| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0006903574325607083, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 6.903574325607083e-05, | |
| "grad_norm": 1.646234393119812, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9717, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.903574325607083e-05, | |
| "eval_loss": 1.402584433555603, | |
| "eval_runtime": 224.6901, | |
| "eval_samples_per_second": 27.144, | |
| "eval_steps_per_second": 13.574, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00013807148651214166, | |
| "grad_norm": 0.5239061117172241, | |
| "learning_rate": 4e-05, | |
| "loss": 0.3297, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.00020710722976821248, | |
| "grad_norm": 1.5050429105758667, | |
| "learning_rate": 6e-05, | |
| "loss": 1.0094, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.00020710722976821248, | |
| "eval_loss": 1.3910108804702759, | |
| "eval_runtime": 222.6889, | |
| "eval_samples_per_second": 27.388, | |
| "eval_steps_per_second": 13.696, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0002761429730242833, | |
| "grad_norm": 1.0256320238113403, | |
| "learning_rate": 8e-05, | |
| "loss": 0.6222, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00034517871628035417, | |
| "grad_norm": 0.9901247024536133, | |
| "learning_rate": 0.0001, | |
| "loss": 0.6314, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00041421445953642496, | |
| "grad_norm": 1.603949785232544, | |
| "learning_rate": 0.00012, | |
| "loss": 0.8367, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00041421445953642496, | |
| "eval_loss": 1.12848961353302, | |
| "eval_runtime": 222.7601, | |
| "eval_samples_per_second": 27.379, | |
| "eval_steps_per_second": 13.692, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.0004832502027924958, | |
| "grad_norm": 3.9065394401550293, | |
| "learning_rate": 0.00014, | |
| "loss": 1.6585, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.0005522859460485666, | |
| "grad_norm": 1.3636605739593506, | |
| "learning_rate": 0.00016, | |
| "loss": 0.3904, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.0006213216893046374, | |
| "grad_norm": 2.2395458221435547, | |
| "learning_rate": 0.00018, | |
| "loss": 0.455, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006213216893046374, | |
| "eval_loss": 0.3233931362628937, | |
| "eval_runtime": 222.7685, | |
| "eval_samples_per_second": 27.378, | |
| "eval_steps_per_second": 13.691, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.0006903574325607083, | |
| "grad_norm": 0.4859631061553955, | |
| "learning_rate": 0.0002, | |
| "loss": 0.1059, | |
| "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": 2265755663990784.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |