Qwen3.5-2B-Reasoning-TogetherAI / trainer_state.json
FormlessAI's picture
Upload folder using huggingface_hub
955dff9 verified
Raw
History Blame Contribute Delete
10.2 kB
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.0,
"eval_steps": 52,
"global_step": 52,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.038461538461538464,
"grad_norm": 4.689635276794434,
"learning_rate": 1e-05,
"loss": 2.4853515625,
"step": 1
},
{
"epoch": 0.07692307692307693,
"grad_norm": 3.844747543334961,
"learning_rate": 9.990877771116588e-06,
"loss": 2.3544921875,
"step": 2
},
{
"epoch": 0.11538461538461539,
"grad_norm": 3.494800090789795,
"learning_rate": 9.96354437049027e-06,
"loss": 2.2099609375,
"step": 3
},
{
"epoch": 0.15384615384615385,
"grad_norm": 2.4297192096710205,
"learning_rate": 9.91809953473572e-06,
"loss": 2.0040283203125,
"step": 4
},
{
"epoch": 0.19230769230769232,
"grad_norm": 2.0086750984191895,
"learning_rate": 9.854709087130261e-06,
"loss": 1.907470703125,
"step": 5
},
{
"epoch": 0.23076923076923078,
"grad_norm": 1.6094433069229126,
"learning_rate": 9.77360433254273e-06,
"loss": 1.8612060546875,
"step": 6
},
{
"epoch": 0.2692307692307692,
"grad_norm": 1.5231853723526,
"learning_rate": 9.675081213427076e-06,
"loss": 1.83349609375,
"step": 7
},
{
"epoch": 0.3076923076923077,
"grad_norm": 1.1918054819107056,
"learning_rate": 9.55949922996045e-06,
"loss": 1.640625,
"step": 8
},
{
"epoch": 0.34615384615384615,
"grad_norm": 0.9854990243911743,
"learning_rate": 9.427280128266049e-06,
"loss": 1.56982421875,
"step": 9
},
{
"epoch": 0.38461538461538464,
"grad_norm": 0.9586904048919678,
"learning_rate": 9.278906361507238e-06,
"loss": 1.5654296875,
"step": 10
},
{
"epoch": 0.4230769230769231,
"grad_norm": 0.8120144605636597,
"learning_rate": 9.114919329468283e-06,
"loss": 1.44482421875,
"step": 11
},
{
"epoch": 0.46153846153846156,
"grad_norm": 0.7073745131492615,
"learning_rate": 8.935917403045251e-06,
"loss": 1.49560546875,
"step": 12
},
{
"epoch": 0.5,
"grad_norm": 0.6228000521659851,
"learning_rate": 8.742553740855507e-06,
"loss": 1.47998046875,
"step": 13
},
{
"epoch": 0.5384615384615384,
"grad_norm": 0.544258177280426,
"learning_rate": 8.535533905932739e-06,
"loss": 1.42950439453125,
"step": 14
},
{
"epoch": 0.5769230769230769,
"grad_norm": 0.44122347235679626,
"learning_rate": 8.315613291203977e-06,
"loss": 1.392578125,
"step": 15
},
{
"epoch": 0.6153846153846154,
"grad_norm": 0.3860686719417572,
"learning_rate": 8.083594363142717e-06,
"loss": 1.38311767578125,
"step": 16
},
{
"epoch": 0.6538461538461539,
"grad_norm": 0.35200247168540955,
"learning_rate": 7.84032373365578e-06,
"loss": 1.3580322265625,
"step": 17
},
{
"epoch": 0.6923076923076923,
"grad_norm": 0.3415108621120453,
"learning_rate": 7.586689070888284e-06,
"loss": 1.326904296875,
"step": 18
},
{
"epoch": 0.7307692307692307,
"grad_norm": 0.3024138808250427,
"learning_rate": 7.323615860218844e-06,
"loss": 1.3759765625,
"step": 19
},
{
"epoch": 0.7692307692307693,
"grad_norm": 0.25955742597579956,
"learning_rate": 7.052064027263785e-06,
"loss": 1.3367919921875,
"step": 20
},
{
"epoch": 0.8076923076923077,
"grad_norm": 0.2363637387752533,
"learning_rate": 6.773024435212678e-06,
"loss": 1.3818359375,
"step": 21
},
{
"epoch": 0.8461538461538461,
"grad_norm": 0.20735107362270355,
"learning_rate": 6.487515269276015e-06,
"loss": 1.27813720703125,
"step": 22
},
{
"epoch": 0.8846153846153846,
"grad_norm": 0.19036373496055603,
"learning_rate": 6.1965783214377895e-06,
"loss": 1.32275390625,
"step": 23
},
{
"epoch": 0.9230769230769231,
"grad_norm": 0.18189361691474915,
"learning_rate": 5.90127518906953e-06,
"loss": 1.298828125,
"step": 24
},
{
"epoch": 0.9615384615384616,
"grad_norm": 0.17046603560447693,
"learning_rate": 5.6026834012766155e-06,
"loss": 1.3623046875,
"step": 25
},
{
"epoch": 1.0,
"grad_norm": 0.16392011940479279,
"learning_rate": 5.301892487111431e-06,
"loss": 1.31689453125,
"step": 26
},
{
"epoch": 1.0384615384615385,
"grad_norm": 0.15912248194217682,
"learning_rate": 5e-06,
"loss": 1.27880859375,
"step": 27
},
{
"epoch": 1.0769230769230769,
"grad_norm": 0.15796270966529846,
"learning_rate": 4.69810751288857e-06,
"loss": 1.3271484375,
"step": 28
},
{
"epoch": 1.1153846153846154,
"grad_norm": 0.13745176792144775,
"learning_rate": 4.397316598723385e-06,
"loss": 1.291015625,
"step": 29
},
{
"epoch": 1.1538461538461537,
"grad_norm": 0.14191485941410065,
"learning_rate": 4.098724810930472e-06,
"loss": 1.288330078125,
"step": 30
},
{
"epoch": 1.1923076923076923,
"grad_norm": 0.13703800737857819,
"learning_rate": 3.803421678562213e-06,
"loss": 1.274169921875,
"step": 31
},
{
"epoch": 1.2307692307692308,
"grad_norm": 0.14957869052886963,
"learning_rate": 3.5124847307239863e-06,
"loss": 1.33819580078125,
"step": 32
},
{
"epoch": 1.2692307692307692,
"grad_norm": 0.14096862077713013,
"learning_rate": 3.226975564787322e-06,
"loss": 1.39404296875,
"step": 33
},
{
"epoch": 1.3076923076923077,
"grad_norm": 0.13106374442577362,
"learning_rate": 2.947935972736217e-06,
"loss": 1.29052734375,
"step": 34
},
{
"epoch": 1.3461538461538463,
"grad_norm": 0.1206049919128418,
"learning_rate": 2.6763841397811576e-06,
"loss": 1.26629638671875,
"step": 35
},
{
"epoch": 1.3846153846153846,
"grad_norm": 0.12056861072778702,
"learning_rate": 2.4133109291117156e-06,
"loss": 1.2890625,
"step": 36
},
{
"epoch": 1.4230769230769231,
"grad_norm": 0.13918845355510712,
"learning_rate": 2.159676266344222e-06,
"loss": 1.2119140625,
"step": 37
},
{
"epoch": 1.4615384615384617,
"grad_norm": 0.14604124426841736,
"learning_rate": 1.9164056368572847e-06,
"loss": 1.28662109375,
"step": 38
},
{
"epoch": 1.5,
"grad_norm": 0.12339212745428085,
"learning_rate": 1.6843867087960252e-06,
"loss": 1.31494140625,
"step": 39
},
{
"epoch": 1.5384615384615383,
"grad_norm": 0.11346733570098877,
"learning_rate": 1.4644660940672628e-06,
"loss": 1.284912109375,
"step": 40
},
{
"epoch": 1.5769230769230769,
"grad_norm": 0.10992596298456192,
"learning_rate": 1.257446259144494e-06,
"loss": 1.265869140625,
"step": 41
},
{
"epoch": 1.6153846153846154,
"grad_norm": 0.1381499022245407,
"learning_rate": 1.0640825969547498e-06,
"loss": 1.26763916015625,
"step": 42
},
{
"epoch": 1.6538461538461537,
"grad_norm": 0.10350609570741653,
"learning_rate": 8.850806705317183e-07,
"loss": 1.2626953125,
"step": 43
},
{
"epoch": 1.6923076923076923,
"grad_norm": 0.10742916166782379,
"learning_rate": 7.210936384927631e-07,
"loss": 1.2371826171875,
"step": 44
},
{
"epoch": 1.7307692307692308,
"grad_norm": 0.11156682670116425,
"learning_rate": 5.727198717339511e-07,
"loss": 1.30615234375,
"step": 45
},
{
"epoch": 1.7692307692307692,
"grad_norm": 0.10545119643211365,
"learning_rate": 4.405007700395497e-07,
"loss": 1.271728515625,
"step": 46
},
{
"epoch": 1.8076923076923077,
"grad_norm": 0.1204240471124649,
"learning_rate": 3.2491878657292643e-07,
"loss": 1.3251953125,
"step": 47
},
{
"epoch": 1.8461538461538463,
"grad_norm": 0.12353746592998505,
"learning_rate": 2.2639566745727203e-07,
"loss": 1.226898193359375,
"step": 48
},
{
"epoch": 1.8846153846153846,
"grad_norm": 0.11921994388103485,
"learning_rate": 1.4529091286973994e-07,
"loss": 1.27685546875,
"step": 49
},
{
"epoch": 1.9230769230769231,
"grad_norm": 0.11171863973140717,
"learning_rate": 8.190046526428241e-08,
"loss": 1.25927734375,
"step": 50
},
{
"epoch": 1.9615384615384617,
"grad_norm": 0.11080524325370789,
"learning_rate": 3.645562950973014e-08,
"loss": 1.3271484375,
"step": 51
},
{
"epoch": 2.0,
"grad_norm": 0.10683345049619675,
"learning_rate": 9.12222888341252e-09,
"loss": 1.28271484375,
"step": 52
},
{
"epoch": 2.0,
"eval_loss": 1.32275390625,
"eval_runtime": 10.3528,
"eval_samples_per_second": 0.29,
"eval_steps_per_second": 0.097,
"step": 52
}
],
"logging_steps": 1.0,
"max_steps": 52,
"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": 5.690612945990451e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}