| { | |
| "best_metric": 1.7144521474838257, | |
| "best_model_checkpoint": "miner_id_24/checkpoint-50", | |
| "epoch": 0.2849002849002849, | |
| "eval_steps": 25, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.005698005698005698, | |
| "grad_norm": 0.4957379698753357, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005698005698005698, | |
| "eval_loss": 2.767381191253662, | |
| "eval_runtime": 9.9519, | |
| "eval_samples_per_second": 118.771, | |
| "eval_steps_per_second": 14.872, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.011396011396011397, | |
| "grad_norm": 0.5616330504417419, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4696, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.017094017094017096, | |
| "grad_norm": 0.5348113775253296, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 1.4703, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.022792022792022793, | |
| "grad_norm": 0.570271909236908, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 1.4865, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.02849002849002849, | |
| "grad_norm": 0.5843020081520081, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 1.5268, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 0.5844607949256897, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 1.4884, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.039886039886039885, | |
| "grad_norm": 1.1006460189819336, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 1.6398, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.045584045584045586, | |
| "grad_norm": 3.487726926803589, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.3385, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.05128205128205128, | |
| "grad_norm": 2.7304158210754395, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 1.9678, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.05698005698005698, | |
| "grad_norm": 1.7947251796722412, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.4213, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06267806267806268, | |
| "grad_norm": 3.5785210132598877, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 3.0586, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.06837606837606838, | |
| "grad_norm": 4.582289695739746, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 3.4243, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.07407407407407407, | |
| "grad_norm": 2.795785427093506, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.4945, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.07977207977207977, | |
| "grad_norm": 3.1796531677246094, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.569, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.08547008547008547, | |
| "grad_norm": 2.5611207485198975, | |
| "learning_rate": 8.296729075500344e-05, | |
| "loss": 1.6105, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.09116809116809117, | |
| "grad_norm": 1.8405492305755615, | |
| "learning_rate": 8.043807145043604e-05, | |
| "loss": 1.6119, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.09686609686609686, | |
| "grad_norm": 1.5602606534957886, | |
| "learning_rate": 7.777851165098012e-05, | |
| "loss": 1.4798, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 1.3331987857818604, | |
| "learning_rate": 7.500000000000001e-05, | |
| "loss": 1.4909, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.10826210826210826, | |
| "grad_norm": 1.0286616086959839, | |
| "learning_rate": 7.211443451095007e-05, | |
| "loss": 1.3649, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.11396011396011396, | |
| "grad_norm": 1.0691101551055908, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.4918, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.11965811965811966, | |
| "grad_norm": 1.7650200128555298, | |
| "learning_rate": 6.607197326515808e-05, | |
| "loss": 1.6705, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.12535612535612536, | |
| "grad_norm": 1.2216529846191406, | |
| "learning_rate": 6.294095225512603e-05, | |
| "loss": 1.7233, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.13105413105413105, | |
| "grad_norm": 1.962334156036377, | |
| "learning_rate": 5.9754516100806423e-05, | |
| "loss": 2.4644, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.13675213675213677, | |
| "grad_norm": 3.2607476711273193, | |
| "learning_rate": 5.6526309611002594e-05, | |
| "loss": 2.7008, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.14245014245014245, | |
| "grad_norm": 4.638629913330078, | |
| "learning_rate": 5.327015646150716e-05, | |
| "loss": 3.1067, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14245014245014245, | |
| "eval_loss": 1.8108062744140625, | |
| "eval_runtime": 9.9755, | |
| "eval_samples_per_second": 118.49, | |
| "eval_steps_per_second": 14.836, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.14814814814814814, | |
| "grad_norm": 0.38528233766555786, | |
| "learning_rate": 5e-05, | |
| "loss": 1.3365, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.15384615384615385, | |
| "grad_norm": 0.42146414518356323, | |
| "learning_rate": 4.6729843538492847e-05, | |
| "loss": 1.4096, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.15954415954415954, | |
| "grad_norm": 0.41507962346076965, | |
| "learning_rate": 4.347369038899744e-05, | |
| "loss": 1.3849, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 0.16524216524216523, | |
| "grad_norm": 0.4070434272289276, | |
| "learning_rate": 4.0245483899193595e-05, | |
| "loss": 1.3668, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 0.17094017094017094, | |
| "grad_norm": 0.44120219349861145, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 1.362, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.17663817663817663, | |
| "grad_norm": 0.48712754249572754, | |
| "learning_rate": 3.392802673484193e-05, | |
| "loss": 1.3407, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 0.18233618233618235, | |
| "grad_norm": 0.7083298563957214, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.3465, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 0.18803418803418803, | |
| "grad_norm": 1.1713000535964966, | |
| "learning_rate": 2.7885565489049946e-05, | |
| "loss": 1.6116, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 0.19373219373219372, | |
| "grad_norm": 1.0762337446212769, | |
| "learning_rate": 2.500000000000001e-05, | |
| "loss": 1.6743, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 0.19943019943019943, | |
| "grad_norm": 1.1851356029510498, | |
| "learning_rate": 2.2221488349019903e-05, | |
| "loss": 1.9379, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 2.0452611446380615, | |
| "learning_rate": 1.9561928549563968e-05, | |
| "loss": 2.2891, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 0.21082621082621084, | |
| "grad_norm": 3.2922749519348145, | |
| "learning_rate": 1.703270924499656e-05, | |
| "loss": 2.551, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 0.21652421652421652, | |
| "grad_norm": 0.3146236538887024, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1345, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 0.2222222222222222, | |
| "grad_norm": 0.3033599257469177, | |
| "learning_rate": 1.2408009626051137e-05, | |
| "loss": 1.3129, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 0.22792022792022792, | |
| "grad_norm": 0.30708345770835876, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 1.3669, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.2336182336182336, | |
| "grad_norm": 0.3161381781101227, | |
| "learning_rate": 8.426519384872733e-06, | |
| "loss": 1.3103, | |
| "step": 41 | |
| }, | |
| { | |
| "epoch": 0.23931623931623933, | |
| "grad_norm": 0.35566478967666626, | |
| "learning_rate": 6.698729810778065e-06, | |
| "loss": 1.3513, | |
| "step": 42 | |
| }, | |
| { | |
| "epoch": 0.245014245014245, | |
| "grad_norm": 0.4288330674171448, | |
| "learning_rate": 5.156362923365588e-06, | |
| "loss": 1.367, | |
| "step": 43 | |
| }, | |
| { | |
| "epoch": 0.25071225071225073, | |
| "grad_norm": 0.5417187809944153, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.3153, | |
| "step": 44 | |
| }, | |
| { | |
| "epoch": 0.2564102564102564, | |
| "grad_norm": 0.8956801295280457, | |
| "learning_rate": 2.653493525244721e-06, | |
| "loss": 1.4011, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.2621082621082621, | |
| "grad_norm": 1.123388409614563, | |
| "learning_rate": 1.70370868554659e-06, | |
| "loss": 1.5048, | |
| "step": 46 | |
| }, | |
| { | |
| "epoch": 0.2678062678062678, | |
| "grad_norm": 0.8824982643127441, | |
| "learning_rate": 9.607359798384785e-07, | |
| "loss": 1.6222, | |
| "step": 47 | |
| }, | |
| { | |
| "epoch": 0.27350427350427353, | |
| "grad_norm": 1.4942333698272705, | |
| "learning_rate": 4.277569313094809e-07, | |
| "loss": 2.1323, | |
| "step": 48 | |
| }, | |
| { | |
| "epoch": 0.2792022792022792, | |
| "grad_norm": 2.534534454345703, | |
| "learning_rate": 1.0705383806982606e-07, | |
| "loss": 2.4563, | |
| "step": 49 | |
| }, | |
| { | |
| "epoch": 0.2849002849002849, | |
| "grad_norm": 3.592038631439209, | |
| "learning_rate": 0.0, | |
| "loss": 2.5733, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.2849002849002849, | |
| "eval_loss": 1.7144521474838257, | |
| "eval_runtime": 9.996, | |
| "eval_samples_per_second": 118.247, | |
| "eval_steps_per_second": 14.806, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 7.83042868150272e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |