| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.00032382108884841123, | |
| "eval_steps": 3, | |
| "global_step": 10, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 3.238210888484113e-05, | |
| "grad_norm": 2.717174530029297, | |
| "learning_rate": 2e-05, | |
| "loss": 1.1754, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 3.238210888484113e-05, | |
| "eval_loss": 1.4427663087844849, | |
| "eval_runtime": 375.0719, | |
| "eval_samples_per_second": 34.668, | |
| "eval_steps_per_second": 17.335, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 6.476421776968226e-05, | |
| "grad_norm": 3.1423768997192383, | |
| "learning_rate": 4e-05, | |
| "loss": 1.5554, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 9.714632665452337e-05, | |
| "grad_norm": 1.973060965538025, | |
| "learning_rate": 6e-05, | |
| "loss": 1.2269, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 9.714632665452337e-05, | |
| "eval_loss": 1.401381492614746, | |
| "eval_runtime": 375.6048, | |
| "eval_samples_per_second": 34.619, | |
| "eval_steps_per_second": 17.311, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0001295284355393645, | |
| "grad_norm": 2.8488619327545166, | |
| "learning_rate": 8e-05, | |
| "loss": 1.5003, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.00016191054442420561, | |
| "grad_norm": 2.439563512802124, | |
| "learning_rate": 0.0001, | |
| "loss": 1.2068, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.00019429265330904674, | |
| "grad_norm": 2.0994584560394287, | |
| "learning_rate": 0.00012, | |
| "loss": 1.2027, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00019429265330904674, | |
| "eval_loss": 0.9562381505966187, | |
| "eval_runtime": 377.6739, | |
| "eval_samples_per_second": 34.429, | |
| "eval_steps_per_second": 17.216, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.00022667476219388787, | |
| "grad_norm": 2.5944273471832275, | |
| "learning_rate": 0.00014, | |
| "loss": 0.8524, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.000259056871078729, | |
| "grad_norm": 1.3427540063858032, | |
| "learning_rate": 0.00016, | |
| "loss": 0.9904, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.00029143897996357013, | |
| "grad_norm": 2.0642831325531006, | |
| "learning_rate": 0.00018, | |
| "loss": 0.8735, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00029143897996357013, | |
| "eval_loss": 0.6668707728385925, | |
| "eval_runtime": 377.908, | |
| "eval_samples_per_second": 34.408, | |
| "eval_steps_per_second": 17.205, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.00032382108884841123, | |
| "grad_norm": 1.7546979188919067, | |
| "learning_rate": 0.0002, | |
| "loss": 0.7048, | |
| "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": 612619230117888.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |