| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.5649717514124294, |
| "eval_steps": 500, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.02824858757062147, |
| "grad_norm": 5.842401568474987, |
| "learning_rate": 5e-06, |
| "loss": 2.0396, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.05649717514124294, |
| "grad_norm": 3.6388768595262957, |
| "learning_rate": 4.997468222143782e-06, |
| "loss": 1.7131, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.0847457627118644, |
| "grad_norm": 1.8710689080902667, |
| "learning_rate": 4.989878016494418e-06, |
| "loss": 1.5907, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.11299435028248588, |
| "grad_norm": 1.880666572553662, |
| "learning_rate": 4.977244756423578e-06, |
| "loss": 1.502, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.14124293785310735, |
| "grad_norm": 1.6520564729299156, |
| "learning_rate": 4.959594029617741e-06, |
| "loss": 1.4357, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.1694915254237288, |
| "grad_norm": 1.7284626155394651, |
| "learning_rate": 4.9369615862523266e-06, |
| "loss": 1.3794, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.1977401129943503, |
| "grad_norm": 1.7131842535751252, |
| "learning_rate": 4.90939326658249e-06, |
| "loss": 1.3396, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.22598870056497175, |
| "grad_norm": 1.6872621752920653, |
| "learning_rate": 4.876944908097249e-06, |
| "loss": 1.3119, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.2542372881355932, |
| "grad_norm": 1.6781047658941155, |
| "learning_rate": 4.8396822324249915e-06, |
| "loss": 1.2932, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.2824858757062147, |
| "grad_norm": 1.8225514648316858, |
| "learning_rate": 4.797680712219421e-06, |
| "loss": 1.2533, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.3107344632768362, |
| "grad_norm": 1.4304345855914073, |
| "learning_rate": 4.751025418295565e-06, |
| "loss": 1.2581, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.3389830508474576, |
| "grad_norm": 2.489693154849688, |
| "learning_rate": 4.699810847325449e-06, |
| "loss": 1.2615, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.3672316384180791, |
| "grad_norm": 1.497470889635536, |
| "learning_rate": 4.644140730442432e-06, |
| "loss": 1.2385, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.3954802259887006, |
| "grad_norm": 1.4852922561551125, |
| "learning_rate": 4.584127823141855e-06, |
| "loss": 1.2228, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.423728813559322, |
| "grad_norm": 1.4374567982916069, |
| "learning_rate": 4.5198936769035504e-06, |
| "loss": 1.2254, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.4519774011299435, |
| "grad_norm": 1.4496375733325404, |
| "learning_rate": 4.451568392998767e-06, |
| "loss": 1.2265, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.480225988700565, |
| "grad_norm": 1.2754388779607286, |
| "learning_rate": 4.3792903589801515e-06, |
| "loss": 1.1846, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.5084745762711864, |
| "grad_norm": 1.3975405752824914, |
| "learning_rate": 4.30320596838852e-06, |
| "loss": 1.178, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.536723163841808, |
| "grad_norm": 1.3749489429241677, |
| "learning_rate": 4.223469324244115e-06, |
| "loss": 1.1717, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.5649717514124294, |
| "grad_norm": 1.393315372114993, |
| "learning_rate": 4.140241926922916e-06, |
| "loss": 1.181, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 708, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 200, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 65229815808000.0, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
