| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.08869179600886919, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0017738359201773836, | |
| "eval_loss": 3.022266149520874, | |
| "eval_runtime": 6.5882, | |
| "eval_samples_per_second": 36.125, | |
| "eval_steps_per_second": 18.062, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008869179600886918, | |
| "grad_norm": 5.320457458496094, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0138, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.017738359201773836, | |
| "grad_norm": 2.8197145462036133, | |
| "learning_rate": 0.0001, | |
| "loss": 2.822, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.017738359201773836, | |
| "eval_loss": 2.6108148097991943, | |
| "eval_runtime": 6.5132, | |
| "eval_samples_per_second": 36.541, | |
| "eval_steps_per_second": 18.271, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.026607538802660754, | |
| "grad_norm": 2.1979382038116455, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4739, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.03547671840354767, | |
| "grad_norm": 1.8390735387802124, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.913, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03547671840354767, | |
| "eval_loss": 1.6460188627243042, | |
| "eval_runtime": 6.5021, | |
| "eval_samples_per_second": 36.604, | |
| "eval_steps_per_second": 18.302, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.04434589800443459, | |
| "grad_norm": 1.8857166767120361, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.5065, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.05321507760532151, | |
| "grad_norm": 1.7874138355255127, | |
| "learning_rate": 5e-05, | |
| "loss": 1.379, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.05321507760532151, | |
| "eval_loss": 1.2987817525863647, | |
| "eval_runtime": 6.5243, | |
| "eval_samples_per_second": 36.479, | |
| "eval_steps_per_second": 18.239, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.06208425720620843, | |
| "grad_norm": 1.5843703746795654, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.2094, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.07095343680709534, | |
| "grad_norm": 1.7861342430114746, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1988, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07095343680709534, | |
| "eval_loss": 1.1790827512741089, | |
| "eval_runtime": 6.5662, | |
| "eval_samples_per_second": 36.246, | |
| "eval_steps_per_second": 18.123, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.07982261640798226, | |
| "grad_norm": 1.3379504680633545, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.2199, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.08869179600886919, | |
| "grad_norm": 1.4290637969970703, | |
| "learning_rate": 0.0, | |
| "loss": 1.2658, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.08869179600886919, | |
| "eval_loss": 1.1593819856643677, | |
| "eval_runtime": 6.4443, | |
| "eval_samples_per_second": 36.932, | |
| "eval_steps_per_second": 18.466, | |
| "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": 1278959891251200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |