| { | |
| "best_metric": 1.6601147651672363, | |
| "best_model_checkpoint": "/mnt/bn/qingyi-bn-lq/llama/saved_bloominstinwild-belle1.5m/checkpoint-1000", | |
| "epoch": 0.6428801028608164, | |
| "global_step": 1000, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.01, | |
| "learning_rate": 5.9999999999999995e-05, | |
| "loss": 2.3902, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.03, | |
| "learning_rate": 0.00011999999999999999, | |
| "loss": 2.1808, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.04, | |
| "learning_rate": 0.00017999999999999998, | |
| "loss": 1.9937, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.05, | |
| "learning_rate": 0.00023999999999999998, | |
| "loss": 1.8967, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.06, | |
| "learning_rate": 0.0003, | |
| "loss": 1.8529, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.08, | |
| "learning_rate": 0.0002958762886597938, | |
| "loss": 1.8004, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 0.09, | |
| "learning_rate": 0.0002917525773195876, | |
| "loss": 1.785, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 0.1, | |
| "learning_rate": 0.0002876288659793814, | |
| "loss": 1.7755, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 0.12, | |
| "learning_rate": 0.00028350515463917525, | |
| "loss": 1.7554, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "learning_rate": 0.0002793814432989691, | |
| "loss": 1.7534, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.13, | |
| "eval_loss": 1.7528996467590332, | |
| "eval_runtime": 17.6175, | |
| "eval_samples_per_second": 113.524, | |
| "eval_steps_per_second": 1.816, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 0.14, | |
| "learning_rate": 0.00027525773195876286, | |
| "loss": 1.7375, | |
| "step": 220 | |
| }, | |
| { | |
| "epoch": 0.15, | |
| "learning_rate": 0.0002711340206185567, | |
| "loss": 1.7331, | |
| "step": 240 | |
| }, | |
| { | |
| "epoch": 0.17, | |
| "learning_rate": 0.00026701030927835047, | |
| "loss": 1.7248, | |
| "step": 260 | |
| }, | |
| { | |
| "epoch": 0.18, | |
| "learning_rate": 0.0002628865979381443, | |
| "loss": 1.7282, | |
| "step": 280 | |
| }, | |
| { | |
| "epoch": 0.19, | |
| "learning_rate": 0.00025876288659793813, | |
| "loss": 1.7167, | |
| "step": 300 | |
| }, | |
| { | |
| "epoch": 0.21, | |
| "learning_rate": 0.0002546391752577319, | |
| "loss": 1.7215, | |
| "step": 320 | |
| }, | |
| { | |
| "epoch": 0.22, | |
| "learning_rate": 0.00025051546391752574, | |
| "loss": 1.7157, | |
| "step": 340 | |
| }, | |
| { | |
| "epoch": 0.23, | |
| "learning_rate": 0.0002463917525773196, | |
| "loss": 1.7146, | |
| "step": 360 | |
| }, | |
| { | |
| "epoch": 0.24, | |
| "learning_rate": 0.00024226804123711338, | |
| "loss": 1.6953, | |
| "step": 380 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "learning_rate": 0.00023814432989690718, | |
| "loss": 1.6951, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.26, | |
| "eval_loss": 1.7059786319732666, | |
| "eval_runtime": 17.3801, | |
| "eval_samples_per_second": 115.074, | |
| "eval_steps_per_second": 1.841, | |
| "step": 400 | |
| }, | |
| { | |
| "epoch": 0.27, | |
| "learning_rate": 0.00023402061855670102, | |
| "loss": 1.6916, | |
| "step": 420 | |
| }, | |
| { | |
| "epoch": 0.28, | |
| "learning_rate": 0.00022989690721649485, | |
| "loss": 1.6893, | |
| "step": 440 | |
| }, | |
| { | |
| "epoch": 0.3, | |
| "learning_rate": 0.00022577319587628863, | |
| "loss": 1.6932, | |
| "step": 460 | |
| }, | |
| { | |
| "epoch": 0.31, | |
| "learning_rate": 0.00022164948453608246, | |
| "loss": 1.6913, | |
| "step": 480 | |
| }, | |
| { | |
| "epoch": 0.32, | |
| "learning_rate": 0.00021752577319587626, | |
| "loss": 1.6823, | |
| "step": 500 | |
| }, | |
| { | |
| "epoch": 0.33, | |
| "learning_rate": 0.0002134020618556701, | |
| "loss": 1.6921, | |
| "step": 520 | |
| }, | |
| { | |
| "epoch": 0.35, | |
| "learning_rate": 0.0002092783505154639, | |
| "loss": 1.6759, | |
| "step": 540 | |
| }, | |
| { | |
| "epoch": 0.36, | |
| "learning_rate": 0.0002051546391752577, | |
| "loss": 1.6758, | |
| "step": 560 | |
| }, | |
| { | |
| "epoch": 0.37, | |
| "learning_rate": 0.0002010309278350515, | |
| "loss": 1.6732, | |
| "step": 580 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "learning_rate": 0.00019690721649484534, | |
| "loss": 1.673, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.39, | |
| "eval_loss": 1.6831790208816528, | |
| "eval_runtime": 17.4032, | |
| "eval_samples_per_second": 114.921, | |
| "eval_steps_per_second": 1.839, | |
| "step": 600 | |
| }, | |
| { | |
| "epoch": 0.4, | |
| "learning_rate": 0.00019278350515463918, | |
| "loss": 1.6625, | |
| "step": 620 | |
| }, | |
| { | |
| "epoch": 0.41, | |
| "learning_rate": 0.00018865979381443298, | |
| "loss": 1.666, | |
| "step": 640 | |
| }, | |
| { | |
| "epoch": 0.42, | |
| "learning_rate": 0.00018453608247422679, | |
| "loss": 1.6662, | |
| "step": 660 | |
| }, | |
| { | |
| "epoch": 0.44, | |
| "learning_rate": 0.0001804123711340206, | |
| "loss": 1.6692, | |
| "step": 680 | |
| }, | |
| { | |
| "epoch": 0.45, | |
| "learning_rate": 0.00017628865979381442, | |
| "loss": 1.6635, | |
| "step": 700 | |
| }, | |
| { | |
| "epoch": 0.46, | |
| "learning_rate": 0.00017216494845360823, | |
| "loss": 1.6685, | |
| "step": 720 | |
| }, | |
| { | |
| "epoch": 0.48, | |
| "learning_rate": 0.00016804123711340206, | |
| "loss": 1.6534, | |
| "step": 740 | |
| }, | |
| { | |
| "epoch": 0.49, | |
| "learning_rate": 0.00016391752577319584, | |
| "loss": 1.6627, | |
| "step": 760 | |
| }, | |
| { | |
| "epoch": 0.5, | |
| "learning_rate": 0.00015979381443298967, | |
| "loss": 1.6596, | |
| "step": 780 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "learning_rate": 0.0001556701030927835, | |
| "loss": 1.6659, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.51, | |
| "eval_loss": 1.6697583198547363, | |
| "eval_runtime": 17.3944, | |
| "eval_samples_per_second": 114.979, | |
| "eval_steps_per_second": 1.84, | |
| "step": 800 | |
| }, | |
| { | |
| "epoch": 0.53, | |
| "learning_rate": 0.0001515463917525773, | |
| "loss": 1.6599, | |
| "step": 820 | |
| }, | |
| { | |
| "epoch": 0.54, | |
| "learning_rate": 0.0001474226804123711, | |
| "loss": 1.6587, | |
| "step": 840 | |
| }, | |
| { | |
| "epoch": 0.55, | |
| "learning_rate": 0.00014329896907216494, | |
| "loss": 1.6586, | |
| "step": 860 | |
| }, | |
| { | |
| "epoch": 0.57, | |
| "learning_rate": 0.00013917525773195875, | |
| "loss": 1.6602, | |
| "step": 880 | |
| }, | |
| { | |
| "epoch": 0.58, | |
| "learning_rate": 0.00013505154639175258, | |
| "loss": 1.6513, | |
| "step": 900 | |
| }, | |
| { | |
| "epoch": 0.59, | |
| "learning_rate": 0.00013092783505154639, | |
| "loss": 1.6477, | |
| "step": 920 | |
| }, | |
| { | |
| "epoch": 0.6, | |
| "learning_rate": 0.0001268041237113402, | |
| "loss": 1.6455, | |
| "step": 940 | |
| }, | |
| { | |
| "epoch": 0.62, | |
| "learning_rate": 0.000122680412371134, | |
| "loss": 1.6543, | |
| "step": 960 | |
| }, | |
| { | |
| "epoch": 0.63, | |
| "learning_rate": 0.00011855670103092781, | |
| "loss": 1.6499, | |
| "step": 980 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "learning_rate": 0.00011443298969072163, | |
| "loss": 1.647, | |
| "step": 1000 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "eval_loss": 1.6601147651672363, | |
| "eval_runtime": 17.3892, | |
| "eval_samples_per_second": 115.014, | |
| "eval_steps_per_second": 1.84, | |
| "step": 1000 | |
| } | |
| ], | |
| "max_steps": 1555, | |
| "num_train_epochs": 1, | |
| "total_flos": 8.598717456522936e+18, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |