| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00010718716755230064, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.0718716755230065e-05, | |
| "grad_norm": 15.979019165039062, | |
| "learning_rate": 2e-05, | |
| "loss": 9.427, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.0718716755230065e-05, | |
| "eval_loss": 9.758045196533203, | |
| "eval_runtime": 716.7944, | |
| "eval_samples_per_second": 54.804, | |
| "eval_steps_per_second": 27.403, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 2.143743351046013e-05, | |
| "grad_norm": 16.201793670654297, | |
| "learning_rate": 4e-05, | |
| "loss": 9.8142, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 3.215615026569019e-05, | |
| "grad_norm": 15.032333374023438, | |
| "learning_rate": 6e-05, | |
| "loss": 9.4479, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 3.215615026569019e-05, | |
| "eval_loss": 9.526849746704102, | |
| "eval_runtime": 717.6921, | |
| "eval_samples_per_second": 54.735, | |
| "eval_steps_per_second": 27.368, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.287486702092026e-05, | |
| "grad_norm": 17.993995666503906, | |
| "learning_rate": 8e-05, | |
| "loss": 10.0198, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 5.359358377615032e-05, | |
| "grad_norm": 16.489856719970703, | |
| "learning_rate": 0.0001, | |
| "loss": 8.4433, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 6.431230053138038e-05, | |
| "grad_norm": 18.94038963317871, | |
| "learning_rate": 0.00012, | |
| "loss": 7.667, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 6.431230053138038e-05, | |
| "eval_loss": 6.128392219543457, | |
| "eval_runtime": 721.4737, | |
| "eval_samples_per_second": 54.448, | |
| "eval_steps_per_second": 27.225, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 7.503101728661045e-05, | |
| "grad_norm": 21.81522560119629, | |
| "learning_rate": 0.00014, | |
| "loss": 6.1899, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 8.574973404184052e-05, | |
| "grad_norm": 21.471542358398438, | |
| "learning_rate": 0.00016, | |
| "loss": 4.5243, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 9.646845079707057e-05, | |
| "grad_norm": 21.635026931762695, | |
| "learning_rate": 0.00018, | |
| "loss": 3.5233, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 9.646845079707057e-05, | |
| "eval_loss": 2.257808208465576, | |
| "eval_runtime": 718.0733, | |
| "eval_samples_per_second": 54.706, | |
| "eval_steps_per_second": 27.354, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00010718716755230064, | |
| "grad_norm": 14.61885929107666, | |
| "learning_rate": 0.0002, | |
| "loss": 2.3176, | |
| "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": 489477793382400.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |