| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00027750990363468596, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.7750990363468595e-05, | |
| "grad_norm": 3.723160743713379, | |
| "learning_rate": 2e-05, | |
| "loss": 3.0125, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.7750990363468595e-05, | |
| "eval_loss": 3.148585319519043, | |
| "eval_runtime": 453.6228, | |
| "eval_samples_per_second": 33.448, | |
| "eval_steps_per_second": 16.725, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 5.550198072693719e-05, | |
| "grad_norm": 4.302385330200195, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7947, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 8.325297109040578e-05, | |
| "grad_norm": 3.315476655960083, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4969, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 8.325297109040578e-05, | |
| "eval_loss": 3.1033620834350586, | |
| "eval_runtime": 451.8289, | |
| "eval_samples_per_second": 33.581, | |
| "eval_steps_per_second": 16.792, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00011100396145387438, | |
| "grad_norm": 3.2767491340637207, | |
| "learning_rate": 8e-05, | |
| "loss": 2.6356, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00013875495181734298, | |
| "grad_norm": 6.775184631347656, | |
| "learning_rate": 0.0001, | |
| "loss": 4.3685, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00016650594218081157, | |
| "grad_norm": 4.239760875701904, | |
| "learning_rate": 0.00012, | |
| "loss": 2.6721, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00016650594218081157, | |
| "eval_loss": 2.5592315196990967, | |
| "eval_runtime": 455.0905, | |
| "eval_samples_per_second": 33.341, | |
| "eval_steps_per_second": 16.671, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00019425693254428018, | |
| "grad_norm": 4.932956218719482, | |
| "learning_rate": 0.00014, | |
| "loss": 2.863, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00022200792290774876, | |
| "grad_norm": 3.9480109214782715, | |
| "learning_rate": 0.00016, | |
| "loss": 2.3524, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002497589132712174, | |
| "grad_norm": 3.3999762535095215, | |
| "learning_rate": 0.00018, | |
| "loss": 1.7824, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002497589132712174, | |
| "eval_loss": 1.721246361732483, | |
| "eval_runtime": 454.366, | |
| "eval_samples_per_second": 33.394, | |
| "eval_steps_per_second": 16.698, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00027750990363468596, | |
| "grad_norm": 4.732113361358643, | |
| "learning_rate": 0.0002, | |
| "loss": 2.0129, | |
| "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": 500097330708480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |