| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0016332530317259401, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00016332530317259402, | |
| "grad_norm": 1.6314306259155273, | |
| "learning_rate": 2e-05, | |
| "loss": 2.0098, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00016332530317259402, | |
| "eval_loss": 2.5260355472564697, | |
| "eval_runtime": 87.5872, | |
| "eval_samples_per_second": 29.434, | |
| "eval_steps_per_second": 14.717, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00032665060634518803, | |
| "grad_norm": 6.0017290115356445, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7205, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0004899759095177821, | |
| "grad_norm": 1.6689376831054688, | |
| "learning_rate": 6e-05, | |
| "loss": 1.6295, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0004899759095177821, | |
| "eval_loss": 2.504948616027832, | |
| "eval_runtime": 86.3813, | |
| "eval_samples_per_second": 29.844, | |
| "eval_steps_per_second": 14.922, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006533012126903761, | |
| "grad_norm": 2.398402690887451, | |
| "learning_rate": 8e-05, | |
| "loss": 2.1467, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0008166265158629701, | |
| "grad_norm": 1.7397522926330566, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3347, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009799518190355642, | |
| "grad_norm": 0.6764419674873352, | |
| "learning_rate": 0.00012, | |
| "loss": 1.818, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009799518190355642, | |
| "eval_loss": 2.405771493911743, | |
| "eval_runtime": 86.3836, | |
| "eval_samples_per_second": 29.844, | |
| "eval_steps_per_second": 14.922, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011432771222081581, | |
| "grad_norm": 1.03862464427948, | |
| "learning_rate": 0.00014, | |
| "loss": 2.2014, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0013066024253807521, | |
| "grad_norm": 1.6394354104995728, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1604, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0014699277285533461, | |
| "grad_norm": 4.608993053436279, | |
| "learning_rate": 0.00018, | |
| "loss": 3.6426, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0014699277285533461, | |
| "eval_loss": 2.279655933380127, | |
| "eval_runtime": 86.6356, | |
| "eval_samples_per_second": 29.757, | |
| "eval_steps_per_second": 14.878, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0016332530317259401, | |
| "grad_norm": 1.063519835472107, | |
| "learning_rate": 0.0002, | |
| "loss": 1.8754, | |
| "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": 332529571725312.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |