| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 2.6666666666666665, | |
| "eval_steps": 500, | |
| "global_step": 300, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.08888888888888889, | |
| "grad_norm": 29.641796112060547, | |
| "learning_rate": 2.9411764705882354e-05, | |
| "loss": 1.3387, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.17777777777777778, | |
| "grad_norm": 2.8391942977905273, | |
| "learning_rate": 5.882352941176471e-05, | |
| "loss": 1.4468, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.26666666666666666, | |
| "grad_norm": 2.4493441581726074, | |
| "learning_rate": 8.823529411764706e-05, | |
| "loss": 1.0612, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.35555555555555557, | |
| "grad_norm": 2.3891420364379883, | |
| "learning_rate": 9.990263847374976e-05, | |
| "loss": 1.0064, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4444444444444444, | |
| "grad_norm": 1.1571154594421387, | |
| "learning_rate": 9.930902394260747e-05, | |
| "loss": 0.9215, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5333333333333333, | |
| "grad_norm": 1.3602615594863892, | |
| "learning_rate": 9.818229479678158e-05, | |
| "loss": 1.2268, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.6222222222222222, | |
| "grad_norm": 1.3397140502929688, | |
| "learning_rate": 9.653463289927411e-05, | |
| "loss": 0.8976, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7111111111111111, | |
| "grad_norm": 1.1149853467941284, | |
| "learning_rate": 9.438385228425938e-05, | |
| "loss": 0.8541, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.9571573734283447, | |
| "learning_rate": 9.175320655700406e-05, | |
| "loss": 0.8365, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8888888888888888, | |
| "grad_norm": 0.8198672533035278, | |
| "learning_rate": 8.86711374827494e-05, | |
| "loss": 0.8059, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9777777777777777, | |
| "grad_norm": 1.072033166885376, | |
| "learning_rate": 8.517096748273951e-05, | |
| "loss": 0.8329, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0666666666666667, | |
| "grad_norm": 0.9767541885375977, | |
| "learning_rate": 8.129053936203687e-05, | |
| "loss": 0.835, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1555555555555554, | |
| "grad_norm": 1.8347275257110596, | |
| "learning_rate": 7.707180716428237e-05, | |
| "loss": 0.8222, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2444444444444445, | |
| "grad_norm": 1.700829267501831, | |
| "learning_rate": 7.256038257695687e-05, | |
| "loss": 0.7214, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3333333333333333, | |
| "grad_norm": 0.6811372637748718, | |
| "learning_rate": 6.780504179127734e-05, | |
| "loss": 0.7347, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4222222222222223, | |
| "grad_norm": 2.6818108558654785, | |
| "learning_rate": 6.28571981484123e-05, | |
| "loss": 0.7399, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.511111111111111, | |
| "grad_norm": 0.9419748187065125, | |
| "learning_rate": 5.7770346273610254e-05, | |
| "loss": 0.6807, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 1.0386956930160522, | |
| "learning_rate": 5.2599483708099016e-05, | |
| "loss": 0.7299, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.6888888888888889, | |
| "grad_norm": 1.0147693157196045, | |
| "learning_rate": 4.740051629190099e-05, | |
| "loss": 0.6873, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.7777777777777777, | |
| "grad_norm": 2.2881972789764404, | |
| "learning_rate": 4.2229653726389765e-05, | |
| "loss": 0.7299, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.8666666666666667, | |
| "grad_norm": 1.0028308629989624, | |
| "learning_rate": 3.714280185158771e-05, | |
| "loss": 0.6641, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9555555555555557, | |
| "grad_norm": 0.7838729619979858, | |
| "learning_rate": 3.219495820872265e-05, | |
| "loss": 0.6632, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 2.0444444444444443, | |
| "grad_norm": 0.7789694666862488, | |
| "learning_rate": 2.7439617423043145e-05, | |
| "loss": 0.6072, | |
| "step": 230 | |
| }, | |
| { | |
| "epoch": 2.1333333333333333, | |
| "grad_norm": 0.7046312689781189, | |
| "learning_rate": 2.2928192835717644e-05, | |
| "loss": 0.6008, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 2.2222222222222223, | |
| "grad_norm": 0.8700507283210754, | |
| "learning_rate": 1.8709460637963123e-05, | |
| "loss": 0.5797, | |
| "step": 250 | |
| }, | |
| { | |
| "epoch": 2.311111111111111, | |
| "grad_norm": 1.1658436059951782, | |
| "learning_rate": 1.4829032517260489e-05, | |
| "loss": 0.5873, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 2.4, | |
| "grad_norm": 1.0423634052276611, | |
| "learning_rate": 1.132886251725061e-05, | |
| "loss": 0.6224, | |
| "step": 270 | |
| }, | |
| { | |
| "epoch": 2.488888888888889, | |
| "grad_norm": 0.8384342193603516, | |
| "learning_rate": 8.246793442995954e-06, | |
| "loss": 0.547, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 2.5777777777777775, | |
| "grad_norm": 0.9187154173851013, | |
| "learning_rate": 5.616147715740611e-06, | |
| "loss": 0.5523, | |
| "step": 290 | |
| }, | |
| { | |
| "epoch": 2.6666666666666665, | |
| "grad_norm": 1.350976586341858, | |
| "learning_rate": 3.465367100725908e-06, | |
| "loss": 0.557, | |
| "step": 300 | |
| } | |
| ], | |
| "logging_steps": 10, | |
| "max_steps": 336, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 3, | |
| "save_steps": 50, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 8997885033560064.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |