Pushing fine-tuned model to Hugging Face Hub

README.md

@@ -0,0 +1,48 @@
+
+---
+language:
+- pt
+- en
+tags:
+- aes
+datasets:
+- kamel-usp/aes_enem_dataset
+base_model: microsoft/phi-4
+metrics:
+- accuracy
+- qwk
+library_name: peft
+model-index:
+  - name: phi-4-phi4_classification_lora-C1-full_context-r16
+    results:
+      - task:
+          type: text-classification
+          name: Automated Essay Score
+        dataset:
+          name: Automated Essay Score ENEM Dataset
+          type: kamel-usp/aes_enem_dataset
+          config: JBCS2025
+          split: test
+        metrics:
+          - name: Macro F1
+            type: f1
+            value: 0.3819840749050985
+          - name: QWK
+            type: qwk
+            value: 0.6146996679746453
+          - name: Weighted Macro F1
+            type: f1
+            value: 0.572765214753023
+---
+# Model ID: phi-4-phi4_classification_lora-C1-full_context-r16
+## Results
+|                  |   test_data |
+|:-----------------|------------:|
+| eval_accuracy    |  0.565217   |
+| eval_RMSE        | 29.2911     |
+| eval_QWK         |  0.6147     |
+| eval_Macro_F1    |  0.381984   |
+| eval_Weighted_F1 |  0.572765   |
+| eval_Micro_F1    |  0.565217   |
+| eval_HDIV        |  0.00724638 |
+        

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-4",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "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": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "qkv_proj",
+    "gate_up_proj",
+    "o_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d453d7202230642f535a75724c747c521ae9c125f3f50242fd9a3680607ccdd
+size 222927424

chat_template.jinja

@@ -0,0 +1 @@
+{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,project_name,run_id,experiment_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2025-07-06T05:42:47,jbcs2025,aa61881a-3ed1-49b6-9f01-57a4a2df6dd1,phi-4-phi4_classification_lora-C1-full_context-r16,6956.129377006029,0.08907656449846453,1.2805478401956313e-05,70.0,657.6838372315818,70.0,0.13335135308316962,1.3232156305160956,0.13297894867048582,1.58954593226975,France,FRA,île-de-france,,,Linux-5.15.0-136-generic-x86_64-with-glibc2.35,3.12.11,3.0.2,192,INTEL(R) XEON(R) PLATINUM 8568Y+,1,1 x NVIDIA H200,2.3494,48.8558,2015.363483428955,machine,N,1.0

evaluation_results.csv

@@ -0,0 +1,4 @@
+eval_loss,eval_model_preparation_time,eval_accuracy,eval_RMSE,eval_QWK,eval_HDIV,eval_Macro_F1,eval_Micro_F1,eval_Weighted_F1,eval_TP_0,eval_TN_0,eval_FP_0,eval_FN_0,eval_TP_1,eval_TN_1,eval_FP_1,eval_FN_1,eval_TP_2,eval_TN_2,eval_FP_2,eval_FN_2,eval_TP_3,eval_TN_3,eval_FP_3,eval_FN_3,eval_TP_4,eval_TN_4,eval_FP_4,eval_FN_4,eval_TP_5,eval_TN_5,eval_FP_5,eval_FN_5,eval_runtime,eval_samples_per_second,eval_steps_per_second,epoch,reference,timestamp,id
+3.467095136642456,0.0091,0.42424242424242425,45.79268169663901,-0.13793103448275867,0.045454545454545414,0.140296332280787,0.42424242424242425,0.2979074200837621,0,131,0,1,0,132,0,0,1,110,15,6,0,93,0,39,55,8,61,8,0,110,0,22,36.5996,3.607,0.902,-1,validation_before_training,2025-07-06 03:47:17,phi-4-phi4_classification_lora-C1-full_context-r16
+1.0629452466964722,0.0091,0.6060606060606061,27.19179912021158,0.6803747221340108,0.0,0.4880785271081273,0.6060606060606061,0.6012096861196649,0,131,0,1,0,132,0,0,5,122,3,2,30,75,18,9,33,52,17,30,12,96,14,10,36.368,3.63,0.907,14.0,validation_after_training,2025-07-06 03:47:17,phi-4-phi4_classification_lora-C1-full_context-r16
+1.143155813217163,0.0091,0.5652173913043478,29.29114225312413,0.6146996679746453,0.007246376811594235,0.38198407490509856,0.5652173913043478,0.572765214753023,0,137,0,1,0,138,0,0,5,111,17,5,47,47,25,19,21,80,7,30,5,117,11,5,39.9267,3.456,0.877,14.0,test_results,2025-07-06 03:47:17,phi-4-phi4_classification_lora-C1-full_context-r16

run_experiment.log

@@ -0,0 +1,769 @@
+[2025-07-06 03:46:47,759][__main__][INFO] - cache_dir: /tmp/
+dataset:
+  name: kamel-usp/aes_enem_dataset
+  split: JBCS2025
+training_params:
+  seed: 42
+  num_train_epochs: 20
+  logging_steps: 100
+  metric_for_best_model: QWK
+  bf16: true
+bootstrap:
+  enabled: true
+  n_bootstrap: 10000
+  bootstrap_seed: 42
+  metrics:
+  - QWK
+  - Macro_F1
+  - Weighted_F1
+post_training_results:
+  model_path: /workspace/jbcs2025/outputs/2025-03-24/20-42-59
+experiments:
+  model:
+    name: microsoft/phi-4
+    type: phi4_classification_lora
+    num_labels: 6
+    output_dir: ./results/
+    logging_dir: ./logs/
+    best_model_dir: ./results/best_model
+    lora_r: 16
+    lora_dropout: 0.1
+    lora_alpha: 32
+    lora_target_modules: all-linear
+  tokenizer:
+    name: microsoft/phi-4
+  dataset:
+    grade_index: 0
+    use_full_context: true
+  training_params:
+    weight_decay: 0.01
+    warmup_ratio: 0.1
+    learning_rate: 5.0e-05
+    train_batch_size: 8
+    eval_batch_size: 4
+    gradient_accumulation_steps: 2
+    gradient_checkpointing: true
+
+[2025-07-06 03:46:51,686][__main__][INFO] - GPU 0: NVIDIA H200 | TDP ≈ 700 W
+[2025-07-06 03:46:51,686][__main__][INFO] - Starting the Fine Tuning training process.
+[2025-07-06 03:46:55,798][transformers.tokenization_utils_base][INFO] - loading file vocab.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/vocab.json
+[2025-07-06 03:46:55,798][transformers.tokenization_utils_base][INFO] - loading file merges.txt from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/merges.txt
+[2025-07-06 03:46:55,798][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/tokenizer.json
+[2025-07-06 03:46:55,798][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/added_tokens.json
+[2025-07-06 03:46:55,798][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/special_tokens_map.json
+[2025-07-06 03:46:55,798][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/tokenizer_config.json
+[2025-07-06 03:46:55,798][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
+[2025-07-06 03:46:55,939][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: False; Use Full Context: True
+[2025-07-06 03:46:56,416][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 03:46:56,416][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 03:46:56,543][transformers.modeling_utils][INFO] - loading weights file model.safetensors from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/model.safetensors.index.json
+[2025-07-06 03:46:56,543][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object
+[2025-07-06 03:46:56,543][transformers.modeling_utils][INFO] - Instantiating Phi3ForSequenceClassification model under default dtype torch.bfloat16.
+[2025-07-06 03:47:14,783][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at microsoft/phi-4 were not used when initializing Phi3ForSequenceClassification: ['lm_head.weight']
+- This IS expected if you are initializing Phi3ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).
+- This IS NOT expected if you are initializing Phi3ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).
+[2025-07-06 03:47:14,783][transformers.modeling_utils][WARNING] - Some weights of Phi3ForSequenceClassification were not initialized from the model checkpoint at microsoft/phi-4 and are newly initialized: ['score.weight']
+You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.
+[2025-07-06 03:47:17,161][__main__][INFO] - Initialized new PEFT model for ce loss
+[2025-07-06 03:47:17,163][__main__][INFO] - None
+[2025-07-06 03:47:17,165][transformers.training_args][INFO] - PyTorch: setting up devices
+[2025-07-06 03:47:17,202][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
+[2025-07-06 03:47:17,210][transformers.trainer][INFO] - You have loaded a model on multiple GPUs. `is_model_parallel` attribute will be force-set to `True` to avoid any unexpected behavior such as device placement mismatching.
+[2025-07-06 03:47:17,244][transformers.trainer][INFO] - Using auto half precision backend
+[2025-07-06 03:47:17,244][transformers.trainer][WARNING] - No label_names provided for model class `PeftModelForSequenceClassification`. Since `PeftModel` hides base models input arguments, if label_names is not given, label_names can't be set automatically within `Trainer`. Note that empty label_names list will be used instead.
+[2025-07-06 03:47:17,245][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 03:47:17,258][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 03:47:17,258][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 03:47:17,258][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 03:47:54,042][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 03:47:54,082][transformers.trainer][INFO] - ***** Running training *****
+[2025-07-06 03:47:54,083][transformers.trainer][INFO] -   Num examples = 500
+[2025-07-06 03:47:54,083][transformers.trainer][INFO] -   Num Epochs = 20
+[2025-07-06 03:47:54,083][transformers.trainer][INFO] -   Instantaneous batch size per device = 8
+[2025-07-06 03:47:54,083][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
+[2025-07-06 03:47:54,083][transformers.trainer][INFO] -   Gradient Accumulation steps = 2
+[2025-07-06 03:47:54,083][transformers.trainer][INFO] -   Total optimization steps = 640
+[2025-07-06 03:47:54,085][transformers.trainer][INFO] -   Number of trainable parameters = 55,736,320
+[2025-07-06 03:47:54,161][transformers.models.phi3.modeling_phi3][WARNING] - `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
+[2025-07-06 03:55:23,376][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 03:55:23,380][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 03:55:23,380][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 03:55:23,380][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 03:55:59,776][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-32
+[2025-07-06 03:56:00,310][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 03:56:00,311][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 04:03:30,176][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 04:03:30,179][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 04:03:30,179][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 04:03:30,180][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 04:04:06,567][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-64
+[2025-07-06 04:04:06,927][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 04:04:06,927][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 04:11:37,304][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 04:11:37,307][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 04:11:37,307][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 04:11:37,307][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 04:12:13,718][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-96
+[2025-07-06 04:12:14,059][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 04:12:14,059][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 04:12:15,093][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-32] due to args.save_total_limit
+[2025-07-06 04:12:15,135][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-64] due to args.save_total_limit
+[2025-07-06 04:19:43,837][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 04:19:43,840][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 04:19:43,840][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 04:19:43,840][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 04:20:20,207][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-128
+[2025-07-06 04:20:20,550][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 04:20:20,551][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 04:20:21,626][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-96] due to args.save_total_limit
+[2025-07-06 04:27:50,364][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 04:27:50,367][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 04:27:50,367][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 04:27:50,367][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 04:28:26,765][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-160
+[2025-07-06 04:28:27,247][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 04:28:27,248][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 04:35:57,157][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 04:35:57,161][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 04:35:57,161][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 04:35:57,161][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 04:36:33,541][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-192
+[2025-07-06 04:36:33,876][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 04:36:33,876][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 04:36:34,879][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-128] due to args.save_total_limit
+[2025-07-06 04:36:34,920][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-160] due to args.save_total_limit
+[2025-07-06 04:44:03,817][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 04:44:03,820][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 04:44:03,820][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 04:44:03,820][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 04:44:40,227][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-224
+[2025-07-06 04:44:40,549][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 04:44:40,550][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 04:44:41,586][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-192] due to args.save_total_limit
+[2025-07-06 04:52:10,579][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 04:52:10,583][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 04:52:10,583][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 04:52:10,583][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 04:52:46,999][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-256
+[2025-07-06 04:52:47,338][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 04:52:47,339][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 05:00:17,176][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 05:00:17,180][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 05:00:17,180][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 05:00:17,180][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 05:00:53,575][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-288
+[2025-07-06 05:00:54,228][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 05:00:54,228][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 05:00:55,274][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-224] due to args.save_total_limit
+[2025-07-06 05:00:55,315][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-256] due to args.save_total_limit
+[2025-07-06 05:08:24,048][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 05:08:24,051][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 05:08:24,052][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 05:08:24,052][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 05:09:00,431][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-320
+[2025-07-06 05:09:00,788][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 05:09:00,788][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 05:16:30,741][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 05:16:30,744][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 05:16:30,744][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 05:16:30,744][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 05:17:07,154][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-352
+[2025-07-06 05:17:07,778][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 05:17:07,779][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 05:17:08,778][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-320] due to args.save_total_limit
+[2025-07-06 05:24:37,832][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 05:24:37,835][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 05:24:37,835][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 05:24:37,835][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 05:25:14,268][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-384
+[2025-07-06 05:25:14,589][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 05:25:14,589][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 05:25:15,577][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-352] due to args.save_total_limit
+[2025-07-06 05:32:44,535][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 05:32:44,539][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 05:32:44,539][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 05:32:44,539][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 05:33:20,951][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-416
+[2025-07-06 05:33:21,277][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 05:33:21,278][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 05:33:22,269][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-384] due to args.save_total_limit
+[2025-07-06 05:40:51,353][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 05:40:51,356][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 05:40:51,356][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 05:40:51,356][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 05:41:27,751][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-448
+[2025-07-06 05:41:28,085][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 05:41:28,085][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 05:41:29,074][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-416] due to args.save_total_limit
+[2025-07-06 05:41:29,109][transformers.trainer][INFO] - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+[2025-07-06 05:41:29,109][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-288 (score: 0.6803747221340108).
+[2025-07-06 05:41:29,351][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/03-46-47/results/checkpoint-448] due to args.save_total_limit
+[2025-07-06 05:41:29,393][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 05:41:29,403][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 05:41:29,403][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-06 05:41:29,403][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 05:42:05,776][__main__][INFO] - Training completed successfully.
+[2025-07-06 05:42:05,776][__main__][INFO] - Running on Test
+[2025-07-06 05:42:05,776][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference. If id, prompt, essay_text, essay_year, id_prompt, grades, supporting_text, reference are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-06 05:42:05,779][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-06 05:42:05,779][transformers.trainer][INFO] -   Num examples = 138
+[2025-07-06 05:42:05,779][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-06 05:42:45,715][__main__][INFO] - Test metrics: {'eval_loss': 1.143155813217163, 'eval_model_preparation_time': 0.0091, 'eval_accuracy': 0.5652173913043478, 'eval_RMSE': 29.29114225312413, 'eval_QWK': 0.6146996679746453, 'eval_HDIV': 0.007246376811594235, 'eval_Macro_F1': 0.38198407490509856, 'eval_Micro_F1': 0.5652173913043478, 'eval_Weighted_F1': 0.572765214753023, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 0, 'eval_TN_1': 138, 'eval_FP_1': 0, 'eval_FN_1': 0, 'eval_TP_2': 5, 'eval_TN_2': 111, 'eval_FP_2': 17, 'eval_FN_2': 5, 'eval_TP_3': 47, 'eval_TN_3': 47, 'eval_FP_3': 25, 'eval_FN_3': 19, 'eval_TP_4': 21, 'eval_TN_4': 80, 'eval_FP_4': 7, 'eval_FN_4': 30, 'eval_TP_5': 5, 'eval_TN_5': 117, 'eval_FP_5': 11, 'eval_FN_5': 5, 'eval_runtime': 39.9267, 'eval_samples_per_second': 3.456, 'eval_steps_per_second': 0.877, 'epoch': 14.0}
+[2025-07-06 05:42:45,716][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
+[2025-07-06 05:42:46,030][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-07-06 05:42:46,031][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100257,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 100265,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17920,
+  "max_position_embeddings": 16384,
+  "model_type": "phi3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 10,
+  "original_max_position_embeddings": 16384,
+  "pad_token_id": 100349,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 250000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 100352
+}
+
+[2025-07-06 05:42:46,715][transformers.tokenization_utils_base][INFO] - chat template saved in ./results/best_model/chat_template.jinja
+[2025-07-06 05:42:46,716][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
+[2025-07-06 05:42:46,716][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
+[2025-07-06 05:42:46,786][__main__][INFO] - Model and tokenizer saved to ./results/best_model
+[2025-07-06 05:42:46,803][__main__][INFO] - Fine Tuning Finished.
+[2025-07-06 05:42:47,313][__main__][INFO] - Total emissions: 0.0891 kg CO2eq

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|dummy_85|>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": true,
+    "single_word": false
+  },
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,781 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "100256": {
+      "content": "<|dummy_0|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100257": {
+      "content": "<|endoftext|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100258": {
+      "content": "<|fim_prefix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100259": {
+      "content": "<|fim_middle|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100260": {
+      "content": "<|fim_suffix|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100261": {
+      "content": "<|dummy_1|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100262": {
+      "content": "<|dummy_2|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100263": {
+      "content": "<|dummy_3|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100264": {
+      "content": "<|im_start|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100265": {
+      "content": "<|im_end|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100266": {
+      "content": "<|im_sep|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100267": {
+      "content": "<|dummy_4|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100268": {
+      "content": "<|dummy_5|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100269": {
+      "content": "<|dummy_6|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100270": {
+      "content": "<|dummy_7|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100271": {
+      "content": "<|dummy_8|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100272": {
+      "content": "<|dummy_9|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100273": {
+      "content": "<|dummy_10|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100274": {
+      "content": "<|dummy_11|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100275": {
+      "content": "<|dummy_12|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100276": {
+      "content": "<|endofprompt|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100277": {
+      "content": "<|dummy_13|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100278": {
+      "content": "<|dummy_14|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100279": {
+      "content": "<|dummy_15|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100280": {
+      "content": "<|dummy_16|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100281": {
+      "content": "<|dummy_17|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100282": {
+      "content": "<|dummy_18|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100283": {
+      "content": "<|dummy_19|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100284": {
+      "content": "<|dummy_20|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100285": {
+      "content": "<|dummy_21|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100286": {
+      "content": "<|dummy_22|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100287": {
+      "content": "<|dummy_23|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100288": {
+      "content": "<|dummy_24|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100289": {
+      "content": "<|dummy_25|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100290": {
+      "content": "<|dummy_26|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100291": {
+      "content": "<|dummy_27|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100292": {
+      "content": "<|dummy_28|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100293": {
+      "content": "<|dummy_29|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100294": {
+      "content": "<|dummy_30|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100295": {
+      "content": "<|dummy_31|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100296": {
+      "content": "<|dummy_32|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100297": {
+      "content": "<|dummy_33|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100298": {
+      "content": "<|dummy_34|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100299": {
+      "content": "<|dummy_35|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100300": {
+      "content": "<|dummy_36|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100301": {
+      "content": "<|dummy_37|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100302": {
+      "content": "<|dummy_38|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100303": {
+      "content": "<|dummy_39|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100304": {
+      "content": "<|dummy_40|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100305": {
+      "content": "<|dummy_41|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100306": {
+      "content": "<|dummy_42|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100307": {
+      "content": "<|dummy_43|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100308": {
+      "content": "<|dummy_44|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100309": {
+      "content": "<|dummy_45|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100310": {
+      "content": "<|dummy_46|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100311": {
+      "content": "<|dummy_47|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100312": {
+      "content": "<|dummy_48|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100313": {
+      "content": "<|dummy_49|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100314": {
+      "content": "<|dummy_50|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100315": {
+      "content": "<|dummy_51|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100316": {
+      "content": "<|dummy_52|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100317": {
+      "content": "<|dummy_53|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100318": {
+      "content": "<|dummy_54|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100319": {
+      "content": "<|dummy_55|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100320": {
+      "content": "<|dummy_56|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100321": {
+      "content": "<|dummy_57|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100322": {
+      "content": "<|dummy_58|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100323": {
+      "content": "<|dummy_59|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100324": {
+      "content": "<|dummy_60|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100325": {
+      "content": "<|dummy_61|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100326": {
+      "content": "<|dummy_62|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100327": {
+      "content": "<|dummy_63|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100328": {
+      "content": "<|dummy_64|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100329": {
+      "content": "<|dummy_65|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100330": {
+      "content": "<|dummy_66|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100331": {
+      "content": "<|dummy_67|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100332": {
+      "content": "<|dummy_68|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100333": {
+      "content": "<|dummy_69|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100334": {
+      "content": "<|dummy_70|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100335": {
+      "content": "<|dummy_71|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100336": {
+      "content": "<|dummy_72|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100337": {
+      "content": "<|dummy_73|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100338": {
+      "content": "<|dummy_74|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100339": {
+      "content": "<|dummy_75|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100340": {
+      "content": "<|dummy_76|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100341": {
+      "content": "<|dummy_77|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100342": {
+      "content": "<|dummy_78|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100343": {
+      "content": "<|dummy_79|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100344": {
+      "content": "<|dummy_80|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100345": {
+      "content": "<|dummy_81|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100346": {
+      "content": "<|dummy_82|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100347": {
+      "content": "<|dummy_83|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100348": {
+      "content": "<|dummy_84|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100349": {
+      "content": "<|dummy_85|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100350": {
+      "content": "<|dummy_86|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "100351": {
+      "content": "<|dummy_87|>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 16384,
+  "pad_token": "<|dummy_85|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec44414d9728ecefb71a15d510249c2abdfb2cf9f880e8fe64fb9b811fa344e0
+size 5777