| { | |
| "best_metric": null, | |
| "best_model_checkpoint": null, | |
| "epoch": 1.9952941176470587, | |
| "eval_steps": 500, | |
| "global_step": 212, | |
| "is_hyper_param_search": false, | |
| "is_local_process_zero": true, | |
| "is_world_process_zero": true, | |
| "log_history": [ | |
| { | |
| "epoch": 0.047058823529411764, | |
| "grad_norm": 1.1233978271484375, | |
| "learning_rate": 4.9931407070965254e-05, | |
| "loss": 0.7646, | |
| "num_input_tokens_seen": 112288, | |
| "step": 5 | |
| }, | |
| { | |
| "epoch": 0.09411764705882353, | |
| "grad_norm": 0.8472293615341187, | |
| "learning_rate": 4.97260046830541e-05, | |
| "loss": 0.507, | |
| "num_input_tokens_seen": 221152, | |
| "step": 10 | |
| }, | |
| { | |
| "epoch": 0.1411764705882353, | |
| "grad_norm": 0.7263442277908325, | |
| "learning_rate": 4.9384919968379945e-05, | |
| "loss": 0.4389, | |
| "num_input_tokens_seen": 332080, | |
| "step": 15 | |
| }, | |
| { | |
| "epoch": 0.18823529411764706, | |
| "grad_norm": 0.6995546221733093, | |
| "learning_rate": 4.891002460691306e-05, | |
| "loss": 0.4212, | |
| "num_input_tokens_seen": 446912, | |
| "step": 20 | |
| }, | |
| { | |
| "epoch": 0.23529411764705882, | |
| "grad_norm": 0.6613317728042603, | |
| "learning_rate": 4.83039245557597e-05, | |
| "loss": 0.386, | |
| "num_input_tokens_seen": 558000, | |
| "step": 25 | |
| }, | |
| { | |
| "epoch": 0.2823529411764706, | |
| "grad_norm": 0.624698281288147, | |
| "learning_rate": 4.756994574914359e-05, | |
| "loss": 0.3521, | |
| "num_input_tokens_seen": 669920, | |
| "step": 30 | |
| }, | |
| { | |
| "epoch": 0.32941176470588235, | |
| "grad_norm": 0.6385682821273804, | |
| "learning_rate": 4.6712115847560355e-05, | |
| "loss": 0.3411, | |
| "num_input_tokens_seen": 786032, | |
| "step": 35 | |
| }, | |
| { | |
| "epoch": 0.3764705882352941, | |
| "grad_norm": 0.6398516297340393, | |
| "learning_rate": 4.573514213625505e-05, | |
| "loss": 0.3385, | |
| "num_input_tokens_seen": 899424, | |
| "step": 40 | |
| }, | |
| { | |
| "epoch": 0.4235294117647059, | |
| "grad_norm": 0.6650343537330627, | |
| "learning_rate": 4.464438569430354e-05, | |
| "loss": 0.3379, | |
| "num_input_tokens_seen": 1017264, | |
| "step": 45 | |
| }, | |
| { | |
| "epoch": 0.47058823529411764, | |
| "grad_norm": 0.6373805403709412, | |
| "learning_rate": 4.344583197604318e-05, | |
| "loss": 0.3198, | |
| "num_input_tokens_seen": 1131984, | |
| "step": 50 | |
| }, | |
| { | |
| "epoch": 0.5176470588235295, | |
| "grad_norm": 0.6740750074386597, | |
| "learning_rate": 4.214605796628527e-05, | |
| "loss": 0.3278, | |
| "num_input_tokens_seen": 1248864, | |
| "step": 55 | |
| }, | |
| { | |
| "epoch": 0.5647058823529412, | |
| "grad_norm": 0.7610446214675903, | |
| "learning_rate": 4.075219608954278e-05, | |
| "loss": 0.313, | |
| "num_input_tokens_seen": 1364864, | |
| "step": 60 | |
| }, | |
| { | |
| "epoch": 0.611764705882353, | |
| "grad_norm": 0.7002452611923218, | |
| "learning_rate": 3.927189507131938e-05, | |
| "loss": 0.3111, | |
| "num_input_tokens_seen": 1477168, | |
| "step": 65 | |
| }, | |
| { | |
| "epoch": 0.6588235294117647, | |
| "grad_norm": 0.6586229801177979, | |
| "learning_rate": 3.7713277966230514e-05, | |
| "loss": 0.311, | |
| "num_input_tokens_seen": 1587472, | |
| "step": 70 | |
| }, | |
| { | |
| "epoch": 0.7058823529411765, | |
| "grad_norm": 0.6844495534896851, | |
| "learning_rate": 3.608489758327472e-05, | |
| "loss": 0.3145, | |
| "num_input_tokens_seen": 1705520, | |
| "step": 75 | |
| }, | |
| { | |
| "epoch": 0.7529411764705882, | |
| "grad_norm": 0.6307282447814941, | |
| "learning_rate": 3.4395689552855955e-05, | |
| "loss": 0.3006, | |
| "num_input_tokens_seen": 1818720, | |
| "step": 80 | |
| }, | |
| { | |
| "epoch": 0.8, | |
| "grad_norm": 0.6304646730422974, | |
| "learning_rate": 3.265492329309867e-05, | |
| "loss": 0.3006, | |
| "num_input_tokens_seen": 1934032, | |
| "step": 85 | |
| }, | |
| { | |
| "epoch": 0.8470588235294118, | |
| "grad_norm": 0.6582378149032593, | |
| "learning_rate": 3.0872151144524595e-05, | |
| "loss": 0.3016, | |
| "num_input_tokens_seen": 2040336, | |
| "step": 90 | |
| }, | |
| { | |
| "epoch": 0.8941176470588236, | |
| "grad_norm": 0.7168837189674377, | |
| "learning_rate": 2.9057155952211502e-05, | |
| "loss": 0.2939, | |
| "num_input_tokens_seen": 2149840, | |
| "step": 95 | |
| }, | |
| { | |
| "epoch": 0.9411764705882353, | |
| "grad_norm": 0.6492182016372681, | |
| "learning_rate": 2.7219897383073373e-05, | |
| "loss": 0.2893, | |
| "num_input_tokens_seen": 2262096, | |
| "step": 100 | |
| }, | |
| { | |
| "epoch": 0.9882352941176471, | |
| "grad_norm": 0.6181011199951172, | |
| "learning_rate": 2.537045727284232e-05, | |
| "loss": 0.271, | |
| "num_input_tokens_seen": 2371520, | |
| "step": 105 | |
| }, | |
| { | |
| "epoch": 1.035294117647059, | |
| "grad_norm": 0.6379333138465881, | |
| "learning_rate": 2.3518984302657146e-05, | |
| "loss": 0.2694, | |
| "num_input_tokens_seen": 2488736, | |
| "step": 110 | |
| }, | |
| { | |
| "epoch": 1.0823529411764705, | |
| "grad_norm": 0.6440654397010803, | |
| "learning_rate": 2.1675638308842145e-05, | |
| "loss": 0.276, | |
| "num_input_tokens_seen": 2604976, | |
| "step": 115 | |
| }, | |
| { | |
| "epoch": 1.1294117647058823, | |
| "grad_norm": 0.7227081060409546, | |
| "learning_rate": 1.9850534531472546e-05, | |
| "loss": 0.2677, | |
| "num_input_tokens_seen": 2719664, | |
| "step": 120 | |
| }, | |
| { | |
| "epoch": 1.1764705882352942, | |
| "grad_norm": 0.6659607887268066, | |
| "learning_rate": 1.8053688107658908e-05, | |
| "loss": 0.277, | |
| "num_input_tokens_seen": 2833008, | |
| "step": 125 | |
| }, | |
| { | |
| "epoch": 1.223529411764706, | |
| "grad_norm": 0.6689413785934448, | |
| "learning_rate": 1.6294959114140034e-05, | |
| "loss": 0.2646, | |
| "num_input_tokens_seen": 2946768, | |
| "step": 130 | |
| }, | |
| { | |
| "epoch": 1.2705882352941176, | |
| "grad_norm": 0.6785162091255188, | |
| "learning_rate": 1.4583998460759424e-05, | |
| "loss": 0.2578, | |
| "num_input_tokens_seen": 3057648, | |
| "step": 135 | |
| }, | |
| { | |
| "epoch": 1.3176470588235294, | |
| "grad_norm": 0.7651886940002441, | |
| "learning_rate": 1.2930194931731382e-05, | |
| "loss": 0.2668, | |
| "num_input_tokens_seen": 3168928, | |
| "step": 140 | |
| }, | |
| { | |
| "epoch": 1.3647058823529412, | |
| "grad_norm": 0.7469376921653748, | |
| "learning_rate": 1.1342623665304209e-05, | |
| "loss": 0.2773, | |
| "num_input_tokens_seen": 3285296, | |
| "step": 145 | |
| }, | |
| { | |
| "epoch": 1.4117647058823528, | |
| "grad_norm": 0.6922341585159302, | |
| "learning_rate": 9.829996354535172e-06, | |
| "loss": 0.2675, | |
| "num_input_tokens_seen": 3396800, | |
| "step": 150 | |
| }, | |
| { | |
| "epoch": 1.4588235294117646, | |
| "grad_norm": 0.7332698702812195, | |
| "learning_rate": 8.400613442446948e-06, | |
| "loss": 0.2719, | |
| "num_input_tokens_seen": 3510752, | |
| "step": 155 | |
| }, | |
| { | |
| "epoch": 1.5058823529411764, | |
| "grad_norm": 0.684525191783905, | |
| "learning_rate": 7.062318573891716e-06, | |
| "loss": 0.2719, | |
| "num_input_tokens_seen": 3623024, | |
| "step": 160 | |
| }, | |
| { | |
| "epoch": 1.5529411764705883, | |
| "grad_norm": 0.69036465883255, | |
| "learning_rate": 5.822455554065217e-06, | |
| "loss": 0.2734, | |
| "num_input_tokens_seen": 3738336, | |
| "step": 165 | |
| }, | |
| { | |
| "epoch": 1.6, | |
| "grad_norm": 0.750205934047699, | |
| "learning_rate": 4.687828049857967e-06, | |
| "loss": 0.2547, | |
| "num_input_tokens_seen": 3846560, | |
| "step": 170 | |
| }, | |
| { | |
| "epoch": 1.6470588235294117, | |
| "grad_norm": 0.6747934222221375, | |
| "learning_rate": 3.6646622551801345e-06, | |
| "loss": 0.2473, | |
| "num_input_tokens_seen": 3960208, | |
| "step": 175 | |
| }, | |
| { | |
| "epoch": 1.6941176470588235, | |
| "grad_norm": 0.683767557144165, | |
| "learning_rate": 2.75857272513132e-06, | |
| "loss": 0.2679, | |
| "num_input_tokens_seen": 4073792, | |
| "step": 180 | |
| }, | |
| { | |
| "epoch": 1.7411764705882353, | |
| "grad_norm": 0.608447253704071, | |
| "learning_rate": 1.9745315664982276e-06, | |
| "loss": 0.2517, | |
| "num_input_tokens_seen": 4185424, | |
| "step": 185 | |
| }, | |
| { | |
| "epoch": 1.788235294117647, | |
| "grad_norm": 0.6212649941444397, | |
| "learning_rate": 1.3168411536452152e-06, | |
| "loss": 0.2485, | |
| "num_input_tokens_seen": 4298448, | |
| "step": 190 | |
| }, | |
| { | |
| "epoch": 1.835294117647059, | |
| "grad_norm": 0.6908031702041626, | |
| "learning_rate": 7.891105195175358e-07, | |
| "loss": 0.2614, | |
| "num_input_tokens_seen": 4416480, | |
| "step": 195 | |
| }, | |
| { | |
| "epoch": 1.8823529411764706, | |
| "grad_norm": 0.673697292804718, | |
| "learning_rate": 3.9423555131007925e-07, | |
| "loss": 0.2634, | |
| "num_input_tokens_seen": 4529488, | |
| "step": 200 | |
| }, | |
| { | |
| "epoch": 1.9294117647058824, | |
| "grad_norm": 0.6629529595375061, | |
| "learning_rate": 1.343830994765982e-07, | |
| "loss": 0.2527, | |
| "num_input_tokens_seen": 4641008, | |
| "step": 205 | |
| }, | |
| { | |
| "epoch": 1.9764705882352942, | |
| "grad_norm": 0.711607038974762, | |
| "learning_rate": 1.0979087280141298e-08, | |
| "loss": 0.2628, | |
| "num_input_tokens_seen": 4751536, | |
| "step": 210 | |
| }, | |
| { | |
| "epoch": 1.9952941176470587, | |
| "num_input_tokens_seen": 4796864, | |
| "step": 212, | |
| "total_flos": 2.0534733878748774e+17, | |
| "train_loss": 0.31159005553092595, | |
| "train_runtime": 2642.3532, | |
| "train_samples_per_second": 2.573, | |
| "train_steps_per_second": 0.08 | |
| } | |
| ], | |
| "logging_steps": 5, | |
| "max_steps": 212, | |
| "num_input_tokens_seen": 4796864, | |
| "num_train_epochs": 2, | |
| "save_steps": 100, | |
| "stateful_callbacks": { | |
| "TrainerControl": { | |
| "args": { | |
| "should_epoch_stop": false, | |
| "should_evaluate": false, | |
| "should_log": false, | |
| "should_save": true, | |
| "should_training_stop": false | |
| }, | |
| "attributes": {} | |
| } | |
| }, | |
| "total_flos": 2.0534733878748774e+17, | |
| "train_batch_size": 2, | |
| "trial_name": null, | |
| "trial_params": null | |
| } | |