| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.014847809948032665, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0014847809948032665, | |
| "grad_norm": 3.460620164871216, | |
| "learning_rate": 2e-05, | |
| "loss": 11.7266, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0014847809948032665, | |
| "eval_loss": 2.9430558681488037, | |
| "eval_runtime": 15.182, | |
| "eval_samples_per_second": 18.706, | |
| "eval_steps_per_second": 9.353, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002969561989606533, | |
| "grad_norm": 4.292764663696289, | |
| "learning_rate": 4e-05, | |
| "loss": 11.2694, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.004454342984409799, | |
| "grad_norm": 2.9690873622894287, | |
| "learning_rate": 6e-05, | |
| "loss": 13.7768, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.004454342984409799, | |
| "eval_loss": 2.9312167167663574, | |
| "eval_runtime": 15.2001, | |
| "eval_samples_per_second": 18.684, | |
| "eval_steps_per_second": 9.342, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.005939123979213066, | |
| "grad_norm": 2.7106869220733643, | |
| "learning_rate": 8e-05, | |
| "loss": 8.8244, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.007423904974016332, | |
| "grad_norm": 5.264049053192139, | |
| "learning_rate": 0.0001, | |
| "loss": 13.7866, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.008908685968819599, | |
| "grad_norm": 6.880161762237549, | |
| "learning_rate": 0.00012, | |
| "loss": 12.5797, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.008908685968819599, | |
| "eval_loss": 2.713064670562744, | |
| "eval_runtime": 15.2012, | |
| "eval_samples_per_second": 18.683, | |
| "eval_steps_per_second": 9.341, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.010393466963622866, | |
| "grad_norm": 9.196951866149902, | |
| "learning_rate": 0.00014, | |
| "loss": 10.1094, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.011878247958426132, | |
| "grad_norm": 8.100080490112305, | |
| "learning_rate": 0.00016, | |
| "loss": 10.5962, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.013363028953229399, | |
| "grad_norm": 23.556520462036133, | |
| "learning_rate": 0.00018, | |
| "loss": 8.5635, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.013363028953229399, | |
| "eval_loss": 1.4313316345214844, | |
| "eval_runtime": 15.2328, | |
| "eval_samples_per_second": 18.644, | |
| "eval_steps_per_second": 9.322, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.014847809948032665, | |
| "grad_norm": 9.365063667297363, | |
| "learning_rate": 0.0002, | |
| "loss": 5.2709, | |
| "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": 3166224305356800.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |