prxy5606's picture
Training in progress, step 50, checkpoint
677c8fc verified
raw
history blame
9.99 kB
{
"best_metric": 0.04590430483222008,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.004492564805247316,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 8.985129610494631e-05,
"grad_norm": 2.388788938522339,
"learning_rate": 1e-05,
"loss": 1.5408,
"step": 1
},
{
"epoch": 8.985129610494631e-05,
"eval_loss": 1.4799306392669678,
"eval_runtime": 901.4276,
"eval_samples_per_second": 20.795,
"eval_steps_per_second": 5.2,
"step": 1
},
{
"epoch": 0.00017970259220989262,
"grad_norm": 2.8213908672332764,
"learning_rate": 2e-05,
"loss": 1.7609,
"step": 2
},
{
"epoch": 0.00026955388831483896,
"grad_norm": 3.2226476669311523,
"learning_rate": 3e-05,
"loss": 2.1178,
"step": 3
},
{
"epoch": 0.00035940518441978525,
"grad_norm": 3.3700153827667236,
"learning_rate": 4e-05,
"loss": 2.1118,
"step": 4
},
{
"epoch": 0.0004492564805247316,
"grad_norm": 3.527953624725342,
"learning_rate": 5e-05,
"loss": 1.9904,
"step": 5
},
{
"epoch": 0.0005391077766296779,
"grad_norm": 3.702324390411377,
"learning_rate": 6e-05,
"loss": 1.9364,
"step": 6
},
{
"epoch": 0.0006289590727346242,
"grad_norm": 3.1446261405944824,
"learning_rate": 7e-05,
"loss": 1.5929,
"step": 7
},
{
"epoch": 0.0007188103688395705,
"grad_norm": 2.7797582149505615,
"learning_rate": 8e-05,
"loss": 1.3322,
"step": 8
},
{
"epoch": 0.0008086616649445168,
"grad_norm": 1.7103683948516846,
"learning_rate": 9e-05,
"loss": 0.9137,
"step": 9
},
{
"epoch": 0.0008985129610494632,
"grad_norm": 1.6252132654190063,
"learning_rate": 0.0001,
"loss": 0.9555,
"step": 10
},
{
"epoch": 0.0009883642571544094,
"grad_norm": 2.3974406719207764,
"learning_rate": 9.999316524962345e-05,
"loss": 0.804,
"step": 11
},
{
"epoch": 0.0010782155532593559,
"grad_norm": 1.7891347408294678,
"learning_rate": 9.997266286704631e-05,
"loss": 0.7281,
"step": 12
},
{
"epoch": 0.0011680668493643021,
"grad_norm": 1.5614227056503296,
"learning_rate": 9.993849845741524e-05,
"loss": 0.6241,
"step": 13
},
{
"epoch": 0.0012579181454692484,
"grad_norm": 1.5713458061218262,
"learning_rate": 9.989068136093873e-05,
"loss": 0.462,
"step": 14
},
{
"epoch": 0.0013477694415741947,
"grad_norm": 1.1358058452606201,
"learning_rate": 9.98292246503335e-05,
"loss": 0.3021,
"step": 15
},
{
"epoch": 0.001437620737679141,
"grad_norm": 1.0922521352767944,
"learning_rate": 9.975414512725057e-05,
"loss": 0.2806,
"step": 16
},
{
"epoch": 0.0015274720337840873,
"grad_norm": 1.394178032875061,
"learning_rate": 9.966546331768191e-05,
"loss": 0.3656,
"step": 17
},
{
"epoch": 0.0016173233298890336,
"grad_norm": 1.058937907218933,
"learning_rate": 9.956320346634876e-05,
"loss": 0.1882,
"step": 18
},
{
"epoch": 0.00170717462599398,
"grad_norm": 1.3172550201416016,
"learning_rate": 9.944739353007344e-05,
"loss": 0.2863,
"step": 19
},
{
"epoch": 0.0017970259220989263,
"grad_norm": 1.8061860799789429,
"learning_rate": 9.931806517013612e-05,
"loss": 0.349,
"step": 20
},
{
"epoch": 0.0018868772182038726,
"grad_norm": 1.3081026077270508,
"learning_rate": 9.917525374361912e-05,
"loss": 0.1169,
"step": 21
},
{
"epoch": 0.0019767285143088187,
"grad_norm": 1.8801676034927368,
"learning_rate": 9.901899829374047e-05,
"loss": 0.3773,
"step": 22
},
{
"epoch": 0.0020665798104137654,
"grad_norm": 1.2898595333099365,
"learning_rate": 9.884934153917997e-05,
"loss": 0.1644,
"step": 23
},
{
"epoch": 0.0021564311065187117,
"grad_norm": 2.21494197845459,
"learning_rate": 9.86663298624003e-05,
"loss": 0.2302,
"step": 24
},
{
"epoch": 0.002246282402623658,
"grad_norm": 1.060278296470642,
"learning_rate": 9.847001329696653e-05,
"loss": 0.1159,
"step": 25
},
{
"epoch": 0.0023361336987286043,
"grad_norm": 1.4339865446090698,
"learning_rate": 9.826044551386744e-05,
"loss": 0.1716,
"step": 26
},
{
"epoch": 0.0024259849948335506,
"grad_norm": 0.9997158646583557,
"learning_rate": 9.803768380684242e-05,
"loss": 0.037,
"step": 27
},
{
"epoch": 0.002515836290938497,
"grad_norm": 2.287733554840088,
"learning_rate": 9.780178907671789e-05,
"loss": 0.1358,
"step": 28
},
{
"epoch": 0.002605687587043443,
"grad_norm": 0.4436582028865814,
"learning_rate": 9.755282581475769e-05,
"loss": 0.0291,
"step": 29
},
{
"epoch": 0.0026955388831483894,
"grad_norm": 0.5807464718818665,
"learning_rate": 9.729086208503174e-05,
"loss": 0.0194,
"step": 30
},
{
"epoch": 0.0027853901792533357,
"grad_norm": 1.409766435623169,
"learning_rate": 9.701596950580806e-05,
"loss": 0.0657,
"step": 31
},
{
"epoch": 0.002875241475358282,
"grad_norm": 1.207972526550293,
"learning_rate": 9.672822322997305e-05,
"loss": 0.1951,
"step": 32
},
{
"epoch": 0.0029650927714632283,
"grad_norm": 0.8214380741119385,
"learning_rate": 9.642770192448536e-05,
"loss": 0.1156,
"step": 33
},
{
"epoch": 0.0030549440675681746,
"grad_norm": 1.9357601404190063,
"learning_rate": 9.611448774886924e-05,
"loss": 0.0873,
"step": 34
},
{
"epoch": 0.003144795363673121,
"grad_norm": 2.1450936794281006,
"learning_rate": 9.578866633275288e-05,
"loss": 0.2288,
"step": 35
},
{
"epoch": 0.003234646659778067,
"grad_norm": 0.5352392792701721,
"learning_rate": 9.545032675245813e-05,
"loss": 0.0288,
"step": 36
},
{
"epoch": 0.0033244979558830134,
"grad_norm": 2.8170526027679443,
"learning_rate": 9.509956150664796e-05,
"loss": 0.3828,
"step": 37
},
{
"epoch": 0.00341434925198796,
"grad_norm": 1.006988286972046,
"learning_rate": 9.473646649103818e-05,
"loss": 0.0432,
"step": 38
},
{
"epoch": 0.0035042005480929064,
"grad_norm": 1.629753828048706,
"learning_rate": 9.43611409721806e-05,
"loss": 0.2112,
"step": 39
},
{
"epoch": 0.0035940518441978527,
"grad_norm": 1.1105238199234009,
"learning_rate": 9.397368756032445e-05,
"loss": 0.073,
"step": 40
},
{
"epoch": 0.003683903140302799,
"grad_norm": 2.558805465698242,
"learning_rate": 9.357421218136386e-05,
"loss": 0.4426,
"step": 41
},
{
"epoch": 0.0037737544364077453,
"grad_norm": 1.6937123537063599,
"learning_rate": 9.316282404787871e-05,
"loss": 0.0511,
"step": 42
},
{
"epoch": 0.0038636057325126916,
"grad_norm": 0.47619715332984924,
"learning_rate": 9.273963562927695e-05,
"loss": 0.0292,
"step": 43
},
{
"epoch": 0.003953457028617637,
"grad_norm": 3.6469249725341797,
"learning_rate": 9.230476262104677e-05,
"loss": 0.1238,
"step": 44
},
{
"epoch": 0.0040433083247225846,
"grad_norm": 1.2075451612472534,
"learning_rate": 9.185832391312644e-05,
"loss": 0.0635,
"step": 45
},
{
"epoch": 0.004133159620827531,
"grad_norm": 2.7494451999664307,
"learning_rate": 9.140044155740101e-05,
"loss": 0.4871,
"step": 46
},
{
"epoch": 0.004223010916932477,
"grad_norm": 3.211578607559204,
"learning_rate": 9.093124073433463e-05,
"loss": 0.4836,
"step": 47
},
{
"epoch": 0.004312862213037423,
"grad_norm": 3.217000722885132,
"learning_rate": 9.045084971874738e-05,
"loss": 0.3402,
"step": 48
},
{
"epoch": 0.00440271350914237,
"grad_norm": 6.685438632965088,
"learning_rate": 8.995939984474624e-05,
"loss": 1.1275,
"step": 49
},
{
"epoch": 0.004492564805247316,
"grad_norm": 40.79585647583008,
"learning_rate": 8.945702546981969e-05,
"loss": 6.6405,
"step": 50
},
{
"epoch": 0.004492564805247316,
"eval_loss": 0.04590430483222008,
"eval_runtime": 906.7297,
"eval_samples_per_second": 20.673,
"eval_steps_per_second": 5.169,
"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": 3.77695431032832e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}