| [2025-07-06 05:42:53,025][__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/phi4-balanced/C2 |
| logging_dir: ./logs/phi4-balanced/C2 |
| best_model_dir: ./results/phi4-balanced/C2/best_model |
| lora_r: 16 |
| lora_dropout: 0.1 |
| lora_alpha: 32 |
| lora_target_modules: all-linear |
| tokenizer: |
| name: microsoft/phi-4 |
| dataset: |
| grade_index: 1 |
| use_full_context: true |
| training_params: |
| weight_decay: 0.01 |
| warmup_ratio: 0.1 |
| learning_rate: 5.0e-05 |
| train_batch_size: 8 |
| eval_batch_size: 4 |
| gradient_accumulation_steps: 2 |
| gradient_checkpointing: true |
|
|
| [2025-07-06 05:42:56,955][__main__][INFO] - GPU 0: NVIDIA H200 | TDP ≈ 700 W |
| [2025-07-06 05:42:56,955][__main__][INFO] - Starting the Fine Tuning training process. |
| [2025-07-06 05:43:00,852][transformers.tokenization_utils_base][INFO] - loading file vocab.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/vocab.json |
| [2025-07-06 05:43:00,852][transformers.tokenization_utils_base][INFO] - loading file merges.txt from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/merges.txt |
| [2025-07-06 05:43:00,852][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/tokenizer.json |
| [2025-07-06 05:43:00,852][transformers.tokenization_utils_base][INFO] - loading file added_tokens.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/added_tokens.json |
| [2025-07-06 05:43:00,852][transformers.tokenization_utils_base][INFO] - loading file special_tokens_map.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/special_tokens_map.json |
| [2025-07-06 05:43:00,852][transformers.tokenization_utils_base][INFO] - loading file tokenizer_config.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/tokenizer_config.json |
| [2025-07-06 05:43:00,852][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None |
| [2025-07-06 05:43:00,992][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: False; Use Full Context: True |
| [2025-07-06 05:43:01,238][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 05:43:01,238][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "id2label": { |
| "0": "LABEL_0", |
| "1": "LABEL_1", |
| "2": "LABEL_2", |
| "3": "LABEL_3", |
| "4": "LABEL_4", |
| "5": "LABEL_5" |
| }, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "label2id": { |
| "LABEL_0": 0, |
| "LABEL_1": 1, |
| "LABEL_2": 2, |
| "LABEL_3": 3, |
| "LABEL_4": 4, |
| "LABEL_5": 5 |
| }, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
|
|
| [2025-07-06 05:43:01,365][transformers.modeling_utils][INFO] - loading weights file model.safetensors from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/model.safetensors.index.json |
| [2025-07-06 05:43:01,366][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object |
| [2025-07-06 05:43:01,366][transformers.modeling_utils][INFO] - Instantiating Phi3ForSequenceClassification model under default dtype torch.bfloat16. |
| [2025-07-06 05:43:19,829][transformers.modeling_utils][INFO] - Some weights of the model checkpoint at microsoft/phi-4 were not used when initializing Phi3ForSequenceClassification: ['lm_head.weight'] |
| - This IS expected if you are initializing Phi3ForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model). |
| - This IS NOT expected if you are initializing Phi3ForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model). |
| [2025-07-06 05:43:19,829][transformers.modeling_utils][WARNING] - Some weights of Phi3ForSequenceClassification were not initialized from the model checkpoint at microsoft/phi-4 and are newly initialized: ['score.weight'] |
| You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference. |
| [2025-07-06 05:43:21,857][__main__][INFO] - Initialized new PEFT model for ce loss |
| [2025-07-06 05:43:21,860][__main__][INFO] - None |
| [2025-07-06 05:43:21,861][transformers.training_args][INFO] - PyTorch: setting up devices |
| [2025-07-06 05:43:21,900][__main__][INFO] - Total steps: 620. Number of warmup steps: 62 |
| [2025-07-06 05:43:21,907][transformers.trainer][INFO] - You have loaded a model on multiple GPUs. `is_model_parallel` attribute will be force-set to `True` to avoid any unexpected behavior such as device placement mismatching. |
| [2025-07-06 05:43:21,940][transformers.trainer][INFO] - Using auto half precision backend |
| [2025-07-06 05:43:21,941][transformers.trainer][WARNING] - No label_names provided for model class `PeftModelForSequenceClassification`. Since `PeftModel` hides base models input arguments, if label_names is not given, label_names can't be set automatically within `Trainer`. Note that empty label_names list will be used instead. |
| [2025-07-06 05:43:21,942][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 05:43:21,955][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 05:43:21,955][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 05:43:21,955][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 05:44:09,428][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 05:44:09,469][transformers.trainer][INFO] - ***** Running training ***** |
| [2025-07-06 05:44:09,469][transformers.trainer][INFO] - Num examples = 500 |
| [2025-07-06 05:44:09,469][transformers.trainer][INFO] - Num Epochs = 20 |
| [2025-07-06 05:44:09,469][transformers.trainer][INFO] - Instantaneous batch size per device = 8 |
| [2025-07-06 05:44:09,469][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16 |
| [2025-07-06 05:44:09,469][transformers.trainer][INFO] - Gradient Accumulation steps = 2 |
| [2025-07-06 05:44:09,469][transformers.trainer][INFO] - Total optimization steps = 640 |
| [2025-07-06 05:44:09,471][transformers.trainer][INFO] - Number of trainable parameters = 55,736,320 |
| [2025-07-06 05:44:09,568][transformers.models.phi3.modeling_phi3][WARNING] - `use_cache=True` is incompatible with gradient checkpointing. Setting `use_cache=False`. |
| [2025-07-06 05:53:55,371][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 05:53:55,374][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 05:53:55,374][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 05:53:55,374][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 05:54:42,590][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-32 |
| [2025-07-06 05:54:42,962][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 05:54:42,962][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
| |
| [2025-07-06 06:04:29,707][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 06:04:29,711][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 06:04:29,711][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 06:04:29,711][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 06:05:16,901][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-64 |
| [2025-07-06 06:05:17,244][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 06:05:17,244][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
|
|
| [2025-07-06 06:05:18,342][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-32] due to args.save_total_limit |
| [2025-07-06 06:15:04,258][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 06:15:04,262][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 06:15:04,262][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 06:15:04,262][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 06:15:51,472][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-96 |
| [2025-07-06 06:15:51,812][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 06:15:51,813][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
| |
| [2025-07-06 06:15:52,857][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-64] due to args.save_total_limit |
| [2025-07-06 06:25:38,456][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 06:25:38,459][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 06:25:38,459][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 06:25:38,459][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 06:26:25,664][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-128 |
| [2025-07-06 06:26:26,151][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 06:26:26,152][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
|
|
| [2025-07-06 06:26:27,245][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-96] due to args.save_total_limit |
| [2025-07-06 06:36:13,060][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 06:36:13,063][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 06:36:13,064][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 06:36:13,064][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 06:37:00,261][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-160 |
| [2025-07-06 06:37:00,594][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 06:37:00,595][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
| |
| [2025-07-06 06:46:47,163][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 06:46:47,166][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 06:46:47,166][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 06:46:47,166][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 06:47:34,344][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-192 |
| [2025-07-06 06:47:34,677][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 06:47:34,677][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
|
|
| [2025-07-06 06:47:35,674][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-160] due to args.save_total_limit |
| [2025-07-06 06:57:21,183][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 06:57:21,186][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 06:57:21,186][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 06:57:21,186][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 06:58:08,374][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-224 |
| [2025-07-06 06:58:08,706][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 06:58:08,706][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
| |
| [2025-07-06 06:58:09,678][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-128] due to args.save_total_limit |
| [2025-07-06 06:58:09,713][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-192] due to args.save_total_limit |
| [2025-07-06 07:07:55,067][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 07:07:55,071][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 07:07:55,071][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 07:07:55,071][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 07:08:42,214][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-256 |
| [2025-07-06 07:08:42,731][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 07:08:42,732][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
|
|
| [2025-07-06 07:08:43,869][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-224] due to args.save_total_limit |
| [2025-07-06 07:18:29,265][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 07:18:29,268][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 07:18:29,268][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 07:18:29,268][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 07:19:16,476][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-288 |
| [2025-07-06 07:19:16,832][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 07:19:16,833][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
| |
| [2025-07-06 07:29:03,608][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 07:29:03,612][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 07:29:03,612][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 07:29:03,612][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 07:29:50,809][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-320 |
| [2025-07-06 07:29:51,119][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 07:29:51,119][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
|
|
| [2025-07-06 07:29:52,167][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-288] due to args.save_total_limit |
| [2025-07-06 07:39:38,201][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 07:39:38,204][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 07:39:38,205][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 07:39:38,205][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 07:40:25,389][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-352 |
| [2025-07-06 07:40:25,731][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 07:40:25,732][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
| |
| [2025-07-06 07:40:26,767][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-320] due to args.save_total_limit |
| [2025-07-06 07:50:12,300][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 07:50:12,303][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 07:50:12,304][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 07:50:12,304][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 07:50:59,498][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-384 |
| [2025-07-06 07:50:59,844][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 07:50:59,845][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
|
|
| [2025-07-06 07:51:00,947][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-352] due to args.save_total_limit |
| [2025-07-06 08:00:45,379][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 08:00:45,383][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 08:00:45,383][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 08:00:45,383][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 08:01:32,339][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-416 |
| [2025-07-06 08:01:32,692][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 08:01:32,692][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
| |
| [2025-07-06 08:01:33,756][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-384] due to args.save_total_limit |
| [2025-07-06 08:01:33,792][transformers.trainer][INFO] - |
| |
| Training completed. Do not forget to share your model on huggingface.co/models =) |
| |
| |
| [2025-07-06 08:01:33,792][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-256 (score: 0.577060350421804). |
| [2025-07-06 08:01:34,058][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-07-06/05-42-53/results/phi4-balanced/C2/checkpoint-416] due to args.save_total_limit |
| [2025-07-06 08:01:34,095][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 08:01:34,103][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 08:01:34,103][transformers.trainer][INFO] - Num examples = 132 |
| [2025-07-06 08:01:34,103][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 08:02:21,069][__main__][INFO] - Training completed successfully. |
| [2025-07-06 08:02:21,069][__main__][INFO] - Running on Test |
| [2025-07-06 08:02:21,069][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference. If essay_year, id, grades, prompt, supporting_text, id_prompt, essay_text, reference are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. |
| [2025-07-06 08:02:21,072][transformers.trainer][INFO] - |
| ***** Running Evaluation ***** |
| [2025-07-06 08:02:21,072][transformers.trainer][INFO] - Num examples = 138 |
| [2025-07-06 08:02:21,072][transformers.trainer][INFO] - Batch size = 4 |
| [2025-07-06 08:03:10,772][__main__][INFO] - Test metrics: {'eval_loss': 1.3918403387069702, 'eval_model_preparation_time': 0.0091, 'eval_accuracy': 0.5144927536231884, 'eval_RMSE': 52.08688393694587, 'eval_QWK': 0.5905356055995131, 'eval_HDIV': 0.050724637681159424, 'eval_Macro_F1': 0.36549678320993584, 'eval_Micro_F1': 0.5144927536231884, 'eval_Weighted_F1': 0.45549927273540014, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 29, 'eval_TN_1': 78, 'eval_FP_1': 25, 'eval_FN_1': 6, 'eval_TP_2': 4, 'eval_TN_2': 125, 'eval_FP_2': 8, 'eval_FN_2': 1, 'eval_TP_3': 26, 'eval_TN_3': 65, 'eval_FP_3': 22, 'eval_FN_3': 25, 'eval_TP_4': 0, 'eval_TN_4': 112, 'eval_FP_4': 0, 'eval_FN_4': 26, 'eval_TP_5': 12, 'eval_TN_5': 106, 'eval_FP_5': 12, 'eval_FN_5': 8, 'eval_runtime': 49.6901, 'eval_samples_per_second': 2.777, 'eval_steps_per_second': 0.704, 'epoch': 13.0} |
| [2025-07-06 08:03:10,772][transformers.trainer][INFO] - Saving model checkpoint to ./results/phi4-balanced/C2/best_model |
| [2025-07-06 08:03:11,094][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /workspace/.hf_home/hub/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json |
| [2025-07-06 08:03:11,095][transformers.configuration_utils][INFO] - Model config Phi3Config { |
| "architectures": [ |
| "Phi3ForCausalLM" |
| ], |
| "attention_bias": false, |
| "attention_dropout": 0.0, |
| "bos_token_id": 100257, |
| "embd_pdrop": 0.0, |
| "eos_token_id": 100265, |
| "hidden_act": "silu", |
| "hidden_size": 5120, |
| "initializer_range": 0.02, |
| "intermediate_size": 17920, |
| "max_position_embeddings": 16384, |
| "model_type": "phi3", |
| "num_attention_heads": 40, |
| "num_hidden_layers": 40, |
| "num_key_value_heads": 10, |
| "original_max_position_embeddings": 16384, |
| "pad_token_id": 100349, |
| "partial_rotary_factor": 1.0, |
| "resid_pdrop": 0.0, |
| "rms_norm_eps": 1e-05, |
| "rope_scaling": null, |
| "rope_theta": 250000, |
| "sliding_window": null, |
| "tie_word_embeddings": false, |
| "torch_dtype": "bfloat16", |
| "transformers_version": "4.53.0", |
| "use_cache": true, |
| "vocab_size": 100352 |
| } |
| |
| [2025-07-06 08:03:11,716][transformers.tokenization_utils_base][INFO] - chat template saved in ./results/phi4-balanced/C2/best_model/chat_template.jinja |
| [2025-07-06 08:03:11,717][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/phi4-balanced/C2/best_model/tokenizer_config.json |
| [2025-07-06 08:03:11,717][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/phi4-balanced/C2/best_model/special_tokens_map.json |
| [2025-07-06 08:03:11,787][__main__][INFO] - Model and tokenizer saved to ./results/phi4-balanced/C2/best_model |
| [2025-07-06 08:03:11,800][__main__][INFO] - Fine Tuning Finished. |
| [2025-07-06 08:03:12,308][__main__][INFO] - Total emissions: 0.1076 kg CO2eq |
| |
