Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+checkpoint-*/
+.ipynb_checkpoints

README.md

@@ -0,0 +1,137 @@
+---
+library_name: transformers
+base_model: bert-base-chinese
+tags:
+- generated_from_trainer
+datasets:
+- real-jiakai/chinese-squadv2
+model-index:
+- name: chinese_squadv2
+  results: []
+---
+
+# bert-base-chinese-finetuned-squadv2
+
+This model is a fine-tuned version of [bert-base-chinese](https://huggingface.co/bert-base-chinese) on the [Chinese SQuAD v2.0 dataset](https://huggingface.co/datasets/real-jiakai/chinese-squadv2).
+
+## Model Description
+
+This model is designed for Chinese question answering tasks, specifically for extractive QA where the answer must be extracted from a given context paragraph. It can handle both answerable and unanswerable questions, following the SQuAD v2.0 format.
+
+Key features:
+- Based on BERT-base Chinese architecture
+- Supports both answerable and unanswerable questions
+- Trained on Chinese question-answer pairs
+- Optimized for extractive question answering
+
+## Intended Uses & Limitations
+
+### Intended Uses
+- Chinese extractive question answering
+- Reading comprehension tasks
+- Information extraction from Chinese text
+- Automated question answering systems
+
+### Limitations
+- Performance is significantly better on unanswerable questions (76.65% accuracy) compared to answerable questions (36.41% accuracy)
+- Limited to extractive QA (cannot generate new answers)
+- May not perform well on domain-specific questions outside the training data
+- Designed for modern Chinese text, may not work well with classical Chinese or dialectal variations
+
+## Training and Evaluation Data
+
+The model was trained on the Chinese SQuAD v2.0 dataset, which contains:
+
+Training Set:
+- Total examples: 90,027
+- Answerable questions: 46,529
+- Unanswerable questions: 43,498
+
+Validation Set:
+- Total examples: 9,936
+- Answerable questions: 3,991
+- Unanswerable questions: 5,945
+
+## Training Procedure
+
+### Training Hyperparameters
+
+- Learning rate: 3e-05
+- Batch size: 12
+- Evaluation batch size: 8
+- Number of epochs: 5
+- Optimizer: AdamW (β1=0.9, β2=0.999, ε=1e-08)
+- Learning rate scheduler: Linear
+- Maximum sequence length: 384
+- Document stride: 128
+- Training device: CUDA-enabled GPU
+
+### Training Results
+
+Final evaluation metrics:
+- Overall Exact Match: 60.49%
+- Overall F1 Score: 60.54%
+- Answerable Questions:
+  - Exact Match: 36.41%
+  - F1 Score: 36.53%
+- Unanswerable Questions:
+  - Exact Match: 76.65%
+  - F1 Score: 76.65%
+
+### Framework Versions
+- Transformers: 4.47.0.dev0
+- PyTorch: 2.5.1+cu124
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
+
+## Usage
+
+```python
+from transformers import AutoModelForQuestionAnswering, AutoTokenizer
+import torch
+
+# Load model and tokenizer
+model_name = "real-jiakai/bert-base-chinese-finetuned-squadv2"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForQuestionAnswering.from_pretrained(model_name)
+
+# Prepare the inputs
+question = "your_question"
+context = "your_context"
+inputs = tokenizer(
+    question,
+    context,
+    add_special_tokens=True,
+    return_tensors="pt"
+)
+
+# Get the answer
+start_scores, end_scores = model(**inputs)
+start_index = torch.argmax(start_scores)
+end_index = torch.argmax(end_scores)
+answer = tokenizer.convert_tokens_to_string(
+    tokenizer.convert_ids_to_tokens(inputs["input_ids"][0][start_index:end_index+1])
+)
+```
+
+## Limitations and Bias
+
+The model shows significant performance disparity between answerable and unanswerable questions, which might indicate:
+1. Dataset quality issues
+2. Potential translation artifacts in the Chinese version of SQuAD
+3. Imbalanced handling of answerable vs. unanswerable questions
+
+## Ethics & Responsible AI
+
+Users should be aware that:
+- The model may reflect biases present in the training data
+- Performance varies significantly based on question type
+- Results should be validated for critical applications
+- The model should not be used as the sole decision-maker in critical systems
+
+### Framework versions
+
+- Transformers 4.47.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,26 @@
+{
+    "epoch": 5.0,
+    "eval_HasAns_exact": 36.40691556001002,
+    "eval_HasAns_f1": 36.53303265681116,
+    "eval_HasAns_total": 3991,
+    "eval_NoAns_exact": 76.65264928511354,
+    "eval_NoAns_f1": 76.65264928511354,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 60.829307568438004,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 60.87996511003758,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 60.487117552334944,
+    "eval_f1": 60.53777509393452,
+    "eval_runtime": 37.7571,
+    "eval_samples": 10637,
+    "eval_samples_per_second": 281.722,
+    "eval_steps_per_second": 35.225,
+    "eval_total": 9936,
+    "total_flos": 9.414718117765632e+16,
+    "train_loss": 0.0,
+    "train_runtime": 0.003,
+    "train_samples": 96082,
+    "train_samples_per_second": 159489123.369,
+    "train_steps_per_second": 13291036.935
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "bert-base-chinese",
+  "architectures": [
+    "BertForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 21128
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:010e819a99f25563cb3e21f8d7edfadd99f156cc74f5c8ef8a171498f2e99ce8
+size 48586682

eval_results.json

@@ -0,0 +1,20 @@
+{
+    "epoch": 5.0,
+    "eval_HasAns_exact": 36.40691556001002,
+    "eval_HasAns_f1": 36.53303265681116,
+    "eval_HasAns_total": 3991,
+    "eval_NoAns_exact": 76.65264928511354,
+    "eval_NoAns_f1": 76.65264928511354,
+    "eval_NoAns_total": 5945,
+    "eval_best_exact": 60.829307568438004,
+    "eval_best_exact_thresh": 0.0,
+    "eval_best_f1": 60.87996511003758,
+    "eval_best_f1_thresh": 0.0,
+    "eval_exact": 60.487117552334944,
+    "eval_f1": 60.53777509393452,
+    "eval_runtime": 37.7571,
+    "eval_samples": 10637,
+    "eval_samples_per_second": 281.722,
+    "eval_steps_per_second": 35.225,
+    "eval_total": 9936
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7828898b0efe20f1392c8ac7d18495b19608784f825cc59a3c39dabfe397afd
+size 406737680

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,56 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "extra_special_tokens": {},
+  "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]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 9.414718117765632e+16,
+    "train_loss": 0.0,
+    "train_runtime": 0.003,
+    "train_samples": 96082,
+    "train_samples_per_second": 159489123.369,
+    "train_steps_per_second": 13291036.935
+}

trainer_state.json

@@ -0,0 +1,602 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 40035,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.062445360309728984,
+      "grad_norm": 14.40565299987793,
+      "learning_rate": 2.9625327838141625e-05,
+      "loss": 1.9858,
+      "step": 500
+    },
+    {
+      "epoch": 0.12489072061945797,
+      "grad_norm": 19.097322463989258,
+      "learning_rate": 2.9250655676283253e-05,
+      "loss": 1.5149,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18733608092918697,
+      "grad_norm": 15.344030380249023,
+      "learning_rate": 2.887598351442488e-05,
+      "loss": 1.4258,
+      "step": 1500
+    },
+    {
+      "epoch": 0.24978144123891594,
+      "grad_norm": 22.120119094848633,
+      "learning_rate": 2.8501311352566505e-05,
+      "loss": 1.3884,
+      "step": 2000
+    },
+    {
+      "epoch": 0.31222680154864496,
+      "grad_norm": 15.072545051574707,
+      "learning_rate": 2.812663919070813e-05,
+      "loss": 1.3306,
+      "step": 2500
+    },
+    {
+      "epoch": 0.37467216185837393,
+      "grad_norm": 15.24660587310791,
+      "learning_rate": 2.7751967028849757e-05,
+      "loss": 1.2959,
+      "step": 3000
+    },
+    {
+      "epoch": 0.4371175221681029,
+      "grad_norm": 13.45875072479248,
+      "learning_rate": 2.7377294866991385e-05,
+      "loss": 1.2756,
+      "step": 3500
+    },
+    {
+      "epoch": 0.49956288247783187,
+      "grad_norm": 12.797966003417969,
+      "learning_rate": 2.700262270513301e-05,
+      "loss": 1.2815,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5620082427875609,
+      "grad_norm": 21.160541534423828,
+      "learning_rate": 2.6627950543274633e-05,
+      "loss": 1.2025,
+      "step": 4500
+    },
+    {
+      "epoch": 0.6244536030972899,
+      "grad_norm": 13.691265106201172,
+      "learning_rate": 2.625327838141626e-05,
+      "loss": 1.1658,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6868989634070188,
+      "grad_norm": 21.028295516967773,
+      "learning_rate": 2.587860621955789e-05,
+      "loss": 1.1849,
+      "step": 5500
+    },
+    {
+      "epoch": 0.7493443237167479,
+      "grad_norm": 15.639451026916504,
+      "learning_rate": 2.5503934057699513e-05,
+      "loss": 1.154,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8117896840264769,
+      "grad_norm": 15.77192497253418,
+      "learning_rate": 2.5129261895841137e-05,
+      "loss": 1.1657,
+      "step": 6500
+    },
+    {
+      "epoch": 0.8742350443362058,
+      "grad_norm": 19.546422958374023,
+      "learning_rate": 2.4754589733982765e-05,
+      "loss": 1.1329,
+      "step": 7000
+    },
+    {
+      "epoch": 0.9366804046459348,
+      "grad_norm": 11.490877151489258,
+      "learning_rate": 2.4379917572124393e-05,
+      "loss": 1.1304,
+      "step": 7500
+    },
+    {
+      "epoch": 0.9991257649556637,
+      "grad_norm": 13.906126022338867,
+      "learning_rate": 2.4005245410266017e-05,
+      "loss": 1.0877,
+      "step": 8000
+    },
+    {
+      "epoch": 1.0615711252653928,
+      "grad_norm": 22.66297721862793,
+      "learning_rate": 2.3630573248407645e-05,
+      "loss": 0.8364,
+      "step": 8500
+    },
+    {
+      "epoch": 1.1240164855751218,
+      "grad_norm": 21.926162719726562,
+      "learning_rate": 2.325590108654927e-05,
+      "loss": 0.8493,
+      "step": 9000
+    },
+    {
+      "epoch": 1.1864618458848508,
+      "grad_norm": 21.4632625579834,
+      "learning_rate": 2.2881228924690897e-05,
+      "loss": 0.8424,
+      "step": 9500
+    },
+    {
+      "epoch": 1.2489072061945796,
+      "grad_norm": 19.286104202270508,
+      "learning_rate": 2.250655676283252e-05,
+      "loss": 0.856,
+      "step": 10000
+    },
+    {
+      "epoch": 1.3113525665043086,
+      "grad_norm": 35.93063735961914,
+      "learning_rate": 2.213188460097415e-05,
+      "loss": 0.8289,
+      "step": 10500
+    },
+    {
+      "epoch": 1.3737979268140377,
+      "grad_norm": 24.366748809814453,
+      "learning_rate": 2.1757212439115773e-05,
+      "loss": 0.868,
+      "step": 11000
+    },
+    {
+      "epoch": 1.4362432871237667,
+      "grad_norm": 22.02488136291504,
+      "learning_rate": 2.13825402772574e-05,
+      "loss": 0.841,
+      "step": 11500
+    },
+    {
+      "epoch": 1.4986886474334957,
+      "grad_norm": 54.16468811035156,
+      "learning_rate": 2.1007868115399025e-05,
+      "loss": 0.8262,
+      "step": 12000
+    },
+    {
+      "epoch": 1.5611340077432247,
+      "grad_norm": 27.68937873840332,
+      "learning_rate": 2.0633195953540653e-05,
+      "loss": 0.8225,
+      "step": 12500
+    },
+    {
+      "epoch": 1.6235793680529538,
+      "grad_norm": 19.883024215698242,
+      "learning_rate": 2.0258523791682277e-05,
+      "loss": 0.8412,
+      "step": 13000
+    },
+    {
+      "epoch": 1.6860247283626828,
+      "grad_norm": 25.48287010192871,
+      "learning_rate": 1.9883851629823905e-05,
+      "loss": 0.8559,
+      "step": 13500
+    },
+    {
+      "epoch": 1.7484700886724116,
+      "grad_norm": 25.736173629760742,
+      "learning_rate": 1.9509179467965533e-05,
+      "loss": 0.798,
+      "step": 14000
+    },
+    {
+      "epoch": 1.8109154489821406,
+      "grad_norm": 15.345009803771973,
+      "learning_rate": 1.9134507306107157e-05,
+      "loss": 0.8568,
+      "step": 14500
+    },
+    {
+      "epoch": 1.8733608092918697,
+      "grad_norm": 13.86083698272705,
+      "learning_rate": 1.875983514424878e-05,
+      "loss": 0.8144,
+      "step": 15000
+    },
+    {
+      "epoch": 1.9358061696015985,
+      "grad_norm": 21.71160316467285,
+      "learning_rate": 1.838516298239041e-05,
+      "loss": 0.8484,
+      "step": 15500
+    },
+    {
+      "epoch": 1.9982515299113275,
+      "grad_norm": 13.77094841003418,
+      "learning_rate": 1.8010490820532037e-05,
+      "loss": 0.8502,
+      "step": 16000
+    },
+    {
+      "epoch": 2.0606968902210565,
+      "grad_norm": 21.91532325744629,
+      "learning_rate": 1.763581865867366e-05,
+      "loss": 0.5608,
+      "step": 16500
+    },
+    {
+      "epoch": 2.1231422505307855,
+      "grad_norm": 19.61579704284668,
+      "learning_rate": 1.7261146496815285e-05,
+      "loss": 0.5345,
+      "step": 17000
+    },
+    {
+      "epoch": 2.1855876108405146,
+      "grad_norm": 17.571279525756836,
+      "learning_rate": 1.6886474334956913e-05,
+      "loss": 0.5251,
+      "step": 17500
+    },
+    {
+      "epoch": 2.2480329711502436,
+      "grad_norm": 45.33535385131836,
+      "learning_rate": 1.651180217309854e-05,
+      "loss": 0.565,
+      "step": 18000
+    },
+    {
+      "epoch": 2.3104783314599726,
+      "grad_norm": 15.158855438232422,
+      "learning_rate": 1.6137130011240165e-05,
+      "loss": 0.5472,
+      "step": 18500
+    },
+    {
+      "epoch": 2.3729236917697016,
+      "grad_norm": 17.102876663208008,
+      "learning_rate": 1.576245784938179e-05,
+      "loss": 0.5638,
+      "step": 19000
+    },
+    {
+      "epoch": 2.4353690520794307,
+      "grad_norm": 34.022037506103516,
+      "learning_rate": 1.5387785687523417e-05,
+      "loss": 0.5259,
+      "step": 19500
+    },
+    {
+      "epoch": 2.4978144123891592,
+      "grad_norm": 20.363927841186523,
+      "learning_rate": 1.5013113525665045e-05,
+      "loss": 0.5672,
+      "step": 20000
+    },
+    {
+      "epoch": 2.5602597726988883,
+      "grad_norm": 26.551931381225586,
+      "learning_rate": 1.4638441363806669e-05,
+      "loss": 0.5642,
+      "step": 20500
+    },
+    {
+      "epoch": 2.6227051330086173,
+      "grad_norm": 37.67859649658203,
+      "learning_rate": 1.4263769201948297e-05,
+      "loss": 0.5836,
+      "step": 21000
+    },
+    {
+      "epoch": 2.6851504933183463,
+      "grad_norm": 23.416738510131836,
+      "learning_rate": 1.3889097040089921e-05,
+      "loss": 0.5932,
+      "step": 21500
+    },
+    {
+      "epoch": 2.7475958536280753,
+      "grad_norm": 37.503047943115234,
+      "learning_rate": 1.3514424878231549e-05,
+      "loss": 0.5601,
+      "step": 22000
+    },
+    {
+      "epoch": 2.8100412139378044,
+      "grad_norm": 26.307445526123047,
+      "learning_rate": 1.3139752716373173e-05,
+      "loss": 0.5784,
+      "step": 22500
+    },
+    {
+      "epoch": 2.8724865742475334,
+      "grad_norm": 15.568779945373535,
+      "learning_rate": 1.27650805545148e-05,
+      "loss": 0.5613,
+      "step": 23000
+    },
+    {
+      "epoch": 2.9349319345572624,
+      "grad_norm": 19.449880599975586,
+      "learning_rate": 1.2390408392656425e-05,
+      "loss": 0.5597,
+      "step": 23500
+    },
+    {
+      "epoch": 2.9973772948669914,
+      "grad_norm": 22.43405532836914,
+      "learning_rate": 1.2015736230798053e-05,
+      "loss": 0.5637,
+      "step": 24000
+    },
+    {
+      "epoch": 3.0598226551767205,
+      "grad_norm": 45.42557907104492,
+      "learning_rate": 1.1641064068939677e-05,
+      "loss": 0.3605,
+      "step": 24500
+    },
+    {
+      "epoch": 3.1222680154864495,
+      "grad_norm": 51.729000091552734,
+      "learning_rate": 1.1266391907081305e-05,
+      "loss": 0.3556,
+      "step": 25000
+    },
+    {
+      "epoch": 3.1847133757961785,
+      "grad_norm": 11.632122993469238,
+      "learning_rate": 1.0891719745222929e-05,
+      "loss": 0.3751,
+      "step": 25500
+    },
+    {
+      "epoch": 3.2471587361059076,
+      "grad_norm": 6.7493743896484375,
+      "learning_rate": 1.0517047583364557e-05,
+      "loss": 0.3554,
+      "step": 26000
+    },
+    {
+      "epoch": 3.309604096415636,
+      "grad_norm": 9.528502464294434,
+      "learning_rate": 1.0142375421506183e-05,
+      "loss": 0.3463,
+      "step": 26500
+    },
+    {
+      "epoch": 3.372049456725365,
+      "grad_norm": 28.454116821289062,
+      "learning_rate": 9.767703259647809e-06,
+      "loss": 0.3823,
+      "step": 27000
+    },
+    {
+      "epoch": 3.434494817035094,
+      "grad_norm": 28.30170440673828,
+      "learning_rate": 9.393031097789435e-06,
+      "loss": 0.3529,
+      "step": 27500
+    },
+    {
+      "epoch": 3.496940177344823,
+      "grad_norm": 14.024445533752441,
+      "learning_rate": 9.018358935931061e-06,
+      "loss": 0.3774,
+      "step": 28000
+    },
+    {
+      "epoch": 3.5593855376545522,
+      "grad_norm": 9.80344295501709,
+      "learning_rate": 8.643686774072687e-06,
+      "loss": 0.3471,
+      "step": 28500
+    },
+    {
+      "epoch": 3.6218308979642813,
+      "grad_norm": 18.51318359375,
+      "learning_rate": 8.269014612214313e-06,
+      "loss": 0.3514,
+      "step": 29000
+    },
+    {
+      "epoch": 3.6842762582740103,
+      "grad_norm": 23.305683135986328,
+      "learning_rate": 7.894342450355939e-06,
+      "loss": 0.3539,
+      "step": 29500
+    },
+    {
+      "epoch": 3.7467216185837393,
+      "grad_norm": 31.820262908935547,
+      "learning_rate": 7.519670288497564e-06,
+      "loss": 0.3364,
+      "step": 30000
+    },
+    {
+      "epoch": 3.8091669788934683,
+      "grad_norm": 28.33430290222168,
+      "learning_rate": 7.144998126639191e-06,
+      "loss": 0.3607,
+      "step": 30500
+    },
+    {
+      "epoch": 3.8716123392031974,
+      "grad_norm": 30.772987365722656,
+      "learning_rate": 6.770325964780817e-06,
+      "loss": 0.3314,
+      "step": 31000
+    },
+    {
+      "epoch": 3.934057699512926,
+      "grad_norm": 16.197298049926758,
+      "learning_rate": 6.395653802922443e-06,
+      "loss": 0.3449,
+      "step": 31500
+    },
+    {
+      "epoch": 3.996503059822655,
+      "grad_norm": 46.485103607177734,
+      "learning_rate": 6.020981641064069e-06,
+      "loss": 0.3263,
+      "step": 32000
+    },
+    {
+      "epoch": 4.058948420132384,
+      "grad_norm": 51.467411041259766,
+      "learning_rate": 5.646309479205695e-06,
+      "loss": 0.2165,
+      "step": 32500
+    },
+    {
+      "epoch": 4.121393780442113,
+      "grad_norm": 3.3639559745788574,
+      "learning_rate": 5.271637317347321e-06,
+      "loss": 0.2134,
+      "step": 33000
+    },
+    {
+      "epoch": 4.183839140751842,
+      "grad_norm": 20.382158279418945,
+      "learning_rate": 4.896965155488947e-06,
+      "loss": 0.229,
+      "step": 33500
+    },
+    {
+      "epoch": 4.246284501061571,
+      "grad_norm": 22.384031295776367,
+      "learning_rate": 4.522292993630573e-06,
+      "loss": 0.2255,
+      "step": 34000
+    },
+    {
+      "epoch": 4.3087298613713,
+      "grad_norm": 2.972531318664551,
+      "learning_rate": 4.147620831772199e-06,
+      "loss": 0.2167,
+      "step": 34500
+    },
+    {
+      "epoch": 4.371175221681029,
+      "grad_norm": 19.604764938354492,
+      "learning_rate": 3.772948669913825e-06,
+      "loss": 0.2192,
+      "step": 35000
+    },
+    {
+      "epoch": 4.433620581990758,
+      "grad_norm": 16.23500633239746,
+      "learning_rate": 3.3982765080554515e-06,
+      "loss": 0.2242,
+      "step": 35500
+    },
+    {
+      "epoch": 4.496065942300487,
+      "grad_norm": 8.235413551330566,
+      "learning_rate": 3.0236043461970775e-06,
+      "loss": 0.2196,
+      "step": 36000
+    },
+    {
+      "epoch": 4.558511302610216,
+      "grad_norm": 22.458770751953125,
+      "learning_rate": 2.6489321843387035e-06,
+      "loss": 0.2244,
+      "step": 36500
+    },
+    {
+      "epoch": 4.620956662919945,
+      "grad_norm": 39.24953842163086,
+      "learning_rate": 2.2742600224803295e-06,
+      "loss": 0.2076,
+      "step": 37000
+    },
+    {
+      "epoch": 4.683402023229674,
+      "grad_norm": 10.973857879638672,
+      "learning_rate": 1.8995878606219555e-06,
+      "loss": 0.2288,
+      "step": 37500
+    },
+    {
+      "epoch": 4.745847383539403,
+      "grad_norm": 11.058865547180176,
+      "learning_rate": 1.5249156987635818e-06,
+      "loss": 0.214,
+      "step": 38000
+    },
+    {
+      "epoch": 4.808292743849132,
+      "grad_norm": 47.875057220458984,
+      "learning_rate": 1.150243536905208e-06,
+      "loss": 0.2237,
+      "step": 38500
+    },
+    {
+      "epoch": 4.870738104158861,
+      "grad_norm": 55.14733123779297,
+      "learning_rate": 7.755713750468341e-07,
+      "loss": 0.2228,
+      "step": 39000
+    },
+    {
+      "epoch": 4.93318346446859,
+      "grad_norm": 3.3354523181915283,
+      "learning_rate": 4.008992131884601e-07,
+      "loss": 0.2024,
+      "step": 39500
+    },
+    {
+      "epoch": 4.9956288247783185,
+      "grad_norm": 62.27578353881836,
+      "learning_rate": 2.6227051330086176e-08,
+      "loss": 0.2024,
+      "step": 40000
+    },
+    {
+      "epoch": 5.0,
+      "step": 40035,
+      "total_flos": 9.414718117765632e+16,
+      "train_loss": 0.0,
+      "train_runtime": 0.003,
+      "train_samples_per_second": 159489123.369,
+      "train_steps_per_second": 13291036.935
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 40035,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 9.414718117765632e+16,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a5c76567ecb5d2c537b2195c3209a227b730343ece8b2e78d7d497310ab2e666
+size 5368