| { |
| "best_global_step": null, |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 0.15047493651838614, |
| "eval_steps": 100, |
| "global_step": 200, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.007523746825919308, |
| "grad_norm": 60.44245910644531, |
| "learning_rate": 1.7999999999999997e-05, |
| "loss": 86.4235, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.015047493651838616, |
| "grad_norm": 40.04138946533203, |
| "learning_rate": 3.8e-05, |
| "loss": 65.01, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.022571240477757923, |
| "grad_norm": 30.586576461791992, |
| "learning_rate": 5.7999999999999994e-05, |
| "loss": 45.3936, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.030094987303677233, |
| "grad_norm": 27.570419311523438, |
| "learning_rate": 7.8e-05, |
| "loss": 34.0648, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.037618734129596536, |
| "grad_norm": 26.078763961791992, |
| "learning_rate": 9.799999999999998e-05, |
| "loss": 28.1261, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.045142480955515846, |
| "grad_norm": 24.367155075073242, |
| "learning_rate": 0.00011799999999999998, |
| "loss": 23.8896, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.052666227781435156, |
| "grad_norm": 18.385601043701172, |
| "learning_rate": 0.000138, |
| "loss": 19.575, |
| "step": 70 |
| }, |
| { |
| "epoch": 0.060189974607354466, |
| "grad_norm": 13.478289604187012, |
| "learning_rate": 0.00015799999999999996, |
| "loss": 14.9189, |
| "step": 80 |
| }, |
| { |
| "epoch": 0.06771372143327377, |
| "grad_norm": 8.762843132019043, |
| "learning_rate": 0.000178, |
| "loss": 10.0506, |
| "step": 90 |
| }, |
| { |
| "epoch": 0.07523746825919307, |
| "grad_norm": 8.72549057006836, |
| "learning_rate": 0.000198, |
| "loss": 5.6379, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.07523746825919307, |
| "eval_loss": 0.49864813685417175, |
| "eval_runtime": 38.1955, |
| "eval_samples_per_second": 32.91, |
| "eval_steps_per_second": 8.247, |
| "step": 100 |
| }, |
| { |
| "epoch": 0.08276121508511239, |
| "grad_norm": 6.59492826461792, |
| "learning_rate": 0.00021799999999999999, |
| "loss": 2.9898, |
| "step": 110 |
| }, |
| { |
| "epoch": 0.09028496191103169, |
| "grad_norm": 2.056182384490967, |
| "learning_rate": 0.00023799999999999998, |
| "loss": 1.6078, |
| "step": 120 |
| }, |
| { |
| "epoch": 0.09780870873695101, |
| "grad_norm": 1.4380172491073608, |
| "learning_rate": 0.000258, |
| "loss": 0.8847, |
| "step": 130 |
| }, |
| { |
| "epoch": 0.10533245556287031, |
| "grad_norm": 1.7172917127609253, |
| "learning_rate": 0.000278, |
| "loss": 0.6103, |
| "step": 140 |
| }, |
| { |
| "epoch": 0.11285620238878961, |
| "grad_norm": 0.5045933723449707, |
| "learning_rate": 0.000298, |
| "loss": 0.3398, |
| "step": 150 |
| }, |
| { |
| "epoch": 0.12037994921470893, |
| "grad_norm": 0.30618351697921753, |
| "learning_rate": 0.0002964, |
| "loss": 0.1732, |
| "step": 160 |
| }, |
| { |
| "epoch": 0.12790369604062823, |
| "grad_norm": 0.7540925145149231, |
| "learning_rate": 0.0002924, |
| "loss": 0.1196, |
| "step": 170 |
| }, |
| { |
| "epoch": 0.13542744286654754, |
| "grad_norm": 0.25162777304649353, |
| "learning_rate": 0.00028839999999999996, |
| "loss": 0.1363, |
| "step": 180 |
| }, |
| { |
| "epoch": 0.14295118969246684, |
| "grad_norm": 0.12225139141082764, |
| "learning_rate": 0.0002844, |
| "loss": 0.0717, |
| "step": 190 |
| }, |
| { |
| "epoch": 0.15047493651838614, |
| "grad_norm": 1.7007333040237427, |
| "learning_rate": 0.0002804, |
| "loss": 0.1011, |
| "step": 200 |
| }, |
| { |
| "epoch": 0.15047493651838614, |
| "eval_loss": 0.012117554433643818, |
| "eval_runtime": 38.2632, |
| "eval_samples_per_second": 32.851, |
| "eval_steps_per_second": 8.232, |
| "step": 200 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 900, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 1, |
| "save_steps": 100, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": true, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 3388839926169600.0, |
| "train_batch_size": 4, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
