| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002965335231147881, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.930670462295763e-05, | |
| "eval_loss": 1.5450586080551147, | |
| "eval_runtime": 276.9831, | |
| "eval_samples_per_second": 25.633, | |
| "eval_steps_per_second": 12.817, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0002965335231147881, | |
| "grad_norm": 1.2492492198944092, | |
| "learning_rate": 5e-05, | |
| "loss": 1.566, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005930670462295762, | |
| "grad_norm": 1.3343446254730225, | |
| "learning_rate": 0.0001, | |
| "loss": 1.4514, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005930670462295762, | |
| "eval_loss": 1.3821200132369995, | |
| "eval_runtime": 279.183, | |
| "eval_samples_per_second": 25.431, | |
| "eval_steps_per_second": 12.716, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008896005693443643, | |
| "grad_norm": 1.9996010065078735, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.4127, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0011861340924591525, | |
| "grad_norm": 1.643600583076477, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2075, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0011861340924591525, | |
| "eval_loss": 1.218291163444519, | |
| "eval_runtime": 282.0831, | |
| "eval_samples_per_second": 25.17, | |
| "eval_steps_per_second": 12.585, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0014826676155739406, | |
| "grad_norm": 1.7878426313400269, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1426, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0017792011386887287, | |
| "grad_norm": 1.7616714239120483, | |
| "learning_rate": 5e-05, | |
| "loss": 1.148, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0017792011386887287, | |
| "eval_loss": 1.153501033782959, | |
| "eval_runtime": 279.9713, | |
| "eval_samples_per_second": 25.36, | |
| "eval_steps_per_second": 12.68, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.002075734661803517, | |
| "grad_norm": 1.5972833633422852, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1512, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.002372268184918305, | |
| "grad_norm": 1.5854142904281616, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1031, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.002372268184918305, | |
| "eval_loss": 1.1262532472610474, | |
| "eval_runtime": 280.072, | |
| "eval_samples_per_second": 25.351, | |
| "eval_steps_per_second": 12.675, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0026688017080330933, | |
| "grad_norm": 1.6224738359451294, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.1091, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.002965335231147881, | |
| "grad_norm": 1.5776338577270508, | |
| "learning_rate": 0.0, | |
| "loss": 1.074, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.002965335231147881, | |
| "eval_loss": 1.1203703880310059, | |
| "eval_runtime": 279.615, | |
| "eval_samples_per_second": 25.392, | |
| "eval_steps_per_second": 12.696, | |
| "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": 2405455154380800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |