NastasiaM/mbert-loraxs-qa-vanilla
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: NastasiaM/mbert-loraxs-qa-vanilla
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-10 00:18:47 +08:00
commit d696db249d
795 changed files with 8285474 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
run-1/checkpoint-2536/config.json Normal file
View File

@@ -0,0 +1,34 @@
{
"add_cross_attention": false,
"architectures": [
"BertForQuestionAnswering"
],
"attention_probs_dropout_prob": 0.1,
"bos_token_id": null,
"classifier_dropout": null,
"directionality": "bidi",
"dtype": "float32",
"eos_token_id": null,
"hidden_act": "gelu",
"hidden_dropout_prob": 0.1,
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 3072,
"is_decoder": false,
"layer_norm_eps": 1e-12,
"max_position_embeddings": 512,
"model_type": "bert",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"pad_token_id": 0,
"pooler_fc_size": 768,
"pooler_num_attention_heads": 12,
"pooler_num_fc_layers": 3,
"pooler_size_per_head": 128,
"pooler_type": "first_token_transform",
"tie_word_embeddings": true,
"transformers_version": "5.9.0",
"type_vocab_size": 2,
"use_cache": true,
"vocab_size": 119547
}

3
run-1/checkpoint-2536/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:06989b83bf9d77da5b12e21fc035ca324b4349657fd8cfb36a435f071f870069
size 709080872

3
run-1/checkpoint-2536/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:64870094ba24066a73902f3c2511e84f95948a6eb7c244962cfd46e5f98190f0
size 1418284811

3
run-1/checkpoint-2536/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1e85fa698aa4806efe3d6074038fa07bcf6133d8cc71f17a6a4dca0b61c4fc4f
size 14645

3
run-1/checkpoint-2536/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a1c6b4addfbdbc469ec0107c5c42d1b0e47cf34c2de1d244fae93607014b55c
size 1383

3
run-1/checkpoint-2536/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7de304905c0f46d926a785e9a31fef27096dc0bb2c49504102ebeabc1bb2f7ea
size 1465

119711
run-1/checkpoint-2536/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

15
run-1/checkpoint-2536/tokenizer_config.json Normal file
View File

@@ -0,0 +1,15 @@
{
"backend": "tokenizers",
"cls_token": "[CLS]",
"do_lower_case": false,
"is_local": false,
"local_files_only": false,
"mask_token": "[MASK]",
"model_max_length": 512,
"pad_token": "[PAD]",
"sep_token": "[SEP]",
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"unk_token": "[UNK]"
}

106
run-1/checkpoint-2536/trainer_state.json Normal file
View File

@@ -0,0 +1,106 @@
{
"best_global_step": 2536,
"best_metric": 76.57829761930071,
"best_model_checkpoint": "mbert-loraxs-qa-vanilla/run-1/checkpoint-2536",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 2536,
"is_hyper_param_search": true,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 1.0,
"grad_norm": 15.868330955505371,
"learning_rate": 5.191675659155908e-05,
"loss": 2.1192049333349763,
"step": 634
},
{
"epoch": 1.0,
"eval_exact_match": 60.08,
"eval_f1": 74.33783203646502,
"eval_loss": 1.2725635766983032,
"eval_runtime": 5.8013,
"eval_samples_per_second": 218.055,
"eval_steps_per_second": 13.79,
"step": 634
},
{
"epoch": 2.0,
"grad_norm": 30.633678436279297,
"learning_rate": 3.46202649052488e-05,
"loss": 0.9956009440617607,
"step": 1268
},
{
"epoch": 2.0,
"eval_exact_match": 62.48,
"eval_f1": 76.03924855668853,
"eval_loss": 1.3048548698425293,
"eval_runtime": 6.0639,
"eval_samples_per_second": 208.613,
"eval_steps_per_second": 13.193,
"step": 1268
},
{
"epoch": 3.0,
"grad_norm": 13.438405990600586,
"learning_rate": 1.7323773218938526e-05,
"loss": 0.49370124889097006,
"step": 1902
},
{
"epoch": 3.0,
"eval_exact_match": 62.8,
"eval_f1": 76.44229300202514,
"eval_loss": 1.4875582456588745,
"eval_runtime": 5.797,
"eval_samples_per_second": 218.217,
"eval_steps_per_second": 13.8,
"step": 1902
},
{
"epoch": 4.0,
"grad_norm": 14.641495704650879,
"learning_rate": 2.728153262824965e-08,
"loss": 0.23204485775920494,
"step": 2536
},
{
"epoch": 4.0,
"eval_exact_match": 62.96,
"eval_f1": 76.57829761930071,
"eval_loss": 1.8072655200958252,
"eval_runtime": 5.8611,
"eval_samples_per_second": 215.829,
"eval_steps_per_second": 13.649,
"step": 2536
}
],
"logging_steps": 500,
"max_steps": 2536,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"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": 7950999010719744.0,
"train_batch_size": 16,
"trial_name": null,
"trial_params": {
"learning_rate": 6.22564574576657e-05,
"num_train_epochs": 4,
"weight_decay": 0.033952923108431954
}
}

3
run-1/checkpoint-2536/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:631288df84c6128821fb37f5b2efce07b97fa34e7c5281aa460f5144e137e955
size 5265