| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.005376344086021506, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0005376344086021505, | |
| "grad_norm": 0.2367846965789795, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1054, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0005376344086021505, | |
| "eval_loss": 1.1771646738052368, | |
| "eval_runtime": 50.2759, | |
| "eval_samples_per_second": 15.594, | |
| "eval_steps_per_second": 7.797, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.001075268817204301, | |
| "grad_norm": 0.2534483075141907, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0431, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0016129032258064516, | |
| "grad_norm": 0.2641952931880951, | |
| "learning_rate": 6e-05, | |
| "loss": 1.1042, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0016129032258064516, | |
| "eval_loss": 1.1709295511245728, | |
| "eval_runtime": 51.3001, | |
| "eval_samples_per_second": 15.283, | |
| "eval_steps_per_second": 7.641, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002150537634408602, | |
| "grad_norm": 0.29012876749038696, | |
| "learning_rate": 8e-05, | |
| "loss": 1.1658, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.002688172043010753, | |
| "grad_norm": 0.29535111784935, | |
| "learning_rate": 0.0001, | |
| "loss": 1.197, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0032258064516129032, | |
| "grad_norm": 0.39269500970840454, | |
| "learning_rate": 0.00012, | |
| "loss": 1.1577, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0032258064516129032, | |
| "eval_loss": 1.1016113758087158, | |
| "eval_runtime": 51.4908, | |
| "eval_samples_per_second": 15.226, | |
| "eval_steps_per_second": 7.613, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.003763440860215054, | |
| "grad_norm": 0.46053290367126465, | |
| "learning_rate": 0.00014, | |
| "loss": 1.0607, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.004301075268817204, | |
| "grad_norm": 0.4400120973587036, | |
| "learning_rate": 0.00016, | |
| "loss": 1.1322, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.004838709677419355, | |
| "grad_norm": 0.5260744690895081, | |
| "learning_rate": 0.00018, | |
| "loss": 0.8884, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.004838709677419355, | |
| "eval_loss": 0.9314318895339966, | |
| "eval_runtime": 50.6945, | |
| "eval_samples_per_second": 15.465, | |
| "eval_steps_per_second": 7.733, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005376344086021506, | |
| "grad_norm": 0.5231564044952393, | |
| "learning_rate": 0.0002, | |
| "loss": 0.9745, | |
| "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": 3257498484080640.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |