| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.02442002442002442, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.002442002442002442, | |
| "grad_norm": 0.33441662788391113, | |
| "learning_rate": 2e-05, | |
| "loss": 0.446, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.002442002442002442, | |
| "eval_loss": 1.0007834434509277, | |
| "eval_runtime": 4.7655, | |
| "eval_samples_per_second": 36.303, | |
| "eval_steps_per_second": 18.256, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.004884004884004884, | |
| "grad_norm": 6.14304780960083, | |
| "learning_rate": 4e-05, | |
| "loss": 1.0701, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.007326007326007326, | |
| "grad_norm": 11.82050895690918, | |
| "learning_rate": 6e-05, | |
| "loss": 1.7132, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.007326007326007326, | |
| "eval_loss": 0.9921661615371704, | |
| "eval_runtime": 3.3488, | |
| "eval_samples_per_second": 51.661, | |
| "eval_steps_per_second": 25.98, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.009768009768009768, | |
| "grad_norm": 9.052845001220703, | |
| "learning_rate": 8e-05, | |
| "loss": 1.492, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.01221001221001221, | |
| "grad_norm": 3.5522308349609375, | |
| "learning_rate": 0.0001, | |
| "loss": 0.8853, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.014652014652014652, | |
| "grad_norm": 10.843049049377441, | |
| "learning_rate": 0.00012, | |
| "loss": 1.8168, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.014652014652014652, | |
| "eval_loss": 0.8879690766334534, | |
| "eval_runtime": 3.4123, | |
| "eval_samples_per_second": 50.699, | |
| "eval_steps_per_second": 25.496, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.017094017094017096, | |
| "grad_norm": 2.5370852947235107, | |
| "learning_rate": 0.00014, | |
| "loss": 0.733, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.019536019536019536, | |
| "grad_norm": 1.1724138259887695, | |
| "learning_rate": 0.00016, | |
| "loss": 0.463, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.02197802197802198, | |
| "grad_norm": 0.8959239721298218, | |
| "learning_rate": 0.00018, | |
| "loss": 0.469, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02197802197802198, | |
| "eval_loss": 0.7278100848197937, | |
| "eval_runtime": 3.3952, | |
| "eval_samples_per_second": 50.954, | |
| "eval_steps_per_second": 25.624, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.02442002442002442, | |
| "grad_norm": 4.533175945281982, | |
| "learning_rate": 0.0002, | |
| "loss": 0.6153, | |
| "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": 505189157044224.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |