| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0396000396000396, | |
| "eval_steps": 50, | |
| "global_step": 200, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.000198000198000198, | |
| "eval_loss": 1.105994701385498, | |
| "eval_runtime": 178.3012, | |
| "eval_samples_per_second": 11.929, | |
| "eval_steps_per_second": 5.967, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00198000198000198, | |
| "grad_norm": 1.0405998229980469, | |
| "learning_rate": 0.00019967573081342103, | |
| "loss": 4.1637, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.00396000396000396, | |
| "grad_norm": 1.3216464519500732, | |
| "learning_rate": 0.0001970941817426052, | |
| "loss": 3.8146, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.00594000594000594, | |
| "grad_norm": 1.0430270433425903, | |
| "learning_rate": 0.00019199794436588243, | |
| "loss": 3.8168, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.00792000792000792, | |
| "grad_norm": 1.129577398300171, | |
| "learning_rate": 0.0001845190085543795, | |
| "loss": 3.6568, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0099000099000099, | |
| "grad_norm": 1.9127590656280518, | |
| "learning_rate": 0.00017485107481711012, | |
| "loss": 3.9296, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0099000099000099, | |
| "eval_loss": 0.894871175289154, | |
| "eval_runtime": 178.1325, | |
| "eval_samples_per_second": 11.941, | |
| "eval_steps_per_second": 5.973, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.01188001188001188, | |
| "grad_norm": 1.6014617681503296, | |
| "learning_rate": 0.00016324453755953773, | |
| "loss": 3.7838, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.01386001386001386, | |
| "grad_norm": 1.0109807252883911, | |
| "learning_rate": 0.00015000000000000001, | |
| "loss": 3.9869, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.01584001584001584, | |
| "grad_norm": 1.2943345308303833, | |
| "learning_rate": 0.00013546048870425356, | |
| "loss": 3.5944, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.01782001782001782, | |
| "grad_norm": 1.6601446866989136, | |
| "learning_rate": 0.00012000256937760445, | |
| "loss": 3.5282, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.0198000198000198, | |
| "grad_norm": 0.954728901386261, | |
| "learning_rate": 0.00010402659401094152, | |
| "loss": 3.4408, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.0198000198000198, | |
| "eval_loss": 0.859486997127533, | |
| "eval_runtime": 178.1376, | |
| "eval_samples_per_second": 11.94, | |
| "eval_steps_per_second": 5.973, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.02178002178002178, | |
| "grad_norm": 0.992143988609314, | |
| "learning_rate": 8.79463319744677e-05, | |
| "loss": 3.1659, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.02376002376002376, | |
| "grad_norm": 1.1014974117279053, | |
| "learning_rate": 7.217825360835473e-05, | |
| "loss": 3.1208, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.02574002574002574, | |
| "grad_norm": 2.178656578063965, | |
| "learning_rate": 5.713074385969457e-05, | |
| "loss": 3.798, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.02772002772002772, | |
| "grad_norm": 1.7209547758102417, | |
| "learning_rate": 4.3193525326884435e-05, | |
| "loss": 3.3661, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.0297000297000297, | |
| "grad_norm": 1.3987736701965332, | |
| "learning_rate": 3.072756464904006e-05, | |
| "loss": 3.2864, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.0297000297000297, | |
| "eval_loss": 0.8439649939537048, | |
| "eval_runtime": 178.2393, | |
| "eval_samples_per_second": 11.933, | |
| "eval_steps_per_second": 5.97, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.03168003168003168, | |
| "grad_norm": 1.8658894300460815, | |
| "learning_rate": 2.0055723659649904e-05, | |
| "loss": 3.32, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.03366003366003366, | |
| "grad_norm": 1.666367530822754, | |
| "learning_rate": 1.1454397434679021e-05, | |
| "loss": 3.3608, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 0.03564003564003564, | |
| "grad_norm": 1.6707497835159302, | |
| "learning_rate": 5.146355805285452e-06, | |
| "loss": 3.8797, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.03762003762003762, | |
| "grad_norm": 1.3093181848526, | |
| "learning_rate": 1.2949737362087156e-06, | |
| "loss": 3.5669, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 0.0396000396000396, | |
| "grad_norm": 1.2601022720336914, | |
| "learning_rate": 0.0, | |
| "loss": 3.1048, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.0396000396000396, | |
| "eval_loss": 0.8417183756828308, | |
| "eval_runtime": 178.0902, | |
| "eval_samples_per_second": 11.943, | |
| "eval_steps_per_second": 5.974, | |
| "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": 9.680730813628416e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |