16-clusters-balanced-2 / trainer_state.json
MHGanainy's picture
MHGanainy/16-clusters-balanced-2
ff52c71 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 3491,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.028645087367516472,
"grad_norm": 0.1262262761592865,
"learning_rate": 6.666666666666667e-06,
"loss": 2.4085,
"step": 100
},
{
"epoch": 0.057290174735032943,
"grad_norm": 0.1915147453546524,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.3837,
"step": 200
},
{
"epoch": 0.08593526210254941,
"grad_norm": 0.29049137234687805,
"learning_rate": 2e-05,
"loss": 2.3033,
"step": 300
},
{
"epoch": 0.11458034947006589,
"grad_norm": 0.37286341190338135,
"learning_rate": 1.995157548035189e-05,
"loss": 2.2488,
"step": 400
},
{
"epoch": 0.14322543683758235,
"grad_norm": 0.5497928261756897,
"learning_rate": 1.9806770908228177e-05,
"loss": 2.2041,
"step": 500
},
{
"epoch": 0.17187052420509882,
"grad_norm": 0.5118074417114258,
"learning_rate": 1.9566988701998455e-05,
"loss": 2.1989,
"step": 600
},
{
"epoch": 0.2005156115726153,
"grad_norm": 0.6133567690849304,
"learning_rate": 1.9234551129294094e-05,
"loss": 2.1834,
"step": 700
},
{
"epoch": 0.22916069894013177,
"grad_norm": 0.6299872398376465,
"learning_rate": 1.881267781606933e-05,
"loss": 2.1355,
"step": 800
},
{
"epoch": 0.2578057863076482,
"grad_norm": 0.598913848400116,
"learning_rate": 1.8305454564833215e-05,
"loss": 2.1441,
"step": 900
},
{
"epoch": 0.2864508736751647,
"grad_norm": 0.7015722990036011,
"learning_rate": 1.7717793784044842e-05,
"loss": 2.1285,
"step": 1000
},
{
"epoch": 0.31509596104268117,
"grad_norm": 0.7097934484481812,
"learning_rate": 1.705538691190936e-05,
"loss": 2.0962,
"step": 1100
},
{
"epoch": 0.34374104841019765,
"grad_norm": 0.7258936762809753,
"learning_rate": 1.6324649295345715e-05,
"loss": 2.0952,
"step": 1200
},
{
"epoch": 0.3723861357777141,
"grad_norm": 0.8039085268974304,
"learning_rate": 1.5532658057968092e-05,
"loss": 2.0718,
"step": 1300
},
{
"epoch": 0.4010312231452306,
"grad_norm": 0.7117269039154053,
"learning_rate": 1.4687083558823592e-05,
"loss": 2.0548,
"step": 1400
},
{
"epoch": 0.4296763105127471,
"grad_norm": 0.9214915633201599,
"learning_rate": 1.3796115105701774e-05,
"loss": 2.0468,
"step": 1500
},
{
"epoch": 0.45832139788026355,
"grad_norm": 0.8132017254829407,
"learning_rate": 1.2868381642475443e-05,
"loss": 2.0551,
"step": 1600
},
{
"epoch": 0.48696648524778,
"grad_norm": 0.8367148637771606,
"learning_rate": 1.1912868178608244e-05,
"loss": 2.0246,
"step": 1700
},
{
"epoch": 0.5156115726152964,
"grad_norm": 0.9992151856422424,
"learning_rate": 1.0938828770201192e-05,
"loss": 2.0513,
"step": 1800
},
{
"epoch": 0.5442566599828129,
"grad_norm": 0.9009063839912415,
"learning_rate": 9.955696895348375e-06,
"loss": 2.0589,
"step": 1900
},
{
"epoch": 0.5729017473503294,
"grad_norm": 0.9736935496330261,
"learning_rate": 8.972994091807894e-06,
"loss": 2.0288,
"step": 2000
},
{
"epoch": 0.6015468347178459,
"grad_norm": 1.0005104541778564,
"learning_rate": 8.000237741823406e-06,
"loss": 2.0456,
"step": 2100
},
{
"epoch": 0.6301919220853623,
"grad_norm": 0.970936119556427,
"learning_rate": 7.046848897191447e-06,
"loss": 2.0249,
"step": 2200
},
{
"epoch": 0.6588370094528788,
"grad_norm": 0.7913901209831238,
"learning_rate": 6.122061037279847e-06,
"loss": 2.0232,
"step": 2300
},
{
"epoch": 0.6874820968203953,
"grad_norm": 1.0088832378387451,
"learning_rate": 5.234830643667135e-06,
"loss": 2.0284,
"step": 2400
},
{
"epoch": 0.7161271841879118,
"grad_norm": 0.8936773538589478,
"learning_rate": 4.393750457478884e-06,
"loss": 1.9721,
"step": 2500
},
{
"epoch": 0.7447722715554282,
"grad_norm": 0.907300591468811,
"learning_rate": 3.6069662595154454e-06,
"loss": 1.9842,
"step": 2600
},
{
"epoch": 0.7734173589229447,
"grad_norm": 1.124584674835205,
"learning_rate": 2.882097979147437e-06,
"loss": 2.0167,
"step": 2700
},
{
"epoch": 0.8020624462904612,
"grad_norm": 1.132207989692688,
"learning_rate": 2.22616589603185e-06,
"loss": 1.9799,
"step": 2800
},
{
"epoch": 0.8307075336579777,
"grad_norm": 0.9082025289535522,
"learning_rate": 1.645522649378023e-06,
"loss": 2.0077,
"step": 2900
},
{
"epoch": 0.8593526210254941,
"grad_norm": 1.0919737815856934,
"learning_rate": 1.1457917132471763e-06,
"loss": 2.0036,
"step": 3000
},
{
"epoch": 0.8879977083930106,
"grad_norm": 1.0823696851730347,
"learning_rate": 7.31812933746403e-07,
"loss": 2.0146,
"step": 3100
},
{
"epoch": 0.9166427957605271,
"grad_norm": 0.8451834917068481,
"learning_rate": 4.0759565558406764e-07,
"loss": 2.0113,
"step": 3200
},
{
"epoch": 0.9452878831280436,
"grad_norm": 0.8617744445800781,
"learning_rate": 1.762798919514952e-07,
"loss": 2.0178,
"step": 3300
},
{
"epoch": 0.97393297049556,
"grad_norm": 0.981512725353241,
"learning_rate": 4.010591379687734e-08,
"loss": 2.0196,
"step": 3400
},
{
"epoch": 1.0,
"step": 3491,
"total_flos": 6.34336402931712e+16,
"train_loss": 2.088384527218987,
"train_runtime": 1088.6852,
"train_samples_per_second": 6.412,
"train_steps_per_second": 3.207
}
],
"logging_steps": 100,
"max_steps": 3491,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 6.34336402931712e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}