| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.6734006734006734, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003367003367003367, | |
| "eval_loss": 0.27984634041786194, | |
| "eval_runtime": 6.4498, | |
| "eval_samples_per_second": 19.38, | |
| "eval_steps_per_second": 9.768, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.03367003367003367, | |
| "grad_norm": 0.02833857573568821, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0902, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.06734006734006734, | |
| "grad_norm": 0.0009272642200812697, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0001, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.10101010101010101, | |
| "grad_norm": 0.0006098205922171474, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.13468013468013468, | |
| "grad_norm": 0.0002674128918442875, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16835016835016836, | |
| "grad_norm": 0.00012873827654402703, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.16835016835016836, | |
| "eval_loss": 3.838794327748474e-06, | |
| "eval_runtime": 5.0581, | |
| "eval_samples_per_second": 24.713, | |
| "eval_steps_per_second": 12.455, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.20202020202020202, | |
| "grad_norm": 9.056493581738323e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.2356902356902357, | |
| "grad_norm": 7.241158891702071e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.26936026936026936, | |
| "grad_norm": 5.9241370763629675e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.30303030303030304, | |
| "grad_norm": 4.677807373809628e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.3367003367003367, | |
| "grad_norm": 4.309026189730503e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.3367003367003367, | |
| "eval_loss": 1.5293666137949913e-06, | |
| "eval_runtime": 5.0843, | |
| "eval_samples_per_second": 24.585, | |
| "eval_steps_per_second": 12.391, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.37037037037037035, | |
| "grad_norm": 3.9325928810285404e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.40404040404040403, | |
| "grad_norm": 3.4849592339014634e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.4377104377104377, | |
| "grad_norm": 3.0408471502596512e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.4713804713804714, | |
| "grad_norm": 2.9038872526143678e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.5050505050505051, | |
| "grad_norm": 2.3728689484414645e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5050505050505051, | |
| "eval_loss": 9.585951374901924e-07, | |
| "eval_runtime": 5.0581, | |
| "eval_samples_per_second": 24.713, | |
| "eval_steps_per_second": 12.455, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.5387205387205387, | |
| "grad_norm": 2.1789359379909e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.5723905723905723, | |
| "grad_norm": 2.3240922018885612e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.6060606060606061, | |
| "grad_norm": 1.9898488972103223e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.6397306397306397, | |
| "grad_norm": 1.7000074876705185e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.6734006734006734, | |
| "grad_norm": 1.546139537822455e-05, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.6734006734006734, | |
| "eval_loss": 7.095484306773869e-07, | |
| "eval_runtime": 5.0574, | |
| "eval_samples_per_second": 24.716, | |
| "eval_steps_per_second": 12.457, | |
| "step": 200 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 200, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4.2243654156288e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |