| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.012759170653907496, | |
| "eval_steps": 8, | |
| "global_step": 30, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0004253056884635832, | |
| "eval_loss": 0.8287492990493774, | |
| "eval_runtime": 127.9312, | |
| "eval_samples_per_second": 7.739, | |
| "eval_steps_per_second": 3.869, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0012759170653907496, | |
| "grad_norm": 0.42551228404045105, | |
| "learning_rate": 3e-05, | |
| "loss": 0.7902, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.002551834130781499, | |
| "grad_norm": 0.56479811668396, | |
| "learning_rate": 6e-05, | |
| "loss": 0.8788, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0034024455077086655, | |
| "eval_loss": 0.7838583588600159, | |
| "eval_runtime": 129.026, | |
| "eval_samples_per_second": 7.673, | |
| "eval_steps_per_second": 3.836, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.003827751196172249, | |
| "grad_norm": 0.39707711338996887, | |
| "learning_rate": 9e-05, | |
| "loss": 0.7425, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.005103668261562998, | |
| "grad_norm": 0.6653342843055725, | |
| "learning_rate": 9.755282581475769e-05, | |
| "loss": 0.7367, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.006379585326953748, | |
| "grad_norm": 0.5052664875984192, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 0.7233, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.006804891015417331, | |
| "eval_loss": 0.7022345066070557, | |
| "eval_runtime": 129.01, | |
| "eval_samples_per_second": 7.674, | |
| "eval_steps_per_second": 3.837, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.007655502392344498, | |
| "grad_norm": 0.5549106001853943, | |
| "learning_rate": 6.545084971874738e-05, | |
| "loss": 0.6407, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.008931419457735247, | |
| "grad_norm": 0.580598771572113, | |
| "learning_rate": 4.2178276747988446e-05, | |
| "loss": 0.7108, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "grad_norm": 0.5167686939239502, | |
| "learning_rate": 2.061073738537635e-05, | |
| "loss": 0.631, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.010207336523125997, | |
| "eval_loss": 0.6679226160049438, | |
| "eval_runtime": 129.0328, | |
| "eval_samples_per_second": 7.672, | |
| "eval_steps_per_second": 3.836, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.011483253588516746, | |
| "grad_norm": 0.5240839123725891, | |
| "learning_rate": 5.449673790581611e-06, | |
| "loss": 0.694, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 0.012759170653907496, | |
| "grad_norm": 0.4730253517627716, | |
| "learning_rate": 0.0, | |
| "loss": 0.6328, | |
| "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": 1.112830925340672e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |