renaudb1999/le-harnais-ft-counsel-Meta-Llama-3.1-8B-Instruct-regular-dom2
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: renaudb1999/le-harnais-ft-counsel-Meta-Llama-3.1-8B-Instruct-regular-dom2
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-02 15:11:18 +08:00
commit 7e1bb2161e
15 changed files with 2913 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

211
trainer_state.json Normal file
View File

@@ -0,0 +1,211 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"eval_steps": 500,
"global_step": 244,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.1652892561983471,
"grad_norm": 77.0,
"learning_rate": 9.631147540983608e-06,
"loss": 1.9138,
"step": 10
},
{
"epoch": 0.3305785123966942,
"grad_norm": 9.3125,
"learning_rate": 9.221311475409836e-06,
"loss": 1.2058,
"step": 20
},
{
"epoch": 0.49586776859504134,
"grad_norm": 9.1875,
"learning_rate": 8.811475409836067e-06,
"loss": 1.0547,
"step": 30
},
{
"epoch": 0.6611570247933884,
"grad_norm": 8.0625,
"learning_rate": 8.401639344262295e-06,
"loss": 1.0034,
"step": 40
},
{
"epoch": 0.8264462809917356,
"grad_norm": 9.75,
"learning_rate": 7.991803278688526e-06,
"loss": 1.008,
"step": 50
},
{
"epoch": 0.9917355371900827,
"grad_norm": 6.78125,
"learning_rate": 7.581967213114755e-06,
"loss": 0.9968,
"step": 60
},
{
"epoch": 1.1487603305785123,
"grad_norm": 8.125,
"learning_rate": 7.172131147540984e-06,
"loss": 0.6478,
"step": 70
},
{
"epoch": 1.3140495867768596,
"grad_norm": 7.25,
"learning_rate": 6.762295081967214e-06,
"loss": 0.5796,
"step": 80
},
{
"epoch": 1.4793388429752066,
"grad_norm": 7.4375,
"learning_rate": 6.352459016393443e-06,
"loss": 0.5963,
"step": 90
},
{
"epoch": 1.6446280991735538,
"grad_norm": 6.53125,
"learning_rate": 5.942622950819673e-06,
"loss": 0.6069,
"step": 100
},
{
"epoch": 1.8099173553719008,
"grad_norm": 7.5,
"learning_rate": 5.5327868852459025e-06,
"loss": 0.5908,
"step": 110
},
{
"epoch": 1.9752066115702478,
"grad_norm": 7.65625,
"learning_rate": 5.122950819672131e-06,
"loss": 0.5999,
"step": 120
},
{
"epoch": 2.1322314049586777,
"grad_norm": 6.09375,
"learning_rate": 4.7131147540983615e-06,
"loss": 0.3677,
"step": 130
},
{
"epoch": 2.2975206611570247,
"grad_norm": 8.25,
"learning_rate": 4.30327868852459e-06,
"loss": 0.3029,
"step": 140
},
{
"epoch": 2.462809917355372,
"grad_norm": 5.78125,
"learning_rate": 3.8934426229508196e-06,
"loss": 0.2945,
"step": 150
},
{
"epoch": 2.628099173553719,
"grad_norm": 5.90625,
"learning_rate": 3.4836065573770495e-06,
"loss": 0.29,
"step": 160
},
{
"epoch": 2.793388429752066,
"grad_norm": 5.9375,
"learning_rate": 3.073770491803279e-06,
"loss": 0.2888,
"step": 170
},
{
"epoch": 2.958677685950413,
"grad_norm": 6.0,
"learning_rate": 2.6639344262295084e-06,
"loss": 0.292,
"step": 180
},
{
"epoch": 3.115702479338843,
"grad_norm": 5.125,
"learning_rate": 2.254098360655738e-06,
"loss": 0.2099,
"step": 190
},
{
"epoch": 3.28099173553719,
"grad_norm": 4.875,
"learning_rate": 1.8442622950819674e-06,
"loss": 0.1907,
"step": 200
},
{
"epoch": 3.446280991735537,
"grad_norm": 5.0,
"learning_rate": 1.4344262295081968e-06,
"loss": 0.194,
"step": 210
},
{
"epoch": 3.6115702479338845,
"grad_norm": 5.3125,
"learning_rate": 1.0245901639344263e-06,
"loss": 0.1867,
"step": 220
},
{
"epoch": 3.7768595041322315,
"grad_norm": 4.625,
"learning_rate": 6.147540983606558e-07,
"loss": 0.1714,
"step": 230
},
{
"epoch": 3.9421487603305785,
"grad_norm": 3.9375,
"learning_rate": 2.0491803278688524e-07,
"loss": 0.1789,
"step": 240
},
{
"epoch": 4.0,
"step": 244,
"total_flos": 8.926999384109875e+16,
"train_loss": 0.5673878478710769,
"train_runtime": 847.1078,
"train_samples_per_second": 4.58,
"train_steps_per_second": 0.288
}
],
"logging_steps": 10,
"max_steps": 244,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 60,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 8.926999384109875e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}