nttx's picture
Training in progress, step 50, checkpoint
1db488a verified
raw
history blame
9.96 kB
{
"best_metric": 11.5,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.07209805335255948,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0014419610670511895,
"grad_norm": 4.551077290670946e-05,
"learning_rate": 1e-05,
"loss": 46.0,
"step": 1
},
{
"epoch": 0.0014419610670511895,
"eval_loss": 11.5,
"eval_runtime": 6.5915,
"eval_samples_per_second": 177.349,
"eval_steps_per_second": 44.451,
"step": 1
},
{
"epoch": 0.002883922134102379,
"grad_norm": 2.4219067199737765e-05,
"learning_rate": 2e-05,
"loss": 46.0,
"step": 2
},
{
"epoch": 0.004325883201153569,
"grad_norm": 3.92902220482938e-05,
"learning_rate": 3e-05,
"loss": 46.0,
"step": 3
},
{
"epoch": 0.005767844268204758,
"grad_norm": 2.3436263290932402e-05,
"learning_rate": 4e-05,
"loss": 46.0,
"step": 4
},
{
"epoch": 0.007209805335255948,
"grad_norm": 2.706063060031738e-05,
"learning_rate": 5e-05,
"loss": 46.0,
"step": 5
},
{
"epoch": 0.008651766402307137,
"grad_norm": 2.5919249310391024e-05,
"learning_rate": 6e-05,
"loss": 46.0,
"step": 6
},
{
"epoch": 0.010093727469358327,
"grad_norm": 3.103033304796554e-05,
"learning_rate": 7e-05,
"loss": 46.0,
"step": 7
},
{
"epoch": 0.011535688536409516,
"grad_norm": 2.729930383793544e-05,
"learning_rate": 8e-05,
"loss": 46.0,
"step": 8
},
{
"epoch": 0.012977649603460706,
"grad_norm": 2.600135121610947e-05,
"learning_rate": 9e-05,
"loss": 46.0,
"step": 9
},
{
"epoch": 0.014419610670511895,
"grad_norm": 4.012700810562819e-05,
"learning_rate": 0.0001,
"loss": 46.0,
"step": 10
},
{
"epoch": 0.015861571737563085,
"grad_norm": 3.073212428716943e-05,
"learning_rate": 9.999316524962345e-05,
"loss": 46.0,
"step": 11
},
{
"epoch": 0.017303532804614274,
"grad_norm": 5.821282684337348e-05,
"learning_rate": 9.997266286704631e-05,
"loss": 46.0,
"step": 12
},
{
"epoch": 0.018745493871665464,
"grad_norm": 5.5768283345969394e-05,
"learning_rate": 9.993849845741524e-05,
"loss": 46.0,
"step": 13
},
{
"epoch": 0.020187454938716654,
"grad_norm": 6.005035902489908e-05,
"learning_rate": 9.989068136093873e-05,
"loss": 46.0,
"step": 14
},
{
"epoch": 0.021629416005767843,
"grad_norm": 6.563588976860046e-05,
"learning_rate": 9.98292246503335e-05,
"loss": 46.0,
"step": 15
},
{
"epoch": 0.023071377072819033,
"grad_norm": 6.29853384452872e-05,
"learning_rate": 9.975414512725057e-05,
"loss": 46.0,
"step": 16
},
{
"epoch": 0.024513338139870222,
"grad_norm": 9.260119986720383e-05,
"learning_rate": 9.966546331768191e-05,
"loss": 46.0,
"step": 17
},
{
"epoch": 0.02595529920692141,
"grad_norm": 6.250675505725667e-05,
"learning_rate": 9.956320346634876e-05,
"loss": 46.0,
"step": 18
},
{
"epoch": 0.0273972602739726,
"grad_norm": 7.49466780689545e-05,
"learning_rate": 9.944739353007344e-05,
"loss": 46.0,
"step": 19
},
{
"epoch": 0.02883922134102379,
"grad_norm": 5.8534747950034216e-05,
"learning_rate": 9.931806517013612e-05,
"loss": 46.0,
"step": 20
},
{
"epoch": 0.03028118240807498,
"grad_norm": 5.025664358981885e-05,
"learning_rate": 9.917525374361912e-05,
"loss": 46.0,
"step": 21
},
{
"epoch": 0.03172314347512617,
"grad_norm": 3.9194019336719066e-05,
"learning_rate": 9.901899829374047e-05,
"loss": 46.0,
"step": 22
},
{
"epoch": 0.03316510454217736,
"grad_norm": 5.6159224186558276e-05,
"learning_rate": 9.884934153917997e-05,
"loss": 46.0,
"step": 23
},
{
"epoch": 0.03460706560922855,
"grad_norm": 7.44333301554434e-05,
"learning_rate": 9.86663298624003e-05,
"loss": 46.0,
"step": 24
},
{
"epoch": 0.03604902667627974,
"grad_norm": 5.360547220334411e-05,
"learning_rate": 9.847001329696653e-05,
"loss": 46.0,
"step": 25
},
{
"epoch": 0.03749098774333093,
"grad_norm": 6.715447671012953e-05,
"learning_rate": 9.826044551386744e-05,
"loss": 46.0,
"step": 26
},
{
"epoch": 0.03893294881038212,
"grad_norm": 5.926714220549911e-05,
"learning_rate": 9.803768380684242e-05,
"loss": 46.0,
"step": 27
},
{
"epoch": 0.04037490987743331,
"grad_norm": 6.435975956264883e-05,
"learning_rate": 9.780178907671789e-05,
"loss": 46.0,
"step": 28
},
{
"epoch": 0.0418168709444845,
"grad_norm": 5.97175931034144e-05,
"learning_rate": 9.755282581475769e-05,
"loss": 46.0,
"step": 29
},
{
"epoch": 0.043258832011535686,
"grad_norm": 5.983871960779652e-05,
"learning_rate": 9.729086208503174e-05,
"loss": 46.0,
"step": 30
},
{
"epoch": 0.044700793078586876,
"grad_norm": 6.905582995386794e-05,
"learning_rate": 9.701596950580806e-05,
"loss": 46.0,
"step": 31
},
{
"epoch": 0.046142754145638065,
"grad_norm": 8.603069727541879e-05,
"learning_rate": 9.672822322997305e-05,
"loss": 46.0,
"step": 32
},
{
"epoch": 0.047584715212689255,
"grad_norm": 0.00010996026685461402,
"learning_rate": 9.642770192448536e-05,
"loss": 46.0,
"step": 33
},
{
"epoch": 0.049026676279740444,
"grad_norm": 0.00011664038902381435,
"learning_rate": 9.611448774886924e-05,
"loss": 46.0,
"step": 34
},
{
"epoch": 0.050468637346791634,
"grad_norm": 5.231019895290956e-05,
"learning_rate": 9.578866633275288e-05,
"loss": 46.0,
"step": 35
},
{
"epoch": 0.05191059841384282,
"grad_norm": 0.00012090209202142432,
"learning_rate": 9.545032675245813e-05,
"loss": 46.0,
"step": 36
},
{
"epoch": 0.05335255948089401,
"grad_norm": 8.062404958764091e-05,
"learning_rate": 9.509956150664796e-05,
"loss": 46.0,
"step": 37
},
{
"epoch": 0.0547945205479452,
"grad_norm": 9.336588846053928e-05,
"learning_rate": 9.473646649103818e-05,
"loss": 46.0,
"step": 38
},
{
"epoch": 0.05623648161499639,
"grad_norm": 8.884619455784559e-05,
"learning_rate": 9.43611409721806e-05,
"loss": 46.0,
"step": 39
},
{
"epoch": 0.05767844268204758,
"grad_norm": 9.600253542885184e-05,
"learning_rate": 9.397368756032445e-05,
"loss": 46.0,
"step": 40
},
{
"epoch": 0.05912040374909877,
"grad_norm": 0.00015312367759179324,
"learning_rate": 9.357421218136386e-05,
"loss": 46.0,
"step": 41
},
{
"epoch": 0.06056236481614996,
"grad_norm": 8.023295231396332e-05,
"learning_rate": 9.316282404787871e-05,
"loss": 46.0,
"step": 42
},
{
"epoch": 0.06200432588320115,
"grad_norm": 8.562370931031182e-05,
"learning_rate": 9.273963562927695e-05,
"loss": 46.0,
"step": 43
},
{
"epoch": 0.06344628695025234,
"grad_norm": 0.00015367928426712751,
"learning_rate": 9.230476262104677e-05,
"loss": 46.0,
"step": 44
},
{
"epoch": 0.06488824801730353,
"grad_norm": 0.00016452718409709632,
"learning_rate": 9.185832391312644e-05,
"loss": 46.0,
"step": 45
},
{
"epoch": 0.06633020908435472,
"grad_norm": 0.00010999064397765324,
"learning_rate": 9.140044155740101e-05,
"loss": 46.0,
"step": 46
},
{
"epoch": 0.06777217015140591,
"grad_norm": 0.00016317500558216125,
"learning_rate": 9.093124073433463e-05,
"loss": 46.0,
"step": 47
},
{
"epoch": 0.0692141312184571,
"grad_norm": 0.00016825605416670442,
"learning_rate": 9.045084971874738e-05,
"loss": 46.0,
"step": 48
},
{
"epoch": 0.07065609228550829,
"grad_norm": 0.0001684524759184569,
"learning_rate": 8.995939984474624e-05,
"loss": 46.0,
"step": 49
},
{
"epoch": 0.07209805335255948,
"grad_norm": 0.00018130935495719314,
"learning_rate": 8.945702546981969e-05,
"loss": 46.0,
"step": 50
},
{
"epoch": 0.07209805335255948,
"eval_loss": 11.5,
"eval_runtime": 6.5542,
"eval_samples_per_second": 178.358,
"eval_steps_per_second": 44.704,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"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": 10974075420672.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}