| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.052896059243586355, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0010579211848717272, | |
| "eval_loss": 1.5909721851348877, | |
| "eval_runtime": 16.4017, | |
| "eval_samples_per_second": 24.266, | |
| "eval_steps_per_second": 12.133, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.005289605924358635, | |
| "grad_norm": 0.9607416391372681, | |
| "learning_rate": 5e-05, | |
| "loss": 1.579, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.01057921184871727, | |
| "grad_norm": 1.046164631843567, | |
| "learning_rate": 0.0001, | |
| "loss": 1.5096, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.01057921184871727, | |
| "eval_loss": 1.426159381866455, | |
| "eval_runtime": 15.8346, | |
| "eval_samples_per_second": 25.135, | |
| "eval_steps_per_second": 12.567, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.015868817773075906, | |
| "grad_norm": 1.0881882905960083, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 1.404, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.02115842369743454, | |
| "grad_norm": 0.8857386708259583, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 1.2675, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.02115842369743454, | |
| "eval_loss": 1.2028179168701172, | |
| "eval_runtime": 15.7734, | |
| "eval_samples_per_second": 25.232, | |
| "eval_steps_per_second": 12.616, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.026448029621793177, | |
| "grad_norm": 0.8890538811683655, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 1.1529, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.03173763554615181, | |
| "grad_norm": 1.0510913133621216, | |
| "learning_rate": 5e-05, | |
| "loss": 1.1821, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.03173763554615181, | |
| "eval_loss": 1.1533937454223633, | |
| "eval_runtime": 15.5472, | |
| "eval_samples_per_second": 25.599, | |
| "eval_steps_per_second": 12.8, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.037027241470510446, | |
| "grad_norm": 0.93487948179245, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.1036, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.04231684739486908, | |
| "grad_norm": 0.7386401295661926, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.1589, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04231684739486908, | |
| "eval_loss": 1.1325243711471558, | |
| "eval_runtime": 15.7244, | |
| "eval_samples_per_second": 25.311, | |
| "eval_steps_per_second": 12.655, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04760645331922772, | |
| "grad_norm": 0.7637987732887268, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.0794, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.052896059243586355, | |
| "grad_norm": 0.8987798094749451, | |
| "learning_rate": 0.0, | |
| "loss": 1.1268, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.052896059243586355, | |
| "eval_loss": 1.1289665699005127, | |
| "eval_runtime": 15.7462, | |
| "eval_samples_per_second": 25.276, | |
| "eval_steps_per_second": 12.638, | |
| "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": 885929729851392.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |