| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.2782608695652174, | |
| "eval_steps": 4, | |
| "global_step": 4, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.06956521739130435, | |
| "grad_norm": 7.7945876121521, | |
| "learning_rate": 1e-05, | |
| "loss": 177.4688, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.06956521739130435, | |
| "eval_loss": 11.082473754882812, | |
| "eval_runtime": 7.3657, | |
| "eval_samples_per_second": 13.169, | |
| "eval_steps_per_second": 1.765, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.1391304347826087, | |
| "grad_norm": 7.366751194000244, | |
| "learning_rate": 2e-05, | |
| "loss": 177.3516, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.20869565217391303, | |
| "grad_norm": 6.917609214782715, | |
| "learning_rate": 3e-05, | |
| "loss": 177.4609, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.2782608695652174, | |
| "grad_norm": 7.315999984741211, | |
| "learning_rate": 4e-05, | |
| "loss": 177.3516, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.2782608695652174, | |
| "eval_loss": 11.079252243041992, | |
| "eval_runtime": 0.1082, | |
| "eval_samples_per_second": 896.219, | |
| "eval_steps_per_second": 120.112, | |
| "step": 4 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 15, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 2, | |
| "save_steps": 4, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 5324685705216.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |