| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03418803418803419, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0006837606837606838, | |
| "eval_loss": 2.725843906402588, | |
| "eval_runtime": 38.5396, | |
| "eval_samples_per_second": 15.984, | |
| "eval_steps_per_second": 7.992, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003418803418803419, | |
| "grad_norm": 1.229407787322998, | |
| "learning_rate": 5e-05, | |
| "loss": 2.7415, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.006837606837606838, | |
| "grad_norm": 1.3119993209838867, | |
| "learning_rate": 0.0001, | |
| "loss": 2.6879, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006837606837606838, | |
| "eval_loss": 2.4666662216186523, | |
| "eval_runtime": 39.1858, | |
| "eval_samples_per_second": 15.72, | |
| "eval_steps_per_second": 7.86, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010256410256410256, | |
| "grad_norm": 1.5256223678588867, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.2302, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.013675213675213675, | |
| "grad_norm": 1.3861064910888672, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1009, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.013675213675213675, | |
| "eval_loss": 2.136064291000366, | |
| "eval_runtime": 39.9849, | |
| "eval_samples_per_second": 15.406, | |
| "eval_steps_per_second": 7.703, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.017094017094017096, | |
| "grad_norm": 1.7798161506652832, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.1197, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.020512820512820513, | |
| "grad_norm": 1.1841003894805908, | |
| "learning_rate": 5e-05, | |
| "loss": 1.9384, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.020512820512820513, | |
| "eval_loss": 2.0720198154449463, | |
| "eval_runtime": 39.64, | |
| "eval_samples_per_second": 15.54, | |
| "eval_steps_per_second": 7.77, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.023931623931623933, | |
| "grad_norm": 1.155068278312683, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 2.2319, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.02735042735042735, | |
| "grad_norm": 1.7004833221435547, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 2.1117, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.02735042735042735, | |
| "eval_loss": 2.0498950481414795, | |
| "eval_runtime": 39.8629, | |
| "eval_samples_per_second": 15.453, | |
| "eval_steps_per_second": 7.726, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.03076923076923077, | |
| "grad_norm": 1.8769172430038452, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.9793, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "grad_norm": 1.4272596836090088, | |
| "learning_rate": 0.0, | |
| "loss": 1.8624, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.03418803418803419, | |
| "eval_loss": 2.0455269813537598, | |
| "eval_runtime": 39.299, | |
| "eval_samples_per_second": 15.675, | |
| "eval_steps_per_second": 7.837, | |
| "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": 8673009309057024.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |