| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.022753128555176336, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004550625711035267, | |
| "eval_loss": 8.276806831359863, | |
| "eval_runtime": 191.4525, | |
| "eval_samples_per_second": 4.837, | |
| "eval_steps_per_second": 2.418, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0022753128555176336, | |
| "grad_norm": 18.482772827148438, | |
| "learning_rate": 5e-05, | |
| "loss": 7.6, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004550625711035267, | |
| "grad_norm": 16.873130798339844, | |
| "learning_rate": 0.0001, | |
| "loss": 4.5357, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.004550625711035267, | |
| "eval_loss": 1.0215221643447876, | |
| "eval_runtime": 193.2723, | |
| "eval_samples_per_second": 4.791, | |
| "eval_steps_per_second": 2.396, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.006825938566552901, | |
| "grad_norm": 9.969215393066406, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 0.3175, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.009101251422070534, | |
| "grad_norm": 0.0247463658452034, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.4614, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.009101251422070534, | |
| "eval_loss": 0.2140456885099411, | |
| "eval_runtime": 193.1936, | |
| "eval_samples_per_second": 4.793, | |
| "eval_steps_per_second": 2.397, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.011376564277588168, | |
| "grad_norm": 0.7247423529624939, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 0.1652, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.013651877133105802, | |
| "grad_norm": 0.0034711698535829782, | |
| "learning_rate": 5e-05, | |
| "loss": 0.1079, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.013651877133105802, | |
| "eval_loss": 0.16020071506500244, | |
| "eval_runtime": 193.3016, | |
| "eval_samples_per_second": 4.79, | |
| "eval_steps_per_second": 2.395, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.015927189988623434, | |
| "grad_norm": 20.983272552490234, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 0.1722, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.01820250284414107, | |
| "grad_norm": 0.6138023138046265, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 0.1248, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.01820250284414107, | |
| "eval_loss": 0.14828301966190338, | |
| "eval_runtime": 193.2763, | |
| "eval_samples_per_second": 4.791, | |
| "eval_steps_per_second": 2.396, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.020477815699658702, | |
| "grad_norm": 12.502432823181152, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 0.4113, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.022753128555176336, | |
| "grad_norm": 0.00241334387101233, | |
| "learning_rate": 0.0, | |
| "loss": 0.2781, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.022753128555176336, | |
| "eval_loss": 0.13595092296600342, | |
| "eval_runtime": 193.1785, | |
| "eval_samples_per_second": 4.793, | |
| "eval_steps_per_second": 2.397, | |
| "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": 1.61937503551488e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |