cjiao/OpenThoughts3-greedy-groups-top-openthinker3-1.5B-checkpoint-375-80
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: cjiao/OpenThoughts3-greedy-groups-top-openthinker3-1.5B-checkpoint-375-80
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-22 11:30:45 +08:00
commit 58f6ef2daa
93 changed files with 765382 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

313
checkpoint-40/trainer_state.json Normal file
View File

@@ -0,0 +1,313 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.5,
"eval_steps": 500,
"global_step": 40,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0125,
"grad_norm": 2.691509962081909,
"learning_rate": 0.00015998457923856519,
"loss": 1.4456,
"step": 1
},
{
"epoch": 0.025,
"grad_norm": 24.26286506652832,
"learning_rate": 0.00015993832289925785,
"loss": 4.3349,
"step": 2
},
{
"epoch": 0.0375,
"grad_norm": 13.163036346435547,
"learning_rate": 0.0001598612488147773,
"loss": 2.6695,
"step": 3
},
{
"epoch": 0.05,
"grad_norm": 9.818785667419434,
"learning_rate": 0.00015975338669865026,
"loss": 2.3799,
"step": 4
},
{
"epoch": 0.0625,
"grad_norm": 6.200242519378662,
"learning_rate": 0.00015961477813377576,
"loss": 2.0935,
"step": 5
},
{
"epoch": 0.075,
"grad_norm": 2.0556814670562744,
"learning_rate": 0.00015944547655639412,
"loss": 1.8465,
"step": 6
},
{
"epoch": 0.0875,
"grad_norm": 2.5195746421813965,
"learning_rate": 0.00015924554723548617,
"loss": 1.7321,
"step": 7
},
{
"epoch": 0.1,
"grad_norm": 4.300451278686523,
"learning_rate": 0.00015901506724761103,
"loss": 1.7284,
"step": 8
},
{
"epoch": 0.1125,
"grad_norm": 1.5021892786026,
"learning_rate": 0.00015875412544719134,
"loss": 1.5971,
"step": 9
},
{
"epoch": 0.125,
"grad_norm": 1.5246820449829102,
"learning_rate": 0.00015846282243225845,
"loss": 1.562,
"step": 10
},
{
"epoch": 0.1375,
"grad_norm": 2.0095787048339844,
"learning_rate": 0.0001581412705056698,
"loss": 1.578,
"step": 11
},
{
"epoch": 0.15,
"grad_norm": 0.9773982763290405,
"learning_rate": 0.00015778959363181415,
"loss": 1.4977,
"step": 12
},
{
"epoch": 0.1625,
"grad_norm": 1.1493251323699951,
"learning_rate": 0.0001574079273888208,
"loss": 1.5075,
"step": 13
},
{
"epoch": 0.175,
"grad_norm": 0.8909309506416321,
"learning_rate": 0.00015699641891629178,
"loss": 1.4158,
"step": 14
},
{
"epoch": 0.1875,
"grad_norm": 0.9415439963340759,
"learning_rate": 0.00015655522685857672,
"loss": 1.4219,
"step": 15
},
{
"epoch": 0.2,
"grad_norm": 1.1703603267669678,
"learning_rate": 0.0001560845213036123,
"loss": 1.4006,
"step": 16
},
{
"epoch": 0.2125,
"grad_norm": 0.7575011849403381,
"learning_rate": 0.00015558448371735025,
"loss": 1.3675,
"step": 17
},
{
"epoch": 0.225,
"grad_norm": 0.6772542595863342,
"learning_rate": 0.00015505530687379875,
"loss": 1.3369,
"step": 18
},
{
"epoch": 0.2375,
"grad_norm": 0.5587411522865295,
"learning_rate": 0.00015449719478070428,
"loss": 1.3632,
"step": 19
},
{
"epoch": 0.25,
"grad_norm": 0.5920618772506714,
"learning_rate": 0.00015391036260090294,
"loss": 1.3511,
"step": 20
},
{
"epoch": 0.2625,
"grad_norm": 0.4218953847885132,
"learning_rate": 0.0001532950365693709,
"loss": 1.3641,
"step": 21
},
{
"epoch": 0.275,
"grad_norm": 0.4676741361618042,
"learning_rate": 0.00015265145390600652,
"loss": 1.3441,
"step": 22
},
{
"epoch": 0.2875,
"grad_norm": 0.38095250725746155,
"learning_rate": 0.00015197986272417774,
"loss": 1.3418,
"step": 23
},
{
"epoch": 0.3,
"grad_norm": 0.42308753728866577,
"learning_rate": 0.00015128052193506944,
"loss": 1.3646,
"step": 24
},
{
"epoch": 0.3125,
"grad_norm": 0.4307089149951935,
"learning_rate": 0.0001505537011478684,
"loss": 1.2992,
"step": 25
},
{
"epoch": 0.325,
"grad_norm": 0.33103814721107483,
"learning_rate": 0.0001497996805658238,
"loss": 1.3435,
"step": 26
},
{
"epoch": 0.3375,
"grad_norm": 0.3511773645877838,
"learning_rate": 0.00014901875087822337,
"loss": 1.3,
"step": 27
},
{
"epoch": 0.35,
"grad_norm": 0.2914850115776062,
"learning_rate": 0.0001482112131483274,
"loss": 1.3103,
"step": 28
},
{
"epoch": 0.3625,
"grad_norm": 0.37050625681877136,
"learning_rate": 0.00014737737869730292,
"loss": 1.2731,
"step": 29
},
{
"epoch": 0.375,
"grad_norm": 0.3476356565952301,
"learning_rate": 0.00014651756898420365,
"loss": 1.3211,
"step": 30
},
{
"epoch": 0.3875,
"grad_norm": 0.27799472212791443,
"learning_rate": 0.0001456321154820411,
"loss": 1.2657,
"step": 31
},
{
"epoch": 0.4,
"grad_norm": 0.318327397108078,
"learning_rate": 0.00014472135954999581,
"loss": 1.3068,
"step": 32
},
{
"epoch": 0.4125,
"grad_norm": 0.30465707182884216,
"learning_rate": 0.00014378565230181657,
"loss": 1.2839,
"step": 33
},
{
"epoch": 0.425,
"grad_norm": 0.2618834376335144,
"learning_rate": 0.0001428253544704596,
"loss": 1.2868,
"step": 34
},
{
"epoch": 0.4375,
"grad_norm": 0.2864656150341034,
"learning_rate": 0.00014184083626901897,
"loss": 1.2815,
"step": 35
},
{
"epoch": 0.45,
"grad_norm": 0.2776831388473511,
"learning_rate": 0.0001408324772480025,
"loss": 1.2895,
"step": 36
},
{
"epoch": 0.4625,
"grad_norm": 0.31238630414009094,
"learning_rate": 0.00013980066614900776,
"loss": 1.2718,
"step": 37
},
{
"epoch": 0.475,
"grad_norm": 0.23365426063537598,
"learning_rate": 0.00013874580075485485,
"loss": 1.2596,
"step": 38
},
{
"epoch": 0.4875,
"grad_norm": 0.23924365639686584,
"learning_rate": 0.00013766828773623352,
"loss": 1.2809,
"step": 39
},
{
"epoch": 0.5,
"grad_norm": 0.24298632144927979,
"learning_rate": 0.00013656854249492382,
"loss": 1.2248,
"step": 40
}
],
"logging_steps": 1,
"max_steps": 160,
"num_input_tokens_seen": 0,
"num_train_epochs": 2,
"save_steps": 40,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.3190320448392397e+18,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}