prxy5604's picture
Training in progress, step 50, checkpoint
3ec46d4 verified
raw
history blame
9.96 kB
{
"best_metric": 2.5834617614746094,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.008263097008758883,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00016526194017517766,
"grad_norm": 1.594321608543396,
"learning_rate": 1e-05,
"loss": 2.4819,
"step": 1
},
{
"epoch": 0.00016526194017517766,
"eval_loss": 3.2956507205963135,
"eval_runtime": 298.3784,
"eval_samples_per_second": 34.155,
"eval_steps_per_second": 8.539,
"step": 1
},
{
"epoch": 0.0003305238803503553,
"grad_norm": 1.8362373113632202,
"learning_rate": 2e-05,
"loss": 2.474,
"step": 2
},
{
"epoch": 0.0004957858205255329,
"grad_norm": 2.0558102130889893,
"learning_rate": 3e-05,
"loss": 2.5933,
"step": 3
},
{
"epoch": 0.0006610477607007106,
"grad_norm": 1.5579073429107666,
"learning_rate": 4e-05,
"loss": 2.42,
"step": 4
},
{
"epoch": 0.0008263097008758883,
"grad_norm": 2.087095260620117,
"learning_rate": 5e-05,
"loss": 2.5554,
"step": 5
},
{
"epoch": 0.0009915716410510659,
"grad_norm": 2.1744778156280518,
"learning_rate": 6e-05,
"loss": 2.7619,
"step": 6
},
{
"epoch": 0.0011568335812262437,
"grad_norm": 2.49554705619812,
"learning_rate": 7e-05,
"loss": 2.7488,
"step": 7
},
{
"epoch": 0.0013220955214014213,
"grad_norm": 2.244565010070801,
"learning_rate": 8e-05,
"loss": 2.6717,
"step": 8
},
{
"epoch": 0.001487357461576599,
"grad_norm": 1.63128662109375,
"learning_rate": 9e-05,
"loss": 2.5385,
"step": 9
},
{
"epoch": 0.0016526194017517765,
"grad_norm": 1.5725308656692505,
"learning_rate": 0.0001,
"loss": 2.5384,
"step": 10
},
{
"epoch": 0.0018178813419269541,
"grad_norm": 2.130584478378296,
"learning_rate": 9.999316524962345e-05,
"loss": 2.8119,
"step": 11
},
{
"epoch": 0.0019831432821021317,
"grad_norm": 1.7600144147872925,
"learning_rate": 9.997266286704631e-05,
"loss": 2.3037,
"step": 12
},
{
"epoch": 0.0021484052222773093,
"grad_norm": 1.920034646987915,
"learning_rate": 9.993849845741524e-05,
"loss": 2.515,
"step": 13
},
{
"epoch": 0.0023136671624524874,
"grad_norm": 1.5650461912155151,
"learning_rate": 9.989068136093873e-05,
"loss": 2.5834,
"step": 14
},
{
"epoch": 0.002478929102627665,
"grad_norm": 1.933816909790039,
"learning_rate": 9.98292246503335e-05,
"loss": 2.5565,
"step": 15
},
{
"epoch": 0.0026441910428028426,
"grad_norm": 1.9310052394866943,
"learning_rate": 9.975414512725057e-05,
"loss": 2.3907,
"step": 16
},
{
"epoch": 0.00280945298297802,
"grad_norm": 2.0040125846862793,
"learning_rate": 9.966546331768191e-05,
"loss": 2.4109,
"step": 17
},
{
"epoch": 0.002974714923153198,
"grad_norm": 1.7697948217391968,
"learning_rate": 9.956320346634876e-05,
"loss": 2.4493,
"step": 18
},
{
"epoch": 0.0031399768633283754,
"grad_norm": 1.7867257595062256,
"learning_rate": 9.944739353007344e-05,
"loss": 2.6587,
"step": 19
},
{
"epoch": 0.003305238803503553,
"grad_norm": 1.7235246896743774,
"learning_rate": 9.931806517013612e-05,
"loss": 2.4252,
"step": 20
},
{
"epoch": 0.0034705007436787306,
"grad_norm": 1.6747289896011353,
"learning_rate": 9.917525374361912e-05,
"loss": 2.5149,
"step": 21
},
{
"epoch": 0.0036357626838539082,
"grad_norm": 1.5265719890594482,
"learning_rate": 9.901899829374047e-05,
"loss": 2.3857,
"step": 22
},
{
"epoch": 0.0038010246240290863,
"grad_norm": 1.76333749294281,
"learning_rate": 9.884934153917997e-05,
"loss": 2.6925,
"step": 23
},
{
"epoch": 0.0039662865642042635,
"grad_norm": 1.7076408863067627,
"learning_rate": 9.86663298624003e-05,
"loss": 2.5469,
"step": 24
},
{
"epoch": 0.0041315485043794415,
"grad_norm": 1.6395620107650757,
"learning_rate": 9.847001329696653e-05,
"loss": 2.4239,
"step": 25
},
{
"epoch": 0.004296810444554619,
"grad_norm": 1.6570926904678345,
"learning_rate": 9.826044551386744e-05,
"loss": 2.3486,
"step": 26
},
{
"epoch": 0.004462072384729797,
"grad_norm": 1.6805280447006226,
"learning_rate": 9.803768380684242e-05,
"loss": 2.395,
"step": 27
},
{
"epoch": 0.004627334324904975,
"grad_norm": 1.8204387426376343,
"learning_rate": 9.780178907671789e-05,
"loss": 2.4308,
"step": 28
},
{
"epoch": 0.004792596265080152,
"grad_norm": 1.7184354066848755,
"learning_rate": 9.755282581475769e-05,
"loss": 2.3483,
"step": 29
},
{
"epoch": 0.00495785820525533,
"grad_norm": 2.094357490539551,
"learning_rate": 9.729086208503174e-05,
"loss": 2.4923,
"step": 30
},
{
"epoch": 0.005123120145430507,
"grad_norm": 1.8471448421478271,
"learning_rate": 9.701596950580806e-05,
"loss": 2.4706,
"step": 31
},
{
"epoch": 0.005288382085605685,
"grad_norm": 2.124126434326172,
"learning_rate": 9.672822322997305e-05,
"loss": 2.5576,
"step": 32
},
{
"epoch": 0.005453644025780862,
"grad_norm": 1.85663902759552,
"learning_rate": 9.642770192448536e-05,
"loss": 2.4436,
"step": 33
},
{
"epoch": 0.00561890596595604,
"grad_norm": 1.9243381023406982,
"learning_rate": 9.611448774886924e-05,
"loss": 2.7482,
"step": 34
},
{
"epoch": 0.005784167906131218,
"grad_norm": 2.0597476959228516,
"learning_rate": 9.578866633275288e-05,
"loss": 2.5625,
"step": 35
},
{
"epoch": 0.005949429846306396,
"grad_norm": 1.9038246870040894,
"learning_rate": 9.545032675245813e-05,
"loss": 2.6131,
"step": 36
},
{
"epoch": 0.006114691786481574,
"grad_norm": 1.9353429079055786,
"learning_rate": 9.509956150664796e-05,
"loss": 2.4935,
"step": 37
},
{
"epoch": 0.006279953726656751,
"grad_norm": 1.7112752199172974,
"learning_rate": 9.473646649103818e-05,
"loss": 2.6013,
"step": 38
},
{
"epoch": 0.006445215666831929,
"grad_norm": 2.026658535003662,
"learning_rate": 9.43611409721806e-05,
"loss": 2.5474,
"step": 39
},
{
"epoch": 0.006610477607007106,
"grad_norm": 1.8708208799362183,
"learning_rate": 9.397368756032445e-05,
"loss": 2.5254,
"step": 40
},
{
"epoch": 0.006775739547182284,
"grad_norm": 1.9076058864593506,
"learning_rate": 9.357421218136386e-05,
"loss": 2.5782,
"step": 41
},
{
"epoch": 0.006941001487357461,
"grad_norm": 1.8290849924087524,
"learning_rate": 9.316282404787871e-05,
"loss": 2.591,
"step": 42
},
{
"epoch": 0.007106263427532639,
"grad_norm": 2.0316317081451416,
"learning_rate": 9.273963562927695e-05,
"loss": 2.6142,
"step": 43
},
{
"epoch": 0.0072715253677078165,
"grad_norm": 1.8418331146240234,
"learning_rate": 9.230476262104677e-05,
"loss": 2.3819,
"step": 44
},
{
"epoch": 0.0074367873078829945,
"grad_norm": 2.284447431564331,
"learning_rate": 9.185832391312644e-05,
"loss": 2.6443,
"step": 45
},
{
"epoch": 0.007602049248058173,
"grad_norm": 2.4346821308135986,
"learning_rate": 9.140044155740101e-05,
"loss": 2.5674,
"step": 46
},
{
"epoch": 0.00776731118823335,
"grad_norm": 2.468438148498535,
"learning_rate": 9.093124073433463e-05,
"loss": 2.5521,
"step": 47
},
{
"epoch": 0.007932573128408527,
"grad_norm": 2.068291664123535,
"learning_rate": 9.045084971874738e-05,
"loss": 2.391,
"step": 48
},
{
"epoch": 0.008097835068583706,
"grad_norm": 2.661067008972168,
"learning_rate": 8.995939984474624e-05,
"loss": 2.8375,
"step": 49
},
{
"epoch": 0.008263097008758883,
"grad_norm": 2.414609670639038,
"learning_rate": 8.945702546981969e-05,
"loss": 2.7058,
"step": 50
},
{
"epoch": 0.008263097008758883,
"eval_loss": 2.5834617614746094,
"eval_runtime": 298.8144,
"eval_samples_per_second": 34.105,
"eval_steps_per_second": 8.527,
"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": 1.3607236534272e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}