lesso's picture
Training in progress, step 50, checkpoint
ab31708 verified
raw
history blame
9.96 kB
{
"best_metric": 0.20289373397827148,
"best_model_checkpoint": "miner_id_24/checkpoint-50",
"epoch": 0.1272264631043257,
"eval_steps": 50,
"global_step": 50,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.002544529262086514,
"grad_norm": 2.0976202487945557,
"learning_rate": 1.0017e-05,
"loss": 0.4494,
"step": 1
},
{
"epoch": 0.002544529262086514,
"eval_loss": 0.6885223388671875,
"eval_runtime": 10.1676,
"eval_samples_per_second": 16.326,
"eval_steps_per_second": 4.131,
"step": 1
},
{
"epoch": 0.005089058524173028,
"grad_norm": 2.4291188716888428,
"learning_rate": 2.0034e-05,
"loss": 0.4714,
"step": 2
},
{
"epoch": 0.007633587786259542,
"grad_norm": 2.6177380084991455,
"learning_rate": 3.0050999999999997e-05,
"loss": 0.4572,
"step": 3
},
{
"epoch": 0.010178117048346057,
"grad_norm": 2.227078676223755,
"learning_rate": 4.0068e-05,
"loss": 0.3751,
"step": 4
},
{
"epoch": 0.01272264631043257,
"grad_norm": 1.521238923072815,
"learning_rate": 5.0085e-05,
"loss": 0.3044,
"step": 5
},
{
"epoch": 0.015267175572519083,
"grad_norm": 1.3237571716308594,
"learning_rate": 6.0101999999999995e-05,
"loss": 0.2047,
"step": 6
},
{
"epoch": 0.017811704834605598,
"grad_norm": 1.6091803312301636,
"learning_rate": 7.0119e-05,
"loss": 0.1256,
"step": 7
},
{
"epoch": 0.020356234096692113,
"grad_norm": 1.4948714971542358,
"learning_rate": 8.0136e-05,
"loss": 0.1606,
"step": 8
},
{
"epoch": 0.022900763358778626,
"grad_norm": 1.0482193231582642,
"learning_rate": 9.0153e-05,
"loss": 0.1225,
"step": 9
},
{
"epoch": 0.02544529262086514,
"grad_norm": 1.3892583847045898,
"learning_rate": 0.00010017,
"loss": 0.1892,
"step": 10
},
{
"epoch": 0.027989821882951654,
"grad_norm": 1.202789306640625,
"learning_rate": 9.964278947368421e-05,
"loss": 0.1744,
"step": 11
},
{
"epoch": 0.030534351145038167,
"grad_norm": 1.1245602369308472,
"learning_rate": 9.911557894736841e-05,
"loss": 0.0761,
"step": 12
},
{
"epoch": 0.03307888040712468,
"grad_norm": 1.1420965194702148,
"learning_rate": 9.858836842105263e-05,
"loss": 0.0954,
"step": 13
},
{
"epoch": 0.035623409669211195,
"grad_norm": 0.8061597943305969,
"learning_rate": 9.806115789473684e-05,
"loss": 0.1012,
"step": 14
},
{
"epoch": 0.03816793893129771,
"grad_norm": 1.2784687280654907,
"learning_rate": 9.753394736842106e-05,
"loss": 0.1408,
"step": 15
},
{
"epoch": 0.04071246819338423,
"grad_norm": 1.0279990434646606,
"learning_rate": 9.700673684210526e-05,
"loss": 0.1174,
"step": 16
},
{
"epoch": 0.043256997455470736,
"grad_norm": 1.0930790901184082,
"learning_rate": 9.647952631578948e-05,
"loss": 0.0984,
"step": 17
},
{
"epoch": 0.04580152671755725,
"grad_norm": 0.4375361502170563,
"learning_rate": 9.595231578947368e-05,
"loss": 0.0476,
"step": 18
},
{
"epoch": 0.04834605597964377,
"grad_norm": 0.5908359289169312,
"learning_rate": 9.542510526315789e-05,
"loss": 0.0612,
"step": 19
},
{
"epoch": 0.05089058524173028,
"grad_norm": 0.4914228916168213,
"learning_rate": 9.48978947368421e-05,
"loss": 0.0473,
"step": 20
},
{
"epoch": 0.05343511450381679,
"grad_norm": 1.2252209186553955,
"learning_rate": 9.437068421052632e-05,
"loss": 0.1821,
"step": 21
},
{
"epoch": 0.05597964376590331,
"grad_norm": 0.7145554423332214,
"learning_rate": 9.384347368421052e-05,
"loss": 0.0709,
"step": 22
},
{
"epoch": 0.058524173027989825,
"grad_norm": 0.2932605445384979,
"learning_rate": 9.331626315789474e-05,
"loss": 0.021,
"step": 23
},
{
"epoch": 0.061068702290076333,
"grad_norm": 0.628063440322876,
"learning_rate": 9.278905263157894e-05,
"loss": 0.0734,
"step": 24
},
{
"epoch": 0.06361323155216285,
"grad_norm": 0.48500677943229675,
"learning_rate": 9.226184210526316e-05,
"loss": 0.0503,
"step": 25
},
{
"epoch": 0.06615776081424936,
"grad_norm": 0.5622182488441467,
"learning_rate": 9.173463157894736e-05,
"loss": 0.0558,
"step": 26
},
{
"epoch": 0.06870229007633588,
"grad_norm": 0.5120857357978821,
"learning_rate": 9.120742105263159e-05,
"loss": 0.045,
"step": 27
},
{
"epoch": 0.07124681933842239,
"grad_norm": 0.12333207577466965,
"learning_rate": 9.068021052631579e-05,
"loss": 0.0056,
"step": 28
},
{
"epoch": 0.0737913486005089,
"grad_norm": 0.8002417087554932,
"learning_rate": 9.0153e-05,
"loss": 0.1115,
"step": 29
},
{
"epoch": 0.07633587786259542,
"grad_norm": 3.1628360748291016,
"learning_rate": 8.96257894736842e-05,
"loss": 0.661,
"step": 30
},
{
"epoch": 0.07888040712468193,
"grad_norm": 1.9972189664840698,
"learning_rate": 8.909857894736842e-05,
"loss": 0.3344,
"step": 31
},
{
"epoch": 0.08142493638676845,
"grad_norm": 1.6704767942428589,
"learning_rate": 8.857136842105263e-05,
"loss": 0.3315,
"step": 32
},
{
"epoch": 0.08396946564885496,
"grad_norm": 1.8845316171646118,
"learning_rate": 8.804415789473684e-05,
"loss": 0.3487,
"step": 33
},
{
"epoch": 0.08651399491094147,
"grad_norm": 2.4319205284118652,
"learning_rate": 8.751694736842105e-05,
"loss": 0.3297,
"step": 34
},
{
"epoch": 0.089058524173028,
"grad_norm": 2.7092981338500977,
"learning_rate": 8.698973684210527e-05,
"loss": 0.5175,
"step": 35
},
{
"epoch": 0.0916030534351145,
"grad_norm": 1.65862238407135,
"learning_rate": 8.646252631578948e-05,
"loss": 0.3395,
"step": 36
},
{
"epoch": 0.09414758269720101,
"grad_norm": 1.9453610181808472,
"learning_rate": 8.593531578947368e-05,
"loss": 0.3279,
"step": 37
},
{
"epoch": 0.09669211195928754,
"grad_norm": 1.8823449611663818,
"learning_rate": 8.54081052631579e-05,
"loss": 0.3059,
"step": 38
},
{
"epoch": 0.09923664122137404,
"grad_norm": 1.427621603012085,
"learning_rate": 8.48808947368421e-05,
"loss": 0.2756,
"step": 39
},
{
"epoch": 0.10178117048346055,
"grad_norm": 1.9383624792099,
"learning_rate": 8.435368421052631e-05,
"loss": 0.3652,
"step": 40
},
{
"epoch": 0.10432569974554708,
"grad_norm": 0.5723309516906738,
"learning_rate": 8.382647368421053e-05,
"loss": 0.0681,
"step": 41
},
{
"epoch": 0.10687022900763359,
"grad_norm": 1.692962884902954,
"learning_rate": 8.329926315789474e-05,
"loss": 0.2737,
"step": 42
},
{
"epoch": 0.10941475826972011,
"grad_norm": 5.488102436065674,
"learning_rate": 8.277205263157894e-05,
"loss": 0.3806,
"step": 43
},
{
"epoch": 0.11195928753180662,
"grad_norm": 2.793001890182495,
"learning_rate": 8.224484210526316e-05,
"loss": 0.3236,
"step": 44
},
{
"epoch": 0.11450381679389313,
"grad_norm": 0.8564298152923584,
"learning_rate": 8.171763157894736e-05,
"loss": 0.0697,
"step": 45
},
{
"epoch": 0.11704834605597965,
"grad_norm": 1.465958595275879,
"learning_rate": 8.119042105263158e-05,
"loss": 0.1509,
"step": 46
},
{
"epoch": 0.11959287531806616,
"grad_norm": 1.0620710849761963,
"learning_rate": 8.066321052631578e-05,
"loss": 0.0998,
"step": 47
},
{
"epoch": 0.12213740458015267,
"grad_norm": 0.551638126373291,
"learning_rate": 8.0136e-05,
"loss": 0.0336,
"step": 48
},
{
"epoch": 0.12468193384223919,
"grad_norm": 1.185890555381775,
"learning_rate": 7.960878947368421e-05,
"loss": 0.0431,
"step": 49
},
{
"epoch": 0.1272264631043257,
"grad_norm": 0.4987131953239441,
"learning_rate": 7.908157894736842e-05,
"loss": 0.017,
"step": 50
},
{
"epoch": 0.1272264631043257,
"eval_loss": 0.20289373397827148,
"eval_runtime": 10.1481,
"eval_samples_per_second": 16.358,
"eval_steps_per_second": 4.139,
"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": 8419190243328000.0,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}