bbytxt's picture
Training in progress, step 50, checkpoint
f1990ce verified
raw
history blame
10.1 kB
{
"best_metric": 1.0674021244049072,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.013531341970839958,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00027062683941679914,
"grad_norm": 0.5000702738761902,
"learning_rate": 5.000000000000001e-07,
"loss": 0.8662,
"step": 1
},
{
"epoch": 0.00027062683941679914,
"eval_loss": 1.2486605644226074,
"eval_runtime": 576.5633,
"eval_samples_per_second": 10.795,
"eval_steps_per_second": 2.699,
"step": 1
},
{
"epoch": 0.0005412536788335983,
"grad_norm": 0.7091050744056702,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.8844,
"step": 2
},
{
"epoch": 0.0008118805182503975,
"grad_norm": 0.7198283076286316,
"learning_rate": 1.5e-06,
"loss": 0.8736,
"step": 3
},
{
"epoch": 0.0010825073576671966,
"grad_norm": 0.7402541041374207,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.9226,
"step": 4
},
{
"epoch": 0.0013531341970839958,
"grad_norm": 0.6890178918838501,
"learning_rate": 2.5e-06,
"loss": 0.9618,
"step": 5
},
{
"epoch": 0.001623761036500795,
"grad_norm": 0.7613320350646973,
"learning_rate": 3e-06,
"loss": 0.9509,
"step": 6
},
{
"epoch": 0.001894387875917594,
"grad_norm": 0.8056195378303528,
"learning_rate": 3.5e-06,
"loss": 0.9464,
"step": 7
},
{
"epoch": 0.002165014715334393,
"grad_norm": 0.8153071403503418,
"learning_rate": 4.000000000000001e-06,
"loss": 0.9766,
"step": 8
},
{
"epoch": 0.0024356415547511926,
"grad_norm": 0.8731986284255981,
"learning_rate": 4.5e-06,
"loss": 0.9854,
"step": 9
},
{
"epoch": 0.0027062683941679916,
"grad_norm": 0.8255438804626465,
"learning_rate": 5e-06,
"loss": 1.0802,
"step": 10
},
{
"epoch": 0.0029768952335847906,
"grad_norm": 0.8778969645500183,
"learning_rate": 4.99847706754774e-06,
"loss": 0.9281,
"step": 11
},
{
"epoch": 0.00324752207300159,
"grad_norm": 0.7399764657020569,
"learning_rate": 4.993910125649561e-06,
"loss": 1.0072,
"step": 12
},
{
"epoch": 0.003518148912418389,
"grad_norm": 0.9628943800926208,
"learning_rate": 4.986304738420684e-06,
"loss": 0.9862,
"step": 13
},
{
"epoch": 0.003788775751835188,
"grad_norm": 0.8942387104034424,
"learning_rate": 4.975670171853926e-06,
"loss": 1.0352,
"step": 14
},
{
"epoch": 0.004059402591251988,
"grad_norm": 0.9490991234779358,
"learning_rate": 4.962019382530521e-06,
"loss": 1.0584,
"step": 15
},
{
"epoch": 0.004330029430668786,
"grad_norm": 0.9122024178504944,
"learning_rate": 4.9453690018345144e-06,
"loss": 1.0072,
"step": 16
},
{
"epoch": 0.004600656270085586,
"grad_norm": 0.7996208667755127,
"learning_rate": 4.925739315689991e-06,
"loss": 1.1048,
"step": 17
},
{
"epoch": 0.004871283109502385,
"grad_norm": 0.9378483891487122,
"learning_rate": 4.903154239845798e-06,
"loss": 1.0365,
"step": 18
},
{
"epoch": 0.005141909948919184,
"grad_norm": 0.8539978861808777,
"learning_rate": 4.8776412907378845e-06,
"loss": 0.9979,
"step": 19
},
{
"epoch": 0.005412536788335983,
"grad_norm": 0.9930011630058289,
"learning_rate": 4.849231551964771e-06,
"loss": 1.0151,
"step": 20
},
{
"epoch": 0.005683163627752783,
"grad_norm": 0.9113985300064087,
"learning_rate": 4.817959636416969e-06,
"loss": 1.0266,
"step": 21
},
{
"epoch": 0.005953790467169581,
"grad_norm": 0.9310271739959717,
"learning_rate": 4.783863644106502e-06,
"loss": 0.998,
"step": 22
},
{
"epoch": 0.006224417306586381,
"grad_norm": 1.0234174728393555,
"learning_rate": 4.746985115747918e-06,
"loss": 1.0837,
"step": 23
},
{
"epoch": 0.00649504414600318,
"grad_norm": 0.890159010887146,
"learning_rate": 4.707368982147318e-06,
"loss": 1.0044,
"step": 24
},
{
"epoch": 0.006765670985419979,
"grad_norm": 1.1107178926467896,
"learning_rate": 4.665063509461098e-06,
"loss": 1.1168,
"step": 25
},
{
"epoch": 0.007036297824836778,
"grad_norm": 1.1049308776855469,
"learning_rate": 4.620120240391065e-06,
"loss": 1.1942,
"step": 26
},
{
"epoch": 0.007306924664253578,
"grad_norm": 1.1453604698181152,
"learning_rate": 4.572593931387604e-06,
"loss": 1.0531,
"step": 27
},
{
"epoch": 0.007577551503670376,
"grad_norm": 1.0684839487075806,
"learning_rate": 4.522542485937369e-06,
"loss": 1.0973,
"step": 28
},
{
"epoch": 0.007848178343087176,
"grad_norm": 1.1629831790924072,
"learning_rate": 4.470026884016805e-06,
"loss": 1.0673,
"step": 29
},
{
"epoch": 0.008118805182503975,
"grad_norm": 1.0914651155471802,
"learning_rate": 4.415111107797445e-06,
"loss": 1.1575,
"step": 30
},
{
"epoch": 0.008389432021920775,
"grad_norm": 1.3187044858932495,
"learning_rate": 4.357862063693486e-06,
"loss": 1.223,
"step": 31
},
{
"epoch": 0.008660058861337572,
"grad_norm": 1.2369117736816406,
"learning_rate": 4.2983495008466285e-06,
"loss": 1.1662,
"step": 32
},
{
"epoch": 0.008930685700754372,
"grad_norm": 1.3803397417068481,
"learning_rate": 4.236645926147493e-06,
"loss": 1.1548,
"step": 33
},
{
"epoch": 0.009201312540171171,
"grad_norm": 1.3240615129470825,
"learning_rate": 4.172826515897146e-06,
"loss": 1.1982,
"step": 34
},
{
"epoch": 0.00947193937958797,
"grad_norm": 1.5324469804763794,
"learning_rate": 4.106969024216348e-06,
"loss": 1.1681,
"step": 35
},
{
"epoch": 0.00974256621900477,
"grad_norm": 1.323723554611206,
"learning_rate": 4.039153688314146e-06,
"loss": 1.1543,
"step": 36
},
{
"epoch": 0.01001319305842157,
"grad_norm": 1.5759074687957764,
"learning_rate": 3.969463130731183e-06,
"loss": 1.1227,
"step": 37
},
{
"epoch": 0.010283819897838367,
"grad_norm": 1.6370131969451904,
"learning_rate": 3.897982258676867e-06,
"loss": 1.1549,
"step": 38
},
{
"epoch": 0.010554446737255167,
"grad_norm": 1.5213303565979004,
"learning_rate": 3.824798160583012e-06,
"loss": 1.1308,
"step": 39
},
{
"epoch": 0.010825073576671966,
"grad_norm": 1.753510594367981,
"learning_rate": 3.7500000000000005e-06,
"loss": 1.2172,
"step": 40
},
{
"epoch": 0.011095700416088766,
"grad_norm": 1.6697436571121216,
"learning_rate": 3.6736789069647273e-06,
"loss": 1.1446,
"step": 41
},
{
"epoch": 0.011366327255505565,
"grad_norm": 1.6956145763397217,
"learning_rate": 3.595927866972694e-06,
"loss": 1.0812,
"step": 42
},
{
"epoch": 0.011636954094922363,
"grad_norm": 1.6840723752975464,
"learning_rate": 3.516841607689501e-06,
"loss": 1.1333,
"step": 43
},
{
"epoch": 0.011907580934339163,
"grad_norm": 1.8532711267471313,
"learning_rate": 3.436516483539781e-06,
"loss": 1.2552,
"step": 44
},
{
"epoch": 0.012178207773755962,
"grad_norm": 2.4561421871185303,
"learning_rate": 3.3550503583141726e-06,
"loss": 1.3493,
"step": 45
},
{
"epoch": 0.012448834613172761,
"grad_norm": 2.4903533458709717,
"learning_rate": 3.272542485937369e-06,
"loss": 1.2094,
"step": 46
},
{
"epoch": 0.012719461452589561,
"grad_norm": 3.978550910949707,
"learning_rate": 3.189093389542498e-06,
"loss": 1.508,
"step": 47
},
{
"epoch": 0.01299008829200636,
"grad_norm": 6.7383856773376465,
"learning_rate": 3.1048047389991693e-06,
"loss": 1.5481,
"step": 48
},
{
"epoch": 0.013260715131423158,
"grad_norm": 7.621368885040283,
"learning_rate": 3.019779227044398e-06,
"loss": 1.7839,
"step": 49
},
{
"epoch": 0.013531341970839958,
"grad_norm": 7.821316242218018,
"learning_rate": 2.9341204441673267e-06,
"loss": 1.8119,
"step": 50
},
{
"epoch": 0.013531341970839958,
"eval_loss": 1.0674021244049072,
"eval_runtime": 581.3896,
"eval_samples_per_second": 10.705,
"eval_steps_per_second": 2.676,
"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": 7.688115974465126e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}