| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02372479240806643, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002372479240806643, | |
| "grad_norm": 0.04915913566946983, | |
| "learning_rate": 2e-05, | |
| "loss": 10.365, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002372479240806643, | |
| "eval_loss": 10.369232177734375, | |
| "eval_runtime": 0.4229, | |
| "eval_samples_per_second": 420.931, | |
| "eval_steps_per_second": 210.466, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004744958481613286, | |
| "grad_norm": 0.04112568125128746, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3811, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0071174377224199285, | |
| "grad_norm": 0.05735113471746445, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3614, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0071174377224199285, | |
| "eval_loss": 10.369229316711426, | |
| "eval_runtime": 0.4193, | |
| "eval_samples_per_second": 424.514, | |
| "eval_steps_per_second": 212.257, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009489916963226572, | |
| "grad_norm": 0.04733097553253174, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3654, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.011862396204033215, | |
| "grad_norm": 0.055613353848457336, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3715, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014234875444839857, | |
| "grad_norm": 0.05609177052974701, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3717, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014234875444839857, | |
| "eval_loss": 10.369152069091797, | |
| "eval_runtime": 0.4591, | |
| "eval_samples_per_second": 387.73, | |
| "eval_steps_per_second": 193.865, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0166073546856465, | |
| "grad_norm": 0.04348461702466011, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3802, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.018979833926453145, | |
| "grad_norm": 0.05182609334588051, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3752, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.021352313167259787, | |
| "grad_norm": 0.04678908735513687, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3739, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.021352313167259787, | |
| "eval_loss": 10.369029998779297, | |
| "eval_runtime": 0.4202, | |
| "eval_samples_per_second": 423.601, | |
| "eval_steps_per_second": 211.801, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02372479240806643, | |
| "grad_norm": 0.03913729637861252, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3739, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 129309081600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |