| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9957805907172996, | |
| "eval_steps": 500, | |
| "global_step": 118, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.008438818565400843, | |
| "grad_norm": 1.022000789642334, | |
| "learning_rate": 2.4999999999999998e-05, | |
| "loss": 2.86, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.04219409282700422, | |
| "grad_norm": 1.4761569499969482, | |
| "learning_rate": 0.000125, | |
| "loss": 2.8149, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08438818565400844, | |
| "grad_norm": 2.290438413619995, | |
| "learning_rate": 0.00025, | |
| "loss": 2.5283, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12658227848101267, | |
| "grad_norm": 5.928793430328369, | |
| "learning_rate": 0.0002994074763922825, | |
| "loss": 1.6863, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.16877637130801687, | |
| "grad_norm": 0.9887209534645081, | |
| "learning_rate": 0.0002958034371120616, | |
| "loss": 1.4771, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.2109704641350211, | |
| "grad_norm": 0.7580465078353882, | |
| "learning_rate": 0.000289003441114775, | |
| "loss": 1.3231, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.25316455696202533, | |
| "grad_norm": 0.5388275384902954, | |
| "learning_rate": 0.0002791565417651033, | |
| "loss": 1.2578, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.29535864978902954, | |
| "grad_norm": 0.5278171896934509, | |
| "learning_rate": 0.00026647857940770634, | |
| "loss": 1.1985, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.33755274261603374, | |
| "grad_norm": 0.31164848804473877, | |
| "learning_rate": 0.0002512474502277316, | |
| "loss": 1.178, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.379746835443038, | |
| "grad_norm": 0.22269943356513977, | |
| "learning_rate": 0.00023379701487054785, | |
| "loss": 1.1526, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4219409282700422, | |
| "grad_norm": 0.220732182264328, | |
| "learning_rate": 0.00021450978034147806, | |
| "loss": 1.134, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.4641350210970464, | |
| "grad_norm": 0.2316388487815857, | |
| "learning_rate": 0.00019380851559554636, | |
| "loss": 1.1167, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5063291139240507, | |
| "grad_norm": 0.2175298035144806, | |
| "learning_rate": 0.00017214698460037218, | |
| "loss": 1.1102, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5485232067510548, | |
| "grad_norm": 0.21935291588306427, | |
| "learning_rate": 0.00015, | |
| "loss": 1.0942, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.5907172995780591, | |
| "grad_norm": 0.2013280689716339, | |
| "learning_rate": 0.00012785301539962782, | |
| "loss": 1.0947, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6329113924050633, | |
| "grad_norm": 0.18674449622631073, | |
| "learning_rate": 0.00010619148440445364, | |
| "loss": 1.0888, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.6751054852320675, | |
| "grad_norm": 0.21201685070991516, | |
| "learning_rate": 8.549021965852197e-05, | |
| "loss": 1.0819, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7172995780590717, | |
| "grad_norm": 0.19578513503074646, | |
| "learning_rate": 6.620298512945214e-05, | |
| "loss": 1.0722, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.759493670886076, | |
| "grad_norm": 0.19662944972515106, | |
| "learning_rate": 4.8752549772268444e-05, | |
| "loss": 1.0615, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8016877637130801, | |
| "grad_norm": 0.20801547169685364, | |
| "learning_rate": 3.352142059229365e-05, | |
| "loss": 1.0642, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8438818565400844, | |
| "grad_norm": 0.18992270529270172, | |
| "learning_rate": 2.0843458234896666e-05, | |
| "loss": 1.0775, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.8860759493670886, | |
| "grad_norm": 0.21922025084495544, | |
| "learning_rate": 1.0996558885224993e-05, | |
| "loss": 1.0757, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.9282700421940928, | |
| "grad_norm": 0.18345749378204346, | |
| "learning_rate": 4.1965628879383875e-06, | |
| "loss": 1.0654, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.9704641350210971, | |
| "grad_norm": 0.19231846928596497, | |
| "learning_rate": 5.925236077174655e-07, | |
| "loss": 1.075, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 0.9957805907172996, | |
| "eval_loss": 1.6381601095199585, | |
| "eval_runtime": 1.1564, | |
| "eval_samples_per_second": 1.729, | |
| "eval_steps_per_second": 0.865, | |
| "step": 118 | |
| }, | |
| { | |
| "epoch": 0.9957805907172996, | |
| "step": 118, | |
| "total_flos": 3.48383355932246e+17, | |
| "train_loss": 1.291591884726185, | |
| "train_runtime": 1283.2771, | |
| "train_samples_per_second": 5.898, | |
| "train_steps_per_second": 0.092 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 118, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.48383355932246e+17, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |