vdos's picture
Training in progress, step 25, checkpoint
e6c95d4 verified
raw
history blame
5.75 kB
{
"best_metric": 0.6936268210411072,
"best_model_checkpoint": "miner_id_24/checkpoint-25",
"epoch": 0.0672834314550042,
"eval_steps": 25,
"global_step": 25,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002691337258200168,
"grad_norm": 0.24618549644947052,
"learning_rate": 5e-05,
"loss": 0.8201,
"step": 1
},
{
"epoch": 0.002691337258200168,
"eval_loss": 0.967555820941925,
"eval_runtime": 27.9138,
"eval_samples_per_second": 89.705,
"eval_steps_per_second": 11.213,
"step": 1
},
{
"epoch": 0.005382674516400336,
"grad_norm": 0.3328123986721039,
"learning_rate": 0.0001,
"loss": 0.9103,
"step": 2
},
{
"epoch": 0.008074011774600504,
"grad_norm": 0.3257139325141907,
"learning_rate": 9.989294616193017e-05,
"loss": 0.9334,
"step": 3
},
{
"epoch": 0.010765349032800672,
"grad_norm": 0.31773149967193604,
"learning_rate": 9.957224306869053e-05,
"loss": 0.9161,
"step": 4
},
{
"epoch": 0.01345668629100084,
"grad_norm": 0.2870025932788849,
"learning_rate": 9.903926402016153e-05,
"loss": 0.8216,
"step": 5
},
{
"epoch": 0.01614802354920101,
"grad_norm": 0.25279363989830017,
"learning_rate": 9.829629131445342e-05,
"loss": 0.8332,
"step": 6
},
{
"epoch": 0.018839360807401177,
"grad_norm": 0.22127391397953033,
"learning_rate": 9.73465064747553e-05,
"loss": 0.7612,
"step": 7
},
{
"epoch": 0.021530698065601345,
"grad_norm": 0.22589439153671265,
"learning_rate": 9.619397662556435e-05,
"loss": 0.7762,
"step": 8
},
{
"epoch": 0.024222035323801513,
"grad_norm": 0.31412026286125183,
"learning_rate": 9.484363707663442e-05,
"loss": 0.8023,
"step": 9
},
{
"epoch": 0.02691337258200168,
"grad_norm": 0.3089049458503723,
"learning_rate": 9.330127018922194e-05,
"loss": 0.8087,
"step": 10
},
{
"epoch": 0.02960470984020185,
"grad_norm": 0.27815794944763184,
"learning_rate": 9.157348061512727e-05,
"loss": 0.7659,
"step": 11
},
{
"epoch": 0.03229604709840202,
"grad_norm": 0.23500941693782806,
"learning_rate": 8.966766701456177e-05,
"loss": 0.7398,
"step": 12
},
{
"epoch": 0.03498738435660219,
"grad_norm": 0.17115627229213715,
"learning_rate": 8.759199037394887e-05,
"loss": 0.6447,
"step": 13
},
{
"epoch": 0.03767872161480235,
"grad_norm": 0.1679994761943817,
"learning_rate": 8.535533905932738e-05,
"loss": 0.7151,
"step": 14
},
{
"epoch": 0.040370058873002525,
"grad_norm": 0.14659446477890015,
"learning_rate": 8.296729075500344e-05,
"loss": 0.7589,
"step": 15
},
{
"epoch": 0.04306139613120269,
"grad_norm": 0.14974281191825867,
"learning_rate": 8.043807145043604e-05,
"loss": 0.741,
"step": 16
},
{
"epoch": 0.04575273338940286,
"grad_norm": 0.14918231964111328,
"learning_rate": 7.777851165098012e-05,
"loss": 0.7215,
"step": 17
},
{
"epoch": 0.048444070647603026,
"grad_norm": 0.15710848569869995,
"learning_rate": 7.500000000000001e-05,
"loss": 0.722,
"step": 18
},
{
"epoch": 0.0511354079058032,
"grad_norm": 0.16022801399230957,
"learning_rate": 7.211443451095007e-05,
"loss": 0.7571,
"step": 19
},
{
"epoch": 0.05382674516400336,
"grad_norm": 0.16629311442375183,
"learning_rate": 6.91341716182545e-05,
"loss": 0.7019,
"step": 20
},
{
"epoch": 0.05651808242220353,
"grad_norm": 0.15958215296268463,
"learning_rate": 6.607197326515808e-05,
"loss": 0.7156,
"step": 21
},
{
"epoch": 0.0592094196804037,
"grad_norm": 0.16728022694587708,
"learning_rate": 6.294095225512603e-05,
"loss": 0.7175,
"step": 22
},
{
"epoch": 0.06190075693860387,
"grad_norm": 0.16817450523376465,
"learning_rate": 5.9754516100806423e-05,
"loss": 0.7395,
"step": 23
},
{
"epoch": 0.06459209419680403,
"grad_norm": 0.17274682223796844,
"learning_rate": 5.6526309611002594e-05,
"loss": 0.6979,
"step": 24
},
{
"epoch": 0.0672834314550042,
"grad_norm": 0.184087336063385,
"learning_rate": 5.327015646150716e-05,
"loss": 0.6764,
"step": 25
},
{
"epoch": 0.0672834314550042,
"eval_loss": 0.6936268210411072,
"eval_runtime": 27.1022,
"eval_samples_per_second": 92.391,
"eval_steps_per_second": 11.549,
"step": 25
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": 5.227878001357619e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}