| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0639386189258312, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0012787723785166241, | |
| "eval_loss": 7.340874195098877, | |
| "eval_runtime": 22.2644, | |
| "eval_samples_per_second": 14.822, | |
| "eval_steps_per_second": 7.411, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00639386189258312, | |
| "grad_norm": 4.520059108734131, | |
| "learning_rate": 5e-05, | |
| "loss": 7.3439, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01278772378516624, | |
| "grad_norm": 3.210003614425659, | |
| "learning_rate": 0.0001, | |
| "loss": 6.8713, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01278772378516624, | |
| "eval_loss": 6.917064666748047, | |
| "eval_runtime": 23.1649, | |
| "eval_samples_per_second": 14.246, | |
| "eval_steps_per_second": 7.123, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01918158567774936, | |
| "grad_norm": 3.9829914569854736, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 5.9484, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02557544757033248, | |
| "grad_norm": 4.64760160446167, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.7204, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02557544757033248, | |
| "eval_loss": 5.454164981842041, | |
| "eval_runtime": 23.667, | |
| "eval_samples_per_second": 13.943, | |
| "eval_steps_per_second": 6.972, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0319693094629156, | |
| "grad_norm": 3.8988356590270996, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 4.9349, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03836317135549872, | |
| "grad_norm": 4.145328998565674, | |
| "learning_rate": 5e-05, | |
| "loss": 5.0624, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03836317135549872, | |
| "eval_loss": 4.404156684875488, | |
| "eval_runtime": 23.9237, | |
| "eval_samples_per_second": 13.794, | |
| "eval_steps_per_second": 6.897, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04475703324808184, | |
| "grad_norm": 3.4549756050109863, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 4.0578, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.05115089514066496, | |
| "grad_norm": 4.30155611038208, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.8777, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05115089514066496, | |
| "eval_loss": 3.955080270767212, | |
| "eval_runtime": 24.1388, | |
| "eval_samples_per_second": 13.671, | |
| "eval_steps_per_second": 6.835, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.05754475703324808, | |
| "grad_norm": 3.680908679962158, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.8316, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0639386189258312, | |
| "grad_norm": 3.6002345085144043, | |
| "learning_rate": 0.0, | |
| "loss": 3.7111, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0639386189258312, | |
| "eval_loss": 3.8821768760681152, | |
| "eval_runtime": 24.239, | |
| "eval_samples_per_second": 13.614, | |
| "eval_steps_per_second": 6.807, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8215821130137600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |