| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0012362314719808138, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.4724629439616273e-05, | |
| "eval_loss": 7.831309795379639, | |
| "eval_runtime": 1144.6074, | |
| "eval_samples_per_second": 14.878, | |
| "eval_steps_per_second": 7.439, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00012362314719808137, | |
| "grad_norm": 6.500582695007324, | |
| "learning_rate": 5e-05, | |
| "loss": 8.1156, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00024724629439616273, | |
| "grad_norm": 6.574873924255371, | |
| "learning_rate": 0.0001, | |
| "loss": 6.4498, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00024724629439616273, | |
| "eval_loss": 5.1529107093811035, | |
| "eval_runtime": 1151.9378, | |
| "eval_samples_per_second": 14.784, | |
| "eval_steps_per_second": 7.392, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003708694415942441, | |
| "grad_norm": 8.13021469116211, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.7931, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0004944925887923255, | |
| "grad_norm": 6.818072319030762, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.3798, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0004944925887923255, | |
| "eval_loss": 0.8881871104240417, | |
| "eval_runtime": 1151.8026, | |
| "eval_samples_per_second": 14.786, | |
| "eval_steps_per_second": 7.393, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0006181157359904069, | |
| "grad_norm": 4.882168292999268, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.9035, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0007417388831884882, | |
| "grad_norm": 2.6614863872528076, | |
| "learning_rate": 5e-05, | |
| "loss": 0.3125, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0007417388831884882, | |
| "eval_loss": 0.48977532982826233, | |
| "eval_runtime": 1152.265, | |
| "eval_samples_per_second": 14.78, | |
| "eval_steps_per_second": 7.39, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0008653620303865696, | |
| "grad_norm": 10.399094581604004, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.5635, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.000988985177584651, | |
| "grad_norm": 3.535245418548584, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1906, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.000988985177584651, | |
| "eval_loss": 0.3746371567249298, | |
| "eval_runtime": 1149.4454, | |
| "eval_samples_per_second": 14.816, | |
| "eval_steps_per_second": 7.408, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0011126083247827323, | |
| "grad_norm": 9.233739852905273, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5945, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0012362314719808138, | |
| "grad_norm": 8.951319694519043, | |
| "learning_rate": 0.0, | |
| "loss": 0.4922, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0012362314719808138, | |
| "eval_loss": 0.34176287055015564, | |
| "eval_runtime": 1153.5101, | |
| "eval_samples_per_second": 14.764, | |
| "eval_steps_per_second": 7.382, | |
| "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": 9247821240729600.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |