gr00t-bread1.3-vn21cjph2k / trainer_state.json
LegrandFrederic's picture
Upload trainer_state.json with huggingface_hub
a8a1e63 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 10.0,
"eval_steps": 500,
"global_step": 310,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.3225806451612903,
"grad_norm": 3.328359365463257,
"learning_rate": 5.6250000000000005e-05,
"loss": 0.9235,
"step": 10
},
{
"epoch": 0.6451612903225806,
"grad_norm": 2.2712912559509277,
"learning_rate": 9.99743108100344e-05,
"loss": 0.4254,
"step": 20
},
{
"epoch": 0.967741935483871,
"grad_norm": 2.140098810195923,
"learning_rate": 9.951834807474191e-05,
"loss": 0.4047,
"step": 30
},
{
"epoch": 1.2903225806451613,
"grad_norm": 1.2997124195098877,
"learning_rate": 9.849750306392084e-05,
"loss": 0.3476,
"step": 40
},
{
"epoch": 1.6129032258064515,
"grad_norm": 3.400588035583496,
"learning_rate": 9.692342110248802e-05,
"loss": 0.2967,
"step": 50
},
{
"epoch": 1.935483870967742,
"grad_norm": 1.3774495124816895,
"learning_rate": 9.481405858508934e-05,
"loss": 0.2498,
"step": 60
},
{
"epoch": 2.258064516129032,
"grad_norm": 1.2473772764205933,
"learning_rate": 9.219347813790416e-05,
"loss": 0.2292,
"step": 70
},
{
"epoch": 2.5806451612903225,
"grad_norm": 1.2545992136001587,
"learning_rate": 8.90915741234015e-05,
"loss": 0.2082,
"step": 80
},
{
"epoch": 2.903225806451613,
"grad_norm": 1.395470380783081,
"learning_rate": 8.554373161936175e-05,
"loss": 0.1895,
"step": 90
},
{
"epoch": 3.225806451612903,
"grad_norm": 1.594893217086792,
"learning_rate": 8.159042276237308e-05,
"loss": 0.1805,
"step": 100
},
{
"epoch": 3.5483870967741935,
"grad_norm": 1.370707392692566,
"learning_rate": 7.727674506052743e-05,
"loss": 0.1647,
"step": 110
},
{
"epoch": 3.870967741935484,
"grad_norm": 0.9895046949386597,
"learning_rate": 7.265190694203085e-05,
"loss": 0.1661,
"step": 120
},
{
"epoch": 4.193548387096774,
"grad_norm": 1.249048113822937,
"learning_rate": 6.776866640834945e-05,
"loss": 0.1488,
"step": 130
},
{
"epoch": 4.516129032258064,
"grad_norm": 1.0707579851150513,
"learning_rate": 6.268272919547537e-05,
"loss": 0.1582,
"step": 140
},
{
"epoch": 4.838709677419355,
"grad_norm": 0.9851087927818298,
"learning_rate": 5.745211330880872e-05,
"loss": 0.1414,
"step": 150
},
{
"epoch": 5.161290322580645,
"grad_norm": 1.1160937547683716,
"learning_rate": 5.213648718074584e-05,
"loss": 0.1393,
"step": 160
},
{
"epoch": 5.483870967741936,
"grad_norm": 0.9369606375694275,
"learning_rate": 4.679648900096436e-05,
"loss": 0.1104,
"step": 170
},
{
"epoch": 5.806451612903226,
"grad_norm": 0.5889655351638794,
"learning_rate": 4.149303498416838e-05,
"loss": 0.1325,
"step": 180
},
{
"epoch": 6.129032258064516,
"grad_norm": 0.9057347178459167,
"learning_rate": 3.628662446625349e-05,
"loss": 0.1321,
"step": 190
},
{
"epoch": 6.451612903225806,
"grad_norm": 0.6751521825790405,
"learning_rate": 3.12366497560313e-05,
"loss": 0.1311,
"step": 200
},
{
"epoch": 6.774193548387097,
"grad_norm": 0.5785370469093323,
"learning_rate": 2.640071861540385e-05,
"loss": 0.1139,
"step": 210
},
{
"epoch": 7.096774193548387,
"grad_norm": 1.005380392074585,
"learning_rate": 2.1833997096818898e-05,
"loss": 0.098,
"step": 220
},
{
"epoch": 7.419354838709677,
"grad_norm": 0.675995409488678,
"learning_rate": 1.758858023461059e-05,
"loss": 0.115,
"step": 230
},
{
"epoch": 7.741935483870968,
"grad_norm": 0.8063868880271912,
"learning_rate": 1.3712897769085903e-05,
"loss": 0.1036,
"step": 240
},
{
"epoch": 8.064516129032258,
"grad_norm": 0.525888204574585,
"learning_rate": 1.0251161682580124e-05,
"loss": 0.0913,
"step": 250
},
{
"epoch": 8.387096774193548,
"grad_norm": 0.769961953163147,
"learning_rate": 7.242861849732696e-06,
"loss": 0.0914,
"step": 260
},
{
"epoch": 8.709677419354838,
"grad_norm": 0.5272254347801208,
"learning_rate": 4.722315555370793e-06,
"loss": 0.1056,
"step": 270
},
{
"epoch": 9.03225806451613,
"grad_norm": 0.6528829336166382,
"learning_rate": 2.71827601889067e-06,
"loss": 0.0911,
"step": 280
},
{
"epoch": 9.35483870967742,
"grad_norm": 0.526793360710144,
"learning_rate": 1.2536043909088191e-06,
"loss": 0.1033,
"step": 290
},
{
"epoch": 9.67741935483871,
"grad_norm": 0.614827036857605,
"learning_rate": 3.4500896389227376e-07,
"loss": 0.0926,
"step": 300
},
{
"epoch": 10.0,
"grad_norm": 1.0483782291412354,
"learning_rate": 2.854571731947253e-09,
"loss": 0.1098,
"step": 310
},
{
"epoch": 10.0,
"step": 310,
"total_flos": 0.0,
"train_loss": 0.1933982212697306,
"train_runtime": 344.2047,
"train_samples_per_second": 43.782,
"train_steps_per_second": 0.901
}
],
"logging_steps": 10,
"max_steps": 310,
"num_input_tokens_seen": 0,
"num_train_epochs": 10,
"save_steps": 3000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 0.0,
"train_batch_size": 49,
"trial_name": null,
"trial_params": null
}