| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9569377990430622, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.019138755980861243, | |
| "eval_loss": 0.7566470503807068, | |
| "eval_runtime": 4.1261, | |
| "eval_samples_per_second": 5.574, | |
| "eval_steps_per_second": 2.908, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.09569377990430622, | |
| "grad_norm": 0.9212210774421692, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6801, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.19138755980861244, | |
| "grad_norm": 0.8981757760047913, | |
| "learning_rate": 0.0001, | |
| "loss": 0.61, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.19138755980861244, | |
| "eval_loss": 0.4450052082538605, | |
| "eval_runtime": 4.3641, | |
| "eval_samples_per_second": 5.27, | |
| "eval_steps_per_second": 2.75, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.28708133971291866, | |
| "grad_norm": 0.5699931383132935, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3297, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.3827751196172249, | |
| "grad_norm": 0.4436829090118408, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.1859, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.3827751196172249, | |
| "eval_loss": 0.1693412810564041, | |
| "eval_runtime": 4.4767, | |
| "eval_samples_per_second": 5.138, | |
| "eval_steps_per_second": 2.681, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.4784688995215311, | |
| "grad_norm": 0.5025739073753357, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.146, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.5741626794258373, | |
| "grad_norm": 0.4182732403278351, | |
| "learning_rate": 5e-05, | |
| "loss": 0.13, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.5741626794258373, | |
| "eval_loss": 0.12438074499368668, | |
| "eval_runtime": 4.5387, | |
| "eval_samples_per_second": 5.068, | |
| "eval_steps_per_second": 2.644, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.6698564593301436, | |
| "grad_norm": 0.4144364595413208, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1074, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.7655502392344498, | |
| "grad_norm": 0.41118383407592773, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1009, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.7655502392344498, | |
| "eval_loss": 0.11148104816675186, | |
| "eval_runtime": 4.5675, | |
| "eval_samples_per_second": 5.036, | |
| "eval_steps_per_second": 2.627, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.861244019138756, | |
| "grad_norm": 0.33219197392463684, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.1239, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.9569377990430622, | |
| "grad_norm": 0.446623831987381, | |
| "learning_rate": 0.0, | |
| "loss": 0.1281, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.9569377990430622, | |
| "eval_loss": 0.10937495529651642, | |
| "eval_runtime": 4.5804, | |
| "eval_samples_per_second": 5.021, | |
| "eval_steps_per_second": 2.62, | |
| "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": 1.84956424814592e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |