| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0009328738929410598, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 9.328738929410599e-05, | |
| "grad_norm": 2.6640608310699463, | |
| "learning_rate": 1e-05, | |
| "loss": 5.3987, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 9.328738929410599e-05, | |
| "eval_loss": 6.5732855796813965, | |
| "eval_runtime": 669.181, | |
| "eval_samples_per_second": 26.981, | |
| "eval_steps_per_second": 13.491, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00018657477858821198, | |
| "grad_norm": 2.5947372913360596, | |
| "learning_rate": 2e-05, | |
| "loss": 6.4017, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00027986216788231794, | |
| "grad_norm": 2.898524284362793, | |
| "learning_rate": 3e-05, | |
| "loss": 6.177, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00027986216788231794, | |
| "eval_loss": 6.384002685546875, | |
| "eval_runtime": 539.2673, | |
| "eval_samples_per_second": 33.481, | |
| "eval_steps_per_second": 16.741, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00037314955717642395, | |
| "grad_norm": 2.396655797958374, | |
| "learning_rate": 4e-05, | |
| "loss": 4.6442, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0004664369464705299, | |
| "grad_norm": 3.150291681289673, | |
| "learning_rate": 5e-05, | |
| "loss": 6.5308, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005597243357646359, | |
| "grad_norm": 2.6992385387420654, | |
| "learning_rate": 6e-05, | |
| "loss": 6.1804, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005597243357646359, | |
| "eval_loss": 5.969189167022705, | |
| "eval_runtime": 539.4806, | |
| "eval_samples_per_second": 33.467, | |
| "eval_steps_per_second": 16.735, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0006530117250587419, | |
| "grad_norm": 3.2998745441436768, | |
| "learning_rate": 7e-05, | |
| "loss": 5.9918, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0007462991143528479, | |
| "grad_norm": 3.2680015563964844, | |
| "learning_rate": 8e-05, | |
| "loss": 6.1079, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0008395865036469539, | |
| "grad_norm": 4.798489570617676, | |
| "learning_rate": 9e-05, | |
| "loss": 5.3533, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0008395865036469539, | |
| "eval_loss": 4.777524471282959, | |
| "eval_runtime": 539.4964, | |
| "eval_samples_per_second": 33.466, | |
| "eval_steps_per_second": 16.734, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0009328738929410598, | |
| "grad_norm": 3.5619800090789795, | |
| "learning_rate": 0.0001, | |
| "loss": 5.2863, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0281552671932416e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |