|
{ |
|
"best_metric": 0.14551572501659393, |
|
"best_model_checkpoint": "multilingual-e5-small-aligned-sentiment-20241214-new/checkpoint-23439", |
|
"epoch": 3.0, |
|
"eval_steps": 500, |
|
"global_step": 23439, |
|
"is_hyper_param_search": false, |
|
"is_local_process_zero": true, |
|
"is_world_process_zero": true, |
|
"log_history": [ |
|
{ |
|
"epoch": 0.06399590426212723, |
|
"grad_norm": 1.8201525211334229, |
|
"learning_rate": 4.8933401595631215e-05, |
|
"loss": 0.3311, |
|
"step": 500 |
|
}, |
|
{ |
|
"epoch": 0.12799180852425446, |
|
"grad_norm": 1.933944821357727, |
|
"learning_rate": 4.786680319126243e-05, |
|
"loss": 0.259, |
|
"step": 1000 |
|
}, |
|
{ |
|
"epoch": 0.19198771278638166, |
|
"grad_norm": 1.5761635303497314, |
|
"learning_rate": 4.680020478689364e-05, |
|
"loss": 0.244, |
|
"step": 1500 |
|
}, |
|
{ |
|
"epoch": 0.2559836170485089, |
|
"grad_norm": 2.812056303024292, |
|
"learning_rate": 4.573360638252485e-05, |
|
"loss": 0.2353, |
|
"step": 2000 |
|
}, |
|
{ |
|
"epoch": 0.3199795213106361, |
|
"grad_norm": 2.022963285446167, |
|
"learning_rate": 4.4667007978156063e-05, |
|
"loss": 0.2261, |
|
"step": 2500 |
|
}, |
|
{ |
|
"epoch": 0.3839754255727633, |
|
"grad_norm": 2.1023800373077393, |
|
"learning_rate": 4.360040957378728e-05, |
|
"loss": 0.22, |
|
"step": 3000 |
|
}, |
|
{ |
|
"epoch": 0.4479713298348906, |
|
"grad_norm": 1.8184232711791992, |
|
"learning_rate": 4.2533811169418495e-05, |
|
"loss": 0.2166, |
|
"step": 3500 |
|
}, |
|
{ |
|
"epoch": 0.5119672340970178, |
|
"grad_norm": 1.9675606489181519, |
|
"learning_rate": 4.146721276504971e-05, |
|
"loss": 0.2124, |
|
"step": 4000 |
|
}, |
|
{ |
|
"epoch": 0.575963138359145, |
|
"grad_norm": 1.7122745513916016, |
|
"learning_rate": 4.040061436068092e-05, |
|
"loss": 0.209, |
|
"step": 4500 |
|
}, |
|
{ |
|
"epoch": 0.6399590426212722, |
|
"grad_norm": 2.49656081199646, |
|
"learning_rate": 3.933401595631213e-05, |
|
"loss": 0.205, |
|
"step": 5000 |
|
}, |
|
{ |
|
"epoch": 0.7039549468833994, |
|
"grad_norm": 3.310446262359619, |
|
"learning_rate": 3.8267417551943344e-05, |
|
"loss": 0.203, |
|
"step": 5500 |
|
}, |
|
{ |
|
"epoch": 0.7679508511455266, |
|
"grad_norm": 2.4122066497802734, |
|
"learning_rate": 3.7200819147574556e-05, |
|
"loss": 0.1964, |
|
"step": 6000 |
|
}, |
|
{ |
|
"epoch": 0.831946755407654, |
|
"grad_norm": 1.8602417707443237, |
|
"learning_rate": 3.613422074320577e-05, |
|
"loss": 0.1982, |
|
"step": 6500 |
|
}, |
|
{ |
|
"epoch": 0.8959426596697811, |
|
"grad_norm": 3.1396756172180176, |
|
"learning_rate": 3.506762233883698e-05, |
|
"loss": 0.1935, |
|
"step": 7000 |
|
}, |
|
{ |
|
"epoch": 0.9599385639319084, |
|
"grad_norm": 4.411809921264648, |
|
"learning_rate": 3.400102393446819e-05, |
|
"loss": 0.1946, |
|
"step": 7500 |
|
}, |
|
{ |
|
"epoch": 1.0, |
|
"eval_loss": 0.16471454501152039, |
|
"eval_mse": 0.16471455099075522, |
|
"eval_runtime": 97.1359, |
|
"eval_samples_per_second": 1874.807, |
|
"eval_steps_per_second": 234.352, |
|
"step": 7813 |
|
}, |
|
{ |
|
"epoch": 1.0239344681940357, |
|
"grad_norm": 2.101229429244995, |
|
"learning_rate": 3.293442553009941e-05, |
|
"loss": 0.1776, |
|
"step": 8000 |
|
}, |
|
{ |
|
"epoch": 1.0879303724561629, |
|
"grad_norm": 1.918332576751709, |
|
"learning_rate": 3.1867827125730624e-05, |
|
"loss": 0.1548, |
|
"step": 8500 |
|
}, |
|
{ |
|
"epoch": 1.15192627671829, |
|
"grad_norm": 2.1414854526519775, |
|
"learning_rate": 3.0801228721361836e-05, |
|
"loss": 0.1489, |
|
"step": 9000 |
|
}, |
|
{ |
|
"epoch": 1.2159221809804173, |
|
"grad_norm": 1.7239971160888672, |
|
"learning_rate": 2.9734630316993045e-05, |
|
"loss": 0.1472, |
|
"step": 9500 |
|
}, |
|
{ |
|
"epoch": 1.2799180852425445, |
|
"grad_norm": 1.5635288953781128, |
|
"learning_rate": 2.866803191262426e-05, |
|
"loss": 0.1491, |
|
"step": 10000 |
|
}, |
|
{ |
|
"epoch": 1.3439139895046717, |
|
"grad_norm": 2.0498759746551514, |
|
"learning_rate": 2.7601433508255476e-05, |
|
"loss": 0.1493, |
|
"step": 10500 |
|
}, |
|
{ |
|
"epoch": 1.4079098937667989, |
|
"grad_norm": 1.2982215881347656, |
|
"learning_rate": 2.6534835103886685e-05, |
|
"loss": 0.1458, |
|
"step": 11000 |
|
}, |
|
{ |
|
"epoch": 1.471905798028926, |
|
"grad_norm": 1.9183140993118286, |
|
"learning_rate": 2.54682366995179e-05, |
|
"loss": 0.149, |
|
"step": 11500 |
|
}, |
|
{ |
|
"epoch": 1.5359017022910533, |
|
"grad_norm": 1.4604493379592896, |
|
"learning_rate": 2.4401638295149112e-05, |
|
"loss": 0.1441, |
|
"step": 12000 |
|
}, |
|
{ |
|
"epoch": 1.5998976065531805, |
|
"grad_norm": 1.4501017332077026, |
|
"learning_rate": 2.3335039890780325e-05, |
|
"loss": 0.1483, |
|
"step": 12500 |
|
}, |
|
{ |
|
"epoch": 1.6638935108153077, |
|
"grad_norm": 1.7177495956420898, |
|
"learning_rate": 2.2268441486411537e-05, |
|
"loss": 0.1443, |
|
"step": 13000 |
|
}, |
|
{ |
|
"epoch": 1.727889415077435, |
|
"grad_norm": 2.2127881050109863, |
|
"learning_rate": 2.120184308204275e-05, |
|
"loss": 0.1458, |
|
"step": 13500 |
|
}, |
|
{ |
|
"epoch": 1.7918853193395623, |
|
"grad_norm": 1.5237836837768555, |
|
"learning_rate": 2.0135244677673965e-05, |
|
"loss": 0.1435, |
|
"step": 14000 |
|
}, |
|
{ |
|
"epoch": 1.8558812236016895, |
|
"grad_norm": 2.217888355255127, |
|
"learning_rate": 1.9068646273305177e-05, |
|
"loss": 0.141, |
|
"step": 14500 |
|
}, |
|
{ |
|
"epoch": 1.9198771278638167, |
|
"grad_norm": 3.9023308753967285, |
|
"learning_rate": 1.800204786893639e-05, |
|
"loss": 0.139, |
|
"step": 15000 |
|
}, |
|
{ |
|
"epoch": 1.983873032125944, |
|
"grad_norm": 1.6923686265945435, |
|
"learning_rate": 1.69354494645676e-05, |
|
"loss": 0.1385, |
|
"step": 15500 |
|
}, |
|
{ |
|
"epoch": 2.0, |
|
"eval_loss": 0.15275108814239502, |
|
"eval_mse": 0.15275108203598506, |
|
"eval_runtime": 101.0827, |
|
"eval_samples_per_second": 1801.605, |
|
"eval_steps_per_second": 225.202, |
|
"step": 15626 |
|
}, |
|
{ |
|
"epoch": 2.0478689363880713, |
|
"grad_norm": 3.1119792461395264, |
|
"learning_rate": 1.5868851060198814e-05, |
|
"loss": 0.1234, |
|
"step": 16000 |
|
}, |
|
{ |
|
"epoch": 2.1118648406501985, |
|
"grad_norm": 1.3244566917419434, |
|
"learning_rate": 1.480225265583003e-05, |
|
"loss": 0.1168, |
|
"step": 16500 |
|
}, |
|
{ |
|
"epoch": 2.1758607449123257, |
|
"grad_norm": 1.8541600704193115, |
|
"learning_rate": 1.3735654251461241e-05, |
|
"loss": 0.1129, |
|
"step": 17000 |
|
}, |
|
{ |
|
"epoch": 2.239856649174453, |
|
"grad_norm": 1.291128396987915, |
|
"learning_rate": 1.2669055847092454e-05, |
|
"loss": 0.1161, |
|
"step": 17500 |
|
}, |
|
{ |
|
"epoch": 2.30385255343658, |
|
"grad_norm": 1.4121185541152954, |
|
"learning_rate": 1.1602457442723666e-05, |
|
"loss": 0.1137, |
|
"step": 18000 |
|
}, |
|
{ |
|
"epoch": 2.3678484576987073, |
|
"grad_norm": 1.1205600500106812, |
|
"learning_rate": 1.053585903835488e-05, |
|
"loss": 0.1151, |
|
"step": 18500 |
|
}, |
|
{ |
|
"epoch": 2.4318443619608345, |
|
"grad_norm": 2.112236976623535, |
|
"learning_rate": 9.469260633986092e-06, |
|
"loss": 0.114, |
|
"step": 19000 |
|
}, |
|
{ |
|
"epoch": 2.4958402662229617, |
|
"grad_norm": 1.419636845588684, |
|
"learning_rate": 8.402662229617304e-06, |
|
"loss": 0.1152, |
|
"step": 19500 |
|
}, |
|
{ |
|
"epoch": 2.559836170485089, |
|
"grad_norm": 1.89504873752594, |
|
"learning_rate": 7.336063825248518e-06, |
|
"loss": 0.1153, |
|
"step": 20000 |
|
}, |
|
{ |
|
"epoch": 2.623832074747216, |
|
"grad_norm": 1.8703386783599854, |
|
"learning_rate": 6.26946542087973e-06, |
|
"loss": 0.1131, |
|
"step": 20500 |
|
}, |
|
{ |
|
"epoch": 2.6878279790093433, |
|
"grad_norm": 1.3758282661437988, |
|
"learning_rate": 5.202867016510943e-06, |
|
"loss": 0.1134, |
|
"step": 21000 |
|
}, |
|
{ |
|
"epoch": 2.7518238832714705, |
|
"grad_norm": 0.9953869581222534, |
|
"learning_rate": 4.1362686121421564e-06, |
|
"loss": 0.1122, |
|
"step": 21500 |
|
}, |
|
{ |
|
"epoch": 2.8158197875335977, |
|
"grad_norm": 1.4371693134307861, |
|
"learning_rate": 3.069670207773369e-06, |
|
"loss": 0.1117, |
|
"step": 22000 |
|
}, |
|
{ |
|
"epoch": 2.879815691795725, |
|
"grad_norm": 1.3081939220428467, |
|
"learning_rate": 2.003071803404582e-06, |
|
"loss": 0.1121, |
|
"step": 22500 |
|
}, |
|
{ |
|
"epoch": 2.943811596057852, |
|
"grad_norm": 1.5292563438415527, |
|
"learning_rate": 9.364733990357951e-07, |
|
"loss": 0.1121, |
|
"step": 23000 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"eval_loss": 0.14551572501659393, |
|
"eval_mse": 0.14551572992011078, |
|
"eval_runtime": 108.2898, |
|
"eval_samples_per_second": 1681.7, |
|
"eval_steps_per_second": 210.214, |
|
"step": 23439 |
|
}, |
|
{ |
|
"epoch": 3.0, |
|
"step": 23439, |
|
"total_flos": 4.9403660544e+16, |
|
"train_loss": 0.16052449254575832, |
|
"train_runtime": 3301.1135, |
|
"train_samples_per_second": 908.784, |
|
"train_steps_per_second": 7.1 |
|
} |
|
], |
|
"logging_steps": 500, |
|
"max_steps": 23439, |
|
"num_input_tokens_seen": 0, |
|
"num_train_epochs": 3, |
|
"save_steps": 500, |
|
"stateful_callbacks": { |
|
"TrainerControl": { |
|
"args": { |
|
"should_epoch_stop": false, |
|
"should_evaluate": false, |
|
"should_log": false, |
|
"should_save": true, |
|
"should_training_stop": true |
|
}, |
|
"attributes": {} |
|
} |
|
}, |
|
"total_flos": 4.9403660544e+16, |
|
"train_batch_size": 128, |
|
"trial_name": null, |
|
"trial_params": null |
|
} |
|
|