| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0003260913871112379, | |
| "eval_steps": 2, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.260913871112379e-05, | |
| "grad_norm": 2.9804935455322266, | |
| "learning_rate": 2e-05, | |
| "loss": 3.2729, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.260913871112379e-05, | |
| "eval_loss": 2.8746273517608643, | |
| "eval_runtime": 399.3712, | |
| "eval_samples_per_second": 16.168, | |
| "eval_steps_per_second": 16.168, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.521827742224758e-05, | |
| "grad_norm": 2.4193668365478516, | |
| "learning_rate": 4e-05, | |
| "loss": 2.602, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 6.521827742224758e-05, | |
| "eval_loss": 2.8728725910186768, | |
| "eval_runtime": 400.1947, | |
| "eval_samples_per_second": 16.135, | |
| "eval_steps_per_second": 16.135, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.782741613337138e-05, | |
| "grad_norm": 3.057901620864868, | |
| "learning_rate": 6e-05, | |
| "loss": 2.8494, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00013043655484449516, | |
| "grad_norm": 2.7539632320404053, | |
| "learning_rate": 8e-05, | |
| "loss": 3.3534, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00013043655484449516, | |
| "eval_loss": 2.842006206512451, | |
| "eval_runtime": 400.6337, | |
| "eval_samples_per_second": 16.117, | |
| "eval_steps_per_second": 16.117, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00016304569355561895, | |
| "grad_norm": 3.022265672683716, | |
| "learning_rate": 0.0001, | |
| "loss": 2.176, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00019565483226674277, | |
| "grad_norm": 2.7493996620178223, | |
| "learning_rate": 0.00012, | |
| "loss": 2.2505, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00019565483226674277, | |
| "eval_loss": 2.7171995639801025, | |
| "eval_runtime": 401.3245, | |
| "eval_samples_per_second": 16.089, | |
| "eval_steps_per_second": 16.089, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00022826397097786656, | |
| "grad_norm": 3.325737953186035, | |
| "learning_rate": 0.00014, | |
| "loss": 2.9736, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0002608731096889903, | |
| "grad_norm": 2.959261894226074, | |
| "learning_rate": 0.00016, | |
| "loss": 2.8115, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002608731096889903, | |
| "eval_loss": 2.495354413986206, | |
| "eval_runtime": 400.9211, | |
| "eval_samples_per_second": 16.105, | |
| "eval_steps_per_second": 16.105, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00029348224840011414, | |
| "grad_norm": 3.5420632362365723, | |
| "learning_rate": 0.00018, | |
| "loss": 2.6092, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0003260913871112379, | |
| "grad_norm": 3.2168703079223633, | |
| "learning_rate": 0.0002, | |
| "loss": 2.1234, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0003260913871112379, | |
| "eval_loss": 2.3552844524383545, | |
| "eval_runtime": 400.4535, | |
| "eval_samples_per_second": 16.124, | |
| "eval_steps_per_second": 16.124, | |
| "step": 10 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 10, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 2, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 967722569564160.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |