0x1202's picture
Training in progress, step 50, checkpoint
cd8144c verified
raw
history blame
9.84 kB
{
"best_metric": 0.2451000064611435,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.003562776115148924,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 7.125552230297848e-05,
"grad_norm": 1.042211651802063,
"learning_rate": 1e-06,
"loss": 0.3057,
"step": 1
},
{
"epoch": 7.125552230297848e-05,
"eval_loss": 0.7187018990516663,
"eval_runtime": 728.4647,
"eval_samples_per_second": 8.112,
"eval_steps_per_second": 2.029,
"step": 1
},
{
"epoch": 0.00014251104460595695,
"grad_norm": 1.606184959411621,
"learning_rate": 2e-06,
"loss": 0.4561,
"step": 2
},
{
"epoch": 0.00021376656690893543,
"grad_norm": 1.5126073360443115,
"learning_rate": 3e-06,
"loss": 0.4418,
"step": 3
},
{
"epoch": 0.0002850220892119139,
"grad_norm": 1.9431225061416626,
"learning_rate": 4e-06,
"loss": 0.5693,
"step": 4
},
{
"epoch": 0.0003562776115148924,
"grad_norm": 1.9813414812088013,
"learning_rate": 4.9999999999999996e-06,
"loss": 0.5906,
"step": 5
},
{
"epoch": 0.00042753313381787086,
"grad_norm": 1.8735884428024292,
"learning_rate": 6e-06,
"loss": 0.4769,
"step": 6
},
{
"epoch": 0.0004987886561208494,
"grad_norm": 1.8006073236465454,
"learning_rate": 7e-06,
"loss": 0.5359,
"step": 7
},
{
"epoch": 0.0005700441784238278,
"grad_norm": 1.539935827255249,
"learning_rate": 8e-06,
"loss": 0.4696,
"step": 8
},
{
"epoch": 0.0006412997007268063,
"grad_norm": 2.0199615955352783,
"learning_rate": 9e-06,
"loss": 0.5917,
"step": 9
},
{
"epoch": 0.0007125552230297848,
"grad_norm": 1.9582463502883911,
"learning_rate": 9.999999999999999e-06,
"loss": 0.4258,
"step": 10
},
{
"epoch": 0.0007838107453327633,
"grad_norm": 1.63983952999115,
"learning_rate": 1.1e-05,
"loss": 0.3967,
"step": 11
},
{
"epoch": 0.0008550662676357417,
"grad_norm": 1.615180253982544,
"learning_rate": 1.2e-05,
"loss": 0.4462,
"step": 12
},
{
"epoch": 0.0009263217899387203,
"grad_norm": 1.6889790296554565,
"learning_rate": 1.3000000000000001e-05,
"loss": 0.3865,
"step": 13
},
{
"epoch": 0.0009975773122416988,
"grad_norm": 1.7628371715545654,
"learning_rate": 1.4e-05,
"loss": 0.5235,
"step": 14
},
{
"epoch": 0.0010688328345446773,
"grad_norm": 1.7251651287078857,
"learning_rate": 1.5e-05,
"loss": 0.2985,
"step": 15
},
{
"epoch": 0.0011400883568476556,
"grad_norm": 1.7641141414642334,
"learning_rate": 1.6e-05,
"loss": 0.4062,
"step": 16
},
{
"epoch": 0.0012113438791506342,
"grad_norm": 1.7730730772018433,
"learning_rate": 1.7e-05,
"loss": 0.2535,
"step": 17
},
{
"epoch": 0.0012825994014536127,
"grad_norm": 1.6763519048690796,
"learning_rate": 1.8e-05,
"loss": 0.2611,
"step": 18
},
{
"epoch": 0.0013538549237565912,
"grad_norm": 1.8056228160858154,
"learning_rate": 1.9e-05,
"loss": 0.3504,
"step": 19
},
{
"epoch": 0.0014251104460595695,
"grad_norm": 1.7897692918777466,
"learning_rate": 1.9999999999999998e-05,
"loss": 0.2584,
"step": 20
},
{
"epoch": 0.001496365968362548,
"grad_norm": 1.8470932245254517,
"learning_rate": 2.1e-05,
"loss": 0.2949,
"step": 21
},
{
"epoch": 0.0015676214906655266,
"grad_norm": 1.2270846366882324,
"learning_rate": 2.2e-05,
"loss": 0.2835,
"step": 22
},
{
"epoch": 0.0016388770129685051,
"grad_norm": 1.2478747367858887,
"learning_rate": 2.3000000000000003e-05,
"loss": 0.2585,
"step": 23
},
{
"epoch": 0.0017101325352714834,
"grad_norm": 1.7448375225067139,
"learning_rate": 2.4e-05,
"loss": 0.3246,
"step": 24
},
{
"epoch": 0.001781388057574462,
"grad_norm": 1.377163290977478,
"learning_rate": 2.5e-05,
"loss": 0.1817,
"step": 25
},
{
"epoch": 0.0018526435798774405,
"grad_norm": 1.6893903017044067,
"learning_rate": 2.6000000000000002e-05,
"loss": 0.2882,
"step": 26
},
{
"epoch": 0.001923899102180419,
"grad_norm": 1.412766456604004,
"learning_rate": 2.7000000000000002e-05,
"loss": 0.293,
"step": 27
},
{
"epoch": 0.0019951546244833976,
"grad_norm": 1.3407995700836182,
"learning_rate": 2.8e-05,
"loss": 0.1812,
"step": 28
},
{
"epoch": 0.002066410146786376,
"grad_norm": 1.8757520914077759,
"learning_rate": 2.9e-05,
"loss": 0.2906,
"step": 29
},
{
"epoch": 0.0021376656690893546,
"grad_norm": 1.1567577123641968,
"learning_rate": 3e-05,
"loss": 0.2146,
"step": 30
},
{
"epoch": 0.002208921191392333,
"grad_norm": 1.3666956424713135,
"learning_rate": 2.9984895998119723e-05,
"loss": 0.1976,
"step": 31
},
{
"epoch": 0.0022801767136953113,
"grad_norm": 1.3091264963150024,
"learning_rate": 2.993961440992859e-05,
"loss": 0.1436,
"step": 32
},
{
"epoch": 0.00235143223599829,
"grad_norm": 1.0269235372543335,
"learning_rate": 2.9864246426519023e-05,
"loss": 0.1848,
"step": 33
},
{
"epoch": 0.0024226877583012683,
"grad_norm": 1.5328474044799805,
"learning_rate": 2.9758943828979444e-05,
"loss": 0.2269,
"step": 34
},
{
"epoch": 0.0024939432806042466,
"grad_norm": 1.4854594469070435,
"learning_rate": 2.9623918682727355e-05,
"loss": 0.1739,
"step": 35
},
{
"epoch": 0.0025651988029072254,
"grad_norm": 1.223655104637146,
"learning_rate": 2.9459442910437798e-05,
"loss": 0.1476,
"step": 36
},
{
"epoch": 0.0026364543252102037,
"grad_norm": 1.455477237701416,
"learning_rate": 2.9265847744427305e-05,
"loss": 0.1762,
"step": 37
},
{
"epoch": 0.0027077098475131824,
"grad_norm": 1.223581075668335,
"learning_rate": 2.904352305959606e-05,
"loss": 0.1392,
"step": 38
},
{
"epoch": 0.0027789653698161608,
"grad_norm": 1.1783467531204224,
"learning_rate": 2.8792916588271762e-05,
"loss": 0.1729,
"step": 39
},
{
"epoch": 0.002850220892119139,
"grad_norm": 1.8590701818466187,
"learning_rate": 2.8514533018536286e-05,
"loss": 0.3492,
"step": 40
},
{
"epoch": 0.002921476414422118,
"grad_norm": 1.1538301706314087,
"learning_rate": 2.820893297785107e-05,
"loss": 0.1841,
"step": 41
},
{
"epoch": 0.002992731936725096,
"grad_norm": 1.5694233179092407,
"learning_rate": 2.7876731904027994e-05,
"loss": 0.2156,
"step": 42
},
{
"epoch": 0.003063987459028075,
"grad_norm": 1.357988953590393,
"learning_rate": 2.7518598805819542e-05,
"loss": 0.2037,
"step": 43
},
{
"epoch": 0.003135242981331053,
"grad_norm": 1.150630235671997,
"learning_rate": 2.7135254915624213e-05,
"loss": 0.1607,
"step": 44
},
{
"epoch": 0.0032064985036340315,
"grad_norm": 1.2249001264572144,
"learning_rate": 2.672747223702045e-05,
"loss": 0.2267,
"step": 45
},
{
"epoch": 0.0032777540259370103,
"grad_norm": 1.1600937843322754,
"learning_rate": 2.6296071990054167e-05,
"loss": 0.1363,
"step": 46
},
{
"epoch": 0.0033490095482399886,
"grad_norm": 1.2449615001678467,
"learning_rate": 2.5841922957410875e-05,
"loss": 0.2024,
"step": 47
},
{
"epoch": 0.003420265070542967,
"grad_norm": 1.292077660560608,
"learning_rate": 2.5365939734802973e-05,
"loss": 0.1311,
"step": 48
},
{
"epoch": 0.0034915205928459456,
"grad_norm": 1.2999500036239624,
"learning_rate": 2.4869080889095693e-05,
"loss": 0.1977,
"step": 49
},
{
"epoch": 0.003562776115148924,
"grad_norm": 1.0472160577774048,
"learning_rate": 2.4352347027881003e-05,
"loss": 0.1228,
"step": 50
},
{
"epoch": 0.003562776115148924,
"eval_loss": 0.2451000064611435,
"eval_runtime": 732.9403,
"eval_samples_per_second": 8.062,
"eval_steps_per_second": 2.017,
"step": 50
}
],
"logging_steps": 1,
"max_steps": 100,
"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": 1.904498393166643e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}