FormlessAI's picture
Upload folder using huggingface_hub
3cd7ffd verified
Raw
History Blame Contribute Delete
8.45 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": 1.7856502532958984,
"learning_rate": 1e-05,
"loss": 1.2998046875,
"step": 1
},
{
"epoch": 0.09523809523809523,
"grad_norm": 1.7217988967895508,
"learning_rate": 9.986018985905901e-06,
"loss": 1.2275390625,
"step": 2
},
{
"epoch": 0.14285714285714285,
"grad_norm": 1.4862382411956787,
"learning_rate": 9.944154131125643e-06,
"loss": 1.1005859375,
"step": 3
},
{
"epoch": 0.19047619047619047,
"grad_norm": 1.64996337890625,
"learning_rate": 9.874639560909118e-06,
"loss": 1.10205078125,
"step": 4
},
{
"epoch": 0.23809523809523808,
"grad_norm": 1.2898013591766357,
"learning_rate": 9.777864028930705e-06,
"loss": 0.91259765625,
"step": 5
},
{
"epoch": 0.2857142857142857,
"grad_norm": 1.2251713275909424,
"learning_rate": 9.654368743221022e-06,
"loss": 0.8291015625,
"step": 6
},
{
"epoch": 0.3333333333333333,
"grad_norm": 1.2967991828918457,
"learning_rate": 9.504844339512096e-06,
"loss": 0.79736328125,
"step": 7
},
{
"epoch": 0.38095238095238093,
"grad_norm": 0.8783257603645325,
"learning_rate": 9.330127018922195e-06,
"loss": 0.67236328125,
"step": 8
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.5831462740898132,
"learning_rate": 9.131193871579975e-06,
"loss": 0.5126953125,
"step": 9
},
{
"epoch": 0.47619047619047616,
"grad_norm": 0.4697442352771759,
"learning_rate": 8.90915741234015e-06,
"loss": 0.545654296875,
"step": 10
},
{
"epoch": 0.5238095238095238,
"grad_norm": 0.33920571208000183,
"learning_rate": 8.665259359149132e-06,
"loss": 0.5191650390625,
"step": 11
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.3368586003780365,
"learning_rate": 8.400863688854598e-06,
"loss": 0.52978515625,
"step": 12
},
{
"epoch": 0.6190476190476191,
"grad_norm": 0.31900179386138916,
"learning_rate": 8.117449009293668e-06,
"loss": 0.539794921875,
"step": 13
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.25366634130477905,
"learning_rate": 7.81660029031811e-06,
"loss": 0.52490234375,
"step": 14
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.21215789020061493,
"learning_rate": 7.500000000000001e-06,
"loss": 0.50341796875,
"step": 15
},
{
"epoch": 0.7619047619047619,
"grad_norm": 0.2041260004043579,
"learning_rate": 7.169418695587791e-06,
"loss": 0.49560546875,
"step": 16
},
{
"epoch": 0.8095238095238095,
"grad_norm": 0.17790615558624268,
"learning_rate": 6.8267051218319766e-06,
"loss": 0.508056640625,
"step": 17
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.15687698125839233,
"learning_rate": 6.473775872054522e-06,
"loss": 0.534912109375,
"step": 18
},
{
"epoch": 0.9047619047619048,
"grad_norm": 0.12181716412305832,
"learning_rate": 6.112604669781572e-06,
"loss": 0.49560546875,
"step": 19
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.07874012738466263,
"learning_rate": 5.745211330880872e-06,
"loss": 0.48046875,
"step": 20
},
{
"epoch": 1.0,
"grad_norm": 0.16810809075832367,
"learning_rate": 5.373650467932122e-06,
"loss": 0.51318359375,
"step": 21
},
{
"epoch": 1.0476190476190477,
"grad_norm": 0.13423927128314972,
"learning_rate": 5e-06,
"loss": 0.49609375,
"step": 22
},
{
"epoch": 1.0952380952380953,
"grad_norm": 0.11767170578241348,
"learning_rate": 4.626349532067879e-06,
"loss": 0.4853515625,
"step": 23
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.11554888635873795,
"learning_rate": 4.254788669119127e-06,
"loss": 0.51318359375,
"step": 24
},
{
"epoch": 1.1904761904761905,
"grad_norm": 0.1263965666294098,
"learning_rate": 3.887395330218429e-06,
"loss": 0.5048828125,
"step": 25
},
{
"epoch": 1.2380952380952381,
"grad_norm": 0.09703799337148666,
"learning_rate": 3.526224127945479e-06,
"loss": 0.492919921875,
"step": 26
},
{
"epoch": 1.2857142857142856,
"grad_norm": 0.09051357209682465,
"learning_rate": 3.173294878168025e-06,
"loss": 0.49169921875,
"step": 27
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.10393014550209045,
"learning_rate": 2.83058130441221e-06,
"loss": 0.504150390625,
"step": 28
},
{
"epoch": 1.380952380952381,
"grad_norm": 0.06461871415376663,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.50927734375,
"step": 29
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.058113571256399155,
"learning_rate": 2.1833997096818897e-06,
"loss": 0.4197998046875,
"step": 30
},
{
"epoch": 1.4761904761904763,
"grad_norm": 0.06653960049152374,
"learning_rate": 1.8825509907063328e-06,
"loss": 0.478759765625,
"step": 31
},
{
"epoch": 1.5238095238095237,
"grad_norm": 0.06834722310304642,
"learning_rate": 1.5991363111454023e-06,
"loss": 0.462646484375,
"step": 32
},
{
"epoch": 1.5714285714285714,
"grad_norm": 0.0657752975821495,
"learning_rate": 1.3347406408508695e-06,
"loss": 0.477294921875,
"step": 33
},
{
"epoch": 1.619047619047619,
"grad_norm": 0.07572554051876068,
"learning_rate": 1.0908425876598512e-06,
"loss": 0.491943359375,
"step": 34
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.07082884013652802,
"learning_rate": 8.688061284200266e-07,
"loss": 0.487548828125,
"step": 35
},
{
"epoch": 1.7142857142857144,
"grad_norm": 0.06343502551317215,
"learning_rate": 6.698729810778065e-07,
"loss": 0.470947265625,
"step": 36
},
{
"epoch": 1.7619047619047619,
"grad_norm": 0.06430655717849731,
"learning_rate": 4.951556604879049e-07,
"loss": 0.467529296875,
"step": 37
},
{
"epoch": 1.8095238095238095,
"grad_norm": 0.08241258561611176,
"learning_rate": 3.4563125677897936e-07,
"loss": 0.484375,
"step": 38
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.0810951218008995,
"learning_rate": 2.2213597106929608e-07,
"loss": 0.515380859375,
"step": 39
},
{
"epoch": 1.9047619047619047,
"grad_norm": 0.07861144840717316,
"learning_rate": 1.253604390908819e-07,
"loss": 0.48046875,
"step": 40
},
{
"epoch": 1.9523809523809523,
"grad_norm": 0.06533784419298172,
"learning_rate": 5.584586887435739e-08,
"loss": 0.4716796875,
"step": 41
},
{
"epoch": 2.0,
"grad_norm": 0.1391107738018036,
"learning_rate": 1.3981014094099354e-08,
"loss": 0.5010986328125,
"step": 42
},
{
"epoch": 2.0,
"eval_loss": 0.4776611328125,
"eval_runtime": 0.5315,
"eval_samples_per_second": 7.526,
"eval_steps_per_second": 1.882,
"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": 7.357626326817178e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}