| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00210737052842316, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 4.21474105684632e-05, | |
| "eval_loss": 0.9627321362495422, | |
| "eval_runtime": 1144.236, | |
| "eval_samples_per_second": 8.731, | |
| "eval_steps_per_second": 4.365, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000210737052842316, | |
| "grad_norm": 3.8283772468566895, | |
| "learning_rate": 5e-05, | |
| "loss": 3.9116, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.000421474105684632, | |
| "grad_norm": 4.155479907989502, | |
| "learning_rate": 0.0001, | |
| "loss": 3.9087, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000421474105684632, | |
| "eval_loss": 0.9144762754440308, | |
| "eval_runtime": 1151.498, | |
| "eval_samples_per_second": 8.676, | |
| "eval_steps_per_second": 4.338, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.000632211158526948, | |
| "grad_norm": 4.6668806076049805, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.7414, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.000842948211369264, | |
| "grad_norm": 3.779848575592041, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 3.5996, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.000842948211369264, | |
| "eval_loss": 0.8836379051208496, | |
| "eval_runtime": 1149.5028, | |
| "eval_samples_per_second": 8.691, | |
| "eval_steps_per_second": 4.345, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00105368526421158, | |
| "grad_norm": 4.130110263824463, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 3.4654, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.001264422317053896, | |
| "grad_norm": 3.261793613433838, | |
| "learning_rate": 5e-05, | |
| "loss": 3.3791, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001264422317053896, | |
| "eval_loss": 0.8699796199798584, | |
| "eval_runtime": 1150.77, | |
| "eval_samples_per_second": 8.681, | |
| "eval_steps_per_second": 4.341, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.001475159369896212, | |
| "grad_norm": 3.957169771194458, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 3.5432, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.001685896422738528, | |
| "grad_norm": 3.976745843887329, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 3.3801, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001685896422738528, | |
| "eval_loss": 0.8637235164642334, | |
| "eval_runtime": 1152.7349, | |
| "eval_samples_per_second": 8.666, | |
| "eval_steps_per_second": 4.333, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.001896633475580844, | |
| "grad_norm": 4.84131383895874, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 3.6084, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.00210737052842316, | |
| "grad_norm": 3.9473683834075928, | |
| "learning_rate": 0.0, | |
| "loss": 3.4833, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.00210737052842316, | |
| "eval_loss": 0.8623529672622681, | |
| "eval_runtime": 1152.6945, | |
| "eval_samples_per_second": 8.667, | |
| "eval_steps_per_second": 4.333, | |
| "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": 1.7219980646940672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |