| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03673094582185491, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001224364860728497, | |
| "eval_loss": 4.179067134857178, | |
| "eval_runtime": 11.5856, | |
| "eval_samples_per_second": 29.692, | |
| "eval_steps_per_second": 14.846, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036730945821854912, | |
| "grad_norm": 1.8443092107772827, | |
| "learning_rate": 4e-05, | |
| "loss": 16.3145, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.006121824303642486, | |
| "eval_loss": 4.167567253112793, | |
| "eval_runtime": 11.5826, | |
| "eval_samples_per_second": 29.7, | |
| "eval_steps_per_second": 14.85, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0073461891643709825, | |
| "grad_norm": 1.8797963857650757, | |
| "learning_rate": 8e-05, | |
| "loss": 16.2943, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.011019283746556474, | |
| "grad_norm": 2.1711182594299316, | |
| "learning_rate": 0.00012, | |
| "loss": 16.6409, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.012243648607284972, | |
| "eval_loss": 4.100686550140381, | |
| "eval_runtime": 11.5886, | |
| "eval_samples_per_second": 29.684, | |
| "eval_steps_per_second": 14.842, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.014692378328741965, | |
| "grad_norm": 1.7879647016525269, | |
| "learning_rate": 0.00016, | |
| "loss": 16.0696, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.018365472910927456, | |
| "grad_norm": 1.9737204313278198, | |
| "learning_rate": 0.0002, | |
| "loss": 16.1788, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.018365472910927456, | |
| "eval_loss": 3.9727108478546143, | |
| "eval_runtime": 11.5897, | |
| "eval_samples_per_second": 29.682, | |
| "eval_steps_per_second": 14.841, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02203856749311295, | |
| "grad_norm": 1.859694480895996, | |
| "learning_rate": 0.00018090169943749476, | |
| "loss": 16.0224, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.024487297214569943, | |
| "eval_loss": 3.8249597549438477, | |
| "eval_runtime": 11.5654, | |
| "eval_samples_per_second": 29.744, | |
| "eval_steps_per_second": 14.872, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.025711662075298437, | |
| "grad_norm": 1.2232089042663574, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 15.1654, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.02938475665748393, | |
| "grad_norm": 1.4554587602615356, | |
| "learning_rate": 6.909830056250527e-05, | |
| "loss": 14.8155, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.030609121518212427, | |
| "eval_loss": 3.7654643058776855, | |
| "eval_runtime": 11.5619, | |
| "eval_samples_per_second": 29.753, | |
| "eval_steps_per_second": 14.876, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03305785123966942, | |
| "grad_norm": 1.4697390794754028, | |
| "learning_rate": 1.9098300562505266e-05, | |
| "loss": 15.2675, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.03673094582185491, | |
| "grad_norm": 1.2916182279586792, | |
| "learning_rate": 0.0, | |
| "loss": 14.5486, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03673094582185491, | |
| "eval_loss": 3.7533998489379883, | |
| "eval_runtime": 11.5608, | |
| "eval_samples_per_second": 29.756, | |
| "eval_steps_per_second": 14.878, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 15, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 258586391347200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |