| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.013169125716376053, | |
| "eval_steps": 9, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00048774539690281675, | |
| "eval_loss": 1.048367977142334, | |
| "eval_runtime": 282.0297, | |
| "eval_samples_per_second": 12.243, | |
| "eval_steps_per_second": 1.532, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014632361907084503, | |
| "grad_norm": 0.37770092487335205, | |
| "learning_rate": 1.5e-05, | |
| "loss": 1.0341, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0029264723814169005, | |
| "grad_norm": 0.4068027436733246, | |
| "learning_rate": 3e-05, | |
| "loss": 1.056, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0043897085721253505, | |
| "grad_norm": 0.5370364189147949, | |
| "learning_rate": 4.5e-05, | |
| "loss": 1.0776, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0043897085721253505, | |
| "eval_loss": 0.9989280104637146, | |
| "eval_runtime": 284.091, | |
| "eval_samples_per_second": 12.155, | |
| "eval_steps_per_second": 1.521, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005852944762833801, | |
| "grad_norm": 0.39467090368270874, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 0.9114, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.007316180953542251, | |
| "grad_norm": 0.472395658493042, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 0.8932, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008779417144250701, | |
| "grad_norm": 0.4325377941131592, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 0.796, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008779417144250701, | |
| "eval_loss": 0.8529807329177856, | |
| "eval_runtime": 284.0503, | |
| "eval_samples_per_second": 12.156, | |
| "eval_steps_per_second": 1.521, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.010242653334959152, | |
| "grad_norm": 0.4993043541908264, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 0.8698, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.011705889525667602, | |
| "grad_norm": 0.4442359507083893, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 0.6909, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.013169125716376053, | |
| "grad_norm": 0.4680705666542053, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 0.8662, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.013169125716376053, | |
| "eval_loss": 0.8155685067176819, | |
| "eval_runtime": 284.0968, | |
| "eval_samples_per_second": 12.154, | |
| "eval_steps_per_second": 1.521, | |
| "step": 27 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.299087963960115e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |