| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.018190086402910415, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0018190086402910413, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0018190086402910413, | |
| "eval_loss": NaN, | |
| "eval_runtime": 1.3169, | |
| "eval_samples_per_second": 176.175, | |
| "eval_steps_per_second": 88.088, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0036380172805820826, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.005457025920873124, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005457025920873124, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.88, | |
| "eval_samples_per_second": 263.633, | |
| "eval_steps_per_second": 131.816, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007276034561164165, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.009095043201455207, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.010914051841746248, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010914051841746248, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.919, | |
| "eval_samples_per_second": 252.445, | |
| "eval_steps_per_second": 126.223, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.01273306048203729, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.01455206912232833, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.01637107776261937, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.01637107776261937, | |
| "eval_loss": NaN, | |
| "eval_runtime": 0.8839, | |
| "eval_samples_per_second": 262.467, | |
| "eval_steps_per_second": 131.234, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.018190086402910415, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0002, | |
| "loss": 0.0, | |
| "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": 994836480.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |