| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.015956598053295037, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00031913196106590075, | |
| "eval_loss": 0.6470243334770203, | |
| "eval_runtime": 43.757, | |
| "eval_samples_per_second": 30.167, | |
| "eval_steps_per_second": 15.083, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015956598053295037, | |
| "grad_norm": 0.10389410704374313, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5954, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0031913196106590075, | |
| "grad_norm": 0.10804926604032516, | |
| "learning_rate": 0.0001, | |
| "loss": 0.584, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0031913196106590075, | |
| "eval_loss": 0.6408673524856567, | |
| "eval_runtime": 43.8281, | |
| "eval_samples_per_second": 30.118, | |
| "eval_steps_per_second": 15.059, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004786979415988511, | |
| "grad_norm": 0.13882894814014435, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.603, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006382639221318015, | |
| "grad_norm": 0.1524791419506073, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6305, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.006382639221318015, | |
| "eval_loss": 0.6011084318161011, | |
| "eval_runtime": 43.967, | |
| "eval_samples_per_second": 30.023, | |
| "eval_steps_per_second": 15.011, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.007978299026647519, | |
| "grad_norm": 0.13234758377075195, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.5891, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.009573958831977022, | |
| "grad_norm": 0.1621832549571991, | |
| "learning_rate": 5e-05, | |
| "loss": 0.5783, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.009573958831977022, | |
| "eval_loss": 0.5724042654037476, | |
| "eval_runtime": 44.2025, | |
| "eval_samples_per_second": 29.863, | |
| "eval_steps_per_second": 14.931, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.011169618637306526, | |
| "grad_norm": 0.13507747650146484, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5216, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01276527844263603, | |
| "grad_norm": 0.1474408060312271, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.558, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01276527844263603, | |
| "eval_loss": 0.5630071759223938, | |
| "eval_runtime": 44.2419, | |
| "eval_samples_per_second": 29.836, | |
| "eval_steps_per_second": 14.918, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.014360938247965534, | |
| "grad_norm": 0.1654672771692276, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5653, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.015956598053295037, | |
| "grad_norm": 0.1382376104593277, | |
| "learning_rate": 0.0, | |
| "loss": 0.5764, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.015956598053295037, | |
| "eval_loss": 0.5614041686058044, | |
| "eval_runtime": 43.6709, | |
| "eval_samples_per_second": 30.226, | |
| "eval_steps_per_second": 15.113, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": 2538735384133632.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |