| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.000173181914612657, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.73181914612657e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 2e-05, | |
| "loss": 0.0, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.73181914612657e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 562.7548, | |
| "eval_samples_per_second": 43.204, | |
| "eval_steps_per_second": 21.603, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.46363829225314e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 4e-05, | |
| "loss": 0.0, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 5.19545743837971e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 6e-05, | |
| "loss": 0.0, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 5.19545743837971e-05, | |
| "eval_loss": NaN, | |
| "eval_runtime": 565.0659, | |
| "eval_samples_per_second": 43.027, | |
| "eval_steps_per_second": 21.514, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.92727658450628e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 8e-05, | |
| "loss": 0.0, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.65909573063285e-05, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.0001, | |
| "loss": 0.0, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0001039091487675942, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00012, | |
| "loss": 0.0, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001039091487675942, | |
| "eval_loss": NaN, | |
| "eval_runtime": 560.125, | |
| "eval_samples_per_second": 43.406, | |
| "eval_steps_per_second": 21.704, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0001212273402288599, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00014, | |
| "loss": 0.0, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001385455316901256, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00016, | |
| "loss": 0.0, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0001558637231513913, | |
| "grad_norm": NaN, | |
| "learning_rate": 0.00018, | |
| "loss": 0.0, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0001558637231513913, | |
| "eval_loss": NaN, | |
| "eval_runtime": 550.5071, | |
| "eval_samples_per_second": 44.165, | |
| "eval_steps_per_second": 22.083, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.000173181914612657, | |
| "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": 445910105456640.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |