model11 / last-checkpoint /trainer_state.json
Agtian's picture
Training in progress, step 200, checkpoint
fdbf37b verified
Raw
History Blame Contribute Delete
4.36 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.07817080320500293,
"eval_steps": 500,
"global_step": 200,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.003908540160250147,
"grad_norm": 4.148934841156006,
"learning_rate": 7.031250000000001e-06,
"loss": 2.8433177947998045,
"step": 10
},
{
"epoch": 0.007817080320500294,
"grad_norm": 2.291874408721924,
"learning_rate": 1.484375e-05,
"loss": 3.8935680389404297,
"step": 20
},
{
"epoch": 0.01172562048075044,
"grad_norm": 3.1765084266662598,
"learning_rate": 2.2656250000000002e-05,
"loss": 3.173785400390625,
"step": 30
},
{
"epoch": 0.015634160641000587,
"grad_norm": 2.4662954807281494,
"learning_rate": 3.0468750000000002e-05,
"loss": 3.7973873138427736,
"step": 40
},
{
"epoch": 0.019542700801250732,
"grad_norm": 84.3653564453125,
"learning_rate": 3.828125e-05,
"loss": 2.689250946044922,
"step": 50
},
{
"epoch": 0.02345124096150088,
"grad_norm": 1.9814364910125732,
"learning_rate": 4.609375e-05,
"loss": 3.010054588317871,
"step": 60
},
{
"epoch": 0.027359781121751026,
"grad_norm": 4.1676201820373535,
"learning_rate": 5.3906250000000006e-05,
"loss": 3.501321792602539,
"step": 70
},
{
"epoch": 0.031268321282001174,
"grad_norm": 3.0464155673980713,
"learning_rate": 6.171875e-05,
"loss": 3.106698226928711,
"step": 80
},
{
"epoch": 0.035176861442251316,
"grad_norm": 3.9472484588623047,
"learning_rate": 6.953125e-05,
"loss": 3.3658538818359376,
"step": 90
},
{
"epoch": 0.039085401602501464,
"grad_norm": 2.833709478378296,
"learning_rate": 7.734375e-05,
"loss": 3.4841968536376955,
"step": 100
},
{
"epoch": 0.04299394176275161,
"grad_norm": 21.948543548583984,
"learning_rate": 8.515625e-05,
"loss": 3.5636287689208985,
"step": 110
},
{
"epoch": 0.04690248192300176,
"grad_norm": 5.58203125,
"learning_rate": 9.296875e-05,
"loss": 2.957254981994629,
"step": 120
},
{
"epoch": 0.0508110220832519,
"grad_norm": 2.311690330505371,
"learning_rate": 0.00010078125,
"loss": 2.8846551895141603,
"step": 130
},
{
"epoch": 0.05471956224350205,
"grad_norm": 3.563748598098755,
"learning_rate": 0.00010859375000000001,
"loss": 3.3207424163818358,
"step": 140
},
{
"epoch": 0.0586281024037522,
"grad_norm": 2.694491147994995,
"learning_rate": 0.00011640625,
"loss": 3.001876449584961,
"step": 150
},
{
"epoch": 0.06253664256400235,
"grad_norm": 4.056739807128906,
"learning_rate": 0.00012421875,
"loss": 3.2485610961914064,
"step": 160
},
{
"epoch": 0.0664451827242525,
"grad_norm": 4.93998908996582,
"learning_rate": 0.00013203125000000001,
"loss": 3.2433551788330077,
"step": 170
},
{
"epoch": 0.07035372288450263,
"grad_norm": 4.614671230316162,
"learning_rate": 0.00013984375,
"loss": 3.1572134017944338,
"step": 180
},
{
"epoch": 0.07426226304475278,
"grad_norm": 1.8324024677276611,
"learning_rate": 0.00014765625,
"loss": 2.9814380645751952,
"step": 190
},
{
"epoch": 0.07817080320500293,
"grad_norm": 2.2585086822509766,
"learning_rate": 0.00015546875,
"loss": 3.5383621215820313,
"step": 200
}
],
"logging_steps": 10,
"max_steps": 2559,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 5.753012541967411e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}