nttx's picture
Training in progress, step 50, checkpoint
a08796b verified
raw
history blame
9.99 kB
{
"best_metric": 0.852555513381958,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.25773195876288657,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.005154639175257732,
"grad_norm": 0.35949328541755676,
"learning_rate": 5.000000000000001e-07,
"loss": 0.7545,
"step": 1
},
{
"epoch": 0.005154639175257732,
"eval_loss": 1.1052348613739014,
"eval_runtime": 30.1244,
"eval_samples_per_second": 10.855,
"eval_steps_per_second": 1.361,
"step": 1
},
{
"epoch": 0.010309278350515464,
"grad_norm": 0.45567527413368225,
"learning_rate": 1.0000000000000002e-06,
"loss": 0.7432,
"step": 2
},
{
"epoch": 0.015463917525773196,
"grad_norm": 0.5274704694747925,
"learning_rate": 1.5e-06,
"loss": 0.8322,
"step": 3
},
{
"epoch": 0.020618556701030927,
"grad_norm": 0.5776087045669556,
"learning_rate": 2.0000000000000003e-06,
"loss": 0.7875,
"step": 4
},
{
"epoch": 0.02577319587628866,
"grad_norm": 0.6656889915466309,
"learning_rate": 2.5e-06,
"loss": 0.8479,
"step": 5
},
{
"epoch": 0.030927835051546393,
"grad_norm": 0.6724861860275269,
"learning_rate": 3e-06,
"loss": 0.9279,
"step": 6
},
{
"epoch": 0.03608247422680412,
"grad_norm": 0.785415530204773,
"learning_rate": 3.5e-06,
"loss": 0.8712,
"step": 7
},
{
"epoch": 0.041237113402061855,
"grad_norm": 0.7006766200065613,
"learning_rate": 4.000000000000001e-06,
"loss": 0.7866,
"step": 8
},
{
"epoch": 0.04639175257731959,
"grad_norm": 0.9407919645309448,
"learning_rate": 4.5e-06,
"loss": 0.8717,
"step": 9
},
{
"epoch": 0.05154639175257732,
"grad_norm": 0.6719709038734436,
"learning_rate": 5e-06,
"loss": 0.8558,
"step": 10
},
{
"epoch": 0.05670103092783505,
"grad_norm": 0.6967365145683289,
"learning_rate": 4.99847706754774e-06,
"loss": 0.8185,
"step": 11
},
{
"epoch": 0.061855670103092786,
"grad_norm": 0.666429877281189,
"learning_rate": 4.993910125649561e-06,
"loss": 0.9746,
"step": 12
},
{
"epoch": 0.06701030927835051,
"grad_norm": 0.687868595123291,
"learning_rate": 4.986304738420684e-06,
"loss": 0.8567,
"step": 13
},
{
"epoch": 0.07216494845360824,
"grad_norm": 0.7461718916893005,
"learning_rate": 4.975670171853926e-06,
"loss": 0.8906,
"step": 14
},
{
"epoch": 0.07731958762886598,
"grad_norm": 0.7825281023979187,
"learning_rate": 4.962019382530521e-06,
"loss": 0.8898,
"step": 15
},
{
"epoch": 0.08247422680412371,
"grad_norm": 0.8114840984344482,
"learning_rate": 4.9453690018345144e-06,
"loss": 0.9206,
"step": 16
},
{
"epoch": 0.08762886597938144,
"grad_norm": 0.8150220513343811,
"learning_rate": 4.925739315689991e-06,
"loss": 0.8875,
"step": 17
},
{
"epoch": 0.09278350515463918,
"grad_norm": 0.7087549567222595,
"learning_rate": 4.903154239845798e-06,
"loss": 0.9555,
"step": 18
},
{
"epoch": 0.0979381443298969,
"grad_norm": 0.8564397692680359,
"learning_rate": 4.8776412907378845e-06,
"loss": 0.9177,
"step": 19
},
{
"epoch": 0.10309278350515463,
"grad_norm": 0.7236621975898743,
"learning_rate": 4.849231551964771e-06,
"loss": 0.8545,
"step": 20
},
{
"epoch": 0.10824742268041238,
"grad_norm": 0.8788579106330872,
"learning_rate": 4.817959636416969e-06,
"loss": 0.9195,
"step": 21
},
{
"epoch": 0.1134020618556701,
"grad_norm": 0.8592295050621033,
"learning_rate": 4.783863644106502e-06,
"loss": 0.9803,
"step": 22
},
{
"epoch": 0.11855670103092783,
"grad_norm": 0.8085874915122986,
"learning_rate": 4.746985115747918e-06,
"loss": 0.9333,
"step": 23
},
{
"epoch": 0.12371134020618557,
"grad_norm": 1.5814393758773804,
"learning_rate": 4.707368982147318e-06,
"loss": 0.9284,
"step": 24
},
{
"epoch": 0.12886597938144329,
"grad_norm": 0.925155758857727,
"learning_rate": 4.665063509461098e-06,
"loss": 1.0185,
"step": 25
},
{
"epoch": 0.13402061855670103,
"grad_norm": 1.0410577058792114,
"learning_rate": 4.620120240391065e-06,
"loss": 0.8878,
"step": 26
},
{
"epoch": 0.13917525773195877,
"grad_norm": 1.2917616367340088,
"learning_rate": 4.572593931387604e-06,
"loss": 0.9616,
"step": 27
},
{
"epoch": 0.14432989690721648,
"grad_norm": 0.9885799884796143,
"learning_rate": 4.522542485937369e-06,
"loss": 0.8762,
"step": 28
},
{
"epoch": 0.14948453608247422,
"grad_norm": 1.0929198265075684,
"learning_rate": 4.470026884016805e-06,
"loss": 1.0202,
"step": 29
},
{
"epoch": 0.15463917525773196,
"grad_norm": 1.0404047966003418,
"learning_rate": 4.415111107797445e-06,
"loss": 0.9885,
"step": 30
},
{
"epoch": 0.15979381443298968,
"grad_norm": 1.0854883193969727,
"learning_rate": 4.357862063693486e-06,
"loss": 0.9228,
"step": 31
},
{
"epoch": 0.16494845360824742,
"grad_norm": 1.257588267326355,
"learning_rate": 4.2983495008466285e-06,
"loss": 0.9343,
"step": 32
},
{
"epoch": 0.17010309278350516,
"grad_norm": 1.0686402320861816,
"learning_rate": 4.236645926147493e-06,
"loss": 0.9171,
"step": 33
},
{
"epoch": 0.17525773195876287,
"grad_norm": 1.2666049003601074,
"learning_rate": 4.172826515897146e-06,
"loss": 0.9904,
"step": 34
},
{
"epoch": 0.18041237113402062,
"grad_norm": 1.3324109315872192,
"learning_rate": 4.106969024216348e-06,
"loss": 1.0908,
"step": 35
},
{
"epoch": 0.18556701030927836,
"grad_norm": 1.1834466457366943,
"learning_rate": 4.039153688314146e-06,
"loss": 0.905,
"step": 36
},
{
"epoch": 0.19072164948453607,
"grad_norm": 1.5354310274124146,
"learning_rate": 3.969463130731183e-06,
"loss": 1.0866,
"step": 37
},
{
"epoch": 0.1958762886597938,
"grad_norm": 1.3238235712051392,
"learning_rate": 3.897982258676867e-06,
"loss": 1.0469,
"step": 38
},
{
"epoch": 0.20103092783505155,
"grad_norm": 1.776808261871338,
"learning_rate": 3.824798160583012e-06,
"loss": 1.1054,
"step": 39
},
{
"epoch": 0.20618556701030927,
"grad_norm": 1.812841534614563,
"learning_rate": 3.7500000000000005e-06,
"loss": 0.9541,
"step": 40
},
{
"epoch": 0.211340206185567,
"grad_norm": 1.7133516073226929,
"learning_rate": 3.6736789069647273e-06,
"loss": 0.9837,
"step": 41
},
{
"epoch": 0.21649484536082475,
"grad_norm": 2.0302529335021973,
"learning_rate": 3.595927866972694e-06,
"loss": 1.0123,
"step": 42
},
{
"epoch": 0.22164948453608246,
"grad_norm": 1.8799409866333008,
"learning_rate": 3.516841607689501e-06,
"loss": 1.1035,
"step": 43
},
{
"epoch": 0.2268041237113402,
"grad_norm": 2.289742946624756,
"learning_rate": 3.436516483539781e-06,
"loss": 1.1235,
"step": 44
},
{
"epoch": 0.23195876288659795,
"grad_norm": 2.045342445373535,
"learning_rate": 3.3550503583141726e-06,
"loss": 1.0909,
"step": 45
},
{
"epoch": 0.23711340206185566,
"grad_norm": 2.1356890201568604,
"learning_rate": 3.272542485937369e-06,
"loss": 1.1785,
"step": 46
},
{
"epoch": 0.2422680412371134,
"grad_norm": 2.7677886486053467,
"learning_rate": 3.189093389542498e-06,
"loss": 1.2987,
"step": 47
},
{
"epoch": 0.24742268041237114,
"grad_norm": 3.38108491897583,
"learning_rate": 3.1048047389991693e-06,
"loss": 1.2262,
"step": 48
},
{
"epoch": 0.25257731958762886,
"grad_norm": 0.44239917397499084,
"learning_rate": 3.019779227044398e-06,
"loss": 0.7028,
"step": 49
},
{
"epoch": 0.25773195876288657,
"grad_norm": 0.610641598701477,
"learning_rate": 2.9341204441673267e-06,
"loss": 0.7112,
"step": 50
},
{
"epoch": 0.25773195876288657,
"eval_loss": 0.852555513381958,
"eval_runtime": 29.9863,
"eval_samples_per_second": 10.905,
"eval_steps_per_second": 1.367,
"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": 8.523101719914086e+16,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}