| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03204930662557781, | |
| "eval_steps": 13, | |
| "global_step": 13, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002465331278890601, | |
| "grad_norm": 26.539125442504883, | |
| "learning_rate": 1e-05, | |
| "loss": 3.6602, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002465331278890601, | |
| "eval_loss": 3.617913246154785, | |
| "eval_runtime": 29.3583, | |
| "eval_samples_per_second": 93.091, | |
| "eval_steps_per_second": 11.649, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004930662557781202, | |
| "grad_norm": 24.928752899169922, | |
| "learning_rate": 2e-05, | |
| "loss": 3.5913, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007395993836671803, | |
| "grad_norm": 25.013662338256836, | |
| "learning_rate": 3e-05, | |
| "loss": 3.4352, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009861325115562404, | |
| "grad_norm": 26.976316452026367, | |
| "learning_rate": 4e-05, | |
| "loss": 3.4006, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.012326656394453005, | |
| "grad_norm": 19.72706413269043, | |
| "learning_rate": 5e-05, | |
| "loss": 3.0162, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014791987673343606, | |
| "grad_norm": 17.657188415527344, | |
| "learning_rate": 6e-05, | |
| "loss": 2.4475, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017257318952234205, | |
| "grad_norm": 22.630268096923828, | |
| "learning_rate": 7e-05, | |
| "loss": 1.8466, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019722650231124808, | |
| "grad_norm": 15.391894340515137, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1958, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.022187981510015407, | |
| "grad_norm": 17.156049728393555, | |
| "learning_rate": 9e-05, | |
| "loss": 0.9063, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02465331278890601, | |
| "grad_norm": 14.354949951171875, | |
| "learning_rate": 0.0001, | |
| "loss": 0.5376, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.02711864406779661, | |
| "grad_norm": 4.375965595245361, | |
| "learning_rate": 9.98458666866564e-05, | |
| "loss": 0.1246, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.029583975346687212, | |
| "grad_norm": 1.0381114482879639, | |
| "learning_rate": 9.938441702975689e-05, | |
| "loss": 0.0747, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.03204930662557781, | |
| "grad_norm": 2.4687139987945557, | |
| "learning_rate": 9.861849601988383e-05, | |
| "loss": 0.0975, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.03204930662557781, | |
| "eval_loss": 0.04013116657733917, | |
| "eval_runtime": 19.4505, | |
| "eval_samples_per_second": 140.511, | |
| "eval_steps_per_second": 17.583, | |
| "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": 1.499584945717248e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |