laion/coderforge-1000-opt1k__Qwen3-8B
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: laion/coderforge-1000-opt1k__Qwen3-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-08 18:15:54 +08:00
commit d90f0553f7
23 changed files with 152645 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

208
trainer_state.json Normal file
View File

@@ -0,0 +1,208 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 7.0,
"eval_steps": 500,
"global_step": 77,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.46875,
"grad_norm": 4.448054524364805,
"learning_rate": 2e-05,
"loss": 0.455,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.13171809911727905,
"step": 5,
"valid_targets_mean": 8612.9,
"valid_targets_min": 1973
},
{
"epoch": 0.9375,
"grad_norm": 0.4031238705852911,
"learning_rate": 3.9979273472934556e-05,
"loss": 0.3189,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.09132535755634308,
"step": 10,
"valid_targets_mean": 10068.0,
"valid_targets_min": 6315
},
{
"epoch": 1.375,
"grad_norm": 0.24568147362182324,
"learning_rate": 3.925834574695599e-05,
"loss": 0.2376,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.07364940643310547,
"step": 15,
"valid_targets_mean": 9279.8,
"valid_targets_min": 2555
},
{
"epoch": 1.84375,
"grad_norm": 0.1931949370341057,
"learning_rate": 3.754365204805189e-05,
"loss": 0.1971,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.06216152757406235,
"step": 20,
"valid_targets_mean": 8479.3,
"valid_targets_min": 2433
},
{
"epoch": 2.28125,
"grad_norm": 0.1869265372551763,
"learning_rate": 3.4923673716953717e-05,
"loss": 0.176,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.05491546541452408,
"step": 25,
"valid_targets_mean": 8381.5,
"valid_targets_min": 3027
},
{
"epoch": 2.75,
"grad_norm": 0.18474170757239242,
"learning_rate": 3.153360644229735e-05,
"loss": 0.1612,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.05455561727285385,
"step": 30,
"valid_targets_mean": 8741.6,
"valid_targets_min": 2273
},
{
"epoch": 3.1875,
"grad_norm": 0.21084299064721884,
"learning_rate": 2.7548383915052287e-05,
"loss": 0.1521,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.048021771013736725,
"step": 35,
"valid_targets_mean": 7941.8,
"valid_targets_min": 2787
},
{
"epoch": 3.65625,
"grad_norm": 0.17938824831413855,
"learning_rate": 2.317365092912503e-05,
"loss": 0.1354,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.04698628932237625,
"step": 40,
"valid_targets_mean": 9171.9,
"valid_targets_min": 1973
},
{
"epoch": 4.09375,
"grad_norm": 0.17629152033532372,
"learning_rate": 1.8635151732706586e-05,
"loss": 0.1277,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.03995367884635925,
"step": 45,
"valid_targets_mean": 9452.5,
"valid_targets_min": 5050
},
{
"epoch": 4.5625,
"grad_norm": 0.18885873440265113,
"learning_rate": 1.4167081210903501e-05,
"loss": 0.1202,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.04391225427389145,
"step": 50,
"valid_targets_mean": 9556.2,
"valid_targets_min": 3856
},
{
"epoch": 5.0,
"grad_norm": 0.19582461359420836,
"learning_rate": 1.0000000000000006e-05,
"loss": 0.1124,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.04943796992301941,
"step": 55,
"valid_targets_mean": 8111.1,
"valid_targets_min": 2073
},
{
"epoch": 5.46875,
"grad_norm": 0.18391944874352525,
"learning_rate": 6.348937135626922e-06,
"loss": 0.105,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.036417774856090546,
"step": 60,
"valid_targets_mean": 9081.7,
"valid_targets_min": 2927
},
{
"epoch": 5.9375,
"grad_norm": 0.16996211811427234,
"learning_rate": 3.402294160019499e-06,
"loss": 0.104,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.03394484519958496,
"step": 65,
"valid_targets_mean": 8957.2,
"valid_targets_min": 4178
},
{
"epoch": 6.375,
"grad_norm": 0.1641421714766095,
"learning_rate": 1.3121232567865793e-06,
"loss": 0.0994,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.03531872481107712,
"step": 70,
"valid_targets_mean": 9267.8,
"valid_targets_min": 2315
},
{
"epoch": 6.84375,
"grad_norm": 0.1586564409417946,
"learning_rate": 1.862810792733849e-07,
"loss": 0.0978,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.035106539726257324,
"step": 75,
"valid_targets_mean": 9101.6,
"valid_targets_min": 1782
},
{
"epoch": 7.0,
"step": 77,
"total_flos": 5.4876432713016934e+17,
"train_loss": 0.0,
"train_runtime": 1.5035,
"train_samples_per_second": 4655.763,
"train_steps_per_second": 51.213
}
],
"logging_steps": 5,
"max_steps": 77,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"save_steps": 50,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.4876432713016934e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}