| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.943589743589744, | |
| "eval_steps": 500, | |
| "global_step": 144, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.10256410256410256, | |
| "grad_norm": 6.330384731292725, | |
| "learning_rate": 2e-05, | |
| "loss": 0.9917, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.20512820512820512, | |
| "grad_norm": 2.223167896270752, | |
| "learning_rate": 1.9936215093023884e-05, | |
| "loss": 0.7004, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.3076923076923077, | |
| "grad_norm": 1.8093996047973633, | |
| "learning_rate": 1.974567407496712e-05, | |
| "loss": 0.5531, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.41025641025641024, | |
| "grad_norm": 1.6542998552322388, | |
| "learning_rate": 1.9430807674052092e-05, | |
| "loss": 0.4873, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.5128205128205128, | |
| "grad_norm": 1.5152506828308105, | |
| "learning_rate": 1.899563263509725e-05, | |
| "loss": 0.4658, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.6153846153846154, | |
| "grad_norm": 1.466179370880127, | |
| "learning_rate": 1.8445700477978207e-05, | |
| "loss": 0.4239, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.717948717948718, | |
| "grad_norm": 1.3292107582092285, | |
| "learning_rate": 1.778802667699196e-05, | |
| "loss": 0.4138, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.8205128205128205, | |
| "grad_norm": 1.4440351724624634, | |
| "learning_rate": 1.7031001164581828e-05, | |
| "loss": 0.3948, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.9230769230769231, | |
| "grad_norm": 1.3163414001464844, | |
| "learning_rate": 1.618428130112533e-05, | |
| "loss": 0.3881, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 1.0205128205128204, | |
| "grad_norm": 1.3107187747955322, | |
| "learning_rate": 1.5258668676167548e-05, | |
| "loss": 0.3565, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 1.123076923076923, | |
| "grad_norm": 1.3364475965499878, | |
| "learning_rate": 1.4265971312744252e-05, | |
| "loss": 0.324, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 1.2256410256410257, | |
| "grad_norm": 1.1268199682235718, | |
| "learning_rate": 1.3218853032651719e-05, | |
| "loss": 0.3167, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 1.3282051282051281, | |
| "grad_norm": 1.2984614372253418, | |
| "learning_rate": 1.2130671904307692e-05, | |
| "loss": 0.3045, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 1.4307692307692308, | |
| "grad_norm": 1.2189068794250488, | |
| "learning_rate": 1.1015309834121083e-05, | |
| "loss": 0.2888, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 1.5333333333333332, | |
| "grad_norm": 1.208184003829956, | |
| "learning_rate": 9.886995475270205e-06, | |
| "loss": 0.2973, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 1.6358974358974359, | |
| "grad_norm": 1.1965588331222534, | |
| "learning_rate": 8.76012271303888e-06, | |
| "loss": 0.2931, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 1.7384615384615385, | |
| "grad_norm": 1.1966915130615234, | |
| "learning_rate": 7.649067042289681e-06, | |
| "loss": 0.2915, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 1.8410256410256411, | |
| "grad_norm": 1.2417312860488892, | |
| "learning_rate": 6.568002179543409e-06, | |
| "loss": 0.2858, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 1.9435897435897436, | |
| "grad_norm": 1.2801405191421509, | |
| "learning_rate": 5.530719249141148e-06, | |
| "loss": 0.287, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 2.041025641025641, | |
| "grad_norm": 1.1753469705581665, | |
| "learning_rate": 4.550450850127626e-06, | |
| "loss": 0.2573, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 2.1435897435897435, | |
| "grad_norm": 1.3422598838806152, | |
| "learning_rate": 3.6397022482313804e-06, | |
| "loss": 0.2207, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 2.246153846153846, | |
| "grad_norm": 1.1634305715560913, | |
| "learning_rate": 2.8100918464225304e-06, | |
| "loss": 0.2188, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 2.348717948717949, | |
| "grad_norm": 1.2047914266586304, | |
| "learning_rate": 2.072202969162234e-06, | |
| "loss": 0.2144, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 2.4512820512820515, | |
| "grad_norm": 1.1728473901748657, | |
| "learning_rate": 1.4354488511294418e-06, | |
| "loss": 0.2065, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 2.5538461538461537, | |
| "grad_norm": 1.2496421337127686, | |
| "learning_rate": 9.079525527612321e-07, | |
| "loss": 0.2107, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 2.6564102564102563, | |
| "grad_norm": 1.200203537940979, | |
| "learning_rate": 4.964433345219354e-07, | |
| "loss": 0.2083, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 2.758974358974359, | |
| "grad_norm": 1.2024612426757812, | |
| "learning_rate": 2.0617081185259512e-07, | |
| "loss": 0.2111, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 2.8615384615384616, | |
| "grad_norm": 1.1126112937927246, | |
| "learning_rate": 4.083798592444899e-08, | |
| "loss": 0.2157, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 2.943589743589744, | |
| "step": 144, | |
| "total_flos": 5.491122506196582e+16, | |
| "train_loss": 0.34712929568356937, | |
| "train_runtime": 1463.7078, | |
| "train_samples_per_second": 6.393, | |
| "train_steps_per_second": 0.098 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 144, | |
| "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": 5.491122506196582e+16, | |
| "train_batch_size": 4, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |