| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11990407673860912, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002398081534772182, | |
| "eval_loss": 10.374227523803711, | |
| "eval_runtime": 4.7315, | |
| "eval_samples_per_second": 593.897, | |
| "eval_steps_per_second": 74.396, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.023980815347721823, | |
| "grad_norm": 0.027691999450325966, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 10.3744, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.023980815347721823, | |
| "eval_loss": 10.373770713806152, | |
| "eval_runtime": 4.4671, | |
| "eval_samples_per_second": 629.048, | |
| "eval_steps_per_second": 78.799, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.047961630695443645, | |
| "grad_norm": 0.027547860518097878, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 10.3738, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.047961630695443645, | |
| "eval_loss": 10.37330150604248, | |
| "eval_runtime": 4.558, | |
| "eval_samples_per_second": 616.503, | |
| "eval_steps_per_second": 77.227, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07194244604316546, | |
| "grad_norm": 0.030619895085692406, | |
| "learning_rate": 3.705904774487396e-05, | |
| "loss": 10.3732, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07194244604316546, | |
| "eval_loss": 10.372995376586914, | |
| "eval_runtime": 4.6099, | |
| "eval_samples_per_second": 609.561, | |
| "eval_steps_per_second": 76.358, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.09592326139088729, | |
| "grad_norm": 0.029737740755081177, | |
| "learning_rate": 1.0332332985438248e-05, | |
| "loss": 10.373, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.09592326139088729, | |
| "eval_loss": 10.37285327911377, | |
| "eval_runtime": 4.5931, | |
| "eval_samples_per_second": 611.788, | |
| "eval_steps_per_second": 76.637, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.11990407673860912, | |
| "grad_norm": 0.02912091463804245, | |
| "learning_rate": 0.0, | |
| "loss": 10.3727, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11990407673860912, | |
| "eval_loss": 10.372833251953125, | |
| "eval_runtime": 4.5186, | |
| "eval_samples_per_second": 621.881, | |
| "eval_steps_per_second": 77.901, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "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": 10344726528000.0, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |