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-3.5-mini-instruct
+metrics:
+- accuracy
+- qwk
+library_name: peft
+model-index:
+  - name: Phi-3.5-mini-instruct-phi35_classification_lora-C4-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: 0.0923997442221613
+          - name: QWK
+            type: qwk
+            value: 0.083437110834371
+          - name: Weighted Macro F1
+            type: f1
+            value: 0.1954039423149483
+---
+# Model ID: Phi-3.5-mini-instruct-phi35_classification_lora-C4-full_context-r16
+## Results
+|                  |   test_data |
+|:-----------------|------------:|
+| eval_accuracy    |   0.34058   |
+| eval_RMSE        |  38.5235    |
+| eval_QWK         |   0.0834371 |
+| eval_Macro_F1    |   0.0923997 |
+| eval_Weighted_F1 |   0.195404  |
+| eval_Micro_F1    |   0.34058   |
+| eval_HDIV        |   0.0144928 |
+        

adapter_config.json

@@ -0,0 +1,41 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3.5-mini-instruct",
+  "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": [
+    "qkv_proj",
+    "o_proj",
+    "gate_up_proj",
+    "down_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 sha256:4c56fd83afc83959c08567c143c3c684deeed6ded6e7a570c28489511ebffe8e
+size 100734696

chat_template.jinja

@@ -0,0 +1,8 @@
+{% for message in messages %}{% if message['role'] == 'system' and message['content'] %}{{'<|system|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'user' %}{{'<|user|>
+' + message['content'] + '<|end|>
+'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>
+' + message['content'] + '<|end|>
+'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>
+' }}{% else %}{{ eos_token }}{% 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
+2025-07-05T10:02:01,jbcs2025,405e9b8b-95b8-41bb-a3df-e105503acb83,Phi-3.5-mini-instruct-phi35_classification_lora-C4-full_context,603.0006932180258,0.007437431404373592,1.2334034584077094e-05,70.0,418.3397736991604,70.0,0.011648846233838892,0.10955205014157343,0.01151794950644835,0.1327188458818607,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
+2.56508731842041,0.0074,0.3787878787878788,36.34848169060327,0.02069153280696978,0.007575757575757569,0.12446524064171123,0.3787878787878788,0.23699562469615945,0,131,0,1,0,132,0,0,0,128,0,4,3,67,1,61,47,3,81,1,0,117,0,15,18.4013,7.173,1.793,-1,validation_before_training,2025-07-05 09:52:11,Phi-3.5-mini-instruct-phi35_classification_lora-C4-full_context
+2.325911045074463,0.0074,0.4090909090909091,35.67530340063379,0.06300703082747416,0.007575757575757569,0.15730614766759346,0.4090909090909091,0.31709120865747376,0,131,0,1,0,132,0,0,0,128,0,4,10,64,4,54,44,10,74,4,0,117,0,15,18.0239,7.324,1.831,6.0,validation_after_training,2025-07-05 09:52:11,Phi-3.5-mini-instruct-phi35_classification_lora-C4-full_context
+1.9528576135635376,0.0074,0.34057971014492755,38.52347298744614,0.083437110834371,0.01449275362318836,0.09239974422216134,0.34057971014492755,0.19540394231494831,0,137,0,1,0,137,0,1,0,129,0,9,2,58,4,74,45,5,87,1,0,133,0,5,19.0083,7.26,1.841,6.0,test_results,2025-07-05 09:52:11,Phi-3.5-mini-instruct-phi35_classification_lora-C4-full_context

run_experiment.log

@@ -0,0 +1,1289 @@
+[2025-07-05 09:51:54,796][__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-3.5-mini-instruct
+    type: phi35_classification_lora
+    num_labels: 6
+    output_dir: ./results/phi35-balanced/C4
+    logging_dir: ./logs/phi35-balanced/C4
+    best_model_dir: ./results/phi35-balanced/C4/best_model
+    lora_r: 16
+    lora_dropout: 0.1
+    lora_alpha: 32
+    lora_target_modules: all-linear
+  tokenizer:
+    name: microsoft/Phi-3.5-mini-instruct
+  dataset:
+    grade_index: 3
+    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
+
+[2025-07-05 09:51:58,697][__main__][INFO] - GPU 0: NVIDIA H200 | TDP ≈ 700 W
+[2025-07-05 09:51:58,697][__main__][INFO] - Starting the Fine Tuning training process.
+[2025-07-05 09:52:02,467][transformers.tokenization_utils_base][INFO] - loading file tokenizer.model from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/tokenizer.model
+[2025-07-05 09:52:02,467][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/tokenizer.json
+[2025-07-05 09:52:02,467][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/added_tokens.json
+[2025-07-05 09:52:02,467][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/special_tokens_map.json
+[2025-07-05 09:52:02,467][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/tokenizer_config.json
+[2025-07-05 09:52:02,467][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
+[2025-07-05 09:52:02,521][transformers.tokenization_utils_base][INFO] - Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.
+[2025-07-05 09:52:02,527][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: False; Use Full Context: True
+[2025-07-05 09:52:03,092][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
+[2025-07-05 09:52:03,092][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "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": 8192,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0800000429153442,
+      1.1100000143051147,
+      1.1399999856948853,
+      1.340000033378601,
+      1.5899999141693115,
+      1.600000023841858,
+      1.6200000047683716,
+      2.620000123977661,
+      3.2300000190734863,
+      3.2300000190734863,
+      4.789999961853027,
+      7.400000095367432,
+      7.700000286102295,
+      9.09000015258789,
+      12.199999809265137,
+      17.670000076293945,
+      24.46000099182129,
+      28.57000160217285,
+      30.420001983642578,
+      30.840002059936523,
+      32.590003967285156,
+      32.93000411987305,
+      42.320003509521484,
+      44.96000289916992,
+      50.340003967285156,
+      50.45000457763672,
+      57.55000305175781,
+      57.93000411987305,
+      58.21000289916992,
+      60.1400032043457,
+      62.61000442504883,
+      62.62000274658203,
+      62.71000289916992,
+      63.1400032043457,
+      63.1400032043457,
+      63.77000427246094,
+      63.93000411987305,
+      63.96000289916992,
+      63.970001220703125,
+      64.02999877929688,
+      64.06999969482422,
+      64.08000183105469,
+      64.12000274658203,
+      64.41000366210938,
+      64.4800033569336,
+      64.51000213623047,
+      64.52999877929688,
+      64.83999633789062
+    ],
+    "short_factor": [
+      1.0,
+      1.0199999809265137,
+      1.0299999713897705,
+      1.0299999713897705,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0699999332427979,
+      1.0999999046325684,
+      1.1099998950958252,
+      1.1599998474121094,
+      1.1599998474121094,
+      1.1699998378753662,
+      1.2899998426437378,
+      1.339999794960022,
+      1.679999828338623,
+      1.7899998426437378,
+      1.8199998140335083,
+      1.8499997854232788,
+      1.8799997568130493,
+      1.9099997282028198,
+      1.9399996995925903,
+      1.9899996519088745,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0799996852874756,
+      2.0899996757507324,
+      2.189999580383301,
+      2.2199995517730713,
+      2.5899994373321533,
+      2.729999542236328,
+      2.749999523162842,
+      2.8399994373321533
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}
+
+[2025-07-05 09:52:03,093][transformers.modeling_utils][INFO] - loading weights file model.safetensors from cache at /tmp/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/model.safetensors.index.json
+[2025-07-05 09:52:03,093][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object
+[2025-07-05 09:52:03,093][transformers.modeling_utils][INFO] - Instantiating Phi3ForSequenceClassification model under default dtype torch.bfloat16.
+[2025-07-05 09:52:10,643][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at microsoft/Phi-3.5-mini-instruct 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).
+[2025-07-05 09:52:10,643][transformers.modeling_utils][WARNING] - Some weights of Phi3ForSequenceClassification were not initialized from the model checkpoint at microsoft/Phi-3.5-mini-instruct 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.
+[2025-07-05 09:52:11,667][__main__][INFO] - Initialized new PEFT model for ce loss
+[2025-07-05 09:52:11,669][__main__][INFO] - None
+[2025-07-05 09:52:11,670][transformers.training_args][INFO] - PyTorch: setting up devices
+[2025-07-05 09:52:11,758][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
+[2025-07-05 09:52:11,764][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.
+[2025-07-05 09:52:11,789][transformers.trainer][INFO] - Using auto half precision backend
+[2025-07-05 09:52:11,790][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.
+[2025-07-05 09:52:11,792][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt. If id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-05 09:52:11,802][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-05 09:52:11,802][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-05 09:52:11,802][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-05 09:52:30,470][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt. If id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-05 09:52:30,502][transformers.trainer][INFO] - ***** Running training *****
+[2025-07-05 09:52:30,503][transformers.trainer][INFO] -   Num examples = 500
+[2025-07-05 09:52:30,503][transformers.trainer][INFO] -   Num Epochs = 20
+[2025-07-05 09:52:30,503][transformers.trainer][INFO] -   Instantaneous batch size per device = 8
+[2025-07-05 09:52:30,503][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
+[2025-07-05 09:52:30,503][transformers.trainer][INFO] -   Gradient Accumulation steps = 2
+[2025-07-05 09:52:30,503][transformers.trainer][INFO] -   Total optimization steps = 640
+[2025-07-05 09:52:30,504][transformers.trainer][INFO] -   Number of trainable parameters = 25,184,256
+[2025-07-05 09:52:30,632][transformers.models.phi3.modeling_phi3][WARNING] - `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`.
+[2025-07-05 09:53:40,622][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt. If id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-05 09:53:40,626][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-05 09:53:40,626][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-05 09:53:40,626][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-05 09:53:58,655][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-32
+[2025-07-05 09:53:58,953][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
+[2025-07-05 09:53:58,954][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0800000429153442,
+      1.1100000143051147,
+      1.1399999856948853,
+      1.340000033378601,
+      1.5899999141693115,
+      1.600000023841858,
+      1.6200000047683716,
+      2.620000123977661,
+      3.2300000190734863,
+      3.2300000190734863,
+      4.789999961853027,
+      7.400000095367432,
+      7.700000286102295,
+      9.09000015258789,
+      12.199999809265137,
+      17.670000076293945,
+      24.46000099182129,
+      28.57000160217285,
+      30.420001983642578,
+      30.840002059936523,
+      32.590003967285156,
+      32.93000411987305,
+      42.320003509521484,
+      44.96000289916992,
+      50.340003967285156,
+      50.45000457763672,
+      57.55000305175781,
+      57.93000411987305,
+      58.21000289916992,
+      60.1400032043457,
+      62.61000442504883,
+      62.62000274658203,
+      62.71000289916992,
+      63.1400032043457,
+      63.1400032043457,
+      63.77000427246094,
+      63.93000411987305,
+      63.96000289916992,
+      63.970001220703125,
+      64.02999877929688,
+      64.06999969482422,
+      64.08000183105469,
+      64.12000274658203,
+      64.41000366210938,
+      64.4800033569336,
+      64.51000213623047,
+      64.52999877929688,
+      64.83999633789062
+    ],
+    "short_factor": [
+      1.0,
+      1.0199999809265137,
+      1.0299999713897705,
+      1.0299999713897705,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0699999332427979,
+      1.0999999046325684,
+      1.1099998950958252,
+      1.1599998474121094,
+      1.1599998474121094,
+      1.1699998378753662,
+      1.2899998426437378,
+      1.339999794960022,
+      1.679999828338623,
+      1.7899998426437378,
+      1.8199998140335083,
+      1.8499997854232788,
+      1.8799997568130493,
+      1.9099997282028198,
+      1.9399996995925903,
+      1.9899996519088745,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0799996852874756,
+      2.0899996757507324,
+      2.189999580383301,
+      2.2199995517730713,
+      2.5899994373321533,
+      2.729999542236328,
+      2.749999523162842,
+      2.8399994373321533
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}
+
+[2025-07-05 09:55:09,379][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt. If id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-05 09:55:09,382][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-05 09:55:09,382][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-05 09:55:09,382][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-05 09:55:27,420][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-64
+[2025-07-05 09:55:27,715][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
+[2025-07-05 09:55:27,715][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0800000429153442,
+      1.1100000143051147,
+      1.1399999856948853,
+      1.340000033378601,
+      1.5899999141693115,
+      1.600000023841858,
+      1.6200000047683716,
+      2.620000123977661,
+      3.2300000190734863,
+      3.2300000190734863,
+      4.789999961853027,
+      7.400000095367432,
+      7.700000286102295,
+      9.09000015258789,
+      12.199999809265137,
+      17.670000076293945,
+      24.46000099182129,
+      28.57000160217285,
+      30.420001983642578,
+      30.840002059936523,
+      32.590003967285156,
+      32.93000411987305,
+      42.320003509521484,
+      44.96000289916992,
+      50.340003967285156,
+      50.45000457763672,
+      57.55000305175781,
+      57.93000411987305,
+      58.21000289916992,
+      60.1400032043457,
+      62.61000442504883,
+      62.62000274658203,
+      62.71000289916992,
+      63.1400032043457,
+      63.1400032043457,
+      63.77000427246094,
+      63.93000411987305,
+      63.96000289916992,
+      63.970001220703125,
+      64.02999877929688,
+      64.06999969482422,
+      64.08000183105469,
+      64.12000274658203,
+      64.41000366210938,
+      64.4800033569336,
+      64.51000213623047,
+      64.52999877929688,
+      64.83999633789062
+    ],
+    "short_factor": [
+      1.0,
+      1.0199999809265137,
+      1.0299999713897705,
+      1.0299999713897705,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0699999332427979,
+      1.0999999046325684,
+      1.1099998950958252,
+      1.1599998474121094,
+      1.1599998474121094,
+      1.1699998378753662,
+      1.2899998426437378,
+      1.339999794960022,
+      1.679999828338623,
+      1.7899998426437378,
+      1.8199998140335083,
+      1.8499997854232788,
+      1.8799997568130493,
+      1.9099997282028198,
+      1.9399996995925903,
+      1.9899996519088745,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0799996852874756,
+      2.0899996757507324,
+      2.189999580383301,
+      2.2199995517730713,
+      2.5899994373321533,
+      2.729999542236328,
+      2.749999523162842,
+      2.8399994373321533
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}
+
+[2025-07-05 09:56:38,026][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt. If id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-05 09:56:38,029][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-05 09:56:38,029][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-05 09:56:38,029][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-05 09:56:56,060][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-96
+[2025-07-05 09:56:56,563][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
+[2025-07-05 09:56:56,563][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0800000429153442,
+      1.1100000143051147,
+      1.1399999856948853,
+      1.340000033378601,
+      1.5899999141693115,
+      1.600000023841858,
+      1.6200000047683716,
+      2.620000123977661,
+      3.2300000190734863,
+      3.2300000190734863,
+      4.789999961853027,
+      7.400000095367432,
+      7.700000286102295,
+      9.09000015258789,
+      12.199999809265137,
+      17.670000076293945,
+      24.46000099182129,
+      28.57000160217285,
+      30.420001983642578,
+      30.840002059936523,
+      32.590003967285156,
+      32.93000411987305,
+      42.320003509521484,
+      44.96000289916992,
+      50.340003967285156,
+      50.45000457763672,
+      57.55000305175781,
+      57.93000411987305,
+      58.21000289916992,
+      60.1400032043457,
+      62.61000442504883,
+      62.62000274658203,
+      62.71000289916992,
+      63.1400032043457,
+      63.1400032043457,
+      63.77000427246094,
+      63.93000411987305,
+      63.96000289916992,
+      63.970001220703125,
+      64.02999877929688,
+      64.06999969482422,
+      64.08000183105469,
+      64.12000274658203,
+      64.41000366210938,
+      64.4800033569336,
+      64.51000213623047,
+      64.52999877929688,
+      64.83999633789062
+    ],
+    "short_factor": [
+      1.0,
+      1.0199999809265137,
+      1.0299999713897705,
+      1.0299999713897705,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0699999332427979,
+      1.0999999046325684,
+      1.1099998950958252,
+      1.1599998474121094,
+      1.1599998474121094,
+      1.1699998378753662,
+      1.2899998426437378,
+      1.339999794960022,
+      1.679999828338623,
+      1.7899998426437378,
+      1.8199998140335083,
+      1.8499997854232788,
+      1.8799997568130493,
+      1.9099997282028198,
+      1.9399996995925903,
+      1.9899996519088745,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0799996852874756,
+      2.0899996757507324,
+      2.189999580383301,
+      2.2199995517730713,
+      2.5899994373321533,
+      2.729999542236328,
+      2.749999523162842,
+      2.8399994373321533
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}
+
+[2025-07-05 09:56:56,872][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-64] due to args.save_total_limit
+[2025-07-05 09:58:06,881][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt. If id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-05 09:58:06,884][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-05 09:58:06,884][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-05 09:58:06,884][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-05 09:58:24,923][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-128
+[2025-07-05 09:58:25,410][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
+[2025-07-05 09:58:25,411][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0800000429153442,
+      1.1100000143051147,
+      1.1399999856948853,
+      1.340000033378601,
+      1.5899999141693115,
+      1.600000023841858,
+      1.6200000047683716,
+      2.620000123977661,
+      3.2300000190734863,
+      3.2300000190734863,
+      4.789999961853027,
+      7.400000095367432,
+      7.700000286102295,
+      9.09000015258789,
+      12.199999809265137,
+      17.670000076293945,
+      24.46000099182129,
+      28.57000160217285,
+      30.420001983642578,
+      30.840002059936523,
+      32.590003967285156,
+      32.93000411987305,
+      42.320003509521484,
+      44.96000289916992,
+      50.340003967285156,
+      50.45000457763672,
+      57.55000305175781,
+      57.93000411987305,
+      58.21000289916992,
+      60.1400032043457,
+      62.61000442504883,
+      62.62000274658203,
+      62.71000289916992,
+      63.1400032043457,
+      63.1400032043457,
+      63.77000427246094,
+      63.93000411987305,
+      63.96000289916992,
+      63.970001220703125,
+      64.02999877929688,
+      64.06999969482422,
+      64.08000183105469,
+      64.12000274658203,
+      64.41000366210938,
+      64.4800033569336,
+      64.51000213623047,
+      64.52999877929688,
+      64.83999633789062
+    ],
+    "short_factor": [
+      1.0,
+      1.0199999809265137,
+      1.0299999713897705,
+      1.0299999713897705,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0699999332427979,
+      1.0999999046325684,
+      1.1099998950958252,
+      1.1599998474121094,
+      1.1599998474121094,
+      1.1699998378753662,
+      1.2899998426437378,
+      1.339999794960022,
+      1.679999828338623,
+      1.7899998426437378,
+      1.8199998140335083,
+      1.8499997854232788,
+      1.8799997568130493,
+      1.9099997282028198,
+      1.9399996995925903,
+      1.9899996519088745,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0799996852874756,
+      2.0899996757507324,
+      2.189999580383301,
+      2.2199995517730713,
+      2.5899994373321533,
+      2.729999542236328,
+      2.749999523162842,
+      2.8399994373321533
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}
+
+[2025-07-05 09:58:25,678][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-96] due to args.save_total_limit
+[2025-07-05 09:59:35,684][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt. If id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-05 09:59:35,687][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-05 09:59:35,687][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-05 09:59:35,687][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-05 09:59:53,724][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-160
+[2025-07-05 09:59:54,025][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
+[2025-07-05 09:59:54,026][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0800000429153442,
+      1.1100000143051147,
+      1.1399999856948853,
+      1.340000033378601,
+      1.5899999141693115,
+      1.600000023841858,
+      1.6200000047683716,
+      2.620000123977661,
+      3.2300000190734863,
+      3.2300000190734863,
+      4.789999961853027,
+      7.400000095367432,
+      7.700000286102295,
+      9.09000015258789,
+      12.199999809265137,
+      17.670000076293945,
+      24.46000099182129,
+      28.57000160217285,
+      30.420001983642578,
+      30.840002059936523,
+      32.590003967285156,
+      32.93000411987305,
+      42.320003509521484,
+      44.96000289916992,
+      50.340003967285156,
+      50.45000457763672,
+      57.55000305175781,
+      57.93000411987305,
+      58.21000289916992,
+      60.1400032043457,
+      62.61000442504883,
+      62.62000274658203,
+      62.71000289916992,
+      63.1400032043457,
+      63.1400032043457,
+      63.77000427246094,
+      63.93000411987305,
+      63.96000289916992,
+      63.970001220703125,
+      64.02999877929688,
+      64.06999969482422,
+      64.08000183105469,
+      64.12000274658203,
+      64.41000366210938,
+      64.4800033569336,
+      64.51000213623047,
+      64.52999877929688,
+      64.83999633789062
+    ],
+    "short_factor": [
+      1.0,
+      1.0199999809265137,
+      1.0299999713897705,
+      1.0299999713897705,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0699999332427979,
+      1.0999999046325684,
+      1.1099998950958252,
+      1.1599998474121094,
+      1.1599998474121094,
+      1.1699998378753662,
+      1.2899998426437378,
+      1.339999794960022,
+      1.679999828338623,
+      1.7899998426437378,
+      1.8199998140335083,
+      1.8499997854232788,
+      1.8799997568130493,
+      1.9099997282028198,
+      1.9399996995925903,
+      1.9899996519088745,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0799996852874756,
+      2.0899996757507324,
+      2.189999580383301,
+      2.2199995517730713,
+      2.5899994373321533,
+      2.729999542236328,
+      2.749999523162842,
+      2.8399994373321533
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}
+
+[2025-07-05 09:59:54,282][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-128] due to args.save_total_limit
+[2025-07-05 10:01:04,308][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt. If id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-05 10:01:04,311][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-05 10:01:04,311][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-05 10:01:04,311][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-05 10:01:22,358][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-192
+[2025-07-05 10:01:22,666][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
+[2025-07-05 10:01:22,667][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0800000429153442,
+      1.1100000143051147,
+      1.1399999856948853,
+      1.340000033378601,
+      1.5899999141693115,
+      1.600000023841858,
+      1.6200000047683716,
+      2.620000123977661,
+      3.2300000190734863,
+      3.2300000190734863,
+      4.789999961853027,
+      7.400000095367432,
+      7.700000286102295,
+      9.09000015258789,
+      12.199999809265137,
+      17.670000076293945,
+      24.46000099182129,
+      28.57000160217285,
+      30.420001983642578,
+      30.840002059936523,
+      32.590003967285156,
+      32.93000411987305,
+      42.320003509521484,
+      44.96000289916992,
+      50.340003967285156,
+      50.45000457763672,
+      57.55000305175781,
+      57.93000411987305,
+      58.21000289916992,
+      60.1400032043457,
+      62.61000442504883,
+      62.62000274658203,
+      62.71000289916992,
+      63.1400032043457,
+      63.1400032043457,
+      63.77000427246094,
+      63.93000411987305,
+      63.96000289916992,
+      63.970001220703125,
+      64.02999877929688,
+      64.06999969482422,
+      64.08000183105469,
+      64.12000274658203,
+      64.41000366210938,
+      64.4800033569336,
+      64.51000213623047,
+      64.52999877929688,
+      64.83999633789062
+    ],
+    "short_factor": [
+      1.0,
+      1.0199999809265137,
+      1.0299999713897705,
+      1.0299999713897705,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0699999332427979,
+      1.0999999046325684,
+      1.1099998950958252,
+      1.1599998474121094,
+      1.1599998474121094,
+      1.1699998378753662,
+      1.2899998426437378,
+      1.339999794960022,
+      1.679999828338623,
+      1.7899998426437378,
+      1.8199998140335083,
+      1.8499997854232788,
+      1.8799997568130493,
+      1.9099997282028198,
+      1.9399996995925903,
+      1.9899996519088745,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0799996852874756,
+      2.0899996757507324,
+      2.189999580383301,
+      2.2199995517730713,
+      2.5899994373321533,
+      2.729999542236328,
+      2.749999523162842,
+      2.8399994373321533
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}
+
+[2025-07-05 10:01:22,966][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-160] due to args.save_total_limit
+[2025-07-05 10:01:22,972][transformers.trainer][INFO] - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+[2025-07-05 10:01:22,973][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-32 (score: 0.06300703082747416).
+[2025-07-05 10:01:23,070][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-05/09-51-54/results/phi35-balanced/C4/checkpoint-192] due to args.save_total_limit
+[2025-07-05 10:01:23,078][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt. If id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-05 10:01:23,081][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-05 10:01:23,081][transformers.trainer][INFO] -   Num examples = 132
+[2025-07-05 10:01:23,081][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-05 10:01:41,115][__main__][INFO] - Training completed successfully.
+[2025-07-05 10:01:41,115][__main__][INFO] - Running on Test
+[2025-07-05 10:01:41,115][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt. If id, reference, essay_year, grades, essay_text, prompt, supporting_text, id_prompt are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-07-05 10:01:41,118][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-07-05 10:01:41,118][transformers.trainer][INFO] -   Num examples = 138
+[2025-07-05 10:01:41,118][transformers.trainer][INFO] -   Batch size = 4
+[2025-07-05 10:02:00,134][__main__][INFO] - Test metrics: {'eval_loss': 1.9528576135635376, 'eval_model_preparation_time': 0.0074, 'eval_accuracy': 0.34057971014492755, 'eval_RMSE': 38.52347298744614, 'eval_QWK': 0.083437110834371, 'eval_HDIV': 0.01449275362318836, 'eval_Macro_F1': 0.09239974422216134, 'eval_Micro_F1': 0.34057971014492755, 'eval_Weighted_F1': 0.19540394231494831, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 0, 'eval_TN_1': 137, 'eval_FP_1': 0, 'eval_FN_1': 1, 'eval_TP_2': 0, 'eval_TN_2': 129, 'eval_FP_2': 0, 'eval_FN_2': 9, 'eval_TP_3': 2, 'eval_TN_3': 58, 'eval_FP_3': 4, 'eval_FN_3': 74, 'eval_TP_4': 45, 'eval_TN_4': 5, 'eval_FP_4': 87, 'eval_FN_4': 1, 'eval_TP_5': 0, 'eval_TN_5': 133, 'eval_FP_5': 0, 'eval_FN_5': 5, 'eval_runtime': 19.0083, 'eval_samples_per_second': 7.26, 'eval_steps_per_second': 1.841, 'epoch': 6.0}
+[2025-07-05 10:02:00,134][transformers.trainer][INFO] - Saving model checkpoint to ./results/phi35-balanced/C4/best_model
+[2025-07-05 10:02:00,426][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--Phi-3.5-mini-instruct/snapshots/3145e03a9fd4cdd7cd953c34d9bbf7ad606122ca/config.json
+[2025-07-05 10:02:00,427][transformers.configuration_utils][INFO] - Model config Phi3Config {
+  "architectures": [
+    "Phi3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "configuration_phi3.Phi3Config",
+    "AutoModelForCausalLM": "modeling_phi3.Phi3ForCausalLM"
+  },
+  "bos_token_id": 1,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 32000,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "model_type": "phi3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "original_max_position_embeddings": 4096,
+  "pad_token_id": 32000,
+  "partial_rotary_factor": 1.0,
+  "resid_pdrop": 0.0,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "long_factor": [
+      1.0800000429153442,
+      1.1100000143051147,
+      1.1399999856948853,
+      1.340000033378601,
+      1.5899999141693115,
+      1.600000023841858,
+      1.6200000047683716,
+      2.620000123977661,
+      3.2300000190734863,
+      3.2300000190734863,
+      4.789999961853027,
+      7.400000095367432,
+      7.700000286102295,
+      9.09000015258789,
+      12.199999809265137,
+      17.670000076293945,
+      24.46000099182129,
+      28.57000160217285,
+      30.420001983642578,
+      30.840002059936523,
+      32.590003967285156,
+      32.93000411987305,
+      42.320003509521484,
+      44.96000289916992,
+      50.340003967285156,
+      50.45000457763672,
+      57.55000305175781,
+      57.93000411987305,
+      58.21000289916992,
+      60.1400032043457,
+      62.61000442504883,
+      62.62000274658203,
+      62.71000289916992,
+      63.1400032043457,
+      63.1400032043457,
+      63.77000427246094,
+      63.93000411987305,
+      63.96000289916992,
+      63.970001220703125,
+      64.02999877929688,
+      64.06999969482422,
+      64.08000183105469,
+      64.12000274658203,
+      64.41000366210938,
+      64.4800033569336,
+      64.51000213623047,
+      64.52999877929688,
+      64.83999633789062
+    ],
+    "short_factor": [
+      1.0,
+      1.0199999809265137,
+      1.0299999713897705,
+      1.0299999713897705,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0499999523162842,
+      1.0699999332427979,
+      1.0999999046325684,
+      1.1099998950958252,
+      1.1599998474121094,
+      1.1599998474121094,
+      1.1699998378753662,
+      1.2899998426437378,
+      1.339999794960022,
+      1.679999828338623,
+      1.7899998426437378,
+      1.8199998140335083,
+      1.8499997854232788,
+      1.8799997568130493,
+      1.9099997282028198,
+      1.9399996995925903,
+      1.9899996519088745,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0199997425079346,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0299997329711914,
+      2.0799996852874756,
+      2.0899996757507324,
+      2.189999580383301,
+      2.2199995517730713,
+      2.5899994373321533,
+      2.729999542236328,
+      2.749999523162842,
+      2.8399994373321533
+    ],
+    "type": "longrope"
+  },
+  "rope_theta": 10000.0,
+  "sliding_window": 262144,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 32064
+}
+
+[2025-07-05 10:02:00,654][transformers.tokenization_utils_base][INFO] - chat template saved in ./results/phi35-balanced/C4/best_model/chat_template.jinja
+[2025-07-05 10:02:00,655][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/phi35-balanced/C4/best_model/tokenizer_config.json
+[2025-07-05 10:02:00,655][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/phi35-balanced/C4/best_model/special_tokens_map.json
+[2025-07-05 10:02:00,680][__main__][INFO] - Model and tokenizer saved to ./results/phi35-balanced/C4/best_model
+[2025-07-05 10:02:00,686][__main__][INFO] - Fine Tuning Finished.
+[2025-07-05 10:02:01,196][__main__][INFO] - Total emissions: 0.0074 kg CO2eq

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|dummy_id_0|>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,139 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<|dummy_id_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 131072,
+  "pad_token": "<|dummy_id_0|>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7073be4ddd68d8c7b5ef808ffc484ee2cba54285c301a4d8597e10860564830d
+size 5841