| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.23757852655625358, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.018275271273557967, | |
| "grad_norm": 4.217789649963379, | |
| "learning_rate": 5e-05, | |
| "loss": 8.8561, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.018275271273557967, | |
| "eval_loss": 8.832687377929688, | |
| "eval_runtime": 66.6285, | |
| "eval_samples_per_second": 5.538, | |
| "eval_steps_per_second": 1.396, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.036550542547115934, | |
| "grad_norm": 4.4302568435668945, | |
| "learning_rate": 0.0001, | |
| "loss": 8.7806, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0548258138206739, | |
| "grad_norm": 4.538593292236328, | |
| "learning_rate": 9.989294616193017e-05, | |
| "loss": 8.662, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.07310108509423187, | |
| "grad_norm": 5.8020195960998535, | |
| "learning_rate": 9.957224306869053e-05, | |
| "loss": 7.9472, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.09137635636778983, | |
| "grad_norm": 6.238458633422852, | |
| "learning_rate": 9.903926402016153e-05, | |
| "loss": 6.4558, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1096516276413478, | |
| "grad_norm": 5.397599220275879, | |
| "learning_rate": 9.829629131445342e-05, | |
| "loss": 4.8986, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.12792689891490577, | |
| "grad_norm": 4.881111145019531, | |
| "learning_rate": 9.73465064747553e-05, | |
| "loss": 4.1723, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.14620217018846374, | |
| "grad_norm": 3.493053436279297, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.2577, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.1644774414620217, | |
| "grad_norm": 2.9015204906463623, | |
| "learning_rate": 9.484363707663442e-05, | |
| "loss": 2.7507, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.18275271273557966, | |
| "grad_norm": 2.8159022331237793, | |
| "learning_rate": 9.330127018922194e-05, | |
| "loss": 2.5523, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.20102798400913763, | |
| "grad_norm": 3.2096753120422363, | |
| "learning_rate": 9.157348061512727e-05, | |
| "loss": 2.0235, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.2193032552826956, | |
| "grad_norm": 3.640693426132202, | |
| "learning_rate": 8.966766701456177e-05, | |
| "loss": 1.4851, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.23757852655625358, | |
| "grad_norm": 3.8002378940582275, | |
| "learning_rate": 8.759199037394887e-05, | |
| "loss": 1.0231, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.23757852655625358, | |
| "eval_loss": 0.6289411783218384, | |
| "eval_runtime": 66.1722, | |
| "eval_samples_per_second": 5.576, | |
| "eval_steps_per_second": 1.405, | |
| "step": 13 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5.281361167510405e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |