| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.008592910848549946, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "grad_norm": 0.939545214176178, | |
| "learning_rate": 2e-05, | |
| "loss": 3.9193, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0008592910848549946, | |
| "eval_loss": 1.0684140920639038, | |
| "eval_runtime": 26.4233, | |
| "eval_samples_per_second": 18.544, | |
| "eval_steps_per_second": 9.272, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0017185821697099893, | |
| "grad_norm": 1.148201823234558, | |
| "learning_rate": 4e-05, | |
| "loss": 5.0462, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0025778732545649837, | |
| "grad_norm": 1.277715802192688, | |
| "learning_rate": 6e-05, | |
| "loss": 4.4225, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0025778732545649837, | |
| "eval_loss": 1.067508578300476, | |
| "eval_runtime": 26.3981, | |
| "eval_samples_per_second": 18.562, | |
| "eval_steps_per_second": 9.281, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0034371643394199786, | |
| "grad_norm": 1.006024956703186, | |
| "learning_rate": 8e-05, | |
| "loss": 3.2906, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.004296455424274973, | |
| "grad_norm": 1.3687950372695923, | |
| "learning_rate": 0.0001, | |
| "loss": 4.1415, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0051557465091299675, | |
| "grad_norm": 1.1862958669662476, | |
| "learning_rate": 0.00012, | |
| "loss": 4.4577, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0051557465091299675, | |
| "eval_loss": 1.045850157737732, | |
| "eval_runtime": 26.4326, | |
| "eval_samples_per_second": 18.538, | |
| "eval_steps_per_second": 9.269, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.006015037593984963, | |
| "grad_norm": 1.2088669538497925, | |
| "learning_rate": 0.00014, | |
| "loss": 3.0819, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006874328678839957, | |
| "grad_norm": 1.3356318473815918, | |
| "learning_rate": 0.00016, | |
| "loss": 3.2304, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007733619763694952, | |
| "grad_norm": 1.5668182373046875, | |
| "learning_rate": 0.00018, | |
| "loss": 4.0227, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007733619763694952, | |
| "eval_loss": 0.9346973299980164, | |
| "eval_runtime": 26.4204, | |
| "eval_samples_per_second": 18.546, | |
| "eval_steps_per_second": 9.273, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.008592910848549946, | |
| "grad_norm": 1.9096448421478271, | |
| "learning_rate": 0.0002, | |
| "loss": 4.1353, | |
| "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": 2304624644456448.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |