| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2176278563656148, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001088139281828074, | |
| "eval_loss": 0.23379267752170563, | |
| "eval_runtime": 24.2307, | |
| "eval_samples_per_second": 15.971, | |
| "eval_steps_per_second": 8.006, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01088139281828074, | |
| "grad_norm": 0.29695209860801697, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 0.814, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02176278563656148, | |
| "grad_norm": 0.3327060341835022, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 0.502, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03264417845484222, | |
| "grad_norm": 1.4574642181396484, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 0.4404, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.04352557127312296, | |
| "grad_norm": 0.9914162755012512, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 0.4392, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0544069640914037, | |
| "grad_norm": 0.5401425361633301, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 0.4205, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0544069640914037, | |
| "eval_loss": 0.10474700480699539, | |
| "eval_runtime": 24.2574, | |
| "eval_samples_per_second": 15.954, | |
| "eval_steps_per_second": 7.998, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.06528835690968444, | |
| "grad_norm": 0.5337303876876831, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 0.4238, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.07616974972796518, | |
| "grad_norm": 0.40790870785713196, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 0.373, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.08705114254624592, | |
| "grad_norm": 0.4428502917289734, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 0.4031, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.09793253536452666, | |
| "grad_norm": 0.33187779784202576, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 0.4286, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.1088139281828074, | |
| "grad_norm": 0.6701465845108032, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 0.431, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.1088139281828074, | |
| "eval_loss": 0.09632764756679535, | |
| "eval_runtime": 24.2649, | |
| "eval_samples_per_second": 15.949, | |
| "eval_steps_per_second": 7.995, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.11969532100108814, | |
| "grad_norm": 1.7176902294158936, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 0.4559, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.1305767138193689, | |
| "grad_norm": 0.39822494983673096, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 0.4364, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.14145810663764963, | |
| "grad_norm": 0.42606645822525024, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 0.3936, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.15233949945593037, | |
| "grad_norm": 0.992786169052124, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 0.4474, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1632208922742111, | |
| "grad_norm": 0.35880205035209656, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 0.3639, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.1632208922742111, | |
| "eval_loss": 0.09264663606882095, | |
| "eval_runtime": 24.2837, | |
| "eval_samples_per_second": 15.937, | |
| "eval_steps_per_second": 7.989, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.17410228509249184, | |
| "grad_norm": 0.4978827238082886, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 0.3512, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.18498367791077258, | |
| "grad_norm": 0.42685166001319885, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 0.3719, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.19586507072905332, | |
| "grad_norm": 0.39568108320236206, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 0.3783, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.20674646354733406, | |
| "grad_norm": 0.6876519918441772, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 0.3972, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.2176278563656148, | |
| "grad_norm": 0.8734281659126282, | |
| "learning_rate": 0.0, | |
| "loss": 0.4679, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.2176278563656148, | |
| "eval_loss": 0.09196602553129196, | |
| "eval_runtime": 24.2724, | |
| "eval_samples_per_second": 15.944, | |
| "eval_steps_per_second": 7.993, | |
| "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": 5.993797210708378e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |