| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0021749768908705344, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.349953781741069e-05, | |
| "eval_loss": 0.7465932369232178, | |
| "eval_runtime": 324.7203, | |
| "eval_samples_per_second": 29.81, | |
| "eval_steps_per_second": 14.905, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00021749768908705346, | |
| "grad_norm": 0.3783012926578522, | |
| "learning_rate": 5e-05, | |
| "loss": 0.7311, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004349953781741069, | |
| "grad_norm": 0.41249537467956543, | |
| "learning_rate": 0.0001, | |
| "loss": 0.7084, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0004349953781741069, | |
| "eval_loss": 0.7224622368812561, | |
| "eval_runtime": 334.342, | |
| "eval_samples_per_second": 28.952, | |
| "eval_steps_per_second": 14.476, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0006524930672611604, | |
| "grad_norm": 0.366901159286499, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.6685, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0008699907563482138, | |
| "grad_norm": 0.4033157229423523, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.6795, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0008699907563482138, | |
| "eval_loss": 0.6729934215545654, | |
| "eval_runtime": 334.9518, | |
| "eval_samples_per_second": 28.9, | |
| "eval_steps_per_second": 14.45, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010874884454352672, | |
| "grad_norm": 0.41979432106018066, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.6557, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0013049861345223207, | |
| "grad_norm": 0.431514710187912, | |
| "learning_rate": 5e-05, | |
| "loss": 0.6638, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0013049861345223207, | |
| "eval_loss": 0.648958683013916, | |
| "eval_runtime": 334.9897, | |
| "eval_samples_per_second": 28.896, | |
| "eval_steps_per_second": 14.448, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001522483823609374, | |
| "grad_norm": 0.422538697719574, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.6469, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.0017399815126964277, | |
| "grad_norm": 0.42244553565979004, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.629, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0017399815126964277, | |
| "eval_loss": 0.6393447518348694, | |
| "eval_runtime": 334.8479, | |
| "eval_samples_per_second": 28.909, | |
| "eval_steps_per_second": 14.454, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0019574792017834812, | |
| "grad_norm": 0.43721675872802734, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.6313, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0021749768908705344, | |
| "grad_norm": 0.4112253189086914, | |
| "learning_rate": 0.0, | |
| "loss": 0.6377, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0021749768908705344, | |
| "eval_loss": 0.6375181078910828, | |
| "eval_runtime": 334.4333, | |
| "eval_samples_per_second": 28.944, | |
| "eval_steps_per_second": 14.472, | |
| "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": 2506761386852352.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |