| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0029047574713713807, | |
| "eval_steps": 13, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.448096080439437e-05, | |
| "eval_loss": 2.5439507961273193, | |
| "eval_runtime": 163.2893, | |
| "eval_samples_per_second": 34.626, | |
| "eval_steps_per_second": 17.313, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007448096080439438, | |
| "grad_norm": 1.191580891609192, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 2.18, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0009682524904571269, | |
| "eval_loss": 1.761672854423523, | |
| "eval_runtime": 161.8682, | |
| "eval_samples_per_second": 34.93, | |
| "eval_steps_per_second": 17.465, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.0014896192160878876, | |
| "grad_norm": 1.4779833555221558, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 1.7836, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0019365049809142538, | |
| "eval_loss": 1.6129094362258911, | |
| "eval_runtime": 162.5125, | |
| "eval_samples_per_second": 34.791, | |
| "eval_steps_per_second": 17.396, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 0.0022344288241318315, | |
| "grad_norm": 1.2293425798416138, | |
| "learning_rate": 8.263518223330697e-05, | |
| "loss": 1.7103, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0029047574713713807, | |
| "eval_loss": 1.585036277770996, | |
| "eval_runtime": 162.7341, | |
| "eval_samples_per_second": 34.744, | |
| "eval_steps_per_second": 17.372, | |
| "step": 39 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 6796280579751936.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |