| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0534045393858478, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.001068090787716956, | |
| "eval_loss": 1.14894437789917, | |
| "eval_runtime": 48.5189, | |
| "eval_samples_per_second": 8.141, | |
| "eval_steps_per_second": 4.081, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0053404539385847796, | |
| "grad_norm": 0.6066215634346008, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1702, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010680907877169559, | |
| "grad_norm": 0.6474339365959167, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0741, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.010680907877169559, | |
| "eval_loss": 0.9659668803215027, | |
| "eval_runtime": 49.2681, | |
| "eval_samples_per_second": 8.017, | |
| "eval_steps_per_second": 4.019, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01602136181575434, | |
| "grad_norm": 0.7500752806663513, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.9175, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.021361815754339118, | |
| "grad_norm": 0.5820088982582092, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.9016, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.021361815754339118, | |
| "eval_loss": 0.8188917636871338, | |
| "eval_runtime": 49.2145, | |
| "eval_samples_per_second": 8.026, | |
| "eval_steps_per_second": 4.023, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0267022696929239, | |
| "grad_norm": 0.6586773991584778, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7804, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03204272363150868, | |
| "grad_norm": 0.625420093536377, | |
| "learning_rate": 5e-05, | |
| "loss": 0.8399, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03204272363150868, | |
| "eval_loss": 0.7655370831489563, | |
| "eval_runtime": 49.1931, | |
| "eval_samples_per_second": 8.03, | |
| "eval_steps_per_second": 4.025, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.037383177570093455, | |
| "grad_norm": 0.5896813869476318, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.7661, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.042723631508678236, | |
| "grad_norm": 0.6344001293182373, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.7195, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.042723631508678236, | |
| "eval_loss": 0.7412234544754028, | |
| "eval_runtime": 49.2436, | |
| "eval_samples_per_second": 8.021, | |
| "eval_steps_per_second": 4.021, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04806408544726302, | |
| "grad_norm": 0.5282084345817566, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.7667, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.0534045393858478, | |
| "grad_norm": 0.6339199542999268, | |
| "learning_rate": 0.0, | |
| "loss": 0.8209, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.0534045393858478, | |
| "eval_loss": 0.7365169525146484, | |
| "eval_runtime": 49.1802, | |
| "eval_samples_per_second": 8.032, | |
| "eval_steps_per_second": 4.026, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "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": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.84956424814592e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |