| { | |
| "best_global_step": null, | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 10.0, | |
| "eval_steps": 500, | |
| "global_step": 40, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.32, | |
| "grad_norm": 0.03316276932047194, | |
| "learning_rate": 0.0, | |
| "loss": 1.855, | |
| "step": 1 | |
| }, | |
| { | |
| "epoch": 0.64, | |
| "grad_norm": 0.03358594767910446, | |
| "learning_rate": 1e-05, | |
| "loss": 1.9926, | |
| "step": 2 | |
| }, | |
| { | |
| "epoch": 0.96, | |
| "grad_norm": 0.1209165240696463, | |
| "learning_rate": 9.983786540671052e-06, | |
| "loss": 1.9848, | |
| "step": 3 | |
| }, | |
| { | |
| "epoch": 1.0, | |
| "grad_norm": 0.1209165240696463, | |
| "learning_rate": 9.935251313189564e-06, | |
| "loss": 1.9371, | |
| "step": 4 | |
| }, | |
| { | |
| "epoch": 1.32, | |
| "grad_norm": 0.23283389969660934, | |
| "learning_rate": 9.854709087130261e-06, | |
| "loss": 1.855, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 1.6400000000000001, | |
| "grad_norm": 0.03579774396999013, | |
| "learning_rate": 9.742682209735727e-06, | |
| "loss": 1.9924, | |
| "step": 6 | |
| }, | |
| { | |
| "epoch": 1.96, | |
| "grad_norm": 0.2537044557560918, | |
| "learning_rate": 9.599897218294122e-06, | |
| "loss": 1.9843, | |
| "step": 7 | |
| }, | |
| { | |
| "epoch": 2.0, | |
| "grad_norm": 0.2537044557560918, | |
| "learning_rate": 9.427280128266049e-06, | |
| "loss": 1.936, | |
| "step": 8 | |
| }, | |
| { | |
| "epoch": 2.32, | |
| "grad_norm": 0.17687464625719426, | |
| "learning_rate": 9.225950427718974e-06, | |
| "loss": 1.8547, | |
| "step": 9 | |
| }, | |
| { | |
| "epoch": 2.64, | |
| "grad_norm": 0.03382467066598868, | |
| "learning_rate": 8.997213817017508e-06, | |
| "loss": 1.9922, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 2.96, | |
| "grad_norm": 0.2149784593374703, | |
| "learning_rate": 8.742553740855507e-06, | |
| "loss": 1.9842, | |
| "step": 11 | |
| }, | |
| { | |
| "epoch": 3.0, | |
| "grad_norm": 0.2149784593374703, | |
| "learning_rate": 8.463621767547998e-06, | |
| "loss": 1.937, | |
| "step": 12 | |
| }, | |
| { | |
| "epoch": 3.32, | |
| "grad_norm": 0.24356251608621823, | |
| "learning_rate": 8.162226877976886e-06, | |
| "loss": 1.8548, | |
| "step": 13 | |
| }, | |
| { | |
| "epoch": 3.64, | |
| "grad_norm": 0.031823439514121366, | |
| "learning_rate": 7.84032373365578e-06, | |
| "loss": 1.9921, | |
| "step": 14 | |
| }, | |
| { | |
| "epoch": 3.96, | |
| "grad_norm": 0.07381485624096076, | |
| "learning_rate": 7.500000000000001e-06, | |
| "loss": 1.984, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 4.0, | |
| "grad_norm": 0.07381485624096076, | |
| "learning_rate": 7.143462807015271e-06, | |
| "loss": 1.936, | |
| "step": 16 | |
| }, | |
| { | |
| "epoch": 4.32, | |
| "grad_norm": 0.8952771910314485, | |
| "learning_rate": 6.773024435212678e-06, | |
| "loss": 1.8546, | |
| "step": 17 | |
| }, | |
| { | |
| "epoch": 4.64, | |
| "grad_norm": 0.045372394637685505, | |
| "learning_rate": 6.391087319582264e-06, | |
| "loss": 1.9922, | |
| "step": 18 | |
| }, | |
| { | |
| "epoch": 4.96, | |
| "grad_norm": 0.06873953530679855, | |
| "learning_rate": 6.000128468880223e-06, | |
| "loss": 1.9835, | |
| "step": 19 | |
| }, | |
| { | |
| "epoch": 5.0, | |
| "grad_norm": 0.06873953530679855, | |
| "learning_rate": 5.6026834012766155e-06, | |
| "loss": 1.9351, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 5.32, | |
| "grad_norm": 0.4683361474512601, | |
| "learning_rate": 5.201329700547077e-06, | |
| "loss": 1.8547, | |
| "step": 21 | |
| }, | |
| { | |
| "epoch": 5.64, | |
| "grad_norm": 0.04126605742167481, | |
| "learning_rate": 4.798670299452926e-06, | |
| "loss": 1.9918, | |
| "step": 22 | |
| }, | |
| { | |
| "epoch": 5.96, | |
| "grad_norm": 0.06385791883220715, | |
| "learning_rate": 4.397316598723385e-06, | |
| "loss": 1.9832, | |
| "step": 23 | |
| }, | |
| { | |
| "epoch": 6.0, | |
| "grad_norm": 0.06385791883220715, | |
| "learning_rate": 3.999871531119779e-06, | |
| "loss": 1.9344, | |
| "step": 24 | |
| }, | |
| { | |
| "epoch": 6.32, | |
| "grad_norm": 0.4663569965672017, | |
| "learning_rate": 3.6089126804177373e-06, | |
| "loss": 1.8546, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 6.64, | |
| "grad_norm": 0.04149945581855151, | |
| "learning_rate": 3.226975564787322e-06, | |
| "loss": 1.9917, | |
| "step": 26 | |
| }, | |
| { | |
| "epoch": 6.96, | |
| "grad_norm": 0.0630463610042768, | |
| "learning_rate": 2.8565371929847286e-06, | |
| "loss": 1.9825, | |
| "step": 27 | |
| }, | |
| { | |
| "epoch": 7.0, | |
| "grad_norm": 0.0630463610042768, | |
| "learning_rate": 2.5000000000000015e-06, | |
| "loss": 1.9341, | |
| "step": 28 | |
| }, | |
| { | |
| "epoch": 7.32, | |
| "grad_norm": 0.5810167468566034, | |
| "learning_rate": 2.159676266344222e-06, | |
| "loss": 1.8545, | |
| "step": 29 | |
| }, | |
| { | |
| "epoch": 7.64, | |
| "grad_norm": 0.040559470445516395, | |
| "learning_rate": 1.8377731220231144e-06, | |
| "loss": 1.9918, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 7.96, | |
| "grad_norm": 0.06845168909030974, | |
| "learning_rate": 1.5363782324520033e-06, | |
| "loss": 1.9824, | |
| "step": 31 | |
| }, | |
| { | |
| "epoch": 8.0, | |
| "grad_norm": 1.3651827318008356, | |
| "learning_rate": 1.257446259144494e-06, | |
| "loss": 1.9314, | |
| "step": 32 | |
| }, | |
| { | |
| "epoch": 8.32, | |
| "grad_norm": 0.05998267896232342, | |
| "learning_rate": 1.0027861829824953e-06, | |
| "loss": 1.8547, | |
| "step": 33 | |
| }, | |
| { | |
| "epoch": 8.64, | |
| "grad_norm": 0.045049793936420675, | |
| "learning_rate": 7.740495722810271e-07, | |
| "loss": 1.9917, | |
| "step": 34 | |
| }, | |
| { | |
| "epoch": 8.96, | |
| "grad_norm": 0.19959181069248683, | |
| "learning_rate": 5.727198717339511e-07, | |
| "loss": 1.9824, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 9.0, | |
| "grad_norm": 0.19959181069248683, | |
| "learning_rate": 4.001027817058789e-07, | |
| "loss": 1.9332, | |
| "step": 36 | |
| }, | |
| { | |
| "epoch": 9.32, | |
| "grad_norm": 0.5537714862650808, | |
| "learning_rate": 2.573177902642726e-07, | |
| "loss": 1.8545, | |
| "step": 37 | |
| }, | |
| { | |
| "epoch": 9.64, | |
| "grad_norm": 0.04209162635648688, | |
| "learning_rate": 1.4529091286973994e-07, | |
| "loss": 1.9917, | |
| "step": 38 | |
| }, | |
| { | |
| "epoch": 9.96, | |
| "grad_norm": 0.1378194828139234, | |
| "learning_rate": 6.474868681043578e-08, | |
| "loss": 1.9825, | |
| "step": 39 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "grad_norm": 0.1378194828139234, | |
| "learning_rate": 1.6213459328950355e-08, | |
| "loss": 1.9322, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 10.0, | |
| "step": 40, | |
| "total_flos": 174553779142656.0, | |
| "train_loss": 1.9411850422620773, | |
| "train_runtime": 1447.4453, | |
| "train_samples_per_second": 0.684, | |
| "train_steps_per_second": 0.028 | |
| } | |
| ], | |
| "logging_steps": 1, | |
| "max_steps": 40, | |
| "num_input_tokens_seen": 0, | |
| "num_train_epochs": 10, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": true | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 174553779142656.0, | |
| "train_batch_size": 1, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |