| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.946236559139785, | |
| "eval_steps": 500, | |
| "global_step": 11, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08602150537634409, | |
| "grad_norm": 0.979141891002655, | |
| "learning_rate": 4.898732434036244e-05, | |
| "loss": 0.9567, | |
| "num_input_tokens_seen": 2097152, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.17204301075268819, | |
| "grad_norm": 0.6088763475418091, | |
| "learning_rate": 4.6031338320779534e-05, | |
| "loss": 0.9146, | |
| "num_input_tokens_seen": 4194304, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.25806451612903225, | |
| "grad_norm": 1.0809179544448853, | |
| "learning_rate": 4.137151834863213e-05, | |
| "loss": 0.8763, | |
| "num_input_tokens_seen": 6291456, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.34408602150537637, | |
| "grad_norm": 1.0754276514053345, | |
| "learning_rate": 3.5385375325047166e-05, | |
| "loss": 0.9113, | |
| "num_input_tokens_seen": 8388608, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.43010752688172044, | |
| "grad_norm": 0.4839036166667938, | |
| "learning_rate": 2.8557870956832132e-05, | |
| "loss": 0.8786, | |
| "num_input_tokens_seen": 10485760, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.5161290322580645, | |
| "grad_norm": 0.6119584441184998, | |
| "learning_rate": 2.1442129043167874e-05, | |
| "loss": 0.8796, | |
| "num_input_tokens_seen": 12582912, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.6021505376344086, | |
| "grad_norm": 0.33435240387916565, | |
| "learning_rate": 1.4614624674952842e-05, | |
| "loss": 0.8462, | |
| "num_input_tokens_seen": 14680064, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.6881720430107527, | |
| "grad_norm": 0.32259252667427063, | |
| "learning_rate": 8.628481651367876e-06, | |
| "loss": 0.8707, | |
| "num_input_tokens_seen": 16777216, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.7741935483870968, | |
| "grad_norm": 0.1886083334684372, | |
| "learning_rate": 3.968661679220468e-06, | |
| "loss": 0.8411, | |
| "num_input_tokens_seen": 18874368, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.8602150537634409, | |
| "grad_norm": 0.16534186899662018, | |
| "learning_rate": 1.0126756596375686e-06, | |
| "loss": 0.8267, | |
| "num_input_tokens_seen": 20971520, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.946236559139785, | |
| "grad_norm": 0.1587287038564682, | |
| "learning_rate": 0.0, | |
| "loss": 0.8827, | |
| "num_input_tokens_seen": 23068672, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.946236559139785, | |
| "num_input_tokens_seen": 23068672, | |
| "step": 11, | |
| "total_flos": 1.0387718738584535e+18, | |
| "train_loss": 0.8804038058627736, | |
| "train_runtime": 1203.6155, | |
| "train_samples_per_second": 4.928, | |
| "train_steps_per_second": 0.009 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 11, | |
| "num_input_tokens_seen": 23068672, | |
| "num_train_epochs": 1, | |
| "save_steps": 500, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 1.0387718738584535e+18, | |
| "train_batch_size": 16, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |