| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.9961802902979373, | |
| "eval_steps": 500, | |
| "global_step": 163, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.061115355233002294, | |
| "grad_norm": 9.6875, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 1.2797, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.12223071046600459, | |
| "grad_norm": 8.8125, | |
| "learning_rate": 4.994792902163481e-05, | |
| "loss": 1.1373, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.18334606569900688, | |
| "grad_norm": 5.375, | |
| "learning_rate": 4.902824459680752e-05, | |
| "loss": 1.1783, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.24446142093200918, | |
| "grad_norm": 3.1875, | |
| "learning_rate": 4.7000305099338396e-05, | |
| "loss": 1.1725, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.30557677616501144, | |
| "grad_norm": 2.5625, | |
| "learning_rate": 4.395764521196406e-05, | |
| "loss": 1.1683, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.36669213139801377, | |
| "grad_norm": 2.6875, | |
| "learning_rate": 4.004060158062306e-05, | |
| "loss": 1.1519, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.42780748663101603, | |
| "grad_norm": 2.53125, | |
| "learning_rate": 3.542984006530792e-05, | |
| "loss": 1.1442, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.48892284186401835, | |
| "grad_norm": 2.171875, | |
| "learning_rate": 3.0338022885994904e-05, | |
| "loss": 1.1354, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.5500381970970206, | |
| "grad_norm": 1.90625, | |
| "learning_rate": 2.5e-05, | |
| "loss": 1.1259, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.6111535523300229, | |
| "grad_norm": 1.8828125, | |
| "learning_rate": 1.9661977114005098e-05, | |
| "loss": 1.0983, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.6722689075630253, | |
| "grad_norm": 1.6953125, | |
| "learning_rate": 1.4570159934692085e-05, | |
| "loss": 1.0884, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.7333842627960275, | |
| "grad_norm": 1.7265625, | |
| "learning_rate": 9.959398419376932e-06, | |
| "loss": 1.0599, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.7944996180290298, | |
| "grad_norm": 1.625, | |
| "learning_rate": 6.042354788035942e-06, | |
| "loss": 1.0558, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.8556149732620321, | |
| "grad_norm": 1.5859375, | |
| "learning_rate": 2.9996949006616094e-06, | |
| "loss": 1.0508, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.9167303284950343, | |
| "grad_norm": 1.6640625, | |
| "learning_rate": 9.71755403192484e-07, | |
| "loss": 1.0264, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 0.9778456837280367, | |
| "grad_norm": 1.6015625, | |
| "learning_rate": 5.20709783651957e-08, | |
| "loss": 1.0426, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.9961802902979373, | |
| "step": 163, | |
| "total_flos": 9.115042887803863e+17, | |
| "train_loss": 1.117896075629018, | |
| "train_runtime": 6585.7608, | |
| "train_samples_per_second": 3.18, | |
| "train_steps_per_second": 0.025 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 163, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 9.115042887803863e+17, | |
| "train_batch_size": 8, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |