qwen_3b_math / trainer_state.json
dulguun222's picture
Upload folder using huggingface_hub
c7eaccc verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.9760765550239237,
"eval_steps": 500,
"global_step": 312,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.09569377990430622,
"grad_norm": 4.315772756794048,
"learning_rate": 3.125e-06,
"loss": 0.4212,
"step": 10
},
{
"epoch": 0.19138755980861244,
"grad_norm": 3.3227666892135432,
"learning_rate": 6.25e-06,
"loss": 0.4736,
"step": 20
},
{
"epoch": 0.28708133971291866,
"grad_norm": 7.502806440154027,
"learning_rate": 9.375000000000001e-06,
"loss": 0.4117,
"step": 30
},
{
"epoch": 0.3827751196172249,
"grad_norm": 4.812933618699202,
"learning_rate": 9.979871469976197e-06,
"loss": 0.3306,
"step": 40
},
{
"epoch": 0.4784688995215311,
"grad_norm": 5.113380763093044,
"learning_rate": 9.898376992116179e-06,
"loss": 0.3924,
"step": 50
},
{
"epoch": 0.5741626794258373,
"grad_norm": 5.2850983406475915,
"learning_rate": 9.755282581475769e-06,
"loss": 0.4365,
"step": 60
},
{
"epoch": 0.6698564593301436,
"grad_norm": 5.364137037341764,
"learning_rate": 9.552387733294081e-06,
"loss": 0.3638,
"step": 70
},
{
"epoch": 0.7655502392344498,
"grad_norm": 4.0260153866397355,
"learning_rate": 9.292243968009332e-06,
"loss": 0.5465,
"step": 80
},
{
"epoch": 0.861244019138756,
"grad_norm": 3.8837148354409137,
"learning_rate": 8.978122744408905e-06,
"loss": 0.4152,
"step": 90
},
{
"epoch": 0.9569377990430622,
"grad_norm": 3.207603400930971,
"learning_rate": 8.613974319136959e-06,
"loss": 0.406,
"step": 100
},
{
"epoch": 1.0478468899521531,
"grad_norm": 3.081310895258368,
"learning_rate": 8.204378069925121e-06,
"loss": 0.273,
"step": 110
},
{
"epoch": 1.1435406698564594,
"grad_norm": 6.305626396570556,
"learning_rate": 7.754484907260513e-06,
"loss": 0.2318,
"step": 120
},
{
"epoch": 1.2392344497607655,
"grad_norm": 5.149450095126118,
"learning_rate": 7.269952498697734e-06,
"loss": 0.2031,
"step": 130
},
{
"epoch": 1.3349282296650717,
"grad_norm": 3.597480792122046,
"learning_rate": 6.7568741204067145e-06,
"loss": 0.1868,
"step": 140
},
{
"epoch": 1.430622009569378,
"grad_norm": 3.7719825769304873,
"learning_rate": 6.2217020306894705e-06,
"loss": 0.2089,
"step": 150
},
{
"epoch": 1.526315789473684,
"grad_norm": 6.079710603280231,
"learning_rate": 5.671166329088278e-06,
"loss": 0.2477,
"step": 160
},
{
"epoch": 1.6220095693779903,
"grad_norm": 2.5888279440746964,
"learning_rate": 5.112190321479026e-06,
"loss": 0.1991,
"step": 170
},
{
"epoch": 1.7177033492822966,
"grad_norm": 3.9779920431632423,
"learning_rate": 4.551803455482833e-06,
"loss": 0.1879,
"step": 180
},
{
"epoch": 1.813397129186603,
"grad_norm": 2.5621003966734115,
"learning_rate": 3.997052921083637e-06,
"loss": 0.1741,
"step": 190
},
{
"epoch": 1.9090909090909092,
"grad_norm": 4.103803645019158,
"learning_rate": 3.4549150281252635e-06,
"loss": 0.2304,
"step": 200
},
{
"epoch": 2.0,
"grad_norm": 10.76835936227807,
"learning_rate": 2.932207475167398e-06,
"loss": 0.1943,
"step": 210
},
{
"epoch": 2.0956937799043063,
"grad_norm": 3.1049956168395,
"learning_rate": 2.43550361297047e-06,
"loss": 0.0971,
"step": 220
},
{
"epoch": 2.1913875598086126,
"grad_norm": 1.8626051426196015,
"learning_rate": 1.971049780795901e-06,
"loss": 0.0747,
"step": 230
},
{
"epoch": 2.287081339712919,
"grad_norm": 2.2249948115867717,
"learning_rate": 1.544686755065677e-06,
"loss": 0.0828,
"step": 240
},
{
"epoch": 2.382775119617225,
"grad_norm": 3.645465893241635,
"learning_rate": 1.1617762982099446e-06,
"loss": 0.0859,
"step": 250
},
{
"epoch": 2.478468899521531,
"grad_norm": 4.11800452730375,
"learning_rate": 8.271337313934869e-07,
"loss": 0.0715,
"step": 260
},
{
"epoch": 2.574162679425837,
"grad_norm": 2.0043986949135855,
"learning_rate": 5.449673790581611e-07,
"loss": 0.095,
"step": 270
},
{
"epoch": 2.6698564593301435,
"grad_norm": 3.2194517540717276,
"learning_rate": 3.18825646801314e-07,
"loss": 0.1088,
"step": 280
},
{
"epoch": 2.7655502392344498,
"grad_norm": 5.7653256964411055,
"learning_rate": 1.5155239811656562e-07,
"loss": 0.0886,
"step": 290
},
{
"epoch": 2.861244019138756,
"grad_norm": 4.725414597201169,
"learning_rate": 4.52511911603265e-08,
"loss": 0.0909,
"step": 300
},
{
"epoch": 2.9569377990430623,
"grad_norm": 2.4916384390306168,
"learning_rate": 1.2588252874673469e-09,
"loss": 0.0912,
"step": 310
},
{
"epoch": 2.9760765550239237,
"step": 312,
"total_flos": 1915811659776.0,
"train_loss": 0.23802761278616694,
"train_runtime": 1918.6836,
"train_samples_per_second": 0.98,
"train_steps_per_second": 0.163
}
],
"logging_steps": 10,
"max_steps": 312,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 50000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1915811659776.0,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}