Upload folder using huggingface_hub

CALF/PEMS03_sl96_pl192_gpt12/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e9523a29e41abdf6d4cfd48d79b51becbf0b1e0fe249664a00ceac7dff3333d
+size 1090570197

CALF/PEMS03_sl96_pl192_gpt12/log.txt

@@ -0,0 +1,23 @@
+>>>>>>>start training>>>>>>>>>>>>>>
+Namespace(is_training=1, model_id='PEMS03_96_192', model='CALF', data='PEMS03', features='M', target='OT', freq='h', checkpoints='/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/CALF/checkpoints/', seq_len=96, pred_len=192, d_model=768, d_ff=768, dropout=0.3, embed='timeF', num_workers=20, train_epochs=100, batch_size=512, patience=3, learning_rate=0.001, lradj='type1', task_loss='smooth_l1', feature_loss='smooth_l1', output_loss='smooth_l1', tmax=20, cos=1, r=8, lora_alpha=32, lora_dropout=0.1, word_embedding_path='/home/hk-project-p0022189/tum_yvc3016/junlong/qx/CALF/wte_pca_500.pt', task_w=1.0, feature_w=0.01, output_w=1.0, gpt_layers=12, test_metrics_path='/home/hk-project-p0022189/tum_yvc3016/junlong/qx/CALF/test_metrics_path/96_192.txt', multi=0, block_or_sublayer='no', load_path='/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/CALF/checkpoints/PEMS03_sl96_pl192_gpt12/log.txt')
+Epoch: 1 cost time: 1213.5586137771606Epoch: 1, Steps: 12627 | Train Loss: 0.2405325 Vali Loss: 0.4243636lr = 0.0009045095Validation loss decreased (inf --> 0.424364).  Saving model ...
+Epoch: 2 cost time: 1214.5051691532135Epoch: 2, Steps: 12627 | Train Loss: 0.1846573 Vali Loss: 0.4036770lr = 0.0006545120Validation loss decreased (0.424364 --> 0.403677).  Saving model ...
+Epoch: 3 cost time: 1216.8372721672058Epoch: 3, Steps: 12627 | Train Loss: 0.1736200 Vali Loss: 0.3934794lr = 0.0003454980Validation loss decreased (0.403677 --> 0.393479).  Saving model ...
+Epoch: 4 cost time: 1209.1885206699371Epoch: 4, Steps: 12627 | Train Loss: 0.1654215 Vali Loss: 0.3756141lr = 0.0000955005Validation loss decreased (0.393479 --> 0.375614).  Saving model ...
+Epoch: 5 cost time: 1221.2066152095795Epoch: 5, Steps: 12627 | Train Loss: 0.1578077 Vali Loss: 0.3667139lr = 0.0000000100Validation loss decreased (0.375614 --> 0.366714).  Saving model ...
+Epoch: 6 cost time: 1215.5747256278992Epoch: 6, Steps: 12627 | Train Loss: 0.1550683 Vali Loss: 0.3650614lr = 0.0000955005Validation loss decreased (0.366714 --> 0.365061).  Saving model ...
+Epoch: 7 cost time: 1222.5011975765228Epoch: 7, Steps: 12627 | Train Loss: 0.1548908 Vali Loss: 0.3642367lr = 0.0003454980Validation loss decreased (0.365061 --> 0.364237).  Saving model ...
+Epoch: 8 cost time: 1218.6213192939758Epoch: 8, Steps: 12627 | Train Loss: 0.1566171 Vali Loss: 0.3638320lr = 0.0006545120Validation loss decreased (0.364237 --> 0.363832).  Saving model ...
+Epoch: 9 cost time: 1217.3795993328094Epoch: 9, Steps: 12627 | Train Loss: 0.1578000 Vali Loss: 0.3680637lr = 0.0009045095EarlyStopping counter: 1 out of 3
+Epoch: 10 cost time: 1219.9044802188873Epoch: 10, Steps: 12627 | Train Loss: 0.1567791 Vali Loss: 0.3629943lr = 0.0010000000Validation loss decreased (0.363832 --> 0.362994).  Saving model ...
+Epoch: 11 cost time: 1219.7232382297516Epoch: 11, Steps: 12627 | Train Loss: 0.1545983 Vali Loss: 0.3605110lr = 0.0009045095Validation loss decreased (0.362994 --> 0.360511).  Saving model ...
+Epoch: 12 cost time: 1214.502541065216Epoch: 12, Steps: 12627 | Train Loss: 0.1509807 Vali Loss: 0.3564376lr = 0.0006545120Validation loss decreased (0.360511 --> 0.356438).  Saving model ...
+Epoch: 13 cost time: 1218.4142220020294Epoch: 13, Steps: 12627 | Train Loss: 0.1465258 Vali Loss: 0.3490480lr = 0.0003454980Validation loss decreased (0.356438 --> 0.349048).  Saving model ...
+Epoch: 14 cost time: 1216.8537709712982Epoch: 14, Steps: 12627 | Train Loss: 0.1419440 Vali Loss: 0.3439195lr = 0.0000955005Validation loss decreased (0.349048 --> 0.343919).  Saving model ...
+Epoch: 15 cost time: 1218.0101554393768Epoch: 15, Steps: 12627 | Train Loss: 0.1383972 Vali Loss: 0.3422484lr = 0.0000000100Validation loss decreased (0.343919 --> 0.342248).  Saving model ...
+Epoch: 16 cost time: 1222.7025911808014Epoch: 16, Steps: 12627 | Train Loss: 0.1374614 Vali Loss: 0.3408269lr = 0.0000955005Validation loss decreased (0.342248 --> 0.340827).  Saving model ...
+Epoch: 17 cost time: 1218.2776758670807Epoch: 17, Steps: 12627 | Train Loss: 0.1378242 Vali Loss: 0.3398700lr = 0.0003454980Validation loss decreased (0.340827 --> 0.339870).  Saving model ...
+Epoch: 18 cost time: 1214.6523876190186Epoch: 18, Steps: 12627 | Train Loss: 0.1396362 Vali Loss: 0.3457815lr = 0.0006545120EarlyStopping counter: 1 out of 3
+Epoch: 19 cost time: 1215.1394522190094Epoch: 19, Steps: 12627 | Train Loss: 0.1422571 Vali Loss: 0.3470419lr = 0.0009045095EarlyStopping counter: 2 out of 3
+Epoch: 20 cost time: 1215.5405178070068Epoch: 20, Steps: 12627 | Train Loss: 0.1439515 Vali Loss: 0.3507722lr = 0.0010000000EarlyStopping counter: 3 out of 3
+Early stopping>>>>>>>testing>>>>>>>>>>>>>>

CALF/PEMS03_sl96_pl336_gpt12/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fde94b09516373bbaf8b1651e40a6fe4c09d400e21a0dc5c6f5d8363931198e1
+size 1091013141

CALF/PEMS03_sl96_pl336_gpt12/log.txt

@@ -0,0 +1,22 @@
+>>>>>>>start training>>>>>>>>>>>>>>
+Namespace(is_training=1, model_id='PEMS03_96_336', model='CALF', data='PEMS03', features='M', target='OT', freq='h', checkpoints='/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/CALF/checkpoints/', seq_len=96, pred_len=336, d_model=768, d_ff=768, dropout=0.3, embed='timeF', num_workers=20, train_epochs=100, batch_size=512, patience=3, learning_rate=0.001, lradj='type1', task_loss='smooth_l1', feature_loss='smooth_l1', output_loss='smooth_l1', tmax=20, cos=1, r=8, lora_alpha=32, lora_dropout=0.1, word_embedding_path='/home/hk-project-p0022189/tum_yvc3016/junlong/qx/CALF/wte_pca_500.pt', task_w=1.0, feature_w=0.01, output_w=1.0, gpt_layers=12, test_metrics_path='/home/hk-project-p0022189/tum_yvc3016/junlong/qx/CALF/test_metrics_path/96_336.txt', multi=0, block_or_sublayer='no', load_path='/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/CALF/checkpoints/PEMS03_sl96_pl336_gpt12/log.txt')
+Epoch: 1 cost time: 1228.0863962173462Epoch: 1, Steps: 12526 | Train Loss: 0.1989904 Vali Loss: 0.3550510lr = 0.0009045095Validation loss decreased (inf --> 0.355051).  Saving model ...
+Epoch: 2 cost time: 1205.9942526817322Epoch: 2, Steps: 12526 | Train Loss: 0.1547784 Vali Loss: 0.3398961lr = 0.0006545120Validation loss decreased (0.355051 --> 0.339896).  Saving model ...
+Epoch: 3 cost time: 1219.171292066574Epoch: 3, Steps: 12526 | Train Loss: 0.1466388 Vali Loss: 0.3313598lr = 0.0003454980Validation loss decreased (0.339896 --> 0.331360).  Saving model ...
+Epoch: 4 cost time: 1218.2594282627106Epoch: 4, Steps: 12526 | Train Loss: 0.1410800 Vali Loss: 0.3234892lr = 0.0000955005Validation loss decreased (0.331360 --> 0.323489).  Saving model ...
+Epoch: 5 cost time: 1217.5273847579956Epoch: 5, Steps: 12526 | Train Loss: 0.1370407 Vali Loss: 0.3151883lr = 0.0000000100Validation loss decreased (0.323489 --> 0.315188).  Saving model ...
+Epoch: 6 cost time: 1220.6260316371918Epoch: 6, Steps: 12526 | Train Loss: 0.1349816 Vali Loss: 0.3143618lr = 0.0000955005Validation loss decreased (0.315188 --> 0.314362).  Saving model ...
+Epoch: 7 cost time: 1219.025268316269Epoch: 7, Steps: 12526 | Train Loss: 0.1350453 Vali Loss: 0.3129805lr = 0.0003454980Validation loss decreased (0.314362 --> 0.312980).  Saving model ...
+Epoch: 8 cost time: 1220.592013835907Epoch: 8, Steps: 12526 | Train Loss: 0.1358405 Vali Loss: 0.3148754lr = 0.0006545120EarlyStopping counter: 1 out of 3
+Epoch: 9 cost time: 1220.2405898571014Epoch: 9, Steps: 12526 | Train Loss: 0.1357594 Vali Loss: 0.3106849lr = 0.0009045095Validation loss decreased (0.312980 --> 0.310685).  Saving model ...
+Epoch: 10 cost time: 1222.7074172496796Epoch: 10, Steps: 12526 | Train Loss: 0.1350104 Vali Loss: 0.3121745lr = 0.0010000000EarlyStopping counter: 1 out of 3
+Epoch: 11 cost time: 1220.4871294498444Epoch: 11, Steps: 12526 | Train Loss: 0.1332038 Vali Loss: 0.3067603lr = 0.0009045095Validation loss decreased (0.310685 --> 0.306760).  Saving model ...
+Epoch: 12 cost time: 1214.7389903068542Epoch: 12, Steps: 12526 | Train Loss: 0.1303220 Vali Loss: 0.3014657lr = 0.0006545120Validation loss decreased (0.306760 --> 0.301466).  Saving model ...
+Epoch: 13 cost time: 1224.0501599311829Epoch: 13, Steps: 12526 | Train Loss: 0.1271204 Vali Loss: 0.2972590lr = 0.0003454980Validation loss decreased (0.301466 --> 0.297259).  Saving model ...
+Epoch: 14 cost time: 1222.7768981456757Epoch: 14, Steps: 12526 | Train Loss: 0.1238745 Vali Loss: 0.2942495lr = 0.0000955005Validation loss decreased (0.297259 --> 0.294249).  Saving model ...
+Epoch: 15 cost time: 1225.6895768642426Epoch: 15, Steps: 12526 | Train Loss: 0.1216603 Vali Loss: 0.2913513lr = 0.0000000100Validation loss decreased (0.294249 --> 0.291351).  Saving model ...
+Epoch: 16 cost time: 1216.2601499557495Epoch: 16, Steps: 12526 | Train Loss: 0.1207567 Vali Loss: 0.2911408lr = 0.0000955005Validation loss decreased (0.291351 --> 0.291141).  Saving model ...
+Epoch: 17 cost time: 1222.1440660953522Epoch: 17, Steps: 12526 | Train Loss: 0.1208047 Vali Loss: 0.2921268lr = 0.0003454980EarlyStopping counter: 1 out of 3
+Epoch: 18 cost time: 1219.8968963623047Epoch: 18, Steps: 12526 | Train Loss: 0.1223113 Vali Loss: 0.2934834lr = 0.0006545120EarlyStopping counter: 2 out of 3
+Epoch: 19 cost time: 1224.0830509662628Epoch: 19, Steps: 12526 | Train Loss: 0.1239117 Vali Loss: 0.2936475lr = 0.0009045095EarlyStopping counter: 3 out of 3
+Early stopping>>>>>>>testing>>>>>>>>>>>>>>

CALF/traffic_sl96_pl720_gpt12/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e051c17a4676999ab8d29b31fa984319dad9a4cdf81e53d8687c1348fe06754
+size 1092194325

CALF/traffic_sl96_pl720_gpt12/log.txt

@@ -0,0 +1,13 @@
+>>>>>>>start training>>>>>>>>>>>>>>
+Namespace(is_training=1, model_id='traffic_96_720', model='CALF', data='traffic', features='M', target='OT', freq='h', checkpoints='/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/CALF/checkpoints/', seq_len=96, pred_len=720, d_model=768, d_ff=768, dropout=0.3, embed='timeF', num_workers=20, train_epochs=100, batch_size=512, patience=3, learning_rate=0.001, lradj='type1', task_loss='smooth_l1', feature_loss='smooth_l1', output_loss='smooth_l1', tmax=20, cos=1, r=8, lora_alpha=32, lora_dropout=0.1, word_embedding_path='/home/hk-project-p0022189/tum_yvc3016/junlong/qx/CALF/wte_pca_500.pt', task_w=1.0, feature_w=0.01, output_w=1.0, gpt_layers=12, test_metrics_path='/home/hk-project-p0022189/tum_yvc3016/junlong/qx/CALF/test_metrics_path/96_720.txt', multi=0, block_or_sublayer='no', load_path='/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/CALF/checkpoints/traffic_sl96_pl720_gpt12/log.txt')
+Epoch: 1 cost time: 1706.1240828037262Epoch: 1, Steps: 19303 | Train Loss: 0.1389736 Vali Loss: 0.4617771lr = 0.0009045095Validation loss decreased (inf --> 0.461777).  Saving model ...
+Epoch: 2 cost time: 1691.999606847763Epoch: 2, Steps: 19303 | Train Loss: 0.1101452 Vali Loss: 0.4579828lr = 0.0006545120Validation loss decreased (0.461777 --> 0.457983).  Saving model ...
+Epoch: 3 cost time: 1694.3127541542053Epoch: 3, Steps: 19303 | Train Loss: 0.1069227 Vali Loss: 0.4562370lr = 0.0003454980Validation loss decreased (0.457983 --> 0.456237).  Saving model ...
+Epoch: 4 cost time: 1685.3278629779816Epoch: 4, Steps: 19303 | Train Loss: 0.1050713 Vali Loss: 0.4541570lr = 0.0000955005Validation loss decreased (0.456237 --> 0.454157).  Saving model ...
+Epoch: 5 cost time: 1705.2223370075226Epoch: 5, Steps: 19303 | Train Loss: 0.1038729 Vali Loss: 0.4523360lr = 0.0000000100Validation loss decreased (0.454157 --> 0.452336).  Saving model ...
+Epoch: 6 cost time: 1688.0082385540009Epoch: 6, Steps: 19303 | Train Loss: 0.1035937 Vali Loss: 0.4521805lr = 0.0000955005Validation loss decreased (0.452336 --> 0.452181).  Saving model ...
+Epoch: 7 cost time: 1696.0097732543945Epoch: 7, Steps: 19303 | Train Loss: 0.1033980 Vali Loss: 0.4520068lr = 0.0003454980Validation loss decreased (0.452181 --> 0.452007).  Saving model ...
+Epoch: 8 cost time: 1705.5962662696838Epoch: 8, Steps: 19303 | Train Loss: 0.1036567 Vali Loss: 0.4533293lr = 0.0006545120EarlyStopping counter: 1 out of 3
+Epoch: 9 cost time: 1708.6191654205322Epoch: 9, Steps: 19303 | Train Loss: 0.1039235 Vali Loss: 0.4534400lr = 0.0009045095EarlyStopping counter: 2 out of 3
+Epoch: 10 cost time: 1716.0039064884186Epoch: 10, Steps: 19303 | Train Loss: 0.1037365 Vali Loss: 0.4530395lr = 0.0010000000EarlyStopping counter: 3 out of 3
+Early stopping>>>>>>>testing>>>>>>>>>>>>>>

CALF/traffic_sl96_pl96_gpt12/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd53739b9377458f71a36d60e6d70a31f0d2566752372fc58c57b329bf9c9d2c
+size 1090274901

CALF/traffic_sl96_pl96_gpt12/log.txt

@@ -0,0 +1,12 @@
+>>>>>>>start training>>>>>>>>>>>>>>
+Namespace(is_training=1, model_id='traffic_96_96', model='CALF', data='traffic', features='M', target='OT', freq='h', checkpoints='/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/CALF/checkpoints/', seq_len=96, pred_len=96, d_model=768, d_ff=768, dropout=0.3, embed='timeF', num_workers=20, train_epochs=100, batch_size=512, patience=3, learning_rate=0.001, lradj='type1', task_loss='smooth_l1', feature_loss='smooth_l1', output_loss='smooth_l1', tmax=20, cos=1, r=8, lora_alpha=32, lora_dropout=0.1, word_embedding_path='/home/hk-project-p0022189/tum_yvc3016/junlong/qx/CALF/wte_pca_500.pt', task_w=1.0, feature_w=0.01, output_w=1.0, gpt_layers=12, test_metrics_path='/home/hk-project-p0022189/tum_yvc3016/junlong/qx/CALF/test_metrics_path/96_96.txt', multi=0, block_or_sublayer='no', load_path='/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/CALF/checkpoints/traffic_sl96_pl96_gpt12/log.txt')
+Epoch: 1 cost time: 1765.7570405006409Epoch: 1, Steps: 20353 | Train Loss: 0.1241191 Vali Loss: 0.4174732lr = 0.0009045095Validation loss decreased (inf --> 0.417473).  Saving model ...
+Epoch: 2 cost time: 1800.9101555347443Epoch: 2, Steps: 20353 | Train Loss: 0.0977185 Vali Loss: 0.4121245lr = 0.0006545120Validation loss decreased (0.417473 --> 0.412125).  Saving model ...
+Epoch: 3 cost time: 1806.9728829860687Epoch: 3, Steps: 20353 | Train Loss: 0.0939899 Vali Loss: 0.4083741lr = 0.0003454980Validation loss decreased (0.412125 --> 0.408374).  Saving model ...
+Epoch: 4 cost time: 1796.8674626350403Epoch: 4, Steps: 20353 | Train Loss: 0.0918263 Vali Loss: 0.4060673lr = 0.0000955005Validation loss decreased (0.408374 --> 0.406067).  Saving model ...
+Epoch: 5 cost time: 1797.072764635086Epoch: 5, Steps: 20353 | Train Loss: 0.0907320 Vali Loss: 0.4039504lr = 0.0000000100Validation loss decreased (0.406067 --> 0.403950).  Saving model ...
+Epoch: 6 cost time: 1812.847502231598Epoch: 6, Steps: 20353 | Train Loss: 0.0902542 Vali Loss: 0.4035453lr = 0.0000955005Validation loss decreased (0.403950 --> 0.403545).  Saving model ...
+Epoch: 7 cost time: 1838.9145092964172Epoch: 7, Steps: 20353 | Train Loss: 0.0903154 Vali Loss: 0.4039853lr = 0.0003454980EarlyStopping counter: 1 out of 3
+Epoch: 8 cost time: 1832.54545378685Epoch: 8, Steps: 20353 | Train Loss: 0.0908403 Vali Loss: 0.4056821lr = 0.0006545120EarlyStopping counter: 2 out of 3
+Epoch: 9 cost time: 1830.4206190109253Epoch: 9, Steps: 20353 | Train Loss: 0.0911053 Vali Loss: 0.4059569lr = 0.0009045095EarlyStopping counter: 3 out of 3
+Early stopping>>>>>>>testing>>>>>>>>>>>>>>

FSCA/ETTm2_96/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:859c5748206934aaac6e851a0cd0384d33944ff164848650735f68a05a8a85cb
+size 552849378

FSCA/Electricity_96/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbfef391437cc4efc56bfadebc64763f1d85404336e1744f4e07ba3dfe12a969
+size 553242594

FSCA/Solar_96/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c19ef293164bbcd336d7af250fef398a71cde93e7380189ba074fb4344d6fb1
+size 553242594

FSCA/weather_96/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a69d95cea6110fb596ac710742e01f219cb8e20d22678e3f70e3823e59a1be6
+size 553242594

OFA/PEMS04_336/checkpoint-65624/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221dba394b4fab3926f62dd85f226fbeab914ffb70e9a93524aa149c89cbdd80
+size 270628842

OFA/PEMS04_336/checkpoint-65624/trainer_state.json

@@ -0,0 +1,1142 @@
+{
+  "best_global_step": 65624,
+  "best_metric": 0.4831537902355194,
+  "best_model_checkpoint": "/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/OFA_layer/haspara/336/PEMS04/checkpoint-65624",
+  "epoch": 13.0,
+  "eval_steps": 500,
+  "global_step": 65624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09904912836767037,
+      "grad_norm": 0.06085604056715965,
+      "learning_rate": 0.0009999803182724851,
+      "loss": 0.6841,
+      "step": 500
+    },
+    {
+      "epoch": 0.19809825673534073,
+      "grad_norm": 0.11020142585039139,
+      "learning_rate": 0.0009999211167982776,
+      "loss": 0.466,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2971473851030111,
+      "grad_norm": 0.2978723347187042,
+      "learning_rate": 0.0009998224001777822,
+      "loss": 0.4559,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39619651347068147,
+      "grad_norm": 0.13569457828998566,
+      "learning_rate": 0.0009996841762138337,
+      "loss": 0.4501,
+      "step": 2000
+    },
+    {
+      "epoch": 0.49524564183835185,
+      "grad_norm": 0.11234386265277863,
+      "learning_rate": 0.0009995064558320358,
+      "loss": 0.4456,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5942947702060222,
+      "grad_norm": 0.23295480012893677,
+      "learning_rate": 0.0009992892530798984,
+      "loss": 0.4427,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6933438985736925,
+      "grad_norm": 0.07768674939870834,
+      "learning_rate": 0.0009990325851257273,
+      "loss": 0.4412,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7923930269413629,
+      "grad_norm": 0.13024824857711792,
+      "learning_rate": 0.000998736472257267,
+      "loss": 0.4392,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8914421553090333,
+      "grad_norm": 0.21133571863174438,
+      "learning_rate": 0.0009984009378800963,
+      "loss": 0.438,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9904912836767037,
+      "grad_norm": 0.3099469542503357,
+      "learning_rate": 0.0009980260085157794,
+      "loss": 0.4366,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0,
+      "eval_MAE": 0.3764905631542206,
+      "eval_MAPE": 349.27911376953125,
+      "eval_MSE": 0.5023903846740723,
+      "eval_MSPE": 154474.234375,
+      "eval_ND": 0.4538463056087494,
+      "eval_RMSE": 0.7087950110435486,
+      "eval_SMAPE": 61.74858474731445,
+      "eval_runtime": 67.2343,
+      "eval_samples_per_second": 18698.269,
+      "eval_steps_per_second": 9.132,
+      "step": 5048
+    },
+    {
+      "epoch": 1.089540412044374,
+      "grad_norm": 0.167328879237175,
+      "learning_rate": 0.0009976117137997695,
+      "loss": 0.4365,
+      "step": 5500
+    },
+    {
+      "epoch": 1.1885895404120443,
+      "grad_norm": 0.15923786163330078,
+      "learning_rate": 0.0009971580864790652,
+      "loss": 0.4335,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2876386687797148,
+      "grad_norm": 0.23647330701351166,
+      "learning_rate": 0.0009966651624096236,
+      "loss": 0.433,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3866877971473852,
+      "grad_norm": 0.08678620308637619,
+      "learning_rate": 0.0009961329805535251,
+      "loss": 0.4323,
+      "step": 7000
+    },
+    {
+      "epoch": 1.4857369255150554,
+      "grad_norm": 0.10297006368637085,
+      "learning_rate": 0.0009955615829758935,
+      "loss": 0.4327,
+      "step": 7500
+    },
+    {
+      "epoch": 1.5847860538827259,
+      "grad_norm": 0.12103519588708878,
+      "learning_rate": 0.0009949510148415722,
+      "loss": 0.4312,
+      "step": 8000
+    },
+    {
+      "epoch": 1.6838351822503963,
+      "grad_norm": 0.1411912441253662,
+      "learning_rate": 0.0009943013244115538,
+      "loss": 0.4317,
+      "step": 8500
+    },
+    {
+      "epoch": 1.7828843106180665,
+      "grad_norm": 0.16333575546741486,
+      "learning_rate": 0.0009936125630391644,
+      "loss": 0.4306,
+      "step": 9000
+    },
+    {
+      "epoch": 1.881933438985737,
+      "grad_norm": 0.25319305062294006,
+      "learning_rate": 0.000992884785166006,
+      "loss": 0.428,
+      "step": 9500
+    },
+    {
+      "epoch": 1.9809825673534074,
+      "grad_norm": 0.08323787152767181,
+      "learning_rate": 0.0009921180483176526,
+      "loss": 0.4294,
+      "step": 10000
+    },
+    {
+      "epoch": 2.0,
+      "eval_MAE": 0.37166666984558105,
+      "eval_MAPE": 348.12994384765625,
+      "eval_MSE": 0.49643462896347046,
+      "eval_MSPE": 161231.390625,
+      "eval_ND": 0.4480312764644623,
+      "eval_RMSE": 0.7045812010765076,
+      "eval_SMAPE": 61.25733947753906,
+      "eval_runtime": 54.411,
+      "eval_samples_per_second": 23104.958,
+      "eval_steps_per_second": 11.284,
+      "step": 10096
+    },
+    {
+      "epoch": 2.0800316957210776,
+      "grad_norm": 0.07184210419654846,
+      "learning_rate": 0.000991312413099103,
+      "loss": 0.4284,
+      "step": 10500
+    },
+    {
+      "epoch": 2.179080824088748,
+      "grad_norm": 0.3041013479232788,
+      "learning_rate": 0.0009904679431899906,
+      "loss": 0.4279,
+      "step": 11000
+    },
+    {
+      "epoch": 2.2781299524564185,
+      "grad_norm": 0.11070399731397629,
+      "learning_rate": 0.0009895847053395504,
+      "loss": 0.4286,
+      "step": 11500
+    },
+    {
+      "epoch": 2.3771790808240887,
+      "grad_norm": 0.14005513489246368,
+      "learning_rate": 0.0009886627693613424,
+      "loss": 0.427,
+      "step": 12000
+    },
+    {
+      "epoch": 2.476228209191759,
+      "grad_norm": 0.09888464212417603,
+      "learning_rate": 0.0009877022081277332,
+      "loss": 0.4266,
+      "step": 12500
+    },
+    {
+      "epoch": 2.5752773375594296,
+      "grad_norm": 0.31440699100494385,
+      "learning_rate": 0.000986703097564137,
+      "loss": 0.4276,
+      "step": 13000
+    },
+    {
+      "epoch": 2.6743264659270998,
+      "grad_norm": 0.1942104548215866,
+      "learning_rate": 0.0009856655166430126,
+      "loss": 0.4269,
+      "step": 13500
+    },
+    {
+      "epoch": 2.7733755942947704,
+      "grad_norm": 0.3018036186695099,
+      "learning_rate": 0.0009845895473776232,
+      "loss": 0.4263,
+      "step": 14000
+    },
+    {
+      "epoch": 2.8724247226624406,
+      "grad_norm": 0.10349088907241821,
+      "learning_rate": 0.0009834752748155522,
+      "loss": 0.4259,
+      "step": 14500
+    },
+    {
+      "epoch": 2.971473851030111,
+      "grad_norm": 0.12177316844463348,
+      "learning_rate": 0.0009823227870319814,
+      "loss": 0.426,
+      "step": 15000
+    },
+    {
+      "epoch": 3.0,
+      "eval_MAE": 0.3759180009365082,
+      "eval_MAPE": 352.69488525390625,
+      "eval_MSE": 0.4976975917816162,
+      "eval_MSPE": 169782.796875,
+      "eval_ND": 0.45315608382225037,
+      "eval_RMSE": 0.7054768800735474,
+      "eval_SMAPE": 61.35142517089844,
+      "eval_runtime": 54.733,
+      "eval_samples_per_second": 22969.03,
+      "eval_steps_per_second": 11.218,
+      "step": 15144
+    },
+    {
+      "epoch": 3.070522979397781,
+      "grad_norm": 0.09670817106962204,
+      "learning_rate": 0.0009811321751227293,
+      "loss": 0.4253,
+      "step": 15500
+    },
+    {
+      "epoch": 3.1695721077654517,
+      "grad_norm": 0.1024642288684845,
+      "learning_rate": 0.000979903533197051,
+      "loss": 0.4254,
+      "step": 16000
+    },
+    {
+      "epoch": 3.268621236133122,
+      "grad_norm": 0.07792851328849792,
+      "learning_rate": 0.0009786369583701987,
+      "loss": 0.4256,
+      "step": 16500
+    },
+    {
+      "epoch": 3.3676703645007926,
+      "grad_norm": 0.1396850198507309,
+      "learning_rate": 0.000977332550755746,
+      "loss": 0.4246,
+      "step": 17000
+    },
+    {
+      "epoch": 3.466719492868463,
+      "grad_norm": 0.2117234766483307,
+      "learning_rate": 0.0009759904134576747,
+      "loss": 0.4242,
+      "step": 17500
+    },
+    {
+      "epoch": 3.565768621236133,
+      "grad_norm": 0.09312921017408371,
+      "learning_rate": 0.0009746106525622252,
+      "loss": 0.4233,
+      "step": 18000
+    },
+    {
+      "epoch": 3.6648177496038032,
+      "grad_norm": 0.12480303645133972,
+      "learning_rate": 0.0009731933771295105,
+      "loss": 0.4246,
+      "step": 18500
+    },
+    {
+      "epoch": 3.763866877971474,
+      "grad_norm": 0.06942948698997498,
+      "learning_rate": 0.0009717386991848969,
+      "loss": 0.4251,
+      "step": 19000
+    },
+    {
+      "epoch": 3.862916006339144,
+      "grad_norm": 0.11137889325618744,
+      "learning_rate": 0.0009702467337101477,
+      "loss": 0.4229,
+      "step": 19500
+    },
+    {
+      "epoch": 3.9619651347068148,
+      "grad_norm": 0.15101556479930878,
+      "learning_rate": 0.0009687175986343367,
+      "loss": 0.4242,
+      "step": 20000
+    },
+    {
+      "epoch": 4.0,
+      "eval_MAE": 0.37888333201408386,
+      "eval_MAPE": 356.0927429199219,
+      "eval_MSE": 0.49698570370674133,
+      "eval_MSPE": 187043.203125,
+      "eval_ND": 0.4567306935787201,
+      "eval_RMSE": 0.7049721479415894,
+      "eval_SMAPE": 61.83990478515625,
+      "eval_runtime": 54.2682,
+      "eval_samples_per_second": 23165.769,
+      "eval_steps_per_second": 11.314,
+      "step": 20192
+    },
+    {
+      "epoch": 4.061014263074485,
+      "grad_norm": 0.1452902853488922,
+      "learning_rate": 0.0009671514148245245,
+      "loss": 0.423,
+      "step": 20500
+    },
+    {
+      "epoch": 4.160063391442155,
+      "grad_norm": 0.08417252451181412,
+      "learning_rate": 0.000965548306076207,
+      "loss": 0.4241,
+      "step": 21000
+    },
+    {
+      "epoch": 4.259112519809825,
+      "grad_norm": 0.13033604621887207,
+      "learning_rate": 0.0009639083991035288,
+      "loss": 0.4226,
+      "step": 21500
+    },
+    {
+      "epoch": 4.358161648177496,
+      "grad_norm": 0.15337254106998444,
+      "learning_rate": 0.0009622318235292677,
+      "loss": 0.4222,
+      "step": 22000
+    },
+    {
+      "epoch": 4.457210776545167,
+      "grad_norm": 0.12474048137664795,
+      "learning_rate": 0.0009605187118745895,
+      "loss": 0.4227,
+      "step": 22500
+    },
+    {
+      "epoch": 4.556259904912837,
+      "grad_norm": 0.11578098684549332,
+      "learning_rate": 0.0009587691995485724,
+      "loss": 0.4204,
+      "step": 23000
+    },
+    {
+      "epoch": 4.655309033280507,
+      "grad_norm": 0.08201416581869125,
+      "learning_rate": 0.000956983424837504,
+      "loss": 0.4237,
+      "step": 23500
+    },
+    {
+      "epoch": 4.754358161648177,
+      "grad_norm": 0.13240130245685577,
+      "learning_rate": 0.0009551615288939518,
+      "loss": 0.4224,
+      "step": 24000
+    },
+    {
+      "epoch": 4.853407290015848,
+      "grad_norm": 0.11744749546051025,
+      "learning_rate": 0.0009533036557256045,
+      "loss": 0.4219,
+      "step": 24500
+    },
+    {
+      "epoch": 4.952456418383518,
+      "grad_norm": 0.1341642141342163,
+      "learning_rate": 0.0009514099521838906,
+      "loss": 0.4208,
+      "step": 25000
+    },
+    {
+      "epoch": 5.0,
+      "eval_MAE": 0.3666294813156128,
+      "eval_MAPE": 356.06121826171875,
+      "eval_MSE": 0.49152618646621704,
+      "eval_MSPE": 207269.796875,
+      "eval_ND": 0.44195911288261414,
+      "eval_RMSE": 0.7010892629623413,
+      "eval_SMAPE": 60.314064025878906,
+      "eval_runtime": 54.6859,
+      "eval_samples_per_second": 22988.83,
+      "eval_steps_per_second": 11.228,
+      "step": 25240
+    },
+    {
+      "epoch": 5.051505546751189,
+      "grad_norm": 0.07947442680597305,
+      "learning_rate": 0.00094948056795237,
+      "loss": 0.4194,
+      "step": 25500
+    },
+    {
+      "epoch": 5.150554675118859,
+      "grad_norm": 0.13597752153873444,
+      "learning_rate": 0.000947515655534903,
+      "loss": 0.4208,
+      "step": 26000
+    },
+    {
+      "epoch": 5.249603803486529,
+      "grad_norm": 0.07506517320871353,
+      "learning_rate": 0.0009455153702435957,
+      "loss": 0.4207,
+      "step": 26500
+    },
+    {
+      "epoch": 5.3486529318541995,
+      "grad_norm": 0.204156756401062,
+      "learning_rate": 0.0009434798701865242,
+      "loss": 0.421,
+      "step": 27000
+    },
+    {
+      "epoch": 5.44770206022187,
+      "grad_norm": 0.10013840347528458,
+      "learning_rate": 0.000941409316255237,
+      "loss": 0.4206,
+      "step": 27500
+    },
+    {
+      "epoch": 5.546751188589541,
+      "grad_norm": 0.11126238107681274,
+      "learning_rate": 0.0009393038721120373,
+      "loss": 0.4209,
+      "step": 28000
+    },
+    {
+      "epoch": 5.645800316957211,
+      "grad_norm": 0.07826147228479385,
+      "learning_rate": 0.0009371637041770472,
+      "loss": 0.4199,
+      "step": 28500
+    },
+    {
+      "epoch": 5.744849445324881,
+      "grad_norm": 0.1696319282054901,
+      "learning_rate": 0.0009349889816150534,
+      "loss": 0.4202,
+      "step": 29000
+    },
+    {
+      "epoch": 5.8438985736925515,
+      "grad_norm": 0.13377857208251953,
+      "learning_rate": 0.0009327798763221355,
+      "loss": 0.4198,
+      "step": 29500
+    },
+    {
+      "epoch": 5.942947702060222,
+      "grad_norm": 0.09888964146375656,
+      "learning_rate": 0.0009305365629120796,
+      "loss": 0.4209,
+      "step": 30000
+    },
+    {
+      "epoch": 6.0,
+      "eval_MAE": 0.3674909174442291,
+      "eval_MAPE": 365.8409118652344,
+      "eval_MSE": 0.49068397283554077,
+      "eval_MSPE": 221797.953125,
+      "eval_ND": 0.442997545003891,
+      "eval_RMSE": 0.7004883885383606,
+      "eval_SMAPE": 60.21101379394531,
+      "eval_runtime": 53.7469,
+      "eval_samples_per_second": 23390.462,
+      "eval_steps_per_second": 11.424,
+      "step": 30288
+    },
+    {
+      "epoch": 6.041996830427892,
+      "grad_norm": 0.10051033645868301,
+      "learning_rate": 0.0009282592187025753,
+      "loss": 0.4202,
+      "step": 30500
+    },
+    {
+      "epoch": 6.141045958795562,
+      "grad_norm": 0.1751776486635208,
+      "learning_rate": 0.0009259480237012013,
+      "loss": 0.4205,
+      "step": 31000
+    },
+    {
+      "epoch": 6.240095087163233,
+      "grad_norm": 0.15444861352443695,
+      "learning_rate": 0.0009236031605911957,
+      "loss": 0.4184,
+      "step": 31500
+    },
+    {
+      "epoch": 6.3391442155309035,
+      "grad_norm": 0.09780099242925644,
+      "learning_rate": 0.0009212248147170174,
+      "loss": 0.42,
+      "step": 32000
+    },
+    {
+      "epoch": 6.438193343898574,
+      "grad_norm": 0.12165773659944534,
+      "learning_rate": 0.0009188131740696953,
+      "loss": 0.4191,
+      "step": 32500
+    },
+    {
+      "epoch": 6.537242472266244,
+      "grad_norm": 0.09260477870702744,
+      "learning_rate": 0.0009163684292719692,
+      "loss": 0.4193,
+      "step": 33000
+    },
+    {
+      "epoch": 6.636291600633914,
+      "grad_norm": 0.09463346749544144,
+      "learning_rate": 0.0009138907735632225,
+      "loss": 0.4184,
+      "step": 33500
+    },
+    {
+      "epoch": 6.735340729001585,
+      "grad_norm": 0.10615640878677368,
+      "learning_rate": 0.0009113804027842078,
+      "loss": 0.4179,
+      "step": 34000
+    },
+    {
+      "epoch": 6.834389857369255,
+      "grad_norm": 0.10410912334918976,
+      "learning_rate": 0.0009088375153615673,
+      "loss": 0.4189,
+      "step": 34500
+    },
+    {
+      "epoch": 6.933438985736926,
+      "grad_norm": 0.10201963037252426,
+      "learning_rate": 0.0009062623122921485,
+      "loss": 0.4187,
+      "step": 35000
+    },
+    {
+      "epoch": 7.0,
+      "eval_MAE": 0.36573904752731323,
+      "eval_MAPE": 352.3959045410156,
+      "eval_MSE": 0.48773863911628723,
+      "eval_MSPE": 185352.046875,
+      "eval_ND": 0.4408857226371765,
+      "eval_RMSE": 0.6983828544616699,
+      "eval_SMAPE": 59.932762145996094,
+      "eval_runtime": 54.521,
+      "eval_samples_per_second": 23058.35,
+      "eval_steps_per_second": 11.262,
+      "step": 35336
+    },
+    {
+      "epoch": 7.032488114104596,
+      "grad_norm": 0.11093030869960785,
+      "learning_rate": 0.000903654997127117,
+      "loss": 0.4191,
+      "step": 35500
+    },
+    {
+      "epoch": 7.131537242472266,
+      "grad_norm": 0.1134202629327774,
+      "learning_rate": 0.0009010157759558673,
+      "loss": 0.4186,
+      "step": 36000
+    },
+    {
+      "epoch": 7.230586370839936,
+      "grad_norm": 0.06474833935499191,
+      "learning_rate": 0.0008983448573897322,
+      "loss": 0.4191,
+      "step": 36500
+    },
+    {
+      "epoch": 7.329635499207607,
+      "grad_norm": 0.11325617134571075,
+      "learning_rate": 0.0008956424525454949,
+      "loss": 0.4164,
+      "step": 37000
+    },
+    {
+      "epoch": 7.428684627575278,
+      "grad_norm": 0.07661303877830505,
+      "learning_rate": 0.0008929087750287004,
+      "loss": 0.4179,
+      "step": 37500
+    },
+    {
+      "epoch": 7.527733755942948,
+      "grad_norm": 0.07534985989332199,
+      "learning_rate": 0.0008901440409167727,
+      "loss": 0.4191,
+      "step": 38000
+    },
+    {
+      "epoch": 7.626782884310618,
+      "grad_norm": 0.09289834648370743,
+      "learning_rate": 0.0008873484687419344,
+      "loss": 0.4177,
+      "step": 38500
+    },
+    {
+      "epoch": 7.725832012678288,
+      "grad_norm": 0.12024533003568649,
+      "learning_rate": 0.0008845222794739341,
+      "loss": 0.417,
+      "step": 39000
+    },
+    {
+      "epoch": 7.824881141045958,
+      "grad_norm": 0.0927654430270195,
+      "learning_rate": 0.00088166569650258,
+      "loss": 0.4181,
+      "step": 39500
+    },
+    {
+      "epoch": 7.9239302694136295,
+      "grad_norm": 0.14443668723106384,
+      "learning_rate": 0.0008787789456200823,
+      "loss": 0.4175,
+      "step": 40000
+    },
+    {
+      "epoch": 8.0,
+      "eval_MAE": 0.36536094546318054,
+      "eval_MAPE": 354.2453918457031,
+      "eval_MSE": 0.48749861121177673,
+      "eval_MSPE": 195818.65625,
+      "eval_ND": 0.4404299259185791,
+      "eval_RMSE": 0.6982110142707825,
+      "eval_SMAPE": 59.863468170166016,
+      "eval_runtime": 54.3633,
+      "eval_samples_per_second": 23125.25,
+      "eval_steps_per_second": 11.294,
+      "step": 40384
+    },
+    {
+      "epoch": 8.022979397781299,
+      "grad_norm": 0.0843660980463028,
+      "learning_rate": 0.0008758622550032065,
+      "loss": 0.418,
+      "step": 40500
+    },
+    {
+      "epoch": 8.12202852614897,
+      "grad_norm": 0.14738310873508453,
+      "learning_rate": 0.0008729158551952377,
+      "loss": 0.4173,
+      "step": 41000
+    },
+    {
+      "epoch": 8.221077654516641,
+      "grad_norm": 0.07845776528120041,
+      "learning_rate": 0.0008699399790877566,
+      "loss": 0.4176,
+      "step": 41500
+    },
+    {
+      "epoch": 8.32012678288431,
+      "grad_norm": 0.1038828119635582,
+      "learning_rate": 0.0008669348619022335,
+      "loss": 0.4175,
+      "step": 42000
+    },
+    {
+      "epoch": 8.419175911251982,
+      "grad_norm": 0.14202700555324554,
+      "learning_rate": 0.000863900741171433,
+      "loss": 0.417,
+      "step": 42500
+    },
+    {
+      "epoch": 8.51822503961965,
+      "grad_norm": 0.1151699423789978,
+      "learning_rate": 0.0008608378567206405,
+      "loss": 0.4181,
+      "step": 43000
+    },
+    {
+      "epoch": 8.617274167987322,
+      "grad_norm": 0.19360342621803284,
+      "learning_rate": 0.0008577464506487054,
+      "loss": 0.4153,
+      "step": 43500
+    },
+    {
+      "epoch": 8.716323296354991,
+      "grad_norm": 0.11765541136264801,
+      "learning_rate": 0.0008546267673089049,
+      "loss": 0.4159,
+      "step": 44000
+    },
+    {
+      "epoch": 8.815372424722662,
+      "grad_norm": 0.15739209949970245,
+      "learning_rate": 0.0008514790532896294,
+      "loss": 0.4162,
+      "step": 44500
+    },
+    {
+      "epoch": 8.914421553090333,
+      "grad_norm": 0.12929894030094147,
+      "learning_rate": 0.0008483035573948916,
+      "loss": 0.4161,
+      "step": 45000
+    },
+    {
+      "epoch": 9.0,
+      "eval_MAE": 0.3685202896595001,
+      "eval_MAPE": 360.7921447753906,
+      "eval_MSE": 0.48982617259025574,
+      "eval_MSPE": 237005.59375,
+      "eval_ND": 0.44423842430114746,
+      "eval_RMSE": 0.6998758316040039,
+      "eval_SMAPE": 60.21327590942383,
+      "eval_runtime": 55.2004,
+      "eval_samples_per_second": 22774.547,
+      "eval_steps_per_second": 11.123,
+      "step": 45432
+    },
+    {
+      "epoch": 9.013470681458003,
+      "grad_norm": 0.08673319220542908,
+      "learning_rate": 0.0008451005306246607,
+      "loss": 0.4164,
+      "step": 45500
+    },
+    {
+      "epoch": 9.112519809825674,
+      "grad_norm": 0.08345810323953629,
+      "learning_rate": 0.000841870226155022,
+      "loss": 0.4154,
+      "step": 46000
+    },
+    {
+      "epoch": 9.211568938193343,
+      "grad_norm": 0.12091132998466492,
+      "learning_rate": 0.0008386128993181656,
+      "loss": 0.4162,
+      "step": 46500
+    },
+    {
+      "epoch": 9.310618066561014,
+      "grad_norm": 0.09233805537223816,
+      "learning_rate": 0.0008353288075822044,
+      "loss": 0.417,
+      "step": 47000
+    },
+    {
+      "epoch": 9.409667194928685,
+      "grad_norm": 0.14294278621673584,
+      "learning_rate": 0.0008320182105308227,
+      "loss": 0.4164,
+      "step": 47500
+    },
+    {
+      "epoch": 9.508716323296355,
+      "grad_norm": 0.08588852733373642,
+      "learning_rate": 0.0008286813698427583,
+      "loss": 0.4151,
+      "step": 48000
+    },
+    {
+      "epoch": 9.607765451664026,
+      "grad_norm": 0.09648016840219498,
+      "learning_rate": 0.0008253185492711182,
+      "loss": 0.4158,
+      "step": 48500
+    },
+    {
+      "epoch": 9.706814580031695,
+      "grad_norm": 0.10604752600193024,
+      "learning_rate": 0.0008219300146225315,
+      "loss": 0.416,
+      "step": 49000
+    },
+    {
+      "epoch": 9.805863708399366,
+      "grad_norm": 0.07823313027620316,
+      "learning_rate": 0.0008185160337361388,
+      "loss": 0.414,
+      "step": 49500
+    },
+    {
+      "epoch": 9.904912836767036,
+      "grad_norm": 0.09862257540225983,
+      "learning_rate": 0.000815076876462422,
+      "loss": 0.4153,
+      "step": 50000
+    },
+    {
+      "epoch": 10.0,
+      "eval_MAE": 0.35969898104667664,
+      "eval_MAPE": 347.6515808105469,
+      "eval_MSE": 0.4838204085826874,
+      "eval_MSPE": 197941.25,
+      "eval_ND": 0.4336046278476715,
+      "eval_RMSE": 0.695572018623352,
+      "eval_SMAPE": 59.28236389160156,
+      "eval_runtime": 55.2356,
+      "eval_samples_per_second": 22760.038,
+      "eval_steps_per_second": 11.116,
+      "step": 50480
+    },
+    {
+      "epoch": 10.003961965134707,
+      "grad_norm": 0.09266933053731918,
+      "learning_rate": 0.0008116128146418738,
+      "loss": 0.4163,
+      "step": 50500
+    },
+    {
+      "epoch": 10.103011093502378,
+      "grad_norm": 0.1360657662153244,
+      "learning_rate": 0.0008081241220835112,
+      "loss": 0.4138,
+      "step": 51000
+    },
+    {
+      "epoch": 10.202060221870047,
+      "grad_norm": 0.12415830045938492,
+      "learning_rate": 0.0008046110745432329,
+      "loss": 0.4154,
+      "step": 51500
+    },
+    {
+      "epoch": 10.301109350237718,
+      "grad_norm": 0.12350622564554214,
+      "learning_rate": 0.0008010739497020226,
+      "loss": 0.4152,
+      "step": 52000
+    },
+    {
+      "epoch": 10.400158478605388,
+      "grad_norm": 0.09407506883144379,
+      "learning_rate": 0.0007975130271440001,
+      "loss": 0.4142,
+      "step": 52500
+    },
+    {
+      "epoch": 10.499207606973059,
+      "grad_norm": 0.07152153551578522,
+      "learning_rate": 0.000793928588334323,
+      "loss": 0.4152,
+      "step": 53000
+    },
+    {
+      "epoch": 10.59825673534073,
+      "grad_norm": 0.11555545032024384,
+      "learning_rate": 0.0007903209165969381,
+      "loss": 0.4149,
+      "step": 53500
+    },
+    {
+      "epoch": 10.697305863708399,
+      "grad_norm": 0.1005263477563858,
+      "learning_rate": 0.0007866902970921869,
+      "loss": 0.4151,
+      "step": 54000
+    },
+    {
+      "epoch": 10.79635499207607,
+      "grad_norm": 0.151838481426239,
+      "learning_rate": 0.0007830370167942662,
+      "loss": 0.4157,
+      "step": 54500
+    },
+    {
+      "epoch": 10.89540412044374,
+      "grad_norm": 0.12097581475973129,
+      "learning_rate": 0.0007793613644685442,
+      "loss": 0.4142,
+      "step": 55000
+    },
+    {
+      "epoch": 10.99445324881141,
+      "grad_norm": 0.07319813221693039,
+      "learning_rate": 0.0007756636306487361,
+      "loss": 0.4145,
+      "step": 55500
+    },
+    {
+      "epoch": 11.0,
+      "eval_MAE": 0.36152151226997375,
+      "eval_MAPE": 355.8778991699219,
+      "eval_MSE": 0.4874439239501953,
+      "eval_MSPE": 242275.75,
+      "eval_ND": 0.43580162525177,
+      "eval_RMSE": 0.698171854019165,
+      "eval_SMAPE": 59.33519744873047,
+      "eval_runtime": 54.9921,
+      "eval_samples_per_second": 22860.849,
+      "eval_steps_per_second": 11.165,
+      "step": 55528
+    },
+    {
+      "epoch": 11.09350237717908,
+      "grad_norm": 0.08475903421640396,
+      "learning_rate": 0.0007719441076139392,
+      "loss": 0.4144,
+      "step": 56000
+    },
+    {
+      "epoch": 11.192551505546751,
+      "grad_norm": 0.09286442399024963,
+      "learning_rate": 0.000768203089365531,
+      "loss": 0.414,
+      "step": 56500
+    },
+    {
+      "epoch": 11.291600633914422,
+      "grad_norm": 0.07604731619358063,
+      "learning_rate": 0.0007644408716039295,
+      "loss": 0.4132,
+      "step": 57000
+    },
+    {
+      "epoch": 11.390649762282091,
+      "grad_norm": 0.10099564492702484,
+      "learning_rate": 0.0007606577517052212,
+      "loss": 0.4128,
+      "step": 57500
+    },
+    {
+      "epoch": 11.489698890649763,
+      "grad_norm": 0.0886906161904335,
+      "learning_rate": 0.0007568540286976551,
+      "loss": 0.4144,
+      "step": 58000
+    },
+    {
+      "epoch": 11.588748019017432,
+      "grad_norm": 0.09952269494533539,
+      "learning_rate": 0.0007530300032380071,
+      "loss": 0.4153,
+      "step": 58500
+    },
+    {
+      "epoch": 11.687797147385103,
+      "grad_norm": 0.09850025922060013,
+      "learning_rate": 0.0007491859775878146,
+      "loss": 0.414,
+      "step": 59000
+    },
+    {
+      "epoch": 11.786846275752774,
+      "grad_norm": 0.16440285742282867,
+      "learning_rate": 0.0007453222555894856,
+      "loss": 0.4135,
+      "step": 59500
+    },
+    {
+      "epoch": 11.885895404120443,
+      "grad_norm": 0.09019125998020172,
+      "learning_rate": 0.000741439142642282,
+      "loss": 0.4141,
+      "step": 60000
+    },
+    {
+      "epoch": 11.984944532488115,
+      "grad_norm": 0.11564897000789642,
+      "learning_rate": 0.0007375369456781793,
+      "loss": 0.4135,
+      "step": 60500
+    },
+    {
+      "epoch": 12.0,
+      "eval_MAE": 0.3628363013267517,
+      "eval_MAPE": 352.1346740722656,
+      "eval_MSE": 0.48805665969848633,
+      "eval_MSPE": 232840.859375,
+      "eval_ND": 0.43738657236099243,
+      "eval_RMSE": 0.6986105442047119,
+      "eval_SMAPE": 59.68527603149414,
+      "eval_runtime": 54.4659,
+      "eval_samples_per_second": 23081.687,
+      "eval_steps_per_second": 11.273,
+      "step": 60576
+    },
+    {
+      "epoch": 12.083993660855784,
+      "grad_norm": 0.14516101777553558,
+      "learning_rate": 0.0007336159731376071,
+      "loss": 0.4132,
+      "step": 61000
+    },
+    {
+      "epoch": 12.183042789223455,
+      "grad_norm": 0.10409526526927948,
+      "learning_rate": 0.0007296765349450678,
+      "loss": 0.4143,
+      "step": 61500
+    },
+    {
+      "epoch": 12.282091917591124,
+      "grad_norm": 0.13454560935497284,
+      "learning_rate": 0.0007257189424846407,
+      "loss": 0.413,
+      "step": 62000
+    },
+    {
+      "epoch": 12.381141045958795,
+      "grad_norm": 0.12388956546783447,
+      "learning_rate": 0.0007217435085753679,
+      "loss": 0.4144,
+      "step": 62500
+    },
+    {
+      "epoch": 12.480190174326466,
+      "grad_norm": 0.12922845780849457,
+      "learning_rate": 0.0007177505474465294,
+      "loss": 0.412,
+      "step": 63000
+    },
+    {
+      "epoch": 12.579239302694136,
+      "grad_norm": 0.11674097180366516,
+      "learning_rate": 0.0007137403747128044,
+      "loss": 0.4128,
+      "step": 63500
+    },
+    {
+      "epoch": 12.678288431061807,
+      "grad_norm": 0.12132911384105682,
+      "learning_rate": 0.000709713307349326,
+      "loss": 0.4133,
+      "step": 64000
+    },
+    {
+      "epoch": 12.777337559429476,
+      "grad_norm": 0.0879695862531662,
+      "learning_rate": 0.0007056696636666243,
+      "loss": 0.4134,
+      "step": 64500
+    },
+    {
+      "epoch": 12.876386687797147,
+      "grad_norm": 0.0823468267917633,
+      "learning_rate": 0.0007016097632854684,
+      "loss": 0.4117,
+      "step": 65000
+    },
+    {
+      "epoch": 12.975435816164818,
+      "grad_norm": 0.11856217682361603,
+      "learning_rate": 0.0006975339271116012,
+      "loss": 0.4126,
+      "step": 65500
+    },
+    {
+      "epoch": 13.0,
+      "eval_MAE": 0.3578062355518341,
+      "eval_MAPE": 340.23406982421875,
+      "eval_MSE": 0.4831537902355194,
+      "eval_MSPE": 227388.484375,
+      "eval_ND": 0.43132299184799194,
+      "eval_RMSE": 0.6950926780700684,
+      "eval_SMAPE": 59.14822769165039,
+      "eval_runtime": 54.2424,
+      "eval_samples_per_second": 23176.786,
+      "eval_steps_per_second": 11.32,
+      "step": 65624
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 176680,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 35,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}

OFA/PEMS04_336/checkpoint-65624/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57783d1c775922679e371b39a13b1f0e1b0afa7e63698d2b8e6f438f59bab39
+size 6584

OFA/Solar_192/checkpoint-14556/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60bd6475e443ba58da1fe6bff4125da6ebd4daa4f4026be81dc6ffae8a5d6965
+size 261338858

OFA/Solar_192/checkpoint-14556/trainer_state.json

@@ -0,0 +1,330 @@
+{
+  "best_global_step": 14556,
+  "best_metric": 0.16441404819488525,
+  "best_model_checkpoint": "/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/OFA_layer/haspara/Solar/checkpoint-14556",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 14556,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.20610057708161583,
+      "grad_norm": 0.13613636791706085,
+      "learning_rate": 0.0009999147860244627,
+      "loss": 0.4442,
+      "step": 500
+    },
+    {
+      "epoch": 0.41220115416323166,
+      "grad_norm": 0.09557799249887466,
+      "learning_rate": 0.0009996584898593923,
+      "loss": 0.1748,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6183017312448474,
+      "grad_norm": 0.16066046059131622,
+      "learning_rate": 0.000999231198873098,
+      "loss": 0.1707,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8244023083264633,
+      "grad_norm": 0.1717931628227234,
+      "learning_rate": 0.0009986330592945485,
+      "loss": 0.1679,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_MAE": 0.24874718487262726,
+      "eval_MAPE": 180.4757843017578,
+      "eval_MSE": 0.16690030694007874,
+      "eval_MSPE": 9273.771484375,
+      "eval_ND": 0.2907600700855255,
+      "eval_RMSE": 0.40853434801101685,
+      "eval_SMAPE": 36.44480895996094,
+      "eval_runtime": 58.8031,
+      "eval_samples_per_second": 11800.483,
+      "eval_steps_per_second": 5.765,
+      "step": 2426
+    },
+    {
+      "epoch": 1.030502885408079,
+      "grad_norm": 0.11462152004241943,
+      "learning_rate": 0.000997864275821097,
+      "loss": 0.166,
+      "step": 2500
+    },
+    {
+      "epoch": 1.2366034624896949,
+      "grad_norm": 0.05391139164566994,
+      "learning_rate": 0.0009969251115484285,
+      "loss": 0.164,
+      "step": 3000
+    },
+    {
+      "epoch": 1.4427040395713109,
+      "grad_norm": 0.08242031186819077,
+      "learning_rate": 0.0009958158878805223,
+      "loss": 0.1628,
+      "step": 3500
+    },
+    {
+      "epoch": 1.6488046166529267,
+      "grad_norm": 0.09068718552589417,
+      "learning_rate": 0.0009945369844196596,
+      "loss": 0.1614,
+      "step": 4000
+    },
+    {
+      "epoch": 1.8549051937345424,
+      "grad_norm": 0.12416058033704758,
+      "learning_rate": 0.000993088838836516,
+      "loss": 0.1604,
+      "step": 4500
+    },
+    {
+      "epoch": 2.0,
+      "eval_MAE": 0.2530505359172821,
+      "eval_MAPE": 184.0513153076172,
+      "eval_MSE": 0.1713208258152008,
+      "eval_MSPE": 8967.3408203125,
+      "eval_ND": 0.29579025506973267,
+      "eval_RMSE": 0.4139091968536377,
+      "eval_SMAPE": 37.25147247314453,
+      "eval_runtime": 58.5412,
+      "eval_samples_per_second": 11853.276,
+      "eval_steps_per_second": 5.791,
+      "step": 4852
+    },
+    {
+      "epoch": 2.061005770816158,
+      "grad_norm": 0.11636342853307724,
+      "learning_rate": 0.000991471946720379,
+      "loss": 0.1596,
+      "step": 5000
+    },
+    {
+      "epoch": 2.267106347897774,
+      "grad_norm": 0.13195322453975677,
+      "learning_rate": 0.0009896868614095468,
+      "loss": 0.1585,
+      "step": 5500
+    },
+    {
+      "epoch": 2.4732069249793898,
+      "grad_norm": 0.1224469393491745,
+      "learning_rate": 0.0009877341938019622,
+      "loss": 0.1582,
+      "step": 6000
+    },
+    {
+      "epoch": 2.6793075020610058,
+      "grad_norm": 0.12972772121429443,
+      "learning_rate": 0.0009856146121461496,
+      "loss": 0.1574,
+      "step": 6500
+    },
+    {
+      "epoch": 2.8854080791426218,
+      "grad_norm": 0.12829646468162537,
+      "learning_rate": 0.0009833288418125239,
+      "loss": 0.1567,
+      "step": 7000
+    },
+    {
+      "epoch": 3.0,
+      "eval_MAE": 0.2434338480234146,
+      "eval_MAPE": 180.72421264648438,
+      "eval_MSE": 0.16737966239452362,
+      "eval_MSPE": 9376.3095703125,
+      "eval_ND": 0.2845493257045746,
+      "eval_RMSE": 0.4091205894947052,
+      "eval_SMAPE": 35.947811126708984,
+      "eval_runtime": 58.2785,
+      "eval_samples_per_second": 11906.705,
+      "eval_steps_per_second": 5.817,
+      "step": 7278
+    },
+    {
+      "epoch": 3.0915086562242373,
+      "grad_norm": 0.07943403720855713,
+      "learning_rate": 0.000980877665045153,
+      "loss": 0.1559,
+      "step": 7500
+    },
+    {
+      "epoch": 3.2976092333058533,
+      "grad_norm": 0.06782522052526474,
+      "learning_rate": 0.0009782619206940547,
+      "loss": 0.1552,
+      "step": 8000
+    },
+    {
+      "epoch": 3.503709810387469,
+      "grad_norm": 0.12171012163162231,
+      "learning_rate": 0.000975482503928123,
+      "loss": 0.155,
+      "step": 8500
+    },
+    {
+      "epoch": 3.709810387469085,
+      "grad_norm": 0.16907528042793274,
+      "learning_rate": 0.0009725403659287799,
+      "loss": 0.1543,
+      "step": 9000
+    },
+    {
+      "epoch": 3.915910964550701,
+      "grad_norm": 0.1479276567697525,
+      "learning_rate": 0.0009694365135644595,
+      "loss": 0.1538,
+      "step": 9500
+    },
+    {
+      "epoch": 4.0,
+      "eval_MAE": 0.23490256071090698,
+      "eval_MAPE": 181.50564575195312,
+      "eval_MSE": 0.16538722813129425,
+      "eval_MSPE": 9649.654296875,
+      "eval_ND": 0.27457714080810547,
+      "eval_RMSE": 0.40667828917503357,
+      "eval_SMAPE": 34.649436950683594,
+      "eval_runtime": 58.6782,
+      "eval_samples_per_second": 11825.598,
+      "eval_steps_per_second": 5.777,
+      "step": 9704
+    },
+    {
+      "epoch": 4.122011541632316,
+      "grad_norm": 0.09500300139188766,
+      "learning_rate": 0.0009661720090460337,
+      "loss": 0.1535,
+      "step": 10000
+    },
+    {
+      "epoch": 4.328112118713932,
+      "grad_norm": 0.0786258801817894,
+      "learning_rate": 0.0009627479695632988,
+      "loss": 0.153,
+      "step": 10500
+    },
+    {
+      "epoch": 4.534212695795548,
+      "grad_norm": 0.07586020231246948,
+      "learning_rate": 0.0009591655669026469,
+      "loss": 0.1523,
+      "step": 11000
+    },
+    {
+      "epoch": 4.740313272877164,
+      "grad_norm": 0.14045332372188568,
+      "learning_rate": 0.0009554260270460539,
+      "loss": 0.1517,
+      "step": 11500
+    },
+    {
+      "epoch": 4.9464138499587795,
+      "grad_norm": 0.08372505754232407,
+      "learning_rate": 0.0009515306297515187,
+      "loss": 0.1512,
+      "step": 12000
+    },
+    {
+      "epoch": 5.0,
+      "eval_MAE": 0.2414267361164093,
+      "eval_MAPE": 181.71209716796875,
+      "eval_MSE": 0.16475139558315277,
+      "eval_MSPE": 9144.029296875,
+      "eval_ND": 0.28220322728157043,
+      "eval_RMSE": 0.40589579939842224,
+      "eval_SMAPE": 35.766761779785156,
+      "eval_runtime": 59.913,
+      "eval_samples_per_second": 11581.882,
+      "eval_steps_per_second": 5.658,
+      "step": 12130
+    },
+    {
+      "epoch": 5.152514427040396,
+      "grad_norm": 0.12079860270023346,
+      "learning_rate": 0.0009474807081151011,
+      "loss": 0.1507,
+      "step": 12500
+    },
+    {
+      "epoch": 5.3586150041220115,
+      "grad_norm": 0.08449820429086685,
+      "learning_rate": 0.0009432776481147042,
+      "loss": 0.1504,
+      "step": 13000
+    },
+    {
+      "epoch": 5.564715581203627,
+      "grad_norm": 0.06070152297616005,
+      "learning_rate": 0.0009389228881357614,
+      "loss": 0.1501,
+      "step": 13500
+    },
+    {
+      "epoch": 5.7708161582852435,
+      "grad_norm": 0.1490793377161026,
+      "learning_rate": 0.0009344179184789862,
+      "loss": 0.1493,
+      "step": 14000
+    },
+    {
+      "epoch": 5.976916735366859,
+      "grad_norm": 0.15414516627788544,
+      "learning_rate": 0.0009297642808503576,
+      "loss": 0.1494,
+      "step": 14500
+    },
+    {
+      "epoch": 6.0,
+      "eval_MAE": 0.23061439394950867,
+      "eval_MAPE": 180.4387969970703,
+      "eval_MSE": 0.16441404819488525,
+      "eval_MSPE": 9619.1962890625,
+      "eval_ND": 0.269564688205719,
+      "eval_RMSE": 0.4054800271987915,
+      "eval_SMAPE": 33.97864532470703,
+      "eval_runtime": 58.9946,
+      "eval_samples_per_second": 11762.182,
+      "eval_steps_per_second": 5.746,
+      "step": 14556
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 84910,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 35,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}

OFA/Solar_192/checkpoint-14556/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9af1751dc8b83f8179385ed6c0777b909ae98e57808be77ef242c73b56ec973
+size 6584

OFA/exchange_rate_192/checkpoint-299/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ace47295691bb7ba9ffee694abb9f152a520eb239be59f22bfe08a529a9d34dc
+size 261338858

OFA/exchange_rate_192/checkpoint-299/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_global_step": 299,
+  "best_metric": 0.25842341780662537,
+  "best_model_checkpoint": "/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/OFA_layer/haspara/192/exchange_rate/checkpoint-299",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 299,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_MAE": 0.3695564270019531,
+      "eval_MAPE": 25.642061233520508,
+      "eval_MSE": 0.25842341780662537,
+      "eval_MSPE": 2.612428903579712,
+      "eval_ND": 0.16934385895729065,
+      "eval_RMSE": 0.5083536505699158,
+      "eval_SMAPE": 21.528039932250977,
+      "eval_runtime": 1.45,
+      "eval_samples_per_second": 3139.386,
+      "eval_steps_per_second": 2.069,
+      "step": 299
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10465,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 35,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

OFA/exchange_rate_192/checkpoint-299/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adab5dda675b19d540a6cd1fafe424edba1cec784a550ddf4f810ab1b4070ff1
+size 6584

OFA/weather_720/checkpoint-368/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d051349812c6ac062d248ad978de78868a2c6d603ebb19c4f43c0c6f40366c50
+size 295402218

OFA/weather_720/checkpoint-368/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_global_step": 368,
+  "best_metric": 0.6688529253005981,
+  "best_model_checkpoint": "/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/OFA_layer/haspara/720/weather/checkpoint-368",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 368,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_MAE": 0.454274982213974,
+      "eval_MAPE": 1555.0623779296875,
+      "eval_MSE": 0.6688529253005981,
+      "eval_MSPE": 14232647.0,
+      "eval_ND": 0.8133898377418518,
+      "eval_RMSE": 0.8178343176841736,
+      "eval_SMAPE": 97.3488540649414,
+      "eval_runtime": 11.3069,
+      "eval_samples_per_second": 8452.448,
+      "eval_steps_per_second": 4.157,
+      "step": 368
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 12880,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 35,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 512,
+  "trial_name": null,
+  "trial_params": null
+}

OFA/weather_720/checkpoint-368/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d346ca809d2df8f0ecac6e575996ddf769302bed020738e91f3c3cc6371672c
+size 6584

TimeLLM/ETTm1_512_192_TimeLLM_ETTm1_sl512_pl192_dm32_nh8_df128/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e257ac465464b06bd92e3e56d0b6dac59b9d7e8cea42d2f9916f02edae805960
+size 714733599

TimeLLM/PEMS07_512_336_TimeLLM_PEMS07_sl512_pl336_dm16_nh8_df32/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8687faa15ce2fbfaccdb59744cc1fc6e0a068bf89df6d2ff4a61482e1c136674
+size 703990367

TimeLLM/PEMS08_512_720_TimeLLM_PEMS08_sl512_pl720_dm16_nh8_df32/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:468dfc1f9e03632771833a9d83fb8524132277f5752ee38633952285427d1237
+size 707137631

TimeLLM/PEMS08_512_720_TimeLLM_PEMS08_sl512_pl720_dm16_nh8_df32/log.txt

@@ -0,0 +1,28 @@
+Namespace(model_id='PEMS08_512_720', model='TimeLLM', seed=2021, data='PEMS08', checkpoints='/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/TimeLLM/hasparacheckpoints720/', load_ckp_base='/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/TimeLLM/hasparacheckpoints96/', seq_len=512, pred_len=720, d_model=16, n_heads=8, d_ff=32, dropout=0.1, patch_size=16, stride=8, llm_dim=768, num_workers=16, train_epochs=10, batch_size=48, patience=3, learning_rate=0.01, lradj='type1', pct_start=0.2, gpt2_llama2='gpt2', part=0, pretrain=1, freeze=1, test_metrics_path='/home/hk-project-p0022189/tum_yvc3016/junlong/qx/Time-LLM/scripts/test_metrics/720.txt', dual_FT=0, selected_layers=[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11], load_path='/hkfs/work/workspace/scratch/tum_yvc3016-R1/qx_data/TimeLLM/hasparacheckpoints720/PEMS08_512_720_TimeLLM_PEMS08_sl512_pl720_dm16_nh8_df32/log.txt', content='PEMS08 is a traffic dataset collected by 170 sensors over a period of 62 days. It includes three types of features: flow, average speed, and average occupancy.')
+Epoch: 1 cost time: 5270.287646770477
+Epoch: 1 | Train Loss: 0.5284430 Vali Loss: 0.6219723
+lr = 0.0004000000
+Epoch: 2 cost time: 5211.907626390457
+Epoch: 2 | Train Loss: 0.5061403 Vali Loss: 0.6203775
+Epoch: 3 cost time: 5205.380863666534
+Epoch: 3 | Train Loss: 0.4967325 Vali Loss: 0.6154433
+Epoch: 4 cost time: 5146.1251401901245
+Epoch: 4 | Train Loss: 0.4909644 Vali Loss: 0.6087528
+Epoch: 5 cost time: 5147.690908670425
+Epoch: 5 | Train Loss: 0.4880833 Vali Loss: 0.6050516
+Epoch: 6 cost time: 5146.230623722076
+Epoch: 6 | Train Loss: 0.4862469 Vali Loss: 0.6055145
+EarlyStopping counter: 1 out of 3
+Epoch: 7 cost time: 5129.8446407318115
+Epoch: 7 | Train Loss: 0.4850045 Vali Loss: 0.6044727
+Epoch: 8 cost time: 5116.925268650055
+Epoch: 8 | Train Loss: 0.4858361 Vali Loss: 0.6041182
+Epoch: 9 cost time: 5114.435469150543
+Epoch: 9 | Train Loss: 0.4855596 Vali Loss: 0.6045282
+EarlyStopping counter: 1 out of 3
+Epoch: 10 cost time: 5103.860981225967
+Epoch: 10 | Train Loss: 0.4847863 Vali Loss: 0.6048156
+EarlyStopping counter: 2 out of 3
+test shape: (1454520, 720, 1) (1454520, 720, 1)
+PEMS08--MAE: 0.4079, MSE: 0.6099
+finish

TimeLLM/electricity_512_192_TimeLLM_electricity_sl512_pl192_dm16_nh8_df32/checkpoint.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88e322b8eb75cf0165dff18c4c154d7815a328b26845e57c52931c9ed93190cb
+size 702810143