| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.03499562554680665, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.003499562554680665, | |
| "grad_norm": 0.8734303712844849, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8215, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.003499562554680665, | |
| "eval_loss": 2.1081454753875732, | |
| "eval_runtime": 6.6406, | |
| "eval_samples_per_second": 18.221, | |
| "eval_steps_per_second": 9.186, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00699912510936133, | |
| "grad_norm": 1.3098673820495605, | |
| "learning_rate": 4e-05, | |
| "loss": 1.9217, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.010498687664041995, | |
| "grad_norm": 1.213475227355957, | |
| "learning_rate": 6e-05, | |
| "loss": 2.622, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.010498687664041995, | |
| "eval_loss": 2.1061320304870605, | |
| "eval_runtime": 5.8008, | |
| "eval_samples_per_second": 20.859, | |
| "eval_steps_per_second": 10.516, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.01399825021872266, | |
| "grad_norm": 1.1587634086608887, | |
| "learning_rate": 8e-05, | |
| "loss": 2.5953, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.017497812773403325, | |
| "grad_norm": 0.9745402336120605, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5775, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.02099737532808399, | |
| "grad_norm": 0.8793157339096069, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6589, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.02099737532808399, | |
| "eval_loss": 2.088965892791748, | |
| "eval_runtime": 5.905, | |
| "eval_samples_per_second": 20.491, | |
| "eval_steps_per_second": 10.33, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.024496937882764653, | |
| "grad_norm": 1.3578169345855713, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1643, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.02799650043744532, | |
| "grad_norm": 1.1986603736877441, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1803, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.031496062992125984, | |
| "grad_norm": 0.9070473313331604, | |
| "learning_rate": 0.00018, | |
| "loss": 1.5215, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.031496062992125984, | |
| "eval_loss": 2.031010866165161, | |
| "eval_runtime": 5.8704, | |
| "eval_samples_per_second": 20.612, | |
| "eval_steps_per_second": 10.391, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.03499562554680665, | |
| "grad_norm": 1.2513223886489868, | |
| "learning_rate": 0.0002, | |
| "loss": 1.9052, | |
| "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": 685606636093440.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |