| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0015503875968992248, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0001550387596899225, | |
| "grad_norm": 0.6437714695930481, | |
| "learning_rate": 2e-05, | |
| "loss": 1.2098, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0001550387596899225, | |
| "eval_loss": 1.2846004962921143, | |
| "eval_runtime": 144.5256, | |
| "eval_samples_per_second": 18.793, | |
| "eval_steps_per_second": 9.396, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.000310077519379845, | |
| "grad_norm": 0.5917322635650635, | |
| "learning_rate": 4e-05, | |
| "loss": 1.1567, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00046511627906976747, | |
| "grad_norm": 0.6734963655471802, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1999, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00046511627906976747, | |
| "eval_loss": 1.2787954807281494, | |
| "eval_runtime": 140.0314, | |
| "eval_samples_per_second": 19.396, | |
| "eval_steps_per_second": 9.698, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00062015503875969, | |
| "grad_norm": 0.6709645986557007, | |
| "learning_rate": 8e-05, | |
| "loss": 1.3684, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0007751937984496124, | |
| "grad_norm": 0.7958816885948181, | |
| "learning_rate": 0.0001, | |
| "loss": 1.1655, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0009302325581395349, | |
| "grad_norm": 1.0037189722061157, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2791, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0009302325581395349, | |
| "eval_loss": 1.1838979721069336, | |
| "eval_runtime": 139.9625, | |
| "eval_samples_per_second": 19.405, | |
| "eval_steps_per_second": 9.703, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0010852713178294573, | |
| "grad_norm": 0.641669750213623, | |
| "learning_rate": 0.00014, | |
| "loss": 1.2007, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00124031007751938, | |
| "grad_norm": 0.6157209873199463, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9989, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0013953488372093023, | |
| "grad_norm": 0.5293413400650024, | |
| "learning_rate": 0.00018, | |
| "loss": 1.0255, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0013953488372093023, | |
| "eval_loss": 1.0745004415512085, | |
| "eval_runtime": 139.9501, | |
| "eval_samples_per_second": 19.407, | |
| "eval_steps_per_second": 9.703, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0015503875968992248, | |
| "grad_norm": 0.5830857157707214, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9577, | |
| "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": 3144259221848064.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |