|
{ |
|
"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": 0.528028130531311, |
|
"learning_rate": 4.9931407070965254e-05, |
|
"loss": 0.9764, |
|
"num_input_tokens_seen": 117552, |
|
"step": 5 |
|
}, |
|
{ |
|
"epoch": 0.09411764705882353, |
|
"grad_norm": 0.38293221592903137, |
|
"learning_rate": 4.97260046830541e-05, |
|
"loss": 0.8018, |
|
"num_input_tokens_seen": 231808, |
|
"step": 10 |
|
}, |
|
{ |
|
"epoch": 0.1411764705882353, |
|
"grad_norm": 0.27834752202033997, |
|
"learning_rate": 4.9384919968379945e-05, |
|
"loss": 0.6775, |
|
"num_input_tokens_seen": 348416, |
|
"step": 15 |
|
}, |
|
{ |
|
"epoch": 0.18823529411764706, |
|
"grad_norm": 0.24095691740512848, |
|
"learning_rate": 4.891002460691306e-05, |
|
"loss": 0.6321, |
|
"num_input_tokens_seen": 468864, |
|
"step": 20 |
|
}, |
|
{ |
|
"epoch": 0.23529411764705882, |
|
"grad_norm": 0.24503234028816223, |
|
"learning_rate": 4.83039245557597e-05, |
|
"loss": 0.5816, |
|
"num_input_tokens_seen": 585296, |
|
"step": 25 |
|
}, |
|
{ |
|
"epoch": 0.2823529411764706, |
|
"grad_norm": 0.23120124638080597, |
|
"learning_rate": 4.756994574914359e-05, |
|
"loss": 0.5273, |
|
"num_input_tokens_seen": 702880, |
|
"step": 30 |
|
}, |
|
{ |
|
"epoch": 0.32941176470588235, |
|
"grad_norm": 0.19739653170108795, |
|
"learning_rate": 4.6712115847560355e-05, |
|
"loss": 0.4928, |
|
"num_input_tokens_seen": 824560, |
|
"step": 35 |
|
}, |
|
{ |
|
"epoch": 0.3764705882352941, |
|
"grad_norm": 0.2082643061876297, |
|
"learning_rate": 4.573514213625505e-05, |
|
"loss": 0.4748, |
|
"num_input_tokens_seen": 943696, |
|
"step": 40 |
|
}, |
|
{ |
|
"epoch": 0.4235294117647059, |
|
"grad_norm": 0.20437505841255188, |
|
"learning_rate": 4.464438569430354e-05, |
|
"loss": 0.4697, |
|
"num_input_tokens_seen": 1066992, |
|
"step": 45 |
|
}, |
|
{ |
|
"epoch": 0.47058823529411764, |
|
"grad_norm": 0.18714147806167603, |
|
"learning_rate": 4.344583197604318e-05, |
|
"loss": 0.4356, |
|
"num_input_tokens_seen": 1187200, |
|
"step": 50 |
|
}, |
|
{ |
|
"epoch": 0.5176470588235295, |
|
"grad_norm": 0.20996348559856415, |
|
"learning_rate": 4.214605796628527e-05, |
|
"loss": 0.4481, |
|
"num_input_tokens_seen": 1309488, |
|
"step": 55 |
|
}, |
|
{ |
|
"epoch": 0.5647058823529412, |
|
"grad_norm": 0.2137318253517151, |
|
"learning_rate": 4.075219608954278e-05, |
|
"loss": 0.4232, |
|
"num_input_tokens_seen": 1430640, |
|
"step": 60 |
|
}, |
|
{ |
|
"epoch": 0.611764705882353, |
|
"grad_norm": 0.18864841759204865, |
|
"learning_rate": 3.927189507131938e-05, |
|
"loss": 0.4115, |
|
"num_input_tokens_seen": 1548432, |
|
"step": 65 |
|
}, |
|
{ |
|
"epoch": 0.6588235294117647, |
|
"grad_norm": 0.21732792258262634, |
|
"learning_rate": 3.7713277966230514e-05, |
|
"loss": 0.4107, |
|
"num_input_tokens_seen": 1664112, |
|
"step": 70 |
|
}, |
|
{ |
|
"epoch": 0.7058823529411765, |
|
"grad_norm": 0.2021615207195282, |
|
"learning_rate": 3.608489758327472e-05, |
|
"loss": 0.4156, |
|
"num_input_tokens_seen": 1787392, |
|
"step": 75 |
|
}, |
|
{ |
|
"epoch": 0.7529411764705882, |
|
"grad_norm": 0.2128894329071045, |
|
"learning_rate": 3.4395689552855955e-05, |
|
"loss": 0.3926, |
|
"num_input_tokens_seen": 1905584, |
|
"step": 80 |
|
}, |
|
{ |
|
"epoch": 0.8, |
|
"grad_norm": 0.24376748502254486, |
|
"learning_rate": 3.265492329309867e-05, |
|
"loss": 0.3914, |
|
"num_input_tokens_seen": 2026336, |
|
"step": 85 |
|
}, |
|
{ |
|
"epoch": 0.8470588235294118, |
|
"grad_norm": 0.23921102285385132, |
|
"learning_rate": 3.0872151144524595e-05, |
|
"loss": 0.389, |
|
"num_input_tokens_seen": 2138112, |
|
"step": 90 |
|
}, |
|
{ |
|
"epoch": 0.8941176470588236, |
|
"grad_norm": 0.25298914313316345, |
|
"learning_rate": 2.9057155952211502e-05, |
|
"loss": 0.3795, |
|
"num_input_tokens_seen": 2252832, |
|
"step": 95 |
|
}, |
|
{ |
|
"epoch": 0.9411764705882353, |
|
"grad_norm": 0.23804712295532227, |
|
"learning_rate": 2.7219897383073373e-05, |
|
"loss": 0.3735, |
|
"num_input_tokens_seen": 2370704, |
|
"step": 100 |
|
}, |
|
{ |
|
"epoch": 0.9882352941176471, |
|
"grad_norm": 0.24087488651275635, |
|
"learning_rate": 2.537045727284232e-05, |
|
"loss": 0.3535, |
|
"num_input_tokens_seen": 2485792, |
|
"step": 105 |
|
}, |
|
{ |
|
"epoch": 1.035294117647059, |
|
"grad_norm": 0.2612946331501007, |
|
"learning_rate": 2.3518984302657146e-05, |
|
"loss": 0.3572, |
|
"num_input_tokens_seen": 2608576, |
|
"step": 110 |
|
}, |
|
{ |
|
"epoch": 1.0823529411764705, |
|
"grad_norm": 0.25626152753829956, |
|
"learning_rate": 2.1675638308842145e-05, |
|
"loss": 0.372, |
|
"num_input_tokens_seen": 2730096, |
|
"step": 115 |
|
}, |
|
{ |
|
"epoch": 1.1294117647058823, |
|
"grad_norm": 0.2505984604358673, |
|
"learning_rate": 1.9850534531472546e-05, |
|
"loss": 0.3643, |
|
"num_input_tokens_seen": 2850032, |
|
"step": 120 |
|
}, |
|
{ |
|
"epoch": 1.1764705882352942, |
|
"grad_norm": 0.2474757432937622, |
|
"learning_rate": 1.8053688107658908e-05, |
|
"loss": 0.3647, |
|
"num_input_tokens_seen": 2969136, |
|
"step": 125 |
|
}, |
|
{ |
|
"epoch": 1.223529411764706, |
|
"grad_norm": 0.26299813389778137, |
|
"learning_rate": 1.6294959114140034e-05, |
|
"loss": 0.3495, |
|
"num_input_tokens_seen": 3088240, |
|
"step": 130 |
|
}, |
|
{ |
|
"epoch": 1.2705882352941176, |
|
"grad_norm": 0.2596004903316498, |
|
"learning_rate": 1.4583998460759424e-05, |
|
"loss": 0.3458, |
|
"num_input_tokens_seen": 3204544, |
|
"step": 135 |
|
}, |
|
{ |
|
"epoch": 1.3176470588235294, |
|
"grad_norm": 0.26845094561576843, |
|
"learning_rate": 1.2930194931731382e-05, |
|
"loss": 0.3547, |
|
"num_input_tokens_seen": 3321536, |
|
"step": 140 |
|
}, |
|
{ |
|
"epoch": 1.3647058823529412, |
|
"grad_norm": 0.2841053903102875, |
|
"learning_rate": 1.1342623665304209e-05, |
|
"loss": 0.3698, |
|
"num_input_tokens_seen": 3443584, |
|
"step": 145 |
|
}, |
|
{ |
|
"epoch": 1.4117647058823528, |
|
"grad_norm": 0.2576062083244324, |
|
"learning_rate": 9.829996354535172e-06, |
|
"loss": 0.3558, |
|
"num_input_tokens_seen": 3560368, |
|
"step": 150 |
|
}, |
|
{ |
|
"epoch": 1.4588235294117646, |
|
"grad_norm": 0.258001446723938, |
|
"learning_rate": 8.400613442446948e-06, |
|
"loss": 0.3573, |
|
"num_input_tokens_seen": 3679744, |
|
"step": 155 |
|
}, |
|
{ |
|
"epoch": 1.5058823529411764, |
|
"grad_norm": 0.26500120759010315, |
|
"learning_rate": 7.062318573891716e-06, |
|
"loss": 0.3563, |
|
"num_input_tokens_seen": 3797392, |
|
"step": 160 |
|
}, |
|
{ |
|
"epoch": 1.5529411764705883, |
|
"grad_norm": 0.28948289155960083, |
|
"learning_rate": 5.822455554065217e-06, |
|
"loss": 0.3583, |
|
"num_input_tokens_seen": 3918144, |
|
"step": 165 |
|
}, |
|
{ |
|
"epoch": 1.6, |
|
"grad_norm": 0.305418998003006, |
|
"learning_rate": 4.687828049857967e-06, |
|
"loss": 0.3376, |
|
"num_input_tokens_seen": 4031792, |
|
"step": 170 |
|
}, |
|
{ |
|
"epoch": 1.6470588235294117, |
|
"grad_norm": 0.26737797260284424, |
|
"learning_rate": 3.6646622551801345e-06, |
|
"loss": 0.3252, |
|
"num_input_tokens_seen": 4150640, |
|
"step": 175 |
|
}, |
|
{ |
|
"epoch": 1.6941176470588235, |
|
"grad_norm": 0.26723966002464294, |
|
"learning_rate": 2.75857272513132e-06, |
|
"loss": 0.3548, |
|
"num_input_tokens_seen": 4269056, |
|
"step": 180 |
|
}, |
|
{ |
|
"epoch": 1.7411764705882353, |
|
"grad_norm": 0.2512056827545166, |
|
"learning_rate": 1.9745315664982276e-06, |
|
"loss": 0.3339, |
|
"num_input_tokens_seen": 4385712, |
|
"step": 185 |
|
}, |
|
{ |
|
"epoch": 1.788235294117647, |
|
"grad_norm": 0.24429625272750854, |
|
"learning_rate": 1.3168411536452152e-06, |
|
"loss": 0.327, |
|
"num_input_tokens_seen": 4503872, |
|
"step": 190 |
|
}, |
|
{ |
|
"epoch": 1.835294117647059, |
|
"grad_norm": 0.27570071816444397, |
|
"learning_rate": 7.891105195175358e-07, |
|
"loss": 0.3442, |
|
"num_input_tokens_seen": 4627488, |
|
"step": 195 |
|
}, |
|
{ |
|
"epoch": 1.8823529411764706, |
|
"grad_norm": 0.25902682542800903, |
|
"learning_rate": 3.9423555131007925e-07, |
|
"loss": 0.3463, |
|
"num_input_tokens_seen": 4745840, |
|
"step": 200 |
|
}, |
|
{ |
|
"epoch": 1.9294117647058824, |
|
"grad_norm": 0.26380208134651184, |
|
"learning_rate": 1.343830994765982e-07, |
|
"loss": 0.3319, |
|
"num_input_tokens_seen": 4862656, |
|
"step": 205 |
|
}, |
|
{ |
|
"epoch": 1.9764705882352942, |
|
"grad_norm": 0.29207655787467957, |
|
"learning_rate": 1.0979087280141298e-08, |
|
"loss": 0.3512, |
|
"num_input_tokens_seen": 4978496, |
|
"step": 210 |
|
}, |
|
{ |
|
"epoch": 1.9952941176470587, |
|
"num_input_tokens_seen": 5025952, |
|
"step": 212, |
|
"total_flos": 1.998519187370148e+17, |
|
"train_loss": 0.42384658416487137, |
|
"train_runtime": 2655.7506, |
|
"train_samples_per_second": 2.56, |
|
"train_steps_per_second": 0.08 |
|
} |
|
], |
|
"logging_steps": 5, |
|
"max_steps": 212, |
|
"num_input_tokens_seen": 5025952, |
|
"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": 1.998519187370148e+17, |
|
"train_batch_size": 2, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|