| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00016525784355039951, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 1.652578435503995e-05, | |
| "grad_norm": 1.5268281698226929, | |
| "learning_rate": 2e-05, | |
| "loss": 7.6901, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 1.652578435503995e-05, | |
| "eval_loss": 1.7071666717529297, | |
| "eval_runtime": 711.2494, | |
| "eval_samples_per_second": 35.823, | |
| "eval_steps_per_second": 17.912, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.30515687100799e-05, | |
| "grad_norm": 1.5581204891204834, | |
| "learning_rate": 4e-05, | |
| "loss": 8.3603, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 4.9577353065119854e-05, | |
| "grad_norm": 1.373064637184143, | |
| "learning_rate": 6e-05, | |
| "loss": 9.0353, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 4.9577353065119854e-05, | |
| "eval_loss": 1.706829309463501, | |
| "eval_runtime": 708.6623, | |
| "eval_samples_per_second": 35.954, | |
| "eval_steps_per_second": 17.978, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 6.61031374201598e-05, | |
| "grad_norm": 1.8199676275253296, | |
| "learning_rate": 8e-05, | |
| "loss": 7.9109, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 8.262892177519976e-05, | |
| "grad_norm": 2.0034425258636475, | |
| "learning_rate": 0.0001, | |
| "loss": 8.509, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 9.915470613023971e-05, | |
| "grad_norm": 1.5793169736862183, | |
| "learning_rate": 0.00012, | |
| "loss": 7.16, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 9.915470613023971e-05, | |
| "eval_loss": 1.6756184101104736, | |
| "eval_runtime": 708.1939, | |
| "eval_samples_per_second": 35.977, | |
| "eval_steps_per_second": 17.989, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00011568049048527966, | |
| "grad_norm": 2.367051362991333, | |
| "learning_rate": 0.00014, | |
| "loss": 6.6789, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0001322062748403196, | |
| "grad_norm": 3.2180848121643066, | |
| "learning_rate": 0.00016, | |
| "loss": 6.5946, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00014873205919535955, | |
| "grad_norm": 5.034686088562012, | |
| "learning_rate": 0.00018, | |
| "loss": 6.5378, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00014873205919535955, | |
| "eval_loss": 1.4698232412338257, | |
| "eval_runtime": 710.1519, | |
| "eval_samples_per_second": 35.878, | |
| "eval_steps_per_second": 17.94, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00016525784355039951, | |
| "grad_norm": 5.680718421936035, | |
| "learning_rate": 0.0002, | |
| "loss": 7.4161, | |
| "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": 1632478030725120.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |