| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 3.1020408163265305, | |
| "eval_steps": 25, | |
| "global_step": 19, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.16326530612244897, | |
| "grad_norm": 13.292391777038574, | |
| "learning_rate": 9.931806517013612e-05, | |
| "loss": 7.7093, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.16326530612244897, | |
| "eval_loss": 6.474945068359375, | |
| "eval_runtime": 1.2853, | |
| "eval_samples_per_second": 32.676, | |
| "eval_steps_per_second": 4.668, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.32653061224489793, | |
| "grad_norm": 9.94768238067627, | |
| "learning_rate": 9.729086208503174e-05, | |
| "loss": 6.5747, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.4897959183673469, | |
| "grad_norm": 10.673785209655762, | |
| "learning_rate": 9.397368756032445e-05, | |
| "loss": 3.9471, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.6530612244897959, | |
| "grad_norm": 9.439733505249023, | |
| "learning_rate": 8.945702546981969e-05, | |
| "loss": 2.3278, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.8163265306122449, | |
| "grad_norm": 12.168706893920898, | |
| "learning_rate": 8.386407858128706e-05, | |
| "loss": 1.5332, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.9795918367346939, | |
| "grad_norm": 3.0643529891967773, | |
| "learning_rate": 7.734740790612136e-05, | |
| "loss": 0.5174, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.1428571428571428, | |
| "grad_norm": 30.97225570678711, | |
| "learning_rate": 7.008477123264848e-05, | |
| "loss": 2.5064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 1.306122448979592, | |
| "grad_norm": 8.355841636657715, | |
| "learning_rate": 6.227427435703997e-05, | |
| "loss": 0.878, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 1.469387755102041, | |
| "grad_norm": 3.421520233154297, | |
| "learning_rate": 5.4128967273616625e-05, | |
| "loss": 0.559, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 1.6326530612244898, | |
| "grad_norm": 3.444258689880371, | |
| "learning_rate": 4.5871032726383386e-05, | |
| "loss": 0.5694, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 1.7959183673469388, | |
| "grad_norm": 2.6673386096954346, | |
| "learning_rate": 3.772572564296005e-05, | |
| "loss": 0.5688, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 1.9591836734693877, | |
| "grad_norm": 3.6954569816589355, | |
| "learning_rate": 2.991522876735154e-05, | |
| "loss": 0.4024, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 2.122448979591837, | |
| "grad_norm": 11.280373573303223, | |
| "learning_rate": 2.2652592093878666e-05, | |
| "loss": 1.751, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 2.2857142857142856, | |
| "grad_norm": 2.736438035964966, | |
| "learning_rate": 1.6135921418712956e-05, | |
| "loss": 0.3118, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 2.4489795918367347, | |
| "grad_norm": 2.5588297843933105, | |
| "learning_rate": 1.0542974530180327e-05, | |
| "loss": 0.2191, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 2.612244897959184, | |
| "grad_norm": 3.75992751121521, | |
| "learning_rate": 6.026312439675552e-06, | |
| "loss": 0.481, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 2.7755102040816326, | |
| "grad_norm": 2.158020257949829, | |
| "learning_rate": 2.7091379149682685e-06, | |
| "loss": 0.4231, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 2.938775510204082, | |
| "grad_norm": 1.491848111152649, | |
| "learning_rate": 6.819348298638839e-07, | |
| "loss": 0.1918, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 3.1020408163265305, | |
| "grad_norm": 5.828289985656738, | |
| "learning_rate": 0.0, | |
| "loss": 1.1263, | |
| "step": 19 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 19, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "EarlyStoppingCallback": { | |
| "args": { | |
| "early_stopping_patience": 1, | |
| "early_stopping_threshold": 0.0 | |
| }, | |
| "attributes": { | |
| "early_stopping_patience_counter": 0 | |
| } | |
| }, | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.320092478046208e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |