michka/Melenchon-Nemo-12B
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: michka/Melenchon-Nemo-12B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-27 23:46:18 +08:00
commit eae0f19d9f
53 changed files with 18519 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

209
checkpoint-240/trainer_state.json Normal file
View File

@@ -0,0 +1,209 @@
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 500,
"global_step": 240,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.041666666666666664,
"grad_norm": 3.5982143878936768,
"learning_rate": 0.0002,
"loss": 7.626,
"step": 10
},
{
"epoch": 0.08333333333333333,
"grad_norm": 2.8034327030181885,
"learning_rate": 0.00019906859460363307,
"loss": 3.236,
"step": 20
},
{
"epoch": 0.125,
"grad_norm": 1.4735996723175049,
"learning_rate": 0.00019629172873477995,
"loss": 1.555,
"step": 30
},
{
"epoch": 0.16666666666666666,
"grad_norm": 1.259310007095337,
"learning_rate": 0.00019172113015054532,
"loss": 1.5749,
"step": 40
},
{
"epoch": 0.20833333333333334,
"grad_norm": 1.0123932361602783,
"learning_rate": 0.00018544194045464886,
"loss": 1.5026,
"step": 50
},
{
"epoch": 0.25,
"grad_norm": 0.8011332750320435,
"learning_rate": 0.000177571129070442,
"loss": 1.3026,
"step": 60
},
{
"epoch": 0.2916666666666667,
"grad_norm": 0.9434933066368103,
"learning_rate": 0.00016825531432186543,
"loss": 1.3517,
"step": 70
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.6396370530128479,
"learning_rate": 0.00015766803221148673,
"loss": 1.4123,
"step": 80
},
{
"epoch": 0.375,
"grad_norm": 1.062090277671814,
"learning_rate": 0.00014600650377311522,
"loss": 1.3411,
"step": 90
},
{
"epoch": 0.4166666666666667,
"grad_norm": 0.515396237373352,
"learning_rate": 0.00013348796121709862,
"loss": 1.319,
"step": 100
},
{
"epoch": 0.4583333333333333,
"grad_norm": 0.5104358792304993,
"learning_rate": 0.0001203456013052634,
"loss": 1.2435,
"step": 110
},
{
"epoch": 0.5,
"grad_norm": 0.8905439972877502,
"learning_rate": 0.0001068242413364671,
"loss": 1.3519,
"step": 120
},
{
"epoch": 0.5416666666666666,
"grad_norm": 0.6107117533683777,
"learning_rate": 9.317575866353292e-05,
"loss": 1.3462,
"step": 130
},
{
"epoch": 0.5833333333333334,
"grad_norm": 0.8154811263084412,
"learning_rate": 7.965439869473664e-05,
"loss": 1.3592,
"step": 140
},
{
"epoch": 0.625,
"grad_norm": 0.5068439245223999,
"learning_rate": 6.651203878290139e-05,
"loss": 1.273,
"step": 150
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.5794748663902283,
"learning_rate": 5.399349622688479e-05,
"loss": 1.2561,
"step": 160
},
{
"epoch": 0.7083333333333334,
"grad_norm": 0.4536129832267761,
"learning_rate": 4.2331967788513295e-05,
"loss": 1.2155,
"step": 170
},
{
"epoch": 0.75,
"grad_norm": 0.44865843653678894,
"learning_rate": 3.174468567813461e-05,
"loss": 1.2809,
"step": 180
},
{
"epoch": 0.7916666666666666,
"grad_norm": 0.49808937311172485,
"learning_rate": 2.242887092955801e-05,
"loss": 1.2845,
"step": 190
},
{
"epoch": 0.8333333333333334,
"grad_norm": 0.4432452917098999,
"learning_rate": 1.4558059545351143e-05,
"loss": 1.3265,
"step": 200
},
{
"epoch": 0.875,
"grad_norm": 0.5799461007118225,
"learning_rate": 8.278869849454718e-06,
"loss": 1.3288,
"step": 210
},
{
"epoch": 0.9166666666666666,
"grad_norm": 1.042983055114746,
"learning_rate": 3.7082712652200867e-06,
"loss": 1.2647,
"step": 220
},
{
"epoch": 0.9583333333333334,
"grad_norm": 0.45813554525375366,
"learning_rate": 9.314053963669245e-07,
"loss": 1.3007,
"step": 230
},
{
"epoch": 1.0,
"grad_norm": 0.6868065595626831,
"learning_rate": 0.0,
"loss": 1.2434,
"step": 240
},
{
"epoch": 1.0,
"eval_loss": 0.30000853538513184,
"eval_runtime": 2.6802,
"eval_samples_per_second": 3.358,
"eval_steps_per_second": 0.746,
"step": 240
}
],
"logging_steps": 10,
"max_steps": 240,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.372368282845184e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}