| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.1301518438177874, | |
| "eval_steps": 5, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004338394793926247, | |
| "eval_loss": 4.0736517906188965, | |
| "eval_runtime": 11.3009, | |
| "eval_samples_per_second": 8.672, | |
| "eval_steps_per_second": 4.336, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.013015184381778741, | |
| "grad_norm": 5.656111717224121, | |
| "learning_rate": 6e-05, | |
| "loss": 3.6883, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.021691973969631236, | |
| "eval_loss": 3.306220293045044, | |
| "eval_runtime": 11.3027, | |
| "eval_samples_per_second": 8.671, | |
| "eval_steps_per_second": 4.335, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.026030368763557483, | |
| "grad_norm": 2.3464417457580566, | |
| "learning_rate": 0.00012, | |
| "loss": 3.1322, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.039045553145336226, | |
| "grad_norm": 2.036963701248169, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6114, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04338394793926247, | |
| "eval_loss": 2.7751786708831787, | |
| "eval_runtime": 11.3023, | |
| "eval_samples_per_second": 8.671, | |
| "eval_steps_per_second": 4.335, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.052060737527114966, | |
| "grad_norm": 2.3901684284210205, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.6058, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0650759219088937, | |
| "grad_norm": 2.0866892337799072, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.1733, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0650759219088937, | |
| "eval_loss": 2.4747469425201416, | |
| "eval_runtime": 11.2685, | |
| "eval_samples_per_second": 8.697, | |
| "eval_steps_per_second": 4.348, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.07809110629067245, | |
| "grad_norm": 1.4665969610214233, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 2.1652, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.08676789587852494, | |
| "eval_loss": 2.3516483306884766, | |
| "eval_runtime": 11.2826, | |
| "eval_samples_per_second": 8.686, | |
| "eval_steps_per_second": 4.343, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0911062906724512, | |
| "grad_norm": 1.8569259643554688, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 2.2347, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.10412147505422993, | |
| "grad_norm": 1.678497552871704, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.3166, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.10845986984815618, | |
| "eval_loss": 2.2885868549346924, | |
| "eval_runtime": 11.2778, | |
| "eval_samples_per_second": 8.69, | |
| "eval_steps_per_second": 4.345, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.11713665943600868, | |
| "grad_norm": 2.1016781330108643, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 2.0839, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.1301518438177874, | |
| "grad_norm": 2.2135860919952393, | |
| "learning_rate": 0.0, | |
| "loss": 2.411, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.1301518438177874, | |
| "eval_loss": 2.2758893966674805, | |
| "eval_runtime": 11.2913, | |
| "eval_samples_per_second": 8.679, | |
| "eval_steps_per_second": 4.34, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3015894871572480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |