| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.04338394793926247, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.004338394793926247, | |
| "grad_norm": 2.6531178951263428, | |
| "learning_rate": 2e-05, | |
| "loss": 15.289, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004338394793926247, | |
| "eval_loss": 3.814282178878784, | |
| "eval_runtime": 1.7593, | |
| "eval_samples_per_second": 55.134, | |
| "eval_steps_per_second": 27.851, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.008676789587852495, | |
| "grad_norm": 2.3595850467681885, | |
| "learning_rate": 4e-05, | |
| "loss": 15.2893, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.013015184381778741, | |
| "grad_norm": 2.574573278427124, | |
| "learning_rate": 6e-05, | |
| "loss": 14.3311, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.013015184381778741, | |
| "eval_loss": 3.8116660118103027, | |
| "eval_runtime": 1.7579, | |
| "eval_samples_per_second": 55.179, | |
| "eval_steps_per_second": 27.874, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01735357917570499, | |
| "grad_norm": 3.053541421890259, | |
| "learning_rate": 8e-05, | |
| "loss": 15.5, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.021691973969631236, | |
| "grad_norm": 2.1343438625335693, | |
| "learning_rate": 0.0001, | |
| "loss": 15.3353, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.026030368763557483, | |
| "grad_norm": 1.8734140396118164, | |
| "learning_rate": 0.00012, | |
| "loss": 15.5012, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.026030368763557483, | |
| "eval_loss": 3.786515712738037, | |
| "eval_runtime": 1.7844, | |
| "eval_samples_per_second": 54.361, | |
| "eval_steps_per_second": 27.461, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03036876355748373, | |
| "grad_norm": 1.9502086639404297, | |
| "learning_rate": 0.00014, | |
| "loss": 14.3359, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.03470715835140998, | |
| "grad_norm": 2.898710250854492, | |
| "learning_rate": 0.00016, | |
| "loss": 14.8791, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.039045553145336226, | |
| "grad_norm": 2.074517011642456, | |
| "learning_rate": 0.00018, | |
| "loss": 15.2378, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.039045553145336226, | |
| "eval_loss": 3.7467966079711914, | |
| "eval_runtime": 1.7559, | |
| "eval_samples_per_second": 55.243, | |
| "eval_steps_per_second": 27.906, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.04338394793926247, | |
| "grad_norm": 1.9527268409729004, | |
| "learning_rate": 0.0002, | |
| "loss": 16.0408, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 3, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 129495151411200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |