| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.046632124352331605, | |
| "eval_steps": 3, | |
| "global_step": 9, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0051813471502590676, | |
| "grad_norm": 2.924191474914551, | |
| "learning_rate": 2e-05, | |
| "loss": 2.5602, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0051813471502590676, | |
| "eval_loss": 2.828925371170044, | |
| "eval_runtime": 6.169, | |
| "eval_samples_per_second": 52.683, | |
| "eval_steps_per_second": 6.646, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.010362694300518135, | |
| "grad_norm": 2.8529112339019775, | |
| "learning_rate": 4e-05, | |
| "loss": 2.7341, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.015544041450777202, | |
| "grad_norm": 2.872540235519409, | |
| "learning_rate": 6e-05, | |
| "loss": 2.7503, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.015544041450777202, | |
| "eval_loss": 2.6559345722198486, | |
| "eval_runtime": 6.0825, | |
| "eval_samples_per_second": 53.432, | |
| "eval_steps_per_second": 6.741, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.02072538860103627, | |
| "grad_norm": 2.4872028827667236, | |
| "learning_rate": 8e-05, | |
| "loss": 2.479, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.025906735751295335, | |
| "grad_norm": 1.9989739656448364, | |
| "learning_rate": 0.0001, | |
| "loss": 2.3739, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.031088082901554404, | |
| "grad_norm": 1.8076043128967285, | |
| "learning_rate": 0.00012, | |
| "loss": 2.1317, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.031088082901554404, | |
| "eval_loss": 2.19926381111145, | |
| "eval_runtime": 6.1019, | |
| "eval_samples_per_second": 53.262, | |
| "eval_steps_per_second": 6.719, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.03626943005181347, | |
| "grad_norm": 1.6933070421218872, | |
| "learning_rate": 0.00014, | |
| "loss": 2.1506, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.04145077720207254, | |
| "grad_norm": 2.2071964740753174, | |
| "learning_rate": 0.00016, | |
| "loss": 2.1208, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.046632124352331605, | |
| "grad_norm": 2.2025673389434814, | |
| "learning_rate": 0.00018, | |
| "loss": 2.1536, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.046632124352331605, | |
| "eval_loss": 2.0101969242095947, | |
| "eval_runtime": 6.1068, | |
| "eval_samples_per_second": 53.22, | |
| "eval_steps_per_second": 6.714, | |
| "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": 1.447629598752768e+16, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |