| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0021315260906991677, | |
| "eval_steps": 10, | |
| "global_step": 39, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 5.465451514613251e-05, | |
| "eval_loss": 3.0376367568969727, | |
| "eval_runtime": 692.0351, | |
| "eval_samples_per_second": 11.132, | |
| "eval_steps_per_second": 5.566, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.00027327257573066255, | |
| "grad_norm": 9.199381828308105, | |
| "learning_rate": 5e-05, | |
| "loss": 13.2748, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.0005465451514613251, | |
| "grad_norm": 10.021293640136719, | |
| "learning_rate": 0.0001, | |
| "loss": 12.8217, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0005465451514613251, | |
| "eval_loss": 2.7879865169525146, | |
| "eval_runtime": 693.1951, | |
| "eval_samples_per_second": 11.114, | |
| "eval_steps_per_second": 5.557, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.0008198177271919876, | |
| "grad_norm": 4.444485664367676, | |
| "learning_rate": 9.619397662556435e-05, | |
| "loss": 10.9946, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.0010930903029226502, | |
| "grad_norm": 6.395273685455322, | |
| "learning_rate": 8.535533905932738e-05, | |
| "loss": 9.5317, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0010930903029226502, | |
| "eval_loss": 2.2416298389434814, | |
| "eval_runtime": 695.2564, | |
| "eval_samples_per_second": 11.081, | |
| "eval_steps_per_second": 5.54, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.0013663628786533127, | |
| "grad_norm": 7.272201061248779, | |
| "learning_rate": 6.91341716182545e-05, | |
| "loss": 8.8218, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0016396354543839753, | |
| "grad_norm": 7.44797945022583, | |
| "learning_rate": 5e-05, | |
| "loss": 8.5272, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0016396354543839753, | |
| "eval_loss": 2.082500696182251, | |
| "eval_runtime": 695.0217, | |
| "eval_samples_per_second": 11.085, | |
| "eval_steps_per_second": 5.542, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.0019129080301146378, | |
| "grad_norm": 9.079113960266113, | |
| "learning_rate": 3.086582838174551e-05, | |
| "loss": 8.1588, | |
| "step": 35 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 50, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 13, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2328864478986240.0, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |