| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003216106260150835, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.2161062601508354e-05, | |
| "grad_norm": 0.037894561886787415, | |
| "learning_rate": 2e-05, | |
| "loss": 10.3721, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.2161062601508354e-05, | |
| "eval_loss": 10.37723159790039, | |
| "eval_runtime": 40.3622, | |
| "eval_samples_per_second": 324.363, | |
| "eval_steps_per_second": 162.181, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.432212520301671e-05, | |
| "grad_norm": 0.03640003129839897, | |
| "learning_rate": 4e-05, | |
| "loss": 10.3779, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.648318780452506e-05, | |
| "grad_norm": 0.0508461557328701, | |
| "learning_rate": 6e-05, | |
| "loss": 10.3819, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.648318780452506e-05, | |
| "eval_loss": 10.37720775604248, | |
| "eval_runtime": 39.8227, | |
| "eval_samples_per_second": 328.757, | |
| "eval_steps_per_second": 164.378, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00012864425040603342, | |
| "grad_norm": 0.0384635366499424, | |
| "learning_rate": 8e-05, | |
| "loss": 10.3668, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00016080531300754176, | |
| "grad_norm": 0.04587297514081001, | |
| "learning_rate": 0.0001, | |
| "loss": 10.3753, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001929663756090501, | |
| "grad_norm": 0.04739292338490486, | |
| "learning_rate": 0.00012, | |
| "loss": 10.3766, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001929663756090501, | |
| "eval_loss": 10.377087593078613, | |
| "eval_runtime": 40.4096, | |
| "eval_samples_per_second": 323.982, | |
| "eval_steps_per_second": 161.991, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00022512743821055849, | |
| "grad_norm": 0.030477037653326988, | |
| "learning_rate": 0.00014, | |
| "loss": 10.3733, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00025728850081206683, | |
| "grad_norm": 0.05945686623454094, | |
| "learning_rate": 0.00016, | |
| "loss": 10.3731, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002894495634135752, | |
| "grad_norm": 0.03877415508031845, | |
| "learning_rate": 0.00018, | |
| "loss": 10.3822, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002894495634135752, | |
| "eval_loss": 10.376890182495117, | |
| "eval_runtime": 40.4574, | |
| "eval_samples_per_second": 323.6, | |
| "eval_steps_per_second": 161.8, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003216106260150835, | |
| "grad_norm": 0.04710560292005539, | |
| "learning_rate": 0.0002, | |
| "loss": 10.3771, | |
| "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": 142239989760.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |