lesso's picture
Training in progress, step 50, checkpoint
3290a51 verified
raw
history blame
10 kB
{
"best_metric": 2.0389838218688965,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.00464101731099457,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 9.28203462198914e-05,
"grad_norm": 0.5333740711212158,
"learning_rate": 1.004e-05,
"loss": 2.123,
"step": 1
},
{
"epoch": 9.28203462198914e-05,
"eval_loss": 2.1500566005706787,
"eval_runtime": 212.426,
"eval_samples_per_second": 21.358,
"eval_steps_per_second": 5.343,
"step": 1
},
{
"epoch": 0.0001856406924397828,
"grad_norm": 0.5310633182525635,
"learning_rate": 2.008e-05,
"loss": 2.1533,
"step": 2
},
{
"epoch": 0.0002784610386596742,
"grad_norm": 0.570530116558075,
"learning_rate": 3.012e-05,
"loss": 1.9656,
"step": 3
},
{
"epoch": 0.0003712813848795656,
"grad_norm": 0.5866032242774963,
"learning_rate": 4.016e-05,
"loss": 1.9126,
"step": 4
},
{
"epoch": 0.000464101731099457,
"grad_norm": 0.5609645247459412,
"learning_rate": 5.02e-05,
"loss": 1.9268,
"step": 5
},
{
"epoch": 0.0005569220773193484,
"grad_norm": 0.5599470138549805,
"learning_rate": 6.024e-05,
"loss": 2.1493,
"step": 6
},
{
"epoch": 0.0006497424235392398,
"grad_norm": 0.5012790560722351,
"learning_rate": 7.028e-05,
"loss": 1.9697,
"step": 7
},
{
"epoch": 0.0007425627697591312,
"grad_norm": 0.5099210739135742,
"learning_rate": 8.032e-05,
"loss": 2.1438,
"step": 8
},
{
"epoch": 0.0008353831159790226,
"grad_norm": 0.5398349165916443,
"learning_rate": 9.036000000000001e-05,
"loss": 1.9605,
"step": 9
},
{
"epoch": 0.000928203462198914,
"grad_norm": 0.5319710969924927,
"learning_rate": 0.0001004,
"loss": 2.274,
"step": 10
},
{
"epoch": 0.0010210238084188054,
"grad_norm": 0.5919522047042847,
"learning_rate": 9.987157894736842e-05,
"loss": 2.1037,
"step": 11
},
{
"epoch": 0.0011138441546386967,
"grad_norm": 0.5564264059066772,
"learning_rate": 9.934315789473684e-05,
"loss": 2.1668,
"step": 12
},
{
"epoch": 0.0012066645008585882,
"grad_norm": 0.5003729462623596,
"learning_rate": 9.881473684210525e-05,
"loss": 1.8983,
"step": 13
},
{
"epoch": 0.0012994848470784797,
"grad_norm": 0.5218623876571655,
"learning_rate": 9.828631578947369e-05,
"loss": 2.063,
"step": 14
},
{
"epoch": 0.001392305193298371,
"grad_norm": 0.5020257830619812,
"learning_rate": 9.77578947368421e-05,
"loss": 2.119,
"step": 15
},
{
"epoch": 0.0014851255395182624,
"grad_norm": 0.510440468788147,
"learning_rate": 9.722947368421052e-05,
"loss": 2.0224,
"step": 16
},
{
"epoch": 0.0015779458857381537,
"grad_norm": 0.5378854274749756,
"learning_rate": 9.670105263157895e-05,
"loss": 2.0703,
"step": 17
},
{
"epoch": 0.0016707662319580452,
"grad_norm": 0.5330931544303894,
"learning_rate": 9.617263157894737e-05,
"loss": 1.9227,
"step": 18
},
{
"epoch": 0.0017635865781779367,
"grad_norm": 0.4982943534851074,
"learning_rate": 9.564421052631579e-05,
"loss": 1.7878,
"step": 19
},
{
"epoch": 0.001856406924397828,
"grad_norm": 0.5345494747161865,
"learning_rate": 9.511578947368421e-05,
"loss": 2.0192,
"step": 20
},
{
"epoch": 0.0019492272706177194,
"grad_norm": 0.5428488254547119,
"learning_rate": 9.458736842105264e-05,
"loss": 1.8952,
"step": 21
},
{
"epoch": 0.002042047616837611,
"grad_norm": 0.4932510256767273,
"learning_rate": 9.405894736842106e-05,
"loss": 2.0396,
"step": 22
},
{
"epoch": 0.002134867963057502,
"grad_norm": 0.5346501469612122,
"learning_rate": 9.353052631578947e-05,
"loss": 2.06,
"step": 23
},
{
"epoch": 0.0022276883092773934,
"grad_norm": 0.5654396414756775,
"learning_rate": 9.300210526315789e-05,
"loss": 2.1686,
"step": 24
},
{
"epoch": 0.002320508655497285,
"grad_norm": 0.5074037313461304,
"learning_rate": 9.247368421052631e-05,
"loss": 2.0209,
"step": 25
},
{
"epoch": 0.0024133290017171764,
"grad_norm": 0.5299178957939148,
"learning_rate": 9.194526315789473e-05,
"loss": 2.0733,
"step": 26
},
{
"epoch": 0.0025061493479370677,
"grad_norm": 0.4903567135334015,
"learning_rate": 9.141684210526316e-05,
"loss": 1.8781,
"step": 27
},
{
"epoch": 0.0025989696941569594,
"grad_norm": 0.5466001629829407,
"learning_rate": 9.088842105263158e-05,
"loss": 2.2091,
"step": 28
},
{
"epoch": 0.0026917900403768506,
"grad_norm": 0.5639941692352295,
"learning_rate": 9.036000000000001e-05,
"loss": 2.0417,
"step": 29
},
{
"epoch": 0.002784610386596742,
"grad_norm": 0.547460675239563,
"learning_rate": 8.983157894736843e-05,
"loss": 2.3328,
"step": 30
},
{
"epoch": 0.0028774307328166336,
"grad_norm": 0.5575900077819824,
"learning_rate": 8.930315789473684e-05,
"loss": 1.9555,
"step": 31
},
{
"epoch": 0.002970251079036525,
"grad_norm": 0.5688737034797668,
"learning_rate": 8.877473684210526e-05,
"loss": 2.2341,
"step": 32
},
{
"epoch": 0.003063071425256416,
"grad_norm": 0.5598611235618591,
"learning_rate": 8.824631578947368e-05,
"loss": 2.0329,
"step": 33
},
{
"epoch": 0.0031558917714763074,
"grad_norm": 0.5636963248252869,
"learning_rate": 8.771789473684211e-05,
"loss": 2.1278,
"step": 34
},
{
"epoch": 0.003248712117696199,
"grad_norm": 0.5724871754646301,
"learning_rate": 8.718947368421053e-05,
"loss": 2.1822,
"step": 35
},
{
"epoch": 0.0033415324639160904,
"grad_norm": 0.5909259915351868,
"learning_rate": 8.666105263157895e-05,
"loss": 2.1601,
"step": 36
},
{
"epoch": 0.0034343528101359816,
"grad_norm": 0.5581693053245544,
"learning_rate": 8.613263157894737e-05,
"loss": 2.1731,
"step": 37
},
{
"epoch": 0.0035271731563558733,
"grad_norm": 0.5789634585380554,
"learning_rate": 8.560421052631578e-05,
"loss": 2.0267,
"step": 38
},
{
"epoch": 0.0036199935025757646,
"grad_norm": 0.5522585511207581,
"learning_rate": 8.50757894736842e-05,
"loss": 2.149,
"step": 39
},
{
"epoch": 0.003712813848795656,
"grad_norm": 0.5890622735023499,
"learning_rate": 8.454736842105263e-05,
"loss": 2.3245,
"step": 40
},
{
"epoch": 0.0038056341950155476,
"grad_norm": 0.6173768043518066,
"learning_rate": 8.401894736842106e-05,
"loss": 2.4872,
"step": 41
},
{
"epoch": 0.003898454541235439,
"grad_norm": 0.5873492360115051,
"learning_rate": 8.349052631578948e-05,
"loss": 1.9492,
"step": 42
},
{
"epoch": 0.00399127488745533,
"grad_norm": 0.6083503365516663,
"learning_rate": 8.29621052631579e-05,
"loss": 2.2825,
"step": 43
},
{
"epoch": 0.004084095233675222,
"grad_norm": 0.5901498794555664,
"learning_rate": 8.243368421052632e-05,
"loss": 2.0717,
"step": 44
},
{
"epoch": 0.004176915579895113,
"grad_norm": 0.627431333065033,
"learning_rate": 8.190526315789474e-05,
"loss": 2.2892,
"step": 45
},
{
"epoch": 0.004269735926115004,
"grad_norm": 0.5825062394142151,
"learning_rate": 8.137684210526315e-05,
"loss": 2.1311,
"step": 46
},
{
"epoch": 0.004362556272334896,
"grad_norm": 0.600988507270813,
"learning_rate": 8.084842105263157e-05,
"loss": 2.1318,
"step": 47
},
{
"epoch": 0.004455376618554787,
"grad_norm": 0.660859227180481,
"learning_rate": 8.032e-05,
"loss": 2.1271,
"step": 48
},
{
"epoch": 0.0045481969647746786,
"grad_norm": 0.6793040633201599,
"learning_rate": 7.979157894736842e-05,
"loss": 2.3411,
"step": 49
},
{
"epoch": 0.00464101731099457,
"grad_norm": 0.6588550806045532,
"learning_rate": 7.926315789473684e-05,
"loss": 2.3991,
"step": 50
},
{
"epoch": 0.00464101731099457,
"eval_loss": 2.0389838218688965,
"eval_runtime": 212.2309,
"eval_samples_per_second": 21.378,
"eval_steps_per_second": 5.348,
"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": 3639935772917760.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}