eeeebbb2's picture
Training in progress, step 50, checkpoint
cbe0973 verified
raw
history blame
10.3 kB
{
"best_metric": 0.3329808712005615,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.01972386587771203,
"eval_steps": 25,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003944773175542406,
"grad_norm": 429.76324462890625,
"learning_rate": 5e-05,
"loss": 130.3346,
"step": 1
},
{
"epoch": 0.0003944773175542406,
"eval_loss": 8.782329559326172,
"eval_runtime": 2.9015,
"eval_samples_per_second": 17.232,
"eval_steps_per_second": 4.48,
"step": 1
},
{
"epoch": 0.0007889546351084812,
"grad_norm": 484.9067077636719,
"learning_rate": 0.0001,
"loss": 141.1426,
"step": 2
},
{
"epoch": 0.001183431952662722,
"grad_norm": 309.4012756347656,
"learning_rate": 9.990365154573717e-05,
"loss": 127.5039,
"step": 3
},
{
"epoch": 0.0015779092702169625,
"grad_norm": 775.7621459960938,
"learning_rate": 9.961501876182148e-05,
"loss": 101.8763,
"step": 4
},
{
"epoch": 0.0019723865877712033,
"grad_norm": 433.8789978027344,
"learning_rate": 9.913533761814537e-05,
"loss": 184.4323,
"step": 5
},
{
"epoch": 0.002366863905325444,
"grad_norm": 1732.094970703125,
"learning_rate": 9.846666218300807e-05,
"loss": 106.7014,
"step": 6
},
{
"epoch": 0.0027613412228796844,
"grad_norm": 145.82847595214844,
"learning_rate": 9.761185582727977e-05,
"loss": 49.7496,
"step": 7
},
{
"epoch": 0.003155818540433925,
"grad_norm": 44.45709991455078,
"learning_rate": 9.657457896300791e-05,
"loss": 47.3565,
"step": 8
},
{
"epoch": 0.0035502958579881655,
"grad_norm": 44.64686584472656,
"learning_rate": 9.535927336897098e-05,
"loss": 47.4358,
"step": 9
},
{
"epoch": 0.0039447731755424065,
"grad_norm": 31.391660690307617,
"learning_rate": 9.397114317029975e-05,
"loss": 46.4179,
"step": 10
},
{
"epoch": 0.004339250493096647,
"grad_norm": 35.36396789550781,
"learning_rate": 9.241613255361455e-05,
"loss": 46.9726,
"step": 11
},
{
"epoch": 0.004733727810650888,
"grad_norm": 1805.6893310546875,
"learning_rate": 9.070090031310558e-05,
"loss": 125.8221,
"step": 12
},
{
"epoch": 0.005128205128205128,
"grad_norm": 1118.767578125,
"learning_rate": 8.883279133655399e-05,
"loss": 168.2086,
"step": 13
},
{
"epoch": 0.005522682445759369,
"grad_norm": 1515.4822998046875,
"learning_rate": 8.681980515339464e-05,
"loss": 99.1604,
"step": 14
},
{
"epoch": 0.005917159763313609,
"grad_norm": 770.9901733398438,
"learning_rate": 8.467056167950311e-05,
"loss": 53.9254,
"step": 15
},
{
"epoch": 0.00631163708086785,
"grad_norm": 736.7328491210938,
"learning_rate": 8.239426430539243e-05,
"loss": 53.6309,
"step": 16
},
{
"epoch": 0.0067061143984220905,
"grad_norm": 582.709228515625,
"learning_rate": 8.000066048588211e-05,
"loss": 49.7792,
"step": 17
},
{
"epoch": 0.007100591715976331,
"grad_norm": 80.58294677734375,
"learning_rate": 7.75e-05,
"loss": 45.2028,
"step": 18
},
{
"epoch": 0.007495069033530572,
"grad_norm": 34.99323272705078,
"learning_rate": 7.490299105985507e-05,
"loss": 44.2781,
"step": 19
},
{
"epoch": 0.007889546351084813,
"grad_norm": 43.09794616699219,
"learning_rate": 7.222075445642904e-05,
"loss": 43.1358,
"step": 20
},
{
"epoch": 0.008284023668639054,
"grad_norm": 58.41071701049805,
"learning_rate": 6.946477593864228e-05,
"loss": 42.5009,
"step": 21
},
{
"epoch": 0.008678500986193294,
"grad_norm": 80.99310302734375,
"learning_rate": 6.664685702961344e-05,
"loss": 41.4039,
"step": 22
},
{
"epoch": 0.009072978303747535,
"grad_norm": 105.64437866210938,
"learning_rate": 6.377906449072578e-05,
"loss": 39.8739,
"step": 23
},
{
"epoch": 0.009467455621301775,
"grad_norm": 379.9095764160156,
"learning_rate": 6.087367864990233e-05,
"loss": 55.6272,
"step": 24
},
{
"epoch": 0.009861932938856016,
"grad_norm": 1128.002685546875,
"learning_rate": 5.794314081535644e-05,
"loss": 101.638,
"step": 25
},
{
"epoch": 0.009861932938856016,
"eval_loss": 2.1840624809265137,
"eval_runtime": 2.9006,
"eval_samples_per_second": 17.238,
"eval_steps_per_second": 4.482,
"step": 25
},
{
"epoch": 0.010256410256410256,
"grad_norm": 134.1509552001953,
"learning_rate": 5.500000000000001e-05,
"loss": 37.7689,
"step": 26
},
{
"epoch": 0.010650887573964497,
"grad_norm": 192.20062255859375,
"learning_rate": 5.205685918464356e-05,
"loss": 30.977,
"step": 27
},
{
"epoch": 0.011045364891518738,
"grad_norm": 278.26812744140625,
"learning_rate": 4.912632135009769e-05,
"loss": 27.1425,
"step": 28
},
{
"epoch": 0.011439842209072978,
"grad_norm": 349.2325439453125,
"learning_rate": 4.6220935509274235e-05,
"loss": 23.5439,
"step": 29
},
{
"epoch": 0.011834319526627219,
"grad_norm": 398.40716552734375,
"learning_rate": 4.3353142970386564e-05,
"loss": 18.3674,
"step": 30
},
{
"epoch": 0.01222879684418146,
"grad_norm": 395.0241394042969,
"learning_rate": 4.053522406135775e-05,
"loss": 11.8943,
"step": 31
},
{
"epoch": 0.0126232741617357,
"grad_norm": 240.70681762695312,
"learning_rate": 3.777924554357096e-05,
"loss": 8.0201,
"step": 32
},
{
"epoch": 0.01301775147928994,
"grad_norm": 94.83889770507812,
"learning_rate": 3.509700894014496e-05,
"loss": 5.7875,
"step": 33
},
{
"epoch": 0.013412228796844181,
"grad_norm": 37.95793151855469,
"learning_rate": 3.250000000000001e-05,
"loss": 4.7613,
"step": 34
},
{
"epoch": 0.013806706114398421,
"grad_norm": 26.57615089416504,
"learning_rate": 2.9999339514117912e-05,
"loss": 4.4461,
"step": 35
},
{
"epoch": 0.014201183431952662,
"grad_norm": 23.705547332763672,
"learning_rate": 2.760573569460757e-05,
"loss": 4.7367,
"step": 36
},
{
"epoch": 0.014595660749506903,
"grad_norm": 576.8201293945312,
"learning_rate": 2.53294383204969e-05,
"loss": 35.7901,
"step": 37
},
{
"epoch": 0.014990138067061143,
"grad_norm": 454.54058837890625,
"learning_rate": 2.3180194846605367e-05,
"loss": 28.4482,
"step": 38
},
{
"epoch": 0.015384615384615385,
"grad_norm": 13.692035675048828,
"learning_rate": 2.1167208663446025e-05,
"loss": 4.371,
"step": 39
},
{
"epoch": 0.015779092702169626,
"grad_norm": 9.434082984924316,
"learning_rate": 1.9299099686894423e-05,
"loss": 4.5141,
"step": 40
},
{
"epoch": 0.016173570019723867,
"grad_norm": 8.686306953430176,
"learning_rate": 1.758386744638546e-05,
"loss": 4.3778,
"step": 41
},
{
"epoch": 0.016568047337278107,
"grad_norm": 14.598600387573242,
"learning_rate": 1.602885682970026e-05,
"loss": 4.5165,
"step": 42
},
{
"epoch": 0.016962524654832348,
"grad_norm": 8.761627197265625,
"learning_rate": 1.464072663102903e-05,
"loss": 4.4743,
"step": 43
},
{
"epoch": 0.01735700197238659,
"grad_norm": 4.435027599334717,
"learning_rate": 1.3425421036992098e-05,
"loss": 4.2297,
"step": 44
},
{
"epoch": 0.01775147928994083,
"grad_norm": 3.197697639465332,
"learning_rate": 1.2388144172720251e-05,
"loss": 4.2066,
"step": 45
},
{
"epoch": 0.01814595660749507,
"grad_norm": 4.16876745223999,
"learning_rate": 1.1533337816991932e-05,
"loss": 4.0468,
"step": 46
},
{
"epoch": 0.01854043392504931,
"grad_norm": 6.92716646194458,
"learning_rate": 1.0864662381854632e-05,
"loss": 4.346,
"step": 47
},
{
"epoch": 0.01893491124260355,
"grad_norm": 6.868653774261475,
"learning_rate": 1.0384981238178534e-05,
"loss": 4.3406,
"step": 48
},
{
"epoch": 0.01932938856015779,
"grad_norm": 76.7080307006836,
"learning_rate": 1.0096348454262845e-05,
"loss": 8.5237,
"step": 49
},
{
"epoch": 0.01972386587771203,
"grad_norm": 772.5637817382812,
"learning_rate": 1e-05,
"loss": 47.5903,
"step": 50
},
{
"epoch": 0.01972386587771203,
"eval_loss": 0.3329808712005615,
"eval_runtime": 2.9191,
"eval_samples_per_second": 17.128,
"eval_steps_per_second": 4.453,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 50,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 25,
"stateful_callbacks": {
"EarlyStoppingCallback": {
"args": {
"early_stopping_patience": 1,
"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": true
},
"attributes": {}
}
},
"total_flos": 5.259104775831552e+17,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}