| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.002201067517746107, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00022010675177461069, | |
| "grad_norm": 2.3378818035125732, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9409, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00022010675177461069, | |
| "eval_loss": 1.067487120628357, | |
| "eval_runtime": 60.8202, | |
| "eval_samples_per_second": 31.453, | |
| "eval_steps_per_second": 15.735, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00044021350354922137, | |
| "grad_norm": 1.5687549114227295, | |
| "learning_rate": 4e-05, | |
| "loss": 0.8715, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0006603202553238321, | |
| "grad_norm": 1.8344545364379883, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0449, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0006603202553238321, | |
| "eval_loss": 1.047654628753662, | |
| "eval_runtime": 59.6437, | |
| "eval_samples_per_second": 32.074, | |
| "eval_steps_per_second": 16.045, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0008804270070984427, | |
| "grad_norm": 3.1621816158294678, | |
| "learning_rate": 8e-05, | |
| "loss": 1.0538, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.0011005337588730535, | |
| "grad_norm": 1.8105907440185547, | |
| "learning_rate": 0.0001, | |
| "loss": 0.816, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0013206405106476642, | |
| "grad_norm": 2.7975521087646484, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8251, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0013206405106476642, | |
| "eval_loss": 0.6414834856987, | |
| "eval_runtime": 59.6493, | |
| "eval_samples_per_second": 32.071, | |
| "eval_steps_per_second": 16.044, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0015407472624222747, | |
| "grad_norm": 1.5536985397338867, | |
| "learning_rate": 0.00014, | |
| "loss": 0.5466, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0017608540141968855, | |
| "grad_norm": 1.6163760423660278, | |
| "learning_rate": 0.00016, | |
| "loss": 0.439, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0019809607659714962, | |
| "grad_norm": 1.6741958856582642, | |
| "learning_rate": 0.00018, | |
| "loss": 0.49, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0019809607659714962, | |
| "eval_loss": 0.44979140162467957, | |
| "eval_runtime": 59.7227, | |
| "eval_samples_per_second": 32.031, | |
| "eval_steps_per_second": 16.024, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.002201067517746107, | |
| "grad_norm": 1.604898452758789, | |
| "learning_rate": 0.0002, | |
| "loss": 0.4402, | |
| "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": 1849564248145920.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |