| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0007120393995134397, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 2.373464665044799e-05, | |
| "eval_loss": 1.3943467140197754, | |
| "eval_runtime": 1877.3027, | |
| "eval_samples_per_second": 9.45, | |
| "eval_steps_per_second": 4.725, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 7.120393995134398e-05, | |
| "grad_norm": 14.41858959197998, | |
| "learning_rate": 6e-05, | |
| "loss": 5.8743, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00014240787990268795, | |
| "grad_norm": 7.234719276428223, | |
| "learning_rate": 0.00012, | |
| "loss": 4.4264, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00018987717320358393, | |
| "eval_loss": 0.6964398622512817, | |
| "eval_runtime": 1877.7151, | |
| "eval_samples_per_second": 9.448, | |
| "eval_steps_per_second": 4.724, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0002136118198540319, | |
| "grad_norm": 4.966245174407959, | |
| "learning_rate": 0.00018, | |
| "loss": 2.7989, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0002848157598053759, | |
| "grad_norm": 4.004361629486084, | |
| "learning_rate": 0.00019510565162951537, | |
| "loss": 2.2768, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.00035601969975671986, | |
| "grad_norm": 2.4428646564483643, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 2.4227, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.00037975434640716787, | |
| "eval_loss": 0.48976579308509827, | |
| "eval_runtime": 1875.0182, | |
| "eval_samples_per_second": 9.461, | |
| "eval_steps_per_second": 4.731, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.0004272236397080638, | |
| "grad_norm": 1.8519223928451538, | |
| "learning_rate": 0.00013090169943749476, | |
| "loss": 1.8599, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.0004984275796594078, | |
| "grad_norm": 1.9304282665252686, | |
| "learning_rate": 8.435655349597689e-05, | |
| "loss": 1.9402, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.0005696315196107518, | |
| "grad_norm": 1.97409987449646, | |
| "learning_rate": 4.12214747707527e-05, | |
| "loss": 2.0165, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0005696315196107518, | |
| "eval_loss": 0.4720425009727478, | |
| "eval_runtime": 1873.0838, | |
| "eval_samples_per_second": 9.471, | |
| "eval_steps_per_second": 4.736, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0006408354595620958, | |
| "grad_norm": 2.031785726547241, | |
| "learning_rate": 1.0899347581163221e-05, | |
| "loss": 1.8595, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.0007120393995134397, | |
| "grad_norm": 1.998368740081787, | |
| "learning_rate": 0.0, | |
| "loss": 2.1204, | |
| "step": 30 | |
| } | |
| ], | |
| "logging_steps": 3, | |
| "max_steps": 30, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 10, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.9863419712700416e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |