Upload folder using huggingface_hub

student_finetuned/checkpoint-282/config.json

@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "output_past": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 120
+    }
+  },
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 22557
+}

student_finetuned/checkpoint-282/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.51.3"
+}

student_finetuned/checkpoint-282/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b902ff392321f8b7ef9a1b9e12591d74125e98cd04e2b6cd9aec38649307716
+size 412679808

student_finetuned/checkpoint-282/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a6d898b50fbc032544a92bd56e8920b56fba1de580989acafc54e842b395a31
+size 825453498

student_finetuned/checkpoint-282/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3837a2b51525e412b7700c9c872dacba4f277c1a3292053e3a1ccd8b5d06bcc4
+size 14244

student_finetuned/checkpoint-282/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82fbb8a41699527f8e897a6a4653fd200a409dcfcca603338998c5883c75ff74
+size 988

student_finetuned/checkpoint-282/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ad6dd2b5727fe8a6f4108f69903c823118467fa11ae53cc14acdc6b5095985b
+size 1064

student_finetuned/checkpoint-282/special_tokens_map.json

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

student_finetuned/checkpoint-282/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

student_finetuned/checkpoint-282/trainer_state.json

@@ -0,0 +1,230 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 282,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10638297872340426,
+      "grad_norm": 2.73763108253479,
+      "learning_rate": 4.840425531914894e-05,
+      "loss": 7.0593,
+      "step": 10
+    },
+    {
+      "epoch": 0.2127659574468085,
+      "grad_norm": 4.184208869934082,
+      "learning_rate": 4.663120567375887e-05,
+      "loss": 4.3509,
+      "step": 20
+    },
+    {
+      "epoch": 0.3191489361702128,
+      "grad_norm": 2.815650224685669,
+      "learning_rate": 4.48581560283688e-05,
+      "loss": 2.3531,
+      "step": 30
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 1.4433400630950928,
+      "learning_rate": 4.3085106382978725e-05,
+      "loss": 1.3585,
+      "step": 40
+    },
+    {
+      "epoch": 0.5319148936170213,
+      "grad_norm": 1.3113492727279663,
+      "learning_rate": 4.1312056737588654e-05,
+      "loss": 0.8143,
+      "step": 50
+    },
+    {
+      "epoch": 0.6382978723404256,
+      "grad_norm": 1.1828652620315552,
+      "learning_rate": 3.953900709219858e-05,
+      "loss": 0.7293,
+      "step": 60
+    },
+    {
+      "epoch": 0.7446808510638298,
+      "grad_norm": 1.0307129621505737,
+      "learning_rate": 3.776595744680852e-05,
+      "loss": 0.5471,
+      "step": 70
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.7392168045043945,
+      "learning_rate": 3.599290780141844e-05,
+      "loss": 0.5001,
+      "step": 80
+    },
+    {
+      "epoch": 0.9574468085106383,
+      "grad_norm": 1.0385117530822754,
+      "learning_rate": 3.4219858156028374e-05,
+      "loss": 0.4176,
+      "step": 90
+    },
+    {
+      "epoch": 1.0638297872340425,
+      "grad_norm": 0.8549280166625977,
+      "learning_rate": 3.2446808510638296e-05,
+      "loss": 0.4753,
+      "step": 100
+    },
+    {
+      "epoch": 1.1702127659574468,
+      "grad_norm": 0.6353434920310974,
+      "learning_rate": 3.067375886524823e-05,
+      "loss": 0.3597,
+      "step": 110
+    },
+    {
+      "epoch": 1.2765957446808511,
+      "grad_norm": 0.5479038953781128,
+      "learning_rate": 2.8900709219858156e-05,
+      "loss": 0.332,
+      "step": 120
+    },
+    {
+      "epoch": 1.3829787234042552,
+      "grad_norm": 0.7110474705696106,
+      "learning_rate": 2.7127659574468084e-05,
+      "loss": 0.4116,
+      "step": 130
+    },
+    {
+      "epoch": 1.4893617021276595,
+      "grad_norm": 0.7794738411903381,
+      "learning_rate": 2.5354609929078016e-05,
+      "loss": 0.3355,
+      "step": 140
+    },
+    {
+      "epoch": 1.5957446808510638,
+      "grad_norm": 0.5863938927650452,
+      "learning_rate": 2.3581560283687945e-05,
+      "loss": 0.3371,
+      "step": 150
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 1.5034053325653076,
+      "learning_rate": 2.1808510638297873e-05,
+      "loss": 0.4327,
+      "step": 160
+    },
+    {
+      "epoch": 1.8085106382978724,
+      "grad_norm": 0.534168541431427,
+      "learning_rate": 2.0035460992907805e-05,
+      "loss": 0.3472,
+      "step": 170
+    },
+    {
+      "epoch": 1.9148936170212765,
+      "grad_norm": 0.5549598336219788,
+      "learning_rate": 1.8262411347517733e-05,
+      "loss": 0.3687,
+      "step": 180
+    },
+    {
+      "epoch": 2.021276595744681,
+      "grad_norm": 0.5196494460105896,
+      "learning_rate": 1.6489361702127658e-05,
+      "loss": 0.2445,
+      "step": 190
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 0.5457848310470581,
+      "learning_rate": 1.4716312056737588e-05,
+      "loss": 0.2548,
+      "step": 200
+    },
+    {
+      "epoch": 2.2340425531914896,
+      "grad_norm": 0.5511345863342285,
+      "learning_rate": 1.2943262411347517e-05,
+      "loss": 0.3374,
+      "step": 210
+    },
+    {
+      "epoch": 2.3404255319148937,
+      "grad_norm": 0.4927542805671692,
+      "learning_rate": 1.1170212765957447e-05,
+      "loss": 0.3462,
+      "step": 220
+    },
+    {
+      "epoch": 2.4468085106382977,
+      "grad_norm": 0.5920850038528442,
+      "learning_rate": 9.397163120567375e-06,
+      "loss": 0.2803,
+      "step": 230
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 0.5556482076644897,
+      "learning_rate": 7.6241134751773054e-06,
+      "loss": 0.3066,
+      "step": 240
+    },
+    {
+      "epoch": 2.6595744680851063,
+      "grad_norm": 0.4986216723918915,
+      "learning_rate": 5.851063829787235e-06,
+      "loss": 0.3169,
+      "step": 250
+    },
+    {
+      "epoch": 2.7659574468085104,
+      "grad_norm": 0.7671786546707153,
+      "learning_rate": 4.078014184397164e-06,
+      "loss": 0.307,
+      "step": 260
+    },
+    {
+      "epoch": 2.872340425531915,
+      "grad_norm": 0.8555495142936707,
+      "learning_rate": 2.304964539007092e-06,
+      "loss": 0.2727,
+      "step": 270
+    },
+    {
+      "epoch": 2.978723404255319,
+      "grad_norm": 0.5921739935874939,
+      "learning_rate": 5.319148936170213e-07,
+      "loss": 0.3595,
+      "step": 280
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 282,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 585555443712000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

student_finetuned/checkpoint-282/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ad1542a29a393c2cf4c700b16fe2ec76a2dc0c61f7e0b88372a33769a5f036c
+size 5304

student_finetuned/config.json

@@ -0,0 +1,41 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "output_past": true,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 120
+    }
+  },
+  "tokenizer_class": "BertTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 22557
+}

student_finetuned/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.51.3"
+}

student_finetuned/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b902ff392321f8b7ef9a1b9e12591d74125e98cd04e2b6cd9aec38649307716
+size 412679808

student_finetuned/special_tokens_map.json

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

student_finetuned/tokenizer_config.json

@@ -0,0 +1,58 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

student_lora_finetuned/README.md

@@ -0,0 +1,202 @@
+---
+base_model: model/student_finetuned
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

student_lora_finetuned/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "model/student_finetuned",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

student_lora_finetuned/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bf506514e5640e36238ee90118f9a45f497597d388bf7135212bacb05ad56ac
+size 1182680

student_lora_finetuned/checkpoint-930/README.md

@@ -0,0 +1,202 @@
+---
+base_model: model/student_finetuned
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.15.2

student_lora_finetuned/checkpoint-930/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "model/student_finetuned",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": true,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "c_attn"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

student_lora_finetuned/checkpoint-930/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bf506514e5640e36238ee90118f9a45f497597d388bf7135212bacb05ad56ac
+size 1182680

student_lora_finetuned/checkpoint-930/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b65d10191a646b90e6f8d0e76d5d916100d26b21870c5759e1b0c2084cc14b2e
+size 2379926

student_lora_finetuned/checkpoint-930/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c66f7c9b9ebf9edafc6b4316956e96432617d138b481b77fa1dff4b94baa30f
+size 14244

student_lora_finetuned/checkpoint-930/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce4e937afc9a48808fd42bd37a24978f04dd25b1d338a7919ad7a288b47ac94
+size 988

student_lora_finetuned/checkpoint-930/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:845303d8f987d5364bdfcd6872d6713369fd584221ee35404491c9065b6ba966
+size 1064

student_lora_finetuned/checkpoint-930/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

student_lora_finetuned/checkpoint-930/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

student_lora_finetuned/checkpoint-930/trainer_state.json

@@ -0,0 +1,1336 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 930,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.026881720430107527,
+      "grad_norm": 7.517879009246826,
+      "learning_rate": 0.00019913978494623657,
+      "loss": 25.7069,
+      "step": 5
+    },
+    {
+      "epoch": 0.053763440860215055,
+      "grad_norm": 9.280155181884766,
+      "learning_rate": 0.00019806451612903227,
+      "loss": 23.6659,
+      "step": 10
+    },
+    {
+      "epoch": 0.08064516129032258,
+      "grad_norm": 12.674245834350586,
+      "learning_rate": 0.00019698924731182798,
+      "loss": 20.9623,
+      "step": 15
+    },
+    {
+      "epoch": 0.10752688172043011,
+      "grad_norm": 10.096162796020508,
+      "learning_rate": 0.00019591397849462368,
+      "loss": 19.079,
+      "step": 20
+    },
+    {
+      "epoch": 0.13440860215053763,
+      "grad_norm": 6.408749103546143,
+      "learning_rate": 0.00019483870967741936,
+      "loss": 17.2508,
+      "step": 25
+    },
+    {
+      "epoch": 0.16129032258064516,
+      "grad_norm": 3.341172456741333,
+      "learning_rate": 0.00019376344086021507,
+      "loss": 16.2135,
+      "step": 30
+    },
+    {
+      "epoch": 0.1881720430107527,
+      "grad_norm": 2.305873155593872,
+      "learning_rate": 0.00019268817204301077,
+      "loss": 15.5422,
+      "step": 35
+    },
+    {
+      "epoch": 0.21505376344086022,
+      "grad_norm": 2.549955129623413,
+      "learning_rate": 0.00019161290322580645,
+      "loss": 15.1318,
+      "step": 40
+    },
+    {
+      "epoch": 0.24193548387096775,
+      "grad_norm": 2.837451457977295,
+      "learning_rate": 0.00019053763440860216,
+      "loss": 14.4746,
+      "step": 45
+    },
+    {
+      "epoch": 0.26881720430107525,
+      "grad_norm": 2.3930716514587402,
+      "learning_rate": 0.00018946236559139786,
+      "loss": 14.0982,
+      "step": 50
+    },
+    {
+      "epoch": 0.2956989247311828,
+      "grad_norm": 2.1569137573242188,
+      "learning_rate": 0.00018838709677419354,
+      "loss": 13.6985,
+      "step": 55
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 2.421198844909668,
+      "learning_rate": 0.00018731182795698925,
+      "loss": 13.1276,
+      "step": 60
+    },
+    {
+      "epoch": 0.34946236559139787,
+      "grad_norm": 2.6210012435913086,
+      "learning_rate": 0.00018623655913978495,
+      "loss": 12.6512,
+      "step": 65
+    },
+    {
+      "epoch": 0.3763440860215054,
+      "grad_norm": 3.0429224967956543,
+      "learning_rate": 0.00018516129032258066,
+      "loss": 11.9908,
+      "step": 70
+    },
+    {
+      "epoch": 0.4032258064516129,
+      "grad_norm": 3.4718668460845947,
+      "learning_rate": 0.00018408602150537634,
+      "loss": 11.2452,
+      "step": 75
+    },
+    {
+      "epoch": 0.43010752688172044,
+      "grad_norm": 4.288656234741211,
+      "learning_rate": 0.00018301075268817204,
+      "loss": 10.4865,
+      "step": 80
+    },
+    {
+      "epoch": 0.45698924731182794,
+      "grad_norm": 5.515636444091797,
+      "learning_rate": 0.00018193548387096775,
+      "loss": 9.4616,
+      "step": 85
+    },
+    {
+      "epoch": 0.4838709677419355,
+      "grad_norm": 8.327155113220215,
+      "learning_rate": 0.00018086021505376345,
+      "loss": 8.167,
+      "step": 90
+    },
+    {
+      "epoch": 0.510752688172043,
+      "grad_norm": 10.667390823364258,
+      "learning_rate": 0.00017978494623655916,
+      "loss": 6.0323,
+      "step": 95
+    },
+    {
+      "epoch": 0.5376344086021505,
+      "grad_norm": 8.344476699829102,
+      "learning_rate": 0.00017870967741935484,
+      "loss": 3.804,
+      "step": 100
+    },
+    {
+      "epoch": 0.5645161290322581,
+      "grad_norm": 5.413161754608154,
+      "learning_rate": 0.00017763440860215054,
+      "loss": 2.9261,
+      "step": 105
+    },
+    {
+      "epoch": 0.5913978494623656,
+      "grad_norm": 6.431153297424316,
+      "learning_rate": 0.00017655913978494625,
+      "loss": 2.3795,
+      "step": 110
+    },
+    {
+      "epoch": 0.6182795698924731,
+      "grad_norm": 4.849709987640381,
+      "learning_rate": 0.00017548387096774195,
+      "loss": 1.7969,
+      "step": 115
+    },
+    {
+      "epoch": 0.6451612903225806,
+      "grad_norm": 1.55392324924469,
+      "learning_rate": 0.00017440860215053766,
+      "loss": 1.54,
+      "step": 120
+    },
+    {
+      "epoch": 0.6720430107526881,
+      "grad_norm": 0.9671318531036377,
+      "learning_rate": 0.00017333333333333334,
+      "loss": 1.3664,
+      "step": 125
+    },
+    {
+      "epoch": 0.6989247311827957,
+      "grad_norm": 0.7121822834014893,
+      "learning_rate": 0.00017225806451612904,
+      "loss": 1.2365,
+      "step": 130
+    },
+    {
+      "epoch": 0.7258064516129032,
+      "grad_norm": 0.5870563983917236,
+      "learning_rate": 0.00017118279569892475,
+      "loss": 1.1677,
+      "step": 135
+    },
+    {
+      "epoch": 0.7526881720430108,
+      "grad_norm": 0.5803866386413574,
+      "learning_rate": 0.00017010752688172045,
+      "loss": 1.11,
+      "step": 140
+    },
+    {
+      "epoch": 0.7795698924731183,
+      "grad_norm": 0.5652913451194763,
+      "learning_rate": 0.00016903225806451616,
+      "loss": 1.0724,
+      "step": 145
+    },
+    {
+      "epoch": 0.8064516129032258,
+      "grad_norm": 0.5393310785293579,
+      "learning_rate": 0.00016795698924731184,
+      "loss": 1.0111,
+      "step": 150
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.6877985000610352,
+      "learning_rate": 0.00016688172043010751,
+      "loss": 0.986,
+      "step": 155
+    },
+    {
+      "epoch": 0.8602150537634409,
+      "grad_norm": 0.7941627502441406,
+      "learning_rate": 0.00016580645161290322,
+      "loss": 0.9341,
+      "step": 160
+    },
+    {
+      "epoch": 0.8870967741935484,
+      "grad_norm": 0.635101318359375,
+      "learning_rate": 0.00016473118279569893,
+      "loss": 0.9572,
+      "step": 165
+    },
+    {
+      "epoch": 0.9139784946236559,
+      "grad_norm": 0.8213858604431152,
+      "learning_rate": 0.00016365591397849463,
+      "loss": 0.9316,
+      "step": 170
+    },
+    {
+      "epoch": 0.9408602150537635,
+      "grad_norm": 0.5716636776924133,
+      "learning_rate": 0.00016258064516129034,
+      "loss": 0.8542,
+      "step": 175
+    },
+    {
+      "epoch": 0.967741935483871,
+      "grad_norm": 0.4731377363204956,
+      "learning_rate": 0.00016150537634408601,
+      "loss": 0.8484,
+      "step": 180
+    },
+    {
+      "epoch": 0.9946236559139785,
+      "grad_norm": 0.49750402569770813,
+      "learning_rate": 0.00016043010752688172,
+      "loss": 0.8229,
+      "step": 185
+    },
+    {
+      "epoch": 1.021505376344086,
+      "grad_norm": 0.4677596092224121,
+      "learning_rate": 0.00015935483870967743,
+      "loss": 0.8301,
+      "step": 190
+    },
+    {
+      "epoch": 1.0483870967741935,
+      "grad_norm": 0.5717447996139526,
+      "learning_rate": 0.00015827956989247313,
+      "loss": 0.7741,
+      "step": 195
+    },
+    {
+      "epoch": 1.075268817204301,
+      "grad_norm": 0.5728289484977722,
+      "learning_rate": 0.0001572043010752688,
+      "loss": 0.7707,
+      "step": 200
+    },
+    {
+      "epoch": 1.1021505376344085,
+      "grad_norm": 0.5678717494010925,
+      "learning_rate": 0.00015612903225806451,
+      "loss": 0.765,
+      "step": 205
+    },
+    {
+      "epoch": 1.129032258064516,
+      "grad_norm": 0.6754461526870728,
+      "learning_rate": 0.00015505376344086022,
+      "loss": 0.7611,
+      "step": 210
+    },
+    {
+      "epoch": 1.1559139784946237,
+      "grad_norm": 0.9893506169319153,
+      "learning_rate": 0.00015397849462365593,
+      "loss": 0.7654,
+      "step": 215
+    },
+    {
+      "epoch": 1.1827956989247312,
+      "grad_norm": 0.6708158254623413,
+      "learning_rate": 0.00015290322580645163,
+      "loss": 0.7437,
+      "step": 220
+    },
+    {
+      "epoch": 1.2096774193548387,
+      "grad_norm": 0.5096806883811951,
+      "learning_rate": 0.0001518279569892473,
+      "loss": 0.7001,
+      "step": 225
+    },
+    {
+      "epoch": 1.2365591397849462,
+      "grad_norm": 0.5710135102272034,
+      "learning_rate": 0.00015075268817204301,
+      "loss": 0.7156,
+      "step": 230
+    },
+    {
+      "epoch": 1.2634408602150538,
+      "grad_norm": 0.4659282863140106,
+      "learning_rate": 0.00014967741935483872,
+      "loss": 0.6673,
+      "step": 235
+    },
+    {
+      "epoch": 1.2903225806451613,
+      "grad_norm": 0.6818357706069946,
+      "learning_rate": 0.00014860215053763443,
+      "loss": 0.6982,
+      "step": 240
+    },
+    {
+      "epoch": 1.3172043010752688,
+      "grad_norm": 0.6473487615585327,
+      "learning_rate": 0.00014752688172043013,
+      "loss": 0.6886,
+      "step": 245
+    },
+    {
+      "epoch": 1.3440860215053765,
+      "grad_norm": 0.5552868247032166,
+      "learning_rate": 0.0001464516129032258,
+      "loss": 0.6913,
+      "step": 250
+    },
+    {
+      "epoch": 1.370967741935484,
+      "grad_norm": 0.5745120048522949,
+      "learning_rate": 0.00014537634408602151,
+      "loss": 0.6605,
+      "step": 255
+    },
+    {
+      "epoch": 1.3978494623655915,
+      "grad_norm": 0.4570547938346863,
+      "learning_rate": 0.00014430107526881722,
+      "loss": 0.6525,
+      "step": 260
+    },
+    {
+      "epoch": 1.424731182795699,
+      "grad_norm": 0.5155510902404785,
+      "learning_rate": 0.00014322580645161293,
+      "loss": 0.6236,
+      "step": 265
+    },
+    {
+      "epoch": 1.4516129032258065,
+      "grad_norm": 0.5411310195922852,
+      "learning_rate": 0.0001421505376344086,
+      "loss": 0.6688,
+      "step": 270
+    },
+    {
+      "epoch": 1.478494623655914,
+      "grad_norm": 0.5378429293632507,
+      "learning_rate": 0.0001410752688172043,
+      "loss": 0.6166,
+      "step": 275
+    },
+    {
+      "epoch": 1.5053763440860215,
+      "grad_norm": 0.6501957178115845,
+      "learning_rate": 0.00014,
+      "loss": 0.5889,
+      "step": 280
+    },
+    {
+      "epoch": 1.532258064516129,
+      "grad_norm": 0.5574774146080017,
+      "learning_rate": 0.0001389247311827957,
+      "loss": 0.6529,
+      "step": 285
+    },
+    {
+      "epoch": 1.5591397849462365,
+      "grad_norm": 0.4855782091617584,
+      "learning_rate": 0.0001378494623655914,
+      "loss": 0.6092,
+      "step": 290
+    },
+    {
+      "epoch": 1.586021505376344,
+      "grad_norm": 0.5358579754829407,
+      "learning_rate": 0.0001367741935483871,
+      "loss": 0.5836,
+      "step": 295
+    },
+    {
+      "epoch": 1.6129032258064515,
+      "grad_norm": 0.4744930565357208,
+      "learning_rate": 0.0001356989247311828,
+      "loss": 0.5813,
+      "step": 300
+    },
+    {
+      "epoch": 1.639784946236559,
+      "grad_norm": 0.5719123482704163,
+      "learning_rate": 0.0001346236559139785,
+      "loss": 0.6039,
+      "step": 305
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.49337533116340637,
+      "learning_rate": 0.0001335483870967742,
+      "loss": 0.5614,
+      "step": 310
+    },
+    {
+      "epoch": 1.6935483870967742,
+      "grad_norm": 0.6838189363479614,
+      "learning_rate": 0.0001324731182795699,
+      "loss": 0.5619,
+      "step": 315
+    },
+    {
+      "epoch": 1.7204301075268817,
+      "grad_norm": 0.5160232782363892,
+      "learning_rate": 0.0001313978494623656,
+      "loss": 0.5811,
+      "step": 320
+    },
+    {
+      "epoch": 1.7473118279569892,
+      "grad_norm": 0.8333256840705872,
+      "learning_rate": 0.0001303225806451613,
+      "loss": 0.5771,
+      "step": 325
+    },
+    {
+      "epoch": 1.7741935483870968,
+      "grad_norm": 0.9703850746154785,
+      "learning_rate": 0.000129247311827957,
+      "loss": 0.578,
+      "step": 330
+    },
+    {
+      "epoch": 1.8010752688172043,
+      "grad_norm": 0.6774953007698059,
+      "learning_rate": 0.0001281720430107527,
+      "loss": 0.5738,
+      "step": 335
+    },
+    {
+      "epoch": 1.827956989247312,
+      "grad_norm": 0.6810261011123657,
+      "learning_rate": 0.0001270967741935484,
+      "loss": 0.5823,
+      "step": 340
+    },
+    {
+      "epoch": 1.8548387096774195,
+      "grad_norm": 0.8924374580383301,
+      "learning_rate": 0.0001260215053763441,
+      "loss": 0.5535,
+      "step": 345
+    },
+    {
+      "epoch": 1.881720430107527,
+      "grad_norm": 0.7481217384338379,
+      "learning_rate": 0.00012494623655913978,
+      "loss": 0.5537,
+      "step": 350
+    },
+    {
+      "epoch": 1.9086021505376345,
+      "grad_norm": 0.8031575679779053,
+      "learning_rate": 0.0001238709677419355,
+      "loss": 0.538,
+      "step": 355
+    },
+    {
+      "epoch": 1.935483870967742,
+      "grad_norm": 1.2430750131607056,
+      "learning_rate": 0.0001227956989247312,
+      "loss": 0.5727,
+      "step": 360
+    },
+    {
+      "epoch": 1.9623655913978495,
+      "grad_norm": 0.8606559038162231,
+      "learning_rate": 0.0001217204301075269,
+      "loss": 0.5603,
+      "step": 365
+    },
+    {
+      "epoch": 1.989247311827957,
+      "grad_norm": 0.9421748518943787,
+      "learning_rate": 0.00012064516129032259,
+      "loss": 0.5462,
+      "step": 370
+    },
+    {
+      "epoch": 2.0161290322580645,
+      "grad_norm": 0.9712075591087341,
+      "learning_rate": 0.0001195698924731183,
+      "loss": 0.4992,
+      "step": 375
+    },
+    {
+      "epoch": 2.043010752688172,
+      "grad_norm": 0.6209003329277039,
+      "learning_rate": 0.00011849462365591399,
+      "loss": 0.5138,
+      "step": 380
+    },
+    {
+      "epoch": 2.0698924731182795,
+      "grad_norm": 1.1672589778900146,
+      "learning_rate": 0.00011741935483870967,
+      "loss": 0.5218,
+      "step": 385
+    },
+    {
+      "epoch": 2.096774193548387,
+      "grad_norm": 1.7826071977615356,
+      "learning_rate": 0.00011634408602150537,
+      "loss": 0.5599,
+      "step": 390
+    },
+    {
+      "epoch": 2.1236559139784945,
+      "grad_norm": 1.728200078010559,
+      "learning_rate": 0.00011526881720430108,
+      "loss": 0.4717,
+      "step": 395
+    },
+    {
+      "epoch": 2.150537634408602,
+      "grad_norm": 2.514089584350586,
+      "learning_rate": 0.00011419354838709677,
+      "loss": 0.527,
+      "step": 400
+    },
+    {
+      "epoch": 2.1774193548387095,
+      "grad_norm": 0.7007973790168762,
+      "learning_rate": 0.00011311827956989247,
+      "loss": 0.5024,
+      "step": 405
+    },
+    {
+      "epoch": 2.204301075268817,
+      "grad_norm": 0.7418361306190491,
+      "learning_rate": 0.00011204301075268817,
+      "loss": 0.4906,
+      "step": 410
+    },
+    {
+      "epoch": 2.2311827956989245,
+      "grad_norm": 1.0487796068191528,
+      "learning_rate": 0.00011096774193548387,
+      "loss": 0.4894,
+      "step": 415
+    },
+    {
+      "epoch": 2.258064516129032,
+      "grad_norm": 2.1650989055633545,
+      "learning_rate": 0.00010989247311827958,
+      "loss": 0.479,
+      "step": 420
+    },
+    {
+      "epoch": 2.28494623655914,
+      "grad_norm": 1.3648617267608643,
+      "learning_rate": 0.00010881720430107527,
+      "loss": 0.4844,
+      "step": 425
+    },
+    {
+      "epoch": 2.3118279569892475,
+      "grad_norm": 1.1497910022735596,
+      "learning_rate": 0.00010774193548387097,
+      "loss": 0.4692,
+      "step": 430
+    },
+    {
+      "epoch": 2.338709677419355,
+      "grad_norm": 0.6426465511322021,
+      "learning_rate": 0.00010666666666666667,
+      "loss": 0.496,
+      "step": 435
+    },
+    {
+      "epoch": 2.3655913978494625,
+      "grad_norm": 1.3800503015518188,
+      "learning_rate": 0.00010559139784946237,
+      "loss": 0.4621,
+      "step": 440
+    },
+    {
+      "epoch": 2.39247311827957,
+      "grad_norm": 1.3282463550567627,
+      "learning_rate": 0.00010451612903225806,
+      "loss": 0.4537,
+      "step": 445
+    },
+    {
+      "epoch": 2.4193548387096775,
+      "grad_norm": 0.9986529350280762,
+      "learning_rate": 0.00010344086021505377,
+      "loss": 0.4602,
+      "step": 450
+    },
+    {
+      "epoch": 2.446236559139785,
+      "grad_norm": 1.266798496246338,
+      "learning_rate": 0.00010236559139784947,
+      "loss": 0.4784,
+      "step": 455
+    },
+    {
+      "epoch": 2.4731182795698925,
+      "grad_norm": 1.2241142988204956,
+      "learning_rate": 0.00010129032258064517,
+      "loss": 0.4332,
+      "step": 460
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.4897130727767944,
+      "learning_rate": 0.00010021505376344087,
+      "loss": 0.4274,
+      "step": 465
+    },
+    {
+      "epoch": 2.5268817204301075,
+      "grad_norm": 1.2320371866226196,
+      "learning_rate": 9.913978494623656e-05,
+      "loss": 0.4431,
+      "step": 470
+    },
+    {
+      "epoch": 2.553763440860215,
+      "grad_norm": 1.0926082134246826,
+      "learning_rate": 9.806451612903226e-05,
+      "loss": 0.4504,
+      "step": 475
+    },
+    {
+      "epoch": 2.5806451612903225,
+      "grad_norm": 0.7217853665351868,
+      "learning_rate": 9.698924731182796e-05,
+      "loss": 0.4533,
+      "step": 480
+    },
+    {
+      "epoch": 2.60752688172043,
+      "grad_norm": 1.0090914964675903,
+      "learning_rate": 9.591397849462365e-05,
+      "loss": 0.3997,
+      "step": 485
+    },
+    {
+      "epoch": 2.6344086021505375,
+      "grad_norm": 1.9857970476150513,
+      "learning_rate": 9.483870967741936e-05,
+      "loss": 0.4439,
+      "step": 490
+    },
+    {
+      "epoch": 2.661290322580645,
+      "grad_norm": 0.9593686461448669,
+      "learning_rate": 9.376344086021506e-05,
+      "loss": 0.4554,
+      "step": 495
+    },
+    {
+      "epoch": 2.688172043010753,
+      "grad_norm": 0.6287310123443604,
+      "learning_rate": 9.268817204301076e-05,
+      "loss": 0.4206,
+      "step": 500
+    },
+    {
+      "epoch": 2.71505376344086,
+      "grad_norm": 0.6817049980163574,
+      "learning_rate": 9.161290322580646e-05,
+      "loss": 0.4118,
+      "step": 505
+    },
+    {
+      "epoch": 2.741935483870968,
+      "grad_norm": 2.3625309467315674,
+      "learning_rate": 9.053763440860215e-05,
+      "loss": 0.4382,
+      "step": 510
+    },
+    {
+      "epoch": 2.768817204301075,
+      "grad_norm": 1.37618088722229,
+      "learning_rate": 8.946236559139786e-05,
+      "loss": 0.4092,
+      "step": 515
+    },
+    {
+      "epoch": 2.795698924731183,
+      "grad_norm": 2.8771934509277344,
+      "learning_rate": 8.838709677419355e-05,
+      "loss": 0.4403,
+      "step": 520
+    },
+    {
+      "epoch": 2.8225806451612905,
+      "grad_norm": 0.670045793056488,
+      "learning_rate": 8.731182795698926e-05,
+      "loss": 0.3922,
+      "step": 525
+    },
+    {
+      "epoch": 2.849462365591398,
+      "grad_norm": 0.6818873286247253,
+      "learning_rate": 8.623655913978495e-05,
+      "loss": 0.3811,
+      "step": 530
+    },
+    {
+      "epoch": 2.8763440860215055,
+      "grad_norm": 0.5645846128463745,
+      "learning_rate": 8.516129032258064e-05,
+      "loss": 0.3923,
+      "step": 535
+    },
+    {
+      "epoch": 2.903225806451613,
+      "grad_norm": 0.8240963816642761,
+      "learning_rate": 8.408602150537634e-05,
+      "loss": 0.3824,
+      "step": 540
+    },
+    {
+      "epoch": 2.9301075268817205,
+      "grad_norm": 0.8166781067848206,
+      "learning_rate": 8.301075268817205e-05,
+      "loss": 0.3977,
+      "step": 545
+    },
+    {
+      "epoch": 2.956989247311828,
+      "grad_norm": 0.6839639544487,
+      "learning_rate": 8.193548387096774e-05,
+      "loss": 0.3778,
+      "step": 550
+    },
+    {
+      "epoch": 2.9838709677419355,
+      "grad_norm": 0.6171432733535767,
+      "learning_rate": 8.086021505376345e-05,
+      "loss": 0.4205,
+      "step": 555
+    },
+    {
+      "epoch": 3.010752688172043,
+      "grad_norm": 0.6487573981285095,
+      "learning_rate": 7.978494623655914e-05,
+      "loss": 0.3774,
+      "step": 560
+    },
+    {
+      "epoch": 3.0376344086021505,
+      "grad_norm": 0.8863518834114075,
+      "learning_rate": 7.870967741935484e-05,
+      "loss": 0.3636,
+      "step": 565
+    },
+    {
+      "epoch": 3.064516129032258,
+      "grad_norm": 1.1676126718521118,
+      "learning_rate": 7.763440860215054e-05,
+      "loss": 0.3438,
+      "step": 570
+    },
+    {
+      "epoch": 3.0913978494623655,
+      "grad_norm": 1.3498252630233765,
+      "learning_rate": 7.655913978494624e-05,
+      "loss": 0.3812,
+      "step": 575
+    },
+    {
+      "epoch": 3.118279569892473,
+      "grad_norm": 0.8388305306434631,
+      "learning_rate": 7.548387096774195e-05,
+      "loss": 0.3551,
+      "step": 580
+    },
+    {
+      "epoch": 3.1451612903225805,
+      "grad_norm": 0.8704394698143005,
+      "learning_rate": 7.440860215053764e-05,
+      "loss": 0.3663,
+      "step": 585
+    },
+    {
+      "epoch": 3.172043010752688,
+      "grad_norm": 0.7780643701553345,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.379,
+      "step": 590
+    },
+    {
+      "epoch": 3.1989247311827955,
+      "grad_norm": 0.6339101195335388,
+      "learning_rate": 7.225806451612904e-05,
+      "loss": 0.3696,
+      "step": 595
+    },
+    {
+      "epoch": 3.225806451612903,
+      "grad_norm": 0.7547860145568848,
+      "learning_rate": 7.118279569892473e-05,
+      "loss": 0.3595,
+      "step": 600
+    },
+    {
+      "epoch": 3.252688172043011,
+      "grad_norm": 0.6610727310180664,
+      "learning_rate": 7.010752688172043e-05,
+      "loss": 0.3806,
+      "step": 605
+    },
+    {
+      "epoch": 3.279569892473118,
+      "grad_norm": 0.9694567322731018,
+      "learning_rate": 6.903225806451613e-05,
+      "loss": 0.4239,
+      "step": 610
+    },
+    {
+      "epoch": 3.306451612903226,
+      "grad_norm": 0.8362919688224792,
+      "learning_rate": 6.795698924731183e-05,
+      "loss": 0.3472,
+      "step": 615
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 1.2766687870025635,
+      "learning_rate": 6.688172043010754e-05,
+      "loss": 0.3855,
+      "step": 620
+    },
+    {
+      "epoch": 3.360215053763441,
+      "grad_norm": 2.0830249786376953,
+      "learning_rate": 6.580645161290323e-05,
+      "loss": 0.3528,
+      "step": 625
+    },
+    {
+      "epoch": 3.3870967741935485,
+      "grad_norm": 0.6089420914649963,
+      "learning_rate": 6.473118279569893e-05,
+      "loss": 0.339,
+      "step": 630
+    },
+    {
+      "epoch": 3.413978494623656,
+      "grad_norm": 0.8975178599357605,
+      "learning_rate": 6.365591397849463e-05,
+      "loss": 0.3466,
+      "step": 635
+    },
+    {
+      "epoch": 3.4408602150537635,
+      "grad_norm": 0.8945618867874146,
+      "learning_rate": 6.258064516129033e-05,
+      "loss": 0.3557,
+      "step": 640
+    },
+    {
+      "epoch": 3.467741935483871,
+      "grad_norm": 0.6987658143043518,
+      "learning_rate": 6.150537634408602e-05,
+      "loss": 0.3398,
+      "step": 645
+    },
+    {
+      "epoch": 3.4946236559139785,
+      "grad_norm": 0.6438629627227783,
+      "learning_rate": 6.0430107526881715e-05,
+      "loss": 0.3298,
+      "step": 650
+    },
+    {
+      "epoch": 3.521505376344086,
+      "grad_norm": 0.9585652351379395,
+      "learning_rate": 5.935483870967742e-05,
+      "loss": 0.3944,
+      "step": 655
+    },
+    {
+      "epoch": 3.5483870967741935,
+      "grad_norm": 0.8226910829544067,
+      "learning_rate": 5.827956989247312e-05,
+      "loss": 0.3783,
+      "step": 660
+    },
+    {
+      "epoch": 3.575268817204301,
+      "grad_norm": 0.6199684739112854,
+      "learning_rate": 5.720430107526882e-05,
+      "loss": 0.3262,
+      "step": 665
+    },
+    {
+      "epoch": 3.6021505376344085,
+      "grad_norm": 0.8326342105865479,
+      "learning_rate": 5.612903225806452e-05,
+      "loss": 0.3152,
+      "step": 670
+    },
+    {
+      "epoch": 3.629032258064516,
+      "grad_norm": 1.2666329145431519,
+      "learning_rate": 5.5053763440860215e-05,
+      "loss": 0.3958,
+      "step": 675
+    },
+    {
+      "epoch": 3.6559139784946235,
+      "grad_norm": 0.6879651546478271,
+      "learning_rate": 5.397849462365592e-05,
+      "loss": 0.3684,
+      "step": 680
+    },
+    {
+      "epoch": 3.682795698924731,
+      "grad_norm": 0.789516031742096,
+      "learning_rate": 5.290322580645162e-05,
+      "loss": 0.3575,
+      "step": 685
+    },
+    {
+      "epoch": 3.709677419354839,
+      "grad_norm": 0.7152576446533203,
+      "learning_rate": 5.182795698924732e-05,
+      "loss": 0.3048,
+      "step": 690
+    },
+    {
+      "epoch": 3.736559139784946,
+      "grad_norm": 0.6960220336914062,
+      "learning_rate": 5.075268817204302e-05,
+      "loss": 0.3395,
+      "step": 695
+    },
+    {
+      "epoch": 3.763440860215054,
+      "grad_norm": 0.66648930311203,
+      "learning_rate": 4.967741935483871e-05,
+      "loss": 0.3475,
+      "step": 700
+    },
+    {
+      "epoch": 3.790322580645161,
+      "grad_norm": 0.711923360824585,
+      "learning_rate": 4.8602150537634414e-05,
+      "loss": 0.327,
+      "step": 705
+    },
+    {
+      "epoch": 3.817204301075269,
+      "grad_norm": 1.0754563808441162,
+      "learning_rate": 4.752688172043011e-05,
+      "loss": 0.3554,
+      "step": 710
+    },
+    {
+      "epoch": 3.8440860215053765,
+      "grad_norm": 0.6272746324539185,
+      "learning_rate": 4.645161290322581e-05,
+      "loss": 0.3262,
+      "step": 715
+    },
+    {
+      "epoch": 3.870967741935484,
+      "grad_norm": 0.6247246861457825,
+      "learning_rate": 4.53763440860215e-05,
+      "loss": 0.3311,
+      "step": 720
+    },
+    {
+      "epoch": 3.8978494623655915,
+      "grad_norm": 0.9296492338180542,
+      "learning_rate": 4.43010752688172e-05,
+      "loss": 0.3433,
+      "step": 725
+    },
+    {
+      "epoch": 3.924731182795699,
+      "grad_norm": 1.0945050716400146,
+      "learning_rate": 4.322580645161291e-05,
+      "loss": 0.3295,
+      "step": 730
+    },
+    {
+      "epoch": 3.9516129032258065,
+      "grad_norm": 0.840998649597168,
+      "learning_rate": 4.2150537634408606e-05,
+      "loss": 0.2839,
+      "step": 735
+    },
+    {
+      "epoch": 3.978494623655914,
+      "grad_norm": 0.6789965629577637,
+      "learning_rate": 4.1075268817204305e-05,
+      "loss": 0.3398,
+      "step": 740
+    },
+    {
+      "epoch": 4.005376344086022,
+      "grad_norm": 0.6800040602684021,
+      "learning_rate": 4e-05,
+      "loss": 0.3378,
+      "step": 745
+    },
+    {
+      "epoch": 4.032258064516129,
+      "grad_norm": 0.9894293546676636,
+      "learning_rate": 3.8924731182795695e-05,
+      "loss": 0.334,
+      "step": 750
+    },
+    {
+      "epoch": 4.059139784946237,
+      "grad_norm": 0.6852840185165405,
+      "learning_rate": 3.78494623655914e-05,
+      "loss": 0.3291,
+      "step": 755
+    },
+    {
+      "epoch": 4.086021505376344,
+      "grad_norm": 0.9194632768630981,
+      "learning_rate": 3.67741935483871e-05,
+      "loss": 0.346,
+      "step": 760
+    },
+    {
+      "epoch": 4.112903225806452,
+      "grad_norm": 0.7930384278297424,
+      "learning_rate": 3.56989247311828e-05,
+      "loss": 0.3765,
+      "step": 765
+    },
+    {
+      "epoch": 4.139784946236559,
+      "grad_norm": 0.6173940896987915,
+      "learning_rate": 3.4623655913978497e-05,
+      "loss": 0.2881,
+      "step": 770
+    },
+    {
+      "epoch": 4.166666666666667,
+      "grad_norm": 1.0658806562423706,
+      "learning_rate": 3.3548387096774195e-05,
+      "loss": 0.3393,
+      "step": 775
+    },
+    {
+      "epoch": 4.193548387096774,
+      "grad_norm": 0.9105071425437927,
+      "learning_rate": 3.2473118279569894e-05,
+      "loss": 0.2922,
+      "step": 780
+    },
+    {
+      "epoch": 4.220430107526882,
+      "grad_norm": 0.7287763953208923,
+      "learning_rate": 3.139784946236559e-05,
+      "loss": 0.3196,
+      "step": 785
+    },
+    {
+      "epoch": 4.247311827956989,
+      "grad_norm": 0.692533552646637,
+      "learning_rate": 3.032258064516129e-05,
+      "loss": 0.2845,
+      "step": 790
+    },
+    {
+      "epoch": 4.274193548387097,
+      "grad_norm": 0.8192632794380188,
+      "learning_rate": 2.924731182795699e-05,
+      "loss": 0.2845,
+      "step": 795
+    },
+    {
+      "epoch": 4.301075268817204,
+      "grad_norm": 0.9781789779663086,
+      "learning_rate": 2.8172043010752692e-05,
+      "loss": 0.3508,
+      "step": 800
+    },
+    {
+      "epoch": 4.327956989247312,
+      "grad_norm": 0.6340736746788025,
+      "learning_rate": 2.709677419354839e-05,
+      "loss": 0.3522,
+      "step": 805
+    },
+    {
+      "epoch": 4.354838709677419,
+      "grad_norm": 0.7697390913963318,
+      "learning_rate": 2.6021505376344086e-05,
+      "loss": 0.2812,
+      "step": 810
+    },
+    {
+      "epoch": 4.381720430107527,
+      "grad_norm": 1.2623796463012695,
+      "learning_rate": 2.4946236559139784e-05,
+      "loss": 0.3291,
+      "step": 815
+    },
+    {
+      "epoch": 4.408602150537634,
+      "grad_norm": 0.5058888792991638,
+      "learning_rate": 2.3870967741935486e-05,
+      "loss": 0.2865,
+      "step": 820
+    },
+    {
+      "epoch": 4.435483870967742,
+      "grad_norm": 0.6579411029815674,
+      "learning_rate": 2.2795698924731185e-05,
+      "loss": 0.314,
+      "step": 825
+    },
+    {
+      "epoch": 4.462365591397849,
+      "grad_norm": 0.794482946395874,
+      "learning_rate": 2.172043010752688e-05,
+      "loss": 0.3424,
+      "step": 830
+    },
+    {
+      "epoch": 4.489247311827957,
+      "grad_norm": 0.7736402750015259,
+      "learning_rate": 2.0645161290322582e-05,
+      "loss": 0.3459,
+      "step": 835
+    },
+    {
+      "epoch": 4.516129032258064,
+      "grad_norm": 0.8923993706703186,
+      "learning_rate": 1.956989247311828e-05,
+      "loss": 0.3199,
+      "step": 840
+    },
+    {
+      "epoch": 4.543010752688172,
+      "grad_norm": 0.6480904221534729,
+      "learning_rate": 1.849462365591398e-05,
+      "loss": 0.3114,
+      "step": 845
+    },
+    {
+      "epoch": 4.56989247311828,
+      "grad_norm": 0.7036060094833374,
+      "learning_rate": 1.741935483870968e-05,
+      "loss": 0.2878,
+      "step": 850
+    },
+    {
+      "epoch": 4.596774193548387,
+      "grad_norm": 0.9546545743942261,
+      "learning_rate": 1.6344086021505377e-05,
+      "loss": 0.3354,
+      "step": 855
+    },
+    {
+      "epoch": 4.623655913978495,
+      "grad_norm": 0.8179369568824768,
+      "learning_rate": 1.5268817204301076e-05,
+      "loss": 0.3203,
+      "step": 860
+    },
+    {
+      "epoch": 4.650537634408602,
+      "grad_norm": 0.7543355822563171,
+      "learning_rate": 1.4193548387096774e-05,
+      "loss": 0.3204,
+      "step": 865
+    },
+    {
+      "epoch": 4.67741935483871,
+      "grad_norm": 1.0491559505462646,
+      "learning_rate": 1.3118279569892475e-05,
+      "loss": 0.3376,
+      "step": 870
+    },
+    {
+      "epoch": 4.704301075268817,
+      "grad_norm": 0.6792603135108948,
+      "learning_rate": 1.2043010752688173e-05,
+      "loss": 0.297,
+      "step": 875
+    },
+    {
+      "epoch": 4.731182795698925,
+      "grad_norm": 0.711181640625,
+      "learning_rate": 1.0967741935483872e-05,
+      "loss": 0.32,
+      "step": 880
+    },
+    {
+      "epoch": 4.758064516129032,
+      "grad_norm": 0.7287176847457886,
+      "learning_rate": 9.89247311827957e-06,
+      "loss": 0.3097,
+      "step": 885
+    },
+    {
+      "epoch": 4.78494623655914,
+      "grad_norm": 0.8330285549163818,
+      "learning_rate": 8.81720430107527e-06,
+      "loss": 0.3242,
+      "step": 890
+    },
+    {
+      "epoch": 4.811827956989247,
+      "grad_norm": 0.6423484086990356,
+      "learning_rate": 7.741935483870968e-06,
+      "loss": 0.3087,
+      "step": 895
+    },
+    {
+      "epoch": 4.838709677419355,
+      "grad_norm": 1.1993571519851685,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 0.3257,
+      "step": 900
+    },
+    {
+      "epoch": 4.865591397849462,
+      "grad_norm": 0.711089551448822,
+      "learning_rate": 5.591397849462366e-06,
+      "loss": 0.2974,
+      "step": 905
+    },
+    {
+      "epoch": 4.89247311827957,
+      "grad_norm": 0.7673178315162659,
+      "learning_rate": 4.516129032258065e-06,
+      "loss": 0.3056,
+      "step": 910
+    },
+    {
+      "epoch": 4.919354838709677,
+      "grad_norm": 0.5399670004844666,
+      "learning_rate": 3.4408602150537635e-06,
+      "loss": 0.2649,
+      "step": 915
+    },
+    {
+      "epoch": 4.946236559139785,
+      "grad_norm": 0.7354225516319275,
+      "learning_rate": 2.3655913978494625e-06,
+      "loss": 0.3402,
+      "step": 920
+    },
+    {
+      "epoch": 4.973118279569892,
+      "grad_norm": 0.9460377097129822,
+      "learning_rate": 1.2903225806451614e-06,
+      "loss": 0.3072,
+      "step": 925
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.9830946326255798,
+      "learning_rate": 2.1505376344086022e-07,
+      "loss": 0.2995,
+      "step": 930
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 930,
+  "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": 975376566190080.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

student_lora_finetuned/checkpoint-930/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7651964235f11f3c6cc8169952914ae8667be060baf51461c65e20e2daa85a88
+size 5304

student_lora_finetuned/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

student_lora_finetuned/tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "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": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "extra_special_tokens": {},
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}