| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000799584216207572, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.995842162075721e-05, | |
| "grad_norm": 0.6495417356491089, | |
| "learning_rate": 2e-05, | |
| "loss": 2.9552, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.995842162075721e-05, | |
| "eval_loss": 0.6995508670806885, | |
| "eval_runtime": 47.9958, | |
| "eval_samples_per_second": 109.718, | |
| "eval_steps_per_second": 54.859, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015991684324151442, | |
| "grad_norm": 1.2527365684509277, | |
| "learning_rate": 4e-05, | |
| "loss": 5.473, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00023987526486227162, | |
| "grad_norm": 0.5610813498497009, | |
| "learning_rate": 6e-05, | |
| "loss": 1.8095, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00023987526486227162, | |
| "eval_loss": 0.6994554996490479, | |
| "eval_runtime": 48.2348, | |
| "eval_samples_per_second": 109.174, | |
| "eval_steps_per_second": 54.587, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00031983368648302884, | |
| "grad_norm": 1.0127778053283691, | |
| "learning_rate": 8e-05, | |
| "loss": 3.1434, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.000399792108103786, | |
| "grad_norm": 0.6170755624771118, | |
| "learning_rate": 0.0001, | |
| "loss": 2.272, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00047975052972454323, | |
| "grad_norm": 0.777292013168335, | |
| "learning_rate": 0.00012, | |
| "loss": 2.9915, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00047975052972454323, | |
| "eval_loss": 0.6983044743537903, | |
| "eval_runtime": 48.7238, | |
| "eval_samples_per_second": 108.079, | |
| "eval_steps_per_second": 54.039, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005597089513453004, | |
| "grad_norm": 0.7125624418258667, | |
| "learning_rate": 0.00014, | |
| "loss": 2.5858, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006396673729660577, | |
| "grad_norm": 1.5198544263839722, | |
| "learning_rate": 0.00016, | |
| "loss": 8.0022, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0007196257945868149, | |
| "grad_norm": 1.132773756980896, | |
| "learning_rate": 0.00018, | |
| "loss": 5.0194, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0007196257945868149, | |
| "eval_loss": 0.6932116746902466, | |
| "eval_runtime": 48.2958, | |
| "eval_samples_per_second": 109.036, | |
| "eval_steps_per_second": 54.518, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000799584216207572, | |
| "grad_norm": 0.5889104604721069, | |
| "learning_rate": 0.0002, | |
| "loss": 1.7851, | |
| "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": 28120099848192.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |