prxy5605's picture
Training in progress, step 50, checkpoint
b58bb43 verified
raw
history blame
9.97 kB
{
"best_metric": 2.3614883422851562,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.005063803929511849,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00010127607859023699,
"grad_norm": 31.278818130493164,
"learning_rate": 1e-05,
"loss": 5.6035,
"step": 1
},
{
"epoch": 0.00010127607859023699,
"eval_loss": 6.345576286315918,
"eval_runtime": 1564.2303,
"eval_samples_per_second": 10.631,
"eval_steps_per_second": 2.658,
"step": 1
},
{
"epoch": 0.00020255215718047398,
"grad_norm": 23.076887130737305,
"learning_rate": 2e-05,
"loss": 5.6016,
"step": 2
},
{
"epoch": 0.00030382823577071097,
"grad_norm": 30.049488067626953,
"learning_rate": 3e-05,
"loss": 5.0056,
"step": 3
},
{
"epoch": 0.00040510431436094796,
"grad_norm": 21.293628692626953,
"learning_rate": 4e-05,
"loss": 4.0928,
"step": 4
},
{
"epoch": 0.0005063803929511849,
"grad_norm": 51.72479248046875,
"learning_rate": 5e-05,
"loss": 3.268,
"step": 5
},
{
"epoch": 0.0006076564715414219,
"grad_norm": 69.23747253417969,
"learning_rate": 6e-05,
"loss": 2.4954,
"step": 6
},
{
"epoch": 0.0007089325501316589,
"grad_norm": 12.229398727416992,
"learning_rate": 7e-05,
"loss": 1.7844,
"step": 7
},
{
"epoch": 0.0008102086287218959,
"grad_norm": 14.901517868041992,
"learning_rate": 8e-05,
"loss": 1.5585,
"step": 8
},
{
"epoch": 0.0009114847073121329,
"grad_norm": 9.97788143157959,
"learning_rate": 9e-05,
"loss": 1.5229,
"step": 9
},
{
"epoch": 0.0010127607859023698,
"grad_norm": 17.119428634643555,
"learning_rate": 0.0001,
"loss": 1.5665,
"step": 10
},
{
"epoch": 0.001114036864492607,
"grad_norm": 8.448174476623535,
"learning_rate": 9.999316524962345e-05,
"loss": 1.2061,
"step": 11
},
{
"epoch": 0.0012153129430828439,
"grad_norm": 6.501319408416748,
"learning_rate": 9.997266286704631e-05,
"loss": 1.2982,
"step": 12
},
{
"epoch": 0.0013165890216730808,
"grad_norm": 6.863130569458008,
"learning_rate": 9.993849845741524e-05,
"loss": 1.4555,
"step": 13
},
{
"epoch": 0.0014178651002633178,
"grad_norm": 7.778407096862793,
"learning_rate": 9.989068136093873e-05,
"loss": 1.4297,
"step": 14
},
{
"epoch": 0.0015191411788535547,
"grad_norm": 4.9213385581970215,
"learning_rate": 9.98292246503335e-05,
"loss": 1.478,
"step": 15
},
{
"epoch": 0.0016204172574437918,
"grad_norm": 6.808879375457764,
"learning_rate": 9.975414512725057e-05,
"loss": 1.6191,
"step": 16
},
{
"epoch": 0.0017216933360340288,
"grad_norm": 4.654536724090576,
"learning_rate": 9.966546331768191e-05,
"loss": 1.3514,
"step": 17
},
{
"epoch": 0.0018229694146242657,
"grad_norm": 5.336677551269531,
"learning_rate": 9.956320346634876e-05,
"loss": 1.3981,
"step": 18
},
{
"epoch": 0.0019242454932145027,
"grad_norm": 5.827622413635254,
"learning_rate": 9.944739353007344e-05,
"loss": 1.3458,
"step": 19
},
{
"epoch": 0.0020255215718047396,
"grad_norm": 6.260201454162598,
"learning_rate": 9.931806517013612e-05,
"loss": 1.7247,
"step": 20
},
{
"epoch": 0.0021267976503949767,
"grad_norm": 9.512893676757812,
"learning_rate": 9.917525374361912e-05,
"loss": 1.7886,
"step": 21
},
{
"epoch": 0.002228073728985214,
"grad_norm": 6.11754846572876,
"learning_rate": 9.901899829374047e-05,
"loss": 1.6451,
"step": 22
},
{
"epoch": 0.0023293498075754506,
"grad_norm": 5.766722679138184,
"learning_rate": 9.884934153917997e-05,
"loss": 1.506,
"step": 23
},
{
"epoch": 0.0024306258861656878,
"grad_norm": 6.981493949890137,
"learning_rate": 9.86663298624003e-05,
"loss": 1.822,
"step": 24
},
{
"epoch": 0.0025319019647559245,
"grad_norm": 5.49668025970459,
"learning_rate": 9.847001329696653e-05,
"loss": 1.6161,
"step": 25
},
{
"epoch": 0.0026331780433461616,
"grad_norm": 6.683679580688477,
"learning_rate": 9.826044551386744e-05,
"loss": 1.6799,
"step": 26
},
{
"epoch": 0.002734454121936399,
"grad_norm": 6.836819648742676,
"learning_rate": 9.803768380684242e-05,
"loss": 1.5681,
"step": 27
},
{
"epoch": 0.0028357302005266355,
"grad_norm": 5.405344486236572,
"learning_rate": 9.780178907671789e-05,
"loss": 1.603,
"step": 28
},
{
"epoch": 0.0029370062791168727,
"grad_norm": 5.259994029998779,
"learning_rate": 9.755282581475769e-05,
"loss": 1.6561,
"step": 29
},
{
"epoch": 0.0030382823577071094,
"grad_norm": 4.639139175415039,
"learning_rate": 9.729086208503174e-05,
"loss": 1.7005,
"step": 30
},
{
"epoch": 0.0031395584362973465,
"grad_norm": 8.204778671264648,
"learning_rate": 9.701596950580806e-05,
"loss": 2.2015,
"step": 31
},
{
"epoch": 0.0032408345148875837,
"grad_norm": 5.750695705413818,
"learning_rate": 9.672822322997305e-05,
"loss": 2.1686,
"step": 32
},
{
"epoch": 0.0033421105934778204,
"grad_norm": 4.413594722747803,
"learning_rate": 9.642770192448536e-05,
"loss": 1.9129,
"step": 33
},
{
"epoch": 0.0034433866720680576,
"grad_norm": 3.6709742546081543,
"learning_rate": 9.611448774886924e-05,
"loss": 1.7818,
"step": 34
},
{
"epoch": 0.0035446627506582947,
"grad_norm": 3.3729166984558105,
"learning_rate": 9.578866633275288e-05,
"loss": 1.7133,
"step": 35
},
{
"epoch": 0.0036459388292485314,
"grad_norm": 3.6017041206359863,
"learning_rate": 9.545032675245813e-05,
"loss": 1.5988,
"step": 36
},
{
"epoch": 0.0037472149078387686,
"grad_norm": 2.8339967727661133,
"learning_rate": 9.509956150664796e-05,
"loss": 1.7085,
"step": 37
},
{
"epoch": 0.0038484909864290053,
"grad_norm": 5.1753644943237305,
"learning_rate": 9.473646649103818e-05,
"loss": 2.3217,
"step": 38
},
{
"epoch": 0.0039497670650192425,
"grad_norm": 8.048284530639648,
"learning_rate": 9.43611409721806e-05,
"loss": 2.868,
"step": 39
},
{
"epoch": 0.004051043143609479,
"grad_norm": 8.418875694274902,
"learning_rate": 9.397368756032445e-05,
"loss": 3.1661,
"step": 40
},
{
"epoch": 0.004152319222199717,
"grad_norm": 7.274316310882568,
"learning_rate": 9.357421218136386e-05,
"loss": 2.6893,
"step": 41
},
{
"epoch": 0.0042535953007899535,
"grad_norm": 5.224125385284424,
"learning_rate": 9.316282404787871e-05,
"loss": 2.3319,
"step": 42
},
{
"epoch": 0.00435487137938019,
"grad_norm": 6.756013870239258,
"learning_rate": 9.273963562927695e-05,
"loss": 2.4331,
"step": 43
},
{
"epoch": 0.004456147457970428,
"grad_norm": 4.957799911499023,
"learning_rate": 9.230476262104677e-05,
"loss": 2.3517,
"step": 44
},
{
"epoch": 0.0045574235365606645,
"grad_norm": 5.128690719604492,
"learning_rate": 9.185832391312644e-05,
"loss": 2.304,
"step": 45
},
{
"epoch": 0.004658699615150901,
"grad_norm": 8.41048526763916,
"learning_rate": 9.140044155740101e-05,
"loss": 2.8535,
"step": 46
},
{
"epoch": 0.004759975693741138,
"grad_norm": 6.968003273010254,
"learning_rate": 9.093124073433463e-05,
"loss": 2.6746,
"step": 47
},
{
"epoch": 0.0048612517723313755,
"grad_norm": 5.947181224822998,
"learning_rate": 9.045084971874738e-05,
"loss": 2.7757,
"step": 48
},
{
"epoch": 0.004962527850921612,
"grad_norm": 4.515350818634033,
"learning_rate": 8.995939984474624e-05,
"loss": 2.4865,
"step": 49
},
{
"epoch": 0.005063803929511849,
"grad_norm": 5.1472296714782715,
"learning_rate": 8.945702546981969e-05,
"loss": 2.5788,
"step": 50
},
{
"epoch": 0.005063803929511849,
"eval_loss": 2.3614883422851562,
"eval_runtime": 1571.6178,
"eval_samples_per_second": 10.581,
"eval_steps_per_second": 2.646,
"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": 8.63610951696384e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}