| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 113, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.04424778761061947, | |
| "grad_norm": 19.216197967529297, | |
| "learning_rate": 0.0001, | |
| "loss": 2.7696, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.08849557522123894, | |
| "grad_norm": 9.90820598602295, | |
| "learning_rate": 9.537037037037038e-05, | |
| "loss": 2.4474, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.13274336283185842, | |
| "grad_norm": 9.913591384887695, | |
| "learning_rate": 9.074074074074075e-05, | |
| "loss": 2.2249, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.17699115044247787, | |
| "grad_norm": 18.111818313598633, | |
| "learning_rate": 8.611111111111112e-05, | |
| "loss": 2.0585, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.22123893805309736, | |
| "grad_norm": 10.692439079284668, | |
| "learning_rate": 8.148148148148148e-05, | |
| "loss": 1.7636, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.26548672566371684, | |
| "grad_norm": 15.1380033493042, | |
| "learning_rate": 7.685185185185185e-05, | |
| "loss": 1.7311, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.30973451327433627, | |
| "grad_norm": 11.560906410217285, | |
| "learning_rate": 7.222222222222222e-05, | |
| "loss": 1.5557, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.35398230088495575, | |
| "grad_norm": 8.727864265441895, | |
| "learning_rate": 6.759259259259259e-05, | |
| "loss": 1.6089, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.39823008849557523, | |
| "grad_norm": 8.90024185180664, | |
| "learning_rate": 6.296296296296296e-05, | |
| "loss": 1.5712, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.4424778761061947, | |
| "grad_norm": 7.171605587005615, | |
| "learning_rate": 5.833333333333334e-05, | |
| "loss": 1.546, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.48672566371681414, | |
| "grad_norm": 20.623746871948242, | |
| "learning_rate": 5.370370370370371e-05, | |
| "loss": 1.5379, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5309734513274337, | |
| "grad_norm": 9.407456398010254, | |
| "learning_rate": 4.9074074074074075e-05, | |
| "loss": 1.6323, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.5752212389380531, | |
| "grad_norm": 8.466376304626465, | |
| "learning_rate": 4.4444444444444447e-05, | |
| "loss": 1.4755, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6194690265486725, | |
| "grad_norm": 5.661746978759766, | |
| "learning_rate": 3.981481481481482e-05, | |
| "loss": 1.6249, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.6637168141592921, | |
| "grad_norm": 6.674346923828125, | |
| "learning_rate": 3.518518518518519e-05, | |
| "loss": 1.5234, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7079646017699115, | |
| "grad_norm": 5.735414505004883, | |
| "learning_rate": 3.055555555555556e-05, | |
| "loss": 1.1557, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.7522123893805309, | |
| "grad_norm": 8.76235580444336, | |
| "learning_rate": 2.5925925925925925e-05, | |
| "loss": 1.7057, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.7964601769911505, | |
| "grad_norm": 12.130348205566406, | |
| "learning_rate": 2.1296296296296296e-05, | |
| "loss": 1.3106, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8407079646017699, | |
| "grad_norm": 8.450634002685547, | |
| "learning_rate": 1.6666666666666667e-05, | |
| "loss": 1.5108, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.8849557522123894, | |
| "grad_norm": 10.024974822998047, | |
| "learning_rate": 1.2037037037037037e-05, | |
| "loss": 1.3794, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9292035398230089, | |
| "grad_norm": 8.237189292907715, | |
| "learning_rate": 7.4074074074074075e-06, | |
| "loss": 1.2443, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 0.9734513274336283, | |
| "grad_norm": 29.493942260742188, | |
| "learning_rate": 2.777777777777778e-06, | |
| "loss": 1.6901, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "step": 113, | |
| "total_flos": 136942586363904.0, | |
| "train_loss": 1.6811428829631974, | |
| "train_runtime": 7619.7234, | |
| "train_samples_per_second": 0.015, | |
| "train_steps_per_second": 0.015 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 113, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "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": 136942586363904.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |