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-C2-full_context
+    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: 0.2233245149911816
+          - name: QWK
+            type: qwk
+            value: 0.4587224505042959
+          - name: Weighted Macro F1
+            type: f1
+            value: 0.3727858293075684
+---
+# Model ID: phi-4-phi4_classification_lora-C2-full_context
+## Results
+|                  |   test_data |
+|:-----------------|------------:|
+| eval_accuracy    |   0.442029  |
+| eval_RMSE        |  54.0531    |
+| eval_QWK         |   0.458722  |
+| eval_Macro_F1    |   0.223325  |
+| eval_Weighted_F1 |   0.372786  |
+| eval_Micro_F1    |   0.442029  |
+| eval_HDIV        |   0.0289855 |
+        

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": [
+    "classifier",
+    "score"
+  ],
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_up_proj",
+    "down_proj",
+    "qkv_proj",
+    "o_proj"
+  ],
+  "task_type": "SEQ_CLS",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa6e445206565f2427234b06336a1f989f632fc5ef4ba31e5481e49218323265
+size 111515584

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
+2025-06-30T09:27:22,jbcs2025,46b44439-3102-4d30-a52f-56cdd62e240d,phi-4-phi4_classification_lora-C2-full_context,4890.491208813153,0.5174636094209252,0.0001058101502132146,66.0,648.6228617858472,70.0,0.08833767328320886,0.8842556029594562,0.09348034965336427,1.0660736258960288,Japan,JPN,,,,Linux-5.15.0-130-generic-x86_64-with-glibc2.35,3.12.11,3.0.2,192,INTEL(R) XEON(R) PLATINUM 8558,1,1 x NVIDIA H200,139.69,35.69,2015.3516235351562,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
+4.2344865798950195,0.0097,0.22727272727272727,61.987290975039734,0.0,0.19696969696969702,0.07407407407407407,0.22727272727272727,0.08417508417508417,0,131,0,1,0,107,0,25,0,132,0,0,0,71,0,61,30,0,102,0,0,117,0,15,45.2744,2.916,0.199,-1,validation_before_training,2025-06-30 08:06:10,phi-4-phi4_classification_lora-C2-full_context
+1.6081122159957886,0.0097,0.5,46.5800061152526,0.5310788282924506,0.007575757575757569,0.30988551518168245,0.5,0.43457471680468196,0,131,0,1,12,99,8,13,0,132,0,0,46,31,40,15,0,102,0,30,8,99,18,7,45.1581,2.923,0.199,10.0,validation_after_training,2025-06-30 08:06:10,phi-4-phi4_classification_lora-C2-full_context
+1.8242748975753784,0.0097,0.4420289855072464,54.053113975374096,0.45872245050429594,0.02898550724637683,0.22332451499118164,0.4420289855072464,0.37278582930756843,0,137,0,1,22,83,20,13,0,133,0,5,35,38,49,16,0,112,0,26,4,110,8,16,48.8241,2.826,0.184,10.0,test_results,2025-06-30 08:06:10,phi-4-phi4_classification_lora-C2-full_context

run_experiment.log

@@ -0,0 +1,605 @@
+[2025-06-30 08:05:48,345][__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: 8
+    lora_dropout: 0.05
+    lora_alpha: 16
+    lora_target_modules: all-linear
+    checkpoint_path: ''
+  tokenizer:
+    name: microsoft/phi-4
+  dataset:
+    grade_index: 1
+    use_full_context: true
+  training_params:
+    weight_decay: 0.01
+    warmup_ratio: 0.1
+    learning_rate: 5.0e-05
+    train_batch_size: 1
+    eval_batch_size: 16
+    gradient_accumulation_steps: 16
+    gradient_checkpointing: false
+
+[2025-06-30 08:05:52,309][__main__][INFO] - GPU 0: NVIDIA H200 | TDP ≈ 700 W
+[2025-06-30 08:05:52,310][__main__][INFO] - Starting the Fine Tuning training process.
+[2025-06-30 08:05:58,177][transformers.tokenization_utils_base][INFO] - loading file vocab.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/vocab.json
+[2025-06-30 08:05:58,177][transformers.tokenization_utils_base][INFO] - loading file merges.txt from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/merges.txt
+[2025-06-30 08:05:58,178][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/tokenizer.json
+[2025-06-30 08:05:58,178][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/added_tokens.json
+[2025-06-30 08:05:58,178][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
+[2025-06-30 08:05:58,178][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/tokenizer_config.json
+[2025-06-30 08:05:58,178][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None
+[2025-06-30 08:05:58,320][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: False; Use Full Context: True
+[2025-06-30 08:06:00,139][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 08:06:00,140][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
+}
+
+[2025-06-30 08:06:00,277][transformers.modeling_utils][INFO] - loading weights file model.safetensors from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/model.safetensors.index.json
+[2025-06-30 08:06:00,278][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object
+[2025-06-30 08:06:00,278][transformers.modeling_utils][INFO] - Instantiating Phi3ForSequenceClassification model under default dtype torch.bfloat16.
+[2025-06-30 08:06:08,653][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).
+[2025-06-30 08:06:08,653][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.
+[2025-06-30 08:06:10,413][__main__][INFO] - Initialized new PEFT model for ce loss
+[2025-06-30 08:06:10,415][__main__][INFO] - None
+[2025-06-30 08:06:10,416][transformers.training_args][INFO] - PyTorch: setting up devices
+[2025-06-30 08:06:10,452][__main__][INFO] - Total steps: 620. Number of warmup steps: 62
+[2025-06-30 08:06:10,457][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.
+[2025-06-30 08:06:10,481][transformers.trainer][INFO] - Using auto half precision backend
+[2025-06-30 08:06:10,482][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.
+[2025-06-30 08:06:10,483][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 08:06:10,496][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 08:06:10,496][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 08:06:10,496][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 08:06:55,940][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 08:06:55,981][transformers.trainer][INFO] - ***** Running training *****
+[2025-06-30 08:06:55,981][transformers.trainer][INFO] -   Num examples = 500
+[2025-06-30 08:06:55,981][transformers.trainer][INFO] -   Num Epochs = 20
+[2025-06-30 08:06:55,981][transformers.trainer][INFO] -   Instantaneous batch size per device = 1
+[2025-06-30 08:06:55,981][transformers.trainer][INFO] -   Total train batch size (w. parallel, distributed & accumulation) = 16
+[2025-06-30 08:06:55,981][transformers.trainer][INFO] -   Gradient Accumulation steps = 16
+[2025-06-30 08:06:55,981][transformers.trainer][INFO] -   Total optimization steps = 640
+[2025-06-30 08:06:55,983][transformers.trainer][INFO] -   Number of trainable parameters = 27,883,520
+[2025-06-30 08:14:02,346][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 08:14:02,349][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 08:14:02,349][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 08:14:02,349][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 08:14:47,567][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-32
+[2025-06-30 08:14:48,049][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 08:14:48,049][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
+}
+
+[2025-06-30 08:21:55,401][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 08:21:55,405][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 08:21:55,405][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 08:21:55,405][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 08:22:40,630][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-64
+[2025-06-30 08:22:41,335][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 08:22:41,336][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
+}
+
+[2025-06-30 08:29:48,445][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 08:29:48,448][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 08:29:48,448][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 08:29:48,448][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 08:30:33,554][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-96
+[2025-06-30 08:30:34,024][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 08:30:34,025][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
+}
+
+[2025-06-30 08:30:34,540][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-32] due to args.save_total_limit
+[2025-06-30 08:30:34,558][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-64] due to args.save_total_limit
+[2025-06-30 08:37:41,234][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 08:37:41,237][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 08:37:41,237][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 08:37:41,237][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 08:38:26,445][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-128
+[2025-06-30 08:38:26,905][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 08:38:26,905][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
+}
+
+[2025-06-30 08:38:27,547][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-96] due to args.save_total_limit
+[2025-06-30 08:45:34,280][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 08:45:34,284][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 08:45:34,284][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 08:45:34,284][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 08:46:19,387][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-160
+[2025-06-30 08:46:19,854][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 08:46:19,854][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
+}
+
+[2025-06-30 08:46:20,555][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-128] due to args.save_total_limit
+[2025-06-30 08:53:27,914][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 08:53:27,917][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 08:53:27,917][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 08:53:27,917][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 08:54:13,046][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-192
+[2025-06-30 08:54:13,515][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 08:54:13,515][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
+}
+
+[2025-06-30 09:01:21,666][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 09:01:21,670][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 09:01:21,670][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 09:01:21,670][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 09:02:06,827][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-224
+[2025-06-30 09:02:07,304][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 09:02:07,304][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
+}
+
+[2025-06-30 09:02:07,852][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-192] due to args.save_total_limit
+[2025-06-30 09:09:14,419][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 09:09:14,423][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 09:09:14,423][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 09:09:14,423][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 09:09:59,575][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-256
+[2025-06-30 09:10:00,040][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 09:10:00,040][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
+}
+
+[2025-06-30 09:10:00,654][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-224] due to args.save_total_limit
+[2025-06-30 09:17:07,402][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 09:17:07,405][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 09:17:07,406][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 09:17:07,406][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 09:17:52,535][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-288
+[2025-06-30 09:17:53,001][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 09:17:53,002][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
+}
+
+[2025-06-30 09:17:53,663][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-256] due to args.save_total_limit
+[2025-06-30 09:25:00,179][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 09:25:00,182][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 09:25:00,183][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 09:25:00,183][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 09:25:45,339][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-320
+[2025-06-30 09:25:45,818][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 09:25:45,818][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
+}
+
+[2025-06-30 09:25:46,565][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-288] due to args.save_total_limit
+[2025-06-30 09:25:46,592][transformers.trainer][INFO] - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+[2025-06-30 09:25:46,592][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-160 (score: 0.5310788282924506).
+[2025-06-30 09:25:46,784][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/08-05-48/results/checkpoint-320] due to args.save_total_limit
+[2025-06-30 09:25:46,809][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 09:25:46,815][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 09:25:46,815][transformers.trainer][INFO] -   Num examples = 132
+[2025-06-30 09:25:46,816][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 09:26:31,982][__main__][INFO] - Training completed successfully.
+[2025-06-30 09:26:31,982][__main__][INFO] - Running on Test
+[2025-06-30 09:26:31,982][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, prompt, id, reference, essay_text, supporting_text, essay_year, grades. If id_prompt, prompt, id, reference, essay_text, supporting_text, essay_year, grades are not expected by `PeftModelForSequenceClassification.forward`,  you can safely ignore this message.
+[2025-06-30 09:26:31,985][transformers.trainer][INFO] - 
+***** Running Evaluation *****
+[2025-06-30 09:26:31,985][transformers.trainer][INFO] -   Num examples = 138
+[2025-06-30 09:26:31,986][transformers.trainer][INFO] -   Batch size = 16
+[2025-06-30 09:27:20,819][__main__][INFO] - Test metrics: {'eval_loss': 1.8242748975753784, 'eval_model_preparation_time': 0.0097, 'eval_accuracy': 0.4420289855072464, 'eval_RMSE': 54.053113975374096, 'eval_QWK': 0.45872245050429594, 'eval_HDIV': 0.02898550724637683, 'eval_Macro_F1': 0.22332451499118164, 'eval_Micro_F1': 0.4420289855072464, 'eval_Weighted_F1': 0.37278582930756843, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 22, 'eval_TN_1': 83, 'eval_FP_1': 20, 'eval_FN_1': 13, 'eval_TP_2': 0, 'eval_TN_2': 133, 'eval_FP_2': 0, 'eval_FN_2': 5, 'eval_TP_3': 35, 'eval_TN_3': 38, 'eval_FP_3': 49, 'eval_FN_3': 16, 'eval_TP_4': 0, 'eval_TN_4': 112, 'eval_FP_4': 0, 'eval_FN_4': 26, 'eval_TP_5': 4, 'eval_TN_5': 110, 'eval_FP_5': 8, 'eval_FN_5': 16, 'eval_runtime': 48.8241, 'eval_samples_per_second': 2.826, 'eval_steps_per_second': 0.184, 'epoch': 10.0}
+[2025-06-30 09:27:20,820][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model
+[2025-06-30 09:27:21,265][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json
+[2025-06-30 09:27:21,265][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
+}
+
+[2025-06-30 09:27:21,697][transformers.tokenization_utils_base][INFO] - chat template saved in ./results/best_model/chat_template.jinja
+[2025-06-30 09:27:21,698][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json
+[2025-06-30 09:27:21,698][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json
+[2025-06-30 09:27:21,769][__main__][INFO] - Model and tokenizer saved to ./results/best_model
+[2025-06-30 09:27:21,789][__main__][INFO] - Fine Tuning Finished.
+[2025-06-30 09:27:22,297][__main__][INFO] - Total emissions: 0.5175 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 sha256:2a5429affc16e17bb005644bbc27e85ecd72f13bd3e364f77bd96ee74b2dc74e
+size 5777