AI-ModelScope/Qwen2.5-VL-3B-sft-reasoning_and_grounding_changecoord_cpt636
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity
Files
main
Qwen2.5-VL-3B-sft-reasoning…/trainer_state.json
ModelHub XC e1e426ab78 初始化项目，由ModelHub XC社区提供模型 
Model: AI-ModelScope/Qwen2.5-VL-3B-sft-reasoning_and_grounding_changecoord_cpt636
Source: Original Platform
2026-06-03 21:43:12 +08:00

476 lines
11 KiB
JSON
Raw Permalink Blame History

{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.9992144540455616,
"eval_steps": 500,
"global_step": 636,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.031421838177533384,
"grad_norm": 0.7421875,
"learning_rate": 9.999750543489357e-06,
"loss": 1.3149,
"step": 10
},
{
"epoch": 0.06284367635506677,
"grad_norm": 0.453125,
"learning_rate": 9.991022178937775e-06,
"loss": 0.9124,
"step": 20
},
{
"epoch": 0.09426551453260015,
"grad_norm": 0.99609375,
"learning_rate": 9.96984586911221e-06,
"loss": 0.8294,
"step": 30
},
{
"epoch": 0.12568735271013354,
"grad_norm": 0.294921875,
"learning_rate": 9.936274429154798e-06,
"loss": 0.8129,
"step": 40
},
{
"epoch": 0.15710919088766692,
"grad_norm": 0.33984375,
"learning_rate": 9.890391588496586e-06,
"loss": 0.7844,
"step": 50
},
{
"epoch": 0.1885310290652003,
"grad_norm": 0.283203125,
"learning_rate": 9.832311782030674e-06,
"loss": 0.7959,
"step": 60
},
{
"epoch": 0.2199528672427337,
"grad_norm": 0.306640625,
"learning_rate": 9.762179864703908e-06,
"loss": 0.7767,
"step": 70
},
{
"epoch": 0.2513747054202671,
"grad_norm": 0.3828125,
"learning_rate": 9.680170750238873e-06,
"loss": 0.7704,
"step": 80
},
{
"epoch": 0.2827965435978005,
"grad_norm": 0.3984375,
"learning_rate": 9.586488974887312e-06,
"loss": 0.7644,
"step": 90
},
{
"epoch": 0.31421838177533384,
"grad_norm": 0.3359375,
"learning_rate": 9.48136818730293e-06,
"loss": 0.7523,
"step": 100
},
{
"epoch": 0.34564021995286726,
"grad_norm": 0.31640625,
"learning_rate": 9.365070565805941e-06,
"loss": 0.7683,
"step": 110
},
{
"epoch": 0.3770620581304006,
"grad_norm": 0.2578125,
"learning_rate": 9.23788616449268e-06,
"loss": 0.7561,
"step": 120
},
{
"epoch": 0.408483896307934,
"grad_norm": 0.36328125,
"learning_rate": 9.100132189821156e-06,
"loss": 0.7601,
"step": 130
},
{
"epoch": 0.4399057344854674,
"grad_norm": 0.376953125,
"learning_rate": 8.952152209476812e-06,
"loss": 0.7559,
"step": 140
},
{
"epoch": 0.4713275726630008,
"grad_norm": 0.279296875,
"learning_rate": 8.794315295491571e-06,
"loss": 0.734,
"step": 150
},
{
"epoch": 0.5027494108405341,
"grad_norm": 0.349609375,
"learning_rate": 8.62701510375336e-06,
"loss": 0.7567,
"step": 160
},
{
"epoch": 0.5341712490180676,
"grad_norm": 0.1904296875,
"learning_rate": 8.450668892201819e-06,
"loss": 0.7396,
"step": 170
},
{
"epoch": 0.565593087195601,
"grad_norm": 0.2490234375,
"learning_rate": 8.265716480158914e-06,
"loss": 0.7424,
"step": 180
},
{
"epoch": 0.5970149253731343,
"grad_norm": 0.25390625,
"learning_rate": 8.072619151389951e-06,
"loss": 0.7442,
"step": 190
},
{
"epoch": 0.6284367635506677,
"grad_norm": 0.423828125,
"learning_rate": 7.8718585036308e-06,
"loss": 0.7211,
"step": 200
},
{
"epoch": 0.6598586017282011,
"grad_norm": 0.2041015625,
"learning_rate": 7.663935247450733e-06,
"loss": 0.743,
"step": 210
},
{
"epoch": 0.6912804399057345,
"grad_norm": 0.322265625,
"learning_rate": 7.449367957446566e-06,
"loss": 0.7389,
"step": 220
},
{
"epoch": 0.7227022780832679,
"grad_norm": 0.81640625,
"learning_rate": 7.2286917788826926e-06,
"loss": 0.7329,
"step": 230
},
{
"epoch": 0.7541241162608012,
"grad_norm": 0.416015625,
"learning_rate": 7.002457093002785e-06,
"loss": 0.7447,
"step": 240
},
{
"epoch": 0.7855459544383346,
"grad_norm": 0.474609375,
"learning_rate": 6.77122814434192e-06,
"loss": 0.7209,
"step": 250
},
{
"epoch": 0.816967792615868,
"grad_norm": 0.28125,
"learning_rate": 6.535581633462728e-06,
"loss": 0.7413,
"step": 260
},
{
"epoch": 0.8483896307934015,
"grad_norm": 0.3828125,
"learning_rate": 6.296105278625368e-06,
"loss": 0.7308,
"step": 270
},
{
"epoch": 0.8798114689709348,
"grad_norm": 0.302734375,
"learning_rate": 6.053396349978632e-06,
"loss": 0.7302,
"step": 280
},
{
"epoch": 0.9112333071484682,
"grad_norm": 0.7109375,
"learning_rate": 5.808060179927983e-06,
"loss": 0.7383,
"step": 290
},
{
"epoch": 0.9426551453260016,
"grad_norm": 0.4140625,
"learning_rate": 5.560708653395796e-06,
"loss": 0.7183,
"step": 300
},
{
"epoch": 0.974076983503535,
"grad_norm": 0.318359375,
"learning_rate": 5.3119586817391655e-06,
"loss": 0.7379,
"step": 310
},
{
"epoch": 1.0062843676355067,
"grad_norm": 0.236328125,
"learning_rate": 5.062430664131463e-06,
"loss": 0.7395,
"step": 320
},
{
"epoch": 1.03770620581304,
"grad_norm": 0.31640625,
"learning_rate": 4.812746940245032e-06,
"loss": 0.7115,
"step": 330
},
{
"epoch": 1.0691280439905735,
"grad_norm": 1.0625,
"learning_rate": 4.563530238094161e-06,
"loss": 0.7328,
"step": 340
},
{
"epoch": 1.1005498821681068,
"grad_norm": 0.4921875,
"learning_rate": 4.315402120909486e-06,
"loss": 0.7178,
"step": 350
},
{
"epoch": 1.1319717203456403,
"grad_norm": 0.287109375,
"learning_rate": 4.068981436917471e-06,
"loss": 0.7277,
"step": 360
},
{
"epoch": 1.1633935585231736,
"grad_norm": 0.2373046875,
"learning_rate": 3.8248827758912535e-06,
"loss": 0.7299,
"step": 370
},
{
"epoch": 1.194815396700707,
"grad_norm": 0.35546875,
"learning_rate": 3.5837149363224045e-06,
"loss": 0.7189,
"step": 380
},
{
"epoch": 1.2262372348782404,
"grad_norm": 0.296875,
"learning_rate": 3.3460794070364923e-06,
"loss": 0.7371,
"step": 390
},
{
"epoch": 1.2576590730557737,
"grad_norm": 0.2734375,
"learning_rate": 3.1125688670394682e-06,
"loss": 0.7148,
"step": 400
},
{
"epoch": 1.2890809112333073,
"grad_norm": 0.365234375,
"learning_rate": 2.8837657073363344e-06,
"loss": 0.7275,
"step": 410
},
{
"epoch": 1.3205027494108406,
"grad_norm": 0.5859375,
"learning_rate": 2.660240578408776e-06,
"loss": 0.7234,
"step": 420
},
{
"epoch": 1.3519245875883739,
"grad_norm": 0.498046875,
"learning_rate": 2.442550966974444e-06,
"loss": 0.7171,
"step": 430
},
{
"epoch": 1.3833464257659074,
"grad_norm": 0.26171875,
"learning_rate": 2.2312398055775496e-06,
"loss": 0.7332,
"step": 440
},
{
"epoch": 1.4147682639434407,
"grad_norm": 0.220703125,
"learning_rate": 2.0268341184785674e-06,
"loss": 0.7167,
"step": 450
},
{
"epoch": 1.446190102120974,
"grad_norm": 0.380859375,
"learning_rate": 1.829843707220243e-06,
"loss": 0.7235,
"step": 460
},
{
"epoch": 1.4776119402985075,
"grad_norm": 0.2255859375,
"learning_rate": 1.6407598791482294e-06,
"loss": 0.7253,
"step": 470
},
{
"epoch": 1.5090337784760408,
"grad_norm": 0.359375,
"learning_rate": 1.4600542220575038e-06,
"loss": 0.7132,
"step": 480
},
{
"epoch": 1.5404556166535741,
"grad_norm": 0.3828125,
"learning_rate": 1.2881774280206554e-06,
"loss": 0.7309,
"step": 490
},
{
"epoch": 1.5718774548311076,
"grad_norm": 0.4375,
"learning_rate": 1.125558169331521e-06,
"loss": 0.7232,
"step": 500
},
{
"epoch": 1.6032992930086412,
"grad_norm": 0.2734375,
"learning_rate": 9.726020293676308e-07,
"loss": 0.7284,
"step": 510
},
{
"epoch": 1.6347211311861742,
"grad_norm": 0.330078125,
"learning_rate": 8.296904910379622e-07,
"loss": 0.7282,
"step": 520
},
{
"epoch": 1.6661429693637078,
"grad_norm": 1.5078125,
"learning_rate": 6.971799853388867e-07,
"loss": 0.7159,
"step": 530
},
{
"epoch": 1.6975648075412413,
"grad_norm": 1.1171875,
"learning_rate": 5.754010023912693e-07,
"loss": 0.7349,
"step": 540
},
{
"epoch": 1.7289866457187746,
"grad_norm": 0.328125,
"learning_rate": 4.646572671758687e-07,
"loss": 0.7208,
"step": 550
},
{
"epoch": 1.7604084838963079,
"grad_norm": 0.361328125,
"learning_rate": 3.6522498202278434e-07,
"loss": 0.7253,
"step": 560
},
{
"epoch": 1.7918303220738414,
"grad_norm": 0.283203125,
"learning_rate": 2.773521377442523e-07,
"loss": 0.7246,
"step": 570
},
{
"epoch": 1.8232521602513747,
"grad_norm": 0.484375,
"learning_rate": 2.012578951288724e-07,
"loss": 0.7161,
"step": 580
},
{
"epoch": 1.854673998428908,
"grad_norm": 0.298828125,
"learning_rate": 1.3713203833984446e-07,
"loss": 0.7316,
"step": 590
},
{
"epoch": 1.8860958366064415,
"grad_norm": 0.234375,
"learning_rate": 8.513450158049109e-08,
"loss": 0.7133,
"step": 600
},
{
"epoch": 1.9175176747839748,
"grad_norm": 0.2353515625,
"learning_rate": 4.5394970207591206e-08,
"loss": 0.7306,
"step": 610
},
{
"epoch": 1.9489395129615081,
"grad_norm": 1.0390625,
"learning_rate": 1.8012557287367394e-08,
"loss": 0.722,
"step": 620
},
{
"epoch": 1.9803613511390417,
"grad_norm": 0.408203125,
"learning_rate": 3.0555564008305504e-09,
"loss": 0.717,
"step": 630
}
],
"logging_steps": 10,
"max_steps": 636,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 500.0,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.042156006349629e+19,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}
Reference in New Issue View Git Blame Copy Permalink