16-clusters-balanced-6 / trainer_state.json
MHGanainy's picture
MHGanainy/16-clusters-balanced-6
3ef4aa4 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 2205,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.045351473922902494,
"grad_norm": 0.1351398527622223,
"learning_rate": 6.666666666666667e-06,
"loss": 2.3177,
"step": 100
},
{
"epoch": 0.09070294784580499,
"grad_norm": 0.23727059364318848,
"learning_rate": 1.3333333333333333e-05,
"loss": 2.3049,
"step": 200
},
{
"epoch": 0.1360544217687075,
"grad_norm": 0.30796971917152405,
"learning_rate": 2e-05,
"loss": 2.2541,
"step": 300
},
{
"epoch": 0.18140589569160998,
"grad_norm": 0.3966788351535797,
"learning_rate": 1.98643264153509e-05,
"loss": 2.1959,
"step": 400
},
{
"epoch": 0.22675736961451248,
"grad_norm": 0.4789985418319702,
"learning_rate": 1.9460987125717907e-05,
"loss": 2.1926,
"step": 500
},
{
"epoch": 0.272108843537415,
"grad_norm": 0.535058856010437,
"learning_rate": 1.8800926628551884e-05,
"loss": 2.1152,
"step": 600
},
{
"epoch": 0.31746031746031744,
"grad_norm": 0.567406415939331,
"learning_rate": 1.790205547859999e-05,
"loss": 2.076,
"step": 700
},
{
"epoch": 0.36281179138321995,
"grad_norm": 0.7135646343231201,
"learning_rate": 1.6788764290072554e-05,
"loss": 2.0738,
"step": 800
},
{
"epoch": 0.40816326530612246,
"grad_norm": 0.6722047328948975,
"learning_rate": 1.549126190423073e-05,
"loss": 2.054,
"step": 900
},
{
"epoch": 0.45351473922902497,
"grad_norm": 0.8051442503929138,
"learning_rate": 1.4044755681030094e-05,
"loss": 2.0124,
"step": 1000
},
{
"epoch": 0.4988662131519274,
"grad_norm": 0.6087419390678406,
"learning_rate": 1.2488496157374425e-05,
"loss": 2.0051,
"step": 1100
},
{
"epoch": 0.54421768707483,
"grad_norm": 0.8336877226829529,
"learning_rate": 1.0864711994907457e-05,
"loss": 1.9954,
"step": 1200
},
{
"epoch": 0.5895691609977324,
"grad_norm": 0.6950428485870361,
"learning_rate": 9.217464117232859e-06,
"loss": 2.0539,
"step": 1300
},
{
"epoch": 0.6349206349206349,
"grad_norm": 0.6528784036636353,
"learning_rate": 7.591450129224569e-06,
"loss": 2.0042,
"step": 1400
},
{
"epoch": 0.6802721088435374,
"grad_norm": 1.0925904512405396,
"learning_rate": 6.03079146017113e-06,
"loss": 2.0167,
"step": 1500
},
{
"epoch": 0.7256235827664399,
"grad_norm": 0.7688515186309814,
"learning_rate": 4.577836141281368e-06,
"loss": 1.9946,
"step": 1600
},
{
"epoch": 0.7709750566893424,
"grad_norm": 1.1727160215377808,
"learning_rate": 3.2720097038450394e-06,
"loss": 1.9847,
"step": 1700
},
{
"epoch": 0.8163265306122449,
"grad_norm": 0.8815014362335205,
"learning_rate": 2.1487453786014513e-06,
"loss": 1.9598,
"step": 1800
},
{
"epoch": 0.8616780045351474,
"grad_norm": 0.8077797889709473,
"learning_rate": 1.2385226250534566e-06,
"loss": 1.9814,
"step": 1900
},
{
"epoch": 0.9070294784580499,
"grad_norm": 1.262542963027954,
"learning_rate": 5.660400799616572e-07,
"loss": 1.9466,
"step": 2000
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.8123142123222351,
"learning_rate": 1.495453668273672e-07,
"loss": 1.9335,
"step": 2100
},
{
"epoch": 0.9977324263038548,
"grad_norm": 0.8020434379577637,
"learning_rate": 3.399517942515029e-10,
"loss": 1.9826,
"step": 2200
},
{
"epoch": 1.0,
"step": 2205,
"total_flos": 4.00628735213568e+16,
"train_loss": 2.065633855547224,
"train_runtime": 693.7957,
"train_samples_per_second": 6.355,
"train_steps_per_second": 3.178
}
],
"logging_steps": 100,
"max_steps": 2205,
"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": 4.00628735213568e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}