prxy5607's picture
Training in progress, step 50, checkpoint
65594b4 verified
raw
history blame
10 kB
{
"best_metric": 2.82340669631958,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.0030028677386904493,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 6.005735477380899e-05,
"grad_norm": 0.7277234792709351,
"learning_rate": 1e-05,
"loss": 1.3234,
"step": 1
},
{
"epoch": 6.005735477380899e-05,
"eval_loss": 3.1906468868255615,
"eval_runtime": 2134.556,
"eval_samples_per_second": 13.138,
"eval_steps_per_second": 3.285,
"step": 1
},
{
"epoch": 0.00012011470954761798,
"grad_norm": 0.8249174952507019,
"learning_rate": 2e-05,
"loss": 1.4146,
"step": 2
},
{
"epoch": 0.00018017206432142696,
"grad_norm": 0.8658198118209839,
"learning_rate": 3e-05,
"loss": 1.5297,
"step": 3
},
{
"epoch": 0.00024022941909523595,
"grad_norm": 0.9398988485336304,
"learning_rate": 4e-05,
"loss": 1.6596,
"step": 4
},
{
"epoch": 0.00030028677386904494,
"grad_norm": 0.823463499546051,
"learning_rate": 5e-05,
"loss": 1.6762,
"step": 5
},
{
"epoch": 0.00036034412864285393,
"grad_norm": 0.7399727702140808,
"learning_rate": 6e-05,
"loss": 1.6846,
"step": 6
},
{
"epoch": 0.0004204014834166629,
"grad_norm": 0.9010226726531982,
"learning_rate": 7e-05,
"loss": 1.644,
"step": 7
},
{
"epoch": 0.0004804588381904719,
"grad_norm": 0.9326359629631042,
"learning_rate": 8e-05,
"loss": 1.5877,
"step": 8
},
{
"epoch": 0.0005405161929642808,
"grad_norm": 0.977419912815094,
"learning_rate": 9e-05,
"loss": 1.7177,
"step": 9
},
{
"epoch": 0.0006005735477380899,
"grad_norm": 0.6996713876724243,
"learning_rate": 0.0001,
"loss": 1.4415,
"step": 10
},
{
"epoch": 0.0006606309025118988,
"grad_norm": 0.7411949634552002,
"learning_rate": 9.999316524962345e-05,
"loss": 1.5325,
"step": 11
},
{
"epoch": 0.0007206882572857079,
"grad_norm": 0.8528963327407837,
"learning_rate": 9.997266286704631e-05,
"loss": 1.4692,
"step": 12
},
{
"epoch": 0.0007807456120595168,
"grad_norm": 0.8318995237350464,
"learning_rate": 9.993849845741524e-05,
"loss": 1.6418,
"step": 13
},
{
"epoch": 0.0008408029668333258,
"grad_norm": 0.7479487061500549,
"learning_rate": 9.989068136093873e-05,
"loss": 1.7038,
"step": 14
},
{
"epoch": 0.0009008603216071348,
"grad_norm": 0.7285621166229248,
"learning_rate": 9.98292246503335e-05,
"loss": 1.4805,
"step": 15
},
{
"epoch": 0.0009609176763809438,
"grad_norm": 0.7259240746498108,
"learning_rate": 9.975414512725057e-05,
"loss": 1.6445,
"step": 16
},
{
"epoch": 0.0010209750311547527,
"grad_norm": 0.7934219837188721,
"learning_rate": 9.966546331768191e-05,
"loss": 1.367,
"step": 17
},
{
"epoch": 0.0010810323859285617,
"grad_norm": 0.8407491445541382,
"learning_rate": 9.956320346634876e-05,
"loss": 1.4958,
"step": 18
},
{
"epoch": 0.0011410897407023708,
"grad_norm": 0.9245749115943909,
"learning_rate": 9.944739353007344e-05,
"loss": 1.6083,
"step": 19
},
{
"epoch": 0.0012011470954761798,
"grad_norm": 0.8109903931617737,
"learning_rate": 9.931806517013612e-05,
"loss": 1.5333,
"step": 20
},
{
"epoch": 0.0012612044502499887,
"grad_norm": 1.2378709316253662,
"learning_rate": 9.917525374361912e-05,
"loss": 1.6405,
"step": 21
},
{
"epoch": 0.0013212618050237976,
"grad_norm": 1.558487057685852,
"learning_rate": 9.901899829374047e-05,
"loss": 1.5916,
"step": 22
},
{
"epoch": 0.0013813191597976068,
"grad_norm": 0.9527750015258789,
"learning_rate": 9.884934153917997e-05,
"loss": 1.593,
"step": 23
},
{
"epoch": 0.0014413765145714157,
"grad_norm": 1.060105562210083,
"learning_rate": 9.86663298624003e-05,
"loss": 1.7384,
"step": 24
},
{
"epoch": 0.0015014338693452246,
"grad_norm": 1.1204156875610352,
"learning_rate": 9.847001329696653e-05,
"loss": 1.9215,
"step": 25
},
{
"epoch": 0.0015614912241190336,
"grad_norm": 1.1645809412002563,
"learning_rate": 9.826044551386744e-05,
"loss": 1.8122,
"step": 26
},
{
"epoch": 0.0016215485788928427,
"grad_norm": 1.0866835117340088,
"learning_rate": 9.803768380684242e-05,
"loss": 1.8427,
"step": 27
},
{
"epoch": 0.0016816059336666517,
"grad_norm": 1.4639962911605835,
"learning_rate": 9.780178907671789e-05,
"loss": 1.7834,
"step": 28
},
{
"epoch": 0.0017416632884404606,
"grad_norm": 1.2034151554107666,
"learning_rate": 9.755282581475769e-05,
"loss": 1.7954,
"step": 29
},
{
"epoch": 0.0018017206432142695,
"grad_norm": 1.3376408815383911,
"learning_rate": 9.729086208503174e-05,
"loss": 1.8065,
"step": 30
},
{
"epoch": 0.0018617779979880787,
"grad_norm": 1.7506548166275024,
"learning_rate": 9.701596950580806e-05,
"loss": 2.0368,
"step": 31
},
{
"epoch": 0.0019218353527618876,
"grad_norm": 1.909898042678833,
"learning_rate": 9.672822322997305e-05,
"loss": 1.766,
"step": 32
},
{
"epoch": 0.0019818927075356966,
"grad_norm": 1.9195573329925537,
"learning_rate": 9.642770192448536e-05,
"loss": 2.0777,
"step": 33
},
{
"epoch": 0.0020419500623095055,
"grad_norm": 1.7940828800201416,
"learning_rate": 9.611448774886924e-05,
"loss": 2.2604,
"step": 34
},
{
"epoch": 0.0021020074170833144,
"grad_norm": 2.1280953884124756,
"learning_rate": 9.578866633275288e-05,
"loss": 2.3557,
"step": 35
},
{
"epoch": 0.0021620647718571234,
"grad_norm": 2.3466970920562744,
"learning_rate": 9.545032675245813e-05,
"loss": 2.6686,
"step": 36
},
{
"epoch": 0.0022221221266309327,
"grad_norm": 2.250682830810547,
"learning_rate": 9.509956150664796e-05,
"loss": 2.7733,
"step": 37
},
{
"epoch": 0.0022821794814047417,
"grad_norm": 2.6434786319732666,
"learning_rate": 9.473646649103818e-05,
"loss": 3.0848,
"step": 38
},
{
"epoch": 0.0023422368361785506,
"grad_norm": 4.73193359375,
"learning_rate": 9.43611409721806e-05,
"loss": 3.0783,
"step": 39
},
{
"epoch": 0.0024022941909523595,
"grad_norm": 3.889577865600586,
"learning_rate": 9.397368756032445e-05,
"loss": 3.4497,
"step": 40
},
{
"epoch": 0.0024623515457261685,
"grad_norm": 4.585144996643066,
"learning_rate": 9.357421218136386e-05,
"loss": 3.6834,
"step": 41
},
{
"epoch": 0.0025224089004999774,
"grad_norm": 5.334516525268555,
"learning_rate": 9.316282404787871e-05,
"loss": 3.5614,
"step": 42
},
{
"epoch": 0.0025824662552737863,
"grad_norm": 6.08420467376709,
"learning_rate": 9.273963562927695e-05,
"loss": 4.0365,
"step": 43
},
{
"epoch": 0.0026425236100475953,
"grad_norm": 6.18115234375,
"learning_rate": 9.230476262104677e-05,
"loss": 3.5424,
"step": 44
},
{
"epoch": 0.0027025809648214046,
"grad_norm": 9.245948791503906,
"learning_rate": 9.185832391312644e-05,
"loss": 4.1178,
"step": 45
},
{
"epoch": 0.0027626383195952136,
"grad_norm": 5.46101713180542,
"learning_rate": 9.140044155740101e-05,
"loss": 3.632,
"step": 46
},
{
"epoch": 0.0028226956743690225,
"grad_norm": 10.615842819213867,
"learning_rate": 9.093124073433463e-05,
"loss": 4.2407,
"step": 47
},
{
"epoch": 0.0028827530291428314,
"grad_norm": 22.699947357177734,
"learning_rate": 9.045084971874738e-05,
"loss": 4.6777,
"step": 48
},
{
"epoch": 0.0029428103839166404,
"grad_norm": 25.06355094909668,
"learning_rate": 8.995939984474624e-05,
"loss": 4.5389,
"step": 49
},
{
"epoch": 0.0030028677386904493,
"grad_norm": 17.44358253479004,
"learning_rate": 8.945702546981969e-05,
"loss": 4.6876,
"step": 50
},
{
"epoch": 0.0030028677386904493,
"eval_loss": 2.82340669631958,
"eval_runtime": 2140.029,
"eval_samples_per_second": 13.104,
"eval_steps_per_second": 3.276,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 200,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 50,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 5,
"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": 7.580280733197926e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}