| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00024724629439616273, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.4724629439616273e-05, | |
| "grad_norm": 9.002562522888184, | |
| "learning_rate": 2e-05, | |
| "loss": 10.1494, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.4724629439616273e-05, | |
| "eval_loss": 7.834451198577881, | |
| "eval_runtime": 516.151, | |
| "eval_samples_per_second": 32.994, | |
| "eval_steps_per_second": 16.497, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 4.9449258879232545e-05, | |
| "grad_norm": 6.542725563049316, | |
| "learning_rate": 4e-05, | |
| "loss": 6.6498, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 7.417388831884883e-05, | |
| "grad_norm": 7.7592453956604, | |
| "learning_rate": 6e-05, | |
| "loss": 7.651, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 7.417388831884883e-05, | |
| "eval_loss": 7.758761405944824, | |
| "eval_runtime": 515.325, | |
| "eval_samples_per_second": 33.047, | |
| "eval_steps_per_second": 16.524, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.889851775846509e-05, | |
| "grad_norm": 7.036420822143555, | |
| "learning_rate": 8e-05, | |
| "loss": 8.4065, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00012362314719808137, | |
| "grad_norm": 7.17626428604126, | |
| "learning_rate": 0.0001, | |
| "loss": 7.5007, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00014834777663769766, | |
| "grad_norm": 7.7558207511901855, | |
| "learning_rate": 0.00012, | |
| "loss": 6.5312, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00014834777663769766, | |
| "eval_loss": 6.3899245262146, | |
| "eval_runtime": 516.0774, | |
| "eval_samples_per_second": 32.999, | |
| "eval_steps_per_second": 16.499, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00017307240607731392, | |
| "grad_norm": 7.050815582275391, | |
| "learning_rate": 0.00014, | |
| "loss": 6.061, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.00019779703551693018, | |
| "grad_norm": 8.801949501037598, | |
| "learning_rate": 0.00016, | |
| "loss": 5.7354, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00022252166495654647, | |
| "grad_norm": 8.916671752929688, | |
| "learning_rate": 0.00018, | |
| "loss": 4.3186, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00022252166495654647, | |
| "eval_loss": 3.9336016178131104, | |
| "eval_runtime": 515.9937, | |
| "eval_samples_per_second": 33.004, | |
| "eval_steps_per_second": 16.502, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00024724629439616273, | |
| "grad_norm": 7.677283763885498, | |
| "learning_rate": 0.0002, | |
| "loss": 4.371, | |
| "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": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |