VERSIL91's picture
End of training
6b2aa44 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.07367160880375725,
"eval_steps": 13,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0014734321760751451,
"grad_norm": 2.526303768157959,
"learning_rate": 1e-05,
"loss": 178.0,
"step": 1
},
{
"epoch": 0.0014734321760751451,
"eval_loss": 11.119754791259766,
"eval_runtime": 16.9469,
"eval_samples_per_second": 67.505,
"eval_steps_per_second": 33.752,
"step": 1
},
{
"epoch": 0.0029468643521502903,
"grad_norm": 2.3691565990448,
"learning_rate": 2e-05,
"loss": 177.875,
"step": 2
},
{
"epoch": 0.004420296528225435,
"grad_norm": 2.2422916889190674,
"learning_rate": 3e-05,
"loss": 178.0,
"step": 3
},
{
"epoch": 0.0058937287043005805,
"grad_norm": 2.2829580307006836,
"learning_rate": 4e-05,
"loss": 177.9375,
"step": 4
},
{
"epoch": 0.007367160880375725,
"grad_norm": 2.3341360092163086,
"learning_rate": 5e-05,
"loss": 178.0,
"step": 5
},
{
"epoch": 0.00884059305645087,
"grad_norm": 2.2904160022735596,
"learning_rate": 6e-05,
"loss": 177.875,
"step": 6
},
{
"epoch": 0.010314025232526015,
"grad_norm": 2.4523940086364746,
"learning_rate": 7e-05,
"loss": 177.9375,
"step": 7
},
{
"epoch": 0.011787457408601161,
"grad_norm": 2.219071388244629,
"learning_rate": 8e-05,
"loss": 178.0,
"step": 8
},
{
"epoch": 0.013260889584676305,
"grad_norm": 2.4279353618621826,
"learning_rate": 9e-05,
"loss": 177.9375,
"step": 9
},
{
"epoch": 0.01473432176075145,
"grad_norm": 2.4859466552734375,
"learning_rate": 0.0001,
"loss": 177.9375,
"step": 10
},
{
"epoch": 0.016207753936826594,
"grad_norm": 2.4604239463806152,
"learning_rate": 9.98458666866564e-05,
"loss": 177.875,
"step": 11
},
{
"epoch": 0.01768118611290174,
"grad_norm": 2.6057918071746826,
"learning_rate": 9.938441702975689e-05,
"loss": 177.8125,
"step": 12
},
{
"epoch": 0.019154618288976886,
"grad_norm": 2.450312376022339,
"learning_rate": 9.861849601988383e-05,
"loss": 177.8125,
"step": 13
},
{
"epoch": 0.019154618288976886,
"eval_loss": 11.113417625427246,
"eval_runtime": 1.4419,
"eval_samples_per_second": 793.402,
"eval_steps_per_second": 396.701,
"step": 13
},
{
"epoch": 0.02062805046505203,
"grad_norm": 2.529689311981201,
"learning_rate": 9.755282581475769e-05,
"loss": 177.875,
"step": 14
},
{
"epoch": 0.022101482641127174,
"grad_norm": 2.641403913497925,
"learning_rate": 9.619397662556435e-05,
"loss": 177.8125,
"step": 15
},
{
"epoch": 0.023574914817202322,
"grad_norm": 2.6765689849853516,
"learning_rate": 9.45503262094184e-05,
"loss": 177.875,
"step": 16
},
{
"epoch": 0.025048346993277466,
"grad_norm": 2.610333204269409,
"learning_rate": 9.263200821770461e-05,
"loss": 177.8125,
"step": 17
},
{
"epoch": 0.02652177916935261,
"grad_norm": 2.503725290298462,
"learning_rate": 9.045084971874738e-05,
"loss": 177.6875,
"step": 18
},
{
"epoch": 0.027995211345427755,
"grad_norm": 2.6443910598754883,
"learning_rate": 8.802029828000156e-05,
"loss": 177.75,
"step": 19
},
{
"epoch": 0.0294686435215029,
"grad_norm": 2.664630651473999,
"learning_rate": 8.535533905932738e-05,
"loss": 177.6875,
"step": 20
},
{
"epoch": 0.030942075697578047,
"grad_norm": 2.6151347160339355,
"learning_rate": 8.247240241650918e-05,
"loss": 177.625,
"step": 21
},
{
"epoch": 0.03241550787365319,
"grad_norm": 2.9669296741485596,
"learning_rate": 7.938926261462366e-05,
"loss": 177.5625,
"step": 22
},
{
"epoch": 0.03388894004972834,
"grad_norm": 3.140516996383667,
"learning_rate": 7.612492823579745e-05,
"loss": 177.4375,
"step": 23
},
{
"epoch": 0.03536237222580348,
"grad_norm": 2.9213013648986816,
"learning_rate": 7.269952498697734e-05,
"loss": 177.5625,
"step": 24
},
{
"epoch": 0.03683580440187863,
"grad_norm": 2.808756113052368,
"learning_rate": 6.91341716182545e-05,
"loss": 177.4375,
"step": 25
},
{
"epoch": 0.03830923657795377,
"grad_norm": 2.989635944366455,
"learning_rate": 6.545084971874738e-05,
"loss": 177.5625,
"step": 26
},
{
"epoch": 0.03830923657795377,
"eval_loss": 11.093968391418457,
"eval_runtime": 1.4116,
"eval_samples_per_second": 810.449,
"eval_steps_per_second": 405.224,
"step": 26
},
{
"epoch": 0.039782668754028916,
"grad_norm": 3.0922422409057617,
"learning_rate": 6.167226819279528e-05,
"loss": 177.5625,
"step": 27
},
{
"epoch": 0.04125610093010406,
"grad_norm": 2.9242608547210693,
"learning_rate": 5.782172325201155e-05,
"loss": 177.5,
"step": 28
},
{
"epoch": 0.042729533106179204,
"grad_norm": 3.0539040565490723,
"learning_rate": 5.392295478639225e-05,
"loss": 177.5,
"step": 29
},
{
"epoch": 0.04420296528225435,
"grad_norm": 2.946568489074707,
"learning_rate": 5e-05,
"loss": 177.5,
"step": 30
},
{
"epoch": 0.04567639745832949,
"grad_norm": 2.963487148284912,
"learning_rate": 4.607704521360776e-05,
"loss": 177.625,
"step": 31
},
{
"epoch": 0.047149829634404644,
"grad_norm": 2.9389593601226807,
"learning_rate": 4.2178276747988446e-05,
"loss": 177.3125,
"step": 32
},
{
"epoch": 0.04862326181047979,
"grad_norm": 3.1627955436706543,
"learning_rate": 3.832773180720475e-05,
"loss": 177.5,
"step": 33
},
{
"epoch": 0.05009669398655493,
"grad_norm": 3.1742196083068848,
"learning_rate": 3.4549150281252636e-05,
"loss": 177.375,
"step": 34
},
{
"epoch": 0.05157012616263008,
"grad_norm": 3.0531041622161865,
"learning_rate": 3.086582838174551e-05,
"loss": 177.3125,
"step": 35
},
{
"epoch": 0.05304355833870522,
"grad_norm": 3.1435036659240723,
"learning_rate": 2.7300475013022663e-05,
"loss": 177.25,
"step": 36
},
{
"epoch": 0.054516990514780365,
"grad_norm": 3.3767170906066895,
"learning_rate": 2.3875071764202563e-05,
"loss": 177.375,
"step": 37
},
{
"epoch": 0.05599042269085551,
"grad_norm": 3.366469383239746,
"learning_rate": 2.061073738537635e-05,
"loss": 177.1875,
"step": 38
},
{
"epoch": 0.057463854866930654,
"grad_norm": 3.1645619869232178,
"learning_rate": 1.7527597583490822e-05,
"loss": 177.4375,
"step": 39
},
{
"epoch": 0.057463854866930654,
"eval_loss": 11.081294059753418,
"eval_runtime": 1.407,
"eval_samples_per_second": 813.067,
"eval_steps_per_second": 406.533,
"step": 39
},
{
"epoch": 0.0589372870430058,
"grad_norm": 3.380972385406494,
"learning_rate": 1.4644660940672627e-05,
"loss": 177.375,
"step": 40
},
{
"epoch": 0.06041071921908095,
"grad_norm": 3.349307060241699,
"learning_rate": 1.1979701719998453e-05,
"loss": 177.25,
"step": 41
},
{
"epoch": 0.061884151395156094,
"grad_norm": 3.404517412185669,
"learning_rate": 9.549150281252633e-06,
"loss": 177.125,
"step": 42
},
{
"epoch": 0.06335758357123124,
"grad_norm": 3.3322713375091553,
"learning_rate": 7.367991782295391e-06,
"loss": 177.5,
"step": 43
},
{
"epoch": 0.06483101574730638,
"grad_norm": 3.0686938762664795,
"learning_rate": 5.449673790581611e-06,
"loss": 177.25,
"step": 44
},
{
"epoch": 0.06630444792338153,
"grad_norm": 3.107104778289795,
"learning_rate": 3.8060233744356633e-06,
"loss": 177.4375,
"step": 45
},
{
"epoch": 0.06777788009945668,
"grad_norm": 3.2900314331054688,
"learning_rate": 2.4471741852423237e-06,
"loss": 177.3125,
"step": 46
},
{
"epoch": 0.06925131227553182,
"grad_norm": 3.3762176036834717,
"learning_rate": 1.3815039801161721e-06,
"loss": 177.375,
"step": 47
},
{
"epoch": 0.07072474445160697,
"grad_norm": 3.4525339603424072,
"learning_rate": 6.15582970243117e-07,
"loss": 177.25,
"step": 48
},
{
"epoch": 0.0721981766276821,
"grad_norm": 3.322770595550537,
"learning_rate": 1.5413331334360182e-07,
"loss": 177.4375,
"step": 49
},
{
"epoch": 0.07367160880375725,
"grad_norm": 3.364713430404663,
"learning_rate": 0.0,
"loss": 177.125,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 13,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1928960409600.0,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}