blood34's picture
Training in progress, step 50, checkpoint
d5a2409 verified
raw
history blame
9.96 kB
{
"best_metric": 1.9447404146194458,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.016874789065136685,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0003374957813027337,
"grad_norm": 0.659518837928772,
"learning_rate": 1e-05,
"loss": 1.7311,
"step": 1
},
{
"epoch": 0.0003374957813027337,
"eval_loss": 2.9957451820373535,
"eval_runtime": 115.497,
"eval_samples_per_second": 43.205,
"eval_steps_per_second": 10.805,
"step": 1
},
{
"epoch": 0.0006749915626054674,
"grad_norm": 0.7038252353668213,
"learning_rate": 2e-05,
"loss": 1.9467,
"step": 2
},
{
"epoch": 0.0010124873439082012,
"grad_norm": 0.7937076091766357,
"learning_rate": 3e-05,
"loss": 2.1449,
"step": 3
},
{
"epoch": 0.0013499831252109348,
"grad_norm": 0.7090626955032349,
"learning_rate": 4e-05,
"loss": 2.052,
"step": 4
},
{
"epoch": 0.0016874789065136687,
"grad_norm": 0.7988624572753906,
"learning_rate": 5e-05,
"loss": 2.3878,
"step": 5
},
{
"epoch": 0.0020249746878164025,
"grad_norm": 0.9716485738754272,
"learning_rate": 6e-05,
"loss": 2.1794,
"step": 6
},
{
"epoch": 0.002362470469119136,
"grad_norm": 0.8470109105110168,
"learning_rate": 7e-05,
"loss": 2.2386,
"step": 7
},
{
"epoch": 0.0026999662504218697,
"grad_norm": 0.7678182125091553,
"learning_rate": 8e-05,
"loss": 2.2977,
"step": 8
},
{
"epoch": 0.0030374620317246033,
"grad_norm": 0.7406213283538818,
"learning_rate": 9e-05,
"loss": 2.2716,
"step": 9
},
{
"epoch": 0.0033749578130273373,
"grad_norm": 0.6096116304397583,
"learning_rate": 0.0001,
"loss": 2.4181,
"step": 10
},
{
"epoch": 0.003712453594330071,
"grad_norm": 0.6520525217056274,
"learning_rate": 9.999316524962345e-05,
"loss": 2.0193,
"step": 11
},
{
"epoch": 0.004049949375632805,
"grad_norm": 0.5647959113121033,
"learning_rate": 9.997266286704631e-05,
"loss": 2.1552,
"step": 12
},
{
"epoch": 0.004387445156935539,
"grad_norm": 0.7149708271026611,
"learning_rate": 9.993849845741524e-05,
"loss": 2.3396,
"step": 13
},
{
"epoch": 0.004724940938238272,
"grad_norm": 0.6472476720809937,
"learning_rate": 9.989068136093873e-05,
"loss": 2.1707,
"step": 14
},
{
"epoch": 0.005062436719541006,
"grad_norm": 0.7469307780265808,
"learning_rate": 9.98292246503335e-05,
"loss": 2.3344,
"step": 15
},
{
"epoch": 0.005399932500843739,
"grad_norm": 0.5477833151817322,
"learning_rate": 9.975414512725057e-05,
"loss": 2.1046,
"step": 16
},
{
"epoch": 0.005737428282146473,
"grad_norm": 0.6585941314697266,
"learning_rate": 9.966546331768191e-05,
"loss": 2.26,
"step": 17
},
{
"epoch": 0.006074924063449207,
"grad_norm": 0.6190670728683472,
"learning_rate": 9.956320346634876e-05,
"loss": 2.1344,
"step": 18
},
{
"epoch": 0.00641241984475194,
"grad_norm": 0.5457659363746643,
"learning_rate": 9.944739353007344e-05,
"loss": 2.1121,
"step": 19
},
{
"epoch": 0.006749915626054675,
"grad_norm": 0.48350393772125244,
"learning_rate": 9.931806517013612e-05,
"loss": 1.9028,
"step": 20
},
{
"epoch": 0.007087411407357408,
"grad_norm": 0.6461214423179626,
"learning_rate": 9.917525374361912e-05,
"loss": 2.166,
"step": 21
},
{
"epoch": 0.007424907188660142,
"grad_norm": 0.6612595319747925,
"learning_rate": 9.901899829374047e-05,
"loss": 2.2152,
"step": 22
},
{
"epoch": 0.0077624029699628755,
"grad_norm": 0.5887338519096375,
"learning_rate": 9.884934153917997e-05,
"loss": 2.0533,
"step": 23
},
{
"epoch": 0.00809989875126561,
"grad_norm": 0.5120691657066345,
"learning_rate": 9.86663298624003e-05,
"loss": 2.1555,
"step": 24
},
{
"epoch": 0.008437394532568343,
"grad_norm": 0.5528091788291931,
"learning_rate": 9.847001329696653e-05,
"loss": 2.2499,
"step": 25
},
{
"epoch": 0.008774890313871077,
"grad_norm": 0.6201184391975403,
"learning_rate": 9.826044551386744e-05,
"loss": 2.1444,
"step": 26
},
{
"epoch": 0.00911238609517381,
"grad_norm": 0.6279026865959167,
"learning_rate": 9.803768380684242e-05,
"loss": 2.2847,
"step": 27
},
{
"epoch": 0.009449881876476544,
"grad_norm": 0.6332525014877319,
"learning_rate": 9.780178907671789e-05,
"loss": 1.958,
"step": 28
},
{
"epoch": 0.009787377657779277,
"grad_norm": 0.569353461265564,
"learning_rate": 9.755282581475769e-05,
"loss": 2.1134,
"step": 29
},
{
"epoch": 0.010124873439082012,
"grad_norm": 0.5256232619285583,
"learning_rate": 9.729086208503174e-05,
"loss": 1.9178,
"step": 30
},
{
"epoch": 0.010462369220384746,
"grad_norm": 0.5967089533805847,
"learning_rate": 9.701596950580806e-05,
"loss": 2.3453,
"step": 31
},
{
"epoch": 0.010799865001687479,
"grad_norm": 0.6425303816795349,
"learning_rate": 9.672822322997305e-05,
"loss": 2.1351,
"step": 32
},
{
"epoch": 0.011137360782990213,
"grad_norm": 0.5986398458480835,
"learning_rate": 9.642770192448536e-05,
"loss": 2.3019,
"step": 33
},
{
"epoch": 0.011474856564292946,
"grad_norm": 0.5946639180183411,
"learning_rate": 9.611448774886924e-05,
"loss": 2.2574,
"step": 34
},
{
"epoch": 0.01181235234559568,
"grad_norm": 0.6006338000297546,
"learning_rate": 9.578866633275288e-05,
"loss": 2.3178,
"step": 35
},
{
"epoch": 0.012149848126898413,
"grad_norm": 0.5436823964118958,
"learning_rate": 9.545032675245813e-05,
"loss": 2.2969,
"step": 36
},
{
"epoch": 0.012487343908201148,
"grad_norm": 0.589877724647522,
"learning_rate": 9.509956150664796e-05,
"loss": 2.4032,
"step": 37
},
{
"epoch": 0.01282483968950388,
"grad_norm": 0.5993760228157043,
"learning_rate": 9.473646649103818e-05,
"loss": 2.3421,
"step": 38
},
{
"epoch": 0.013162335470806615,
"grad_norm": 0.5923803448677063,
"learning_rate": 9.43611409721806e-05,
"loss": 2.3048,
"step": 39
},
{
"epoch": 0.01349983125210935,
"grad_norm": 0.6783635020256042,
"learning_rate": 9.397368756032445e-05,
"loss": 2.3467,
"step": 40
},
{
"epoch": 0.013837327033412082,
"grad_norm": 0.5711936354637146,
"learning_rate": 9.357421218136386e-05,
"loss": 2.3039,
"step": 41
},
{
"epoch": 0.014174822814714817,
"grad_norm": 0.6027695536613464,
"learning_rate": 9.316282404787871e-05,
"loss": 2.2872,
"step": 42
},
{
"epoch": 0.01451231859601755,
"grad_norm": 0.6241564750671387,
"learning_rate": 9.273963562927695e-05,
"loss": 2.313,
"step": 43
},
{
"epoch": 0.014849814377320284,
"grad_norm": 0.6565014123916626,
"learning_rate": 9.230476262104677e-05,
"loss": 2.3402,
"step": 44
},
{
"epoch": 0.015187310158623017,
"grad_norm": 0.6258305311203003,
"learning_rate": 9.185832391312644e-05,
"loss": 2.2641,
"step": 45
},
{
"epoch": 0.015524805939925751,
"grad_norm": 0.6962496042251587,
"learning_rate": 9.140044155740101e-05,
"loss": 2.5017,
"step": 46
},
{
"epoch": 0.015862301721228485,
"grad_norm": 0.643883466720581,
"learning_rate": 9.093124073433463e-05,
"loss": 2.4286,
"step": 47
},
{
"epoch": 0.01619979750253122,
"grad_norm": 0.6366576552391052,
"learning_rate": 9.045084971874738e-05,
"loss": 2.3306,
"step": 48
},
{
"epoch": 0.01653729328383395,
"grad_norm": 0.723232090473175,
"learning_rate": 8.995939984474624e-05,
"loss": 2.4223,
"step": 49
},
{
"epoch": 0.016874789065136685,
"grad_norm": 0.8257110118865967,
"learning_rate": 8.945702546981969e-05,
"loss": 2.3262,
"step": 50
},
{
"epoch": 0.016874789065136685,
"eval_loss": 1.9447404146194458,
"eval_runtime": 114.5205,
"eval_samples_per_second": 43.573,
"eval_steps_per_second": 10.898,
"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": 3434439770112000.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}