| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.18248175182481752, | |
| "eval_steps": 10, | |
| "global_step": 50, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0036496350364963502, | |
| "eval_loss": 2.5532567501068115, | |
| "eval_runtime": 3.8819, | |
| "eval_samples_per_second": 29.882, | |
| "eval_steps_per_second": 14.941, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.01824817518248175, | |
| "grad_norm": 0.31805118918418884, | |
| "learning_rate": 5e-05, | |
| "loss": 2.5126, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0364963503649635, | |
| "grad_norm": 0.43643781542778015, | |
| "learning_rate": 0.0001, | |
| "loss": 2.5551, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0364963503649635, | |
| "eval_loss": 2.522387742996216, | |
| "eval_runtime": 2.8014, | |
| "eval_samples_per_second": 41.408, | |
| "eval_steps_per_second": 20.704, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.05474452554744526, | |
| "grad_norm": 0.4731990098953247, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 2.4786, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "grad_norm": 0.5890198349952698, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 2.2385, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.072992700729927, | |
| "eval_loss": 2.2581331729888916, | |
| "eval_runtime": 2.169, | |
| "eval_samples_per_second": 53.48, | |
| "eval_steps_per_second": 26.74, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.09124087591240876, | |
| "grad_norm": 0.5110591053962708, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 2.1577, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.10948905109489052, | |
| "grad_norm": 0.5509865880012512, | |
| "learning_rate": 5e-05, | |
| "loss": 2.0208, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.10948905109489052, | |
| "eval_loss": 1.9784634113311768, | |
| "eval_runtime": 2.1817, | |
| "eval_samples_per_second": 53.17, | |
| "eval_steps_per_second": 26.585, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.12773722627737227, | |
| "grad_norm": 0.5470987558364868, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 1.9102, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.145985401459854, | |
| "grad_norm": 0.5841451287269592, | |
| "learning_rate": 1.4644660940672627e-05, | |
| "loss": 1.93, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.145985401459854, | |
| "eval_loss": 1.834256649017334, | |
| "eval_runtime": 2.2161, | |
| "eval_samples_per_second": 52.343, | |
| "eval_steps_per_second": 26.172, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.16423357664233576, | |
| "grad_norm": 0.5830029845237732, | |
| "learning_rate": 3.8060233744356633e-06, | |
| "loss": 1.7527, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.18248175182481752, | |
| "grad_norm": 0.643513560295105, | |
| "learning_rate": 0.0, | |
| "loss": 1.8492, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.18248175182481752, | |
| "eval_loss": 1.8075827360153198, | |
| "eval_runtime": 2.3061, | |
| "eval_samples_per_second": 50.302, | |
| "eval_steps_per_second": 25.151, | |
| "step": 50 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1278959891251200.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |