| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.004410629617377881, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00014702098724592936, | |
| "eval_loss": 2.663548231124878, | |
| "eval_runtime": 38.5641, | |
| "eval_samples_per_second": 74.266, | |
| "eval_steps_per_second": 37.133, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0004410629617377881, | |
| "grad_norm": 5.5260009765625, | |
| "learning_rate": 3e-05, | |
| "loss": 10.6338, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008821259234755762, | |
| "grad_norm": 4.263761043548584, | |
| "learning_rate": 6e-05, | |
| "loss": 11.0809, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0011761678979674349, | |
| "eval_loss": 2.6338651180267334, | |
| "eval_runtime": 37.6305, | |
| "eval_samples_per_second": 76.109, | |
| "eval_steps_per_second": 38.054, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013231888852133643, | |
| "grad_norm": 4.422386169433594, | |
| "learning_rate": 9e-05, | |
| "loss": 11.002, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0017642518469511523, | |
| "grad_norm": 5.122983932495117, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 10.9766, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0022053148086889404, | |
| "grad_norm": 3.5707857608795166, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 10.5283, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0023523357959348698, | |
| "eval_loss": 2.5702929496765137, | |
| "eval_runtime": 37.7442, | |
| "eval_samples_per_second": 75.879, | |
| "eval_steps_per_second": 37.94, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0026463777704267286, | |
| "grad_norm": 4.648046970367432, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 10.5752, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0030874407321645164, | |
| "grad_norm": 4.9672956466674805, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 10.0353, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0035285036939023046, | |
| "grad_norm": 4.531546115875244, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 10.1832, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0035285036939023046, | |
| "eval_loss": 2.53702712059021, | |
| "eval_runtime": 37.7096, | |
| "eval_samples_per_second": 75.949, | |
| "eval_steps_per_second": 37.974, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0039695666556400925, | |
| "grad_norm": 6.2528300285339355, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 10.3929, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.004410629617377881, | |
| "grad_norm": 4.932206153869629, | |
| "learning_rate": 0.0, | |
| "loss": 10.4641, | |
| "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": 149811841990656.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |