| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.3177966101694915, | |
| "eval_steps": 500, | |
| "global_step": 150, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.00211864406779661, | |
| "grad_norm": 6772.94736433113, | |
| "learning_rate": 5.263157894736842e-06, | |
| "loss": 5.4426, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0211864406779661, | |
| "grad_norm": 43.76552598391156, | |
| "learning_rate": 5.263157894736842e-05, | |
| "loss": 6.5697, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0423728813559322, | |
| "grad_norm": 1.4214989301078385, | |
| "learning_rate": 0.00010526315789473683, | |
| "loss": 5.8015, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0635593220338983, | |
| "grad_norm": 1.8559172078320925, | |
| "learning_rate": 0.00015789473684210527, | |
| "loss": 4.6978, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0847457627118644, | |
| "grad_norm": 0.9523887604864526, | |
| "learning_rate": 0.00021052631578947367, | |
| "loss": 3.9616, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.1059322033898305, | |
| "grad_norm": 0.5313592686196623, | |
| "learning_rate": 0.0002631578947368421, | |
| "loss": 3.2816, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.1271186440677966, | |
| "grad_norm": 0.9882421975844679, | |
| "learning_rate": 0.00031578947368421053, | |
| "loss": 2.9453, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.1483050847457627, | |
| "grad_norm": 1.3764980998221854, | |
| "learning_rate": 0.00036842105263157896, | |
| "loss": 2.7478, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.1694915254237288, | |
| "grad_norm": 0.6188567319965684, | |
| "learning_rate": 0.00042105263157894734, | |
| "loss": 2.6778, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.1906779661016949, | |
| "grad_norm": 0.45391127998861047, | |
| "learning_rate": 0.00047368421052631577, | |
| "loss": 2.6651, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.211864406779661, | |
| "grad_norm": 0.3359651886818045, | |
| "learning_rate": 0.0004999904062938913, | |
| "loss": 2.6871, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.2330508474576271, | |
| "grad_norm": 0.2538059916992196, | |
| "learning_rate": 0.0004999136610628463, | |
| "loss": 2.6047, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 0.2542372881355932, | |
| "grad_norm": 0.7420239318499638, | |
| "learning_rate": 0.0004997601941609823, | |
| "loss": 2.6122, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.2754237288135593, | |
| "grad_norm": 1.0130312150097984, | |
| "learning_rate": 0.0004995300527015189, | |
| "loss": 2.8314, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 0.2966101694915254, | |
| "grad_norm": 0.45185267289061176, | |
| "learning_rate": 0.0004992233073362051, | |
| "loss": 2.7241, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.3177966101694915, | |
| "grad_norm": 1.2647337895757225, | |
| "learning_rate": 0.0004988400522336304, | |
| "loss": 2.6269, | |
| "step": 150 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 1888, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 4, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3715483865972736.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |