| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.021105951878429716, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00042211903756859433, | |
| "eval_loss": 2.3645458221435547, | |
| "eval_runtime": 777.7782, | |
| "eval_samples_per_second": 1.283, | |
| "eval_steps_per_second": 0.642, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002110595187842972, | |
| "grad_norm": 6.993026256561279, | |
| "learning_rate": 5e-05, | |
| "loss": 9.41, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004221190375685944, | |
| "grad_norm": 13.77673625946045, | |
| "learning_rate": 0.0001, | |
| "loss": 8.1771, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004221190375685944, | |
| "eval_loss": 1.9789879322052002, | |
| "eval_runtime": 838.986, | |
| "eval_samples_per_second": 1.19, | |
| "eval_steps_per_second": 0.595, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006331785563528915, | |
| "grad_norm": 28.14606475830078, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 6.3495, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.008442380751371888, | |
| "grad_norm": 12.39108943939209, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 5.0889, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.008442380751371888, | |
| "eval_loss": 1.39557683467865, | |
| "eval_runtime": 835.5563, | |
| "eval_samples_per_second": 1.194, | |
| "eval_steps_per_second": 0.597, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010552975939214858, | |
| "grad_norm": 15.066307067871094, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 5.7179, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.01266357112705783, | |
| "grad_norm": 8.998570442199707, | |
| "learning_rate": 5e-05, | |
| "loss": 4.9981, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.01266357112705783, | |
| "eval_loss": 1.2956539392471313, | |
| "eval_runtime": 836.4017, | |
| "eval_samples_per_second": 1.193, | |
| "eval_steps_per_second": 0.597, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.014774166314900802, | |
| "grad_norm": 11.392327308654785, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 5.3543, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.016884761502743775, | |
| "grad_norm": 9.426527976989746, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 5.4934, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.016884761502743775, | |
| "eval_loss": 1.2708839178085327, | |
| "eval_runtime": 752.0022, | |
| "eval_samples_per_second": 1.327, | |
| "eval_steps_per_second": 0.664, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.018995356690586745, | |
| "grad_norm": 9.66463851928711, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 5.3099, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.021105951878429716, | |
| "grad_norm": 9.411620140075684, | |
| "learning_rate": 0.0, | |
| "loss": 4.6061, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.021105951878429716, | |
| "eval_loss": 1.2672959566116333, | |
| "eval_runtime": 977.7388, | |
| "eval_samples_per_second": 1.021, | |
| "eval_steps_per_second": 0.51, | |
| "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": 8143665679564800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |