laion/swesmith-1000__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/swesmith-1000__Qwen3-8B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-05 05:35:25 +08:00
commit 0e6a69ed25
23 changed files with 152651 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

212
trainer_state.json Normal file
View File

@@ -0,0 +1,212 @@
{
"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": 1.6584312748391856,
"learning_rate": 2e-05,
"loss": 0.358,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.09996187686920166,
"step": 5,
"valid_targets_mean": 6473.8,
"valid_targets_min": 1524
},
{
"epoch": 0.9375,
"grad_norm": 0.6059472813471147,
"learning_rate": 3.9979273472934556e-05,
"loss": 0.2982,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.08913302421569824,
"step": 10,
"valid_targets_mean": 5224.7,
"valid_targets_min": 1096
},
{
"epoch": 1.375,
"grad_norm": 0.3554380091469559,
"learning_rate": 3.925834574695599e-05,
"loss": 0.2627,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.08456847071647644,
"step": 15,
"valid_targets_mean": 8057.2,
"valid_targets_min": 1524
},
{
"epoch": 1.84375,
"grad_norm": 0.30184278750286936,
"learning_rate": 3.754365204805189e-05,
"loss": 0.2378,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.07224074751138687,
"step": 20,
"valid_targets_mean": 4704.4,
"valid_targets_min": 1013
},
{
"epoch": 2.28125,
"grad_norm": 0.1935590534415232,
"learning_rate": 3.4923673716953717e-05,
"loss": 0.2022,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.06797438859939575,
"step": 25,
"valid_targets_mean": 6318.8,
"valid_targets_min": 1096
},
{
"epoch": 2.75,
"grad_norm": 0.18728816665180203,
"learning_rate": 3.153360644229735e-05,
"loss": 0.2027,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.06250719726085663,
"step": 30,
"valid_targets_mean": 4503.4,
"valid_targets_min": 978
},
{
"epoch": 3.1875,
"grad_norm": 0.16373518200964554,
"learning_rate": 2.7548383915052287e-05,
"loss": 0.1981,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.06715655326843262,
"step": 35,
"valid_targets_mean": 6662.6,
"valid_targets_min": 990
},
{
"epoch": 3.65625,
"grad_norm": 0.15753986396501643,
"learning_rate": 2.317365092912503e-05,
"loss": 0.184,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.05037520080804825,
"step": 40,
"valid_targets_mean": 5237.5,
"valid_targets_min": 1023
},
{
"epoch": 4.09375,
"grad_norm": 0.13464524831217287,
"learning_rate": 1.8635151732706586e-05,
"loss": 0.1769,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.06514693051576614,
"step": 45,
"valid_targets_mean": 5255.4,
"valid_targets_min": 516
},
{
"epoch": 4.5625,
"grad_norm": 0.1492527991721431,
"learning_rate": 1.4167081210903501e-05,
"loss": 0.1771,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.05879808962345123,
"step": 50,
"valid_targets_mean": 5966.8,
"valid_targets_min": 1185
},
{
"epoch": 5.0,
"grad_norm": 0.15069434637684775,
"learning_rate": 1.0000000000000006e-05,
"loss": 0.1716,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.068663090467453,
"step": 55,
"valid_targets_mean": 5956.2,
"valid_targets_min": 399
},
{
"epoch": 5.46875,
"grad_norm": 0.14890881138028308,
"learning_rate": 6.348937135626922e-06,
"loss": 0.1687,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.045535460114479065,
"step": 60,
"valid_targets_mean": 4807.5,
"valid_targets_min": 436
},
{
"epoch": 5.9375,
"grad_norm": 0.132392659020721,
"learning_rate": 3.402294160019499e-06,
"loss": 0.1754,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.05873378366231918,
"step": 65,
"valid_targets_mean": 5606.9,
"valid_targets_min": 1425
},
{
"epoch": 6.375,
"grad_norm": 0.158965357158266,
"learning_rate": 1.3121232567865793e-06,
"loss": 0.1679,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.05117513984441757,
"step": 70,
"valid_targets_mean": 4612.0,
"valid_targets_min": 510
},
{
"epoch": 6.84375,
"grad_norm": 0.13712387603113121,
"learning_rate": 1.862810792733849e-07,
"loss": 0.1758,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.05727507174015045,
"step": 75,
"valid_targets_mean": 7398.4,
"valid_targets_min": 1134
},
{
"epoch": 7.0,
"loss_nan_ranks": 0,
"loss_rank_avg": 0.09160405397415161,
"step": 77,
"total_flos": 2.1021193659010253e+17,
"train_loss": 0.20924820180063125,
"train_runtime": 2215.847,
"train_samples_per_second": 3.159,
"train_steps_per_second": 0.035,
"valid_targets_mean": 6769.5,
"valid_targets_min": 1162
}
],
"logging_steps": 5,
"max_steps": 77,
"num_input_tokens_seen": 0,
"num_train_epochs": 7,
"save_steps": 300,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.1021193659010253e+17,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}