| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015772870662460567, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0015772870662460567, | |
| "grad_norm": 0.05421409383416176, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015772870662460567, | |
| "eval_loss": 10.378344535827637, | |
| "eval_runtime": 0.957, | |
| "eval_samples_per_second": 278.992, | |
| "eval_steps_per_second": 140.018, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0031545741324921135, | |
| "grad_norm": 0.06451243162155151, | |
| "learning_rate": 4e-05, | |
| "loss": 10.378, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00473186119873817, | |
| "grad_norm": 0.053572166711091995, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3766, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00473186119873817, | |
| "eval_loss": 10.37829875946045, | |
| "eval_runtime": 0.9721, | |
| "eval_samples_per_second": 274.671, | |
| "eval_steps_per_second": 137.85, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006309148264984227, | |
| "grad_norm": 0.06943820416927338, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3774, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007886435331230283, | |
| "grad_norm": 0.06262843310832977, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3788, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00946372239747634, | |
| "grad_norm": 0.05760049447417259, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3752, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00946372239747634, | |
| "eval_loss": 10.378085136413574, | |
| "eval_runtime": 0.9756, | |
| "eval_samples_per_second": 273.679, | |
| "eval_steps_per_second": 137.352, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011041009463722398, | |
| "grad_norm": 0.057022251188755035, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3779, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.012618296529968454, | |
| "grad_norm": 0.07072316110134125, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3768, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.014195583596214511, | |
| "grad_norm": 0.05467568710446358, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3849, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014195583596214511, | |
| "eval_loss": 10.37771987915039, | |
| "eval_runtime": 0.9692, | |
| "eval_samples_per_second": 275.493, | |
| "eval_steps_per_second": 138.262, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.015772870662460567, | |
| "grad_norm": 0.06076139211654663, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3778, | |
| "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": 248919982080.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |