Qwen3.5-0.8B-Math-TogetherAI / trainer_state.json
FormlessAI's picture
Upload folder using huggingface_hub
9be0b53 verified
Raw
History Blame Contribute Delete
8.43 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": 6.073901176452637,
"learning_rate": 1e-05,
"loss": 1.24609375,
"step": 1
},
{
"epoch": 0.09523809523809523,
"grad_norm": 4.874844074249268,
"learning_rate": 9.986018985905901e-06,
"loss": 1.115234375,
"step": 2
},
{
"epoch": 0.14285714285714285,
"grad_norm": 3.750936508178711,
"learning_rate": 9.944154131125643e-06,
"loss": 1.0830078125,
"step": 3
},
{
"epoch": 0.19047619047619047,
"grad_norm": 2.819389581680298,
"learning_rate": 9.874639560909118e-06,
"loss": 0.943359375,
"step": 4
},
{
"epoch": 0.23809523809523808,
"grad_norm": 1.9768736362457275,
"learning_rate": 9.777864028930705e-06,
"loss": 0.787109375,
"step": 5
},
{
"epoch": 0.2857142857142857,
"grad_norm": 1.7158842086791992,
"learning_rate": 9.654368743221022e-06,
"loss": 0.75732421875,
"step": 6
},
{
"epoch": 0.3333333333333333,
"grad_norm": 1.4797794818878174,
"learning_rate": 9.504844339512096e-06,
"loss": 0.731201171875,
"step": 7
},
{
"epoch": 0.38095238095238093,
"grad_norm": 1.116447925567627,
"learning_rate": 9.330127018922195e-06,
"loss": 0.67626953125,
"step": 8
},
{
"epoch": 0.42857142857142855,
"grad_norm": 1.1091934442520142,
"learning_rate": 9.131193871579975e-06,
"loss": 0.6683349609375,
"step": 9
},
{
"epoch": 0.47619047619047616,
"grad_norm": 0.7402724623680115,
"learning_rate": 8.90915741234015e-06,
"loss": 0.62744140625,
"step": 10
},
{
"epoch": 0.5238095238095238,
"grad_norm": 0.7217769622802734,
"learning_rate": 8.665259359149132e-06,
"loss": 0.6005859375,
"step": 11
},
{
"epoch": 0.5714285714285714,
"grad_norm": 0.6323782205581665,
"learning_rate": 8.400863688854598e-06,
"loss": 0.608154296875,
"step": 12
},
{
"epoch": 0.6190476190476191,
"grad_norm": 0.5849839448928833,
"learning_rate": 8.117449009293668e-06,
"loss": 0.58154296875,
"step": 13
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.4686709940433502,
"learning_rate": 7.81660029031811e-06,
"loss": 0.5687255859375,
"step": 14
},
{
"epoch": 0.7142857142857143,
"grad_norm": 0.4547746777534485,
"learning_rate": 7.500000000000001e-06,
"loss": 0.56689453125,
"step": 15
},
{
"epoch": 0.7619047619047619,
"grad_norm": 0.38605666160583496,
"learning_rate": 7.169418695587791e-06,
"loss": 0.5771484375,
"step": 16
},
{
"epoch": 0.8095238095238095,
"grad_norm": 0.38534843921661377,
"learning_rate": 6.8267051218319766e-06,
"loss": 0.54248046875,
"step": 17
},
{
"epoch": 0.8571428571428571,
"grad_norm": 0.3715933561325073,
"learning_rate": 6.473775872054522e-06,
"loss": 0.5146484375,
"step": 18
},
{
"epoch": 0.9047619047619048,
"grad_norm": 0.3346211910247803,
"learning_rate": 6.112604669781572e-06,
"loss": 0.51220703125,
"step": 19
},
{
"epoch": 0.9523809523809523,
"grad_norm": 0.31094199419021606,
"learning_rate": 5.745211330880872e-06,
"loss": 0.537109375,
"step": 20
},
{
"epoch": 1.0,
"grad_norm": 0.31583544611930847,
"learning_rate": 5.373650467932122e-06,
"loss": 0.523193359375,
"step": 21
},
{
"epoch": 1.0476190476190477,
"grad_norm": 0.29443153738975525,
"learning_rate": 5e-06,
"loss": 0.52099609375,
"step": 22
},
{
"epoch": 1.0952380952380953,
"grad_norm": 0.2739787995815277,
"learning_rate": 4.626349532067879e-06,
"loss": 0.5283203125,
"step": 23
},
{
"epoch": 1.1428571428571428,
"grad_norm": 0.30799806118011475,
"learning_rate": 4.254788669119127e-06,
"loss": 0.50341796875,
"step": 24
},
{
"epoch": 1.1904761904761905,
"grad_norm": 0.2711120843887329,
"learning_rate": 3.887395330218429e-06,
"loss": 0.5244140625,
"step": 25
},
{
"epoch": 1.2380952380952381,
"grad_norm": 0.2500905990600586,
"learning_rate": 3.526224127945479e-06,
"loss": 0.52685546875,
"step": 26
},
{
"epoch": 1.2857142857142856,
"grad_norm": 0.24108710885047913,
"learning_rate": 3.173294878168025e-06,
"loss": 0.5343017578125,
"step": 27
},
{
"epoch": 1.3333333333333333,
"grad_norm": 0.2509496212005615,
"learning_rate": 2.83058130441221e-06,
"loss": 0.5244140625,
"step": 28
},
{
"epoch": 1.380952380952381,
"grad_norm": 0.24448473751544952,
"learning_rate": 2.5000000000000015e-06,
"loss": 0.511474609375,
"step": 29
},
{
"epoch": 1.4285714285714286,
"grad_norm": 0.25556090474128723,
"learning_rate": 2.1833997096818897e-06,
"loss": 0.51416015625,
"step": 30
},
{
"epoch": 1.4761904761904763,
"grad_norm": 0.2327951043844223,
"learning_rate": 1.8825509907063328e-06,
"loss": 0.52587890625,
"step": 31
},
{
"epoch": 1.5238095238095237,
"grad_norm": 0.23128774762153625,
"learning_rate": 1.5991363111454023e-06,
"loss": 0.50390625,
"step": 32
},
{
"epoch": 1.5714285714285714,
"grad_norm": 0.24347372353076935,
"learning_rate": 1.3347406408508695e-06,
"loss": 0.5244140625,
"step": 33
},
{
"epoch": 1.619047619047619,
"grad_norm": 0.25006499886512756,
"learning_rate": 1.0908425876598512e-06,
"loss": 0.5093994140625,
"step": 34
},
{
"epoch": 1.6666666666666665,
"grad_norm": 0.21885156631469727,
"learning_rate": 8.688061284200266e-07,
"loss": 0.511474609375,
"step": 35
},
{
"epoch": 1.7142857142857144,
"grad_norm": 0.23900581896305084,
"learning_rate": 6.698729810778065e-07,
"loss": 0.513916015625,
"step": 36
},
{
"epoch": 1.7619047619047619,
"grad_norm": 0.2283465415239334,
"learning_rate": 4.951556604879049e-07,
"loss": 0.53271484375,
"step": 37
},
{
"epoch": 1.8095238095238095,
"grad_norm": 0.2637370526790619,
"learning_rate": 3.4563125677897936e-07,
"loss": 0.502197265625,
"step": 38
},
{
"epoch": 1.8571428571428572,
"grad_norm": 0.2450195848941803,
"learning_rate": 2.2213597106929608e-07,
"loss": 0.47998046875,
"step": 39
},
{
"epoch": 1.9047619047619047,
"grad_norm": 0.2379116266965866,
"learning_rate": 1.253604390908819e-07,
"loss": 0.483154296875,
"step": 40
},
{
"epoch": 1.9523809523809523,
"grad_norm": 0.2274172306060791,
"learning_rate": 5.584586887435739e-08,
"loss": 0.5126953125,
"step": 41
},
{
"epoch": 2.0,
"grad_norm": 0.22687792778015137,
"learning_rate": 1.3981014094099354e-08,
"loss": 0.499755859375,
"step": 42
},
{
"epoch": 2.0,
"eval_loss": 0.5048828125,
"eval_runtime": 10.6218,
"eval_samples_per_second": 0.188,
"eval_steps_per_second": 0.094,
"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": 1.2237809330946048e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}