| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0031181789834736516, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0003118178983473651, | |
| "grad_norm": 0.6566165685653687, | |
| "learning_rate": 2e-05, | |
| "loss": 1.8957, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0003118178983473651, | |
| "eval_loss": 1.8035469055175781, | |
| "eval_runtime": 57.7332, | |
| "eval_samples_per_second": 23.401, | |
| "eval_steps_per_second": 11.709, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0006236357966947302, | |
| "grad_norm": 0.7361301183700562, | |
| "learning_rate": 4e-05, | |
| "loss": 1.8645, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0009354536950420954, | |
| "grad_norm": 0.5800981521606445, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7754, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0009354536950420954, | |
| "eval_loss": 1.79875910282135, | |
| "eval_runtime": 55.7045, | |
| "eval_samples_per_second": 24.253, | |
| "eval_steps_per_second": 12.135, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0012472715933894605, | |
| "grad_norm": 0.6629976034164429, | |
| "learning_rate": 8e-05, | |
| "loss": 1.7424, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0015590894917368258, | |
| "grad_norm": 0.7607347965240479, | |
| "learning_rate": 0.0001, | |
| "loss": 1.7342, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0018709073900841909, | |
| "grad_norm": 0.728712260723114, | |
| "learning_rate": 0.00012, | |
| "loss": 1.6289, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0018709073900841909, | |
| "eval_loss": 1.7151895761489868, | |
| "eval_runtime": 55.8278, | |
| "eval_samples_per_second": 24.199, | |
| "eval_steps_per_second": 12.109, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.002182725288431556, | |
| "grad_norm": 0.8463139533996582, | |
| "learning_rate": 0.00014, | |
| "loss": 1.8157, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.002494543186778921, | |
| "grad_norm": 0.6177520155906677, | |
| "learning_rate": 0.00016, | |
| "loss": 1.7816, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.002806361085126286, | |
| "grad_norm": 1.193546175956726, | |
| "learning_rate": 0.00018, | |
| "loss": 1.626, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002806361085126286, | |
| "eval_loss": 1.691176414489746, | |
| "eval_runtime": 55.8437, | |
| "eval_samples_per_second": 24.193, | |
| "eval_steps_per_second": 12.105, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0031181789834736516, | |
| "grad_norm": 1.5937474966049194, | |
| "learning_rate": 0.0002, | |
| "loss": 1.6128, | |
| "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": 2820585478422528.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |