| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 3.0, |
| "eval_steps": 500, |
| "global_step": 222, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.13513513513513514, |
| "grad_norm": 8.553983688354492, |
| "learning_rate": 2.9985590229902075e-05, |
| "loss": 2.2413, |
| "step": 10 |
| }, |
| { |
| "epoch": 0.2702702702702703, |
| "grad_norm": 6.761566162109375, |
| "learning_rate": 2.9769996963595184e-05, |
| "loss": 1.9233, |
| "step": 20 |
| }, |
| { |
| "epoch": 0.40540540540540543, |
| "grad_norm": 4.515566349029541, |
| "learning_rate": 2.9231601996901433e-05, |
| "loss": 1.6958, |
| "step": 30 |
| }, |
| { |
| "epoch": 0.5405405405405406, |
| "grad_norm": 4.692012310028076, |
| "learning_rate": 2.8389885141842673e-05, |
| "loss": 1.5499, |
| "step": 40 |
| }, |
| { |
| "epoch": 0.6756756756756757, |
| "grad_norm": 4.716691970825195, |
| "learning_rate": 2.7262786131837576e-05, |
| "loss": 1.5507, |
| "step": 50 |
| }, |
| { |
| "epoch": 0.8108108108108109, |
| "grad_norm": 3.746539354324341, |
| "learning_rate": 2.5874327125471205e-05, |
| "loss": 1.5286, |
| "step": 60 |
| }, |
| { |
| "epoch": 0.9459459459459459, |
| "grad_norm": 4.379043102264404, |
| "learning_rate": 2.4254100715890846e-05, |
| "loss": 1.4556, |
| "step": 70 |
| }, |
| { |
| "epoch": 1.0810810810810811, |
| "grad_norm": 4.175866603851318, |
| "learning_rate": 2.2436639216060278e-05, |
| "loss": 1.4824, |
| "step": 80 |
| }, |
| { |
| "epoch": 1.2162162162162162, |
| "grad_norm": 4.680153846740723, |
| "learning_rate": 2.0460678662462197e-05, |
| "loss": 1.3278, |
| "step": 90 |
| }, |
| { |
| "epoch": 1.3513513513513513, |
| "grad_norm": 4.0540876388549805, |
| "learning_rate": 1.83683332237322e-05, |
| "loss": 1.1611, |
| "step": 100 |
| }, |
| { |
| "epoch": 1.4864864864864864, |
| "grad_norm": 4.385258674621582, |
| "learning_rate": 1.6204197610270818e-05, |
| "loss": 1.2449, |
| "step": 110 |
| }, |
| { |
| "epoch": 1.6216216216216215, |
| "grad_norm": 3.5538058280944824, |
| "learning_rate": 1.4014396615414458e-05, |
| "loss": 1.241, |
| "step": 120 |
| }, |
| { |
| "epoch": 1.7567567567567568, |
| "grad_norm": 4.351037979125977, |
| "learning_rate": 1.184560204554501e-05, |
| "loss": 1.3186, |
| "step": 130 |
| }, |
| { |
| "epoch": 1.8918918918918919, |
| "grad_norm": 4.51339864730835, |
| "learning_rate": 9.74403799156606e-06, |
| "loss": 1.1958, |
| "step": 140 |
| }, |
| { |
| "epoch": 2.027027027027027, |
| "grad_norm": 3.8219175338745117, |
| "learning_rate": 7.754495642657282e-06, |
| "loss": 1.3746, |
| "step": 150 |
| }, |
| { |
| "epoch": 2.1621621621621623, |
| "grad_norm": 3.6247808933258057, |
| "learning_rate": 5.919378639841282e-06, |
| "loss": 1.1587, |
| "step": 160 |
| }, |
| { |
| "epoch": 2.2972972972972974, |
| "grad_norm": 3.5114660263061523, |
| "learning_rate": 4.277799315994287e-06, |
| "loss": 1.1466, |
| "step": 170 |
| }, |
| { |
| "epoch": 2.4324324324324325, |
| "grad_norm": 3.632798433303833, |
| "learning_rate": 2.86474508437579e-06, |
| "loss": 1.0461, |
| "step": 180 |
| }, |
| { |
| "epoch": 2.5675675675675675, |
| "grad_norm": 3.5737032890319824, |
| "learning_rate": 1.7103327426583264e-06, |
| "loss": 1.0794, |
| "step": 190 |
| }, |
| { |
| "epoch": 2.7027027027027026, |
| "grad_norm": 3.7333688735961914, |
| "learning_rate": 8.391665856723657e-07, |
| "loss": 1.0767, |
| "step": 200 |
| }, |
| { |
| "epoch": 2.8378378378378377, |
| "grad_norm": 3.0237176418304443, |
| "learning_rate": 2.698140075787459e-07, |
| "loss": 1.1567, |
| "step": 210 |
| }, |
| { |
| "epoch": 2.972972972972973, |
| "grad_norm": 3.271709680557251, |
| "learning_rate": 1.4409770097926767e-08, |
| "loss": 1.0932, |
| "step": 220 |
| }, |
| { |
| "epoch": 3.0, |
| "step": 222, |
| "total_flos": 941914803142656.0, |
| "train_loss": 1.365021477948438, |
| "train_runtime": 75.8765, |
| "train_samples_per_second": 46.497, |
| "train_steps_per_second": 2.926 |
| } |
| ], |
| "logging_steps": 10, |
| "max_steps": 222, |
| "num_input_tokens_seen": 0, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "stateful_callbacks": { |
| "TrainerControl": { |
| "args": { |
| "should_epoch_stop": false, |
| "should_evaluate": false, |
| "should_log": false, |
| "should_save": false, |
| "should_training_stop": false |
| }, |
| "attributes": {} |
| } |
| }, |
| "total_flos": 941914803142656.0, |
| "train_batch_size": 16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
