| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.7863309952245419, |
| "eval_steps": 25000, |
| "global_step": 150000, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2977218325374236, |
| "grad_norm": 14.776897430419922, |
| "learning_rate": 4.729071698412804e-05, |
| "loss": 2.2576, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.2977218325374236, |
| "eval_loss": 1.9398064613342285, |
| "eval_runtime": 1130.9439, |
| "eval_samples_per_second": 148.496, |
| "eval_steps_per_second": 1.161, |
| "step": 25000 |
| }, |
| { |
| "epoch": 0.5954436650748473, |
| "grad_norm": 15.924115180969238, |
| "learning_rate": 3.9023268738380516e-05, |
| "loss": 1.9854, |
| "step": 50000 |
| }, |
| { |
| "epoch": 0.5954436650748473, |
| "eval_loss": 1.7355190515518188, |
| "eval_runtime": 1139.3123, |
| "eval_samples_per_second": 147.406, |
| "eval_steps_per_second": 1.152, |
| "step": 50000 |
| }, |
| { |
| "epoch": 0.8931654976122709, |
| "grad_norm": 18.3256893157959, |
| "learning_rate": 3.075648210020709e-05, |
| "loss": 1.8002, |
| "step": 75000 |
| }, |
| { |
| "epoch": 0.8931654976122709, |
| "eval_loss": 1.5857831239700317, |
| "eval_runtime": 1105.4287, |
| "eval_samples_per_second": 151.924, |
| "eval_steps_per_second": 1.188, |
| "step": 75000 |
| }, |
| { |
| "epoch": 1.1908873301496945, |
| "grad_norm": 24.324203491210938, |
| "learning_rate": 2.2488703050672525e-05, |
| "loss": 1.6281, |
| "step": 100000 |
| }, |
| { |
| "epoch": 1.1908873301496945, |
| "eval_loss": 1.4414993524551392, |
| "eval_runtime": 1083.6047, |
| "eval_samples_per_second": 154.984, |
| "eval_steps_per_second": 1.212, |
| "step": 100000 |
| }, |
| { |
| "epoch": 1.4886091626871183, |
| "grad_norm": 21.457475662231445, |
| "learning_rate": 1.4222247216286134e-05, |
| "loss": 1.5041, |
| "step": 125000 |
| }, |
| { |
| "epoch": 1.4886091626871183, |
| "eval_loss": 1.3530445098876953, |
| "eval_runtime": 1069.2866, |
| "eval_samples_per_second": 157.059, |
| "eval_steps_per_second": 1.228, |
| "step": 125000 |
| }, |
| { |
| "epoch": 1.7863309952245419, |
| "grad_norm": 8.10311222076416, |
| "learning_rate": 5.9544681667515734e-06, |
| "loss": 1.4019, |
| "step": 150000 |
| }, |
| { |
| "epoch": 1.7863309952245419, |
| "eval_loss": 1.2703442573547363, |
| "eval_runtime": 1053.7311, |
| "eval_samples_per_second": 159.377, |
| "eval_steps_per_second": 1.246, |
| "step": 150000 |
| } |
| ], |
| "logging_steps": 25000, |
| "max_steps": 167942, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 2, |
| "save_steps": 25000, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 1.1184982650879437e+18, |
| "train_batch_size": 8, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
