| { | |
| "best_metric": 0.019987082897612984, | |
| "best_model_checkpoint": "./checkpoints/easyrec-roberta-base", | |
| "epoch": 1.7954432887568101, | |
| "eval_steps": 1000, | |
| "global_step": 29000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.030955918771669144, | |
| "grad_norm": 37.25, | |
| "learning_rate": 4.9484068020472185e-05, | |
| "loss": 2.3504, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.06191183754333829, | |
| "grad_norm": 27.625, | |
| "learning_rate": 4.896813604094436e-05, | |
| "loss": 2.0019, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.09286775631500743, | |
| "grad_norm": 43.75, | |
| "learning_rate": 4.8452204061416544e-05, | |
| "loss": 1.9156, | |
| "step": 1500 | |
| }, | |
| { | |
| "epoch": 0.12382367508667658, | |
| "grad_norm": 36.75, | |
| "learning_rate": 4.793627208188873e-05, | |
| "loss": 1.8431, | |
| "step": 2000 | |
| }, | |
| { | |
| "epoch": 0.15477959385834572, | |
| "grad_norm": 31.25, | |
| "learning_rate": 4.74203401023609e-05, | |
| "loss": 1.8579, | |
| "step": 2500 | |
| }, | |
| { | |
| "epoch": 0.18573551263001487, | |
| "grad_norm": 27.375, | |
| "learning_rate": 4.6904408122833086e-05, | |
| "loss": 1.8486, | |
| "step": 3000 | |
| }, | |
| { | |
| "epoch": 0.216691431401684, | |
| "grad_norm": 28.5, | |
| "learning_rate": 4.638847614330527e-05, | |
| "loss": 1.771, | |
| "step": 3500 | |
| }, | |
| { | |
| "epoch": 0.24764735017335315, | |
| "grad_norm": 39.75, | |
| "learning_rate": 4.587254416377745e-05, | |
| "loss": 1.7856, | |
| "step": 4000 | |
| }, | |
| { | |
| "epoch": 0.2786032689450223, | |
| "grad_norm": 31.0, | |
| "learning_rate": 4.5356612184249634e-05, | |
| "loss": 1.7762, | |
| "step": 4500 | |
| }, | |
| { | |
| "epoch": 0.30955918771669144, | |
| "grad_norm": 50.75, | |
| "learning_rate": 4.484068020472182e-05, | |
| "loss": 1.7399, | |
| "step": 5000 | |
| }, | |
| { | |
| "epoch": 0.3405151064883606, | |
| "grad_norm": 32.5, | |
| "learning_rate": 4.432474822519399e-05, | |
| "loss": 1.7679, | |
| "step": 5500 | |
| }, | |
| { | |
| "epoch": 0.37147102526002973, | |
| "grad_norm": 31.625, | |
| "learning_rate": 4.3808816245666175e-05, | |
| "loss": 1.7481, | |
| "step": 6000 | |
| }, | |
| { | |
| "epoch": 0.4024269440316989, | |
| "grad_norm": 54.0, | |
| "learning_rate": 4.329288426613836e-05, | |
| "loss": 1.7463, | |
| "step": 6500 | |
| }, | |
| { | |
| "epoch": 0.433382862803368, | |
| "grad_norm": 40.75, | |
| "learning_rate": 4.2776952286610534e-05, | |
| "loss": 1.7458, | |
| "step": 7000 | |
| }, | |
| { | |
| "epoch": 0.46433878157503716, | |
| "grad_norm": 46.5, | |
| "learning_rate": 4.226102030708272e-05, | |
| "loss": 1.7173, | |
| "step": 7500 | |
| }, | |
| { | |
| "epoch": 0.4952947003467063, | |
| "grad_norm": 68.5, | |
| "learning_rate": 4.17450883275549e-05, | |
| "loss": 1.7502, | |
| "step": 8000 | |
| }, | |
| { | |
| "epoch": 0.5262506191183755, | |
| "grad_norm": 41.25, | |
| "learning_rate": 4.1229156348027076e-05, | |
| "loss": 1.7286, | |
| "step": 8500 | |
| }, | |
| { | |
| "epoch": 0.5572065378900446, | |
| "grad_norm": 30.25, | |
| "learning_rate": 4.071322436849926e-05, | |
| "loss": 1.7159, | |
| "step": 9000 | |
| }, | |
| { | |
| "epoch": 0.5881624566617137, | |
| "grad_norm": 35.5, | |
| "learning_rate": 4.019729238897144e-05, | |
| "loss": 1.6927, | |
| "step": 9500 | |
| }, | |
| { | |
| "epoch": 0.6191183754333829, | |
| "grad_norm": 29.75, | |
| "learning_rate": 3.968136040944362e-05, | |
| "loss": 1.7077, | |
| "step": 10000 | |
| }, | |
| { | |
| "epoch": 0.650074294205052, | |
| "grad_norm": 40.5, | |
| "learning_rate": 3.91654284299158e-05, | |
| "loss": 1.6932, | |
| "step": 10500 | |
| }, | |
| { | |
| "epoch": 0.6810302129767212, | |
| "grad_norm": 30.25, | |
| "learning_rate": 3.864949645038798e-05, | |
| "loss": 1.7078, | |
| "step": 11000 | |
| }, | |
| { | |
| "epoch": 0.7119861317483903, | |
| "grad_norm": 31.25, | |
| "learning_rate": 3.813356447086016e-05, | |
| "loss": 1.7004, | |
| "step": 11500 | |
| }, | |
| { | |
| "epoch": 0.7429420505200595, | |
| "grad_norm": 28.75, | |
| "learning_rate": 3.761763249133234e-05, | |
| "loss": 1.6726, | |
| "step": 12000 | |
| }, | |
| { | |
| "epoch": 0.7738979692917286, | |
| "grad_norm": 52.0, | |
| "learning_rate": 3.7101700511804524e-05, | |
| "loss": 1.7026, | |
| "step": 12500 | |
| }, | |
| { | |
| "epoch": 0.8048538880633977, | |
| "grad_norm": 30.375, | |
| "learning_rate": 3.658576853227671e-05, | |
| "loss": 1.6645, | |
| "step": 13000 | |
| }, | |
| { | |
| "epoch": 0.8358098068350669, | |
| "grad_norm": 33.75, | |
| "learning_rate": 3.606983655274889e-05, | |
| "loss": 1.6833, | |
| "step": 13500 | |
| }, | |
| { | |
| "epoch": 0.866765725606736, | |
| "grad_norm": 32.75, | |
| "learning_rate": 3.555390457322107e-05, | |
| "loss": 1.6909, | |
| "step": 14000 | |
| }, | |
| { | |
| "epoch": 0.8977216443784052, | |
| "grad_norm": 49.0, | |
| "learning_rate": 3.503797259369325e-05, | |
| "loss": 1.684, | |
| "step": 14500 | |
| }, | |
| { | |
| "epoch": 0.9286775631500743, | |
| "grad_norm": 52.0, | |
| "learning_rate": 3.452204061416543e-05, | |
| "loss": 1.681, | |
| "step": 15000 | |
| }, | |
| { | |
| "epoch": 0.9596334819217435, | |
| "grad_norm": 38.0, | |
| "learning_rate": 3.4006108634637614e-05, | |
| "loss": 1.672, | |
| "step": 15500 | |
| }, | |
| { | |
| "epoch": 0.9905894006934126, | |
| "grad_norm": 32.75, | |
| "learning_rate": 3.349017665510979e-05, | |
| "loss": 1.6553, | |
| "step": 16000 | |
| }, | |
| { | |
| "epoch": 1.0215453194650816, | |
| "grad_norm": 35.75, | |
| "learning_rate": 3.297424467558197e-05, | |
| "loss": 1.6618, | |
| "step": 16500 | |
| }, | |
| { | |
| "epoch": 1.052501238236751, | |
| "grad_norm": 37.5, | |
| "learning_rate": 3.2458312696054156e-05, | |
| "loss": 1.657, | |
| "step": 17000 | |
| }, | |
| { | |
| "epoch": 1.08345715700842, | |
| "grad_norm": 30.25, | |
| "learning_rate": 3.194238071652633e-05, | |
| "loss": 1.6701, | |
| "step": 17500 | |
| }, | |
| { | |
| "epoch": 1.1144130757800892, | |
| "grad_norm": 32.25, | |
| "learning_rate": 3.1426448736998515e-05, | |
| "loss": 1.6779, | |
| "step": 18000 | |
| }, | |
| { | |
| "epoch": 1.1453689945517582, | |
| "grad_norm": 37.5, | |
| "learning_rate": 3.09105167574707e-05, | |
| "loss": 1.6635, | |
| "step": 18500 | |
| }, | |
| { | |
| "epoch": 1.1763249133234275, | |
| "grad_norm": 30.75, | |
| "learning_rate": 3.0394584777942874e-05, | |
| "loss": 1.664, | |
| "step": 19000 | |
| }, | |
| { | |
| "epoch": 1.2072808320950965, | |
| "grad_norm": 55.75, | |
| "learning_rate": 2.9878652798415056e-05, | |
| "loss": 1.6398, | |
| "step": 19500 | |
| }, | |
| { | |
| "epoch": 1.2382367508667658, | |
| "grad_norm": 51.0, | |
| "learning_rate": 2.936272081888724e-05, | |
| "loss": 1.6424, | |
| "step": 20000 | |
| }, | |
| { | |
| "epoch": 1.2691926696384348, | |
| "grad_norm": 32.0, | |
| "learning_rate": 2.884678883935942e-05, | |
| "loss": 1.6251, | |
| "step": 20500 | |
| }, | |
| { | |
| "epoch": 1.300148588410104, | |
| "grad_norm": 31.5, | |
| "learning_rate": 2.83308568598316e-05, | |
| "loss": 1.6295, | |
| "step": 21000 | |
| }, | |
| { | |
| "epoch": 1.331104507181773, | |
| "grad_norm": 38.75, | |
| "learning_rate": 2.7814924880303784e-05, | |
| "loss": 1.6628, | |
| "step": 21500 | |
| }, | |
| { | |
| "epoch": 1.3620604259534423, | |
| "grad_norm": 54.5, | |
| "learning_rate": 2.729899290077596e-05, | |
| "loss": 1.6579, | |
| "step": 22000 | |
| }, | |
| { | |
| "epoch": 1.3930163447251114, | |
| "grad_norm": 64.5, | |
| "learning_rate": 2.6783060921248143e-05, | |
| "loss": 1.6185, | |
| "step": 22500 | |
| }, | |
| { | |
| "epoch": 1.4239722634967806, | |
| "grad_norm": 30.875, | |
| "learning_rate": 2.6267128941720326e-05, | |
| "loss": 1.6521, | |
| "step": 23000 | |
| }, | |
| { | |
| "epoch": 1.4549281822684497, | |
| "grad_norm": 34.75, | |
| "learning_rate": 2.57511969621925e-05, | |
| "loss": 1.6372, | |
| "step": 23500 | |
| }, | |
| { | |
| "epoch": 1.485884101040119, | |
| "grad_norm": 48.5, | |
| "learning_rate": 2.5235264982664684e-05, | |
| "loss": 1.6597, | |
| "step": 24000 | |
| }, | |
| { | |
| "epoch": 1.516840019811788, | |
| "grad_norm": 31.75, | |
| "learning_rate": 2.4719333003136867e-05, | |
| "loss": 1.6437, | |
| "step": 24500 | |
| }, | |
| { | |
| "epoch": 1.5477959385834572, | |
| "grad_norm": 18.75, | |
| "learning_rate": 2.420340102360905e-05, | |
| "loss": 1.6191, | |
| "step": 25000 | |
| }, | |
| { | |
| "epoch": 1.5787518573551265, | |
| "grad_norm": 26.5, | |
| "learning_rate": 2.368746904408123e-05, | |
| "loss": 1.6564, | |
| "step": 25500 | |
| }, | |
| { | |
| "epoch": 1.6097077761267955, | |
| "grad_norm": 37.5, | |
| "learning_rate": 2.3171537064553412e-05, | |
| "loss": 1.6498, | |
| "step": 26000 | |
| }, | |
| { | |
| "epoch": 1.6406636948984645, | |
| "grad_norm": 42.75, | |
| "learning_rate": 2.265560508502559e-05, | |
| "loss": 1.6201, | |
| "step": 26500 | |
| }, | |
| { | |
| "epoch": 1.6716196136701336, | |
| "grad_norm": 35.5, | |
| "learning_rate": 2.213967310549777e-05, | |
| "loss": 1.6459, | |
| "step": 27000 | |
| }, | |
| { | |
| "epoch": 1.7025755324418028, | |
| "grad_norm": 27.875, | |
| "learning_rate": 2.1623741125969954e-05, | |
| "loss": 1.6636, | |
| "step": 27500 | |
| }, | |
| { | |
| "epoch": 1.733531451213472, | |
| "grad_norm": 33.75, | |
| "learning_rate": 2.1107809146442133e-05, | |
| "loss": 1.6359, | |
| "step": 28000 | |
| }, | |
| { | |
| "epoch": 1.764487369985141, | |
| "grad_norm": 34.75, | |
| "learning_rate": 2.0591877166914312e-05, | |
| "loss": 1.6679, | |
| "step": 28500 | |
| }, | |
| { | |
| "epoch": 1.7954432887568101, | |
| "grad_norm": 27.0, | |
| "learning_rate": 2.0075945187386495e-05, | |
| "loss": 1.6409, | |
| "step": 29000 | |
| } | |
| ], | |
| "logging_steps": 500, | |
| "max_steps": 48456, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 1000, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": false, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 0.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |