| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002784150962852208, | |
| "eval_steps": 9, | |
| "global_step": 27, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00010311670232785956, | |
| "eval_loss": 2.0299148559570312, | |
| "eval_runtime": 1157.9003, | |
| "eval_samples_per_second": 14.107, | |
| "eval_steps_per_second": 1.764, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003093501069835787, | |
| "grad_norm": 23.948354721069336, | |
| "learning_rate": 1.5e-05, | |
| "loss": 8.1239, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006187002139671574, | |
| "grad_norm": 19.15797996520996, | |
| "learning_rate": 3e-05, | |
| "loss": 9.1409, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.000928050320950736, | |
| "grad_norm": 9.434832572937012, | |
| "learning_rate": 4.5e-05, | |
| "loss": 7.1953, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000928050320950736, | |
| "eval_loss": 1.6139401197433472, | |
| "eval_runtime": 1163.807, | |
| "eval_samples_per_second": 14.035, | |
| "eval_steps_per_second": 1.755, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0012374004279343148, | |
| "grad_norm": 6.820188522338867, | |
| "learning_rate": 4.993910125649561e-05, | |
| "loss": 6.3209, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.0015467505349178933, | |
| "grad_norm": 8.132386207580566, | |
| "learning_rate": 4.962019382530521e-05, | |
| "loss": 6.0845, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.001856100641901472, | |
| "grad_norm": 6.336308479309082, | |
| "learning_rate": 4.9031542398457974e-05, | |
| "loss": 5.3419, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.001856100641901472, | |
| "eval_loss": 1.508717656135559, | |
| "eval_runtime": 1164.3323, | |
| "eval_samples_per_second": 14.029, | |
| "eval_steps_per_second": 1.754, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0021654507488850505, | |
| "grad_norm": 8.175219535827637, | |
| "learning_rate": 4.817959636416969e-05, | |
| "loss": 5.8257, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0024748008558686295, | |
| "grad_norm": 11.247066497802734, | |
| "learning_rate": 4.707368982147318e-05, | |
| "loss": 6.2536, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.002784150962852208, | |
| "grad_norm": 6.052129745483398, | |
| "learning_rate": 4.572593931387604e-05, | |
| "loss": 6.0575, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.002784150962852208, | |
| "eval_loss": 1.4805811643600464, | |
| "eval_runtime": 1164.3067, | |
| "eval_samples_per_second": 14.029, | |
| "eval_steps_per_second": 1.754, | |
| "step": 27 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 100, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 9, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.972681667549594e+16, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |