lesso's picture
Training in progress, step 50, checkpoint
7315d82 verified
raw
history blame
10 kB
{
"best_metric": 0.6465714573860168,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.07072135785007072,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0014144271570014145,
"grad_norm": 30.358135223388672,
"learning_rate": 1.0100000000000002e-05,
"loss": 5.9636,
"step": 1
},
{
"epoch": 0.0014144271570014145,
"eval_loss": 1.5057185888290405,
"eval_runtime": 65.8108,
"eval_samples_per_second": 144.733,
"eval_steps_per_second": 4.528,
"step": 1
},
{
"epoch": 0.002828854314002829,
"grad_norm": 31.44856071472168,
"learning_rate": 2.0200000000000003e-05,
"loss": 6.0251,
"step": 2
},
{
"epoch": 0.004243281471004243,
"grad_norm": 22.16029930114746,
"learning_rate": 3.0299999999999998e-05,
"loss": 5.5536,
"step": 3
},
{
"epoch": 0.005657708628005658,
"grad_norm": 17.20639991760254,
"learning_rate": 4.0400000000000006e-05,
"loss": 4.7391,
"step": 4
},
{
"epoch": 0.007072135785007072,
"grad_norm": 12.612313270568848,
"learning_rate": 5.05e-05,
"loss": 4.1681,
"step": 5
},
{
"epoch": 0.008486562942008486,
"grad_norm": 8.703054428100586,
"learning_rate": 6.0599999999999996e-05,
"loss": 3.637,
"step": 6
},
{
"epoch": 0.009900990099009901,
"grad_norm": 9.403382301330566,
"learning_rate": 7.07e-05,
"loss": 3.7323,
"step": 7
},
{
"epoch": 0.011315417256011316,
"grad_norm": 12.620731353759766,
"learning_rate": 8.080000000000001e-05,
"loss": 3.6018,
"step": 8
},
{
"epoch": 0.01272984441301273,
"grad_norm": 8.057601928710938,
"learning_rate": 9.09e-05,
"loss": 3.4366,
"step": 9
},
{
"epoch": 0.014144271570014143,
"grad_norm": 4.481306552886963,
"learning_rate": 0.000101,
"loss": 3.2684,
"step": 10
},
{
"epoch": 0.015558698727015558,
"grad_norm": 4.987090110778809,
"learning_rate": 0.00010046842105263158,
"loss": 3.1242,
"step": 11
},
{
"epoch": 0.016973125884016973,
"grad_norm": 4.0390849113464355,
"learning_rate": 9.993684210526315e-05,
"loss": 2.8276,
"step": 12
},
{
"epoch": 0.018387553041018388,
"grad_norm": 4.3538432121276855,
"learning_rate": 9.940526315789473e-05,
"loss": 3.0122,
"step": 13
},
{
"epoch": 0.019801980198019802,
"grad_norm": 3.8758561611175537,
"learning_rate": 9.887368421052632e-05,
"loss": 3.1345,
"step": 14
},
{
"epoch": 0.021216407355021217,
"grad_norm": 4.682952880859375,
"learning_rate": 9.83421052631579e-05,
"loss": 3.0093,
"step": 15
},
{
"epoch": 0.02263083451202263,
"grad_norm": 3.6436381340026855,
"learning_rate": 9.781052631578948e-05,
"loss": 2.8878,
"step": 16
},
{
"epoch": 0.024045261669024046,
"grad_norm": 3.1359572410583496,
"learning_rate": 9.727894736842106e-05,
"loss": 2.8174,
"step": 17
},
{
"epoch": 0.02545968882602546,
"grad_norm": 3.475654363632202,
"learning_rate": 9.674736842105263e-05,
"loss": 2.6673,
"step": 18
},
{
"epoch": 0.026874115983026876,
"grad_norm": 3.38742733001709,
"learning_rate": 9.621578947368421e-05,
"loss": 2.8075,
"step": 19
},
{
"epoch": 0.028288543140028287,
"grad_norm": 6.014629364013672,
"learning_rate": 9.568421052631578e-05,
"loss": 3.0922,
"step": 20
},
{
"epoch": 0.0297029702970297,
"grad_norm": 3.0035653114318848,
"learning_rate": 9.515263157894737e-05,
"loss": 2.9599,
"step": 21
},
{
"epoch": 0.031117397454031116,
"grad_norm": 3.9666907787323,
"learning_rate": 9.462105263157895e-05,
"loss": 2.8904,
"step": 22
},
{
"epoch": 0.03253182461103253,
"grad_norm": 3.315082550048828,
"learning_rate": 9.408947368421054e-05,
"loss": 2.7768,
"step": 23
},
{
"epoch": 0.033946251768033946,
"grad_norm": 2.5618789196014404,
"learning_rate": 9.355789473684211e-05,
"loss": 2.6475,
"step": 24
},
{
"epoch": 0.03536067892503536,
"grad_norm": 2.922630548477173,
"learning_rate": 9.302631578947369e-05,
"loss": 2.5942,
"step": 25
},
{
"epoch": 0.036775106082036775,
"grad_norm": 4.30806827545166,
"learning_rate": 9.249473684210526e-05,
"loss": 3.0147,
"step": 26
},
{
"epoch": 0.03818953323903819,
"grad_norm": 2.8271915912628174,
"learning_rate": 9.196315789473685e-05,
"loss": 2.8583,
"step": 27
},
{
"epoch": 0.039603960396039604,
"grad_norm": 2.8441073894500732,
"learning_rate": 9.143157894736843e-05,
"loss": 2.7133,
"step": 28
},
{
"epoch": 0.04101838755304102,
"grad_norm": 2.657393455505371,
"learning_rate": 9.09e-05,
"loss": 2.6705,
"step": 29
},
{
"epoch": 0.042432814710042434,
"grad_norm": 2.526547908782959,
"learning_rate": 9.036842105263158e-05,
"loss": 2.6752,
"step": 30
},
{
"epoch": 0.04384724186704385,
"grad_norm": 2.5309224128723145,
"learning_rate": 8.983684210526316e-05,
"loss": 2.6006,
"step": 31
},
{
"epoch": 0.04526166902404526,
"grad_norm": 3.246652841567993,
"learning_rate": 8.930526315789474e-05,
"loss": 2.926,
"step": 32
},
{
"epoch": 0.04667609618104668,
"grad_norm": 2.7534706592559814,
"learning_rate": 8.877368421052632e-05,
"loss": 2.8862,
"step": 33
},
{
"epoch": 0.04809052333804809,
"grad_norm": 2.599621295928955,
"learning_rate": 8.82421052631579e-05,
"loss": 2.7434,
"step": 34
},
{
"epoch": 0.04950495049504951,
"grad_norm": 2.4461135864257812,
"learning_rate": 8.771052631578948e-05,
"loss": 2.6901,
"step": 35
},
{
"epoch": 0.05091937765205092,
"grad_norm": 2.444023370742798,
"learning_rate": 8.717894736842105e-05,
"loss": 2.5766,
"step": 36
},
{
"epoch": 0.05233380480905234,
"grad_norm": 2.3293182849884033,
"learning_rate": 8.664736842105263e-05,
"loss": 2.4633,
"step": 37
},
{
"epoch": 0.05374823196605375,
"grad_norm": 2.4258995056152344,
"learning_rate": 8.61157894736842e-05,
"loss": 2.6781,
"step": 38
},
{
"epoch": 0.055162659123055166,
"grad_norm": 3.006838083267212,
"learning_rate": 8.55842105263158e-05,
"loss": 2.8319,
"step": 39
},
{
"epoch": 0.056577086280056574,
"grad_norm": 2.496774673461914,
"learning_rate": 8.505263157894737e-05,
"loss": 2.644,
"step": 40
},
{
"epoch": 0.05799151343705799,
"grad_norm": 2.602163076400757,
"learning_rate": 8.452105263157896e-05,
"loss": 2.6905,
"step": 41
},
{
"epoch": 0.0594059405940594,
"grad_norm": 2.52225661277771,
"learning_rate": 8.398947368421053e-05,
"loss": 2.5921,
"step": 42
},
{
"epoch": 0.06082036775106082,
"grad_norm": 2.3774173259735107,
"learning_rate": 8.345789473684211e-05,
"loss": 2.4794,
"step": 43
},
{
"epoch": 0.06223479490806223,
"grad_norm": 2.1766254901885986,
"learning_rate": 8.292631578947368e-05,
"loss": 2.5138,
"step": 44
},
{
"epoch": 0.06364922206506365,
"grad_norm": 2.6760802268981934,
"learning_rate": 8.239473684210526e-05,
"loss": 2.7873,
"step": 45
},
{
"epoch": 0.06506364922206506,
"grad_norm": 2.3476643562316895,
"learning_rate": 8.186315789473683e-05,
"loss": 2.6749,
"step": 46
},
{
"epoch": 0.06647807637906648,
"grad_norm": 2.3106589317321777,
"learning_rate": 8.133157894736842e-05,
"loss": 2.5956,
"step": 47
},
{
"epoch": 0.06789250353606789,
"grad_norm": 2.198598861694336,
"learning_rate": 8.080000000000001e-05,
"loss": 2.5047,
"step": 48
},
{
"epoch": 0.06930693069306931,
"grad_norm": 2.2239043712615967,
"learning_rate": 8.026842105263159e-05,
"loss": 2.5194,
"step": 49
},
{
"epoch": 0.07072135785007072,
"grad_norm": 2.4284136295318604,
"learning_rate": 7.973684210526316e-05,
"loss": 2.4291,
"step": 50
},
{
"epoch": 0.07072135785007072,
"eval_loss": 0.6465714573860168,
"eval_runtime": 65.9647,
"eval_samples_per_second": 144.395,
"eval_steps_per_second": 4.518,
"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": 5.723998478401536e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}