| [2025-06-30 09:27:28,426][__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: 2 | |
| 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 09:27:32,417][__main__][INFO] - GPU 0: NVIDIA H200 | TDP ≈ 700 W | |
| [2025-06-30 09:27:32,417][__main__][INFO] - Starting the Fine Tuning training process. | |
| [2025-06-30 09:27:38,120][transformers.tokenization_utils_base][INFO] - loading file vocab.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/vocab.json | |
| [2025-06-30 09:27:38,120][transformers.tokenization_utils_base][INFO] - loading file merges.txt from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/merges.txt | |
| [2025-06-30 09:27:38,120][transformers.tokenization_utils_base][INFO] - loading file tokenizer.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/tokenizer.json | |
| [2025-06-30 09:27:38,120][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 09:27:38,120][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 09:27:38,120][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 09:27:38,120][transformers.tokenization_utils_base][INFO] - loading file chat_template.jinja from cache at None | |
| [2025-06-30 09:27:38,260][__main__][INFO] - Tokenizer function parameters- Padding:longest; Truncation: False; Use Full Context: True | |
| [2025-06-30 09:27:39,994][transformers.configuration_utils][INFO] - loading configuration file config.json from cache at /tmp/models--microsoft--phi-4/snapshots/187ef0342fff0eb3333be9f00389385e95ef0b61/config.json | |
| [2025-06-30 09:27:39,995][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 09:27:40,134][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 09:27:40,134][transformers.modeling_utils][INFO] - Will use torch_dtype=torch.bfloat16 as defined in model's config object | |
| [2025-06-30 09:27:40,134][transformers.modeling_utils][INFO] - Instantiating Phi3ForSequenceClassification model under default dtype torch.bfloat16. | |
| [2025-06-30 09:27:46,898][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 09:27:46,898][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 09:27:48,485][__main__][INFO] - Initialized new PEFT model for ce loss | |
| [2025-06-30 09:27:48,487][__main__][INFO] - None | |
| [2025-06-30 09:27:48,488][transformers.training_args][INFO] - PyTorch: setting up devices | |
| [2025-06-30 09:27:48,542][__main__][INFO] - Total steps: 620. Number of warmup steps: 62 | |
| [2025-06-30 09:27:48,548][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 09:27:48,572][transformers.trainer][INFO] - Using auto half precision backend | |
| [2025-06-30 09:27:48,572][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 09:27:48,574][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 09:27:48,587][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 09:27:48,588][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 09:27:48,588][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 09:28:27,001][transformers.trainer][INFO] - The following columns in the Training set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 09:28:27,042][transformers.trainer][INFO] - ***** Running training ***** | |
| [2025-06-30 09:28:27,042][transformers.trainer][INFO] - Num examples = 500 | |
| [2025-06-30 09:28:27,042][transformers.trainer][INFO] - Num Epochs = 20 | |
| [2025-06-30 09:28:27,042][transformers.trainer][INFO] - Instantaneous batch size per device = 1 | |
| [2025-06-30 09:28:27,042][transformers.trainer][INFO] - Total train batch size (w. parallel, distributed & accumulation) = 16 | |
| [2025-06-30 09:28:27,042][transformers.trainer][INFO] - Gradient Accumulation steps = 16 | |
| [2025-06-30 09:28:27,042][transformers.trainer][INFO] - Total optimization steps = 640 | |
| [2025-06-30 09:28:27,045][transformers.trainer][INFO] - Number of trainable parameters = 27,883,520 | |
| [2025-06-30 09:34:26,717][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 09:34:26,720][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 09:34:26,720][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 09:34:26,720][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 09:35:04,792][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-32 | |
| [2025-06-30 09:35:05,321][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 09:35:05,322][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 09:41:05,170][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 09:41:05,173][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 09:41:05,173][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 09:41:05,173][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 09:41:43,156][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-64 | |
| [2025-06-30 09:41:44,909][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 09:41:44,910][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 09:41:45,517][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-32] due to args.save_total_limit | |
| [2025-06-30 09:47:45,007][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 09:47:45,011][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 09:47:45,011][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 09:47:45,011][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 09:48:23,016][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-96 | |
| [2025-06-30 09:48:23,501][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 09:48:23,502][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 09:48:24,225][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-64] due to args.save_total_limit | |
| [2025-06-30 09:54:23,857][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 09:54:23,862][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 09:54:23,862][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 09:54:23,862][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 09:55:01,937][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-128 | |
| [2025-06-30 09:55:02,392][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 09:55:02,393][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 09:55:03,040][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-96] due to args.save_total_limit | |
| [2025-06-30 10:01:02,645][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 10:01:02,648][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 10:01:02,648][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 10:01:02,648][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 10:01:40,692][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-160 | |
| [2025-06-30 10:01:41,167][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 10:01:41,167][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 10:01:41,843][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-128] due to args.save_total_limit | |
| [2025-06-30 10:07:41,238][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 10:07:41,241][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 10:07:41,241][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 10:07:41,241][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 10:08:19,273][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-192 | |
| [2025-06-30 10:08:19,744][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 10:08:19,744][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 10:08:20,460][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-160] due to args.save_total_limit | |
| [2025-06-30 10:14:19,880][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 10:14:19,883][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 10:14:19,883][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 10:14:19,883][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 10:14:57,863][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-224 | |
| [2025-06-30 10:14:58,337][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 10:14:58,337][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 10:20:58,302][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 10:20:58,305][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 10:20:58,305][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 10:20:58,305][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 10:21:36,277][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-256 | |
| [2025-06-30 10:21:36,974][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 10:21:36,975][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 10:21:37,639][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-192] due to args.save_total_limit | |
| [2025-06-30 10:21:37,665][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-224] due to args.save_total_limit | |
| [2025-06-30 10:27:37,157][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 10:27:37,160][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 10:27:37,160][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 10:27:37,160][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 10:28:15,166][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-288 | |
| [2025-06-30 10:28:16,135][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 10:28:16,136][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 10:34:16,026][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 10:34:16,029][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 10:34:16,030][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 10:34:16,030][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 10:34:54,029][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-320 | |
| [2025-06-30 10:34:54,524][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 10:34:54,525][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 10:34:55,146][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-288] due to args.save_total_limit | |
| [2025-06-30 10:40:54,560][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 10:40:54,564][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 10:40:54,564][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 10:40:54,564][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 10:41:32,561][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-352 | |
| [2025-06-30 10:41:33,024][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 10:41:33,024][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 10:41:33,623][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-320] due to args.save_total_limit | |
| [2025-06-30 10:47:32,871][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 10:47:32,874][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 10:47:32,874][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 10:47:32,874][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 10:48:10,869][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-384 | |
| [2025-06-30 10:48:11,343][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 10:48:11,343][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 10:48:11,923][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-352] due to args.save_total_limit | |
| [2025-06-30 10:54:11,653][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 10:54:11,656][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 10:54:11,656][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 10:54:11,656][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 10:54:49,712][transformers.trainer][INFO] - Saving model checkpoint to /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-416 | |
| [2025-06-30 10:54:50,181][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 10:54:50,182][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 10:54:50,853][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-384] due to args.save_total_limit | |
| [2025-06-30 10:54:50,876][transformers.trainer][INFO] - | |
| Training completed. Do not forget to share your model on huggingface.co/models =) | |
| [2025-06-30 10:54:50,876][transformers.trainer][INFO] - Loading best model from /workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-256 (score: 0.6063931297709924). | |
| [2025-06-30 10:54:51,090][transformers.trainer][INFO] - Deleting older checkpoint [/workspace/jbcs2025/outputs/2025-06-30/09-27-28/results/checkpoint-416] due to args.save_total_limit | |
| [2025-06-30 10:54:51,118][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 10:54:51,124][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 10:54:51,124][transformers.trainer][INFO] - Num examples = 132 | |
| [2025-06-30 10:54:51,124][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 10:55:29,135][__main__][INFO] - Training completed successfully. | |
| [2025-06-30 10:55:29,135][__main__][INFO] - Running on Test | |
| [2025-06-30 10:55:29,135][transformers.trainer][INFO] - The following columns in the Evaluation set don't have a corresponding argument in `PeftModelForSequenceClassification.forward` and have been ignored: grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year. If grades, id, id_prompt, prompt, reference, essay_text, supporting_text, essay_year are not expected by `PeftModelForSequenceClassification.forward`, you can safely ignore this message. | |
| [2025-06-30 10:55:29,138][transformers.trainer][INFO] - | |
| ***** Running Evaluation ***** | |
| [2025-06-30 10:55:29,138][transformers.trainer][INFO] - Num examples = 138 | |
| [2025-06-30 10:55:29,138][transformers.trainer][INFO] - Batch size = 16 | |
| [2025-06-30 10:56:10,542][__main__][INFO] - Test metrics: {'eval_loss': 1.6282387971878052, 'eval_model_preparation_time': 0.01, 'eval_accuracy': 0.45652173913043476, 'eval_RMSE': 38.972305291195504, 'eval_QWK': 0.6404105501849862, 'eval_HDIV': 0.007246376811594235, 'eval_Macro_F1': 0.25875045870127034, 'eval_Micro_F1': 0.45652173913043476, 'eval_Weighted_F1': 0.41459058726322784, 'eval_TP_0': 0, 'eval_TN_0': 137, 'eval_FP_0': 0, 'eval_FN_0': 1, 'eval_TP_1': 16, 'eval_TN_1': 97, 'eval_FP_1': 12, 'eval_FN_1': 13, 'eval_TP_2': 0, 'eval_TN_2': 118, 'eval_FP_2': 2, 'eval_FN_2': 18, 'eval_TP_3': 25, 'eval_TN_3': 56, 'eval_FP_3': 37, 'eval_FN_3': 20, 'eval_TP_4': 22, 'eval_TN_4': 76, 'eval_FP_4': 24, 'eval_FN_4': 16, 'eval_TP_5': 0, 'eval_TN_5': 131, 'eval_FP_5': 0, 'eval_FN_5': 7, 'eval_runtime': 41.3939, 'eval_samples_per_second': 3.334, 'eval_steps_per_second': 0.217, 'epoch': 13.0} | |
| [2025-06-30 10:56:10,543][transformers.trainer][INFO] - Saving model checkpoint to ./results/best_model | |
| [2025-06-30 10:56:11,286][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 10:56:11,287][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 10:56:11,723][transformers.tokenization_utils_base][INFO] - chat template saved in ./results/best_model/chat_template.jinja | |
| [2025-06-30 10:56:11,724][transformers.tokenization_utils_base][INFO] - tokenizer config file saved in ./results/best_model/tokenizer_config.json | |
| [2025-06-30 10:56:11,724][transformers.tokenization_utils_base][INFO] - Special tokens file saved in ./results/best_model/special_tokens_map.json | |
| [2025-06-30 10:56:11,797][__main__][INFO] - Model and tokenizer saved to ./results/best_model | |
| [2025-06-30 10:56:11,815][__main__][INFO] - Fine Tuning Finished. | |
| [2025-06-30 10:56:12,324][__main__][INFO] - Total emissions: 0.5587 kg CO2eq | |