| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 0.0198373338623289, | |
| "eval_steps": 25, | |
| "global_step": 25, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.0007934933544931561, | |
| "grad_norm": 48.7606315612793, | |
| "learning_rate": 6.666666666666667e-05, | |
| "loss": 29.6105, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0007934933544931561, | |
| "eval_loss": 3.7225465774536133, | |
| "eval_runtime": 212.1774, | |
| "eval_samples_per_second": 5.005, | |
| "eval_steps_per_second": 2.503, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.0015869867089863122, | |
| "grad_norm": 46.967803955078125, | |
| "learning_rate": 0.00013333333333333334, | |
| "loss": 29.9806, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.0023804800634794686, | |
| "grad_norm": 50.5672492980957, | |
| "learning_rate": 0.0002, | |
| "loss": 26.9378, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 0.0031739734179726245, | |
| "grad_norm": 46.023780822753906, | |
| "learning_rate": 0.0001999048221581858, | |
| "loss": 21.9639, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 0.003967466772465781, | |
| "grad_norm": 31.295907974243164, | |
| "learning_rate": 0.00019961946980917456, | |
| "loss": 10.6674, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.004760960126958937, | |
| "grad_norm": 23.777172088623047, | |
| "learning_rate": 0.00019914448613738106, | |
| "loss": 6.2121, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 0.005554453481452093, | |
| "grad_norm": 23.954105377197266, | |
| "learning_rate": 0.00019848077530122083, | |
| "loss": 4.3349, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 0.006347946835945249, | |
| "grad_norm": 7.861544132232666, | |
| "learning_rate": 0.00019762960071199333, | |
| "loss": 3.1486, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 0.007141440190438405, | |
| "grad_norm": 6.988774299621582, | |
| "learning_rate": 0.00019659258262890683, | |
| "loss": 2.6602, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 0.007934933544931562, | |
| "grad_norm": 32.20113754272461, | |
| "learning_rate": 0.0001953716950748227, | |
| "loss": 4.0596, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.008728426899424718, | |
| "grad_norm": 14.095051765441895, | |
| "learning_rate": 0.00019396926207859084, | |
| "loss": 2.995, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 0.009521920253917874, | |
| "grad_norm": 13.5059232711792, | |
| "learning_rate": 0.0001923879532511287, | |
| "loss": 3.2571, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 0.010315413608411029, | |
| "grad_norm": 7.761572360992432, | |
| "learning_rate": 0.000190630778703665, | |
| "loss": 3.0002, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 0.011108906962904185, | |
| "grad_norm": 4.439308166503906, | |
| "learning_rate": 0.00018870108331782217, | |
| "loss": 2.6362, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 0.011902400317397342, | |
| "grad_norm": 6.415318489074707, | |
| "learning_rate": 0.00018660254037844388, | |
| "loss": 3.1925, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.012695893671890498, | |
| "grad_norm": 6.409482955932617, | |
| "learning_rate": 0.0001843391445812886, | |
| "loss": 3.062, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 0.013489387026383654, | |
| "grad_norm": 3.2289886474609375, | |
| "learning_rate": 0.0001819152044288992, | |
| "loss": 2.8807, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 0.01428288038087681, | |
| "grad_norm": 7.170831680297852, | |
| "learning_rate": 0.00017933533402912354, | |
| "loss": 3.1952, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 0.015076373735369967, | |
| "grad_norm": 8.997602462768555, | |
| "learning_rate": 0.0001766044443118978, | |
| "loss": 2.9534, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 0.015869867089863123, | |
| "grad_norm": 18.465681076049805, | |
| "learning_rate": 0.0001737277336810124, | |
| "loss": 6.0253, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.01666336044435628, | |
| "grad_norm": 6.664717674255371, | |
| "learning_rate": 0.00017071067811865476, | |
| "loss": 3.1157, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 0.017456853798849436, | |
| "grad_norm": 6.979747772216797, | |
| "learning_rate": 0.00016755902076156604, | |
| "loss": 3.0816, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 0.018250347153342592, | |
| "grad_norm": 4.373898506164551, | |
| "learning_rate": 0.00016427876096865394, | |
| "loss": 2.921, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 0.01904384050783575, | |
| "grad_norm": 3.7028324604034424, | |
| "learning_rate": 0.00016087614290087208, | |
| "loss": 2.8931, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 0.0198373338623289, | |
| "grad_norm": 2.8346545696258545, | |
| "learning_rate": 0.0001573576436351046, | |
| "loss": 2.8573, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.0198373338623289, | |
| "eval_loss": 0.37545695900917053, | |
| "eval_runtime": 213.9659, | |
| "eval_samples_per_second": 4.963, | |
| "eval_steps_per_second": 2.482, | |
| "step": 25 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 75, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 1, | |
| "save_steps": 25, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 3.26729100951552e+16, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |