FormlessAI's picture
Upload folder using huggingface_hub
df708a8 verified
Raw
History Blame Contribute Delete
8.44 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 42,
"global_step": 42,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.047619047619047616,
"grad_norm": 1.8468271493911743,
"learning_rate": 1e-05,
"loss": 1.087890625,
"step": 1
},
{
"epoch": 0.09523809523809523,
"grad_norm": 1.7420322895050049,
"learning_rate": 9.986018985905901e-06,
"loss": 1.037109375,
"step": 2
},
{
"epoch": 0.14285714285714285,
"grad_norm": 1.560319185256958,
"learning_rate": 9.944154131125643e-06,
"loss": 0.974609375,
"step": 3
},
{
"epoch": 0.19047619047619047,
"grad_norm": 1.3724197149276733,
"learning_rate": 9.874639560909118e-06,
"loss": 0.91650390625,
"step": 4
},
{
"epoch": 0.23809523809523808,
"grad_norm": 1.0526386499404907,
"learning_rate": 9.777864028930705e-06,
"loss": 0.79443359375,
"step": 5
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.8902638554573059,
"learning_rate": 9.654368743221022e-06,
"loss": 0.6953125,
"step": 6
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.9359312653541565,
"learning_rate": 9.504844339512096e-06,
"loss": 0.669921875,
"step": 7
},
{
"epoch": 0.38095238095238093,
"grad_norm": 0.8327934741973877,
"learning_rate": 9.330127018922195e-06,
"loss": 0.592529296875,
"step": 8
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.6353632807731628,
"learning_rate": 9.131193871579975e-06,
"loss": 0.53076171875,
"step": 9
},
{
"epoch": 0.47619047619047616,
"grad_norm": 0.8587208390235901,
"learning_rate": 8.90915741234015e-06,
"loss": 0.510986328125,
"step": 10
},
{
"epoch": 0.5238095238095238,
"grad_norm": 0.7000951170921326,
"learning_rate": 8.665259359149132e-06,
"loss": 0.475830078125,
"step": 11
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.6319581270217896,
"learning_rate": 8.400863688854598e-06,
"loss": 0.483154296875,
"step": 12
},
{
"epoch": 0.6190476190476191,
"grad_norm": 0.3320125937461853,
"learning_rate": 8.117449009293668e-06,
"loss": 0.441650390625,
"step": 13
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.4056682884693146,
"learning_rate": 7.81660029031811e-06,
"loss": 0.430908203125,
"step": 14
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.301974356174469,
"learning_rate": 7.500000000000001e-06,
"loss": 0.404296875,
"step": 15
},
{
"epoch": 0.7619047619047619,
"grad_norm": 0.2189040184020996,
"learning_rate": 7.169418695587791e-06,
"loss": 0.406005859375,
"step": 16
},
{
"epoch": 0.8095238095238095,
"grad_norm": 0.18893173336982727,
"learning_rate": 6.8267051218319766e-06,
"loss": 0.38671875,
"step": 17
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.16727837920188904,
"learning_rate": 6.473775872054522e-06,
"loss": 0.38916015625,
"step": 18
},
{
"epoch": 0.9047619047619048,
"grad_norm": 0.2440917193889618,
"learning_rate": 6.112604669781572e-06,
"loss": 0.39013671875,
"step": 19
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.16641832888126373,
"learning_rate": 5.745211330880872e-06,
"loss": 0.39111328125,
"step": 20
},
{
"epoch": 1.0,
"grad_norm": 0.15235400199890137,
"learning_rate": 5.373650467932122e-06,
"loss": 0.38818359375,
"step": 21
},
{
"epoch": 1.0476190476190477,
"grad_norm": 0.14812521636486053,
"learning_rate": 5e-06,
"loss": 0.376220703125,
"step": 22
},
{
"epoch": 1.0952380952380953,
"grad_norm": 0.1415979415178299,
"learning_rate": 4.626349532067879e-06,
"loss": 0.372314453125,
"step": 23
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.12885110080242157,
"learning_rate": 4.254788669119127e-06,
"loss": 0.3671875,
"step": 24
},
{
"epoch": 1.1904761904761905,
"grad_norm": 0.12903711199760437,
"learning_rate": 3.887395330218429e-06,
"loss": 0.3701171875,
"step": 25
},
{
"epoch": 1.2380952380952381,
"grad_norm": 0.11666175723075867,
"learning_rate": 3.526224127945479e-06,
"loss": 0.371337890625,
"step": 26
},
{
"epoch": 1.2857142857142856,
"grad_norm": 0.10441309958696365,
"learning_rate": 3.173294878168025e-06,
"loss": 0.361328125,
"step": 27
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.11899272352457047,
"learning_rate": 2.83058130441221e-06,
"loss": 0.371826171875,
"step": 28
},
{
"epoch": 1.380952380952381,
"grad_norm": 0.1065606102347374,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.369873046875,
"step": 29
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.11209557950496674,
"learning_rate": 2.1833997096818897e-06,
"loss": 0.3541259765625,
"step": 30
},
{
"epoch": 1.4761904761904763,
"grad_norm": 0.09497517347335815,
"learning_rate": 1.8825509907063328e-06,
"loss": 0.36376953125,
"step": 31
},
{
"epoch": 1.5238095238095237,
"grad_norm": 0.1043071299791336,
"learning_rate": 1.5991363111454023e-06,
"loss": 0.3536376953125,
"step": 32
},
{
"epoch": 1.5714285714285714,
"grad_norm": 0.10889200866222382,
"learning_rate": 1.3347406408508695e-06,
"loss": 0.3724365234375,
"step": 33
},
{
"epoch": 1.619047619047619,
"grad_norm": 0.09507866203784943,
"learning_rate": 1.0908425876598512e-06,
"loss": 0.361328125,
"step": 34
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.09925027936697006,
"learning_rate": 8.688061284200266e-07,
"loss": 0.3580322265625,
"step": 35
},
{
"epoch": 1.7142857142857144,
"grad_norm": 0.0932762548327446,
"learning_rate": 6.698729810778065e-07,
"loss": 0.348876953125,
"step": 36
},
{
"epoch": 1.7619047619047619,
"grad_norm": 0.08697953075170517,
"learning_rate": 4.951556604879049e-07,
"loss": 0.36279296875,
"step": 37
},
{
"epoch": 1.8095238095238095,
"grad_norm": 0.09406810998916626,
"learning_rate": 3.4563125677897936e-07,
"loss": 0.3447265625,
"step": 38
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.08604250848293304,
"learning_rate": 2.2213597106929608e-07,
"loss": 0.3594970703125,
"step": 39
},
{
"epoch": 1.9047619047619047,
"grad_norm": 0.09233129769563675,
"learning_rate": 1.253604390908819e-07,
"loss": 0.3564453125,
"step": 40
},
{
"epoch": 1.9523809523809523,
"grad_norm": 0.09016957879066467,
"learning_rate": 5.584586887435739e-08,
"loss": 0.365966796875,
"step": 41
},
{
"epoch": 2.0,
"grad_norm": 0.09346268326044083,
"learning_rate": 1.3981014094099354e-08,
"loss": 0.3680419921875,
"step": 42
},
{
"epoch": 2.0,
"eval_loss": 0.34423828125,
"eval_runtime": 0.5326,
"eval_samples_per_second": 11.266,
"eval_steps_per_second": 1.878,
"step": 42
}
],
"logging_steps": 1.0,
"max_steps": 42,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 0,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.966928673767424e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}