Qwen3.5-2B-Translation-TogetherAI / trainer_state.json
FormlessAI's picture
Upload folder using huggingface_hub
330c97a verified
Raw
History Blame Contribute Delete
8.37 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": 9.564770698547363,
"learning_rate": 1e-05,
"loss": 4.2451171875,
"step": 1
},
{
"epoch": 0.09523809523809523,
"grad_norm": 7.958559036254883,
"learning_rate": 9.986018985905901e-06,
"loss": 4.033203125,
"step": 2
},
{
"epoch": 0.14285714285714285,
"grad_norm": 6.644944667816162,
"learning_rate": 9.944154131125643e-06,
"loss": 3.216796875,
"step": 3
},
{
"epoch": 0.19047619047619047,
"grad_norm": 5.330323219299316,
"learning_rate": 9.874639560909118e-06,
"loss": 3.0478515625,
"step": 4
},
{
"epoch": 0.23809523809523808,
"grad_norm": 4.44828987121582,
"learning_rate": 9.777864028930705e-06,
"loss": 3.1669921875,
"step": 5
},
{
"epoch": 0.2857142857142857,
"grad_norm": 3.3391776084899902,
"learning_rate": 9.654368743221022e-06,
"loss": 2.3984375,
"step": 6
},
{
"epoch": 0.3333333333333333,
"grad_norm": 2.7876625061035156,
"learning_rate": 9.504844339512096e-06,
"loss": 2.3056640625,
"step": 7
},
{
"epoch": 0.38095238095238093,
"grad_norm": 2.139387845993042,
"learning_rate": 9.330127018922195e-06,
"loss": 1.9521484375,
"step": 8
},
{
"epoch": 0.42857142857142855,
"grad_norm": 1.7173882722854614,
"learning_rate": 9.131193871579975e-06,
"loss": 1.9716796875,
"step": 9
},
{
"epoch": 0.47619047619047616,
"grad_norm": 1.9741867780685425,
"learning_rate": 8.90915741234015e-06,
"loss": 2.595703125,
"step": 10
},
{
"epoch": 0.5238095238095238,
"grad_norm": 1.4212232828140259,
"learning_rate": 8.665259359149132e-06,
"loss": 2.02294921875,
"step": 11
},
{
"epoch": 0.5714285714285714,
"grad_norm": 1.2649765014648438,
"learning_rate": 8.400863688854598e-06,
"loss": 1.79541015625,
"step": 12
},
{
"epoch": 0.6190476190476191,
"grad_norm": 1.1514559984207153,
"learning_rate": 8.117449009293668e-06,
"loss": 1.9970703125,
"step": 13
},
{
"epoch": 0.6666666666666666,
"grad_norm": 1.2227715253829956,
"learning_rate": 7.81660029031811e-06,
"loss": 2.23486328125,
"step": 14
},
{
"epoch": 0.7142857142857143,
"grad_norm": 1.27517831325531,
"learning_rate": 7.500000000000001e-06,
"loss": 2.37158203125,
"step": 15
},
{
"epoch": 0.7619047619047619,
"grad_norm": 0.7255933880805969,
"learning_rate": 7.169418695587791e-06,
"loss": 1.814453125,
"step": 16
},
{
"epoch": 0.8095238095238095,
"grad_norm": 0.6774395108222961,
"learning_rate": 6.8267051218319766e-06,
"loss": 1.70947265625,
"step": 17
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.6797354817390442,
"learning_rate": 6.473775872054522e-06,
"loss": 1.95361328125,
"step": 18
},
{
"epoch": 0.9047619047619048,
"grad_norm": 0.9845736026763916,
"learning_rate": 6.112604669781572e-06,
"loss": 2.30712890625,
"step": 19
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.5166913866996765,
"learning_rate": 5.745211330880872e-06,
"loss": 1.796875,
"step": 20
},
{
"epoch": 1.0,
"grad_norm": 0.5498979091644287,
"learning_rate": 5.373650467932122e-06,
"loss": 1.9619140625,
"step": 21
},
{
"epoch": 1.0476190476190477,
"grad_norm": 0.511072039604187,
"learning_rate": 5e-06,
"loss": 1.94189453125,
"step": 22
},
{
"epoch": 1.0952380952380953,
"grad_norm": 0.4813345670700073,
"learning_rate": 4.626349532067879e-06,
"loss": 1.9228515625,
"step": 23
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.42678311467170715,
"learning_rate": 4.254788669119127e-06,
"loss": 1.625,
"step": 24
},
{
"epoch": 1.1904761904761905,
"grad_norm": 0.3565751910209656,
"learning_rate": 3.887395330218429e-06,
"loss": 1.69580078125,
"step": 25
},
{
"epoch": 1.2380952380952381,
"grad_norm": 0.37901973724365234,
"learning_rate": 3.526224127945479e-06,
"loss": 1.95458984375,
"step": 26
},
{
"epoch": 1.2857142857142856,
"grad_norm": 0.3272838592529297,
"learning_rate": 3.173294878168025e-06,
"loss": 1.59423828125,
"step": 27
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.28080224990844727,
"learning_rate": 2.83058130441221e-06,
"loss": 1.62451171875,
"step": 28
},
{
"epoch": 1.380952380952381,
"grad_norm": 0.26315128803253174,
"learning_rate": 2.5000000000000015e-06,
"loss": 1.46044921875,
"step": 29
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.25534820556640625,
"learning_rate": 2.1833997096818897e-06,
"loss": 1.541015625,
"step": 30
},
{
"epoch": 1.4761904761904763,
"grad_norm": 0.3211769759654999,
"learning_rate": 1.8825509907063328e-06,
"loss": 2.06689453125,
"step": 31
},
{
"epoch": 1.5238095238095237,
"grad_norm": 0.24552041292190552,
"learning_rate": 1.5991363111454023e-06,
"loss": 1.67578125,
"step": 32
},
{
"epoch": 1.5714285714285714,
"grad_norm": 0.22990255057811737,
"learning_rate": 1.3347406408508695e-06,
"loss": 1.52001953125,
"step": 33
},
{
"epoch": 1.619047619047619,
"grad_norm": 0.24707551300525665,
"learning_rate": 1.0908425876598512e-06,
"loss": 1.73486328125,
"step": 34
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.3010173439979553,
"learning_rate": 8.688061284200266e-07,
"loss": 1.939453125,
"step": 35
},
{
"epoch": 1.7142857142857144,
"grad_norm": 0.36162257194519043,
"learning_rate": 6.698729810778065e-07,
"loss": 2.10693359375,
"step": 36
},
{
"epoch": 1.7619047619047619,
"grad_norm": 0.22403044998645782,
"learning_rate": 4.951556604879049e-07,
"loss": 1.65380859375,
"step": 37
},
{
"epoch": 1.8095238095238095,
"grad_norm": 0.22684480249881744,
"learning_rate": 3.4563125677897936e-07,
"loss": 1.5712890625,
"step": 38
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.23393622040748596,
"learning_rate": 2.2213597106929608e-07,
"loss": 1.82177734375,
"step": 39
},
{
"epoch": 1.9047619047619047,
"grad_norm": 0.3885467052459717,
"learning_rate": 1.253604390908819e-07,
"loss": 2.15625,
"step": 40
},
{
"epoch": 1.9523809523809523,
"grad_norm": 0.2221776843070984,
"learning_rate": 5.584586887435739e-08,
"loss": 1.70556640625,
"step": 41
},
{
"epoch": 2.0,
"grad_norm": 0.24670307338237762,
"learning_rate": 1.3981014094099354e-08,
"loss": 1.8701171875,
"step": 42
},
{
"epoch": 2.0,
"eval_loss": 1.71875,
"eval_runtime": 9.9543,
"eval_samples_per_second": 0.1,
"eval_steps_per_second": 0.1,
"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": 1.3051295792994714e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}