| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.13245033112582782, | |
| "eval_steps": 2, | |
| "global_step": 5, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.026490066225165563, | |
| "grad_norm": 3.16664981842041, | |
| "learning_rate": 1e-05, | |
| "loss": 8.7401, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.026490066225165563, | |
| "eval_loss": 8.819480895996094, | |
| "eval_runtime": 45.1738, | |
| "eval_samples_per_second": 1.417, | |
| "eval_steps_per_second": 0.708, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.052980132450331126, | |
| "grad_norm": 3.264606475830078, | |
| "learning_rate": 2e-05, | |
| "loss": 8.0147, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.052980132450331126, | |
| "eval_loss": 8.68916130065918, | |
| "eval_runtime": 1.1778, | |
| "eval_samples_per_second": 54.34, | |
| "eval_steps_per_second": 27.17, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.07947019867549669, | |
| "grad_norm": 3.1200716495513916, | |
| "learning_rate": 3e-05, | |
| "loss": 8.1948, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.10596026490066225, | |
| "grad_norm": 3.152296304702759, | |
| "learning_rate": 4e-05, | |
| "loss": 8.1883, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.10596026490066225, | |
| "eval_loss": 8.567996978759766, | |
| "eval_runtime": 1.2205, | |
| "eval_samples_per_second": 52.436, | |
| "eval_steps_per_second": 26.218, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.13245033112582782, | |
| "grad_norm": 3.482865810394287, | |
| "learning_rate": 5e-05, | |
| "loss": 8.0298, | |
| "step": 5 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 5, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1640097329971200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |