| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.0, | |
| "eval_steps": 500, | |
| "global_step": 560, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.03571428571428571, | |
| "grad_norm": 1.8447134494781494, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 2.5344, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.07142857142857142, | |
| "grad_norm": 1.3903896808624268, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 1.8578, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.10714285714285714, | |
| "grad_norm": 0.9996151328086853, | |
| "learning_rate": 9.920634920634922e-05, | |
| "loss": 1.161, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.14285714285714285, | |
| "grad_norm": 0.7677631974220276, | |
| "learning_rate": 9.523809523809524e-05, | |
| "loss": 0.9116, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.17857142857142858, | |
| "grad_norm": 1.040696144104004, | |
| "learning_rate": 9.126984126984128e-05, | |
| "loss": 0.8243, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.21428571428571427, | |
| "grad_norm": 0.970762312412262, | |
| "learning_rate": 8.730158730158731e-05, | |
| "loss": 0.7555, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.25, | |
| "grad_norm": 1.0803948640823364, | |
| "learning_rate": 8.333333333333334e-05, | |
| "loss": 0.6679, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.2857142857142857, | |
| "grad_norm": 1.0338200330734253, | |
| "learning_rate": 7.936507936507937e-05, | |
| "loss": 0.6522, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.32142857142857145, | |
| "grad_norm": 0.8714532256126404, | |
| "learning_rate": 7.53968253968254e-05, | |
| "loss": 0.6209, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.35714285714285715, | |
| "grad_norm": 0.9677976965904236, | |
| "learning_rate": 7.142857142857143e-05, | |
| "loss": 0.6242, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.39285714285714285, | |
| "grad_norm": 0.962899386882782, | |
| "learning_rate": 6.746031746031747e-05, | |
| "loss": 0.5844, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.42857142857142855, | |
| "grad_norm": 1.0176018476486206, | |
| "learning_rate": 6.349206349206349e-05, | |
| "loss": 0.5915, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.4642857142857143, | |
| "grad_norm": 0.9592286348342896, | |
| "learning_rate": 5.9523809523809524e-05, | |
| "loss": 0.5948, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "grad_norm": 0.9406882524490356, | |
| "learning_rate": 5.555555555555556e-05, | |
| "loss": 0.5557, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.5357142857142857, | |
| "grad_norm": 1.0566672086715698, | |
| "learning_rate": 5.158730158730159e-05, | |
| "loss": 0.5596, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.5714285714285714, | |
| "grad_norm": 1.0166610479354858, | |
| "learning_rate": 4.761904761904762e-05, | |
| "loss": 0.5514, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.6071428571428571, | |
| "grad_norm": 1.110986590385437, | |
| "learning_rate": 4.3650793650793655e-05, | |
| "loss": 0.5523, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.6428571428571429, | |
| "grad_norm": 1.1951007843017578, | |
| "learning_rate": 3.968253968253968e-05, | |
| "loss": 0.5395, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.6785714285714286, | |
| "grad_norm": 1.0911144018173218, | |
| "learning_rate": 3.571428571428572e-05, | |
| "loss": 0.548, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.7142857142857143, | |
| "grad_norm": 1.1718319654464722, | |
| "learning_rate": 3.1746031746031745e-05, | |
| "loss": 0.5188, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.75, | |
| "grad_norm": 0.9721041917800903, | |
| "learning_rate": 2.777777777777778e-05, | |
| "loss": 0.5081, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.7857142857142857, | |
| "grad_norm": 1.103784203529358, | |
| "learning_rate": 2.380952380952381e-05, | |
| "loss": 0.5183, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.8214285714285714, | |
| "grad_norm": 1.1778147220611572, | |
| "learning_rate": 1.984126984126984e-05, | |
| "loss": 0.5064, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.8571428571428571, | |
| "grad_norm": 1.0783812999725342, | |
| "learning_rate": 1.5873015873015872e-05, | |
| "loss": 0.527, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.8928571428571429, | |
| "grad_norm": 1.0787134170532227, | |
| "learning_rate": 1.1904761904761905e-05, | |
| "loss": 0.5132, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.9285714285714286, | |
| "grad_norm": 1.0964124202728271, | |
| "learning_rate": 7.936507936507936e-06, | |
| "loss": 0.4971, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.9642857142857143, | |
| "grad_norm": 1.1419587135314941, | |
| "learning_rate": 3.968253968253968e-06, | |
| "loss": 0.5368, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 1.0203648805618286, | |
| "learning_rate": 0.0, | |
| "loss": 0.501, | |
| "step": 560 | |
| } | |
| ], | |
| "logging_steps": 20, | |
| "max_steps": 560, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8419093040332800.0, | |
| "train_batch_size": 5, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |