Qwen3-32B-Code-TogetherAI / trainer_state.json
FormlessAI's picture
Upload folder using huggingface_hub
0cebf4c verified
Raw
History Blame Contribute Delete
8.42 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": 0.6524344086647034,
"learning_rate": 1e-05,
"loss": 2.4072265625,
"step": 1
},
{
"epoch": 0.09523809523809523,
"grad_norm": 0.43840861320495605,
"learning_rate": 9.986018985905901e-06,
"loss": 1.73046875,
"step": 2
},
{
"epoch": 0.14285714285714285,
"grad_norm": 0.8311549425125122,
"learning_rate": 9.944154131125643e-06,
"loss": 2.865234375,
"step": 3
},
{
"epoch": 0.19047619047619047,
"grad_norm": 0.6437926888465881,
"learning_rate": 9.874639560909118e-06,
"loss": 2.1650390625,
"step": 4
},
{
"epoch": 0.23809523809523808,
"grad_norm": 0.316669225692749,
"learning_rate": 9.777864028930705e-06,
"loss": 1.189453125,
"step": 5
},
{
"epoch": 0.2857142857142857,
"grad_norm": 0.4141232669353485,
"learning_rate": 9.654368743221022e-06,
"loss": 1.2841796875,
"step": 6
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.6203616261482239,
"learning_rate": 9.504844339512096e-06,
"loss": 1.6884765625,
"step": 7
},
{
"epoch": 0.38095238095238093,
"grad_norm": 0.5661473274230957,
"learning_rate": 9.330127018922195e-06,
"loss": 1.4794921875,
"step": 8
},
{
"epoch": 0.42857142857142855,
"grad_norm": 0.8129859566688538,
"learning_rate": 9.131193871579975e-06,
"loss": 1.80224609375,
"step": 9
},
{
"epoch": 0.47619047619047616,
"grad_norm": 0.354056179523468,
"learning_rate": 8.90915741234015e-06,
"loss": 0.95849609375,
"step": 10
},
{
"epoch": 0.5238095238095238,
"grad_norm": 0.5867434144020081,
"learning_rate": 8.665259359149132e-06,
"loss": 1.25634765625,
"step": 11
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.49527591466903687,
"learning_rate": 8.400863688854598e-06,
"loss": 0.875,
"step": 12
},
{
"epoch": 0.6190476190476191,
"grad_norm": 0.7747569680213928,
"learning_rate": 8.117449009293668e-06,
"loss": 1.14111328125,
"step": 13
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.44143417477607727,
"learning_rate": 7.81660029031811e-06,
"loss": 0.84814453125,
"step": 14
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.5234490036964417,
"learning_rate": 7.500000000000001e-06,
"loss": 0.94482421875,
"step": 15
},
{
"epoch": 0.7619047619047619,
"grad_norm": 0.29542046785354614,
"learning_rate": 7.169418695587791e-06,
"loss": 0.7724609375,
"step": 16
},
{
"epoch": 0.8095238095238095,
"grad_norm": 0.34254831075668335,
"learning_rate": 6.8267051218319766e-06,
"loss": 0.8232421875,
"step": 17
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.4682796895503998,
"learning_rate": 6.473775872054522e-06,
"loss": 0.8740234375,
"step": 18
},
{
"epoch": 0.9047619047619048,
"grad_norm": 0.34994277358055115,
"learning_rate": 6.112604669781572e-06,
"loss": 0.788330078125,
"step": 19
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.19499827921390533,
"learning_rate": 5.745211330880872e-06,
"loss": 0.623779296875,
"step": 20
},
{
"epoch": 1.0,
"grad_norm": 0.2733888328075409,
"learning_rate": 5.373650467932122e-06,
"loss": 0.6943359375,
"step": 21
},
{
"epoch": 1.0476190476190477,
"grad_norm": 0.2766434848308563,
"learning_rate": 5e-06,
"loss": 0.661865234375,
"step": 22
},
{
"epoch": 1.0952380952380953,
"grad_norm": 0.17610260844230652,
"learning_rate": 4.626349532067879e-06,
"loss": 0.5859375,
"step": 23
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.29853567481040955,
"learning_rate": 4.254788669119127e-06,
"loss": 0.699951171875,
"step": 24
},
{
"epoch": 1.1904761904761905,
"grad_norm": 0.2070755511522293,
"learning_rate": 3.887395330218429e-06,
"loss": 0.6240234375,
"step": 25
},
{
"epoch": 1.2380952380952381,
"grad_norm": 0.10244687646627426,
"learning_rate": 3.526224127945479e-06,
"loss": 0.516357421875,
"step": 26
},
{
"epoch": 1.2857142857142856,
"grad_norm": 0.11527957022190094,
"learning_rate": 3.173294878168025e-06,
"loss": 0.500732421875,
"step": 27
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.16032108664512634,
"learning_rate": 2.83058130441221e-06,
"loss": 0.587890625,
"step": 28
},
{
"epoch": 1.380952380952381,
"grad_norm": 0.14240753650665283,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.5753173828125,
"step": 29
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.19114552438259125,
"learning_rate": 2.1833997096818897e-06,
"loss": 0.6060791015625,
"step": 30
},
{
"epoch": 1.4761904761904763,
"grad_norm": 0.0961521565914154,
"learning_rate": 1.8825509907063328e-06,
"loss": 0.48529052734375,
"step": 31
},
{
"epoch": 1.5238095238095237,
"grad_norm": 0.14089089632034302,
"learning_rate": 1.5991363111454023e-06,
"loss": 0.58203125,
"step": 32
},
{
"epoch": 1.5714285714285714,
"grad_norm": 0.11384878307580948,
"learning_rate": 1.3347406408508695e-06,
"loss": 0.392578125,
"step": 33
},
{
"epoch": 1.619047619047619,
"grad_norm": 0.17307597398757935,
"learning_rate": 1.0908425876598512e-06,
"loss": 0.5501708984375,
"step": 34
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.11703500151634216,
"learning_rate": 8.688061284200266e-07,
"loss": 0.528564453125,
"step": 35
},
{
"epoch": 1.7142857142857144,
"grad_norm": 0.16454102098941803,
"learning_rate": 6.698729810778065e-07,
"loss": 0.564453125,
"step": 36
},
{
"epoch": 1.7619047619047619,
"grad_norm": 0.11863923817873001,
"learning_rate": 4.951556604879049e-07,
"loss": 0.5511474609375,
"step": 37
},
{
"epoch": 1.8095238095238095,
"grad_norm": 0.1439819186925888,
"learning_rate": 3.4563125677897936e-07,
"loss": 0.579833984375,
"step": 38
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.19448505342006683,
"learning_rate": 2.2213597106929608e-07,
"loss": 0.575927734375,
"step": 39
},
{
"epoch": 1.9047619047619047,
"grad_norm": 0.16301444172859192,
"learning_rate": 1.253604390908819e-07,
"loss": 0.5849609375,
"step": 40
},
{
"epoch": 1.9523809523809523,
"grad_norm": 0.10161160677671432,
"learning_rate": 5.584586887435739e-08,
"loss": 0.520263671875,
"step": 41
},
{
"epoch": 2.0,
"grad_norm": 0.1480644941329956,
"learning_rate": 1.3981014094099354e-08,
"loss": 0.5703125,
"step": 42
},
{
"epoch": 2.0,
"eval_loss": 0.522216796875,
"eval_runtime": 5.117,
"eval_samples_per_second": 0.586,
"eval_steps_per_second": 0.195,
"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": 7.222115369400402e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}