211751 (lr=8.3497e-05) (hash(x)=25201108) +2478 train 7.333510 (lr=8.3454e-05) (hash(x)=24962427) +2479 train 7.187705 (lr=8.3412e-05) (hash(x)=24793412) +2480 train 7.225802 (lr=8.3370e-05) (hash(x)=24452301) +2481 train 7.236655 (lr=8.3327e-05) (hash(x)=25177251) +2482 train 7.160674 (lr=8.3285e-05) (hash(x)=25801499) +2483 train 7.349445 (lr=8.3242e-05) (hash(x)=27256707) +2484 train 7.618198 (lr=8.3200e-05) (hash(x)=25303237) +2485 train 7.187094 (lr=8.3157e-05) (hash(x)=21641481) +2486 train 7.171885 (lr=8.3115e-05) (hash(x)=23818831) +2487 train 6.942281 (lr=8.3073e-05) (hash(x)=19280989) +2488 train 7.267448 (lr=8.3030e-05) (hash(x)=24075167) +2489 train 7.311476 (lr=8.2988e-05) (hash(x)=26651546) +2490 train 7.236259 (lr=8.2945e-05) (hash(x)=25367186) +2491 train 7.180909 (lr=8.2903e-05) (hash(x)=26508642) +2492 train 7.276831 (lr=8.2861e-05) (hash(x)=25294182) +2493 train 7.193929 (lr=8.2818e-05) (hash(x)=23916886) +2494 train 7.053050 (lr=8.2776e-05) (hash(x)=21189910) +2495 train 7.176385 (lr=8.2733e-05) (hash(x)=22751150) +2496 train 7.573328 (lr=8.2691e-05) (hash(x)=26608502) +2497 train 7.981729 (lr=8.2648e-05) (hash(x)=25372010) +2498 train 7.216223 (lr=8.2606e-05) (hash(x)=22006251) +2499 train 7.153714 (lr=8.2564e-05) (hash(x)=23880160) +2500 val loss 7.2961 +2500 val perplexity 1474.5966 +2500 train 7.122612 (lr=8.2521e-05) (hash(x)=23225337) +2501 train 7.274484 (lr=8.2479e-05) (hash(x)=24932950) +2502 train 7.010636 (lr=8.2436e-05) (hash(x)=20022340) +2503 train 7.394510 (lr=8.2394e-05) (hash(x)=23537942) +2504 train 7.243787 (lr=8.2352e-05) (hash(x)=24884288) +2505 train 6.932744 (lr=8.2309e-05) (hash(x)=21296580) +2506 train 7.168616 (lr=8.2267e-05) (hash(x)=23001455) +2507 train 7.450728 (lr=8.2224e-05) (hash(x)=26975313) +2508 train 7.473167 (lr=8.2182e-05) (hash(x)=26029962) +2509 train 7.157282 (lr=8.2139e-05) (hash(x)=24302204) +2510 train 6.895515 (lr=8.2097e-05) (hash(x)=22997203) +2511 train 7.016727 (lr=8.2055e-05) (hash(x)=23748375) +2512 train 7.217201 (lr=8.2012e-05) (hash(x)=24453191) +2513 train 6.917987 (lr=8.1970e-05) (hash(x)=22026776) +2514 train 7.049522 (lr=8.1927e-05) (hash(x)=19934168) +2515 train 7.337404 (lr=8.1885e-05) (hash(x)=25541754) +2516 train 7.704763 (lr=8.1843e-05) (hash(x)=26604471) +2517 train 7.659677 (lr=8.1800e-05) (hash(x)=27900386) +2518 train 7.619905 (lr=8.1758e-05) (hash(x)=26403431) +2519 train 7.641664 (lr=8.1715e-05) (hash(x)=27413825) +2520 train 7.728311 (lr=8.1673e-05) (hash(x)=28332637) +2521 train 7.527172 (lr=8.1630e-05) (hash(x)=27223027) +2522 train 7.531412 (lr=8.1588e-05) (hash(x)=23843387) +2523 train 7.576363 (lr=8.1546e-05) (hash(x)=27075951) +2524 train 7.772761 (lr=8.1503e-05) (hash(x)=29300154) +2525 train 7.377004 (lr=8.1461e-05) (hash(x)=28100582) +2526 train 7.427633 (lr=8.1418e-05) (hash(x)=28051084) +2527 train 7.135681 (lr=8.1376e-05) (hash(x)=21682445) +2528 train 7.325681 (lr=8.1334e-05) (hash(x)=24062589) +2529 train 7.536491 (lr=8.1291e-05) (hash(x)=29616079) +2530 train 7.455698 (lr=8.1249e-05) (hash(x)=25170523) +2531 train 7.037433 (lr=8.1206e-05) (hash(x)=23361504) +2532 train 7.244047 (lr=8.1164e-05) (hash(x)=24444462) +2533 train 7.253613 (lr=8.1121e-05) (hash(x)=24035993) +2534 train 7.228626 (lr=8.1079e-05) (hash(x)=24696651) +2535 train 7.190675 (lr=8.1037e-05) (hash(x)=22040184) +2536 train 7.115434 (lr=8.0994e-05) (hash(x)=27400103) +2537 train 7.447011 (lr=8.0952e-05) (hash(x)=27383080) +2538 train 7.261426 (lr=8.0909e-05) (hash(x)=24212212) +2539 train 7.125212 (lr=8.0867e-05) (hash(x)=23727731) +2540 train 7.265790 (lr=8.0825e-05) (hash(x)=24149487) +2541 train 7.022325 (lr=8.0782e-05) (hash(x)=23794649) +2542 train 7.196140 (lr=8.0740e-05) (hash(x)=26147774) +2543 train 7.324619 (lr=8.0697e-05) (hash(x)=24463229) +2544 train 7.397209 (lr=8.0655e-05) (hash(x)=26361238) +2545 train 7.061827 (lr=8.0613e-05) (hash(x)=18891545) +2546 train 7.596498 (lr=8.0570e-05) (hash(x)=30380438) +2547 train 7.822968 (lr=8.0528e-05) (hash(x)=32663792) +2548 train 7.260961 (lr=8.0485e-05) (hash(x)=25175499) +2549 train 7.431541 (lr=8.0443e-05) (hash(x)=26702407) +2550 val loss 7.3211 +2550 val perplexity 1511.9111 +2550 train 7.225383 (lr=8.0401e-05) (hash(x)=24578061) +2551 train 7.276891 (lr=8.0358e-05) (hash(x)=24091954) +2552 train 7.296619 (lr=8.0316e-05) (hash(x)=23041778) +2553 train 7.110645 (lr=8.0273e-05) (hash(x)=23686239) +2554 train 7.219968 (lr=8.0231e-05) (hash(x)=22745355) +2555 train 7.236395 (lr=8.0189e-05) (hash(x)=23599013) +2556 train 7.142297 (lr=8.0146e-05) (hash(x)=26033088) +2557 train 7.212789 (lr=8.0104e-05) (hash(x)=21634218) +2558 train 7.162965 (lr=8.0061e-05) (hash(x)=20985281) +2559 train 7.387537 (lr=8.0019e-05) (hash(x)=26670219) +2560 train 7.168712 (lr=7.9977e-05) (hash(x)=26499936) +2561 train 7.272755 (lr=7.9934e-05) (hash(x)=23547908) +2562 train 7.109765 (lr=7.9892e-05) (hash(x)=22306373) +2563 train 7.234741 (lr=7.9849e-05) (hash(x)=24380893) +2564 train 7.170108 (lr=7.9807e-05) (hash(x)=23726190) +2565 train 7.206880 (lr=7.9765e-05) (hash(x)=26967512) +2566 train 7.283545 (lr=7.9722e-05) (hash(x)=23414576) +2567 train 7.518642 (lr=7.9680e-05) (hash(x)=25558986) +2568 train 7.390058 (lr=7.9638e-05) (hash(x)=27057505) +2569 train 7.380301 (lr=7.9595e-05) (hash(x)=26048135) +2570 train 7.330968 (lr=7.9553e-05) (hash(x)=26991032) +2571 train 7.406522 (lr=7.9510e-05) (hash(x)=25729492) +2572 train 6.966433 (lr=7.9468e-05) (hash(x)=20611723) +2573 train 7.069005 (lr=7.9426e-05) (hash(x)=24563606) +2574 train 7.123571 (lr=7.9383e-05) (hash(x)=23330043) +2575 train 7.237789 (lr=7.9341e-05) (hash(x)=19218943) +2576 train 7.571275 (lr=7.9298e-05) (hash(x)=20985122) +2577 train 7.142613 (lr=7.9256e-05) (hash(x)=24133609) +2578 train 7.464667 (lr=7.9214e-05) (hash(x)=28368610) +2579 train 7.206300 (lr=7.9171e-05) (hash(x)=23952206) +2580 train 7.104878 (lr=7.9129e-05) (hash(x)=23068957) +2581 train 7.224107 (lr=7.9087e-05) (hash(x)=25365277) +2582 train 7.562363 (lr=7.9044e-05) (hash(x)=24721184) +2583 train 7.250568 (lr=7.9002e-05) (hash(x)=24551402) +2584 train 6.986985 (lr=7.8960e-05) (hash(x)=20469327) +2585 train 7.401836 (lr=7.8917e-05) (hash(x)=24966478) +2586 train 7.140091 (lr=7.8875e-05) (hash(x)=18626184) +2587 train 7.126472 (lr=7.8832e-05) (hash(x)=24007642) +2588 train 7.127740 (lr=7.8790e-05) (hash(x)=23521875) +2589 train 7.315759 (lr=7.8748e-05) (hash(x)=25204207) +2590 train 7.123306 (lr=7.8705e-05) (hash(x)=25449801) +2591 train 7.312784 (lr=7.8663e-05) (hash(x)=25229281) +2592 train 7.154463 (lr=7.8621e-05) (hash(x)=23202696) +2593 train 7.008571 (lr=7.8578e-05) (hash(x)=22435944) +2594 train 7.025649 (lr=7.8536e-05) (hash(x)=20787439) +2595 train 6.671036 (lr=7.8494e-05) (hash(x)=18214283) +2596 train 6.821051 (lr=7.8451e-05) (hash(x)=20851477) +2597 train 6.833341 (lr=7.8409e-05) (hash(x)=20609675) +2598 train 6.940543 (lr=7.8367e-05) (hash(x)=20061218) +2599 train 6.960968 (lr=7.8324e-05) (hash(x)=21251127) +2600 val loss 7.2847 +2600 val perplexity 1457.8549 +2600 train 7.480533 (lr=7.8282e-05) (hash(x)=30948038) +2601 train 7.781346 (lr=7.8240e-05) (hash(x)=32279160) +2602 train 7.407484 (lr=7.8197e-05) (hash(x)=26607151) +2603 train 7.278456 (lr=7.8155e-05) (hash(x)=25097619) +2604 train 6.802191 (lr=7.8113e-05) (hash(x)=20892421) +2605 train 6.996153 (lr=7.8070e-05) (hash(x)=22212821) +2606 train 7.310990 (lr=7.8028e-05) (hash(x)=24720588) +2607 train 7.335941 (lr=7.7986e-05) (hash(x)=25800857) +2608 train 7.149622 (lr=7.7943e-05) (hash(x)=22901279) +2609 train 6.975078 (lr=7.7901e-05) (hash(x)=20921910) +2610 train 7.205818 (lr=7.7859e-05) (hash(x)=24846267) +2611 train 7.137745 (lr=7.7816e-05) (hash(x)=22918428) +2612 train 7.070829 (lr=7.7774e-05) (hash(x)=22805901) +2613 train 7.253364 (lr=7.7732e-05) (hash(x)=24345816) +2614 train 7.094745 (lr=7.7689e-05) (hash(x)=22962012) +2615 train 7.362476 (lr=7.7647e-05) (hash(x)=25836189) +2616 train 7.389452 (lr=7.7605e-05) (hash(x)=27922916) +2617 train 7.102791 (lr=7.7562e-05) (hash(x)=21697866) +2618 train 7.087952 (lr=7.7520e-05) (hash(x)=24283369) +2619 train 7.029501 (lr=7.7478e-05) (hash(x)=24504567) +2620 train 7.105111 (lr=7.7436e-05) (hash(x)=25557725) +2621 train 7.150238 (lr=7.7393e-05) (hash(x)=23135849) +2622 train 7.084840 (lr=7.7351e-05) (hash(x)=22888908) +2623 train 7.295557 (lr=7.7309e-05) (hash(x)=25999255) +2624 train 7.160075 (lr=7.7266e-05) (hash(x)=24446851) +2625 train 6.890457 (lr=7.7224e-05) (hash(x)=21137520) +2626 train 7.218210 (lr=7.7182e-05) (hash(x)=26245754) +2627 train 7.521189 (lr=7.7140e-05) (hash(x)=27308968) +2628 train 7.288448 (lr=7.7097e-05) (hash(x)=23961169) +2629 train 7.245899 (lr=7.7055e-05) (hash(x)=25924731) +2630 train 7.315715 (lr=7.7013e-05) (hash(x)=25782315) +2631 train 7.387815 (lr=7.6970e-05) (hash(x)=20149394) +2632 train 7.453958 (lr=7.6928e-05) (hash(x)=23801981) +2633 train 7.214227 (lr=7.6886e-05) (hash(x)=23830286) +2634 train 7.145375 (lr=7.6844e-05) (hash(x)=25325236) +2635 train 7.122708 (lr=7.6801e-05) (hash(x)=24498556) +2636 train 7.135996 (lr=7.6759e-05) (hash(x)=23693078) +2637 train 7.274402 (lr=7.6717e-05) (hash(x)=25484922) +2638 train 6.973961 (lr=7.6675e-05) (hash(x)=22645025) +2639 train 6.928778 (lr=7.6632e-05) (hash(x)=21999338) +2640 train 7.172998 (lr=7.6590e-05) (hash(x)=21758019) +2641 train 7.121455 (lr=7.6548e-05) (hash(x)=24064168) +2642 train 7.132048 (lr=7.6505e-05) (hash(x)=26847292) +2643 train 6.987525 (lr=7.6463e-05) (hash(x)=23280568) +2644 train 7.024277 (lr=7.6421e-05) (hash(x)=21749161) +2645 train 7.641422 (lr=7.6379e-05) (hash(x)=30082352) +2646 train 7.511014 (lr=7.6336e-05) (hash(x)=28334297) +2647 train 7.662369 (lr=7.6294e-05) (hash(x)=27611302) +2648 train 8.055243 (lr=7.6252e-05) (hash(x)=31007436) +2649 train 6.957883 (lr=7.6210e-05) (hash(x)=22356183) +2650 val loss 7.2837 +2650 val perplexity 1456.3146 +2650 train 7.010366 (lr=7.6168e-05) (hash(x)=23071731) +2651 train 7.020827 (lr=7.6125e-05) (hash(x)=23982308) +2652 train 7.360619 (lr=7.6083e-05) (hash(x)=25673823) +2653 train 7.142602 (lr=7.6041e-05) (hash(x)=22973788) +2654 train 7.313718 (lr=7.5999e-05) (hash(x)=25386647) +2655 train 7.042804 (lr=7.5956e-05) (hash(x)=22778356) +2656 train 7.269065 (lr=7.5914e-05) (hash(x)=26669130) +2657 train 6.997468 (lr=7.5872e-05) (hash(x)=23542930) +2658 train 7.105545 (lr=7.5830e-05) (hash(x)=23307871) +2659 train 7.095657 (lr=7.5788e-05) (hash(x)=23467046) +2660 train 7.231615 (lr=7.5745e-05) (hash(x)=24728872) +2661 train 7.839401 (lr=7.5703e-05) (hash(x)=29719902) +2662 train 7.155216 (lr=7.5661e-05) (hash(x)=25114165) +2663 train 7.066025 (lr=7.5619e-05) (hash(x)=24195959) +2664 train 7.274463 (lr=7.5577e-05) (hash(x)=26938509) +2665 train 7.484161 (lr=7.5534e-05) (hash(x)=27168434) +2666 train 7.615304 (lr=7.5492e-05) (hash(x)=27488221) +2667 train 8.344469 (lr=7.5450e-05) (hash(x)=32710438) +2668 train 7.419310 (lr=7.5408e-05) (hash(x)=25073185) +2669 train 7.421440 (lr=7.5366e-05) (hash(x)=26951664) +2670 train 7.584833 (lr=7.5323e-05) (hash(x)=24886228) +2671 train 7.063259 (lr=7.5281e-05) (hash(x)=19127465) +2672 train 7.289745 (lr=7.5239e-05) (hash(x)=27134917) +2673 train 7.224046 (lr=7.5197e-05) (hash(x)=25673955) +2674 train 7.773572 (lr=7.5155e-05) (hash(x)=27111776) +2675 train 7.646787 (lr=7.5113e-05) (hash(x)=28962580) +2676 train 7.223812 (lr=7.5070e-05) (hash(x)=25593381) +2677 train 7.264618 (lr=7.5028e-05) (hash(x)=25238916) +2678 train 7.181981 (lr=7.4986e-05) (hash(x)=27453574) +2679 train 7.141411 (lr=7.4944e-05) (hash(x)=22426274) +2680 train 7.160778 (lr=7.4902e-05) (hash(x)=22974780) +2681 train 7.187837 (lr=7.4860e-05) (hash(x)=24668644) +2682 train 7.182190 (lr=7.4817e-05) (hash(x)=26182084) +2683 train 7.384549 (lr=7.4775e-05) (hash(x)=25606512) +2684 train 7.216715 (lr=7.4733e-05) (hash(x)=24885252) +2685 train 7.012640 (lr=7.4691e-05) (hash(x)=21290254) +2686 train 6.945847 (lr=7.4649e-05) (hash(x)=21367078) +2687 train 7.136464 (lr=7.4607e-05) (hash(x)=23785205) +2688 train 7.051550 (lr=7.4565e-05) (hash(x)=24640056) +2689 train 7.477104 (lr=7.4523e-05) (hash(x)=27083886) +2690 train 7.160355 (lr=7.4480e-05) (hash(x)=23603571) +2691 train 7.239348 (lr=7.4438e-05) (hash(x)=24779414) +2692 train 6.944545 (lr=7.4396e-05) (hash(x)=22200693) +2693 train 7.313373 (lr=7.4354e-05) (hash(x)=26907868) +2694 train 7.638025 (lr=7.4312e-05) (hash(x)=32034827) +2695 train 7.493053 (lr=7.4270e-05) (hash(x)=28505676) +2696 train 7.076192 (lr=7.4228e-05) (hash(x)=23805750) +2697 train 7.417959 (lr=7.4186e-05) (hash(x)=29804750) +2698 train 7.684789 (lr=7.4144e-05) (hash(x)=28443583) +2699 train 7.616715 (lr=7.4101e-05) (hash(x)=29156288) +2700 val loss 7.2841 +2700 val perplexity 1456.8771 +2700 train 7.334617 (lr=7.4059e-05) (hash(x)=25895743) +2701 train 6.934385 (lr=7.4017e-05) (hash(x)=21173795) +2702 train 6.816939 (lr=7.3975e-05) (hash(x)=20790866) +2703 train 7.435020 (lr=7.3933e-05) (hash(x)=27706477) +2704 train 7.521756 (lr=7.3891e-05) (hash(x)=30358985) +2705 train 7.121882 (lr=7.3849e-05) (hash(x)=23548492) +2706 train 7.258325 (lr=7.3807e-05) (hash(x)=25879696) +2707 train 7.141647 (lr=7.3765e-05) (hash(x)=23711800) +2708 train 7.626169 (lr=7.3723e-05) (hash(x)=28763123) +2709 train 7.275274 (lr=7.3681e-05) (hash(x)=23327642) +2710 train 7.334448 (lr=7.3639e-05) (hash(x)=25634166) +2711 train 7.221578 (lr=7.3597e-05) (hash(x)=28684175) +2712 train 7.333028 (lr=7.3555e-05) (hash(x)=23996278) +2713 train 6.944966 (lr=7.3513e-05) (hash(x)=21795980) +2714 train 7.273337 (lr=7.3470e-05) (hash(x)=24840769) +2715 train 7.187393 (lr=7.3428e-05) (hash(x)=25225466) +2716 train 7.518455 (lr=7.3386e-05) (hash(x)=27500471) +2717 train 7.187406 (lr=7.3344e-05) (hash(x)=24703036) +2718 train 7.327531 (lr=7.3302e-05) (hash(x)=24294293) +2719 train 7.276319 (lr=7.3260e-05) (hash(x)=28003600) +2720 train 7.002933 (lr=7.3218e-05) (hash(x)=22822962) +2721 train 6.905117 (lr=7.3176e-05) (hash(x)=24189246) +2722 train 7.027326 (lr=7.3134e-05) (hash(x)=22608951) +2723 train 7.716028 (lr=7.3092e-05) (hash(x)=27989890) +2724 train 7.371746 (lr=7.3050e-05) (hash(x)=24175838) +2725 train 7.255520 (lr=7.3008e-05) (hash(x)=24781792) +2726 train 7.062423 (lr=7.2966e-05) (hash(x)=23413276) +2727 train 7.515473 (lr=7.2924e-05) (hash(x)=27586845) +2728 train 7.268528 (lr=7.2882e-05) (hash(x)=27336264) +2729 train 7.365137 (lr=7.2840e-05) (hash(x)=26808464) +2730 train 7.152097 (lr=7.2798e-05) (hash(x)=22312009) +2731 train 7.200985 (lr=7.2756e-05) (hash(x)=22373927) +2732 train 7.157932 (lr=7.2714e-05) (hash(x)=23428834) +2733 train 7.147136 (lr=7.2672e-05) (hash(x)=25304441) +2734 train 7.183858 (lr=7.2630e-05) (hash(x)=24798164) +2735 train 6.987289 (lr=7.2588e-05) (hash(x)=21176405) +2736 train 7.097172 (lr=7.2547e-05) (hash(x)=22343075) +2737 train 7.131382 (lr=7.2505e-05) (hash(x)=23825332) +2738 train 7.180363 (lr=7.2463e-05) (hash(x)=24191865) +2739 train 6.997946 (lr=7.2421e-05) (hash(x)=23806052) +2740 train 7.053807 (lr=7.2379e-05) (hash(x)=21764591) +2741 train 7.172872 (lr=7.2337e-05) (hash(x)=25548695) +2742 train 7.391529 (lr=7.2295e-05) (hash(x)=26847535) +2743 train 7.093987 (lr=7.2253e-05) (hash(x)=25888433) +2744 train 7.096614 (lr=7.2211e-05) (hash(x)=24327454) +2745 train 6.975482 (lr=7.2169e-05) (hash(x)=22543301) +2746 train 7.446204 (lr=7.2127e-05) (hash(x)=24593022) +2747 train 8.102130 (lr=7.2085e-05) (hash(x)=27797727) +2748 train 7.498378 (lr=7.2043e-05) (hash(x)=28067682) +2749 train 7.099786 (lr=7.2001e-05) (hash(x)=25278538) +2750 val loss 7.2712 +2750 val perplexity 1438.3456 +2750 train 7.054852 (lr=7.1960e-05) (hash(x)=23875731) +2751 train 7.249107 (lr=7.1918e-05) (hash(x)=27916982) +2752 train 7.210107 (lr=7.1876e-05) (hash(x)=25726799) +2753 train 7.076332 (lr=7.1834e-05) (hash(x)=25227141) +2754 train 7.322216 (lr=7.1792e-05) (hash(x)=27679212) +2755 train 7.031523 (lr=7.1750e-05) (hash(x)=24621793) +2756 train 6.976003 (lr=7.1708e-05) (hash(x)=21962296) +2757 train 7.280547 (lr=7.1666e-05) (hash(x)=24899679) +2758 train 7.003519 (lr=7.1624e-05) (hash(x)=21452158) +2759 train 7.085799 (lr=7.1583e-05) (hash(x)=24334708) +2760 train 7.332556 (lr=7.1541e-05) (hash(x)=25523041) +2761 train 7.469636 (lr=7.1499e-05) (hash(x)=30389813) +2762 train 7.007007 (lr=7.1457e-05) (hash(x)=22426014) +2763 train 7.101192 (lr=7.1415e-05) (hash(x)=24419143) +2764 train 7.170202 (lr=7.1373e-05) (hash(x)=24850536) +2765 train 7.267557 (lr=7.1332e-05) (hash(x)=24181393) +2766 train 6.763300 (lr=7.1290e-05) (hash(x)=18882503) +2767 train 7.265455 (lr=7.1248e-05) (hash(x)=25617709) +2768 train 7.178847 (lr=7.1206e-05) (hash(x)=24076662) +2769 train 7.087470 (lr=7.1164e-05) (hash(x)=21656802) +2770 train 7.040777 (lr=7.1122e-05) (hash(x)=21014265) +2771 train 7.208316 (lr=7.1081e-05) (hash(x)=24556034) +2772 train 6.964212 (lr=7.1039e-05) (hash(x)=22046665) +2773 train 7.227165 (lr=7.0997e-05) (hash(x)=26761579) +2774 train 8.723167 (lr=7.0955e-05) (hash(x)=41414315) +2775 train 7.128966 (lr=7.0913e-05) (hash(x)=25152362) +2776 train 7.311177 (lr=7.0872e-05) (hash(x)=25567641) +2777 train 7.229510 (lr=7.0830e-05) (hash(x)=25427935) +2778 train 7.315529 (lr=7.0788e-05) (hash(x)=25824457) +2779 train 7.229071 (lr=7.0746e-05) (hash(x)=24326376) +2780 train 7.252223 (lr=7.0704e-05) (hash(x)=27447230) +2781 train 7.126862 (lr=7.0663e-05) (hash(x)=24003710) +2782 train 7.034348 (lr=7.0621e-05) (hash(x)=24157390) +2783 train 7.114339 (lr=7.0579e-05) (hash(x)=24276512) +2784 train 6.943647 (lr=7.0537e-05) (hash(x)=21503752) +2785 train 6.851837 (lr=7.0496e-05) (hash(x)=20031488) +2786 train 6.923950 (lr=7.0454e-05) (hash(x)=21788715) +2787 train 7.118770 (lr=7.0412e-05) (hash(x)=24344695) +2788 train 7.156787 (lr=7.0371e-05) (hash(x)=22927763) +2789 train 7.028705 (lr=7.0329e-05) (hash(x)=23710755) +2790 train 7.271059 (lr=7.0287e-05) (hash(x)=26924620) +2791 train 7.650572 (lr=7.0245e-05) (hash(x)=26776133) +2792 train 7.043587 (lr=7.0204e-05) (hash(x)=19936770) +2793 train 7.219668 (lr=7.0162e-05) (hash(x)=25440959) +2794 train 7.187032 (lr=7.0120e-05) (hash(x)=25146097) +2795 train 6.950494 (lr=7.0079e-05) (hash(x)=21847282) +2796 train 7.148767 (lr=7.0037e-05) (hash(x)=25639784) +2797 train 6.935390 (lr=6.9995e-05) (hash(x)=21199921) +2798 train 7.133569 (lr=6.9953e-05) (hash(x)=22360806) +2799 train 6.592790 (lr=6.9912e-05) (hash(x)=20254159) +2800 val loss 7.2563 +2800 val perplexity 1416.9357 +2800 train 6.773027 (lr=6.9870e-05) (hash(x)=23348345) +2801 train 7.338662 (lr=6.9828e-05) (hash(x)=24908033) +2802 train 7.110130 (lr=6.9787e-05) (hash(x)=23350309) +2803 train 7.172745 (lr=6.9745e-05) (hash(x)=25044762) +2804 train 7.061403 (lr=6.9703e-05) (hash(x)=24071026) +2805 train 6.875687 (lr=6.9662e-05) (hash(x)=22169363) +2806 train 7.148582 (lr=6.9620e-05) (hash(x)=23757564) +2807 train 7.593606 (lr=6.9579e-05) (hash(x)=27873855) +2808 train 7.316032 (lr=6.9537e-05) (hash(x)=26577893) +2809 train 7.385612 (lr=6.9495e-05) (hash(x)=27001634) +2810 train 7.158884 (lr=6.9454e-05) (hash(x)=24796541) +2811 train 7.072173 (lr=6.9412e-05) (hash(x)=22575615) +2812 train 7.175344 (lr=6.9370e-05) (hash(x)=25876475) +2813 train 7.174271 (lr=6.9329e-05) (hash(x)=24765155) +2814 train 7.116386 (lr=6.9287e-05) (hash(x)=25785699) +2815 train 7.314737 (lr=6.9246e-05) (hash(x)=25113614) +2816 train 7.182402 (lr=6.9204e-05) (hash(x)=24415748) +2817 train 7.306217 (lr=6.9162e-05) (hash(x)=25140622) +2818 train 7.161446 (lr=6.9121e-05) (hash(x)=24845866) +2819 train 7.631583 (lr=6.9079e-05) (hash(x)=28062905) +2820 train 7.154811 (lr=6.9038e-05) (hash(x)=22041086) +2821 train 7.257602 (lr=6.8996e-05) (hash(x)=24957184) +2822 train 7.181183 (lr=6.8955e-05) (hash(x)=24360380) +2823 train 7.306068 (lr=6.8913e-05) (hash(x)=26192886) +2824 train 7.197168 (lr=6.8871e-05) (hash(x)=25001858) +2825 train 7.155009 (lr=6.8830e-05) (hash(x)=24721193) +2826 train 7.212135 (lr=6.8788e-05) (hash(x)=26186227) +2827 train 7.190857 (lr=6.8747e-05) (hash(x)=25770338) +2828 train 7.254528 (lr=6.8705e-05) (hash(x)=25920767) +2829 train 7.185800 (lr=6.8664e-05) (hash(x)=25060684) +2830 train 6.871077 (lr=6.8622e-05) (hash(x)=22933946) +2831 train 7.049675 (lr=6.8581e-05) (hash(x)=24614912) +2832 train 6.791728 (lr=6.8539e-05) (hash(x)=19955522) +2833 train 6.864340 (lr=6.8498e-05) (hash(x)=21111215) +2834 train 7.727947 (lr=6.8456e-05) (hash(x)=28817924) +2835 train 7.247640 (lr=6.8415e-05) (hash(x)=26934071) +2836 train 7.168293 (lr=6.8373e-05) (hash(x)=24768851) +2837 train 7.126374 (lr=6.8332e-05) (hash(x)=25706447) +2838 train 6.957653 (lr=6.8290e-05) (hash(x)=19579834) +2839 train 7.159551 (lr=6.8249e-05) (hash(x)=25397093) +2840 train 7.662645 (lr=6.8207e-05) (hash(x)=27902141) +2841 train 7.228677 (lr=6.8166e-05) (hash(x)=25383069) +2842 train 7.009963 (lr=6.8125e-05) (hash(x)=22007373) +2843 train 7.108209 (lr=6.8083e-05) (hash(x)=25925963) +2844 train 7.148732 (lr=6.8042e-05) (hash(x)=25711128) +2845 train 6.927975 (lr=6.8000e-05) (hash(x)=21881216) +2846 train 7.039178 (lr=6.7959e-05) (hash(x)=20277075) +2847 train 7.076804 (lr=6.7917e-05) (hash(x)=19811802) +2848 train 7.030718 (lr=6.7876e-05) (hash(x)=23878906) +2849 train 7.258907 (lr=6.7835e-05) (hash(x)=25034966) +2850 val loss 7.2461 +2850 val perplexity 1402.6312 +2850 train 7.320281 (lr=6.7793e-05) (hash(x)=24359507) +2851 train 7.053188 (lr=6.7752e-05) (hash(x)=23248423) +2852 train 7.048946 (lr=6.7710e-05) (hash(x)=21782773) +2853 train 7.195138 (lr=6.7669e-05) (hash(x)=23804418) +2854 train 7.240523 (lr=6.7628e-05) (hash(x)=22525078) +2855 train 7.187768 (lr=6.7586e-05) (hash(x)=25579655) +2856 train 7.314970 (lr=6.7545e-05) (hash(x)=27048876) +2857 train 7.425292 (lr=6.7503e-05) (hash(x)=26468479) +2858 train 7.115472 (lr=6.7462e-05) (hash(x)=23854933) +2859 train 7.502890 (lr=6.7421e-05) (hash(x)=25537603) +2860 train 6.908300 (lr=6.7379e-05) (hash(x)=20979252) +2861 train 7.487079 (lr=6.7338e-05) (hash(x)=26504374) +2862 train 7.279373 (lr=6.7297e-05) (hash(x)=27561842) +2863 train 7.289295 (lr=6.7255e-05) (hash(x)=26096514) +2864 train 7.282904 (lr=6.7214e-05) (hash(x)=25926899) +2865 train 7.275669 (lr=6.7173e-05) (hash(x)=26058348) +2866 train 7.316411 (lr=6.7131e-05) (hash(x)=29802259) +2867 train 7.242168 (lr=6.7090e-05) (hash(x)=24132888) +2868 train 6.956578 (lr=6.7049e-05) (hash(x)=23369410) +2869 train 7.117563 (lr=6.7008e-05) (hash(x)=25387506) +2870 train 7.315714 (lr=6.6966e-05) (hash(x)=27375344) +2871 train 7.043509 (lr=6.6925e-05) (hash(x)=22589633) +2872 train 7.182031 (lr=6.6884e-05) (hash(x)=23250237) +2873 train 7.090219 (lr=6.6842e-05) (hash(x)=25511322) +2874 train 6.782417 (lr=6.6801e-05) (hash(x)=18356418) +2875 train 7.173875 (lr=6.6760e-05) (hash(x)=27781566) +2876 train 7.017122 (lr=6.6719e-05) (hash(x)=24878173) +2877 train 7.558875 (lr=6.6677e-05) (hash(x)=30018637) +2878 train 7.406685 (lr=6.6636e-05) (hash(x)=27168416) +2879 train 7.393531 (lr=6.6595e-05) (hash(x)=26757147) +2880 train 7.400821 (lr=6.6554e-05) (hash(x)=26637081) +2881 train 7.284401 (lr=6.6513e-05) (hash(x)=24795024) +2882 train 7.556928 (lr=6.6471e-05) (hash(x)=29787745) +2883 train 7.380370 (lr=6.6430e-05) (hash(x)=26649864) +2884 train 7.201478 (lr=6.6389e-05) (hash(x)=27306612) +2885 train 7.314903 (lr=6.6348e-05) (hash(x)=27568311) +2886 train 7.338214 (lr=6.6307e-05) (hash(x)=27440150) +2887 train 7.094035 (lr=6.6265e-05) (hash(x)=24963730) +2888 train 7.089737 (lr=6.6224e-05) (hash(x)=23619807) +2889 train 7.590632 (lr=6.6183e-05) (hash(x)=29447356) +2890 train 7.096538 (lr=6.6142e-05) (hash(x)=25144675) +2891 train 7.042937 (lr=6.6101e-05) (hash(x)=25249959) +2892 train 7.060583 (lr=6.6060e-05) (hash(x)=26608712) +2893 train 7.080840 (lr=6.6018e-05) (hash(x)=26333258) +2894 train 6.873219 (lr=6.5977e-05) (hash(x)=20682182) +2895 train 7.289177 (lr=6.5936e-05) (hash(x)=27703124) +2896 train 7.085350 (lr=6.5895e-05) (hash(x)=23228180) +2897 train 6.970671 (lr=6.5854e-05) (hash(x)=25252411) +2898 train 6.932730 (lr=6.5813e-05) (hash(x)=22879178) +2899 train 7.233190 (lr=6.5772e-05) (hash(x)=26459082) +2900 val loss 7.2459 +2900 val perplexity 1402.3730 +2900 train 7.049414 (lr=6.5731e-05) (hash(x)=24569501) +2901 train 6.873092 (lr=6.5690e-05) (hash(x)=19803884) +2902 train 6.929083 (lr=6.5649e-05) (hash(x)=18799747) +2903 train 7.205794 (lr=6.5607e-05) (hash(x)=24781713) +2904 train 7.356137 (lr=6.5566e-05) (hash(x)=25016590) +2905 train 7.537268 (lr=6.5525e-05) (hash(x)=29006906) +2906 train 7.278700 (lr=6.5484e-05) (hash(x)=24069959) +2907 train 7.468099 (lr=6.5443e-05) (hash(x)=26597693) +2908 train 7.038522 (lr=6.5402e-05) (hash(x)=25014146) +2909 train 7.280867 (lr=6.5361e-05) (hash(x)=24943747) +2910 train 7.199217 (lr=6.5320e-05) (hash(x)=27847542) +2911 train 7.132949 (lr=6.5279e-05) (hash(x)=24720476) +2912 train 6.989066 (lr=6.5238e-05) (hash(x)=24388804) +2913 train 7.132129 (lr=6.5197e-05) (hash(x)=23567535) +2914 train 7.401938 (lr=6.5156e-05) (hash(x)=29673625) +2915 train 7.154475 (lr=6.5115e-05) (hash(x)=23691295) +2916 train 7.535368 (lr=6.5074e-05) (hash(x)=26572819) +2917 train 7.184894 (lr=6.5033e-05) (hash(x)=23237812) +2918 train 7.421592 (lr=6.4992e-05) (hash(x)=26531016) +2919 train 6.962270 (lr=6.4951e-05) (hash(x)=23481301) +2920 train 7.270001 (lr=6.4910e-05) (hash(x)=24839184) +2921 train 7.104662 (lr=6.4869e-05) (hash(x)=23327755) +2922 train 7.329740 (lr=6.4828e-05) (hash(x)=26347114) +2923 train 7.028687 (lr=6.4787e-05) (hash(x)=23295676) +2924 train 7.097627 (lr=6.4746e-05) (hash(x)=24557178) +2925 train 7.151073 (lr=6.4706e-05) (hash(x)=26067788) +2926 train 7.060817 (lr=6.4665e-05) (hash(x)=25694982) +2927 train 7.163858 (lr=6.4624e-05) (hash(x)=25641033) +2928 train 7.207744 (lr=6.4583e-05) (hash(x)=24906422) +2929 train 7.398190 (lr=6.4542e-05) (hash(x)=27803515) +2930 train 7.371894 (lr=6.4501e-05) (hash(x)=26208803) +2931 train 6.841254 (lr=6.4460e-05) (hash(x)=22441379) +2932 train 7.121990 (lr=6.4419e-05) (hash(x)=24741626) +2933 train 6.992866 (lr=6.4378e-05) (hash(x)=24595257) +2934 train 7.061710 (lr=6.4338e-05) (hash(x)=23939167) +2935 train 7.339034 (lr=6.4297e-05) (hash(x)=27369437) +2936 train 6.970576 (lr=6.4256e-05) (hash(x)=21409783) +2937 train 7.252066 (lr=6.4215e-05) (hash(x)=25923735) +2938 train 7.258795 (lr=6.4174e-05) (hash(x)=29559511) +2939 train 7.114534 (lr=6.4133e-05) (hash(x)=24482272) +2940 train 7.118141 (lr=6.4093e-05) (hash(x)=24767658) +2941 train 7.309386 (lr=6.4052e-05) (hash(x)=26425020) +2942 train 7.669001 (lr=6.4011e-05) (hash(x)=27444868) +2943 train 7.123859 (lr=6.3970e-05) (hash(x)=24760900) +2944 train 7.174453 (lr=6.3929e-05) (hash(x)=25605407) +2945 train 7.062167 (lr=6.3889e-05) (hash(x)=22886951) +2946 train 7.351193 (lr=6.3848e-05) (hash(x)=26112205) +2947 train 7.200685 (lr=6.3807e-05) (hash(x)=23919156) +2948 train 7.158202 (lr=6.3766e-05) (hash(x)=23729312) +2949 train 7.391688 (lr=6.3726e-05) (hash(x)=30440878) +2950 val loss 7.2495 +2950 val perplexity 1407.3752 +2950 train 6.906147 (lr=6.3685e-05) (hash(x)=20004041) +2951 train 6.865425 (lr=6.3644e-05) (hash(x)=21692546) +2952 train 6.929765 (lr=6.3603e-05) (hash(x)=23021681) +2953 train 7.290946 (lr=6.3563e-05) (hash(x)=26663597) +2954 train 7.123088 (lr=6.3522e-05) (hash(x)=23727385) +2955 train 7.146905 (lr=6.3481e-05) (hash(x)=27692087) +2956 train 7.148920 (lr=6.3441e-05) (hash(x)=24003378) +2957 train 7.817894 (lr=6.3400e-05) (hash(x)=29534673) +2958 train 7.043297 (lr=6.3359e-05) (hash(x)=22875068) +2959 train 7.036452 (lr=6.3318e-05) (hash(x)=22720391) +2960 train 6.817276 (lr=6.3278e-05) (hash(x)=17997400) +2961 train 7.033055 (lr=6.3237e-05) (hash(x)=22853822) +2962 train 7.120912 (lr=6.3196e-05) (hash(x)=25238004) +2963 train 7.239944 (lr=6.3156e-05) (hash(x)=26146560) +2964 train 7.374069 (lr=6.3115e-05) (hash(x)=21894867) +2965 train 7.361858 (lr=6.3075e-05) (hash(x)=23001150) +2966 train 7.028850 (lr=6.3034e-05) (hash(x)=23392923) +2967 train 7.093961 (lr=6.2993e-05) (hash(x)=24376979) +2968 train 7.080553 (lr=6.2953e-05) (hash(x)=23781449) +2969 train 7.212060 (lr=6.2912e-05) (hash(x)=25315495) +2970 train 7.359613 (lr=6.2872e-05) (hash(x)=27165470) +2971 train 7.188875 (lr=6.2831e-05) (hash(x)=22917712) +2972 train 7.530580 (lr=6.2790e-05) (hash(x)=27928456) +2973 train 6.934373 (lr=6.2750e-05) (hash(x)=19890855) +2974 train 6.898331 (lr=6.2709e-05) (hash(x)=21318134) +2975 train 7.026333 (lr=6.2669e-05) (hash(x)=22244509) +2976 train 6.918352 (lr=6.2628e-05) (hash(x)=21293137) +2977 train 7.053320 (lr=6.2588e-05) (hash(x)=23465789) +2978 train 7.030521 (lr=6.2547e-05) (hash(x)=21169753) +2979 train 7.392714 (lr=6.2507e-05) (hash(x)=25243385) +2980 train 7.415749 (lr=6.2466e-05) (hash(x)=27465812) +2981 train 7.126834 (lr=6.2426e-05) (hash(x)=24615492) +2982 train 7.069215 (lr=6.2385e-05) (hash(x)=23081307) +2983 train 6.813109 (lr=6.2345e-05) (hash(x)=21831960) +2984 train 6.947968 (lr=6.2304e-05) (hash(x)=23242850) +2985 train 7.070784 (lr=6.2264e-05) (hash(x)=24308188) +2986 train 7.268730 (lr=6.2223e-05) (hash(x)=28541601) +2987 train 7.158374 (lr=6.2183e-05) (hash(x)=24842373) +2988 train 6.878001 (lr=6.2142e-05) (hash(x)=21967126) +2989 train 7.094290 (lr=6.2102e-05) (hash(x)=22951616) +2990 train 7.172090 (lr=6.2061e-05) (hash(x)=24325714) +2991 train 7.007131 (lr=6.2021e-05) (hash(x)=24921535) +2992 train 7.230857 (lr=6.1981e-05) (hash(x)=25937112) +2993 train 6.920949 (lr=6.1940e-05) (hash(x)=20716218) +2994 train 7.175223 (lr=6.1900e-05) (hash(x)=25450724) +2995 train 7.125850 (lr=6.1859e-05) (hash(x)=24344615) +2996 train 6.858295 (lr=6.1819e-05) (hash(x)=20299058) +2997 train 7.136715 (lr=6.1779e-05) (hash(x)=23859426) +2998 train 7.115419 (lr=6.1738e-05) (hash(x)=23094397) +2999 train 7.388107 (lr=6.1698e-05) (hash(x)=25381251) +3000 val loss 7.2415 +3000 val perplexity 1396.2391 +3000 train 7.151254 (lr=6.1657e-05) (hash(x)=23586527) +3001 train 7.019939 (lr=6.1617e-05) (hash(x)=24220410) +3002 train 6.914127 (lr=6.1577e-05) (hash(x)=20597347) +3003 train 7.014612 (lr=6.1536e-05) (hash(x)=22887303) +3004 train 7.314167 (lr=6.1496e-05) (hash(x)=25869462) +3005 train 7.035871 (lr=6.1456e-05) (hash(x)=22098530) +3006 train 7.302182 (lr=6.1416e-05) (hash(x)=26246291) +3007 train 7.242986 (lr=6.1375e-05) (hash(x)=25687352) +3008 train 7.007713 (lr=6.1335e-05) (hash(x)=25425646) +3009 train 7.202586 (lr=6.1295e-05) (hash(x)=26021124) +3010 train 7.229015 (lr=6.1254e-05) (hash(x)=25392057) +3011 train 7.332593 (lr=6.1214e-05) (hash(x)=27791412) +3012 train 7.118815 (lr=6.1174e-05) (hash(x)=23181098) +3013 train 7.152612 (lr=6.1134e-05) (hash(x)=25521889) +3014 train 6.962357 (lr=6.1093e-05) (hash(x)=21685795) +3015 train 7.125618 (lr=6.1053e-05) (hash(x)=25221654) +3016 train 7.300643 (lr=6.1013e-05) (hash(x)=24888744) +3017 train 7.191012 (lr=6.0973e-05) (hash(x)=24200150) +3018 train 7.141618 (lr=6.0933e-05) (hash(x)=26943942) +3019 train 7.124892 (lr=6.0892e-05) (hash(x)=23243731) +3020 train 6.967113 (lr=6.0852e-05) (hash(x)=21068284) +3021 train 7.166547 (lr=6.0812e-05) (hash(x)=23876902) +3022 train 7.285546 (lr=6.0772e-05) (hash(x)=25337639) +3023 train 7.176492 (lr=6.0732e-05) (hash(x)=24469863) +3024 train 7.655034 (lr=6.0692e-05) (hash(x)=27850876) +3025 train 7.461496 (lr=6.0651e-05) (hash(x)=20515778) +3026 train 7.269203 (lr=6.0611e-05) (hash(x)=29019173) +3027 train 6.902063 (lr=6.0571e-05) (hash(x)=22484936) +3028 train 7.063681 (lr=6.0531e-05) (hash(x)=24639400) +3029 train 7.226335 (lr=6.0491e-05) (hash(x)=26835174) +3030 train 7.359701 (lr=6.0451e-05) (hash(x)=29843763) +3031 train 7.083749 (lr=6.0411e-05) (hash(x)=25291413) +3032 train 7.043733 (lr=6.0371e-05) (hash(x)=24590244) +3033 train 7.235220 (lr=6.0331e-05) (hash(x)=28880142) +3034 train 7.027939 (lr=6.0291e-05) (hash(x)=23372199) +3035 train 6.988941 (lr=6.0250e-05) (hash(x)=23952225) +3036 train 7.157613 (lr=6.0210e-05) (hash(x)=24589186) +3037 train 7.107957 (lr=6.0170e-05) (hash(x)=23260323) +3038 train 7.260315 (lr=6.0130e-05) (hash(x)=25824498) +3039 train 7.202658 (lr=6.0090e-05) (hash(x)=25744274) +3040 train 7.171266 (lr=6.0050e-05) (hash(x)=21610247) +3041 train 7.280822 (lr=6.0010e-05) (hash(x)=25079786) +3042 train 6.933307 (lr=5.9970e-05) (hash(x)=23219195) +3043 train 6.877429 (lr=5.9930e-05) (hash(x)=22616739) +3044 train 7.169061 (lr=5.9890e-05) (hash(x)=24908480) +3045 train 7.009451 (lr=5.9850e-05) (hash(x)=22293489) +3046 train 7.043562 (lr=5.9810e-05) (hash(x)=23557651) +3047 train 7.087030 (lr=5.9771e-05) (hash(x)=24246963) +3048 train 7.194356 (lr=5.9731e-05) (hash(x)=24490083) +3049 train 7.220139 (lr=5.9691e-05) (hash(x)=22372895) +3050 val loss 7.2409 +3050 val perplexity 1395.3394 +3050 train 6.941085 (lr=5.9651e-05) (hash(x)=21759470) +3051 train 6.812764 (lr=5.9611e-05) (hash(x)=19407094) +3052 train 7.189447 (lr=5.9571e-05) (hash(x)=23957047) +3053 train 7.282118 (lr=5.9531e-05) (hash(x)=24719318) +3054 train 7.046317 (lr=5.9491e-05) (hash(x)=20719314) +3055 train 6.988994 (lr=5.9451e-05) (hash(x)=19724058) +3056 train 6.841704 (lr=5.9411e-05) (hash(x)=14407266) +3057 train 6.708889 (lr=5.9372e-05) (hash(x)=12468292) +3058 train 6.952165 (lr=5.9332e-05) (hash(x)=16098279) +3059 train 7.049846 (lr=5.9292e-05) (hash(x)=18836491) +3060 train 6.890355 (lr=5.9252e-05) (hash(x)=19132277) +3061 train 7.017404 (lr=5.9212e-05) (hash(x)=22814208) +3062 train 7.087346 (lr=5.9172e-05) (hash(x)=24838508) +3063 train 6.978889 (lr=5.9133e-05) (hash(x)=20705649) +3064 train 8.046498 (lr=5.9093e-05) (hash(x)=29416914) +3065 train 7.444792 (lr=5.9053e-05) (hash(x)=25972430) +3066 train 6.809605 (lr=5.9013e-05) (hash(x)=23705805) +3067 train 6.873817 (lr=5.8974e-05) (hash(x)=21325875) +3068 train 7.100693 (lr=5.8934e-05) (hash(x)=23526506) +3069 train 7.575131 (lr=5.8894e-05) (hash(x)=27282337) +3070 train 7.422306 (lr=5.8854e-05) (hash(x)=27968043) +3071 train 7.241570 (lr=5.8815e-05) (hash(x)=24938685) +3072 train 7.441571 (lr=5.8775e-05) (hash(x)=26942737) +3073 train 7.328861 (lr=5.8735e-05) (hash(x)=23506879) +3074 train 7.025355 (lr=5.8695e-05) (hash(x)=23589913) +3075 train 7.217459 (lr=5.8656e-05) (hash(x)=25152403) +3076 train 7.316381 (lr=5.8616e-05) (hash(x)=23425868) +3077 train 7.595808 (lr=5.8576e-05) (hash(x)=23966181) +3078 train 7.582542 (lr=5.8537e-05) (hash(x)=27312570) +3079 train 7.144685 (lr=5.8497e-05) (hash(x)=21707000) +3080 train 7.104912 (lr=5.8457e-05) (hash(x)=25600427) +3081 train 7.223728 (lr=5.8418e-05) (hash(x)=24270631) +3082 train 7.332902 (lr=5.8378e-05) (hash(x)=25199537) +3083 train 6.622687 (lr=5.8339e-05) (hash(x)=17952018) +3084 train 6.746414 (lr=5.8299e-05) (hash(x)=18733143) +3085 train 7.367571 (lr=5.8259e-05) (hash(x)=26946100) +3086 train 7.172871 (lr=5.8220e-05) (hash(x)=25547515) +3087 train 7.135817 (lr=5.8180e-05) (hash(x)=24948980) +3088 train 8.455967 (lr=5.8141e-05) (hash(x)=35461645) +3089 train 7.375638 (lr=5.8101e-05) (hash(x)=28330877) +3090 train 7.263057 (lr=5.8062e-05) (hash(x)=27687861) +3091 train 7.404186 (lr=5.8022e-05) (hash(x)=28012110) +3092 train 7.260379 (lr=5.7982e-05) (hash(x)=24684480) +3093 train 7.217412 (lr=5.7943e-05) (hash(x)=26225786) +3094 train 6.896442 (lr=5.7903e-05) (hash(x)=23098156) +3095 train 7.500735 (lr=5.7864e-05) (hash(x)=30773958) +3096 train 7.801897 (lr=5.7824e-05) (hash(x)=28640406) +3097 train 7.716417 (lr=5.7785e-05) (hash(x)=28201086) +3098 train 8.113207 (lr=5.7745e-05) (hash(x)=35002344) +3099 train 7.663924 (lr=5.7706e-05) (hash(x)=29481068) +3100 val loss 7.2503 +3100 val perplexity 1408.5938 +3100 train 7.138008 (lr=5.7667e-05) (hash(x)=26374528) +3101 train 7.127319 (lr=5.7627e-05) (hash(x)=24153602) +3102 train 7.178334 (lr=5.7588e-05) (hash(x)=25478746) +3103 train 7.458254 (lr=5.7548e-05) (hash(x)=26769046) +3104 train 7.094960 (lr=5.7509e-05) (hash(x)=21841970) +3105 train 7.356673 (lr=5.7469e-05) (hash(x)=27693052) +3106 train 6.881326 (lr=5.7430e-05) (hash(x)=20689448) +3107 train 7.213788 (lr=5.7391e-05) (hash(x)=26755048) +3108 train 7.237819 (lr=5.7351e-05) (hash(x)=24431904) +3109 train 7.080688 (lr=5.7312e-05) (hash(x)=21009792) +3110 train 7.128336 (lr=5.7273e-05) (hash(x)=21909003) +3111 train 7.209841 (lr=5.7233e-05) (hash(x)=18849656) +3112 train 7.282306 (lr=5.7194e-05) (hash(x)=22223376) +3113 train 7.559467 (lr=5.7155e-05) (hash(x)=25652491) +3114 train 7.455456 (lr=5.7115e-05) (hash(x)=23521434) +3115 train 7.529547 (lr=5.7076e-05) (hash(x)=25449800) +3116 train 7.912096 (lr=5.7037e-05) (hash(x)=27655847) +3117 train 7.999158 (lr=5.6997e-05) (hash(x)=29878248) +3118 train 8.037463 (lr=5.6958e-05) (hash(x)=30444094) +3119 train 7.662141 (lr=5.6919e-05) (hash(x)=24624950) +3120 train 6.905144 (lr=5.6880e-05) (hash(x)=20798511) +3121 train 7.306411 (lr=5.6840e-05) (hash(x)=26581679) +3122 train 7.220646 (lr=5.6801e-05) (hash(x)=25333422) +3123 train 7.253381 (lr=5.6762e-05) (hash(x)=26174069) +3124 train 7.316833 (lr=5.6723e-05) (hash(x)=25219475) +3125 train 7.250081 (lr=5.6684e-05) (hash(x)=20919061) +3126 train 7.152673 (lr=5.6644e-05) (hash(x)=23828688) +3127 train 7.727535 (lr=5.6605e-05) (hash(x)=27299605) +3128 train 7.049673 (lr=5.6566e-05) (hash(x)=23797514) +3129 train 7.287460 (lr=5.6527e-05) (hash(x)=23601883) +3130 train 7.462506 (lr=5.6488e-05) (hash(x)=31003964) +3131 train 7.224834 (lr=5.6449e-05) (hash(x)=24777273) +3132 train 7.122869 (lr=5.6409e-05) (hash(x)=25403249) +3133 train 7.341417 (lr=5.6370e-05) (hash(x)=28913150) +3134 train 7.303003 (lr=5.6331e-05) (hash(x)=26541508) +3135 train 7.249717 (lr=5.6292e-05) (hash(x)=24113445) +3136 train 7.031651 (lr=5.6253e-05) (hash(x)=25464565) +3137 train 7.284196 (lr=5.6214e-05) (hash(x)=26581432) +3138 train 7.149943 (lr=5.6175e-05) (hash(x)=23074513) +3139 train 7.026116 (lr=5.6136e-05) (hash(x)=23970384) +3140 train 7.266170 (lr=5.6097e-05) (hash(x)=26694495) +3141 train 7.229058 (lr=5.6058e-05) (hash(x)=26883445) +3142 train 7.374876 (lr=5.6019e-05) (hash(x)=28632211) +3143 train 7.834934 (lr=5.5980e-05) (hash(x)=32644465) +3144 train 7.572044 (lr=5.5941e-05) (hash(x)=27490443) +3145 train 7.119316 (lr=5.5902e-05) (hash(x)=23814853) +3146 train 7.551825 (lr=5.5863e-05) (hash(x)=29664236) +3147 train 7.846190 (lr=5.5824e-05) (hash(x)=29951548) +3148 train 7.629488 (lr=5.5785e-05) (hash(x)=28426503) +3149 train 6.998903 (lr=5.5746e-05) (hash(x)=23727657) +3150 val loss 7.2573 +3150 val perplexity 1418.3619 +3150 train 7.140289 (lr=5.5707e-05) (hash(x)=21430659) +3151 train 7.194149 (lr=5.5668e-05) (hash(x)=25829219) +3152 train 7.379383 (lr=5.5629e-05) (hash(x)=29735208) +3153 train 7.429334 (lr=5.5590e-05) (hash(x)=28173447) +3154 train 7.091145 (lr=5.5551e-05) (hash(x)=22909641) +3155 train 7.279197 (lr=5.5512e-05) (hash(x)=20556094) +3156 train 7.043412 (lr=5.5474e-05) (hash(x)=24013769) +3157 train 7.020221 (lr=5.5435e-05) (hash(x)=22525971) +3158 train 7.130405 (lr=5.5396e-05) (hash(x)=25492728) +3159 train 7.164354 (lr=5.5357e-05) (hash(x)=25194550) +3160 train 7.252380 (lr=5.5318e-05) (hash(x)=25610603) +3161 train 7.242287 (lr=5.5279e-05) (hash(x)=23848640) +3162 train 7.043143 (lr=5.5240e-05) (hash(x)=24082226) +3163 train 7.433879 (lr=5.5202e-05) (hash(x)=28482186) +3164 train 7.324866 (lr=5.5163e-05) (hash(x)=27542978) +3165 train 7.070454 (lr=5.5124e-05) (hash(x)=22540954) +3166 train 7.236292 (lr=5.5085e-05) (hash(x)=26103641) +3167 train 7.157455 (lr=5.5047e-05) (hash(x)=25941804) +3168 train 7.166978 (lr=5.5008e-05) (hash(x)=25965921) +3169 train 7.437710 (lr=5.4969e-05) (hash(x)=25631269) +3170 train 7.012679 (lr=5.4930e-05) (hash(x)=23471525) +3171 train 7.242826 (lr=5.4892e-05) (hash(x)=27049208) +3172 train 7.279129 (lr=5.4853e-05) (hash(x)=27074992) +3173 train 7.207471 (lr=5.4814e-05) (hash(x)=25712617) +3174 train 7.147790 (lr=5.4776e-05) (hash(x)=25884917) +3175 train 7.184096 (lr=5.4737e-05) (hash(x)=24075727) +3176 train 7.061288 (lr=5.4698e-05) (hash(x)=23681759) +3177 train 7.327285 (lr=5.4660e-05) (hash(x)=25786577) +3178 train 7.318977 (lr=5.4621e-05) (hash(x)=27307614) +3179 train 7.346715 (lr=5.4582e-05) (hash(x)=25082806) +3180 train 7.331658 (lr=5.4544e-05) (hash(x)=26098308) +3181 train 7.108585 (lr=5.4505e-05) (hash(x)=24080140) +3182 train 7.315866 (lr=5.4467e-05) (hash(x)=26399395) +3183 train 7.397242 (lr=5.4428e-05) (hash(x)=23104539) +3184 train 7.006310 (lr=5.4389e-05) (hash(x)=23356930) +3185 train 7.256941 (lr=5.4351e-05) (hash(x)=27972420) +3186 train 6.934036 (lr=5.4312e-05) (hash(x)=21338924) +3187 train 7.373159 (lr=5.4274e-05) (hash(x)=25351113) +3188 train 7.269142 (lr=5.4235e-05) (hash(x)=26019439) +3189 train 7.377603 (lr=5.4197e-05) (hash(x)=30149312) +3190 train 7.046958 (lr=5.4158e-05) (hash(x)=23028152) +3191 train 7.416785 (lr=5.4120e-05) (hash(x)=23018983) +3192 train 7.045328 (lr=5.4081e-05) (hash(x)=23190787) +3193 train 7.468074 (lr=5.4043e-05) (hash(x)=27798543) +3194 train 7.242931 (lr=5.4004e-05) (hash(x)=25193663) +3195 train 7.050922 (lr=5.3966e-05) (hash(x)=25302106) +3196 train 7.174371 (lr=5.3927e-05) (hash(x)=24325364) +3197 train 7.181284 (lr=5.3889e-05) (hash(x)=25399101) +3198 train 7.048288 (lr=5.3851e-05) (hash(x)=23606439) +3199 train 7.084831 (lr=5.3812e-05) (hash(x)=24422929) +3200 val loss 7.2247 +3200 val perplexity 1372.9044 +3200 train 7.253038 (lr=5.3774e-05) (hash(x)=24760381) +3201 train 6.919887 (lr=5.3735e-05) (hash(x)=23278576) +3202 train 7.168324 (lr=5.3697e-05) (hash(x)=24897511) +3203 train 7.463484 (lr=5.3659e-05) (hash(x)=29052117) +3204 train 7.195221 (lr=5.3620e-05) (hash(x)=25772923) +3205 train 7.332503 (lr=5.3582e-05) (hash(x)=25885977) +3206 train 7.116942 (lr=5.3544e-05) (hash(x)=21985272) +3207 train 7.048560 (lr=5.3505e-05) (hash(x)=23389696) +3208 train 6.985292 (lr=5.3467e-05) (hash(x)=25299042) +3209 train 7.238697 (lr=5.3429e-05) (hash(x)=23703987) +3210 train 7.135088 (lr=5.3390e-05) (hash(x)=23362342) +3211 train 7.193175 (lr=5.3352e-05) (hash(x)=23962503) +3212 train 7.103847 (lr=5.3314e-05) (hash(x)=21216023) +3213 train 7.162430 (lr=5.3276e-05) (hash(x)=25841931) +3214 train 7.025432 (lr=5.3237e-05) (hash(x)=23631428) +3215 train 7.411212 (lr=5.3199e-05) (hash(x)=29102969) +3216 train 7.185054 (lr=5.3161e-05) (hash(x)=25782766) +3217 train 7.435496 (lr=5.3123e-05) (hash(x)=28825867) +3218 train 7.409069 (lr=5.3085e-05) (hash(x)=24609499) +3219 train 7.318544 (lr=5.3046e-05) (hash(x)=24948166) +3220 train 7.363227 (lr=5.3008e-05) (hash(x)=26919841) +3221 train 7.227837 (lr=5.2970e-05) (hash(x)=27236198) +3222 train 7.034084 (lr=5.2932e-05) (hash(x)=24029305) +3223 train 7.572530 (lr=5.2894e-05) (hash(x)=28359859) +3224 train 7.384549 (lr=5.2856e-05) (hash(x)=24886008) +3225 train 7.198612 (lr=5.2818e-05) (hash(x)=27159867) +3226 train 7.458357 (lr=5.2780e-05) (hash(x)=20672023) +3227 train 7.137877 (lr=5.2741e-05) (hash(x)=22360298) +3228 train 7.557652 (lr=5.2703e-05) (hash(x)=27478658) +3229 train 7.336487 (lr=5.2665e-05) (hash(x)=26575886) +3230 train 7.545467 (lr=5.2627e-05) (hash(x)=26890615) +3231 train 7.144718 (lr=5.2589e-05) (hash(x)=24630955) +3232 train 7.430509 (lr=5.2551e-05) (hash(x)=27016054) +3233 train 7.692317 (lr=5.2513e-05) (hash(x)=28444407) +3234 train 7.048929 (lr=5.2475e-05) (hash(x)=24053336) +3235 train 7.348851 (lr=5.2437e-05) (hash(x)=26897402) +3236 train 7.513855 (lr=5.2399e-05) (hash(x)=29451214) +3237 train 7.288076 (lr=5.2361e-05) (hash(x)=27268677) +3238 train 7.429437 (lr=5.2323e-05) (hash(x)=27494000) +3239 train 7.087340 (lr=5.2285e-05) (hash(x)=22969113) +3240 train 7.043495 (lr=5.2247e-05) (hash(x)=21944576) +3241 train 7.274675 (lr=5.2210e-05) (hash(x)=21671079) +3242 train 7.137769 (lr=5.2172e-05) (hash(x)=23912980) +3243 train 7.117669 (lr=5.2134e-05) (hash(x)=25205781) +3244 train 7.083292 (lr=5.2096e-05) (hash(x)=25654244) +3245 train 7.032905 (lr=5.2058e-05) (hash(x)=23335929) +3246 train 7.388815 (lr=5.2020e-05) (hash(x)=27953926) +3247 train 7.159172 (lr=5.1982e-05) (hash(x)=27004415) +3248 train 6.916980 (lr=5.1944e-05) (hash(x)=20471566) +3249 train 7.109439 (lr=5.1907e-05) (hash(x)=25797941) +3250 val loss 7.2221 +3250 val perplexity 1369.3640 +3250 train 6.995252 (lr=5.1869e-05) (hash(x)=21787064) +3251 train 7.017361 (lr=5.1831e-05) (hash(x)=22974875) +3252 train 7.260055 (lr=5.1793e-05) (hash(x)=28431267) +3253 train 7.163101 (lr=5.1756e-05) (hash(x)=25584910) +3254 train 6.938875 (lr=5.1718e-05) (hash(x)=23888922) +3255 train 7.174943 (lr=5.1680e-05) (hash(x)=22265063) +3256 train 6.814101 (lr=5.1642e-05) (hash(x)=21926624) +3257 train 7.069147 (lr=5.1605e-05) (hash(x)=23073191) +3258 train 7.086562 (lr=5.1567e-05) (hash(x)=24409183) +3259 train 7.138126 (lr=5.1529e-05) (hash(x)=23312114) +3260 train 7.045019 (lr=5.1491e-05) (hash(x)=21001289) +3261 train 7.229764 (lr=5.1454e-05) (hash(x)=25514824) +3262 train 7.027764 (lr=5.1416e-05) (hash(x)=22526800) +3263 train 7.437098 (lr=5.1378e-05) (hash(x)=26905990) +3264 train 7.115674 (lr=5.1341e-05) (hash(x)=24469631) +3265 train 6.948639 (lr=5.1303e-05) (hash(x)=21149081) +3266 train 7.145001 (lr=5.1266e-05) (hash(x)=24696215) +3267 train 7.488564 (lr=5.1228e-05) (hash(x)=27089280) +3268 train 7.012102 (lr=5.1190e-05) (hash(x)=23100446) +3269 train 7.229616 (lr=5.1153e-05) (hash(x)=25061229) +3270 train 7.142110 (lr=5.1115e-05) (hash(x)=24337543) +3271 train 7.214731 (lr=5.1078e-05) (hash(x)=24047679) +3272 train 7.273426 (lr=5.1040e-05) (hash(x)=27616773) +3273 train 7.166669 (lr=5.1003e-05) (hash(x)=25315110) +3274 train 7.236675 (lr=5.0965e-05) (hash(x)=28354645) +3275 train 7.121509 (lr=5.0928e-05) (hash(x)=25034684) +3276 train 7.123544 (lr=5.0890e-05) (hash(x)=23550342) +3277 train 7.801155 (lr=5.0853e-05) (hash(x)=28661487) +3278 train 7.370822 (lr=5.0815e-05) (hash(x)=24724622) +3279 train 7.322771 (lr=5.0778e-05) (hash(x)=26905582) +3280 train 7.413845 (lr=5.0740e-05) (hash(x)=26838818) +3281 train 7.148180 (lr=5.0703e-05) (hash(x)=23949017) +3282 train 6.657707 (lr=5.0666e-05) (hash(x)=18846300) +3283 train 7.023131 (lr=5.0628e-05) (hash(x)=21406950) +3284 train 6.852652 (lr=5.0591e-05) (hash(x)=21157696) +3285 train 6.932451 (lr=5.0553e-05) (hash(x)=21440152) +3286 train 7.126949 (lr=5.0516e-05) (hash(x)=26749182) +3287 train 7.263297 (lr=5.0479e-05) (hash(x)=29018970) +3288 train 7.248762 (lr=5.0441e-05) (hash(x)=27577517) +3289 train 6.886420 (lr=5.0404e-05) (hash(x)=19190537) +3290 train 6.933141 (lr=5.0367e-05) (hash(x)=21957991) +3291 train 6.939287 (lr=5.0329e-05) (hash(x)=20853530) +3292 train 6.892078 (lr=5.0292e-05) (hash(x)=22291731) +3293 train 7.067413 (lr=5.0255e-05) (hash(x)=23786853) +3294 train 7.215363 (lr=5.0218e-05) (hash(x)=25740147) +3295 train 7.307659 (lr=5.0180e-05) (hash(x)=24503315) +3296 train 7.049316 (lr=5.0143e-05) (hash(x)=22541728) +3297 train 7.383329 (lr=5.0106e-05) (hash(x)=27067328) +3298 train 7.045269 (lr=5.0069e-05) (hash(x)=22600715) +3299 train 7.043334 (lr=5.0031e-05) (hash(x)=23080074) +3300 val loss 7.2120 +3300 val perplexity 1355.5651 +3300 train 6.820844 (lr=4.9994e-05) (hash(x)=22097758) +3301 train 7.053061 (lr=4.9957e-05) (hash(x)=24105430) +3302 train 6.896676 (lr=4.9920e-05) (hash(x)=23343775) +3303 train 7.149380 (lr=4.9883e-05) (hash(x)=22607537) +3304 train 7.237298 (lr=4.9846e-05) (hash(x)=26501182) +3305 train 7.484025 (lr=4.9809e-05) (hash(x)=26063650) +3306 train 7.084325 (lr=4.9771e-05) (hash(x)=23486602) +3307 train 8.051009 (lr=4.9734e-05) (hash(x)=32179773) +3308 train 11.337567 (lr=4.9697e-05) (hash(x)=66155855) +3309 train 8.502723 (lr=4.9660e-05) (hash(x)=37724427) +3310 train 7.569670 (lr=4.9623e-05) (hash(x)=28861610) +3311 train 7.519716 (lr=4.9586e-05) (hash(x)=26690225) +3312 train 7.065564 (lr=4.9549e-05) (hash(x)=24136450) +3313 train 7.263088 (lr=4.9512e-05) (hash(x)=23702010) +3314 train 7.502670 (lr=4.9475e-05) (hash(x)=28761762) +3315 train 6.847220 (lr=4.9438e-05) (hash(x)=22109609) +3316 train 7.197878 (lr=4.9401e-05) (hash(x)=25168631) +3317 train 7.096753 (lr=4.9364e-05) (hash(x)=24503786) +3318 train 7.110854 (lr=4.9327e-05) (hash(x)=23698606) +3319 train 7.157218 (lr=4.9290e-05) (hash(x)=24226255) +3320 train 7.717035 (lr=4.9253e-05) (hash(x)=31110577) +3321 train 7.150457 (lr=4.9216e-05) (hash(x)=24752754) +3322 train 7.008475 (lr=4.9179e-05) (hash(x)=21135610) +3323 train 6.946060 (lr=4.9143e-05) (hash(x)=23013573) +3324 train 6.720679 (lr=4.9106e-05) (hash(x)=20289715) +3325 train 6.947302 (lr=4.9069e-05) (hash(x)=22700287) +3326 train 7.029026 (lr=4.9032e-05) (hash(x)=21320362) +3327 train 7.141197 (lr=4.8995e-05) (hash(x)=23622702) +3328 train 7.440743 (lr=4.8958e-05) (hash(x)=27435461) +3329 train 7.199247 (lr=4.8922e-05) (hash(x)=25435452) +3330 train 7.183309 (lr=4.8885e-05) (hash(x)=27952557) +3331 train 6.867729 (lr=4.8848e-05) (hash(x)=21517429) +3332 train 7.002280 (lr=4.8811e-05) (hash(x)=24288985) +3333 train 7.184332 (lr=4.8774e-05) (hash(x)=23374788) +3334 train 7.003429 (lr=4.8738e-05) (hash(x)=22042499) +3335 train 7.220912 (lr=4.8701e-05) (hash(x)=23910425) +3336 train 7.541885 (lr=4.8664e-05) (hash(x)=28118508) +3337 train 7.325429 (lr=4.8628e-05) (hash(x)=26737440) +3338 train 7.068260 (lr=4.8591e-05) (hash(x)=24472271) +3339 train 7.029246 (lr=4.8554e-05) (hash(x)=24407484) +3340 train 7.585656 (lr=4.8518e-05) (hash(x)=27908937) +3341 train 7.757895 (lr=4.8481e-05) (hash(x)=29038937) +3342 train 7.488290 (lr=4.8444e-05) (hash(x)=24802580) +3343 train 7.471060 (lr=4.8408e-05) (hash(x)=27213318) +3344 train 7.512475 (lr=4.8371e-05) (hash(x)=28693458) +3345 train 6.845497 (lr=4.8335e-05) (hash(x)=20332324) +3346 train 7.218531 (lr=4.8298e-05) (hash(x)=26726007) +3347 train 7.113403 (lr=4.8261e-05) (hash(x)=25524191) +3348 train 7.205589 (lr=4.8225e-05) (hash(x)=25553293) +3349 train 7.149155 (lr=4.8188e-05) (hash(x)=25614848) +3350 val loss 7.2159 +3350 val perplexity 1360.9368 +3350 train 7.241374 (lr=4.8152e-05) (hash(x)=25747903) +3351 train 7.198995 (lr=4.8115e-05) (hash(x)=26701577) +3352 train 6.951138 (lr=4.8079e-05) (hash(x)=21964135) +3353 train 7.078691 (lr=4.8042e-05) (hash(x)=24461007) +3354 train 7.093013 (lr=4.8006e-05) (hash(x)=25818495) +3355 train 6.943084 (lr=4.7969e-05) (hash(x)=22091266) +3356 train 6.936237 (lr=4.7933e-05) (hash(x)=24476213) +3357 train 7.310015 (lr=4.7896e-05) (hash(x)=24500423) +3358 train 7.060158 (lr=4.7860e-05) (hash(x)=21754841) +3359 train 7.373631 (lr=4.7824e-05) (hash(x)=26216794) +3360 train 6.886009 (lr=4.7787e-05) (hash(x)=24267249) +3361 train 7.214975 (lr=4.7751e-05) (hash(x)=23143515) +3362 train 7.063386 (lr=4.7715e-05) (hash(x)=24120302) +3363 train 7.189819 (lr=4.7678e-05) (hash(x)=20817340) +3364 train 7.194316 (lr=4.7642e-05) (hash(x)=22285847) +3365 train 7.544694 (lr=4.7606e-05) (hash(x)=28151597) +3366 train 7.946216 (lr=4.7569e-05) (hash(x)=31593285) +3367 train 7.616538 (lr=4.7533e-05) (hash(x)=27579623) +3368 train 7.188121 (lr=4.7497e-05) (hash(x)=24995988) +3369 train 6.832092 (lr=4.7460e-05) (hash(x)=22166810) +3370 train 7.088374 (lr=4.7424e-05) (hash(x)=23948298) +3371 train 6.963620 (lr=4.7388e-05) (hash(x)=21532187) +3372 train 7.043288 (lr=4.7352e-05) (hash(x)=23571652) +3373 train 7.478333 (lr=4.7315e-05) (hash(x)=26911513) +3374 train 7.385816 (lr=4.7279e-05) (hash(x)=24011329) +3375 train 7.570302 (lr=4.7243e-05) (hash(x)=26086198) +3376 train 7.148786 (lr=4.7207e-05) (hash(x)=22844402) +3377 train 7.109375 (lr=4.7171e-05) (hash(x)=21817762) +3378 train 7.159574 (lr=4.7135e-05) (hash(x)=23903232) +3379 train 7.133775 (lr=4.7099e-05) (hash(x)=23911729) +3380 train 7.095527 (lr=4.7062e-05) (hash(x)=24485288) +3381 train 7.296894 (lr=4.7026e-05) (hash(x)=27955492) +3382 train 6.982831 (lr=4.6990e-05) (hash(x)=25884586) +3383 train 7.222655 (lr=4.6954e-05) (hash(x)=24863441) +3384 train 7.503583 (lr=4.6918e-05) (hash(x)=22045992) +3385 train 7.642181 (lr=4.6882e-05) (hash(x)=29174796) +3386 train 7.929926 (lr=4.6846e-05) (hash(x)=32589942) +3387 train 7.535138 (lr=4.6810e-05) (hash(x)=28856978) +3388 train 6.997137 (lr=4.6774e-05) (hash(x)=21667904) +3389 train 6.981944 (lr=4.6738e-05) (hash(x)=23431801) +3390 train 6.809462 (lr=4.6702e-05) (hash(x)=20877285) +3391 train 7.062589 (lr=4.6666e-05) (hash(x)=25236385) +3392 train 7.286302 (lr=4.6630e-05) (hash(x)=25373071) +3393 train 7.440488 (lr=4.6594e-05) (hash(x)=25713464) +3394 train 7.428332 (lr=4.6558e-05) (hash(x)=25713475) +3395 train 7.271702 (lr=4.6522e-05) (hash(x)=24278687) +3396 train 7.385565 (lr=4.6487e-05) (hash(x)=27491349) +3397 train 7.278881 (lr=4.6451e-05) (hash(x)=24513692) +3398 train 7.387567 (lr=4.6415e-05) (hash(x)=26853415) +3399 train 7.441724 (lr=4.6379e-05) (hash(x)=25330803) +3400 val loss 7.2131 +3400 val perplexity 1357.0985 +3400 train 7.417874 (lr=4.6343e-05) (hash(x)=26578066) +3401 train 7.442287 (lr=4.6307e-05) (hash(x)=26811522) +3402 train 7.146881 (lr=4.6272e-05) (hash(x)=25611092) +3403 train 6.958282 (lr=4.6236e-05) (hash(x)=21568545) +3404 train 6.952680 (lr=4.6200e-05) (hash(x)=22756484) +3405 train 7.234020 (lr=4.6164e-05) (hash(x)=27927608) +3406 train 7.262116 (lr=4.6128e-05) (hash(x)=27497018) +3407 train 7.051602 (lr=4.6093e-05) (hash(x)=22508532) +3408 train 7.479868 (lr=4.6057e-05) (hash(x)=26673287) +3409 train 7.153890 (lr=4.6021e-05) (hash(x)=23675869) +3410 train 7.079851 (lr=4.5986e-05) (hash(x)=25496948) +3411 train 7.069318 (lr=4.5950e-05) (hash(x)=24850662) +3412 train 7.322186 (lr=4.5914e-05) (hash(x)=29790167) +3413 train 6.982854 (lr=4.5879e-05) (hash(x)=24193434) +3414 train 7.323078 (lr=4.5843e-05) (hash(x)=25310919) +3415 train 7.045185 (lr=4.5807e-05) (hash(x)=21799261) +3416 train 7.329909 (lr=4.5772e-05) (hash(x)=26620074) +3417 train 7.252126 (lr=4.5736e-05) (hash(x)=26719309) +3418 train 7.617497 (lr=4.5701e-05) (hash(x)=23190530) +3419 train 7.219843 (lr=4.5665e-05) (hash(x)=24884891) +3420 train 7.209741 (lr=4.5630e-05) (hash(x)=25545849) +3421 train 7.141930 (lr=4.5594e-05) (hash(x)=26021405) +3422 train 7.138861 (lr=4.5559e-05) (hash(x)=23887343) +3423 train 7.204076 (lr=4.5523e-05) (hash(x)=26311168) +3424 train 6.882394 (lr=4.5488e-05) (hash(x)=21051541) +3425 train 7.217782 (lr=4.5452e-05) (hash(x)=23553179) +3426 train 7.114790 (lr=4.5417e-05) (hash(x)=24345540) +3427 train 7.595689 (lr=4.5381e-05) (hash(x)=27549895) +3428 train 6.899612 (lr=4.5346e-05) (hash(x)=22559753) +3429 train 6.881074 (lr=4.5310e-05) (hash(x)=21647642) +3430 train 6.768795 (lr=4.5275e-05) (hash(x)=20130901) +3431 train 6.915189 (lr=4.5240e-05) (hash(x)=20977430) +3432 train 6.914631 (lr=4.5204e-05) (hash(x)=21356429) +3433 train 6.932446 (lr=4.5169e-05) (hash(x)=23494380) +3434 train 7.180274 (lr=4.5134e-05) (hash(x)=23805501) +3435 train 7.113672 (lr=4.5098e-05) (hash(x)=23448855) +3436 train 7.481259 (lr=4.5063e-05) (hash(x)=26000319) +3437 train 6.928431 (lr=4.5028e-05) (hash(x)=21760032) +3438 train 7.088295 (lr=4.4992e-05) (hash(x)=24424886) +3439 train 7.461802 (lr=4.4957e-05) (hash(x)=26941617) +3440 train 7.475137 (lr=4.4922e-05) (hash(x)=26798528) +3441 train 7.496878 (lr=4.4887e-05) (hash(x)=27464193) +3442 train 7.400997 (lr=4.4851e-05) (hash(x)=25649118) +3443 train 7.417522 (lr=4.4816e-05) (hash(x)=26953192) +3444 train 7.296014 (lr=4.4781e-05) (hash(x)=22224958) +3445 train 7.078795 (lr=4.4746e-05) (hash(x)=24044587) +3446 train 7.485172 (lr=4.4711e-05) (hash(x)=29584466) +3447 train 7.876208 (lr=4.4676e-05) (hash(x)=30008957) +3448 train 7.769755 (lr=4.4640e-05) (hash(x)=26059290) +3449 train 6.753157 (lr=4.4605e-05) (hash(x)=19733965) +3450 val loss 7.2216 +3450 val perplexity 1368.6564 +3450 train 7.262848 (lr=4.4570e-05) (hash(x)=23960200) +3451 train 7.433029 (lr=4.4535e-05) (hash(x)=27069893) +3452 train 7.065672 (lr=4.4500e-05) (hash(x)=23947772) +3453 train 7.150724 (lr=4.4465e-05) (hash(x)=22707406) +3454 train 7.314450 (lr=4.4430e-05) (hash(x)=27832550) +3455 train 7.192670 (lr=4.4395e-05) (hash(x)=27125962) +3456 train 7.074295 (lr=4.4360e-05) (hash(x)=24510254) +3457 train 6.871360 (lr=4.4325e-05) (hash(x)=23545652) +3458 train 6.948112 (lr=4.4290e-05) (hash(x)=23554751) +3459 train 7.088034 (lr=4.4255e-05) (hash(x)=23341415) +3460 train 7.262085 (lr=4.4220e-05) (hash(x)=21784583) +3461 train 7.013927 (lr=4.4185e-05) (hash(x)=22214769) +3462 train 7.102684 (lr=4.4150e-05) (hash(x)=24206922) +3463 train 7.220507 (lr=4.4115e-05) (hash(x)=25888358) +3464 train 7.018986 (lr=4.4080e-05) (hash(x)=22689666) +3465 train 7.158653 (lr=4.4046e-05) (hash(x)=24918697) +3466 train 7.439197 (lr=4.4011e-05) (hash(x)=28237214) +3467 train 7.497075 (lr=4.3976e-05) (hash(x)=26761645) +3468 train 7.207904 (lr=4.3941e-05) (hash(x)=26979307) +3469 train 7.082482 (lr=4.3906e-05) (hash(x)=23553754) +3470 train 7.231159 (lr=4.3871e-05) (hash(x)=25256849) +3471 train 7.107405 (lr=4.3837e-05) (hash(x)=21725719) +3472 train 7.214769 (lr=4.3802e-05) (hash(x)=24897801) +3473 train 7.145044 (lr=4.3767e-05) (hash(x)=26175307) +3474 train 6.955380 (lr=4.3732e-05) (hash(x)=23309218) +3475 train 7.025475 (lr=4.3698e-05) (hash(x)=25746493) +3476 train 7.354303 (lr=4.3663e-05) (hash(x)=27169613) +3477 train 7.043956 (lr=4.3628e-05) (hash(x)=22937341) +3478 train 7.153168 (lr=4.3594e-05) (hash(x)=24250636) +3479 train 6.971733 (lr=4.3559e-05) (hash(x)=21669704) +3480 train 7.001049 (lr=4.3524e-05) (hash(x)=24431839) +3481 train 7.021196 (lr=4.3490e-05) (hash(x)=22763387) +3482 train 6.998058 (lr=4.3455e-05) (hash(x)=20489446) +3483 train 6.952473 (lr=4.3421e-05) (hash(x)=21167493) +3484 train 6.952503 (lr=4.3386e-05) (hash(x)=23465087) +3485 train 7.191522 (lr=4.3351e-05) (hash(x)=26175023) +3486 train 7.322791 (lr=4.3317e-05) (hash(x)=24986207) +3487 train 6.872631 (lr=4.3282e-05) (hash(x)=23166993) +3488 train 7.161869 (lr=4.3248e-05) (hash(x)=25281216) +3489 train 6.956737 (lr=4.3213e-05) (hash(x)=21824285) +3490 train 6.999938 (lr=4.3179e-05) (hash(x)=22352750) +3491 train 7.228240 (lr=4.3144e-05) (hash(x)=23947208) +3492 train 7.296319 (lr=4.3110e-05) (hash(x)=26257363) +3493 train 7.123004 (lr=4.3075e-05) (hash(x)=25103214) +3494 train 7.157806 (lr=4.3041e-05) (hash(x)=25267583) +3495 train 7.234810 (lr=4.3007e-05) (hash(x)=26235974) +3496 train 7.452065 (lr=4.2972e-05) (hash(x)=26430769) +3497 train 7.900311 (lr=4.2938e-05) (hash(x)=28282027) +3498 train 7.738896 (lr=4.2903e-05) (hash(x)=28386462) +3499 train 7.335005 (lr=4.2869e-05) (hash(x)=29822604) +3500 val loss 7.2033 +3500 val perplexity 1343.8339 +3500 train 7.250591 (lr=4.2835e-05) (hash(x)=29225386) +3501 train 7.130775 (lr=4.2800e-05) (hash(x)=25249294) +3502 train 6.885950 (lr=4.2766e-05) (hash(x)=20020741) +3503 train 7.069852 (lr=4.2732e-05) (hash(x)=25426430) +3504 train 7.026372 (lr=4.2698e-05) (hash(x)=25720411) +3505 train 7.051296 (lr=4.2663e-05) (hash(x)=25602639) +3506 train 7.166734 (lr=4.2629e-05) (hash(x)=26724388) +3507 train 7.049935 (lr=4.2595e-05) (hash(x)=26043735) +3508 train 7.028546 (lr=4.2561e-05) (hash(x)=24955163) +3509 train 7.020395 (lr=4.2527e-05) (hash(x)=20936107) +3510 train 6.976842 (lr=4.2492e-05) (hash(x)=20317378) +3511 train 7.004613 (lr=4.2458e-05) (hash(x)=22966314) +3512 train 7.362073 (lr=4.2424e-05) (hash(x)=25870930) +3513 train 7.181423 (lr=4.2390e-05) (hash(x)=24656635) +3514 train 7.451408 (lr=4.2356e-05) (hash(x)=28576810) +3515 train 7.353775 (lr=4.2322e-05) (hash(x)=27944619) +3516 train 7.171124 (lr=4.2288e-05) (hash(x)=27421509) +3517 train 6.940041 (lr=4.2254e-05) (hash(x)=20844620) +3518 train 7.146794 (lr=4.2220e-05) (hash(x)=28569406) +3519 train 7.037210 (lr=4.2185e-05) (hash(x)=23448505) +3520 train 7.225056 (lr=4.2151e-05) (hash(x)=24852577) +3521 train 7.097113 (lr=4.2117e-05) (hash(x)=23963103) +3522 train 6.980699 (lr=4.2083e-05) (hash(x)=24816516) +3523 train 7.162998 (lr=4.2050e-05) (hash(x)=24205942) +3524 train 6.771314 (lr=4.2016e-05) (hash(x)=20988660) +3525 train 6.854810 (lr=4.1982e-05) (hash(x)=21631366) +3526 train 7.087662 (lr=4.1948e-05) (hash(x)=23499370) +3527 train 7.184825 (lr=4.1914e-05) (hash(x)=26330693) +3528 train 6.825517 (lr=4.1880e-05) (hash(x)=23937176) +3529 train 7.125861 (lr=4.1846e-05) (hash(x)=27345885) +3530 train 6.812929 (lr=4.1812e-05) (hash(x)=21104610) +3531 train 7.196935 (lr=4.1778e-05) (hash(x)=24844466) +3532 train 6.572882 (lr=4.1745e-05) (hash(x)=21055483) +3533 train 6.879056 (lr=4.1711e-05) (hash(x)=23229414) +3534 train 7.213628 (lr=4.1677e-05) (hash(x)=26676920) +3535 train 7.168544 (lr=4.1643e-05) (hash(x)=29550596) +3536 train 6.931885 (lr=4.1609e-05) (hash(x)=22231942) +3537 train 7.108923 (lr=4.1576e-05) (hash(x)=25843852) +3538 train 7.260375 (lr=4.1542e-05) (hash(x)=27110533) +3539 train 6.805068 (lr=4.1508e-05) (hash(x)=20506540) +3540 train 6.945774 (lr=4.1475e-05) (hash(x)=21599346) +3541 train 7.129869 (lr=4.1441e-05) (hash(x)=26395519) +3542 train 7.089002 (lr=4.1407e-05) (hash(x)=25892512) +3543 train 7.156290 (lr=4.1374e-05) (hash(x)=22124892) +3544 train 7.022690 (lr=4.1340e-05) (hash(x)=21882567) +3545 train 7.104369 (lr=4.1306e-05) (hash(x)=24316212) +3546 train 7.036561 (lr=4.1273e-05) (hash(x)=24296310) +3547 train 7.120767 (lr=4.1239e-05) (hash(x)=24867036) +3548 train 7.104544 (lr=4.1206e-05) (hash(x)=23351896) +3549 train 7.075733 (lr=4.1172e-05) (hash(x)=21576408) +3550 val loss 7.1993 +3550 val perplexity 1338.5060 +3550 train 7.184894 (lr=4.1138e-05) (hash(x)=26377338) +3551 train 7.032757 (lr=4.1105e-05) (hash(x)=25607640) +3552 train 7.369025 (lr=4.1071e-05) (hash(x)=27619776) +3553 train 6.843540 (lr=4.1038e-05) (hash(x)=23454533) +3554 train 7.049445 (lr=4.1005e-05) (hash(x)=22542519) +3555 train 7.107842 (lr=4.0971e-05) (hash(x)=26176930) +3556 train 6.897360 (lr=4.0938e-05) (hash(x)=22815181) +3557 train 6.857871 (lr=4.0904e-05) (hash(x)=21821757) +3558 train 6.918836 (lr=4.0871e-05) (hash(x)=23988293) +3559 train 6.833589 (lr=4.0837e-05) (hash(x)=23795894) +3560 train 6.801767 (lr=4.0804e-05) (hash(x)=22898969) +3561 train 6.821826 (lr=4.0771e-05) (hash(x)=21510825) +3562 train 6.753239 (lr=4.0737e-05) (hash(x)=22499317) +3563 train 6.797220 (lr=4.0704e-05) (hash(x)=23756298) +3564 train 6.829759 (lr=4.0671e-05) (hash(x)=23964512) +3565 train 6.922928 (lr=4.0637e-05) (hash(x)=23262803) +3566 train 7.101192 (lr=4.0604e-05) (hash(x)=23347279) +3567 train 7.012844 (lr=4.0571e-05) (hash(x)=24165449) +3568 train 7.107376 (lr=4.0538e-05) (hash(x)=25503946) +3569 train 7.109479 (lr=4.0505e-05) (hash(x)=26532839) +3570 train 6.759950 (lr=4.0471e-05) (hash(x)=21889816) +3571 train 7.049408 (lr=4.0438e-05) (hash(x)=26643739) +3572 train 7.232782 (lr=4.0405e-05) (hash(x)=26826130) +3573 train 7.243684 (lr=4.0372e-05) (hash(x)=25810624) +3574 train 7.121637 (lr=4.0339e-05) (hash(x)=23080331) +3575 train 7.245621 (lr=4.0306e-05) (hash(x)=24697756) +3576 train 7.105772 (lr=4.0272e-05) (hash(x)=25158900) +3577 train 7.258035 (lr=4.0239e-05) (hash(x)=25793633) +3578 train 6.836801 (lr=4.0206e-05) (hash(x)=21468493) +3579 train 7.145477 (lr=4.0173e-05) (hash(x)=24431101) +3580 train 7.018476 (lr=4.0140e-05) (hash(x)=27314357) +3581 train 7.243120 (lr=4.0107e-05) (hash(x)=26286249) +3582 train 7.481365 (lr=4.0074e-05) (hash(x)=25954856) +3583 train 7.342525 (lr=4.0041e-05) (hash(x)=27218899) +3584 train 7.128957 (lr=4.0008e-05) (hash(x)=24249114) +3585 train 7.007781 (lr=3.9975e-05) (hash(x)=23659934) +3586 train 7.015565 (lr=3.9942e-05) (hash(x)=25995600) +3587 train 7.000995 (lr=3.9909e-05) (hash(x)=29462219) +3588 train 7.106748 (lr=3.9877e-05) (hash(x)=23346714) +3589 train 7.223112 (lr=3.9844e-05) (hash(x)=27168432) +3590 train 7.035223 (lr=3.9811e-05) (hash(x)=23954240) +3591 train 7.001387 (lr=3.9778e-05) (hash(x)=24748522) +3592 train 7.190720 (lr=3.9745e-05) (hash(x)=24887007) +3593 train 6.930254 (lr=3.9712e-05) (hash(x)=25539383) +3594 train 6.881081 (lr=3.9679e-05) (hash(x)=20104613) +3595 train 7.408906 (lr=3.9647e-05) (hash(x)=24843486) +3596 train 7.411699 (lr=3.9614e-05) (hash(x)=24357864) +3597 train 7.091016 (lr=3.9581e-05) (hash(x)=23873745) +3598 train 7.226717 (lr=3.9548e-05) (hash(x)=25142829) +3599 train 7.286177 (lr=3.9516e-05) (hash(x)=24965317) +3600 val loss 7.1908 +3600 val perplexity 1327.1692 +3600 train 6.796718 (lr=3.9483e-05) (hash(x)=18505205) +3601 train 6.853796 (lr=3.9450e-05) (hash(x)=23632877) +3602 train 7.037483 (lr=3.9418e-05) (hash(x)=23704554) +3603 train 7.195497 (lr=3.9385e-05) (hash(x)=26584754) +3604 train 6.842313 (lr=3.9352e-05) (hash(x)=20667709) +3605 train 6.718737 (lr=3.9320e-05) (hash(x)=20573248) +3606 train 6.861540 (lr=3.9287e-05) (hash(x)=23998997) +3607 train 7.049583 (lr=3.9255e-05) (hash(x)=22031210) +3608 train 7.114891 (lr=3.9222e-05) (hash(x)=24124536) +3609 train 7.005568 (lr=3.9190e-05) (hash(x)=22650144) +3610 train 7.090001 (lr=3.9157e-05) (hash(x)=23796998) +3611 train 7.137288 (lr=3.9124e-05) (hash(x)=24860582) +3612 train 6.691112 (lr=3.9092e-05) (hash(x)=20591300) +3613 train 7.088913 (lr=3.9060e-05) (hash(x)=23447130) +3614 train 7.044120 (lr=3.9027e-05) (hash(x)=26237963) +3615 train 7.204828 (lr=3.8995e-05) (hash(x)=25877990) +3616 train 6.957765 (lr=3.8962e-05) (hash(x)=24808003) +3617 train 7.172487 (lr=3.8930e-05) (hash(x)=24103543) +3618 train 7.098602 (lr=3.8897e-05) (hash(x)=24877184) +3619 train 7.183383 (lr=3.8865e-05) (hash(x)=24970646) +3620 train 7.135561 (lr=3.8833e-05) (hash(x)=25764524) +3621 train 7.279239 (lr=3.8800e-05) (hash(x)=25313591) +3622 train 7.181123 (lr=3.8768e-05) (hash(x)=23260940) +3623 train 7.054499 (lr=3.8736e-05) (hash(x)=24382381) +3624 train 7.030673 (lr=3.8703e-05) (hash(x)=24618902) +3625 train 7.205748 (lr=3.8671e-05) (hash(x)=25074871) +3626 train 6.915503 (lr=3.8639e-05) (hash(x)=24472251) +3627 train 7.030047 (lr=3.8607e-05) (hash(x)=25221746) +3628 train 7.139144 (lr=3.8574e-05) (hash(x)=27448790) +3629 train 7.094524 (lr=3.8542e-05) (hash(x)=25221431) +3630 train 6.722917 (lr=3.8510e-05) (hash(x)=22034366) +3631 train 7.249448 (lr=3.8478e-05) (hash(x)=24551999) +3632 train 6.963506 (lr=3.8446e-05) (hash(x)=24330217) +3633 train 7.047510 (lr=3.8414e-05) (hash(x)=22792380) +3634 train 6.874267 (lr=3.8381e-05) (hash(x)=22393767) +3635 train 7.197895 (lr=3.8349e-05) (hash(x)=28151378) +3636 train 7.233027 (lr=3.8317e-05) (hash(x)=26999341) +3637 train 7.223217 (lr=3.8285e-05) (hash(x)=27251870) +3638 train 7.157479 (lr=3.8253e-05) (hash(x)=23439462) +3639 train 7.258783 (lr=3.8221e-05) (hash(x)=25765516) +3640 train 7.089774 (lr=3.8189e-05) (hash(x)=24720171) +3641 train 7.304271 (lr=3.8157e-05) (hash(x)=23927187) +3642 train 7.083722 (lr=3.8125e-05) (hash(x)=23879561) +3643 train 7.181894 (lr=3.8093e-05) (hash(x)=25630696) +3644 train 6.788840 (lr=3.8061e-05) (hash(x)=22030016) +3645 train 7.241487 (lr=3.8029e-05) (hash(x)=28781600) +3646 train 7.244307 (lr=3.7997e-05) (hash(x)=26668019) +3647 train 7.287840 (lr=3.7966e-05) (hash(x)=25204247) +3648 train 7.513835 (lr=3.7934e-05) (hash(x)=31261394) +3649 train 7.276554 (lr=3.7902e-05) (hash(x)=26193103) +3650 val loss 7.1985 +3650 val perplexity 1337.4170 +3650 train 7.129018 (lr=3.7870e-05) (hash(x)=23872456) +3651 train 7.021750 (lr=3.7838e-05) (hash(x)=26326447) +3652 train 7.004948 (lr=3.7806e-05) (hash(x)=26449631) +3653 train 7.300436 (lr=3.7775e-05) (hash(x)=26373461) +3654 train 7.145249 (lr=3.7743e-05) (hash(x)=24882768) +3655 train 7.209630 (lr=3.7711e-05) (hash(x)=26321813) +3656 train 7.261417 (lr=3.7679e-05) (hash(x)=27056428) +3657 train 7.221785 (lr=3.7648e-05) (hash(x)=24583976) +3658 train 6.923654 (lr=3.7616e-05) (hash(x)=22259624) +3659 train 7.071468 (lr=3.7584e-05) (hash(x)=25400396) +3660 train 6.925407 (lr=3.7553e-05) (hash(x)=21095507) +3661 train 7.170796 (lr=3.7521e-05) (hash(x)=27231042) +3662 train 6.977666 (lr=3.7489e-05) (hash(x)=27292771) +3663 train 7.375313 (lr=3.7458e-05) (hash(x)=25528323) +3664 train 7.152399 (lr=3.7426e-05) (hash(x)=24374502) +3665 train 6.938100 (lr=3.7395e-05) (hash(x)=22463800) +3666 train 7.206594 (lr=3.7363e-05) (hash(x)=25413960) +3667 train 7.127985 (lr=3.7332e-05) (hash(x)=24035353) +3668 train 7.059135 (lr=3.7300e-05) (hash(x)=24815852) +3669 train 6.927373 (lr=3.7269e-05) (hash(x)=22995856) +3670 train 7.204933 (lr=3.7237e-05) (hash(x)=28128238) +3671 train 7.261230 (lr=3.7206e-05) (hash(x)=25114729) +3672 train 6.992836 (lr=3.7174e-05) (hash(x)=19337726) +3673 train 7.434950 (lr=3.7143e-05) (hash(x)=26674420) +3674 train 6.913277 (lr=3.7111e-05) (hash(x)=22553270) +3675 train 6.750420 (lr=3.7080e-05) (hash(x)=21634962) +3676 train 6.949525 (lr=3.7049e-05) (hash(x)=23362669) +3677 train 7.122641 (lr=3.7017e-05) (hash(x)=24781824) +3678 train 6.640501 (lr=3.6986e-05) (hash(x)=17909688) +3679 train 7.884645 (lr=3.6955e-05) (hash(x)=31341964) +3680 train 7.382892 (lr=3.6923e-05) (hash(x)=29071335) +3681 train 6.805855 (lr=3.6892e-05) (hash(x)=19486640) +3682 train 6.960156 (lr=3.6861e-05) (hash(x)=24301133) +3683 train 7.122569 (lr=3.6830e-05) (hash(x)=29172813) +3684 train 7.696238 (lr=3.6798e-05) (hash(x)=31501337) +3685 train 7.261302 (lr=3.6767e-05) (hash(x)=27377840) +3686 train 7.082117 (lr=3.6736e-05) (hash(x)=24499761) +3687 train 7.065466 (lr=3.6705e-05) (hash(x)=26326024) +3688 train 7.066150 (lr=3.6674e-05) (hash(x)=23179996) +3689 train 6.740854 (lr=3.6642e-05) (hash(x)=20963675) +3690 train 7.029003 (lr=3.6611e-05) (hash(x)=26650521) +3691 train 6.789792 (lr=3.6580e-05) (hash(x)=20140071) +3692 train 6.803449 (lr=3.6549e-05) (hash(x)=21734340) +3693 train 7.089458 (lr=3.6518e-05) (hash(x)=23848422) +3694 train 7.160092 (lr=3.6487e-05) (hash(x)=27499953) +3695 train 7.364086 (lr=3.6456e-05) (hash(x)=27273311) +3696 train 7.308818 (lr=3.6425e-05) (hash(x)=25741091) +3697 train 7.011902 (lr=3.6394e-05) (hash(x)=22010794) +3698 train 7.128025 (lr=3.6363e-05) (hash(x)=24616138) +3699 train 7.502464 (lr=3.6332e-05) (hash(x)=31276487) +3700 val loss 7.1916 +3700 val perplexity 1328.2145 +3700 train 7.160686 (lr=3.6301e-05) (hash(x)=24042922) +3701 train 6.929550 (lr=3.6270e-05) (hash(x)=21985431) +3702 train 6.777584 (lr=3.6239e-05) (hash(x)=21336316) +3703 train 6.642432 (lr=3.6208e-05) (hash(x)=17819313) +3704 train 7.269812 (lr=3.6178e-05) (hash(x)=27033851) +3705 train 7.258319 (lr=3.6147e-05) (hash(x)=27260043) +3706 train 7.347307 (lr=3.6116e-05) (hash(x)=26847649) +3707 train 7.281160 (lr=3.6085e-05) (hash(x)=25843618) +3708 train 7.268556 (lr=3.6054e-05) (hash(x)=25828009) +3709 train 7.324835 (lr=3.6024e-05) (hash(x)=24960960) +3710 train 7.402749 (lr=3.5993e-05) (hash(x)=24852741) +3711 train 6.873134 (lr=3.5962e-05) (hash(x)=23769243) +3712 train 7.055810 (lr=3.5931e-05) (hash(x)=27110690) +3713 train 7.095843 (lr=3.5901e-05) (hash(x)=22817285) +3714 train 6.802516 (lr=3.5870e-05) (hash(x)=19618355) +3715 train 7.319433 (lr=3.5839e-05) (hash(x)=28731298) +3716 train 7.098761 (lr=3.5809e-05) (hash(x)=23091196) +3717 train 7.654583 (lr=3.5778e-05) (hash(x)=28825233) +3718 train 7.175251 (lr=3.5747e-05) (hash(x)=25778506) +3719 train 7.092715 (lr=3.5717e-05) (hash(x)=23788738) +3720 train 6.502929 (lr=3.5686e-05) (hash(x)=16684794) +3721 train 7.005251 (lr=3.5656e-05) (hash(x)=24755102) +3722 train 7.264670 (lr=3.5625e-05) (hash(x)=26839238) +3723 train 7.300893 (lr=3.5595e-05) (hash(x)=26599031) +3724 train 7.174611 (lr=3.5564e-05) (hash(x)=25945650) +3725 train 7.338567 (lr=3.5534e-05) (hash(x)=27434751) +3726 train 7.089014 (lr=3.5503e-05) (hash(x)=24814591) +3727 train 7.042024 (lr=3.5473e-05) (hash(x)=24818744) +3728 train 7.145859 (lr=3.5442e-05) (hash(x)=25649817) +3729 train 7.040586 (lr=3.5412e-05) (hash(x)=24987021) +3730 train 6.968857 (lr=3.5382e-05) (hash(x)=24667779) +3731 train 6.943425 (lr=3.5351e-05) (hash(x)=23053871) +3732 train 6.667002 (lr=3.5321e-05) (hash(x)=19264856) +3733 train 7.253471 (lr=3.5291e-05) (hash(x)=23718117) +3734 train 6.956268 (lr=3.5260e-05) (hash(x)=21904779) +3735 train 7.162458 (lr=3.5230e-05) (hash(x)=23472795) +3736 train 7.410232 (lr=3.5200e-05) (hash(x)=24650440) +3737 train 7.473015 (lr=3.5169e-05) (hash(x)=25243911) +3738 train 7.885060 (lr=3.5139e-05) (hash(x)=30423616) +3739 train 7.894575 (lr=3.5109e-05) (hash(x)=29748225) +3740 train 7.233720 (lr=3.5079e-05) (hash(x)=25180684) +3741 train 7.243970 (lr=3.5049e-05) (hash(x)=25619065) +3742 train 7.629159 (lr=3.5018e-05) (hash(x)=31847002) +3743 train 7.183177 (lr=3.4988e-05) (hash(x)=24991832) +3744 train 7.118145 (lr=3.4958e-05) (hash(x)=23836263) +3745 train 7.004973 (lr=3.4928e-05) (hash(x)=24651902) +3746 train 7.541097 (lr=3.4898e-05) (hash(x)=22936538) +3747 train 7.536099 (lr=3.4868e-05) (hash(x)=23681545) +3748 train 6.921567 (lr=3.4838e-05) (hash(x)=21140825) +3749 train 7.103238 (lr=3.4808e-05) (hash(x)=24932453) +3750 val loss 7.1998 +3750 val perplexity 1339.1495 +3750 train 7.253008 (lr=3.4778e-05) (hash(x)=25919062) +3751 train 7.071481 (lr=3.4748e-05) (hash(x)=22424066) +3752 train 7.127196 (lr=3.4718e-05) (hash(x)=23542210) +3753 train 6.973787 (lr=3.4688e-05) (hash(x)=22113561) +3754 train 6.881009 (lr=3.4658e-05) (hash(x)=24892794) +3755 train 7.341486 (lr=3.4628e-05) (hash(x)=25262748) +3756 train 7.124444 (lr=3.4598e-05) (hash(x)=24477975) +3757 train 6.950553 (lr=3.4568e-05) (hash(x)=24681189) +3758 train 6.958235 (lr=3.4538e-05) (hash(x)=24052603) +3759 train 7.227890 (lr=3.4509e-05) (hash(x)=26474878) +3760 train 7.761997 (lr=3.4479e-05) (hash(x)=28228836) +3761 train 7.284532 (lr=3.4449e-05) (hash(x)=23832522) +3762 train 7.220709 (lr=3.4419e-05) (hash(x)=24416789) +3763 train 6.997516 (lr=3.4389e-05) (hash(x)=23930593) +3764 train 7.061749 (lr=3.4360e-05) (hash(x)=23895092) +3765 train 6.993328 (lr=3.4330e-05) (hash(x)=26865287) +3766 train 7.033607 (lr=3.4300e-05) (hash(x)=21330722) +3767 train 7.108977 (lr=3.4271e-05) (hash(x)=22704349) +3768 train 7.239270 (lr=3.4241e-05) (hash(x)=27740886) +3769 train 7.217856 (lr=3.4211e-05) (hash(x)=24935936) +3770 train 7.058591 (lr=3.4182e-05) (hash(x)=23497487) +3771 train 7.272497 (lr=3.4152e-05) (hash(x)=24801048) +3772 train 7.009686 (lr=3.4122e-05) (hash(x)=25490486) +3773 train 7.022198 (lr=3.4093e-05) (hash(x)=21166466) +3774 train 7.248306 (lr=3.4063e-05) (hash(x)=23225244) +3775 train 7.037389 (lr=3.4034e-05) (hash(x)=22293673) +3776 train 7.342783 (lr=3.4004e-05) (hash(x)=25700016) +3777 train 6.870516 (lr=3.3975e-05) (hash(x)=22370207) +3778 train 7.228444 (lr=3.3945e-05) (hash(x)=25224849) +3779 train 7.149422 (lr=3.3916e-05) (hash(x)=23311934) +3780 train 6.868070 (lr=3.3886e-05) (hash(x)=19627124) +3781 train 7.428249 (lr=3.3857e-05) (hash(x)=27132838) +3782 train 7.317469 (lr=3.3828e-05) (hash(x)=27242104) +3783 train 6.837650 (lr=3.3798e-05) (hash(x)=21785487) +3784 train 7.134882 (lr=3.3769e-05) (hash(x)=25798262) +3785 train 7.037506 (lr=3.3739e-05) (hash(x)=24806937) +3786 train 6.886395 (lr=3.3710e-05) (hash(x)=24098756) +3787 train 6.897568 (lr=3.3681e-05) (hash(x)=22981456) +3788 train 7.307701 (lr=3.3652e-05) (hash(x)=22441908) +3789 train 7.260732 (lr=3.3622e-05) (hash(x)=25867804) +3790 train 7.140359 (lr=3.3593e-05) (hash(x)=22835586) +3791 train 7.358664 (lr=3.3564e-05) (hash(x)=25251063) +3792 train 7.162197 (lr=3.3535e-05) (hash(x)=27059729) +3793 train 7.160582 (lr=3.3505e-05) (hash(x)=23819311) +3794 train 6.850957 (lr=3.3476e-05) (hash(x)=21345757) +3795 train 7.097429 (lr=3.3447e-05) (hash(x)=25796422) +3796 train 6.777113 (lr=3.3418e-05) (hash(x)=21414971) +3797 train 7.077253 (lr=3.3389e-05) (hash(x)=26120920) +3798 train 7.006793 (lr=3.3360e-05) (hash(x)=22008247) +3799 train 7.098940 (lr=3.3331e-05) (hash(x)=22722211) +3800 val loss 7.1811 +3800 val perplexity 1314.2936 +3800 train 6.834338 (lr=3.3302e-05) (hash(x)=24484513) +3801 train 7.167488 (lr=3.3273e-05) (hash(x)=24463866) +3802 train 7.173922 (lr=3.3244e-05) (hash(x)=26470775) +3803 train 7.180820 (lr=3.3215e-05) (hash(x)=24296755) +3804 train 7.188184 (lr=3.3186e-05) (hash(x)=24381309) +3805 train 7.376666 (lr=3.3157e-05) (hash(x)=26781262) +3806 train 6.892002 (lr=3.3128e-05) (hash(x)=23563137) +3807 train 7.084507 (lr=3.3099e-05) (hash(x)=24522269) +3808 train 6.925259 (lr=3.3070e-05) (hash(x)=22871995) +3809 train 7.243277 (lr=3.3041e-05) (hash(x)=24751946) +3810 train 7.066905 (lr=3.3012e-05) (hash(x)=19879741) +3811 train 7.120482 (lr=3.2983e-05) (hash(x)=25617184) +3812 train 6.822845 (lr=3.2954e-05) (hash(x)=21776722) +3813 train 6.939682 (lr=3.2926e-05) (hash(x)=22663402) +3814 train 7.268650 (lr=3.2897e-05) (hash(x)=26072046) +3815 train 6.930638 (lr=3.2868e-05) (hash(x)=23329475) +3816 train 7.000389 (lr=3.2839e-05) (hash(x)=25519031) +3817 train 7.010925 (lr=3.2811e-05) (hash(x)=22846270) +3818 train 6.991301 (lr=3.2782e-05) (hash(x)=20299429) +3819 train 7.461424 (lr=3.2753e-05) (hash(x)=30652062) +3820 train 6.805022 (lr=3.2725e-05) (hash(x)=19824665) +3821 train 7.327148 (lr=3.2696e-05) (hash(x)=26698904) +3822 train 7.158213 (lr=3.2667e-05) (hash(x)=27612163) +3823 train 6.943733 (lr=3.2639e-05) (hash(x)=24735165) +3824 train 6.692717 (lr=3.2610e-05) (hash(x)=19965890) +3825 train 6.891288 (lr=3.2582e-05) (hash(x)=23518594) +3826 train 6.854398 (lr=3.2553e-05) (hash(x)=22388460) +3827 train 6.942941 (lr=3.2525e-05) (hash(x)=23795686) +3828 train 6.821544 (lr=3.2496e-05) (hash(x)=24470150) +3829 train 6.513958 (lr=3.2468e-05) (hash(x)=19483392) +3830 train 6.929645 (lr=3.2439e-05) (hash(x)=23304516) +3831 train 7.281114 (lr=3.2411e-05) (hash(x)=27002892) +3832 train 6.993756 (lr=3.2382e-05) (hash(x)=22114813) +3833 train 7.184073 (lr=3.2354e-05) (hash(x)=26221916) +3834 train 6.751472 (lr=3.2325e-05) (hash(x)=27261960) +3835 train 7.004014 (lr=3.2297e-05) (hash(x)=21189101) +3836 train 6.671837 (lr=3.2269e-05) (hash(x)=20638173) +3837 train 7.124084 (lr=3.2240e-05) (hash(x)=25497439) +3838 train 6.607613 (lr=3.2212e-05) (hash(x)=20460499) +3839 train 7.059116 (lr=3.2184e-05) (hash(x)=23499349) +3840 train 7.940271 (lr=3.2156e-05) (hash(x)=22671939) +3841 train 7.979619 (lr=3.2127e-05) (hash(x)=26809295) +3842 train 7.140314 (lr=3.2099e-05) (hash(x)=28094504) +3843 train 7.109097 (lr=3.2071e-05) (hash(x)=26807896) +3844 train 7.195441 (lr=3.2043e-05) (hash(x)=24749334) +3845 train 7.084378 (lr=3.2014e-05) (hash(x)=25031330) +3846 train 6.993186 (lr=3.1986e-05) (hash(x)=23008126) +3847 train 6.961284 (lr=3.1958e-05) (hash(x)=22461589) +3848 train 7.242705 (lr=3.1930e-05) (hash(x)=24959391) +3849 train 7.124872 (lr=3.1902e-05) (hash(x)=24239512) +3850 val loss 7.1778 +3850 val perplexity 1310.0214 +3850 train 6.971757 (lr=3.1874e-05) (hash(x)=24760422) +3851 train 7.467918 (lr=3.1846e-05) (hash(x)=26904123) +3852 train 6.610110 (lr=3.1818e-05) (hash(x)=17986444) +3853 train 6.964986 (lr=3.1790e-05) (hash(x)=21618533) +3854 train 7.022832 (lr=3.1762e-05) (hash(x)=27107027) +3855 train 7.266214 (lr=3.1734e-05) (hash(x)=26415040) +3856 train 7.841388 (lr=3.1706e-05) (hash(x)=28682703) +3857 train 6.993505 (lr=3.1678e-05) (hash(x)=22824767) +3858 train 7.152393 (lr=3.1650e-05) (hash(x)=24540450) +3859 train 7.092966 (lr=3.1622e-05) (hash(x)=24463181) +3860 train 7.021291 (lr=3.1594e-05) (hash(x)=22832558) +3861 train 7.226544 (lr=3.1567e-05) (hash(x)=26582384) +3862 train 7.877771 (lr=3.1539e-05) (hash(x)=32327364) +3863 train 7.254330 (lr=3.1511e-05) (hash(x)=26349465) +3864 train 6.991210 (lr=3.1483e-05) (hash(x)=23079414) +3865 train 7.043369 (lr=3.1455e-05) (hash(x)=23464639) +3866 train 6.881810 (lr=3.1428e-05) (hash(x)=21406620) +3867 train 6.723362 (lr=3.1400e-05) (hash(x)=21205988) +3868 train 6.790756 (lr=3.1372e-05) (hash(x)=22742634) +3869 train 6.856003 (lr=3.1344e-05) (hash(x)=24868938) +3870 train 7.221594 (lr=3.1317e-05) (hash(x)=28095283) +3871 train 6.894435 (lr=3.1289e-05) (hash(x)=21596677) +3872 train 7.150549 (lr=3.1262e-05) (hash(x)=26884381) +3873 train 7.210010 (lr=3.1234e-05) (hash(x)=26410272) +3874 train 6.967173 (lr=3.1206e-05) (hash(x)=22915785) +3875 train 7.000971 (lr=3.1179e-05) (hash(x)=23575666) +3876 train 6.952659 (lr=3.1151e-05) (hash(x)=25313223) +3877 train 6.417073 (lr=3.1124e-05) (hash(x)=16319719) +3878 train 7.068936 (lr=3.1096e-05) (hash(x)=23227579) +3879 train 7.008932 (lr=3.1069e-05) (hash(x)=24117012) +3880 train 7.052654 (lr=3.1041e-05) (hash(x)=24681517) +3881 train 6.985812 (lr=3.1014e-05) (hash(x)=23186527) +3882 train 6.979100 (lr=3.0986e-05) (hash(x)=23472784) +3883 train 6.984890 (lr=3.0959e-05) (hash(x)=26013014) +3884 train 7.255095 (lr=3.0932e-05) (hash(x)=25952206) +3885 train 7.314950 (lr=3.0904e-05) (hash(x)=23897834) +3886 train 7.032739 (lr=3.0877e-05) (hash(x)=26350364) +3887 train 7.082642 (lr=3.0850e-05) (hash(x)=24105761) +3888 train 7.192684 (lr=3.0822e-05) (hash(x)=22801707) +3889 train 7.001634 (lr=3.0795e-05) (hash(x)=21821937) +3890 train 6.952478 (lr=3.0768e-05) (hash(x)=24264640) +3891 train 6.900198 (lr=3.0741e-05) (hash(x)=20369133) +3892 train 6.882306 (lr=3.0713e-05) (hash(x)=24313506) +3893 train 6.892406 (lr=3.0686e-05) (hash(x)=22104086) +3894 train 7.106783 (lr=3.0659e-05) (hash(x)=25312602) +3895 train 7.172913 (lr=3.0632e-05) (hash(x)=25725049) +3896 train 6.988027 (lr=3.0605e-05) (hash(x)=22981231) +3897 train 6.854400 (lr=3.0578e-05) (hash(x)=18021467) +3898 train 6.821631 (lr=3.0550e-05) (hash(x)=17960254) +3899 train 7.018947 (lr=3.0523e-05) (hash(x)=19808118) +3900 val loss 7.1742 +3900 val perplexity 1305.3485 +3900 train 6.786296 (lr=3.0496e-05) (hash(x)=21022829) +3901 train 6.962004 (lr=3.0469e-05) (hash(x)=22434663) +3902 train 6.686827 (lr=3.0442e-05) (hash(x)=20208091) +3903 train 6.805414 (lr=3.0415e-05) (hash(x)=22892776) +3904 train 6.920599 (lr=3.0388e-05) (hash(x)=21554367) +3905 train 7.068912 (lr=3.0361e-05) (hash(x)=23704875) +3906 train 7.018057 (lr=3.0334e-05) (hash(x)=21690340) +3907 train 6.951229 (lr=3.0308e-05) (hash(x)=23736780) +3908 train 6.815140 (lr=3.0281e-05) (hash(x)=21060920) +3909 train 6.767292 (lr=3.0254e-05) (hash(x)=20091559) +3910 train 7.041125 (lr=3.0227e-05) (hash(x)=22147974) +3911 train 6.996611 (lr=3.0200e-05) (hash(x)=21630383) +3912 train 7.260005 (lr=3.0173e-05) (hash(x)=28339385) +3913 train 7.063073 (lr=3.0146e-05) (hash(x)=25355505) +3914 train 6.921594 (lr=3.0120e-05) (hash(x)=20843914) +3915 train 7.413623 (lr=3.0093e-05) (hash(x)=25397467) +3916 train 7.119503 (lr=3.0066e-05) (hash(x)=23587501) +3917 train 6.726419 (lr=3.0040e-05) (hash(x)=19036533) +3918 train 6.901289 (lr=3.0013e-05) (hash(x)=29749389) +3919 train 6.815471 (lr=2.9986e-05) (hash(x)=24727094) +3920 train 6.834372 (lr=2.9960e-05) (hash(x)=22723450) +3921 train 7.011889 (lr=2.9933e-05) (hash(x)=24424680) +3922 train 7.181754 (lr=2.9906e-05) (hash(x)=25817917) +3923 train 6.932485 (lr=2.9880e-05) (hash(x)=23951182) +3924 train 6.958196 (lr=2.9853e-05) (hash(x)=21177944) +3925 train 6.816103 (lr=2.9827e-05) (hash(x)=23533768) +3926 train 7.035071 (lr=2.9800e-05) (hash(x)=24263615) +3927 train 6.860940 (lr=2.9774e-05) (hash(x)=22835000) +3928 train 7.072669 (lr=2.9747e-05) (hash(x)=26076156) +3929 train 7.030786 (lr=2.9721e-05) (hash(x)=25171508) +3930 train 7.053300 (lr=2.9694e-05) (hash(x)=22021396) +3931 train 7.339581 (lr=2.9668e-05) (hash(x)=28767849) +3932 train 7.268169 (lr=2.9641e-05) (hash(x)=29497606) +3933 train 6.917274 (lr=2.9615e-05) (hash(x)=22723124) +3934 train 7.152611 (lr=2.9589e-05) (hash(x)=27106616) +3935 train 7.027034 (lr=2.9562e-05) (hash(x)=22839049) +3936 train 7.062318 (lr=2.9536e-05) (hash(x)=25101923) +3937 train 7.032794 (lr=2.9510e-05) (hash(x)=25945975) +3938 train 7.152845 (lr=2.9484e-05) (hash(x)=25382013) +3939 train 6.729002 (lr=2.9457e-05) (hash(x)=19930900) +3940 train 6.856444 (lr=2.9431e-05) (hash(x)=22202373) +3941 train 7.050385 (lr=2.9405e-05) (hash(x)=24592992) +3942 train 6.930090 (lr=2.9379e-05) (hash(x)=25002271) +3943 train 6.813916 (lr=2.9353e-05) (hash(x)=20654136) +3944 train 6.871587 (lr=2.9326e-05) (hash(x)=20061590) +3945 train 6.806853 (lr=2.9300e-05) (hash(x)=21441361) +3946 train 6.997829 (lr=2.9274e-05) (hash(x)=20055468) +3947 train 7.734145 (lr=2.9248e-05) (hash(x)=28495621) +3948 train 7.128910 (lr=2.9222e-05) (hash(x)=25959236) +3949 train 7.464672 (lr=2.9196e-05) (hash(x)=26750193) +3950 val loss 7.1748 +3950 val perplexity 1306.0415 +3950 train 7.303829 (lr=2.9170e-05) (hash(x)=25882605) +3951 train 7.359646 (lr=2.9144e-05) (hash(x)=26776000) +3952 train 6.949532 (lr=2.9118e-05) (hash(x)=24155107) +3953 train 7.030990 (lr=2.9092e-05) (hash(x)=23441845) +3954 train 6.947021 (lr=2.9066e-05) (hash(x)=22860915) +3955 train 6.749992 (lr=2.9040e-05) (hash(x)=21584429) +3956 train 6.358603 (lr=2.9014e-05) (hash(x)=16535556) +3957 train 6.443997 (lr=2.8988e-05) (hash(x)=17946180) +3958 train 6.990730 (lr=2.8963e-05) (hash(x)=25367610) +3959 train 6.866565 (lr=2.8937e-05) (hash(x)=22560658) +3960 train 7.154089 (lr=2.8911e-05) (hash(x)=23809585) +3961 train 7.392783 (lr=2.8885e-05) (hash(x)=20438213) +3962 train 7.751945 (lr=2.8859e-05) (hash(x)=30520037) +3963 train 7.384092 (lr=2.8834e-05) (hash(x)=25276565) +3964 train 7.089900 (lr=2.8808e-05) (hash(x)=26796532) +3965 train 6.898118 (lr=2.8782e-05) (hash(x)=22850475) +3966 train 7.403166 (lr=2.8757e-05) (hash(x)=25983698) +3967 train 7.300545 (lr=2.8731e-05) (hash(x)=25995933) +3968 train 7.469910 (lr=2.8705e-05) (hash(x)=25319339) +3969 train 7.091020 (lr=2.8680e-05) (hash(x)=25066892) +3970 train 7.280902 (lr=2.8654e-05) (hash(x)=26931819) +3971 train 7.248802 (lr=2.8629e-05) (hash(x)=24163910) +3972 train 7.141578 (lr=2.8603e-05) (hash(x)=25359634) +3973 train 7.043775 (lr=2.8577e-05) (hash(x)=24323444) +3974 train 7.200238 (lr=2.8552e-05) (hash(x)=26529231) +3975 train 7.218015 (lr=2.8527e-05) (hash(x)=24635394) +3976 train 7.509487 (lr=2.8501e-05) (hash(x)=24783093) +3977 train 7.658687 (lr=2.8476e-05) (hash(x)=26710509) +3978 train 7.044450 (lr=2.8450e-05) (hash(x)=25396630) +3979 train 6.952259 (lr=2.8425e-05) (hash(x)=22556381) +3980 train 7.276208 (lr=2.8399e-05) (hash(x)=26912161) +3981 train 6.816760 (lr=2.8374e-05) (hash(x)=22268078) +3982 train 7.890492 (lr=2.8349e-05) (hash(x)=30430328) +3983 train 7.499481 (lr=2.8323e-05) (hash(x)=27537228) +3984 train 6.909999 (lr=2.8298e-05) (hash(x)=24468603) +3985 train 7.213571 (lr=2.8273e-05) (hash(x)=27006663) +3986 train 7.458225 (lr=2.8248e-05) (hash(x)=27014728) +3987 train 6.932420 (lr=2.8222e-05) (hash(x)=20883633) +3988 train 7.024422 (lr=2.8197e-05) (hash(x)=23361791) +3989 train 7.119829 (lr=2.8172e-05) (hash(x)=26775925) +3990 train 7.672043 (lr=2.8147e-05) (hash(x)=30648934) +3991 train 7.171169 (lr=2.8122e-05) (hash(x)=26496730) +3992 train 7.006614 (lr=2.8097e-05) (hash(x)=25942897) +3993 train 7.024738 (lr=2.8071e-05) (hash(x)=24887111) +3994 train 6.939485 (lr=2.8046e-05) (hash(x)=22908550) +3995 train 6.649817 (lr=2.8021e-05) (hash(x)=20342150) +3996 train 6.931175 (lr=2.7996e-05) (hash(x)=22261760) +3997 train 6.991802 (lr=2.7971e-05) (hash(x)=22731641) +3998 train 6.859593 (lr=2.7946e-05) (hash(x)=20669749) +3999 train 6.791239 (lr=2.7921e-05) (hash(x)=16533310) +4000 val loss 7.1718 +4000 val perplexity 1302.2164 +4000 train 7.013978 (lr=2.7896e-05) (hash(x)=23661341) +4001 train 6.998288 (lr=2.7871e-05) (hash(x)=24644301) +4002 train 6.815990 (lr=2.7847e-05) (hash(x)=22938438) +4003 train 6.917964 (lr=2.7822e-05) (hash(x)=24315862) +4004 train 7.117396 (lr=2.7797e-05) (hash(x)=25169315) +4005 train 7.080208 (lr=2.7772e-05) (hash(x)=24752796) +4006 train 7.082100 (lr=2.7747e-05) (hash(x)=23103706) +4007 train 7.172225 (lr=2.7722e-05) (hash(x)=24881176) +4008 train 7.063666 (lr=2.7698e-05) (hash(x)=23971947) +4009 train 7.383003 (lr=2.7673e-05) (hash(x)=27741054) +4010 train 7.758024 (lr=2.7648e-05) (hash(x)=30956251) +4011 train 7.129683 (lr=2.7623e-05) (hash(x)=23649686) +4012 train 6.934062 (lr=2.7599e-05) (hash(x)=23344798) +4013 train 7.594459 (lr=2.7574e-05) (hash(x)=29529498) +4014 train 7.118653 (lr=2.7549e-05) (hash(x)=24688359) +4015 train 7.069146 (lr=2.7525e-05) (hash(x)=25593613) +4016 train 7.217362 (lr=2.7500e-05) (hash(x)=25674488) +4017 train 6.668942 (lr=2.7476e-05) (hash(x)=21345346) +4018 train 6.958019 (lr=2.7451e-05) (hash(x)=21978324) +4019 train 6.997412 (lr=2.7426e-05) (hash(x)=23669244) +4020 train 6.870175 (lr=2.7402e-05) (hash(x)=22479613) +4021 train 6.876058 (lr=2.7377e-05) (hash(x)=22855256) +4022 train 7.265795 (lr=2.7353e-05) (hash(x)=19759826) +4023 train 7.167641 (lr=2.7328e-05) (hash(x)=22886646) +4024 train 7.099040 (lr=2.7304e-05) (hash(x)=25553008) +4025 train 7.006223 (lr=2.7280e-05) (hash(x)=25487028) +4026 train 7.579729 (lr=2.7255e-05) (hash(x)=26799246) +4027 train 7.843260 (lr=2.7231e-05) (hash(x)=30728540) +4028 train 7.245677 (lr=2.7207e-05) (hash(x)=23966676) +4029 train 7.005416 (lr=2.7182e-05) (hash(x)=22118783) +4030 train 7.116393 (lr=2.7158e-05) (hash(x)=24744703) +4031 train 7.091264 (lr=2.7134e-05) (hash(x)=21407676) +4032 train 7.024320 (lr=2.7109e-05) (hash(x)=20623349) +4033 train 6.833093 (lr=2.7085e-05) (hash(x)=24723788) +4034 train 7.152109 (lr=2.7061e-05) (hash(x)=25030709) +4035 train 7.186693 (lr=2.7037e-05) (hash(x)=26326164) +4036 train 7.049156 (lr=2.7013e-05) (hash(x)=23754475) +4037 train 7.658952 (lr=2.6988e-05) (hash(x)=30112933) +4038 train 7.392285 (lr=2.6964e-05) (hash(x)=27474299) +4039 train 6.892795 (lr=2.6940e-05) (hash(x)=21720304) +4040 train 7.293518 (lr=2.6916e-05) (hash(x)=25142674) +4041 train 7.522836 (lr=2.6892e-05) (hash(x)=25284552) +4042 train 7.421910 (lr=2.6868e-05) (hash(x)=24554942) +4043 train 7.138219 (lr=2.6844e-05) (hash(x)=23773870) +4044 train 6.920102 (lr=2.6820e-05) (hash(x)=23896338) +4045 train 7.736927 (lr=2.6796e-05) (hash(x)=34984911) +4046 train 7.013528 (lr=2.6772e-05) (hash(x)=23854263) +4047 train 7.291966 (lr=2.6748e-05) (hash(x)=27263416) +4048 train 6.972830 (lr=2.6724e-05) (hash(x)=24989642) +4049 train 7.027434 (lr=2.6700e-05) (hash(x)=24492055) +4050 val loss 7.1803 +4050 val perplexity 1313.2781 +4050 train 6.917507 (lr=2.6677e-05) (hash(x)=21579916) +4051 train 7.140384 (lr=2.6653e-05) (hash(x)=25274710) +4052 train 7.028111 (lr=2.6629e-05) (hash(x)=24701947) +4053 train 7.049405 (lr=2.6605e-05) (hash(x)=25477340) +4054 train 6.929274 (lr=2.6581e-05) (hash(x)=23774195) +4055 train 7.197583 (lr=2.6558e-05) (hash(x)=25840801) +4056 train 7.425987 (lr=2.6534e-05) (hash(x)=27972529) +4057 train 7.145441 (lr=2.6510e-05) (hash(x)=26952458) +4058 train 6.661766 (lr=2.6487e-05) (hash(x)=22683653) +4059 train 6.739178 (lr=2.6463e-05) (hash(x)=20984129) +4060 train 6.909454 (lr=2.6439e-05) (hash(x)=22816482) +4061 train 7.190052 (lr=2.6416e-05) (hash(x)=24285302) +4062 train 7.611822 (lr=2.6392e-05) (hash(x)=31517950) +4063 train 7.864732 (lr=2.6368e-05) (hash(x)=31424568) +4064 train 7.504985 (lr=2.6345e-05) (hash(x)=29497876) +4065 train 7.386289 (lr=2.6321e-05) (hash(x)=27277376) +4066 train 7.137138 (lr=2.6298e-05) (hash(x)=26832588) +4067 train 6.959523 (lr=2.6274e-05) (hash(x)=25149712) +4068 train 6.971551 (lr=2.6251e-05) (hash(x)=23728457) +4069 train 6.852570 (lr=2.6227e-05) (hash(x)=25265136) +4070 train 7.400706 (lr=2.6204e-05) (hash(x)=25241681) +4071 train 7.094626 (lr=2.6181e-05) (hash(x)=23403065) +4072 train 7.069156 (lr=2.6157e-05) (hash(x)=25808207) +4073 train 6.965811 (lr=2.6134e-05) (hash(x)=23904844) +4074 train 6.679368 (lr=2.6111e-05) (hash(x)=18865309) +4075 train 7.137897 (lr=2.6087e-05) (hash(x)=23531744) +4076 train 7.162398 (lr=2.6064e-05) (hash(x)=25784275) +4077 train 6.902641 (lr=2.6041e-05) (hash(x)=22417529) +4078 train 6.922073 (lr=2.6018e-05) (hash(x)=23095491) +4079 train 7.063469 (lr=2.5994e-05) (hash(x)=22656033) +4080 train 7.056767 (lr=2.5971e-05) (hash(x)=25865435) +4081 train 7.173225 (lr=2.5948e-05) (hash(x)=25699377) +4082 train 7.162250 (lr=2.5925e-05) (hash(x)=20854084) +4083 train 6.728592 (lr=2.5902e-05) (hash(x)=18950799) +4084 train 6.953790 (lr=2.5879e-05) (hash(x)=22633739) +4085 train 7.807085 (lr=2.5855e-05) (hash(x)=34054446) +4086 train 7.294539 (lr=2.5832e-05) (hash(x)=27599387) +4087 train 7.131840 (lr=2.5809e-05) (hash(x)=26869295) +4088 train 7.124730 (lr=2.5786e-05) (hash(x)=24075139) +4089 train 7.539556 (lr=2.5763e-05) (hash(x)=29784110) +4090 train 7.860716 (lr=2.5740e-05) (hash(x)=34273918) +4091 train 8.175191 (lr=2.5717e-05) (hash(x)=34472685) +4092 train 7.575471 (lr=2.5695e-05) (hash(x)=30113791) +4093 train 6.833837 (lr=2.5672e-05) (hash(x)=22366381) +4094 train 7.075379 (lr=2.5649e-05) (hash(x)=24922935) +4095 train 7.300447 (lr=2.5626e-05) (hash(x)=25504151) +4096 train 7.261137 (lr=2.5603e-05) (hash(x)=24517375) +4097 train 7.910589 (lr=2.5580e-05) (hash(x)=25871651) +4098 train 6.978902 (lr=2.5557e-05) (hash(x)=23480225) +4099 train 6.821890 (lr=2.5535e-05) (hash(x)=22559978) +4100 val loss 7.1730 +4100 val perplexity 1303.7815 +4100 train 7.259817 (lr=2.5512e-05) (hash(x)=25795272) +4101 train 7.240514 (lr=2.5489e-05) (hash(x)=25440399) +4102 train 6.900675 (lr=2.5467e-05) (hash(x)=21581806) +4103 train 6.988177 (lr=2.5444e-05) (hash(x)=25781518) +4104 train 7.085687 (lr=2.5421e-05) (hash(x)=24682372) +4105 train 6.916686 (lr=2.5399e-05) (hash(x)=22440094) +4106 train 7.088928 (lr=2.5376e-05) (hash(x)=23661032) +4107 train 7.323509 (lr=2.5353e-05) (hash(x)=26966012) +4108 train 7.357301 (lr=2.5331e-05) (hash(x)=26232227) +4109 train 7.013024 (lr=2.5308e-05) (hash(x)=24110656) +4110 train 7.294304 (lr=2.5286e-05) (hash(x)=25938621) +4111 train 7.097920 (lr=2.5263e-05) (hash(x)=26432850) +4112 train 7.087144 (lr=2.5241e-05) (hash(x)=25387672) +4113 train 6.877262 (lr=2.5218e-05) (hash(x)=22740017) +4114 train 7.259304 (lr=2.5196e-05) (hash(x)=26384190) +4115 train 6.956977 (lr=2.5173e-05) (hash(x)=24725583) +4116 train 7.065678 (lr=2.5151e-05) (hash(x)=23986700) +4117 train 7.112410 (lr=2.5129e-05) (hash(x)=18529900) +4118 train 7.105544 (lr=2.5106e-05) (hash(x)=22236257) +4119 train 6.748999 (lr=2.5084e-05) (hash(x)=20155894) +4120 train 6.550818 (lr=2.5062e-05) (hash(x)=17423813) +4121 train 6.491292 (lr=2.5040e-05) (hash(x)=18905183) +4122 train 6.867987 (lr=2.5017e-05) (hash(x)=22534398) +4123 train 7.559404 (lr=2.4995e-05) (hash(x)=25247868) +4124 train 7.068448 (lr=2.4973e-05) (hash(x)=23994188) +4125 train 6.922894 (lr=2.4951e-05) (hash(x)=22929754) +4126 train 6.824776 (lr=2.4929e-05) (hash(x)=22485897) +4127 train 6.876600 (lr=2.4906e-05) (hash(x)=22270169) +4128 train 6.849041 (lr=2.4884e-05) (hash(x)=23638027) +4129 train 7.145606 (lr=2.4862e-05) (hash(x)=23821210) +4130 train 7.012353 (lr=2.4840e-05) (hash(x)=25021512) +4131 train 7.095746 (lr=2.4818e-05) (hash(x)=25240141) +4132 train 7.071268 (lr=2.4796e-05) (hash(x)=22833160) +4133 train 6.995227 (lr=2.4774e-05) (hash(x)=22909944) +4134 train 7.224452 (lr=2.4752e-05) (hash(x)=26163558) +4135 train 6.993726 (lr=2.4730e-05) (hash(x)=22108461) +4136 train 6.937765 (lr=2.4708e-05) (hash(x)=22549232) +4137 train 7.156264 (lr=2.4686e-05) (hash(x)=24701302) +4138 train 7.214096 (lr=2.4664e-05) (hash(x)=25206013) +4139 train 7.223520 (lr=2.4643e-05) (hash(x)=27896130) +4140 train 6.939670 (lr=2.4621e-05) (hash(x)=24106243) +4141 train 7.542768 (lr=2.4599e-05) (hash(x)=27158651) +4142 train 7.109832 (lr=2.4577e-05) (hash(x)=23841147) +4143 train 7.067370 (lr=2.4555e-05) (hash(x)=24802848) +4144 train 7.363900 (lr=2.4534e-05) (hash(x)=24911295) +4145 train 7.123436 (lr=2.4512e-05) (hash(x)=26473900) +4146 train 7.203803 (lr=2.4490e-05) (hash(x)=26785092) +4147 train 7.487604 (lr=2.4468e-05) (hash(x)=30188532) +4148 train 7.004764 (lr=2.4447e-05) (hash(x)=25010649) +4149 train 6.983919 (lr=2.4425e-05) (hash(x)=22409016) +4150 val loss 7.1743 +4150 val perplexity 1305.5048 +4150 train 7.756027 (lr=2.4404e-05) (hash(x)=31675024) +4151 train 7.014580 (lr=2.4382e-05) (hash(x)=25086604) +4152 train 7.043926 (lr=2.4360e-05) (hash(x)=24429343) +4153 train 7.203441 (lr=2.4339e-05) (hash(x)=25014232) +4154 train 7.118006 (lr=2.4317e-05) (hash(x)=25366275) +4155 train 7.582210 (lr=2.4296e-05) (hash(x)=24031473) +4156 train 7.101635 (lr=2.4274e-05) (hash(x)=26651059) +4157 train 7.205573 (lr=2.4253e-05) (hash(x)=26069721) +4158 train 7.367058 (lr=2.4232e-05) (hash(x)=28114382) +4159 train 7.356337 (lr=2.4210e-05) (hash(x)=26983186) +4160 train 6.702929 (lr=2.4189e-05) (hash(x)=21944670) +4161 train 7.467416 (lr=2.4167e-05) (hash(x)=28155702) +4162 train 6.900896 (lr=2.4146e-05) (hash(x)=24765002) +4163 train 7.137973 (lr=2.4125e-05) (hash(x)=26492636) +4164 train 7.105614 (lr=2.4103e-05) (hash(x)=24063705) +4165 train 7.380712 (lr=2.4082e-05) (hash(x)=27079573) +4166 train 7.038915 (lr=2.4061e-05) (hash(x)=24912201) +4167 train 7.145119 (lr=2.4040e-05) (hash(x)=27208507) +4168 train 7.040349 (lr=2.4019e-05) (hash(x)=25824320) +4169 train 7.572559 (lr=2.3997e-05) (hash(x)=29641677) +4170 train 7.307070 (lr=2.3976e-05) (hash(x)=26275614) +4171 train 7.125183 (lr=2.3955e-05) (hash(x)=25227725) +4172 train 7.219728 (lr=2.3934e-05) (hash(x)=27417375) +4173 train 7.394345 (lr=2.3913e-05) (hash(x)=25581973) +4174 train 7.647917 (lr=2.3892e-05) (hash(x)=30360417) +4175 train 6.946986 (lr=2.3871e-05) (hash(x)=23862845) +4176 train 7.047952 (lr=2.3850e-05) (hash(x)=25415130) +4177 train 7.023575 (lr=2.3829e-05) (hash(x)=23111123) +4178 train 6.981290 (lr=2.3808e-05) (hash(x)=24022804) +4179 train 7.012242 (lr=2.3787e-05) (hash(x)=25148490) +4180 train 7.247074 (lr=2.3766e-05) (hash(x)=22792092) +4181 train 7.342461 (lr=2.3745e-05) (hash(x)=24779698) +4182 train 7.228518 (lr=2.3724e-05) (hash(x)=24870844) +4183 train 6.937751 (lr=2.3703e-05) (hash(x)=22664494) +4184 train 6.972665 (lr=2.3683e-05) (hash(x)=22599729) +4185 train 7.195410 (lr=2.3662e-05) (hash(x)=24707078) +4186 train 6.975173 (lr=2.3641e-05) (hash(x)=23823945) +4187 train 6.692846 (lr=2.3620e-05) (hash(x)=22219856) +4188 train 7.405575 (lr=2.3600e-05) (hash(x)=27061401) +4189 train 7.115677 (lr=2.3579e-05) (hash(x)=23398766) +4190 train 7.183506 (lr=2.3558e-05) (hash(x)=27916730) +4191 train 7.081659 (lr=2.3537e-05) (hash(x)=24092927) +4192 train 7.153078 (lr=2.3517e-05) (hash(x)=24723657) +4193 train 7.166796 (lr=2.3496e-05) (hash(x)=24676155) +4194 train 7.061884 (lr=2.3476e-05) (hash(x)=23455369) +4195 train 7.010982 (lr=2.3455e-05) (hash(x)=21999890) +4196 train 6.958189 (lr=2.3435e-05) (hash(x)=23385567) +4197 train 7.137905 (lr=2.3414e-05) (hash(x)=25120814) +4198 train 6.830400 (lr=2.3393e-05) (hash(x)=21308113) +4199 train 7.150747 (lr=2.3373e-05) (hash(x)=27213812) +4200 val loss 7.1696 +4200 val perplexity 1299.2814 +4200 train 6.704509 (lr=2.3353e-05) (hash(x)=19675382) +4201 train 7.009693 (lr=2.3332e-05) (hash(x)=23882161) +4202 train 6.976280 (lr=2.3312e-05) (hash(x)=24338567) +4203 train 7.284860 (lr=2.3291e-05) (hash(x)=27649723) +4204 train 7.093503 (lr=2.3271e-05) (hash(x)=27563514) +4205 train 7.106037 (lr=2.3251e-05) (hash(x)=23128552) +4206 train 6.996546 (lr=2.3230e-05) (hash(x)=26203283) +4207 train 7.048210 (lr=2.3210e-05) (hash(x)=23929955) +4208 train 6.735911 (lr=2.3190e-05) (hash(x)=20978691) +4209 train 7.036125 (lr=2.3170e-05) (hash(x)=21875178) +4210 train 7.089971 (lr=2.3149e-05) (hash(x)=23563293) +4211 train 7.243894 (lr=2.3129e-05) (hash(x)=25538503) +4212 train 7.280533 (lr=2.3109e-05) (hash(x)=24171014) +4213 train 7.106027 (lr=2.3089e-05) (hash(x)=22306665) +4214 train 7.063398 (lr=2.3069e-05) (hash(x)=26082318) +4215 train 6.860490 (lr=2.3049e-05) (hash(x)=23025790) +4216 train 6.895126 (lr=2.3029e-05) (hash(x)=21146597) +4217 train 7.287660 (lr=2.3008e-05) (hash(x)=27470230) +4218 train 7.028130 (lr=2.2988e-05) (hash(x)=22691005) +4219 train 6.823448 (lr=2.2968e-05) (hash(x)=21550313) +4220 train 6.933409 (lr=2.2948e-05) (hash(x)=20618443) +4221 train 7.000305 (lr=2.2928e-05) (hash(x)=25260787) +4222 train 7.104132 (lr=2.2909e-05) (hash(x)=25249873) +4223 train 6.714675 (lr=2.2889e-05) (hash(x)=20452272) +4224 train 6.998532 (lr=2.2869e-05) (hash(x)=25649764) +4225 train 6.908605 (lr=2.2849e-05) (hash(x)=19589460) +4226 train 7.287494 (lr=2.2829e-05) (hash(x)=26477595) +4227 train 7.457660 (lr=2.2809e-05) (hash(x)=27585442) +4228 train 7.287703 (lr=2.2789e-05) (hash(x)=25821343) +4229 train 7.201707 (lr=2.2770e-05) (hash(x)=24549919) +4230 train 7.094081 (lr=2.2750e-05) (hash(x)=26124522) +4231 train 7.402154 (lr=2.2730e-05) (hash(x)=26473464) +4232 train 7.417171 (lr=2.2711e-05) (hash(x)=28883028) +4233 train 7.334278 (lr=2.2691e-05) (hash(x)=29611296) +4234 train 7.223219 (lr=2.2671e-05) (hash(x)=29059941) +4235 train 7.084138 (lr=2.2652e-05) (hash(x)=26368203) +4236 train 7.111942 (lr=2.2632e-05) (hash(x)=27021360) +4237 train 7.062889 (lr=2.2612e-05) (hash(x)=26135379) +4238 train 6.835368 (lr=2.2593e-05) (hash(x)=25862549) +4239 train 7.252500 (lr=2.2573e-05) (hash(x)=28276603) +4240 train 6.844533 (lr=2.2554e-05) (hash(x)=22170090) +4241 train 7.162290 (lr=2.2534e-05) (hash(x)=22625589) +4242 train 7.212574 (lr=2.2515e-05) (hash(x)=25751475) +4243 train 7.076077 (lr=2.2495e-05) (hash(x)=25836838) +4244 train 7.003954 (lr=2.2476e-05) (hash(x)=23938214) +4245 train 6.948451 (lr=2.2457e-05) (hash(x)=22759365) +4246 train 6.927683 (lr=2.2437e-05) (hash(x)=24964628) +4247 train 6.654408 (lr=2.2418e-05) (hash(x)=21480367) +4248 train 7.230999 (lr=2.2399e-05) (hash(x)=25974694) +4249 train 7.553183 (lr=2.2379e-05) (hash(x)=29830546) +4250 val loss 7.1672 +4250 val perplexity 1296.2078 +4250 train 7.195104 (lr=2.2360e-05) (hash(x)=26283200) +4251 train 7.233574 (lr=2.2341e-05) (hash(x)=25605672) +4252 train 6.886880 (lr=2.2321e-05) (hash(x)=21439107) +4253 train 6.797742 (lr=2.2302e-05) (hash(x)=22626883) +4254 train 7.162091 (lr=2.2283e-05) (hash(x)=25627150) +4255 train 7.357545 (lr=2.2264e-05) (hash(x)=24658642) +4256 train 7.425202 (lr=2.2245e-05) (hash(x)=29755505) +4257 train 7.107974 (lr=2.2226e-05) (hash(x)=22750846) +4258 train 7.024393 (lr=2.2207e-05) (hash(x)=21892651) +4259 train 7.079056 (lr=2.2188e-05) (hash(x)=22487960) +4260 train 7.165419 (lr=2.2169e-05) (hash(x)=24059869) +4261 train 6.900398 (lr=2.2150e-05) (hash(x)=21090180) +4262 train 7.046241 (lr=2.2131e-05) (hash(x)=22716452) +4263 train 7.291382 (lr=2.2112e-05) (hash(x)=26854801) +4264 train 7.067077 (lr=2.2093e-05) (hash(x)=23815428) +4265 train 6.923657 (lr=2.2074e-05) (hash(x)=23368704) +4266 train 6.992131 (lr=2.2055e-05) (hash(x)=24301098) +4267 train 7.195708 (lr=2.2036e-05) (hash(x)=25025039) +4268 train 6.938857 (lr=2.2017e-05) (hash(x)=25425736) +4269 train 7.171590 (lr=2.1998e-05) (hash(x)=27439380) +4270 train 6.638483 (lr=2.1979e-05) (hash(x)=18682756) +4271 train 6.774171 (lr=2.1961e-05) (hash(x)=17862226) +4272 train 7.362292 (lr=2.1942e-05) (hash(x)=29946491) +4273 train 6.568388 (lr=2.1923e-05) (hash(x)=21392062) +4274 train 7.176038 (lr=2.1905e-05) (hash(x)=25195556) +4275 train 7.143051 (lr=2.1886e-05) (hash(x)=26682036) +4276 train 7.074763 (lr=2.1867e-05) (hash(x)=21235260) +4277 train 6.863950 (lr=2.1849e-05) (hash(x)=22118984) +4278 train 6.911652 (lr=2.1830e-05) (hash(x)=24094510) +4279 train 7.423871 (lr=2.1811e-05) (hash(x)=28519182) +4280 train 7.085103 (lr=2.1793e-05) (hash(x)=26652859) +4281 train 7.014308 (lr=2.1774e-05) (hash(x)=24463139) +4282 train 6.985605 (lr=2.1756e-05) (hash(x)=23281870) +4283 train 7.226392 (lr=2.1737e-05) (hash(x)=29181174) +4284 train 6.899539 (lr=2.1719e-05) (hash(x)=24797417) +4285 train 7.226222 (lr=2.1700e-05) (hash(x)=29026537) +4286 train 7.056365 (lr=2.1682e-05) (hash(x)=23045165) +4287 train 6.966676 (lr=2.1664e-05) (hash(x)=25193694) +4288 train 7.015244 (lr=2.1645e-05) (hash(x)=23475407) +4289 train 7.136984 (lr=2.1627e-05) (hash(x)=24875410) +4290 train 7.032446 (lr=2.1609e-05) (hash(x)=26328101) +4291 train 7.315019 (lr=2.1590e-05) (hash(x)=26273661) +4292 train 7.054207 (lr=2.1572e-05) (hash(x)=23271891) +4293 train 7.010349 (lr=2.1554e-05) (hash(x)=23300732) +4294 train 7.119958 (lr=2.1536e-05) (hash(x)=24243693) +4295 train 7.184736 (lr=2.1517e-05) (hash(x)=25642620) +4296 train 7.226284 (lr=2.1499e-05) (hash(x)=27730411) +4297 train 6.986328 (lr=2.1481e-05) (hash(x)=25485335) +4298 train 6.861084 (lr=2.1463e-05) (hash(x)=25268789) +4299 train 7.318936 (lr=2.1445e-05) (hash(x)=28917143) +4300 val loss 7.1683 +4300 val perplexity 1297.6023 +4300 train 7.477037 (lr=2.1427e-05) (hash(x)=28987991) +4301 train 7.211293 (lr=2.1409e-05) (hash(x)=25989151) +4302 train 7.081890 (lr=2.1391e-05) (hash(x)=25658195) +4303 train 7.026028 (lr=2.1373e-05) (hash(x)=25765909) +4304 train 7.046479 (lr=2.1355e-05) (hash(x)=25704261) +4305 train 7.076176 (lr=2.1337e-05) (hash(x)=24438198) +4306 train 6.863586 (lr=2.1319e-05) (hash(x)=22871710) +4307 train 6.719722 (lr=2.1301e-05) (hash(x)=20160896) +4308 train 7.281378 (lr=2.1283e-05) (hash(x)=24218641) +4309 train 6.695310 (lr=2.1265e-05) (hash(x)=22073751) +4310 train 7.020996 (lr=2.1247e-05) (hash(x)=26434959) +4311 train 6.722913 (lr=2.1229e-05) (hash(x)=20750531) +4312 train 6.858577 (lr=2.1212e-05) (hash(x)=22232293) +4313 train 7.163472 (lr=2.1194e-05) (hash(x)=27324521) +4314 train 6.819960 (lr=2.1176e-05) (hash(x)=22217862) +4315 train 7.282056 (lr=2.1158e-05) (hash(x)=25741958) +4316 train 7.029678 (lr=2.1141e-05) (hash(x)=22738456) +4317 train 7.065561 (lr=2.1123e-05) (hash(x)=25387302) +4318 train 7.025993 (lr=2.1105e-05) (hash(x)=24669014) +4319 train 7.162360 (lr=2.1088e-05) (hash(x)=24917098) +4320 train 7.089649 (lr=2.1070e-05) (hash(x)=26698227) +4321 train 6.910553 (lr=2.1053e-05) (hash(x)=23518293) +4322 train 6.860309 (lr=2.1035e-05) (hash(x)=23643971) +4323 train 7.041081 (lr=2.1018e-05) (hash(x)=25659505) +4324 train 6.874152 (lr=2.1000e-05) (hash(x)=22697720) +4325 train 7.337646 (lr=2.0983e-05) (hash(x)=25082178) +4326 train 6.879827 (lr=2.0965e-05) (hash(x)=24166546) +4327 train 7.046835 (lr=2.0948e-05) (hash(x)=24499766) +4328 train 7.176403 (lr=2.0930e-05) (hash(x)=24338607) +4329 train 6.944205 (lr=2.0913e-05) (hash(x)=23225420) +4330 train 7.092618 (lr=2.0896e-05) (hash(x)=25907032) +4331 train 6.909181 (lr=2.0878e-05) (hash(x)=24634979) +4332 train 6.978027 (lr=2.0861e-05) (hash(x)=22161377) +4333 train 7.131243 (lr=2.0844e-05) (hash(x)=22559939) +4334 train 6.903835 (lr=2.0826e-05) (hash(x)=20840022) +4335 train 7.219856 (lr=2.0809e-05) (hash(x)=25067358) +4336 train 6.869397 (lr=2.0792e-05) (hash(x)=23432626) +4337 train 7.018734 (lr=2.0775e-05) (hash(x)=23820385) +4338 train 7.842360 (lr=2.0758e-05) (hash(x)=31594930) +4339 train 7.271402 (lr=2.0741e-05) (hash(x)=27138750) +4340 train 7.465549 (lr=2.0723e-05) (hash(x)=30031341) +4341 train 6.989639 (lr=2.0706e-05) (hash(x)=24602807) +4342 train 6.779369 (lr=2.0689e-05) (hash(x)=21584976) +4343 train 7.201519 (lr=2.0672e-05) (hash(x)=27479796) +4344 train 6.859421 (lr=2.0655e-05) (hash(x)=22746241) +4345 train 7.064440 (lr=2.0638e-05) (hash(x)=19728452) +4346 train 6.833751 (lr=2.0621e-05) (hash(x)=24502020) +4347 train 7.322432 (lr=2.0604e-05) (hash(x)=28225954) +4348 train 6.942940 (lr=2.0588e-05) (hash(x)=23893447) +4349 train 7.269974 (lr=2.0571e-05) (hash(x)=25654586) +4350 val loss 7.1648 +4350 val perplexity 1293.0391 +4350 train 7.118086 (lr=2.0554e-05) (hash(x)=23856469) +4351 train 7.031055 (lr=2.0537e-05) (hash(x)=23136080) +4352 train 7.167697 (lr=2.0520e-05) (hash(x)=26532918) +4353 train 7.031671 (lr=2.0503e-05) (hash(x)=25461947) +4354 train 7.074826 (lr=2.0487e-05) (hash(x)=26590231) +4355 train 6.801560 (lr=2.0470e-05) (hash(x)=21441985) +4356 train 7.087326 (lr=2.0453e-05) (hash(x)=26507941) +4357 train 7.384537 (lr=2.0436e-05) (hash(x)=26245238) +4358 train 7.150574 (lr=2.0420e-05) (hash(x)=24879059) +4359 train 7.418729 (lr=2.0403e-05) (hash(x)=29810074) +4360 train 6.822673 (lr=2.0386e-05) (hash(x)=24258069) +4361 train 6.951407 (lr=2.0370e-05) (hash(x)=25229360) +4362 train 7.177245 (lr=2.0353e-05) (hash(x)=25440206) +4363 train 7.027861 (lr=2.0337e-05) (hash(x)=23222125) +4364 train 6.877622 (lr=2.0320e-05) (hash(x)=23353186) +4365 train 7.075859 (lr=2.0304e-05) (hash(x)=26995240) +4366 train 7.032789 (lr=2.0287e-05) (hash(x)=24135899) +4367 train 7.057426 (lr=2.0271e-05) (hash(x)=24765539) +4368 train 7.108964 (lr=2.0254e-05) (hash(x)=26051004) +4369 train 6.868657 (lr=2.0238e-05) (hash(x)=22559142) +4370 train 6.797432 (lr=2.0222e-05) (hash(x)=20364388) +4371 train 7.235406 (lr=2.0205e-05) (hash(x)=25938817) +4372 train 7.291016 (lr=2.0189e-05) (hash(x)=26060945) +4373 train 7.190941 (lr=2.0173e-05) (hash(x)=27866714) +4374 train 7.118966 (lr=2.0156e-05) (hash(x)=27104972) +4375 train 6.827370 (lr=2.0140e-05) (hash(x)=22216309) +4376 train 6.889698 (lr=2.0124e-05) (hash(x)=20781533) +4377 train 6.742889 (lr=2.0108e-05) (hash(x)=18784350) +4378 train 6.915769 (lr=2.0092e-05) (hash(x)=21102897) +4379 train 7.185179 (lr=2.0075e-05) (hash(x)=25647489) +4380 train 6.983955 (lr=2.0059e-05) (hash(x)=24486462) +4381 train 7.230159 (lr=2.0043e-05) (hash(x)=26539114) +4382 train 6.859924 (lr=2.0027e-05) (hash(x)=20026045) +4383 train 7.158850 (lr=2.0011e-05) (hash(x)=20613861) +4384 train 6.903114 (lr=1.9995e-05) (hash(x)=20676237) +4385 train 7.089644 (lr=1.9979e-05) (hash(x)=24893163) +4386 train 6.622938 (lr=1.9963e-05) (hash(x)=17299395) +4387 train 6.814169 (lr=1.9947e-05) (hash(x)=19580191) +4388 train 6.991985 (lr=1.9931e-05) (hash(x)=25588218) +4389 train 7.144136 (lr=1.9915e-05) (hash(x)=26433063) +4390 train 7.211107 (lr=1.9899e-05) (hash(x)=24917693) +4391 train 6.888937 (lr=1.9884e-05) (hash(x)=23462447) +4392 train 7.109544 (lr=1.9868e-05) (hash(x)=27185416) +4393 train 7.188521 (lr=1.9852e-05) (hash(x)=24109010) +4394 train 6.977581 (lr=1.9836e-05) (hash(x)=21486000) +4395 train 6.873456 (lr=1.9820e-05) (hash(x)=22230006) +4396 train 7.284215 (lr=1.9805e-05) (hash(x)=26092311) +4397 train 7.025969 (lr=1.9789e-05) (hash(x)=24112426) +4398 train 6.873704 (lr=1.9773e-05) (hash(x)=21881373) +4399 train 7.009566 (lr=1.9758e-05) (hash(x)=26739455) +4400 val loss 7.1614 +4400 val perplexity 1288.7462 +4400 train 6.880902 (lr=1.9742e-05) (hash(x)=22873602) +4401 train 6.982751 (lr=1.9726e-05) (hash(x)=26748712) +4402 train 7.171482 (lr=1.9711e-05) (hash(x)=26306618) +4403 train 7.401235 (lr=1.9695e-05) (hash(x)=26898808) +4404 train 7.028697 (lr=1.9680e-05) (hash(x)=25067751) +4405 train 7.100374 (lr=1.9664e-05) (hash(x)=25397145) +4406 train 7.236710 (lr=1.9649e-05) (hash(x)=24796962) +4407 train 7.040543 (lr=1.9633e-05) (hash(x)=23222996) +4408 train 7.006868 (lr=1.9618e-05) (hash(x)=24820189) +4409 train 7.420264 (lr=1.9602e-05) (hash(x)=27669038) +4410 train 6.995810 (lr=1.9587e-05) (hash(x)=24283976) +4411 train 7.223017 (lr=1.9572e-05) (hash(x)=25018789) +4412 train 7.110780 (lr=1.9556e-05) (hash(x)=26247064) +4413 train 7.142931 (lr=1.9541e-05) (hash(x)=22942904) +4414 train 7.036479 (lr=1.9526e-05) (hash(x)=23918746) +4415 train 7.147846 (lr=1.9510e-05) (hash(x)=26489285) +4416 train 6.162386 (lr=1.9495e-05) (hash(x)=14942495) +4417 train 6.946712 (lr=1.9480e-05) (hash(x)=23908505) +4418 train 7.180884 (lr=1.9465e-05) (hash(x)=25854036) +4419 train 7.051872 (lr=1.9450e-05) (hash(x)=27522868) +4420 train 6.956583 (lr=1.9435e-05) (hash(x)=26549205) +4421 train 6.825468 (lr=1.9419e-05) (hash(x)=24565522) +4422 train 7.212209 (lr=1.9404e-05) (hash(x)=23919123) +4423 train 7.024395 (lr=1.9389e-05) (hash(x)=25185942) +4424 train 7.043636 (lr=1.9374e-05) (hash(x)=24818969) +4425 train 7.127683 (lr=1.9359e-05) (hash(x)=26750372) +4426 train 7.157799 (lr=1.9344e-05) (hash(x)=25621536) +4427 train 7.628268 (lr=1.9329e-05) (hash(x)=28037060) +4428 train 7.650609 (lr=1.9314e-05) (hash(x)=30829517) +4429 train 7.187113 (lr=1.9299e-05) (hash(x)=28728766) +4430 train 7.115633 (lr=1.9285e-05) (hash(x)=25936895) +4431 train 7.256312 (lr=1.9270e-05) (hash(x)=27476158) +4432 train 6.992488 (lr=1.9255e-05) (hash(x)=23297921) +4433 train 6.947576 (lr=1.9240e-05) (hash(x)=23201299) +4434 train 6.913972 (lr=1.9225e-05) (hash(x)=22681766) +4435 train 6.882470 (lr=1.9211e-05) (hash(x)=23217512) +4436 train 7.372540 (lr=1.9196e-05) (hash(x)=29322443) +4437 train 6.943785 (lr=1.9181e-05) (hash(x)=23502072) +4438 train 7.052258 (lr=1.9166e-05) (hash(x)=28873527) +4439 train 7.078513 (lr=1.9152e-05) (hash(x)=23653175) +4440 train 6.893796 (lr=1.9137e-05) (hash(x)=21635879) +4441 train 6.908565 (lr=1.9122e-05) (hash(x)=22201854) +4442 train 6.856467 (lr=1.9108e-05) (hash(x)=23101164) +4443 train 7.260155 (lr=1.9093e-05) (hash(x)=25475122) +4444 train 7.002493 (lr=1.9079e-05) (hash(x)=25124825) +4445 train 7.113441 (lr=1.9064e-05) (hash(x)=26883852) +4446 train 6.927162 (lr=1.9050e-05) (hash(x)=24731829) +4447 train 6.926187 (lr=1.9035e-05) (hash(x)=22405076) +4448 train 7.080373 (lr=1.9021e-05) (hash(x)=27633869) +4449 train 7.139981 (lr=1.9007e-05) (hash(x)=25162594) +4450 val loss 7.1587 +4450 val perplexity 1285.2463 +4450 train 7.134843 (lr=1.8992e-05) (hash(x)=26438149) +4451 train 7.160243 (lr=1.8978e-05) (hash(x)=26748800) +4452 train 6.884839 (lr=1.8963e-05) (hash(x)=22971620) +4453 train 7.027532 (lr=1.8949e-05) (hash(x)=25886430) +4454 train 6.809740 (lr=1.8935e-05) (hash(x)=21084137) +4455 train 6.984412 (lr=1.8921e-05) (hash(x)=25673545) +4456 train 7.669107 (lr=1.8906e-05) (hash(x)=29389002) +4457 train 6.749303 (lr=1.8892e-05) (hash(x)=21676076) +4458 train 6.804948 (lr=1.8878e-05) (hash(x)=22616647) +4459 train 7.204976 (lr=1.8864e-05) (hash(x)=22771197) +4460 train 7.133406 (lr=1.8850e-05) (hash(x)=26393514) +4461 train 7.368637 (lr=1.8836e-05) (hash(x)=24996433) +4462 train 7.000891 (lr=1.8821e-05) (hash(x)=19594028) +4463 train 7.145981 (lr=1.8807e-05) (hash(x)=22675428) +4464 train 7.135307 (lr=1.8793e-05) (hash(x)=26566551) +4465 train 7.148131 (lr=1.8779e-05) (hash(x)=22469290) +4466 train 7.637353 (lr=1.8765e-05) (hash(x)=29821654) +4467 train 7.144094 (lr=1.8751e-05) (hash(x)=26305388) +4468 train 6.941333 (lr=1.8738e-05) (hash(x)=21998506) +4469 train 7.408158 (lr=1.8724e-05) (hash(x)=23953315) +4470 train 7.026852 (lr=1.8710e-05) (hash(x)=23985456) +4471 train 7.404010 (lr=1.8696e-05) (hash(x)=28168456) +4472 train 7.079547 (lr=1.8682e-05) (hash(x)=25126411) +4473 train 6.902246 (lr=1.8668e-05) (hash(x)=24619336) +4474 train 7.077465 (lr=1.8654e-05) (hash(x)=24467798) +4475 train 7.966461 (lr=1.8641e-05) (hash(x)=31673254) +4476 train 7.713169 (lr=1.8627e-05) (hash(x)=29929610) +4477 train 7.453145 (lr=1.8613e-05) (hash(x)=29412572) +4478 train 7.592266 (lr=1.8600e-05) (hash(x)=31910006) +4479 train 7.231493 (lr=1.8586e-05) (hash(x)=26072586) +4480 train 7.177726 (lr=1.8572e-05) (hash(x)=25782825) +4481 train 7.007134 (lr=1.8559e-05) (hash(x)=21131363) +4482 train 7.122638 (lr=1.8545e-05) (hash(x)=25071223) +4483 train 7.740363 (lr=1.8532e-05) (hash(x)=32249577) +4484 train 6.981097 (lr=1.8518e-05) (hash(x)=24752808) +4485 train 7.021606 (lr=1.8505e-05) (hash(x)=24970539) +4486 train 6.913745 (lr=1.8491e-05) (hash(x)=24191005) +4487 train 7.145429 (lr=1.8478e-05) (hash(x)=24974331) +4488 train 7.317261 (lr=1.8464e-05) (hash(x)=27043409) +4489 train 6.771218 (lr=1.8451e-05) (hash(x)=11320385) +4490 train 6.753524 (lr=1.8437e-05) (hash(x)=11919565) +4491 train 6.807300 (lr=1.8424e-05) (hash(x)=10404694) +4492 train 6.853664 (lr=1.8411e-05) (hash(x)=12393159) +4493 train 6.752660 (lr=1.8397e-05) (hash(x)=11843609) +4494 train 6.805088 (lr=1.8384e-05) (hash(x)=12632729) +4495 train 7.022346 (lr=1.8371e-05) (hash(x)=21951984) +4496 train 7.687286 (lr=1.8358e-05) (hash(x)=19411544) +4497 train 7.641280 (lr=1.8344e-05) (hash(x)=21000228) +4498 train 7.226093 (lr=1.8331e-05) (hash(x)=26018207) +4499 train 7.256619 (lr=1.8318e-05) (hash(x)=24659058) +4500 val loss 7.1579 +4500 val perplexity 1284.2638 +4500 train 7.457157 (lr=1.8305e-05) (hash(x)=27919597) +4501 train 6.993834 (lr=1.8292e-05) (hash(x)=26232596) +4502 train 7.145412 (lr=1.8279e-05) (hash(x)=26248912) +4503 train 7.030590 (lr=1.8266e-05) (hash(x)=25403751) +4504 train 6.960179 (lr=1.8253e-05) (hash(x)=21096637) +4505 train 7.088039 (lr=1.8240e-05) (hash(x)=26560941) +4506 train 7.094340 (lr=1.8227e-05) (hash(x)=24942406) +4507 train 7.177507 (lr=1.8214e-05) (hash(x)=24405748) +4508 train 7.056602 (lr=1.8201e-05) (hash(x)=22975455) +4509 train 6.985047 (lr=1.8188e-05) (hash(x)=26358820) +4510 train 6.986255 (lr=1.8175e-05) (hash(x)=24211938) +4511 train 7.165533 (lr=1.8162e-05) (hash(x)=26396012) +4512 train 6.847263 (lr=1.8149e-05) (hash(x)=22534410) +4513 train 6.963048 (lr=1.8137e-05) (hash(x)=23855025) +4514 train 6.863487 (lr=1.8124e-05) (hash(x)=22722345) +4515 train 6.864418 (lr=1.8111e-05) (hash(x)=22779251) +4516 train 7.148614 (lr=1.8098e-05) (hash(x)=23973078) +4517 train 7.028572 (lr=1.8086e-05) (hash(x)=19886228) +4518 train 7.075897 (lr=1.8073e-05) (hash(x)=23849694) +4519 train 7.464502 (lr=1.8060e-05) (hash(x)=24827190) +4520 train 7.046892 (lr=1.8048e-05) (hash(x)=25111498) +4521 train 7.860925 (lr=1.8035e-05) (hash(x)=29752556) +4522 train 7.302381 (lr=1.8023e-05) (hash(x)=25606805) +4523 train 7.078566 (lr=1.8010e-05) (hash(x)=22209714) +4524 train 6.827477 (lr=1.7998e-05) (hash(x)=24991834) +4525 train 7.081726 (lr=1.7985e-05) (hash(x)=27808158) +4526 train 7.041051 (lr=1.7973e-05) (hash(x)=23041199) +4527 train 7.104582 (lr=1.7960e-05) (hash(x)=24847458) +4528 train 7.020482 (lr=1.7948e-05) (hash(x)=25091787) +4529 train 7.937320 (lr=1.7935e-05) (hash(x)=29745551) +4530 train 6.735490 (lr=1.7923e-05) (hash(x)=20447167) +4531 train 6.947362 (lr=1.7911e-05) (hash(x)=20720911) +4532 train 7.106813 (lr=1.7898e-05) (hash(x)=24803353) +4533 train 7.171192 (lr=1.7886e-05) (hash(x)=23780724) +4534 train 7.185510 (lr=1.7874e-05) (hash(x)=23423120) +4535 train 6.847997 (lr=1.7862e-05) (hash(x)=22159088) +4536 train 7.015409 (lr=1.7849e-05) (hash(x)=25820304) +4537 train 6.836727 (lr=1.7837e-05) (hash(x)=22813612) +4538 train 7.163303 (lr=1.7825e-05) (hash(x)=27827979) +4539 train 7.160118 (lr=1.7813e-05) (hash(x)=25737179) +4540 train 7.319159 (lr=1.7801e-05) (hash(x)=23401504) +4541 train 7.017844 (lr=1.7789e-05) (hash(x)=25071988) +4542 train 7.063054 (lr=1.7777e-05) (hash(x)=22844541) +4543 train 6.822109 (lr=1.7765e-05) (hash(x)=22140034) +4544 train 7.070803 (lr=1.7753e-05) (hash(x)=26522091) +4545 train 7.108680 (lr=1.7741e-05) (hash(x)=24099725) +4546 train 6.697919 (lr=1.7729e-05) (hash(x)=19127182) +4547 train 6.837524 (lr=1.7717e-05) (hash(x)=18992693) +4548 train 7.911419 (lr=1.7705e-05) (hash(x)=26723015) +4549 train 7.602773 (lr=1.7693e-05) (hash(x)=30389969) +4550 val loss 7.1576 +4550 val perplexity 1283.8413 +4550 train 6.947741 (lr=1.7681e-05) (hash(x)=24065654) +4551 train 6.717110 (lr=1.7669e-05) (hash(x)=19044797) +4552 train 7.197792 (lr=1.7658e-05) (hash(x)=24919665) +4553 train 7.217496 (lr=1.7646e-05) (hash(x)=22780968) +4554 train 6.939682 (lr=1.7634e-05) (hash(x)=24549699) +4555 train 6.868440 (lr=1.7622e-05) (hash(x)=21374811) +4556 train 6.982395 (lr=1.7611e-05) (hash(x)=25225950) +4557 train 7.110016 (lr=1.7599e-05) (hash(x)=25691882) +4558 train 7.010321 (lr=1.7587e-05) (hash(x)=24685235) +4559 train 6.829283 (lr=1.7576e-05) (hash(x)=23932794) +4560 train 7.415868 (lr=1.7564e-05) (hash(x)=28152043) +4561 train 6.926786 (lr=1.7553e-05) (hash(x)=23417051) +4562 train 6.992568 (lr=1.7541e-05) (hash(x)=26250211) +4563 train 7.229651 (lr=1.7530e-05) (hash(x)=25428813) +4564 train 7.390230 (lr=1.7518e-05) (hash(x)=27477379) +4565 train 7.153363 (lr=1.7507e-05) (hash(x)=23015212) +4566 train 6.900981 (lr=1.7495e-05) (hash(x)=22837608) +4567 train 6.979256 (lr=1.7484e-05) (hash(x)=25256890) +4568 train 6.903657 (lr=1.7472e-05) (hash(x)=22742827) +4569 train 7.311546 (lr=1.7461e-05) (hash(x)=30167922) +4570 train 6.995248 (lr=1.7450e-05) (hash(x)=24540265) +4571 train 7.298637 (lr=1.7438e-05) (hash(x)=26752941) +4572 train 7.129424 (lr=1.7427e-05) (hash(x)=25094026) +4573 train 7.803162 (lr=1.7416e-05) (hash(x)=28508785) +4574 train 7.216469 (lr=1.7405e-05) (hash(x)=26501871) +4575 train 6.995576 (lr=1.7393e-05) (hash(x)=24161711) +4576 train 6.914301 (lr=1.7382e-05) (hash(x)=24313695) +4577 train 7.355691 (lr=1.7371e-05) (hash(x)=28248933) +4578 train 7.515778 (lr=1.7360e-05) (hash(x)=28445722) +4579 train 7.112227 (lr=1.7349e-05) (hash(x)=24589015) +4580 train 7.288340 (lr=1.7338e-05) (hash(x)=26192193) +4581 train 6.924413 (lr=1.7327e-05) (hash(x)=25131316) +4582 train 6.997348 (lr=1.7316e-05) (hash(x)=26631504) +4583 train 6.854856 (lr=1.7305e-05) (hash(x)=22036817) +4584 train 7.480777 (lr=1.7294e-05) (hash(x)=28361254) +4585 train 7.106230 (lr=1.7283e-05) (hash(x)=24828340) +4586 train 6.773915 (lr=1.7272e-05) (hash(x)=24067304) +4587 train 6.585748 (lr=1.7261e-05) (hash(x)=20733289) +4588 train 6.494887 (lr=1.7250e-05) (hash(x)=19526622) +4589 train 6.895912 (lr=1.7239e-05) (hash(x)=22148688) +4590 train 7.088838 (lr=1.7228e-05) (hash(x)=24141800) +4591 train 7.145470 (lr=1.7217e-05) (hash(x)=26663208) +4592 train 6.810814 (lr=1.7207e-05) (hash(x)=22536305) +4593 train 7.050905 (lr=1.7196e-05) (hash(x)=23608185) +4594 train 6.949767 (lr=1.7185e-05) (hash(x)=23348495) +4595 train 7.121008 (lr=1.7175e-05) (hash(x)=25409759) +4596 train 7.075794 (lr=1.7164e-05) (hash(x)=25572131) +4597 train 7.080664 (lr=1.7153e-05) (hash(x)=21782039) +4598 train 7.025455 (lr=1.7143e-05) (hash(x)=24643923) +4599 train 6.996269 (lr=1.7132e-05) (hash(x)=24072213) +4600 val loss 7.1547 +4600 val perplexity 1280.1436 +4600 train 6.917192 (lr=1.7121e-05) (hash(x)=23925612) +4601 train 7.022594 (lr=1.7111e-05) (hash(x)=23315415) +4602 train 7.008983 (lr=1.7100e-05) (hash(x)=21793800) +4603 train 6.960045 (lr=1.7090e-05) (hash(x)=24921200) +4604 train 7.223483 (lr=1.7079e-05) (hash(x)=27226113) +4605 train 7.018493 (lr=1.7069e-05) (hash(x)=22920960) +4606 train 6.970392 (lr=1.7059e-05) (hash(x)=21947750) +4607 train 7.014398 (lr=1.7048e-05) (hash(x)=22766044) +4608 train 7.411907 (lr=1.7038e-05) (hash(x)=28237005) +4609 train 6.867423 (lr=1.7028e-05) (hash(x)=24922621) +4610 train 7.074614 (lr=1.7017e-05) (hash(x)=24899830) +4611 train 7.458705 (lr=1.7007e-05) (hash(x)=32920298) +4612 train 6.916310 (lr=1.6997e-05) (hash(x)=25083835) +4613 train 6.956140 (lr=1.6986e-05) (hash(x)=22863054) +4614 train 7.008005 (lr=1.6976e-05) (hash(x)=24841464) +4615 train 7.291978 (lr=1.6966e-05) (hash(x)=27871153) +4616 train 7.317009 (lr=1.6956e-05) (hash(x)=28025163) +4617 train 6.949304 (lr=1.6946e-05) (hash(x)=24659561) +4618 train 7.033348 (lr=1.6936e-05) (hash(x)=25067194) +4619 train 7.040268 (lr=1.6926e-05) (hash(x)=22731460) +4620 train 7.008626 (lr=1.6916e-05) (hash(x)=20445873) +4621 train 7.074684 (lr=1.6906e-05) (hash(x)=26033948) +4622 train 6.940498 (lr=1.6896e-05) (hash(x)=22473213) +4623 train 7.550528 (lr=1.6886e-05) (hash(x)=24037280) +4624 train 7.964511 (lr=1.6876e-05) (hash(x)=25624131) +4625 train 7.623319 (lr=1.6866e-05) (hash(x)=26799867) +4626 train 7.106345 (lr=1.6856e-05) (hash(x)=27187602) +4627 train 7.062068 (lr=1.6846e-05) (hash(x)=23277695) +4628 train 7.038815 (lr=1.6836e-05) (hash(x)=24748234) +4629 train 7.171838 (lr=1.6826e-05) (hash(x)=26103104) +4630 train 7.089733 (lr=1.6817e-05) (hash(x)=24327389) +4631 train 7.202801 (lr=1.6807e-05) (hash(x)=24121850) +4632 train 7.045621 (lr=1.6797e-05) (hash(x)=23714590) +4633 train 7.069959 (lr=1.6787e-05) (hash(x)=22379412) +4634 train 7.320655 (lr=1.6778e-05) (hash(x)=24454713) +4635 train 6.986774 (lr=1.6768e-05) (hash(x)=22966977) +4636 train 6.968631 (lr=1.6758e-05) (hash(x)=23764884) +4637 train 6.834045 (lr=1.6749e-05) (hash(x)=23827429) +4638 train 7.078335 (lr=1.6739e-05) (hash(x)=24088592) +4639 train 7.043361 (lr=1.6730e-05) (hash(x)=24380031) +4640 train 7.137447 (lr=1.6720e-05) (hash(x)=26065050) +4641 train 7.026443 (lr=1.6711e-05) (hash(x)=24442902) +4642 train 6.627811 (lr=1.6701e-05) (hash(x)=18548782) +4643 train 7.133444 (lr=1.6692e-05) (hash(x)=26957303) +4644 train 7.115097 (lr=1.6682e-05) (hash(x)=25032727) +4645 train 6.996892 (lr=1.6673e-05) (hash(x)=27224706) +4646 train 7.164384 (lr=1.6663e-05) (hash(x)=27508476) +4647 train 6.876116 (lr=1.6654e-05) (hash(x)=23055215) +4648 train 7.022653 (lr=1.6645e-05) (hash(x)=24496194) +4649 train 8.377996 (lr=1.6636e-05) (hash(x)=13982941) +4650 val loss 7.1538 +4650 val perplexity 1278.9727 +4650 train 7.539390 (lr=1.6626e-05) (hash(x)=16721547) +4651 train 7.019322 (lr=1.6617e-05) (hash(x)=22929154) +4652 train 6.963301 (lr=1.6608e-05) (hash(x)=23323994) +4653 train 7.296575 (lr=1.6599e-05) (hash(x)=24877951) +4654 train 7.145764 (lr=1.6589e-05) (hash(x)=24096183) +4655 train 6.983190 (lr=1.6580e-05) (hash(x)=25329724) +4656 train 6.955884 (lr=1.6571e-05) (hash(x)=23877337) +4657 train 6.588934 (lr=1.6562e-05) (hash(x)=20923083) +4658 train 6.912446 (lr=1.6553e-05) (hash(x)=23807996) +4659 train 6.996433 (lr=1.6544e-05) (hash(x)=24370475) +4660 train 7.395307 (lr=1.6535e-05) (hash(x)=28202255) +4661 train 7.116999 (lr=1.6526e-05) (hash(x)=26142119) +4662 train 6.893318 (lr=1.6517e-05) (hash(x)=21387743) +4663 train 7.041447 (lr=1.6508e-05) (hash(x)=25662408) +4664 train 7.062041 (lr=1.6499e-05) (hash(x)=23962815) +4665 train 7.021384 (lr=1.6490e-05) (hash(x)=23987677) +4666 train 7.283667 (lr=1.6482e-05) (hash(x)=26554284) +4667 train 7.359640 (lr=1.6473e-05) (hash(x)=25991817) +4668 train 7.043695 (lr=1.6464e-05) (hash(x)=24256966) +4669 train 6.827388 (lr=1.6455e-05) (hash(x)=22187158) +4670 train 7.115880 (lr=1.6446e-05) (hash(x)=26295320) +4671 train 7.140721 (lr=1.6438e-05) (hash(x)=26346814) +4672 train 7.385811 (lr=1.6429e-05) (hash(x)=26594196) +4673 train 7.156457 (lr=1.6420e-05) (hash(x)=24322101) +4674 train 7.239742 (lr=1.6412e-05) (hash(x)=27274566) +4675 train 7.072099 (lr=1.6403e-05) (hash(x)=24505725) +4676 train 7.231159 (lr=1.6394e-05) (hash(x)=26167371) +4677 train 7.347241 (lr=1.6386e-05) (hash(x)=28062311) +4678 train 7.074909 (lr=1.6377e-05) (hash(x)=23476009) +4679 train 7.158067 (lr=1.6369e-05) (hash(x)=25283256) +4680 train 6.868335 (lr=1.6360e-05) (hash(x)=22033246) +4681 train 6.907339 (lr=1.6352e-05) (hash(x)=22716214) +4682 train 7.066570 (lr=1.6343e-05) (hash(x)=25672672) +4683 train 6.906158 (lr=1.6335e-05) (hash(x)=22979072) +4684 train 7.138067 (lr=1.6327e-05) (hash(x)=27439204) +4685 train 7.061466 (lr=1.6318e-05) (hash(x)=24857737) +4686 train 7.327228 (lr=1.6310e-05) (hash(x)=29615897) +4687 train 6.915305 (lr=1.6302e-05) (hash(x)=24021771) +4688 train 7.051107 (lr=1.6293e-05) (hash(x)=27410807) +4689 train 6.859107 (lr=1.6285e-05) (hash(x)=22850411) +4690 train 7.130140 (lr=1.6277e-05) (hash(x)=24949696) +4691 train 6.943560 (lr=1.6269e-05) (hash(x)=22956381) +4692 train 7.429581 (lr=1.6261e-05) (hash(x)=28193458) +4693 train 6.960854 (lr=1.6252e-05) (hash(x)=25596844) +4694 train 6.961501 (lr=1.6244e-05) (hash(x)=22101377) +4695 train 6.864749 (lr=1.6236e-05) (hash(x)=23576840) +4696 train 6.862390 (lr=1.6228e-05) (hash(x)=21849758) +4697 train 7.054531 (lr=1.6220e-05) (hash(x)=26431349) +4698 train 7.146125 (lr=1.6212e-05) (hash(x)=22960758) +4699 train 7.011360 (lr=1.6204e-05) (hash(x)=23243097) +4700 val loss 7.1525 +4700 val perplexity 1277.3368 +4700 train 6.950771 (lr=1.6196e-05) (hash(x)=23715370) +4701 train 7.620113 (lr=1.6188e-05) (hash(x)=30678293) +4702 train 7.696607 (lr=1.6180e-05) (hash(x)=32481620) +4703 train 7.239861 (lr=1.6172e-05) (hash(x)=26414858) +4704 train 7.097538 (lr=1.6164e-05) (hash(x)=24768691) +4705 train 6.772140 (lr=1.6157e-05) (hash(x)=21627762) +4706 train 6.884870 (lr=1.6149e-05) (hash(x)=21024917) +4707 train 6.819242 (lr=1.6141e-05) (hash(x)=23570951) +4708 train 6.964299 (lr=1.6133e-05) (hash(x)=23729185) +4709 train 7.273604 (lr=1.6126e-05) (hash(x)=25933754) +4710 train 6.800377 (lr=1.6118e-05) (hash(x)=23091014) +4711 train 6.871162 (lr=1.6110e-05) (hash(x)=20099261) +4712 train 7.022737 (lr=1.6103e-05) (hash(x)=26807297) +4713 train 6.921613 (lr=1.6095e-05) (hash(x)=25332115) +4714 train 6.926069 (lr=1.6087e-05) (hash(x)=23247605) +4715 train 6.788447 (lr=1.6080e-05) (hash(x)=23786549) +4716 train 6.891989 (lr=1.6072e-05) (hash(x)=23981166) +4717 train 7.055380 (lr=1.6065e-05) (hash(x)=25967754) +4718 train 6.942700 (lr=1.6057e-05) (hash(x)=23659116) +4719 train 6.957038 (lr=1.6050e-05) (hash(x)=22453718) +4720 train 6.911649 (lr=1.6042e-05) (hash(x)=22597951) +4721 train 7.124124 (lr=1.6035e-05) (hash(x)=25284885) +4722 train 7.119394 (lr=1.6028e-05) (hash(x)=24748569) +4723 train 6.713706 (lr=1.6020e-05) (hash(x)=19448608) +4724 train 7.053268 (lr=1.6013e-05) (hash(x)=24888040) +4725 train 6.905855 (lr=1.6006e-05) (hash(x)=23203503) +4726 train 6.660295 (lr=1.5998e-05) (hash(x)=20387787) +4727 train 6.752945 (lr=1.5991e-05) (hash(x)=22529445) +4728 train 7.059082 (lr=1.5984e-05) (hash(x)=22455471) +4729 train 7.055818 (lr=1.5977e-05) (hash(x)=25661132) +4730 train 7.054470 (lr=1.5969e-05) (hash(x)=24997711) +4731 train 7.171024 (lr=1.5962e-05) (hash(x)=22575521) +4732 train 6.918880 (lr=1.5955e-05) (hash(x)=22640285) +4733 train 6.791177 (lr=1.5948e-05) (hash(x)=18637357) +4734 train 6.924394 (lr=1.5941e-05) (hash(x)=22845826) +4735 train 7.120365 (lr=1.5934e-05) (hash(x)=24484543) +4736 train 6.961635 (lr=1.5927e-05) (hash(x)=23352320) +4737 train 6.782726 (lr=1.5920e-05) (hash(x)=21544758) +4738 train 6.587580 (lr=1.5913e-05) (hash(x)=18292136) +4739 train 7.230881 (lr=1.5906e-05) (hash(x)=24893614) +4740 train 7.067332 (lr=1.5899e-05) (hash(x)=28103443) +4741 train 6.897533 (lr=1.5892e-05) (hash(x)=22233356) +4742 train 6.757030 (lr=1.5885e-05) (hash(x)=21133541) +4743 train 7.036997 (lr=1.5878e-05) (hash(x)=24043998) +4744 train 7.324780 (lr=1.5872e-05) (hash(x)=24801185) +4745 train 7.089201 (lr=1.5865e-05) (hash(x)=23858358) +4746 train 7.127160 (lr=1.5858e-05) (hash(x)=23926989) +4747 train 7.193825 (lr=1.5851e-05) (hash(x)=24813708) +4748 train 6.994925 (lr=1.5845e-05) (hash(x)=26339467) +4749 train 6.867517 (lr=1.5838e-05) (hash(x)=21850656) +4750 val loss 7.1550 +4750 val perplexity 1280.4823 +4750 train 6.849538 (lr=1.5831e-05) (hash(x)=21475802) +4751 train 7.048189 (lr=1.5825e-05) (hash(x)=24301906) +4752 train 6.855768 (lr=1.5818e-05) (hash(x)=22748495) +4753 train 7.013252 (lr=1.5812e-05) (hash(x)=25649256) +4754 train 6.956213 (lr=1.5805e-05) (hash(x)=23934346) +4755 train 7.043285 (lr=1.5799e-05) (hash(x)=26332892) +4756 train 6.921422 (lr=1.5792e-05) (hash(x)=23279389) +4757 train 7.003882 (lr=1.5786e-05) (hash(x)=23146858) +4758 train 7.364214 (lr=1.5779e-05) (hash(x)=26892932) +4759 train 6.851758 (lr=1.5773e-05) (hash(x)=26328881) +4760 train 6.966873 (lr=1.5766e-05) (hash(x)=24394655) +4761 train 6.945218 (lr=1.5760e-05) (hash(x)=22122308) +4762 train 7.109081 (lr=1.5754e-05) (hash(x)=24200369) +4763 train 7.215741 (lr=1.5747e-05) (hash(x)=26841776) +4764 train 7.168011 (lr=1.5741e-05) (hash(x)=27196641) +4765 train 6.939973 (lr=1.5735e-05) (hash(x)=24912822) +4766 train 7.196829 (lr=1.5729e-05) (hash(x)=25946055) +4767 train 6.769836 (lr=1.5722e-05) (hash(x)=23101508) +4768 train 6.973957 (lr=1.5716e-05) (hash(x)=24287798) +4769 train 7.046829 (lr=1.5710e-05) (hash(x)=22798964) +4770 train 6.952766 (lr=1.5704e-05) (hash(x)=24164479) +4771 train 7.018842 (lr=1.5698e-05) (hash(x)=24946464) +4772 train 7.153818 (lr=1.5692e-05) (hash(x)=25154423) +4773 train 6.865555 (lr=1.5686e-05) (hash(x)=23173476) +4774 train 7.089293 (lr=1.5680e-05) (hash(x)=25373559) +4775 train 7.073082 (lr=1.5674e-05) (hash(x)=23527176) +4776 train 7.044137 (lr=1.5668e-05) (hash(x)=24865403) +4777 train 6.983769 (lr=1.5662e-05) (hash(x)=24451067) +4778 train 7.646442 (lr=1.5656e-05) (hash(x)=28187162) +4779 train 7.818193 (lr=1.5650e-05) (hash(x)=31163350) +4780 train 8.125758 (lr=1.5644e-05) (hash(x)=33563280) +4781 train 8.188759 (lr=1.5638e-05) (hash(x)=34939183) +4782 train 7.687144 (lr=1.5632e-05) (hash(x)=30263543) +4783 train 6.946937 (lr=1.5627e-05) (hash(x)=22705673) +4784 train 6.826450 (lr=1.5621e-05) (hash(x)=21415023) +4785 train 7.042651 (lr=1.5615e-05) (hash(x)=26079097) +4786 train 7.386569 (lr=1.5610e-05) (hash(x)=25503836) +4787 train 7.206938 (lr=1.5604e-05) (hash(x)=24705721) +4788 train 7.089867 (lr=1.5598e-05) (hash(x)=24384657) +4789 train 6.986659 (lr=1.5593e-05) (hash(x)=22550579) +4790 train 7.055176 (lr=1.5587e-05) (hash(x)=22452164) +4791 train 7.328568 (lr=1.5581e-05) (hash(x)=28664796) +4792 train 7.681587 (lr=1.5576e-05) (hash(x)=26139280) +4793 train 7.352870 (lr=1.5570e-05) (hash(x)=23862341) +4794 train 6.939147 (lr=1.5565e-05) (hash(x)=23784757) +4795 train 6.785106 (lr=1.5559e-05) (hash(x)=22659441) +4796 train 7.546722 (lr=1.5554e-05) (hash(x)=29744216) +4797 train 7.434619 (lr=1.5549e-05) (hash(x)=25822591) +4798 train 6.875524 (lr=1.5543e-05) (hash(x)=22370895) +4799 train 7.299476 (lr=1.5538e-05) (hash(x)=27102890) +4800 val loss 7.1593 +4800 val perplexity 1285.9955 +4800 train 7.333095 (lr=1.5532e-05) (hash(x)=27014625) +4801 train 7.090857 (lr=1.5527e-05) (hash(x)=25755963) +4802 train 7.319258 (lr=1.5522e-05) (hash(x)=29675278) +4803 train 7.425461 (lr=1.5517e-05) (hash(x)=26660930) +4804 train 7.345389 (lr=1.5511e-05) (hash(x)=24557060) +4805 train 7.495239 (lr=1.5506e-05) (hash(x)=24622741) +4806 train 7.544376 (lr=1.5501e-05) (hash(x)=23952601) +4807 train 7.169649 (lr=1.5496e-05) (hash(x)=26787259) +4808 train 7.429657 (lr=1.5491e-05) (hash(x)=28919605) +4809 train 7.783916 (lr=1.5486e-05) (hash(x)=37061654) +4810 train 7.515653 (lr=1.5481e-05) (hash(x)=30379739) +4811 train 7.274315 (lr=1.5476e-05) (hash(x)=26097180) +4812 train 7.441213 (lr=1.5471e-05) (hash(x)=26327092) +4813 train 7.206170 (lr=1.5466e-05) (hash(x)=23258030) +4814 train 7.265543 (lr=1.5461e-05) (hash(x)=25582015) +4815 train 6.958454 (lr=1.5456e-05) (hash(x)=23396088) +4816 train 6.949403 (lr=1.5451e-05) (hash(x)=21904146) +4817 train 7.162979 (lr=1.5446e-05) (hash(x)=26281676) +4818 train 6.918631 (lr=1.5441e-05) (hash(x)=23140470) +4819 train 7.226729 (lr=1.5436e-05) (hash(x)=24611098) +4820 train 7.013921 (lr=1.5431e-05) (hash(x)=23832642) +4821 train 7.256905 (lr=1.5427e-05) (hash(x)=21439671) +4822 train 7.065341 (lr=1.5422e-05) (hash(x)=25128845) +4823 train 6.984193 (lr=1.5417e-05) (hash(x)=24911831) +4824 train 7.157264 (lr=1.5412e-05) (hash(x)=26051723) +4825 train 7.206544 (lr=1.5408e-05) (hash(x)=26479565) +4826 train 7.297212 (lr=1.5403e-05) (hash(x)=26228987) +4827 train 7.183795 (lr=1.5399e-05) (hash(x)=25131300) +4828 train 6.908455 (lr=1.5394e-05) (hash(x)=19921978) +4829 train 6.895180 (lr=1.5389e-05) (hash(x)=23173449) +4830 train 7.221280 (lr=1.5385e-05) (hash(x)=24791832) +4831 train 6.953769 (lr=1.5380e-05) (hash(x)=23453491) +4832 train 7.180432 (lr=1.5376e-05) (hash(x)=22564139) +4833 train 6.960370 (lr=1.5371e-05) (hash(x)=21659918) +4834 train 7.061254 (lr=1.5367e-05) (hash(x)=22956076) +4835 train 7.171252 (lr=1.5363e-05) (hash(x)=22237612) +4836 train 7.258760 (lr=1.5358e-05) (hash(x)=24736427) +4837 train 7.359224 (lr=1.5354e-05) (hash(x)=24939751) +4838 train 7.202990 (lr=1.5350e-05) (hash(x)=25059298) +4839 train 7.125873 (lr=1.5345e-05) (hash(x)=23453396) +4840 train 6.652740 (lr=1.5341e-05) (hash(x)=17919338) +4841 train 7.117795 (lr=1.5337e-05) (hash(x)=23428815) +4842 train 7.425290 (lr=1.5332e-05) (hash(x)=27042659) +4843 train 7.476279 (lr=1.5328e-05) (hash(x)=25161278) +4844 train 7.263626 (lr=1.5324e-05) (hash(x)=24113253) +4845 train 7.385369 (lr=1.5320e-05) (hash(x)=26139263) +4846 train 7.405374 (lr=1.5316e-05) (hash(x)=27787006) +4847 train 7.143064 (lr=1.5312e-05) (hash(x)=23869612) +4848 train 7.286560 (lr=1.5308e-05) (hash(x)=26092193) +4849 train 7.331741 (lr=1.5304e-05) (hash(x)=29351182) +4850 val loss 7.1465 +4850 val perplexity 1269.6315 +4850 train 7.462986 (lr=1.5300e-05) (hash(x)=28773463) +4851 train 7.410854 (lr=1.5296e-05) (hash(x)=28207741) +4852 train 6.947032 (lr=1.5292e-05) (hash(x)=23280878) +4853 train 7.395789 (lr=1.5288e-05) (hash(x)=26742336) +4854 train 7.191811 (lr=1.5284e-05) (hash(x)=23543321) +4855 train 7.564556 (lr=1.5280e-05) (hash(x)=26581590) +4856 train 7.017206 (lr=1.5276e-05) (hash(x)=22728668) +4857 train 6.835682 (lr=1.5272e-05) (hash(x)=19854534) +4858 train 7.263675 (lr=1.5269e-05) (hash(x)=26612813) +4859 train 7.391915 (lr=1.5265e-05) (hash(x)=25827863) +4860 train 7.089612 (lr=1.5261e-05) (hash(x)=24574997) +4861 train 7.265631 (lr=1.5257e-05) (hash(x)=26187830) +4862 train 7.203683 (lr=1.5254e-05) (hash(x)=25105823) +4863 train 7.266183 (lr=1.5250e-05) (hash(x)=28056342) +4864 train 7.140564 (lr=1.5246e-05) (hash(x)=21885801) +4865 train 7.329476 (lr=1.5243e-05) (hash(x)=25659043) +4866 train 7.288841 (lr=1.5239e-05) (hash(x)=23852824) +4867 train 7.098140 (lr=1.5236e-05) (hash(x)=23965470) +4868 train 7.123900 (lr=1.5232e-05) (hash(x)=25035012) +4869 train 7.308197 (lr=1.5229e-05) (hash(x)=26639165) +4870 train 7.287134 (lr=1.5225e-05) (hash(x)=29205362) +4871 train 7.154670 (lr=1.5222e-05) (hash(x)=25900866) +4872 train 7.190475 (lr=1.5218e-05) (hash(x)=25636242) +4873 train 7.262058 (lr=1.5215e-05) (hash(x)=25430698) +4874 train 7.238029 (lr=1.5212e-05) (hash(x)=27629981) +4875 train 7.231553 (lr=1.5208e-05) (hash(x)=27682625) +4876 train 7.451523 (lr=1.5205e-05) (hash(x)=27549409) +4877 train 7.160918 (lr=1.5202e-05) (hash(x)=24661627) +4878 train 7.245471 (lr=1.5198e-05) (hash(x)=25196542) +4879 train 7.137471 (lr=1.5195e-05) (hash(x)=24549177) +4880 train 7.106874 (lr=1.5192e-05) (hash(x)=23740600) +4881 train 6.998155 (lr=1.5189e-05) (hash(x)=21460850) +4882 train 7.245865 (lr=1.5186e-05) (hash(x)=27101400) +4883 train 7.288477 (lr=1.5182e-05) (hash(x)=24193076) +4884 train 7.168849 (lr=1.5179e-05) (hash(x)=24582947) +4885 train 7.147281 (lr=1.5176e-05) (hash(x)=25133839) +4886 train 7.142616 (lr=1.5173e-05) (hash(x)=24759454) +4887 train 7.207109 (lr=1.5170e-05) (hash(x)=28239583) +4888 train 7.458454 (lr=1.5167e-05) (hash(x)=29594489) +4889 train 7.149599 (lr=1.5164e-05) (hash(x)=23833431) +4890 train 7.114107 (lr=1.5161e-05) (hash(x)=23139411) +4891 train 7.075813 (lr=1.5158e-05) (hash(x)=20885864) +4892 train 7.478703 (lr=1.5155e-05) (hash(x)=26217418) +4893 train 7.232082 (lr=1.5153e-05) (hash(x)=27321870) +4894 train 6.753546 (lr=1.5150e-05) (hash(x)=19912955) +4895 train 7.062490 (lr=1.5147e-05) (hash(x)=23223554) +4896 train 7.251369 (lr=1.5144e-05) (hash(x)=25667219) +4897 train 7.500707 (lr=1.5141e-05) (hash(x)=28007972) +4898 train 7.287924 (lr=1.5139e-05) (hash(x)=27748764) +4899 train 7.235626 (lr=1.5136e-05) (hash(x)=27425770) +4900 val loss 7.1473 +4900 val perplexity 1270.7223 +4900 train 7.353484 (lr=1.5133e-05) (hash(x)=28394020) +4901 train 7.186605 (lr=1.5131e-05) (hash(x)=24080235) +4902 train 7.034716 (lr=1.5128e-05) (hash(x)=23309527) +4903 train 7.052913 (lr=1.5125e-05) (hash(x)=24793480) +4904 train 7.262078 (lr=1.5123e-05) (hash(x)=25344456) +4905 train 7.220873 (lr=1.5120e-05) (hash(x)=24590670) +4906 train 7.164018 (lr=1.5118e-05) (hash(x)=26937171) +4907 train 7.281262 (lr=1.5115e-05) (hash(x)=26949097) +4908 train 7.009207 (lr=1.5113e-05) (hash(x)=22443915) +4909 train 7.078905 (lr=1.5110e-05) (hash(x)=23814995) +4910 train 7.113313 (lr=1.5108e-05) (hash(x)=26135871) +4911 train 6.922306 (lr=1.5106e-05) (hash(x)=25415570) +4912 train 7.256129 (lr=1.5103e-05) (hash(x)=26756326) +4913 train 7.138366 (lr=1.5101e-05) (hash(x)=22920200) +4914 train 7.202264 (lr=1.5099e-05) (hash(x)=26710977) +4915 train 7.101732 (lr=1.5096e-05) (hash(x)=24985634) +4916 train 7.243789 (lr=1.5094e-05) (hash(x)=26004335) +4917 train 7.144754 (lr=1.5092e-05) (hash(x)=25637457) +4918 train 7.373023 (lr=1.5090e-05) (hash(x)=26645180) +4919 train 7.219783 (lr=1.5087e-05) (hash(x)=24425760) +4920 train 7.424703 (lr=1.5085e-05) (hash(x)=28223544) +4921 train 7.138636 (lr=1.5083e-05) (hash(x)=25538618) +4922 train 7.374347 (lr=1.5081e-05) (hash(x)=26984784) +4923 train 7.420235 (lr=1.5079e-05) (hash(x)=29154578) +4924 train 7.119960 (lr=1.5077e-05) (hash(x)=25308123) +4925 train 7.444327 (lr=1.5075e-05) (hash(x)=27939259) +4926 train 7.057456 (lr=1.5073e-05) (hash(x)=21984545) +4927 train 7.096368 (lr=1.5071e-05) (hash(x)=23707134) +4928 train 7.121770 (lr=1.5069e-05) (hash(x)=27201034) +4929 train 7.530694 (lr=1.5067e-05) (hash(x)=31623877) +4930 train 7.143537 (lr=1.5065e-05) (hash(x)=22162782) +4931 train 7.053335 (lr=1.5063e-05) (hash(x)=20049335) +4932 train 7.001155 (lr=1.5062e-05) (hash(x)=25594665) +4933 train 7.109651 (lr=1.5060e-05) (hash(x)=25265312) +4934 train 7.211789 (lr=1.5058e-05) (hash(x)=27094896) +4935 train 7.611850 (lr=1.5056e-05) (hash(x)=28321697) +4936 train 7.075624 (lr=1.5055e-05) (hash(x)=25006013) +4937 train 7.314662 (lr=1.5053e-05) (hash(x)=24596431) +4938 train 7.328802 (lr=1.5051e-05) (hash(x)=25150510) +4939 train 6.855742 (lr=1.5050e-05) (hash(x)=21497535) +4940 train 7.115044 (lr=1.5048e-05) (hash(x)=25094669) +4941 train 7.010792 (lr=1.5046e-05) (hash(x)=24024557) +4942 train 7.291573 (lr=1.5045e-05) (hash(x)=24370776) +4943 train 7.127013 (lr=1.5043e-05) (hash(x)=23434031) +4944 train 7.122495 (lr=1.5042e-05) (hash(x)=24383517) +4945 train 7.174882 (lr=1.5040e-05) (hash(x)=25858759) +4946 train 6.789160 (lr=1.5039e-05) (hash(x)=20409561) +4947 train 7.444299 (lr=1.5037e-05) (hash(x)=27469117) +4948 train 6.995589 (lr=1.5036e-05) (hash(x)=22086623) +4949 train 7.285863 (lr=1.5035e-05) (hash(x)=25759281) +4950 val loss 7.1398 +4950 val perplexity 1261.2189 +4950 train 7.178722 (lr=1.5033e-05) (hash(x)=27130117) +4951 train 7.069231 (lr=1.5032e-05) (hash(x)=27003481) +4952 train 7.395199 (lr=1.5031e-05) (hash(x)=26725937) +4953 train 7.116580 (lr=1.5029e-05) (hash(x)=22691119) +4954 train 7.236612 (lr=1.5028e-05) (hash(x)=17272898) +4955 train 7.017462 (lr=1.5027e-05) (hash(x)=17850370) +4956 train 7.021141 (lr=1.5026e-05) (hash(x)=18729639) +4957 train 7.216726 (lr=1.5025e-05) (hash(x)=25327160) +4958 train 7.332700 (lr=1.5024e-05) (hash(x)=28709044) +4959 train 6.923229 (lr=1.5022e-05) (hash(x)=22236893) +4960 train 6.874686 (lr=1.5021e-05) (hash(x)=21729251) +4961 train 7.004777 (lr=1.5020e-05) (hash(x)=23852346) +4962 train 7.201318 (lr=1.5019e-05) (hash(x)=23974368) +4963 train 7.119163 (lr=1.5018e-05) (hash(x)=25764691) +4964 train 7.513060 (lr=1.5017e-05) (hash(x)=28341865) +4965 train 7.024220 (lr=1.5016e-05) (hash(x)=23856238) +4966 train 7.250696 (lr=1.5015e-05) (hash(x)=24568904) +4967 train 7.129229 (lr=1.5015e-05) (hash(x)=26857458) +4968 train 7.023298 (lr=1.5014e-05) (hash(x)=20507972) +4969 train 7.221363 (lr=1.5013e-05) (hash(x)=23139455) +4970 train 7.026639 (lr=1.5012e-05) (hash(x)=24853703) +4971 train 7.099865 (lr=1.5011e-05) (hash(x)=25654849) +4972 train 6.926939 (lr=1.5010e-05) (hash(x)=22963710) +4973 train 7.316352 (lr=1.5010e-05) (hash(x)=25652110) +4974 train 7.253050 (lr=1.5009e-05) (hash(x)=24085957) +4975 train 7.452592 (lr=1.5008e-05) (hash(x)=26413122) +4976 train 7.596219 (lr=1.5008e-05) (hash(x)=26989387) +4977 train 7.258336 (lr=1.5007e-05) (hash(x)=22784033) +4978 train 7.623193 (lr=1.5006e-05) (hash(x)=26694945) +4979 train 7.556362 (lr=1.5006e-05) (hash(x)=24507726) +4980 train 7.611696 (lr=1.5005e-05) (hash(x)=26490335) +4981 train 7.532152 (lr=1.5005e-05) (hash(x)=25624751) +4982 train 7.489930 (lr=1.5004e-05) (hash(x)=27846204) +4983 train 7.352257 (lr=1.5004e-05) (hash(x)=27696537) +4984 train 7.234995 (lr=1.5003e-05) (hash(x)=28915842) +4985 train 7.299316 (lr=1.5003e-05) (hash(x)=28274576) +4986 train 7.333492 (lr=1.5003e-05) (hash(x)=28923892) +4987 train 6.932189 (lr=1.5002e-05) (hash(x)=21602520) +4988 train 6.890810 (lr=1.5002e-05) (hash(x)=21061011) +4989 train 7.349211 (lr=1.5002e-05) (hash(x)=28060542) +4990 train 7.154910 (lr=1.5001e-05) (hash(x)=24838134) +4991 train 7.113096 (lr=1.5001e-05) (hash(x)=21950234) +4992 train 7.373912 (lr=1.5001e-05) (hash(x)=27192740) +4993 train 7.326112 (lr=1.5001e-05) (hash(x)=26770105) +4994 train 7.024946 (lr=1.5000e-05) (hash(x)=23721261) +4995 train 7.082059 (lr=1.5000e-05) (hash(x)=26064895) +4996 train 7.274263 (lr=1.5000e-05) (hash(x)=25651075) +4997 train 7.094430 (lr=1.5000e-05) (hash(x)=25029447) +4998 train 7.278578 (lr=1.5000e-05) (hash(x)=26088225) +4999 val loss 7.1425 +4999 val perplexity 1264.6310 +4999 train 7.184783 (lr=1.5000e-05) (hash(x)=24051952) diff --git a/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/model_02500.pt b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/model_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..2968f6d4f0262f5cb07d5f47f57d9df895f2d472 --- /dev/null +++ b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/model_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeaff4c3f064596a7c6a31d30fa44da60d5ac37739f57a43d6108de1f75eadc8 +size 38587970 diff --git a/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/model_04999.pt b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/model_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..a17bf6ff5b38735cd9132777dd96b390befe38ad --- /dev/null +++ b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/model_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8be4ca39278c727a550dc8ff9a116d943b26bf4341af9d25029279f1c3411f5 +size 38587970 diff --git a/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/optimizer_02500.pt b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/optimizer_02500.pt new file mode 100644 index 0000000000000000000000000000000000000000..b8b8230b8bee78515d6eacb0f247c89d5b2556f0 --- /dev/null +++ b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/optimizer_02500.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af69e08de0bb417897064c645b7909aa1b4a744746f3fecb02ea1dfd4f39d25 +size 70895430 diff --git a/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/optimizer_04999.pt b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/optimizer_04999.pt new file mode 100644 index 0000000000000000000000000000000000000000..424dede90b51afddf229073f04d903dcbec77ed0 --- /dev/null +++ b/lr1.5e-4_total_batch_size5120_seq_len256_decay_lrtrue_attention_kindselective_warmup_steps1/optimizer_04999.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fa1a65c6f2c7be7e78ec31be717b793733e13696e46a0e10c30df7a09b8266d +size 70895430