MATH-V2 / checkpoint-118 /trainer_state.json
burnboom's picture
Upload folder using huggingface_hub
475ff30 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 118,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.08533333333333333,
"grad_norm": 0.15005646646022797,
"learning_rate": 0.0001923728813559322,
"loss": 1.0408,
"step": 10
},
{
"epoch": 0.17066666666666666,
"grad_norm": 0.10998421907424927,
"learning_rate": 0.00018389830508474576,
"loss": 0.8946,
"step": 20
},
{
"epoch": 0.256,
"grad_norm": 0.09101815521717072,
"learning_rate": 0.00017542372881355933,
"loss": 0.8307,
"step": 30
},
{
"epoch": 0.3413333333333333,
"grad_norm": 0.09716884791851044,
"learning_rate": 0.0001669491525423729,
"loss": 0.8124,
"step": 40
},
{
"epoch": 0.4266666666666667,
"grad_norm": 0.08716615289449692,
"learning_rate": 0.00015847457627118645,
"loss": 0.7973,
"step": 50
},
{
"epoch": 0.512,
"grad_norm": 0.08717850595712662,
"learning_rate": 0.00015000000000000001,
"loss": 0.8174,
"step": 60
},
{
"epoch": 0.5973333333333334,
"grad_norm": 0.08700486272573471,
"learning_rate": 0.00014152542372881358,
"loss": 0.7927,
"step": 70
},
{
"epoch": 0.6826666666666666,
"grad_norm": 0.08963647484779358,
"learning_rate": 0.0001330508474576271,
"loss": 0.7954,
"step": 80
},
{
"epoch": 0.768,
"grad_norm": 0.09428053349256516,
"learning_rate": 0.00012457627118644068,
"loss": 0.824,
"step": 90
},
{
"epoch": 0.8533333333333334,
"grad_norm": 0.10081394761800766,
"learning_rate": 0.00011610169491525424,
"loss": 0.789,
"step": 100
},
{
"epoch": 0.9386666666666666,
"grad_norm": 0.09507747739553452,
"learning_rate": 0.0001076271186440678,
"loss": 0.7882,
"step": 110
}
],
"logging_steps": 10,
"max_steps": 236,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 2.071952621568e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}