| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02735603884557516, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005471207769115032, | |
| "eval_loss": 6.341391086578369, | |
| "eval_runtime": 51.8631, | |
| "eval_samples_per_second": 14.847, | |
| "eval_steps_per_second": 7.423, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002735603884557516, | |
| "grad_norm": 3.2491846084594727, | |
| "learning_rate": 5e-05, | |
| "loss": 5.8444, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.005471207769115032, | |
| "grad_norm": 3.9482262134552, | |
| "learning_rate": 0.0001, | |
| "loss": 5.8172, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.005471207769115032, | |
| "eval_loss": 4.977085113525391, | |
| "eval_runtime": 51.3689, | |
| "eval_samples_per_second": 14.99, | |
| "eval_steps_per_second": 7.495, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008206811653672548, | |
| "grad_norm": 8.238612174987793, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 3.7912, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.010942415538230063, | |
| "grad_norm": 6.331942081451416, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.1827, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.010942415538230063, | |
| "eval_loss": 1.2586541175842285, | |
| "eval_runtime": 51.2706, | |
| "eval_samples_per_second": 15.018, | |
| "eval_steps_per_second": 7.509, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01367801942278758, | |
| "grad_norm": 3.4683191776275635, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.7444, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.016413623307345096, | |
| "grad_norm": 3.1235790252685547, | |
| "learning_rate": 5e-05, | |
| "loss": 1.0391, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.016413623307345096, | |
| "eval_loss": 0.6169207096099854, | |
| "eval_runtime": 51.3498, | |
| "eval_samples_per_second": 14.995, | |
| "eval_steps_per_second": 7.498, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.019149227191902613, | |
| "grad_norm": 4.052883148193359, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.4649, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.021884831076460127, | |
| "grad_norm": 2.838388681411743, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.5171, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.021884831076460127, | |
| "eval_loss": 0.5030908584594727, | |
| "eval_runtime": 51.5327, | |
| "eval_samples_per_second": 14.942, | |
| "eval_steps_per_second": 7.471, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.024620434961017644, | |
| "grad_norm": 2.749112129211426, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.5911, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.02735603884557516, | |
| "grad_norm": 2.3166110515594482, | |
| "learning_rate": 0.0, | |
| "loss": 0.4508, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.02735603884557516, | |
| "eval_loss": 0.482439786195755, | |
| "eval_runtime": 51.5445, | |
| "eval_samples_per_second": 14.939, | |
| "eval_steps_per_second": 7.469, | |
| "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": 9192405143126016.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |