| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006902502157031924, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 7.669446841146582e-05, | |
| "grad_norm": 0.29293447732925415, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1216, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.669446841146582e-05, | |
| "eval_loss": 1.237951636314392, | |
| "eval_runtime": 287.3585, | |
| "eval_samples_per_second": 19.105, | |
| "eval_steps_per_second": 9.553, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00015338893682293164, | |
| "grad_norm": 0.323147177696228, | |
| "learning_rate": 4e-05, | |
| "loss": 1.3984, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00023008340523439746, | |
| "grad_norm": 0.3718980550765991, | |
| "learning_rate": 6e-05, | |
| "loss": 1.3219, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00023008340523439746, | |
| "eval_loss": 1.2360836267471313, | |
| "eval_runtime": 286.7391, | |
| "eval_samples_per_second": 19.146, | |
| "eval_steps_per_second": 9.573, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0003067778736458633, | |
| "grad_norm": 0.3561649024486542, | |
| "learning_rate": 8e-05, | |
| "loss": 1.2385, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0003834723420573291, | |
| "grad_norm": 0.36357933282852173, | |
| "learning_rate": 0.0001, | |
| "loss": 1.0535, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0004601668104687949, | |
| "grad_norm": 0.4672258794307709, | |
| "learning_rate": 0.00012, | |
| "loss": 1.3853, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004601668104687949, | |
| "eval_loss": 1.2194606065750122, | |
| "eval_runtime": 286.9155, | |
| "eval_samples_per_second": 19.135, | |
| "eval_steps_per_second": 9.567, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0005368612788802608, | |
| "grad_norm": 0.576995313167572, | |
| "learning_rate": 0.00014, | |
| "loss": 1.5042, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0006135557472917265, | |
| "grad_norm": 0.33490216732025146, | |
| "learning_rate": 0.00016, | |
| "loss": 1.0653, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006902502157031924, | |
| "grad_norm": 0.41501566767692566, | |
| "learning_rate": 0.00018, | |
| "loss": 1.1493, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006902502157031924, | |
| "eval_loss": 1.1577930450439453, | |
| "eval_runtime": 286.902, | |
| "eval_samples_per_second": 19.135, | |
| "eval_steps_per_second": 9.568, | |
| "step": 9 | |
| } | |
| ], | |
| "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": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2931719644643328.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |