Uranium2 / trainer_state.json
manbeast3b's picture
Upload model
382b66f verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.12358882947118241,
"eval_steps": 62,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0030897207367795603,
"grad_norm": 4588.7900390625,
"learning_rate": 4.0000000000000004e-11,
"loss": 11.1378,
"step": 1
},
{
"epoch": 0.006179441473559121,
"grad_norm": 4484.97314453125,
"learning_rate": 8.000000000000001e-11,
"loss": 11.1465,
"step": 2
},
{
"epoch": 0.009269162210338681,
"grad_norm": 4465.8408203125,
"learning_rate": 1.2e-10,
"loss": 11.0439,
"step": 3
},
{
"epoch": 0.012358882947118241,
"grad_norm": 4807.01171875,
"learning_rate": 1.6000000000000002e-10,
"loss": 11.3464,
"step": 4
},
{
"epoch": 0.015448603683897801,
"grad_norm": 4590.3369140625,
"learning_rate": 2e-10,
"loss": 11.0523,
"step": 5
},
{
"epoch": 0.018538324420677363,
"grad_norm": 4261.99658203125,
"learning_rate": 1.9984815164333162e-10,
"loss": 10.9142,
"step": 6
},
{
"epoch": 0.02162804515745692,
"grad_norm": 4459.41455078125,
"learning_rate": 1.9939306773179497e-10,
"loss": 11.0083,
"step": 7
},
{
"epoch": 0.024717765894236483,
"grad_norm": 4372.3876953125,
"learning_rate": 1.9863613034027225e-10,
"loss": 10.9957,
"step": 8
},
{
"epoch": 0.027807486631016044,
"grad_norm": 4308.26953125,
"learning_rate": 1.9757963826274357e-10,
"loss": 10.9736,
"step": 9
},
{
"epoch": 0.030897207367795602,
"grad_norm": 3821.595458984375,
"learning_rate": 1.9622680003092504e-10,
"loss": 10.4572,
"step": 10
},
{
"epoch": 0.03398692810457516,
"grad_norm": 4184.8388671875,
"learning_rate": 1.9458172417006345e-10,
"loss": 10.7733,
"step": 11
},
{
"epoch": 0.037076648841354726,
"grad_norm": 4909.9609375,
"learning_rate": 1.9264940672148017e-10,
"loss": 11.6039,
"step": 12
},
{
"epoch": 0.040166369578134284,
"grad_norm": 4097.865234375,
"learning_rate": 1.9043571606975777e-10,
"loss": 10.7497,
"step": 13
},
{
"epoch": 0.04325609031491384,
"grad_norm": 4388.50244140625,
"learning_rate": 1.879473751206489e-10,
"loss": 10.8997,
"step": 14
},
{
"epoch": 0.04634581105169341,
"grad_norm": 4527.54150390625,
"learning_rate": 1.851919408838327e-10,
"loss": 11.0818,
"step": 15
},
{
"epoch": 0.049435531788472965,
"grad_norm": 4139.16552734375,
"learning_rate": 1.821777815225245e-10,
"loss": 10.6874,
"step": 16
},
{
"epoch": 0.052525252525252523,
"grad_norm": 4184.986328125,
"learning_rate": 1.7891405093963936e-10,
"loss": 10.6914,
"step": 17
},
{
"epoch": 0.05561497326203209,
"grad_norm": 4698.89599609375,
"learning_rate": 1.7541066097768963e-10,
"loss": 11.3234,
"step": 18
},
{
"epoch": 0.05870469399881165,
"grad_norm": 4441.7099609375,
"learning_rate": 1.7167825131684515e-10,
"loss": 11.0614,
"step": 19
},
{
"epoch": 0.061794414735591205,
"grad_norm": 4341.03955078125,
"learning_rate": 1.6772815716257412e-10,
"loss": 10.9571,
"step": 20
},
{
"epoch": 0.06488413547237076,
"grad_norm": 4568.626953125,
"learning_rate": 1.6357237482099684e-10,
"loss": 11.1655,
"step": 21
},
{
"epoch": 0.06797385620915032,
"grad_norm": 4392.01953125,
"learning_rate": 1.59223525266498e-10,
"loss": 11.0342,
"step": 22
},
{
"epoch": 0.0710635769459299,
"grad_norm": 4315.537109375,
"learning_rate": 1.5469481581224272e-10,
"loss": 11.0743,
"step": 23
},
{
"epoch": 0.07415329768270945,
"grad_norm": 4450.1845703125,
"learning_rate": 1.5e-10,
"loss": 10.9424,
"step": 24
},
{
"epoch": 0.07724301841948901,
"grad_norm": 4252.31982421875,
"learning_rate": 1.4515333583108894e-10,
"loss": 10.8202,
"step": 25
},
{
"epoch": 0.08033273915626857,
"grad_norm": 4481.5,
"learning_rate": 1.4016954246529695e-10,
"loss": 11.0462,
"step": 26
},
{
"epoch": 0.08342245989304813,
"grad_norm": 4287.03515625,
"learning_rate": 1.3506375551927545e-10,
"loss": 11.0053,
"step": 27
},
{
"epoch": 0.08651218062982768,
"grad_norm": 4513.53662109375,
"learning_rate": 1.2985148110016947e-10,
"loss": 11.1842,
"step": 28
},
{
"epoch": 0.08960190136660724,
"grad_norm": 4208.63330078125,
"learning_rate": 1.2454854871407994e-10,
"loss": 10.9974,
"step": 29
},
{
"epoch": 0.09269162210338681,
"grad_norm": 4587.828125,
"learning_rate": 1.1917106319237384e-10,
"loss": 11.3144,
"step": 30
},
{
"epoch": 0.09578134284016637,
"grad_norm": 4346.50341796875,
"learning_rate": 1.1373535578184083e-10,
"loss": 11.0087,
"step": 31
},
{
"epoch": 0.09887106357694593,
"grad_norm": 4239.73974609375,
"learning_rate": 1.0825793454723326e-10,
"loss": 10.8437,
"step": 32
},
{
"epoch": 0.10196078431372549,
"grad_norm": 4778.1728515625,
"learning_rate": 1.0275543423681622e-10,
"loss": 11.3694,
"step": 33
},
{
"epoch": 0.10505050505050505,
"grad_norm": 4481.9033203125,
"learning_rate": 9.724456576318382e-11,
"loss": 11.1087,
"step": 34
},
{
"epoch": 0.1081402257872846,
"grad_norm": 4602.31005859375,
"learning_rate": 9.174206545276678e-11,
"loss": 11.3214,
"step": 35
},
{
"epoch": 0.11122994652406418,
"grad_norm": 4783.39501953125,
"learning_rate": 8.626464421815918e-11,
"loss": 11.2677,
"step": 36
},
{
"epoch": 0.11431966726084374,
"grad_norm": 4314.626953125,
"learning_rate": 8.082893680762619e-11,
"loss": 10.9266,
"step": 37
},
{
"epoch": 0.1174093879976233,
"grad_norm": 4121.65478515625,
"learning_rate": 7.54514512859201e-11,
"loss": 10.7766,
"step": 38
},
{
"epoch": 0.12049910873440285,
"grad_norm": 4387.51318359375,
"learning_rate": 7.014851889983058e-11,
"loss": 11.1114,
"step": 39
},
{
"epoch": 0.12358882947118241,
"grad_norm": 4680.94140625,
"learning_rate": 6.493624448072457e-11,
"loss": 11.3017,
"step": 40
}
],
"logging_steps": 1,
"max_steps": 62,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 10,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 6.637517228998656e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}