| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.22346368715083798, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0223463687150838, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 5.2067, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0223463687150838, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.7616, | |
| "eval_samples_per_second": 10.786, | |
| "eval_steps_per_second": 5.677, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0446927374301676, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 2.0659, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0670391061452514, | |
| "grad_norm": 34.9081916809082, | |
| "learning_rate": 6e-05, | |
| "loss": 5.7547, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0670391061452514, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.6218, | |
| "eval_samples_per_second": 30.558, | |
| "eval_steps_per_second": 16.083, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0893854748603352, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 3.7165, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.11173184357541899, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.1340782122905028, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1340782122905028, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.6099, | |
| "eval_samples_per_second": 31.155, | |
| "eval_steps_per_second": 16.397, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.1564245810055866, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 14.8844, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.1787709497206704, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 10.7419, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.2011173184357542, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 4.075, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.2011173184357542, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.6168, | |
| "eval_samples_per_second": 30.803, | |
| "eval_steps_per_second": 16.212, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.22346368715083798, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 9.1604, | |
| "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": 1796486530596864.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |