bbytxt's picture
Training in progress, step 50, checkpoint
c2b2ff0 verified
raw
history blame
9.96 kB
{
"best_metric": 11.924012184143066,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.03139224611520954,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0006278449223041908,
"grad_norm": 0.02513544075191021,
"learning_rate": 5e-06,
"loss": 11.9326,
"step": 1
},
{
"epoch": 0.0006278449223041908,
"eval_loss": 11.9313383102417,
"eval_runtime": 28.1146,
"eval_samples_per_second": 95.431,
"eval_steps_per_second": 23.867,
"step": 1
},
{
"epoch": 0.0012556898446083817,
"grad_norm": 0.022503087297081947,
"learning_rate": 1e-05,
"loss": 11.9316,
"step": 2
},
{
"epoch": 0.0018835347669125726,
"grad_norm": 0.0192073043435812,
"learning_rate": 1.5e-05,
"loss": 11.9334,
"step": 3
},
{
"epoch": 0.0025113796892167633,
"grad_norm": 0.019655032083392143,
"learning_rate": 2e-05,
"loss": 11.9319,
"step": 4
},
{
"epoch": 0.0031392246115209545,
"grad_norm": 0.02161627821624279,
"learning_rate": 2.5e-05,
"loss": 11.9297,
"step": 5
},
{
"epoch": 0.003767069533825145,
"grad_norm": 0.020643681287765503,
"learning_rate": 3e-05,
"loss": 11.932,
"step": 6
},
{
"epoch": 0.004394914456129336,
"grad_norm": 0.021672042086720467,
"learning_rate": 3.5e-05,
"loss": 11.9308,
"step": 7
},
{
"epoch": 0.005022759378433527,
"grad_norm": 0.022838007658720016,
"learning_rate": 4e-05,
"loss": 11.935,
"step": 8
},
{
"epoch": 0.005650604300737718,
"grad_norm": 0.02091800980269909,
"learning_rate": 4.5e-05,
"loss": 11.9292,
"step": 9
},
{
"epoch": 0.006278449223041909,
"grad_norm": 0.02816697768867016,
"learning_rate": 5e-05,
"loss": 11.9201,
"step": 10
},
{
"epoch": 0.006906294145346099,
"grad_norm": 0.018409784883260727,
"learning_rate": 5.500000000000001e-05,
"loss": 11.9301,
"step": 11
},
{
"epoch": 0.00753413906765029,
"grad_norm": 0.06388456374406815,
"learning_rate": 6e-05,
"loss": 11.9289,
"step": 12
},
{
"epoch": 0.00816198398995448,
"grad_norm": 0.026801548898220062,
"learning_rate": 6.500000000000001e-05,
"loss": 11.9307,
"step": 13
},
{
"epoch": 0.008789828912258673,
"grad_norm": 0.029942037537693977,
"learning_rate": 7e-05,
"loss": 11.9314,
"step": 14
},
{
"epoch": 0.009417673834562863,
"grad_norm": 0.025479784235358238,
"learning_rate": 7.500000000000001e-05,
"loss": 11.9338,
"step": 15
},
{
"epoch": 0.010045518756867053,
"grad_norm": 0.027909839525818825,
"learning_rate": 8e-05,
"loss": 11.9308,
"step": 16
},
{
"epoch": 0.010673363679171245,
"grad_norm": 0.02828867919743061,
"learning_rate": 8.5e-05,
"loss": 11.9292,
"step": 17
},
{
"epoch": 0.011301208601475436,
"grad_norm": 0.022867796942591667,
"learning_rate": 9e-05,
"loss": 11.931,
"step": 18
},
{
"epoch": 0.011929053523779626,
"grad_norm": 0.038008660078048706,
"learning_rate": 9.5e-05,
"loss": 11.9306,
"step": 19
},
{
"epoch": 0.012556898446083818,
"grad_norm": 0.030086949467658997,
"learning_rate": 0.0001,
"loss": 11.9318,
"step": 20
},
{
"epoch": 0.013184743368388008,
"grad_norm": 0.02166604809463024,
"learning_rate": 9.991845519630678e-05,
"loss": 11.9325,
"step": 21
},
{
"epoch": 0.013812588290692198,
"grad_norm": 0.04334748908877373,
"learning_rate": 9.967408676742751e-05,
"loss": 11.9082,
"step": 22
},
{
"epoch": 0.01444043321299639,
"grad_norm": 0.05343957245349884,
"learning_rate": 9.926769179238466e-05,
"loss": 11.9279,
"step": 23
},
{
"epoch": 0.01506827813530058,
"grad_norm": 0.03913533315062523,
"learning_rate": 9.870059584711668e-05,
"loss": 11.9316,
"step": 24
},
{
"epoch": 0.01569612305760477,
"grad_norm": 0.04433680325746536,
"learning_rate": 9.797464868072488e-05,
"loss": 11.9272,
"step": 25
},
{
"epoch": 0.01632396797990896,
"grad_norm": 0.03774190694093704,
"learning_rate": 9.709221818197624e-05,
"loss": 11.9315,
"step": 26
},
{
"epoch": 0.016951812902213155,
"grad_norm": 0.04844358563423157,
"learning_rate": 9.60561826557425e-05,
"loss": 11.9325,
"step": 27
},
{
"epoch": 0.017579657824517345,
"grad_norm": 0.07205117493867874,
"learning_rate": 9.486992143456792e-05,
"loss": 11.9292,
"step": 28
},
{
"epoch": 0.018207502746821536,
"grad_norm": 0.03811033442616463,
"learning_rate": 9.353730385598887e-05,
"loss": 11.9309,
"step": 29
},
{
"epoch": 0.018835347669125726,
"grad_norm": 0.051117513328790665,
"learning_rate": 9.206267664155907e-05,
"loss": 11.9311,
"step": 30
},
{
"epoch": 0.019463192591429916,
"grad_norm": 0.08851032704114914,
"learning_rate": 9.045084971874738e-05,
"loss": 11.9316,
"step": 31
},
{
"epoch": 0.020091037513734106,
"grad_norm": 0.08320491760969162,
"learning_rate": 8.870708053195413e-05,
"loss": 11.9287,
"step": 32
},
{
"epoch": 0.0207188824360383,
"grad_norm": 0.07352913171052933,
"learning_rate": 8.683705689382024e-05,
"loss": 11.9271,
"step": 33
},
{
"epoch": 0.02134672735834249,
"grad_norm": 0.07860593497753143,
"learning_rate": 8.484687843276469e-05,
"loss": 11.9295,
"step": 34
},
{
"epoch": 0.02197457228064668,
"grad_norm": 0.09285508096218109,
"learning_rate": 8.274303669726426e-05,
"loss": 11.9289,
"step": 35
},
{
"epoch": 0.02260241720295087,
"grad_norm": 0.10461730509996414,
"learning_rate": 8.053239398177191e-05,
"loss": 11.9282,
"step": 36
},
{
"epoch": 0.02323026212525506,
"grad_norm": 0.11389969289302826,
"learning_rate": 7.822216094333847e-05,
"loss": 11.9257,
"step": 37
},
{
"epoch": 0.02385810704755925,
"grad_norm": 0.09162261337041855,
"learning_rate": 7.58198730819481e-05,
"loss": 11.9299,
"step": 38
},
{
"epoch": 0.024485951969863445,
"grad_norm": 0.1054549589753151,
"learning_rate": 7.333336616128369e-05,
"loss": 11.9254,
"step": 39
},
{
"epoch": 0.025113796892167636,
"grad_norm": 0.12928307056427002,
"learning_rate": 7.077075065009433e-05,
"loss": 11.9247,
"step": 40
},
{
"epoch": 0.025741641814471826,
"grad_norm": 0.08289871364831924,
"learning_rate": 6.814038526753205e-05,
"loss": 11.9277,
"step": 41
},
{
"epoch": 0.026369486736776016,
"grad_norm": 0.086146779358387,
"learning_rate": 6.545084971874738e-05,
"loss": 11.9263,
"step": 42
},
{
"epoch": 0.026997331659080206,
"grad_norm": 0.1091722697019577,
"learning_rate": 6.271091670967436e-05,
"loss": 11.9255,
"step": 43
},
{
"epoch": 0.027625176581384397,
"grad_norm": 0.0930371880531311,
"learning_rate": 5.992952333228728e-05,
"loss": 11.9262,
"step": 44
},
{
"epoch": 0.02825302150368859,
"grad_norm": 0.09138721227645874,
"learning_rate": 5.7115741913664264e-05,
"loss": 11.9259,
"step": 45
},
{
"epoch": 0.02888086642599278,
"grad_norm": 0.08972511440515518,
"learning_rate": 5.427875042394199e-05,
"loss": 11.9245,
"step": 46
},
{
"epoch": 0.02950871134829697,
"grad_norm": 0.07062887400388718,
"learning_rate": 5.142780253968481e-05,
"loss": 11.9238,
"step": 47
},
{
"epoch": 0.03013655627060116,
"grad_norm": 0.07069500535726547,
"learning_rate": 4.85721974603152e-05,
"loss": 11.9254,
"step": 48
},
{
"epoch": 0.03076440119290535,
"grad_norm": 0.07684428244829178,
"learning_rate": 4.5721249576058027e-05,
"loss": 11.9225,
"step": 49
},
{
"epoch": 0.03139224611520954,
"grad_norm": 0.08182159811258316,
"learning_rate": 4.288425808633575e-05,
"loss": 11.9253,
"step": 50
},
{
"epoch": 0.03139224611520954,
"eval_loss": 11.924012184143066,
"eval_runtime": 28.3289,
"eval_samples_per_second": 94.709,
"eval_steps_per_second": 23.686,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 75,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"early_stopping_threshold": 0.0
},
"attributes": {
"early_stopping_patience_counter": 0
}
},
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 488108851200.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}