| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.11707317073170732, | |
| "eval_steps": 500, | |
| "global_step": 60, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01951219512195122, | |
| "grad_norm": 0.14488260447978973, | |
| "learning_rate": 0.00019934683213585893, | |
| "loss": 0.6356, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.03902439024390244, | |
| "grad_norm": 0.1634250283241272, | |
| "learning_rate": 0.00019804049640757677, | |
| "loss": 0.4368, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.05853658536585366, | |
| "grad_norm": 0.1504327356815338, | |
| "learning_rate": 0.0001967341606792946, | |
| "loss": 0.407, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.07804878048780488, | |
| "grad_norm": 0.16282524168491364, | |
| "learning_rate": 0.00019542782495101242, | |
| "loss": 0.3788, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.0975609756097561, | |
| "grad_norm": 0.17505913972854614, | |
| "learning_rate": 0.00019412148922273026, | |
| "loss": 0.3705, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.11707317073170732, | |
| "grad_norm": 0.18271876871585846, | |
| "learning_rate": 0.00019281515349444807, | |
| "loss": 0.3654, | |
| "step": 60 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1536, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 20, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 4022303701475328.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |